diff --git a/upstream/inoue0426-awesome-computational-biology/catalogue/.github/PULL_REQUEST_TEMPLATE.md b/upstream/inoue0426-awesome-computational-biology/catalogue/.github/PULL_REQUEST_TEMPLATE.md new file mode 100644 index 0000000..c03d526 --- /dev/null +++ b/upstream/inoue0426-awesome-computational-biology/catalogue/.github/PULL_REQUEST_TEMPLATE.md @@ -0,0 +1,28 @@ +--- +title: "Pull Request Template" +task: "" +lineage_type: import +upstream_source: https://github.com/inoue0426/awesome-computational-biology/blob/12d87583/.github/PULL_REQUEST_TEMPLATE.md +upstream_sha: 12d87583 +imported_at: 2026-06-26 +prompt_class: catalogue +upstream_changes: accepted +author: upstream +validated: false +--- + +## Description + + + +## Checklist + +- [ ] I have searched previous suggestions and this is not a duplicate. +- [ ] I have added only one link per pull request. +- [ ] The link follows the format: `[name](https://example.com/)` - A short description ends with a period. +- [ ] Descriptions are concise. +- [ ] Alphabetical ordering is maintained where applicable. +- [ ] If a new section was added, the section description and title are included, and the title is added to the Index. +- [ ] Spelling and grammar have been checked. +- [ ] There is no trailing whitespace. +- [ ] The pull request title follows the format: `Add user/repo - Short repo description` diff --git a/upstream/inoue0426-awesome-computational-biology/catalogue/.github/workflows/docs-check.yml b/upstream/inoue0426-awesome-computational-biology/catalogue/.github/workflows/docs-check.yml new file mode 100644 index 0000000..c79bfde --- /dev/null +++ b/upstream/inoue0426-awesome-computational-biology/catalogue/.github/workflows/docs-check.yml @@ -0,0 +1,46 @@ +--- +title: "Docs Check" +task: "" +lineage_type: import +upstream_source: https://github.com/inoue0426/awesome-computational-biology/blob/12d87583/.github/workflows/docs-check.yml +upstream_sha: 12d87583 +imported_at: 2026-06-26 +prompt_class: unknown +upstream_changes: accepted +author: upstream +validated: false +--- + +name: Docs / lint + +on: + push: + paths: + - '**/*.md' + pull_request: + paths: + - '**/*.md' + +permissions: + contents: read + +jobs: + docs-check: + runs-on: ubuntu-latest + steps: + - name: Checkout + uses: actions/checkout@v4 + + - name: Setup Node.js + uses: actions/setup-node@v4 + with: + node-version: 'lts/*' + + - name: Install tooling + run: npm install -g markdownlint-cli@0.33.0 cspell@6.30.1 --no-fund + + - name: Run markdownlint + run: markdownlint '**/*.md' --ignore node_modules + + - name: Run cspell (spellcheck) + run: cspell "**/*.md" --no-summary --no-progress diff --git a/upstream/inoue0426-awesome-computational-biology/catalogue/.github/workflows/generate-artifacts.yml b/upstream/inoue0426-awesome-computational-biology/catalogue/.github/workflows/generate-artifacts.yml new file mode 100644 index 0000000..ba14a5b --- /dev/null +++ b/upstream/inoue0426-awesome-computational-biology/catalogue/.github/workflows/generate-artifacts.yml @@ -0,0 +1,55 @@ +--- +title: "Generate Artifacts" +task: "" +lineage_type: import +upstream_source: https://github.com/inoue0426/awesome-computational-biology/blob/12d87583/.github/workflows/generate-artifacts.yml +upstream_sha: 12d87583 +imported_at: 2026-06-26 +prompt_class: unknown +upstream_changes: accepted +author: upstream +validated: false +--- + +name: Generate data artifacts + +on: + push: + paths: + - 'data/resources.yml' + pull_request: + paths: + - 'data/resources.yml' + workflow_dispatch: + +jobs: + generate: + runs-on: ubuntu-latest + permissions: + contents: write + + steps: + - name: Checkout + uses: actions/checkout@v4 + with: + ref: ${{ github.head_ref || github.ref_name }} + + - name: Set up Python + uses: actions/setup-python@v5 + with: + python-version: '3.11' + + - name: Install dependencies + run: pip install pyyaml + + - name: Generate JSON and CSV + run: python scripts/generate_artifacts.py + + - name: Commit artifacts (push events only) + if: github.event_name == 'push' || github.event_name == 'workflow_dispatch' + run: | + git config user.name "github-actions[bot]" + git config user.email "github-actions[bot]@users.noreply.github.com" + git add data/resources.json data/resources.csv docs/data/resources.json + git diff --cached --quiet || git commit -m "chore: regenerate resources.json and resources.csv" + git push diff --git a/upstream/inoue0426-awesome-computational-biology/catalogue/.github/workflows/link-check.yml b/upstream/inoue0426-awesome-computational-biology/catalogue/.github/workflows/link-check.yml new file mode 100644 index 0000000..f465a0a --- /dev/null +++ b/upstream/inoue0426-awesome-computational-biology/catalogue/.github/workflows/link-check.yml @@ -0,0 +1,42 @@ +--- +title: "Link Check" +task: "" +lineage_type: import +upstream_source: https://github.com/inoue0426/awesome-computational-biology/blob/12d87583/.github/workflows/link-check.yml +upstream_sha: 12d87583 +imported_at: 2026-06-26 +prompt_class: unknown +upstream_changes: accepted +author: upstream +validated: false +--- + +name: Link Check + +on: + schedule: + - cron: '0 5 * * 1' # 毎週月曜 05:00 UTC + workflow_dispatch: # 手動実行も可能 + +permissions: + contents: read + +jobs: + link-check: + runs-on: ubuntu-latest + steps: + - name: Checkout + uses: actions/checkout@v4 + + - name: Setup Node.js + uses: actions/setup-node@v4 + with: + node-version: 'lts/*' + + - name: Install markdown-link-check + run: npm install -g markdown-link-check@3.12.2 --no-fund + + - name: Run markdown-link-check + run: | + find . -name '*.md' -not -path './node_modules/*' -print0 | \ + xargs -0 -I{} markdown-link-check {} -q -c .markdown-link-check.json diff --git a/upstream/inoue0426-awesome-computational-biology/catalogue/.github/workflows/pr-quality-checks.yml b/upstream/inoue0426-awesome-computational-biology/catalogue/.github/workflows/pr-quality-checks.yml new file mode 100644 index 0000000..38e8d66 --- /dev/null +++ b/upstream/inoue0426-awesome-computational-biology/catalogue/.github/workflows/pr-quality-checks.yml @@ -0,0 +1,56 @@ +--- +title: "Pr Quality Checks" +task: "" +lineage_type: import +upstream_source: https://github.com/inoue0426/awesome-computational-biology/blob/12d87583/.github/workflows/pr-quality-checks.yml +upstream_sha: 12d87583 +imported_at: 2026-06-26 +prompt_class: unknown +upstream_changes: accepted +author: upstream +validated: false +--- + +name: PR Quality Checks + +on: + pull_request: + paths: + - README.md + - data/resources.yml + - data/resources.json + - data/resources.csv + - docs/data/resources.json + - scripts/*.py + - scripts/**/*.py + +permissions: + contents: read + +jobs: + resources-consistency: + runs-on: ubuntu-latest + steps: + - name: Checkout + uses: actions/checkout@v4 + + - name: Setup uv + uses: astral-sh/setup-uv@v3 + + - name: Sync resources from README + run: uv run --with pyyaml python scripts/sync_resources_from_readme.py + + - name: Build resource artifacts + run: uv run --with pyyaml python scripts/build_resources.py + + - name: Verify generated artifacts are committed + run: | + if git diff --quiet; then + echo "Resources are in sync." + exit 0 + fi + echo "Generated files are out of date. Run:" + echo " uv run --with pyyaml python scripts/sync_resources_from_readme.py" + echo " uv run --with pyyaml python scripts/build_resources.py" + git status --short + exit 1 diff --git a/upstream/inoue0426-awesome-computational-biology/catalogue/.github/workflows/sync_resources.yml b/upstream/inoue0426-awesome-computational-biology/catalogue/.github/workflows/sync_resources.yml new file mode 100644 index 0000000..5a871be --- /dev/null +++ b/upstream/inoue0426-awesome-computational-biology/catalogue/.github/workflows/sync_resources.yml @@ -0,0 +1,73 @@ +--- +title: "Sync Resources" +task: "" +lineage_type: import +upstream_source: https://github.com/inoue0426/awesome-computational-biology/blob/12d87583/.github/workflows/sync_resources.yml +upstream_sha: 12d87583 +imported_at: 2026-06-26 +prompt_class: unknown +upstream_changes: accepted +author: upstream +validated: false +--- + +name: Sync Resources + +on: + push: + branches: + - main + paths: + - README.md + - data/resources.yml + - scripts/*.py + - scripts/**/*.py + +permissions: + contents: write + +jobs: + sync: + if: github.actor != 'github-actions[bot]' + runs-on: ubuntu-latest + steps: + - name: Checkout + uses: actions/checkout@v4 + with: + fetch-depth: 0 + + - name: Setup uv + uses: astral-sh/setup-uv@v3 + + - name: Detect Changed Files + id: changes + run: | + BEFORE="${{ github.event.before }}" + AFTER="${{ github.sha }}" + if [ -z "$BEFORE" ] || [ "$BEFORE" = "0000000000000000000000000000000000000000" ]; then + CHANGED=$(git diff --name-only HEAD~1..HEAD) + else + CHANGED=$(git diff --name-only "$BEFORE" "$AFTER") + fi + echo "changed<> "$GITHUB_OUTPUT" + echo "$CHANGED" >> "$GITHUB_OUTPUT" + echo "EOF" >> "$GITHUB_OUTPUT" + + - name: Sync From README + if: contains(steps.changes.outputs.changed, 'README.md') + run: uv run python scripts/sync_resources_from_readme.py + + - name: Build Artifacts + run: uv run --with pyyaml python scripts/build_resources.py + + - name: Commit Updates + run: | + if git diff --quiet; then + echo "No changes to commit." + exit 0 + fi + git config user.name "github-actions[bot]" + git config user.email "41898282+github-actions[bot]@users.noreply.github.com" + git add data/resources.yml data/resources.json data/resources.csv docs/data/resources.json + git commit -m "chore: sync resources" + git push diff --git a/upstream/inoue0426-awesome-computational-biology/catalogue/.github/workflows/update-overview.yml b/upstream/inoue0426-awesome-computational-biology/catalogue/.github/workflows/update-overview.yml new file mode 100644 index 0000000..3c965e7 --- /dev/null +++ b/upstream/inoue0426-awesome-computational-biology/catalogue/.github/workflows/update-overview.yml @@ -0,0 +1,58 @@ +--- +title: "Update Overview" +task: "" +lineage_type: import +upstream_source: https://github.com/inoue0426/awesome-computational-biology/blob/12d87583/.github/workflows/update-overview.yml +upstream_sha: 12d87583 +imported_at: 2026-06-26 +prompt_class: unknown +upstream_changes: accepted +author: upstream +validated: false +--- + +name: Update Overview Figure + +on: + push: + branches: + - main + paths: + - docs/data/resources.json + schedule: + # Every Monday at 03:00 UTC + - cron: '0 3 * * 1' + workflow_dispatch: + +permissions: + contents: write + +jobs: + update-overview: + runs-on: ubuntu-latest + + steps: + - name: Checkout + uses: actions/checkout@v4 + with: + # Use the default GITHUB_TOKEN so commits don't re-trigger this workflow + token: ${{ secrets.GITHUB_TOKEN }} + + - name: Set up Python + uses: actions/setup-python@v5 + with: + python-version: '3.11' + + - name: Install dependencies + run: pip install matplotlib + + - name: Regenerate overview figure + run: python scripts/generate_overview.py + + - name: Commit updated overview + run: | + git config user.name "github-actions[bot]" + git config user.email "41898282+github-actions[bot]@users.noreply.github.com" + git add docs/overview.png + git diff --cached --quiet || git commit -m "chore: regenerate overview figure" + git push diff --git a/upstream/inoue0426-awesome-computational-biology/catalogue/.markdown-link-check.json b/upstream/inoue0426-awesome-computational-biology/catalogue/.markdown-link-check.json new file mode 100644 index 0000000..a8efe60 --- /dev/null +++ b/upstream/inoue0426-awesome-computational-biology/catalogue/.markdown-link-check.json @@ -0,0 +1,16 @@ +--- +title: ".Markdown Link Check" +task: "" +lineage_type: import +upstream_source: https://github.com/inoue0426/awesome-computational-biology/blob/12d87583/.markdown-link-check.json +upstream_sha: 12d87583 +imported_at: 2026-06-26 +prompt_class: catalogue +upstream_changes: accepted +author: upstream +validated: false +--- + +{ +"aliveStatusCodes": [200, 206, 301, 302, 307, 308, 403] +} diff --git a/upstream/inoue0426-awesome-computational-biology/catalogue/README.md b/upstream/inoue0426-awesome-computational-biology/catalogue/README.md new file mode 100644 index 0000000..42bfd3d --- /dev/null +++ b/upstream/inoue0426-awesome-computational-biology/catalogue/README.md @@ -0,0 +1,533 @@ +--- +title: "Awesome Computational Biology [![Awesome](https://awesome.re/badge.svg)](https://awesome.re)" +task: "" +lineage_type: import +upstream_source: https://github.com/inoue0426/awesome-computational-biology/blob/12d87583/README.md +upstream_sha: 12d87583 +imported_at: 2026-06-26 +prompt_class: catalogue +upstream_changes: accepted +author: upstream +validated: false +--- + +# Awesome Computational Biology [![Awesome](https://awesome.re/badge.svg)](https://awesome.re) + +A curated collection of databases, software, and papers related to computational biology. + +> Computational biology involves the development and application of data-analytical and theoretical methods, mathematical modelling and computational simulation techniques to the study of biological, ecological, behavioural, and social systems. — [Wikipedia](https://en.wikipedia.org/wiki/Computational_biology) + +--- + +## Overview + +[![Resource Landscape Overview](docs/overview.png)](https://inoue0426.github.io/awesome-computational-biology/overview.html) + +> Interactive version: [Resource Overview page](https://inoue0426.github.io/awesome-computational-biology/overview.html) +> Regenerate the figure: `python scripts/generate_overview.py` + +--- + +## GitHub Pages UI + +Browse and search the resources via the [GitHub Pages UI](https://inoue0426.github.io/awesome-computational-biology/). + +- Search matches `name`, `description`, `tasks`, `modalities`, and `tags`. +- The **Task**, **Modality**, and **Type** filters map directly to `tasks`, `modalities`, and `type` in `docs/data/resources.json`. +- Clicking badges on cards applies the corresponding filter. + +--- + +## Table of Contents + +- [Awesome Computational Biology](#awesome-computational-biology-) + - [Table of Contents](#table-of-contents) + - [Overview](#overview) + - [GitHub Pages UI](#github-pages-ui) + - [Citation](#citation) + - [Curation Criteria (Strict)](#curation-criteria-strict) + - [Update & Link Rot Policy](#update--link-rot-policy) + - [Data Schema & Contribution Workflow](#data-schema--contribution-workflow) + - [Databases](#databases) + - [scRNA](#scrna) + - [Compound](#compound) + - [Pathway](#pathway) + - [Mass Spectra](#mass-spectra) + - [Protein](#protein) + - [Genome](#genome) + - [Disease](#disease) + - [Interaction](#interaction) + - [Drug-Gene Interaction](#drug-gene-interaction) + - [Drug (Cell Line) Response](#drug-cell-line-response) + - [Chemical-Protein Interaction](#chemical-protein-interaction) + - [Protein-Protein Interaction](#protein-protein-interaction) + - [Knowledge Graph](#knowledge-graph) + - [Gene Regulatory Network](#gene-regulatory-network) + - [Clinical Trial](#clinical-trial) + - [Benchmarks & Datasets](#benchmarks--datasets) + - [API](#api) + - [Preprocessing Tools](#preprocessing-tools) + - [Machine Learning Tasks and Models](#machine-learning-tasks-and-models) + - [Drug Discovery](#drug-discovery) + - [Drug Response Prediction](#drug-response-prediction) + - [Drug Repurposing](#drug-repurposing) + - [Drug Target Interaction](#drug-target-interaction) + - [Compound-Protein Interaction](#compound-protein-interaction) + - [Molecular Generation](#molecular-generation) + - [LLM for Biology](#llm-for-biology) + - [Foundation Models](#foundation-models) + - [Single-cell Foundation Models](#single-cell-foundation-models) + - [Transcriptomics Foundation Models](#transcriptomics-foundation-models) + - [Spatial Foundation Models](#spatial-foundation-models) + - [Multi-Omics Foundation Models](#multi-omics-foundation-models) + - [Domain Alignment](#domain-alignment) + - [Compound Foundation Models](#compound-foundation-models) + - [Compound Embedding](#compound-embedding) + - [Protein Foundation Models](#protein-foundation-models) + - [Pre-trained Embedding](#pre-trained-embedding) + - [Protein Structure Prediction and Design](#protein-structure-prediction-and-design) + - [Multi-Modal Foundation Models](#multi-modal-foundation-models) + - [Genomics Foundation Models](#genomics-foundation-models) + +--- + +## Databases + +### scRNA + +- [CZ CELLxGENE](https://cellxgene.cziscience.com/) — Single-cell dataset repository and interactive explorer from the Chan Zuckerberg Initiative. +- [Gene Expression Omnibus](https://www.ncbi.nlm.nih.gov/geo/) — Public functional genomics database. +- [Human Cell Atlas](https://www.humancellatlas.org/) — Open global atlas of all cells in the human body. +- [Single Cell PORTAL](https://singlecell.broadinstitute.org/single_cell) — Public database for single-cell RNA. +- [Single Cell Expression Atlas](https://www.ebi.ac.uk/gxa/sc/home) — Public database for single-cell RNA. + +### Compound + +- [PubChem](https://pubchem.ncbi.nlm.nih.gov/) — One of the largest chemical databases (compounds, genes, and proteins). +- [ChEBI](https://www.ebi.ac.uk/chebi/) — Database focused on small chemical compounds. +- [ChEMBL](https://www.ebi.ac.uk/chembl/) — Bioactive molecules with drug-like properties. +- [ChemSpider](http://www.chemspider.com/) — Chemical structure database. +- [DrugTargetCommons](https://drugtargetcommons.fimm.fi/) — Community platform for curating and integrating experimental bioactivity data across drugs and targets. +- [HMDB (Human Metabolome Database)](https://hmdb.ca/) — Comprehensive database of small molecule metabolites found in the human body. +- [KEGG COMPOUND](https://www.genome.jp/kegg/compound/) — Collection of small molecules and biopolymers. +- [LIPID MAPS](https://www.lipidmaps.org/databases/lmsd/overview) — Database of lipids. +- [Rhea](https://www.rhea-db.org/) — Database of chemical reactions. +- [DrugCentral](http://drugcentral.org/) — Online drug compendium with drug mode of action and indication information. +- [Drug Repurposing Hub](https://repo-hub.broadinstitute.org/repurposing#download-data) — Collections of drug repurposing data (drug, MoA, target, etc). +- [Therapeutic Target Database](https://idrblab.net/ttd/full-data-download) — Drug-target, target-disease, and drug-disease datasets. +- [ZINC ligand discovery database](https://zinc.docking.org/) — Free database of commercially-available compounds for virtual screening. + +### Pathway + +- [PathwayCommons](https://www.pathwaycommons.org/) — Database of pathways and interactions. +- [KEGG PATHWAY](https://www.genome.jp/kegg/pathway.html) — Collection of pathway maps. +- [WikiPathways](https://wikipathways.org/) — Database of biological pathways. +- [Reactome](https://reactome.org/) — Expert-curated, peer-reviewed pathway database with detailed reaction mechanisms. +- [BioCyc](https://biocyc.org/) — Collection of pathway/genome databases across thousands of organisms. +- [OmniPath](https://omnipathdb.org/) — Comprehensive resource integrating protein interactions, signaling pathways, gene regulatory networks, and miRNA targets from over 100 databases. +- [SIGNOR 2.0](https://signor.uniroma2.it/) — Database of causal signaling interactions and pathways, with signed and directed relationships between proteins. +- [MSigDB (Molecular Signatures Database)](https://www.gsea-msigdb.org/gsea/msigdb) — Curated gene sets derived from pathways and biological processes. + +### Mass Spectra + +- [MassBank](http://www.massbank.jp/) — Open source databases and tools for mass spectrometry reference spectra. +- [MoNA MassBank of North America](https://mona.fiehnlab.ucdavis.edu/) — Meta-database of metabolite mass spectra, metadata, and associated compounds. + +### Protein + +- [THE HUMAN PROTEIN ATLAS](https://www.proteinatlas.org/) — Comprehensive human protein database (cells, tissues, organs). +- [PROTEIN DATA BANK (PDB)](https://www.rcsb.org/) — 3D structures of proteins, nucleic acids, complexes. +- [UniProt](https://www.uniprot.org/) — Functional information on proteins. +- [AlphaFold Protein Structure Database](https://alphafold.ebi.ac.uk/api-docs) — 3D protein structure predictions. +- [RCSB Protein Data Bank](https://www.rcsb.org/) — Repository for structural data of biological molecules. +- [Critical Assessment of Structure Prediction (CASP)](https://predictioncenter.org/) — Assessing methods for protein structure prediction. +- [Uniclust](https://uniclust.mmseqs.com/) — Clustered protein sequence databases. +- [UniRef](https://www.uniprot.org/uniref/) — Non-redundant sequence database clustering UniProtKB entries at multiple sequence identity thresholds. +- [CATH database](https://www.cathdb.info/) — Hierarchical classification of protein domain structures. +- [SAbDab](https://opig.stats.ox.ac.uk/webapps/sabdab-sabpred/sabdab) — Structural Antibody Database containing all antibody structures in the PDB. +- [OADB (Observed Antibody Space Database)](http://opig.stats.ox.ac.uk/webapps/oas/) — Database of antibody sequences from immune repertoire sequencing. +- [InterPro](https://www.ebi.ac.uk/interpro/) — Protein families, domains, and functional sites database integrating 14 member databases including Pfam and PROSITE. +- [Pfam](https://www.ebi.ac.uk/interpro/entry/pfam/) — Database of protein families described by multiple sequence alignments and hidden Markov models. +- [NeXtProt](https://www.nextprot.org/) — Expert knowledge base on human proteins with deep functional annotation, complementary to UniProt. + +### Genome + +- [ENCODE](https://www.encodeproject.org/) — Encyclopedia of DNA Elements; regulatory and functional genomic elements across the genome. +- [Ensembl](https://www.ensembl.org/) — Genome browser and annotation database for vertebrate and other eukaryotic genomes. +- [Human Genome Resources at NCBI](https://www.ncbi.nlm.nih.gov/projects/genome/guide/human/index.shtml) — Database for genomics, proteomics, transcriptomics, and systems biology. +- [GenBank](https://www.ncbi.nlm.nih.gov/genbank/) — NCBI's database of genetic sequences. +- [UCSC Genome Browser](https://genome.ucsc.edu/) — UCSC's genome browser. +- [cBioPortal](https://www.cbioportal.org/) — Cancer genomics database; aggregating many patient datasets. +- [10x Genomics Dataset](https://www.10xgenomics.com/resources/datasets) — Collection of single-cell datasets. +- [The Genotype-Tissue Expression (GTEx)](https://gtexportal.org/home/) — Human gene expression and regulation resource. +- [Dependency Map (DepMap)](https://depmap.org/portal/) — CRISPR-Cas9 screens in cancer cell lines. +- [Catalogue Of Somatic Mutations In Cancer (COSMIC)](https://cancer.sanger.ac.uk/cosmic) — Resource on somatic mutations in cancers. +- [MGnify](https://www.ebi.ac.uk/metagenomics/) — Resource for metagenomic and metatranscriptomic data. +- [JASPAR](http://jaspar.genereg.net/) — Database of transcription factor binding profiles. +- [gnomAD](https://gnomad.broadinstitute.org/) — Genome Aggregation Database; genetic variation from large-scale sequencing projects. +- [Rfam](https://rfam.org/) — Database of RNA families with sequence alignments and consensus structures. +- [ROADMAP Epigenomics](http://www.roadmapepigenomics.org/) — Reference epigenome maps for 111 primary human cell types and tissues, including histone modifications, chromatin accessibility, and DNA methylation. +- [FANTOM5](https://fantom.gsc.riken.jp/5/) — Functional annotation of mammalian genome; comprehensive atlas of active enhancers, promoters, and transcription start sites across human and mouse cell types. + +### Disease + +- [KEGG DRUG](https://www.genome.jp/kegg/drug/) — Comprehensive, approved drug information. +- [DrugBank](https://go.drugbank.com/) — Database of drugs and targets (University of Alberta). +- [DisGeNET](https://www.disgenet.org/) — Database of gene-disease associations integrating expert-curated and GWAS data. +- [OMIM (Online Mendelian Inheritance in Man)](https://www.omim.org/) — Comprehensive database of human genes and genetic disorders. +- [Open Targets Platform](https://platform.opentargets.org/) — Systematic target identification and prioritization platform integrating genetics, genomics, and drug data for drug discovery. +- [Human Phenotype Ontology (HPO)](https://hpo.jax.org/) — Standardized vocabulary of phenotypic abnormalities in human disease, linking genes, variants, and clinical features. +- [DISEASES](https://diseases.jensenlab.org/) — Gene–disease association database integrating evidence from text mining, curated databases, and experimental data. + +### Interaction + +#### Drug-Gene Interaction + +- [DGIdb](https://www.dgidb.org/) — Drug-gene interactions and the druggable genome. +- [Comparative Toxicogenomics Database](http://ctdbase.org/) — Chemical-gene interactions, chemical-disease and gene-disease associations, chemical-phenotype associations. +- [SNAP](https://snap.stanford.edu/biodata/datasets/10002/10002-ChG-Miner.html) — Dataset of drug-gene interactions. + +#### Drug (Cell Line) Response + +- [NCI60](https://dtp.cancer.gov/discovery_development/nci-60/) — Focuses on 60 cancer cell lines and many drugs. +- [Genomics of Drug Sensitivity in Cancer (GDSC)](https://www.cancerrxgene.org/) — Drug sensitivity for ~1000 human cancer cell lines and hundreds of compounds. +- [Cancer Cell Line Encyclopedia](https://sites.broadinstitute.org/ccle/) — Database of ~1000 cancer cell lines. +- [CellMiner Cross Database (CellMinerCDB)](https://discover.nci.nih.gov/cellminercdb/) — Integrates multiple cancer cell line databases. + +#### Chemical-Protein Interaction + +- [STITCH](http://stitch.embl.de/) — Chemical-protein interactions. +- [BindingDB](https://www.bindingdb.org/rwd/bind/index.jsp) — Compounds and target database. +- [Davis kinase inhibitors DB](http://staff.cs.utu.fi/~aijrinas/dti/) — Experimental kinase inhibitor binding affinity dataset for protein–ligand interaction research. +- [Kinase Inhibitor Bioactivity Data (KIBA)](https://janeliascicomp.github.io/KIBA/) — Integrated bioactivity scores for kinase inhibitors combining Ki, Kd, and IC50 measurements. +- [PDBBind](https://www.pdbbind-plus.org.cn/) — Binding affinity data for biomolecular complexes. + +#### Protein-Protein Interaction + +- [STRING](https://string-db.org/) — PPI networks for multiple organisms. +- [BioGRID](https://thebiogrid.org/) — Protein, genetic, and chemical interactions. +- [HIPPIE](http://cbdm-01.zdv.uni-mainz.de/~mschaefer/hippie/) — Human protein-protein interaction database. +- [IntAct](https://www.ebi.ac.uk/intact/home) — Open-source molecular interaction database and analysis system from EMBL-EBI. + +#### Knowledge Graph + +- [Drug Mechanism Database (DrugMechDB)](https://github.com/SuLab/DrugMechDB/tree/2.0.1) — Mechanisms of action from drug to disease. +- [DRKG](https://github.com/gnn4dr/DRKG) — Large-scale biological knowledge graph for drug discovery. +- [Hetionet](https://github.com/hetio/hetionet) — Heterogeneous network integrating genes, diseases, drugs, pathways, and more. +- [PrimeKG](https://github.com/mims-harvard/PrimeKG) — Multi-modal precision medicine knowledge graph integrating clinical, genetic, and drug data. + +#### Gene Regulatory Network + +- [TRRUST v2](https://www.grnpedia.org/trrust/) — Manually curated database of human and mouse transcriptional regulatory interactions between transcription factors and their target genes, expanded with literature-derived evidence. +- [RegNetwork](http://www.regnetworkweb.org/) — Database of gene regulatory networks covering transcription factor–target gene and miRNA–gene interaction data across multiple species. +- [miRBase](https://www.mirbase.org/) — Reference repository for microRNA gene annotations, sequences, and experimentally validated targets. + +### Clinical Trial + +- [ClinicalTrials.gov](https://clinicaltrials.gov/) — Privately and publicly funded clinical studies. +- [ICD10](https://icd.who.int/browse10/2019/en) — International Classification of Diseases, 10th revision. +- [EU Drug Regulating Authorities Clinical Trials DB (EudraCT)](https://eudract.ema.europa.eu/) — European clinical trial database. +- [MIMIC-IV](https://mimic.mit.edu/) — Freely accessible critical care database. + +--- + +## Benchmarks & Datasets + +- [1000 Genomes Project](https://www.internationalgenome.org/) — Reference panel of human genetic variation from 2,504 individuals across 26 populations. +- [BACE](https://www.kaggle.com/datasets/gokturkkoch/bace) — Binary classification and regression dataset for β-secretase 1 (BACE-1) inhibitor binding affinity. +- [BEAT AML](https://biodev.github.io/BeatAML2/) — Functional ex vivo drug sensitivity measurements paired with genomics for acute myeloid leukemia. +- [Bento](https://github.com/LigandPro/Bento) — Protein-ligand docking benchmark covering rigid, flexible, de novo, blind, induced-fit, and covalent docking tasks. +- [BindingDB Curated Sets](https://www.bindingdb.org/rwd/bind/chemsearch/marvin/SDFdownload.jsp?all_download=yes) — Curated binding affinity datasets for protein–ligand interaction benchmarking. +- [Cancer Therapeutics Response Portal (CTRP)](https://portals.broadinstitute.org/ctrp/) — Drug sensitivity profiles across ~900 cancer cell lines for >400 compounds. +- [ClinTox](https://tdcommons.ai/single_pred_tasks/tox/#clintox) — Clinical toxicity dataset contrasting FDA-approved drugs with those that failed clinical trials due to toxicity. +- [CPTAC (Clinical Proteomic Tumor Analysis Consortium)](https://proteomics.cancer.gov/programs/cptac) — Multi-omic proteogenomic datasets for multiple cancer types linking proteomics with genomics. +- [CrossDocked2020](https://arxiv.org/abs/2001.01037) — Large-scale dataset for structure-based virtual screening. +- [DUD-E (Directory of Useful Decoys, Enhanced)](http://dude.docking.org/) — Structure-based virtual screening benchmark with active ligands and challenging decoy sets across diverse protein targets. +- [FLIP (Fitness Landscape Inference for Proteins)](https://github.com/J-SNACKKB/FLIP) — Benchmark collection of protein fitness landscape datasets for evaluating protein ML models. +- [Genomics of Drug Sensitivity in Cancer (GDSC)](https://www.cancerrxgene.org/) — Drug sensitivity for ~1000 human cancer cell lines and hundreds of compounds. +- [GuacaMol](https://github.com/BenevolentAI/guacamol) — Benchmark suite for generative molecular design models. +- [JUMP Cell Painting Datasets](https://github.com/jump-cellpainting/datasets) — Consortium-scale cell imaging perturbation datasets (chemical and genetic) for phenotypic profiling and drug discovery research. +- [LINCS L1000](https://lincsproject.org/LINCS/tools/workflows/find-the-best-place-to-obtain-the-lincs-l1000-data) — Gene expression profiles (978 landmark genes) for >20,000 chemical and genetic perturbations across cell lines. +- [MoleculeNet](http://moleculenet.ai/) — Benchmark datasets for molecular machine learning. +- [MOSES](https://github.com/molecularsets/moses) — Benchmarking platform for molecular generation models. +- [NCI60](https://dtp.cancer.gov/discovery_development/nci-60/) — Drug sensitivity benchmark across 60 diverse human cancer cell lines. +- [OGB (Open Graph Benchmark)](https://ogb.stanford.edu/) — Large-scale graph ML benchmark suite including biological datasets such as ogbl-ppa (protein-protein associations) and ogbg-molhiv. +- [OpenBioLink](https://github.com/OpenBioLink/OpenBioLink) — Benchmark datasets for biological knowledge graph completion. +- [PharmGKB](https://www.pharmgkb.org/) — Curated pharmacogenomics dataset linking genetic variants to drug response phenotypes across thousands of drugs. +- [PK-DB](https://pk-db.com/) — Open database of experimental pharmacokinetics (PK) and ADME data from clinical and preclinical studies. +- [PRISM](https://depmap.org/portal/prism/) — Cancer drug sensitivity profiling of >4,500 drugs across >900 cancer cell lines using pooled-cell-line barcoding. +- [ProteinGym](https://github.com/OATML-Markslab/ProteinGym) — Large-scale benchmark of deep mutational scanning assays for evaluating protein fitness landscape models. +- [QM9](https://figshare.com/collections/Quantum_chemistry_structures_and_properties_of_134_kilo_molecules/978904) — Quantum chemistry properties for 134K stable small organic molecules computed at DFT level. +- [scIB (Single-cell Integration Benchmarks)](https://github.com/theislab/scib) — Comprehensive benchmarking framework for single-cell data integration methods. +- [scPerturb](https://github.com/sanderlab/scPerturb) — Curated and continuously updated single-cell perturbation data resource spanning CRISPR and drug perturbation studies. +- [SIDER (Side Effect Resource)](http://sideeffects.embl.de/) — Database of 1,430 approved drugs with their recorded adverse drug reactions across 27 system-organ classes. +- [Tabula Muris](https://tabula-muris.ds.czbiohub.org/) — Comprehensive single-cell atlas of 20 mouse organs and tissues, enabling cross-tissue and cross-species comparisons. +- [Tabula Sapiens](https://tabula-sapiens-portal.ds.czbiohub.org/) — Comprehensive human single-cell atlas of ~500K cells from 24 organs and tissues across multiple donors. +- [TAPE (Tasks Assessing Protein Embeddings)](https://github.com/songlab-cal/tape) — Benchmark suite of five biologically meaningful semi-supervised learning tasks for evaluating protein representations. +- [The Cancer Genome Atlas (TCGA)](https://www.cancer.gov/about-nci/organization/ccg/research/structural-genomics/tcga) — Comprehensive multi-omics (genomics, transcriptomics, proteomics, methylation) dataset for 33 cancer types across ~11,000 patients. +- [Therapeutics Data Commons (TDC)](https://tdcommons.ai/) — Unified benchmark suite covering ADMET, drug-target interaction, drug response, and more. +- [Tox21](https://tripod.nih.gov/tox21/challenge/) — 12,707 compounds tested in 12 nuclear receptor and stress-response pathway biochemical assays for toxicity prediction. +- [UK Biobank](https://www.ukbiobank.ac.uk/) — Large-scale biomedical database of ~500K participants with genetic, imaging, and health data for population genetics and disease studies. + +--- + +## API + +- [PubMed E-utilities (esearch/efetch)](https://www.nlm.nih.gov/dataguide/edirect/esearch.html) — APIs for searching and retrieving biomedical literature from PubMed. +- [NCBI E-utilities](https://www.ncbi.nlm.nih.gov/books/NBK25501/) — Unified APIs for accessing NCBI databases (Gene, GEO, SRA, PubChem, etc). +- [UniProt REST API](https://www.uniprot.org/help/api) — Programmatic access to protein sequence and functional annotation data. +- [Ensembl REST API](https://rest.ensembl.org/) — API for genomic annotations, variants, genes, and comparative genomics. +- [KEGG REST API](https://www.kegg.jp/kegg/rest/keggapi.html) — API for accessing KEGG pathways, compounds, genes, and reactions. +- [ChEMBL Web Services](https://www.ebi.ac.uk/chembl/ws) — REST API for bioactive molecules, targets, and bioassays. +- [Open Targets Platform API](https://platform.opentargets.org/api) — API for target–disease associations integrating genetics, genomics, and drug data. +- [ClinicalTrials.gov API](https://clinicaltrials.gov/api/gui) — API for querying clinical trial metadata and results. + +--- + +## Preprocessing Tools + +- [Chemistry Development Kit](https://github.com/cdk/cdk) — Cheminformatics software & machine learning tools. +- [Biopython](https://biopython.org/) — Collection of Python tools for biological computation including sequence analysis, structure parsing, and database access. +- [FlashDeconv](https://github.com/cafferychen777/flashdeconv) — High-performance spatial transcriptomics deconvolution (~1M spots in ~3 min). +- [RDKit](https://github.com/rdkit/rdkit) — Cheminformatics software & machine learning toolkit. +- [DeepChem](https://github.com/deepchem/deepchem) — Deep learning library for drug discovery, quantum chemistry, and materials science. +- [ChatSpatial](https://github.com/cafferychen777/ChatSpatial) — MCP server for spatial transcriptomics analysis via natural language. +- [Scanpy](https://scanpy.readthedocs.io/en/stable/) — Python library for scRNA-seq analysis. +- [Seurat](https://satijalab.org/seurat/) — R library for scRNA-seq analysis. +- [scvi-tools](https://scvi-tools.org/) — Probabilistic models for single-cell omics data analysis. +- [CellTypist](https://github.com/Teichlab/celltypist) — Automated cell type annotation for scRNA-seq. +- [Squidpy](https://squidpy.readthedocs.io/) — Python library for spatial single-cell analysis. +- [GROMACS](https://www.gromacs.org/) — Molecular dynamics simulation package for biochemical molecules. +- [MDAnalysis](https://www.mdanalysis.org/) — Python library for analyzing and altering molecular dynamics simulation trajectories. +- [OpenMM](https://openmm.org/) — High-performance toolkit for molecular simulation and GPU-accelerated MD. +- [scVelo](https://github.com/theislab/scvelo) — RNA velocity estimation for single-cell transcriptomics, inferring the direction and speed of cell differentiation. +- [STAR](https://github.com/alexdobin/STAR) — Ultrafast universal RNA-seq aligner with support for spliced alignment and single-cell quantification via STARsolo. +- [kallisto](https://pachterlab.github.io/kallisto/) — Near-optimal RNA-seq quantification using pseudoalignment for fast transcript abundance estimation. +- [Harmony](https://github.com/immunogenomics/harmony) — Fast and scalable integration of single-cell data across datasets, conditions, technologies, and species. +- [Monocle3](https://cole-trapnell-lab.github.io/monocle3/) — Single-cell trajectory analysis tool for learning developmental trajectories and ordering cells in pseudotime. +- [CellChat](https://github.com/sqjin/CellChat) — Inference and analysis of cell-cell communication ligand-receptor networks from single-cell transcriptomics data. +- [SCENIC](https://github.com/aertslab/SCENIC) — Single-cell regulatory network inference and clustering linking transcription factors to co-expressed gene modules. +- [DoubletFinder](https://github.com/chris-mcginnis-ucsf/DoubletFinder) — Machine learning approach for detecting multiplet (doublet) artifacts in single-cell RNA-seq data. +- [Numbat](https://github.com/kharchenkolab/numbat) — Haplotype-aware copy number variation inference from single-cell RNA-seq using hidden Markov models. +- [CaSpER](https://github.com/akdess/CaSpER) — CNV identification and visualization by integrative analysis of single-cell or bulk RNA-seq data. +- [CellCharter](https://github.com/CSOgroup/cellcharter) — Identification and characterization of spatial cell niches from spatial transcriptomics using VAEs and Gaussian mixture models. +- [STAGATE](https://github.com/RucDongLab/STAGATE) — Adaptive graph attention auto-encoder for spatial domain identification in spatial transcriptomics. +- [NCEM](https://github.com/theislab/ncem) — GNN-based model for learning intercellular communication from spatial graphs of cells. +- [DeepTalk](https://github.com/JiangBioLab/DeepTalk) — Graph attention network for deciphering cell-cell communication from spatial transcriptomics data. +- [COMMOT](https://github.com/zcang/COMMOT) — Optimal transport-based framework for screening cell-cell communication in spatial transcriptomics. +- [TIGON](https://github.com/yutongo/TIGON) — Neural optimal transport method for reconstructing growth and dynamic trajectories from single-cell transcriptomics. +- [LINGER](https://github.com/Durenlab/LINGER) — Neural network for gene regulatory network inference from single-cell multiome (RNA+ATAC-seq) data with bulk data pretraining. +- [sciPENN](https://github.com/jlakkis/sciPENN) — RNN-based method for simultaneous protein expression prediction, uncertainty estimation, and cell-type label transfer from CITE-seq and scRNA-seq data. +- [MOGONET](https://github.com/txWang/MOGONET) — Multi-omics graph convolutional network framework for patient classification and biomarker identification. +- [AutoZyme](https://github.com/ElliotXie/autozyme) — Autonomous agentic framework that speeds up bioinformatics software (e.g. Scanpy, Seurat) on CPUs while preserving the original results. + +--- + +## Machine Learning Tasks and Models + +### Drug Discovery + +#### Drug Response Prediction + +- [drGAT](https://github.com/inoue0426/drGAT) — Attention-based model for drug response prediction with gene explainability. +- [MOFGCN](https://github.com/weiba/MOFGCN/tree/main) — GCN + heterogeneous network. +- [DeepDSC](https://ieeexplore-ieee-org.ezp2.lib.umn.edu/stamp/stamp.jsp?tp=&arnumber=8723620&tag=1) — Autoencoder + fully connected NN. +- [DGDRP](https://github.com/minwoopak/heteronet) — Multi-view embedding neural network. +- [DeepAEG](https://github.com/zhejiangzhuque/DeepAEG) — GNN embedding + attention mechanism. +- [RECOVER](https://github.com/RECOVERcoalition/Recover) — Machine learning framework for predicting synergistic drug combination responses across cell lines. +- [TGSA](https://github.com/violet-sto/TGSA) — Tumor gene set and attention-based model leveraging biological pathway knowledge for drug response prediction. +- [HiDRA](https://github.com/bsml320/HiDRA) — Hierarchical network model incorporating gene and pathway-level information for cancer drug response prediction. +- [PRNet](https://github.com/Perturbation-Response-Prediction/PRnet) — Deep generative model for predicting transcriptional responses to novel chemical perturbations for drug discovery. +- [chemCPA](https://github.com/theislab/chemCPA) — Compositional perturbation autoencoder for predicting single-cell transcriptional responses to unseen drug perturbations and dose combinations. +- [cycleCDR](https://github.com/hliulab/cycleCDR) — Interpretable cycle-consistency framework for modeling cellular responses to drug perturbations. +- [DRUML](https://github.com/CutillasLab/DRUMLR) — Ensemble machine learning framework combining standard ML with deep learning to systematically rank anti-cancer drugs from proteomics and RNA-seq data. + +#### Drug Repurposing + +- [DeepPurpose](https://github.com/kexinhuang12345/DeepPurpose) — Deep learning library for drug repurposing. +- [TranSiGen](https://github.com/myzhengSIMM/TranSiGen) — Dual-VAE architecture for ligand-based virtual screening, drug response prediction, and drug repurposing using chemical-induced transcriptional profiles. + +#### Drug Target Interaction + +- [NeoDTI](https://github.com/FangpingWan/NeoDTI) — Library for drug-target interaction prediction. +- [DTINet](https://github.com/luoyunan/DTINet) — Network-based framework integrating heterogeneous biological data for DTI prediction. +- [DeepDTA](https://github.com/hkmztrk/DeepDTA) — Deep learning model using CNNs on protein sequences and drug SMILES. +- [GraphDTA](https://github.com/thinng/GraphDTA) — Graph neural network–based DTI prediction using molecular graphs. +- [MolTrans](https://github.com/kexinhuang12345/MolTrans) — Transformer-based DTI model leveraging molecular substructures. +- [DrugBAN](https://github.com/peizhenbai/DrugBAN) — Bilinear attention network for interpretable DTI prediction. + +#### Compound-Protein Interaction + +- [MCPINN](https://github.com/mhlee0903/multi_channels_PINN) — Drug discovery via compound-protein interaction and machine learning. +- [TransformerCPI](https://github.com/lifanchen-simm/transformerCPI) — CPI prediction using Transformer. + +#### Molecular Generation + +- [REINVENT](https://github.com/MolecularAI/Reinvent) — Reinforcement learning for de novo drug design. +- [MolGPT](https://github.com/devalab/molgpt) — Transformer-based model for molecular generation. +- [Molecular Transformer](https://github.com/pschwllr/MolecularTransformer) — Sequence-to-sequence model for retrosynthesis prediction. +- [Matcha](https://github.com/LigandPro/Matcha) — Multi-stage Riemannian flow matching model for physically valid molecular docking with scoring, pose filtering, and benchmarks. +- [TargetDiff](https://github.com/guanjq/targetdiff) — 3D equivariant diffusion model for structure-based drug design. +- [DiffDock](https://github.com/gcorso/DiffDock) — Diffusion generative model for molecular docking, predicting the binding pose of small molecules to protein targets. +- [JTVAE](https://github.com/wengong-jin/icml18-jtnn) — Junction tree variational autoencoder for molecular graph generation that guarantees chemical validity via a hierarchical tree decomposition. +- [DiffSBDD](https://github.com/arneschneuing/DiffSBDD) — Equivariant diffusion model for structure-based drug design that generates molecules and binding conformations for protein targets. +- [ReLeaSE](https://github.com/isayev/ReLeaSE) — Deep reinforcement learning framework for de novo drug design combining a generative and predictive model. +- [PaccMannRL](https://github.com/PaccMann/paccmann_generator) — Reinforcement learning-based generative model for de novo hit-like anticancer molecule design from transcriptomic data. + +### LLM for Biology + +- [AI4Chem/ChemLLM-7B-Chat](https://huggingface.co/AI4Chem/ChemLLM-7B-Chat) — LLM for chemical & molecular science. +- [BioGPT](https://github.com/microsoft/BioGPT) — LLM for biomedical text generation. +- [GeneGPT](https://github.com/ncbi/GeneGPT) — LLM for biomedical information, integrated with various APIs. +- [GenePT](https://github.com/yiqunchen/GenePT) — Foundation LLM for single-cell data. +- [scPRINT](https://github.com/cantinilab/scPRINT) — Pretrained on 50M cells for scRNA-seq denoising & zero imputation. +- [ClawBio](https://github.com/ClawBio/ClawBio) — Bioinformatics-native AI agent skill library with local-first pharmacogenomics, ancestry PCA, semantic similarity, nutrigenomics, and metagenomics skills. +- [BioMedLM](https://huggingface.co/stanford-crfm/BioMedLM) — 2.7B parameter GPT-2-style language model trained exclusively on biomedical literature from PubMed for biomedical question answering and text generation. +- [MolT5](https://github.com/blender-nlp/MolT5) — Language model for molecular tasks bridging text and SMILES, enabling molecule captioning and text-driven molecule generation. +- [ChatDrug](https://github.com/chao1224/ChatDrug) — LLM-based conversational pipeline for drug discovery, using natural language prompts for iterative drug editing and optimization. +- [CASSIA](https://github.com/ElliotXie/CASSIA) — Multi-agent LLM for reference-free, interpretable cell-type annotation of single-cell RNA-seq data, with dedicated annotation, validation, scoring, and reporting agents. + +### Foundation Models + +#### Single-cell Foundation Models + +##### Transcriptomics Foundation Models + +- [scFoundation](https://github.com/biomap-research/scFoundation) — Large-scale foundation model for single-cell gene expression, enabling multiple downstream tasks. +- [scGPT](https://github.com/bowang-lab/scGPT) — Transformer-based foundation model pretrained on millions of single-cell profiles. +- [Geneformer](https://huggingface.co/ctheodoris/Geneformer) — Context-aware, attention-based deep learning model pretrained on a large corpus of single-cell transcriptomes. +- [BulkFormer](https://github.com/KangBoming/BulkFormer) — Foundation model for bulk RNA-seq data; learns general transcriptomic representations. +- [scBERT](https://github.com/TencentAILabHealthcare/scBERT) — BERT-based foundation model pretrained on large-scale scRNA-seq data for cell type annotation. +- [CellPLM](https://github.com/OmicsML/CellPLM) — Cell pre-trained language model with inter-cell transformer architecture for diverse single-cell analysis tasks. +- [UCE](https://github.com/snap-stanford/UCE) — Universal Cell Embeddings: zero-shot single-cell embedding model trained on 36M cells across species, tissues, and assays without fine-tuning. +- [GEARS](https://github.com/snap-stanford/GEARS) — Graph-based model for predicting transcriptional responses to single and combinatorial genetic perturbations using biological priors. +- [SATURN](https://github.com/snap-stanford/SATURN) — Transformer-based model integrating gene expression and protein sequences via a protein language model to learn unified multi-species cell embeddings. +- [CancerFoundation](https://github.com/BoevaLab/CancerFoundation) — Single-cell RNA-seq foundation model trained exclusively on a curated dataset of malignant cells to learn cancer-specific embeddings. + +##### Spatial Foundation Models + +- [GigaPath](https://github.com/prov-gigapath/prov-gigapath) — Slide-level digital pathology foundation model pretrained on 1.3 billion pathology image tokens from whole-slide images. +- [UNI](https://github.com/mahmoodlab/UNI) — General-purpose self-supervised pathology foundation model trained on 100K+ whole-slide images for diverse computational pathology tasks. +- [CONCH](https://github.com/mahmoodlab/CONCH) — Vision-language foundation model for computational pathology trained with contrastive captioning on pathology image–text pairs. +- [Phikon](https://huggingface.co/owkin/phikon) — ViT-based pathology foundation model pretrained with iBOT self-supervision on TCGA whole-slide images. +- [Nicheformer](https://github.com/theislab/nicheformer) — Foundation model for single-cell and spatial omics using a transformer architecture with positional embeddings to encode spatial cell information. +- [scGPT-spatial](https://github.com/bowang-lab/scGPT-spatial) — Extension of scGPT for spatial transcriptomics with continual pretraining and a mixture-of-experts decoder for spatial gene expression analysis. + +##### Multi-Omics Foundation Models + +- [scMulan](https://github.com/SuperBianC/scMulan) — Single-cell multi-omic language model pretrained on ~10M cells spanning transcriptomics, epigenomics, and proteomics for cross-omics transfer tasks. +- [totalVI](https://github.com/scverse/scvi-tools) — Probabilistic framework for joint analysis of paired scRNA-seq and protein (CITE-seq) data enabling multi-modal cell state representation across single-cell datasets. +- [MultiVI](https://github.com/scverse/scvi-tools) — Multi-modal variational autoencoder for integrating paired and unpaired single-cell RNA-seq and ATAC-seq measurements into a unified latent space. +- [MIRA](https://github.com/cistrome/MIRA) — Probabilistic multimodal topic model jointly modeling single-cell transcriptomics and chromatin accessibility for regulatory network inference. +- [GLUE](https://github.com/gao-lab/GLUE) — Graph-Linked Unified Embedding framework for unpaired single-cell multi-omics data integration across RNA, ATAC, methylation, and protein modalities. +- [BABEL](https://github.com/wukevin/babel) — Cross-modality translation model enabling prediction between scRNA-seq and scATAC-seq profiles without requiring paired single-cell measurements. +- [Multigrate](https://github.com/theislab/multigrate) — Asymmetric multi-omics variational autoencoder for integrating single-cell data across RNA, ATAC, and protein modalities with missing-modality support. +- [MOFA+](https://github.com/bioFAM/MOFA2) — Multi-Omics Factor Analysis framework identifying shared axes of variation across bulk and single-cell datasets including RNA, ATAC, proteomics, methylation, and copy number. +- [GeneCompass](https://github.com/xCompass-AI/GeneCompass) — Large-scale foundation model integrating DNA regulatory sequences and single-cell transcriptomics from 120M+ cells across multiple species for gene regulation prediction. +- [UnitedNet](https://github.com/LiuLab-Bioelectronics-Harvard/UnitedNet) — Interpretable multi-task deep neural network for single-cell multi-omics integration spanning transcriptomics, chromatin accessibility, and proteomics. +- [SpatialGlue](https://github.com/zhanglabtools/SpatialGlue) — Graph attention network for spatial multi-omics integration jointly embedding spatial transcriptomics with chromatin accessibility or proteomics. +- [MIDAS](https://github.com/labomics/midas) — Mosaic integration and differential accessibility model for single-cell multi-omics data that handles arbitrary missing-modality combinations across transcriptomics, chromatin accessibility, and proteomics. +- [Concerto](https://github.com/melobio/Concerto-reproducibility) — Contrastive self-supervised learning framework for single-cell multimodal data integration, batch correction, and reference-query mapping. +- [scButterfly](https://github.com/BioX-NKU/scButterfly) — Dual-aligned variational autoencoder for single-cell cross-modality translation between paired and unpaired multiomics data. +- [JAMIE](https://github.com/Oafish1/JAMIE) — Joint variational autoencoder for multimodal single-cell data imputation and embedding. +- [scPair](https://github.com/quon-titative-biology/scPair) — Bidirectional feedforward network for single-cell multimodal analysis with cross-modality prediction leveraging single-cell atlases. + +##### Domain Alignment + +- [scArches](https://github.com/theislab/scarches) — Transfer learning framework for mapping new single-cell datasets onto pre-trained reference atlases across batches, conditions, and modalities. +- [TOSICA](https://github.com/JackieHanlaopo/TOSICA) — Transformer-based framework for one-stop interpretable cell-type annotation supporting cross-dataset and cross-species transfer. + +#### Compound Foundation Models + +##### Compound Embedding + +- [ChemBERTa-2](https://github.com/seyonechithrananda/bert-loves-chemistry) — RoBERTa-based molecular language model pretrained on SMILES for small-molecule representation learning. +- [GROVER](https://github.com/tencent-ailab/grover) — Self-supervised graph transformer for large-scale molecular representation learning from unlabeled compounds. +- [Mol2Vec](https://github.com/samoturk/mol2vec) — Unsupervised molecular embedding method inspired by Word2Vec for learning vector representations of chemical substructures. +- [MolFormer](https://github.com/IBM/molformer) — Linear attention transformer pretrained on millions of SMILES strings for efficient molecular embeddings. +- [Uni-Mol](https://github.com/deepmodeling/Uni-Mol) — 3D molecular pretraining framework for universal representation learning on molecules and protein pockets. + +#### Protein Foundation Models + +##### Pre-trained Embedding + +- [Evolutionary Scale Modeling (ESM)](https://github.com/facebookresearch/esm) — Protein embeddings. +- [ProtTrans](https://github.com/agemagician/ProtTrans) — Suite of protein language models (ProtBERT, ProtT5, ProtXLNet) trained on billions of protein sequences from UniRef and BFD. +- [ProGen2](https://github.com/salesforce/progen) — Protein language model trained on diverse protein families for sequence generation and fitness prediction. +- [Ankh](https://github.com/agemagician/Ankh) — Efficient protein language model optimized for downstream prediction tasks including secondary structure, localization, and function annotation. + +##### Protein Structure Prediction and Design + +- [AlphaFold3](https://github.com/google-deepmind/alphafold3) — Predicts structures of proteins, nucleic acids, small molecules, and their complexes. +- [Boltz-1](https://github.com/jwohlwend/boltz) — Open-source all-atom biomolecular structure prediction model for proteins, nucleic acids, small molecules, and their complexes achieving AlphaFold3-level accuracy. +- [Chai-1](https://github.com/chaidiscovery/chai-lab) — Unified molecular structure prediction model covering proteins, nucleic acids, small molecules, and complexes. +- [ESM3](https://github.com/evolutionaryscale/esm) — Multimodal protein language model that jointly reasons over sequence, structure, and function for generative protein design and engineering. +- [ESMFold](https://github.com/facebookresearch/esm) — Fast protein structure prediction using language model embeddings. +- [RFdiffusion](https://github.com/RosettaCommons/RFdiffusion) — Generative model for protein backbone design using diffusion. +- [ProteinMPNN](https://github.com/dauparas/ProteinMPNN) — Deep learning model for protein sequence design given backbone structure. +- [OmegaFold](https://github.com/HeliXonProtein/OmegaFold) — High-resolution de novo protein structure prediction from sequence. +- [RoseTTAFold](https://github.com/RosettaCommons/RoseTTAFold) — Three-track neural network for protein structure prediction. +- [OpenFold](https://github.com/aqlaboratory/openfold) — Trainable, memory-efficient open-source reproduction of AlphaFold2 enabling custom protein structure prediction workflows. +- [SaProt](https://github.com/westlake-reup/SaProt) — Structure-aware protein language model using structure-aware tokens that encode both sequence and backbone geometry for improved function prediction. +- [EvoDiff](https://github.com/microsoft/evodiff) — Discrete diffusion framework for protein sequence generation trained on evolutionary-scale data, supporting unconditional generation, disordered region design, and functional motif scaffolding. [ [paper-2023](https://www.biorxiv.org/content/10.1101/2023.09.11.556673v1) ] + +#### Multi-Modal Foundation Models + +- [CHIEF](https://github.com/hms-dbmi/CHIEF) — Clinical Histopathology Imaging Evaluation Foundation model integrating histology images and clinical context for pan-cancer analysis. +- [BiomedCLIP](https://huggingface.co/microsoft/BiomedCLIP-PubMedBERT_256-vit_g_14) — CLIP-based vision-language foundation model for biomedical images and text trained on PubMed figure–caption pairs. +- [PORPOISE](https://github.com/mahmoodlab/PORPOISE) — Pan-cancer integrative histology-genomic analysis framework using multimodal deep learning for patient stratification. +- [PathomicFusion](https://github.com/mahmoodlab/PathomicFusion) — Integrated framework fusing histopathology and genomic features via CNN, GNN, and attention gating for cancer diagnosis and prognosis. +- [Virchow](https://huggingface.co/paige-ai/Virchow) — Million-slide digital pathology foundation model using a vision transformer and self-supervised distillation for tile-level pathology image representation. +- [TOAD](https://github.com/mahmoodlab/TOAD) — Tumor Origin Assessment via Deep-learning; weakly-supervised multi-task model predicting cancer primary origin from H&E whole-slide images. +- [PLIP](https://github.com/PathologyFoundation/plip) — Vision-language foundation model for pathology trained with contrastive learning on pathology image–text pairs for image classification and text-to-image retrieval. +- [MUSK](https://github.com/lilab-stanford/MUSK) — Vision-language foundation model for precision oncology analyzing multimodal paired text and pathology image data for biomarker prediction and retrieval. + +#### Genomics Foundation Models + +- [Nucleotide Transformer](https://github.com/instadeepai/nucleotide-transformer) — Foundation model for genomic sequences across multiple species. +- [DNABERT](https://github.com/jerryji1993/DNABERT) — Pre-trained bidirectional encoder for DNA sequence analysis. +- [DNABERT-2](https://github.com/Zhihan1996/DNABERT_2) — Improved genome foundation model with efficient tokenization. +- [Enformer](https://github.com/deepmind/deepmind-research/tree/master/enformer) — Transformer model predicting gene expression from DNA sequence. +- [Basenji](https://github.com/calico/basenji) — Sequential regulatory activity prediction from DNA sequences. +- [Caduceus](https://github.com/kuleshov-group/caduceus) — Bidirectional equivariant long-range DNA sequence model based on Mamba. +- [Evo](https://github.com/evo-design/evo) — Long-context genomic foundation model (up to 1M tokens). +- [HyenaDNA](https://github.com/HazyResearch/hyena-dna) — Long-range genomic foundation model handling sequences up to 1M tokens with sub-quadratic attention. +- [Borzoi](https://github.com/calico/borzoi) — Extended successor to Enformer for predicting RNA-seq coverage from long genomic sequence windows (524 kb) with improved resolution. +- [DeepSEA](http://deepsea.princeton.edu/) — Deep learning framework for predicting chromatin effects of sequence alterations with single-nucleotide sensitivity across thousands of chromatin features. +- [Sei](https://github.com/FunctionLab/sei-framework) — Sequence-to-function framework learning a genome-wide regulatory activity code from DNA sequences for variant effect prediction. +- [GPN (Genomic Pre-trained Network)](https://github.com/songlab-cal/gpn) — Masked language model for DNA sequences enabling zero-shot variant effect prediction without requiring functional annotations. + +--- + +## Citation + +If you use this list in papers, slides, or documentation, please cite this repository via [`CITATION.cff`](./CITATION.cff) (also available through GitHub's **Cite this repository** button). + +## Curation Criteria (Strict) + +To keep quality high, additions should meet all of the following: + +- The resource is trustworthy and relevant to computational biology. +- The primary link points to an official source (official docs, organization site, maintained repository, or official dataset page). +- The resource has evidence of technical substance: ideally a peer-reviewed paper; at minimum a preprint or official technical documentation. +- The description is factual and concise (no marketing copy). +- Duplicate or near-duplicate entries should be avoided. + +We generally do **not** accept entries that are only promotional pages, personal opinion posts, or generic blog posts without technical references. + +## Update & Link Rot Policy + +- Link validity is monitored by the [Link Check workflow](./.github/workflows/link-check.yml). +- If a link repeatedly fails, maintainers may replace it with an official mirror/canonical URL or remove the entry until a stable URL is available. +- Contributions fixing broken links are welcome and encouraged. + +## Data Schema & Contribution Workflow + +- Data schema reference: [`docs/data/SCHEMA.md`](./docs/data/SCHEMA.md). +- Source-of-truth workflow: + 1. Edit/add resources in `README.md`. + 2. Regenerate machine-readable artifacts: + - `python scripts/sync_resources_from_readme.py` + - `python scripts/build_resources.py` + 3. Commit updated data files (`data/resources.yml`, `data/resources.json`, `data/resources.csv`, `docs/data/resources.json`) with your README change. +- Contribution guide: [`contributing.md`](./contributing.md). diff --git a/upstream/inoue0426-awesome-computational-biology/catalogue/code-of-conduct.md b/upstream/inoue0426-awesome-computational-biology/catalogue/code-of-conduct.md new file mode 100644 index 0000000..5c05260 --- /dev/null +++ b/upstream/inoue0426-awesome-computational-biology/catalogue/code-of-conduct.md @@ -0,0 +1,87 @@ +--- +title: "Contributor Covenant Code of Conduct" +task: "" +lineage_type: import +upstream_source: https://github.com/inoue0426/awesome-computational-biology/blob/12d87583/code-of-conduct.md +upstream_sha: 12d87583 +imported_at: 2026-06-26 +prompt_class: unknown +upstream_changes: accepted +author: upstream +validated: false +--- + +# Contributor Covenant Code of Conduct + +## Our Pledge + +In the interest of fostering an open and welcoming environment, we as +contributors and maintainers pledge to making participation in our project and +our community a harassment-free experience for everyone, regardless of age, body +size, disability, ethnicity, gender identity and expression, level of experience, +nationality, personal appearance, race, religion, or sexual identity and +orientation. + +## Our Standards + +Examples of behavior that contributes to creating a positive environment +include: + +* Using welcoming and inclusive language +* Being respectful of differing viewpoints and experiences +* Gracefully accepting constructive criticism +* Focusing on what is best for the community +* Showing empathy towards other community members + +Examples of unacceptable behavior by participants include: + +* The use of sexualized language or imagery and unwelcome sexual attention or +advances +* Trolling, insulting/derogatory comments, and personal or political attacks +* Public or private harassment +* Publishing others' private information, such as a physical or electronic + address, without explicit permission +* Other conduct which could reasonably be considered inappropriate in a + professional setting + +## Our Responsibilities + +Project maintainers are responsible for clarifying the standards of acceptable +behavior and are expected to take appropriate and fair corrective action in +response to any instances of unacceptable behavior. + +Project maintainers have the right and responsibility to remove, edit, or +reject comments, commits, code, wiki edits, issues, and other contributions +that are not aligned to this Code of Conduct, or to ban temporarily or +permanently any contributor for other behaviors that they deem inappropriate, +threatening, offensive, or harmful. + +## Scope + +This Code of Conduct applies both within project spaces and in public spaces +when an individual is representing the project or its community. Examples of +representing a project or community include using an official project e-mail +address, posting via an official social media account, or acting as an appointed +representative at an online or offline event. Representation of a project may be +further defined and clarified by project maintainers. + +## Enforcement + +Instances of abusive, harassing, or otherwise unacceptable behavior may be +reported by contacting the project team at inoue019@umn.edu. All +complaints will be reviewed and investigated and will result in a response that +is deemed necessary and appropriate to the circumstances. The project team is +obligated to maintain confidentiality with regard to the reporter of an incident. +Further details of specific enforcement policies may be posted separately. + +Project maintainers who do not follow or enforce the Code of Conduct in good +faith may face temporary or permanent repercussions as determined by other +members of the project's leadership. + +## Attribution + +This Code of Conduct is adapted from the [Contributor Covenant][homepage], version 1.4, +available at [http://contributor-covenant.org/version/1/4][version] + +[homepage]: http://contributor-covenant.org +[version]: http://contributor-covenant.org/version/1/4/ diff --git a/upstream/inoue0426-awesome-computational-biology/catalogue/contributing.md b/upstream/inoue0426-awesome-computational-biology/catalogue/contributing.md new file mode 100644 index 0000000..97435c4 --- /dev/null +++ b/upstream/inoue0426-awesome-computational-biology/catalogue/contributing.md @@ -0,0 +1,77 @@ +--- +title: "Contribution Guidelines" +task: "" +lineage_type: import +upstream_source: https://github.com/inoue0426/awesome-computational-biology/blob/12d87583/contributing.md +upstream_sha: 12d87583 +imported_at: 2026-06-26 +prompt_class: catalogue +upstream_changes: accepted +author: upstream +validated: false +--- + +# Contribution Guidelines + +Contributions are welcome! + +Please note that this project is released with a +[Contributor Code of Conduct](code-of-conduct.md). By participating in this +project you agree to abide by its terms. + +## Pull Requests + +- Search previous suggestions before making a new one, as yours may be a duplicate. +- Add one link per pull request. +- Prefer official and trustworthy sources (official docs, organization pages, maintained repositories, or official dataset pages). +- Include supporting technical evidence for new resources: + - Ideally a peer-reviewed publication. + - At minimum, a preprint or official technical documentation. +- Avoid submissions that are primarily promotional pages, generic blog posts, or opinion-only writeups. +- Add the link: + - `[name](http://example.com/)` - A short description ends with a period. + - Keep descriptions concise. + - Maintain alphabetical ordering where applicable. +- Add a section if needed. + - Add the section description. + - Add the section title to the [Index](https://github.com/inoue0426/awesome-computational-biology#Contents). +- Check your spelling and grammar. +- Remove any trailing whitespace. +- Send a pull request with the reason why the addition is awesome. +- Use the following format for your pull request title: + - Add user/repo - Short repo description + +## Data Workflow (README and JSON) + +- The curated source list is maintained in `README.md`. +- Machine-readable files are generated from README: + - `python scripts/sync_resources_from_readme.py` + - `python scripts/build_resources.py` +- For resource additions/edits, include updated generated files in the same PR: + - `data/resources.yml` + - `data/resources.json` + - `data/resources.csv` + - `docs/data/resources.json` +- Field definitions and naming rules are documented in [`docs/data/SCHEMA.md`](docs/data/SCHEMA.md). + +## GitHub Pages UI + +- The UI reads `docs/data/resources.json`. +- Search and filters are driven by these fields: + - Search: `name`, `description`, `tasks`, `modalities`, `tags` + - Filters: `type`, `tasks`, `modalities` + +## Updates to Existing Links or Sections + +- Improvements to the existing sections are welcome. +- If you think a listed link is not awesome, feel free to submit an issue or pull request to begin the discussion. +- Broken links are checked by CI; if you find one, please submit a fix to the canonical URL (or remove the entry if no stable canonical URL exists). + +## Updating your PR + +A lot of times, making a PR adhere to the standards above can be difficult. +If the maintainers notice anything that we'd like changed, we'll ask you to +edit your PR before we merge it. There's no need to open a new PR, just edit +the existing one. If you're not sure how to do that, +[here is a guide](https://github.com/RichardLitt/knowledge/blob/master/github/amending-a-commit-guide.md) +on the different ways you can update your PR so that we can merge it. diff --git a/upstream/inoue0426-awesome-computational-biology/catalogue/cspell.json b/upstream/inoue0426-awesome-computational-biology/catalogue/cspell.json new file mode 100644 index 0000000..99485cf --- /dev/null +++ b/upstream/inoue0426-awesome-computational-biology/catalogue/cspell.json @@ -0,0 +1,165 @@ +--- +title: "Cspell" +task: "" +lineage_type: import +upstream_source: https://github.com/inoue0426/awesome-computational-biology/blob/12d87583/cspell.json +upstream_sha: 12d87583 +imported_at: 2026-06-26 +prompt_class: unknown +upstream_changes: accepted +author: upstream +validated: false +--- + +{ + "language": "en", + "allowCompoundWords": true, + "words": [ + "behavioural", + "KEGG", + "NCBI", + "UCSC", + "EMBL", + "RCSB", + "CASP", + "Uniclust", + "Reactome", + "Bioactive", + "biopolymers", + "proteomics", + "transcriptomics", + "metagenomic", + "metatranscriptomic", + "CRISPR", + "JASPAR", + "druggable", + "Toxicogenomics", + "GDSC", + "biomolecular", + "DRKG", + "Hetionet", + "Eudra", + "esearch", + "efetch", + "Ensembl", + "Cheminformatics", + "Deconv", + "Scanpy", + "Squidpy", + "explainability", + "MOFGCN", + "Autoencoder", + "DGDRP", + "MCPINN", + "Pretrained", + "pretrained", + "denoising", + "transcriptomic", + "CELLxGENE", + "eukaryotic", + "metabolites", + "OMIM", + "Mendelian", + "DisGeNET", + "GWAS", + "IntAct", + "Biopython", + "MDAnalysis", + "trajectories", + "Geneformer", + "equivariant", + "HyenaDNA", + "Hyena", + "Caduceus", + "Mamba", + "retrosynthesis", + "TargetDiff", + "Chai", + "Zuckerberg", + "HMDB", + "CTRP", + "ADMET", + "Omics", + "omics", + "omic", + "OADB", + "Gnify", + "gnom", + "Rfam", + "Guaca", + "deconvolution", + "scvi", + "pharmacogenomics", + "nutrigenomics", + "Giga", + "Phikon", + "TCGA", + "Mulan", + "epigenomics", + "methylation", + "ATAC", + "MOFA", + "TOSICA", + "Boltz", + "MPNN", + "Enformer", + "Velo", + "BACE", + "secretase", + "Clin", + "CPTAC", + "Proteomic", + "proteogenomic", + "LINCS", + "ogbl", + "ogbg", + "SIDER", + "Muris", + "Pfam", + "PROSITE", + "epigenome", + "TRRUST", + "kallisto", + "pseudoalignment", + "multiplet", + "TGSA", + "JTVAE", + "miRBase", + "miRNA", + "ProtTrans", + "ProtBERT", + "ProGen", + "Ankh", + "DeepSEA", + "RegNetwork", + "ROADMAP", + "FANTOM", + "NeXtProt", + "HiDRA", + "MolT", + "ChatDrug", + "DoubletFinder", + "pseudotime", + "ligand", + "SCENIC", + "GPN", + "Sei", + "KIBA", + "pharmacokinetics", + "ADME", + "Haplotype", + "NCEM", + "multiome", + "MOGONET", + "convolutional", + "DRUML", + "SBDD", + "Pacc", + "multiomics", + "Pathomic", + "PLIP" + ], + "ignorePaths": [ + "node_modules/**" + ] +} diff --git a/upstream/inoue0426-awesome-computational-biology/catalogue/data/resources.json b/upstream/inoue0426-awesome-computational-biology/catalogue/data/resources.json new file mode 100644 index 0000000..99b761c --- /dev/null +++ b/upstream/inoue0426-awesome-computational-biology/catalogue/data/resources.json @@ -0,0 +1,4996 @@ +--- +title: "Resources" +task: "" +lineage_type: import +upstream_source: https://github.com/inoue0426/awesome-computational-biology/blob/12d87583/data/resources.json +upstream_sha: 12d87583 +imported_at: 2026-06-26 +prompt_class: catalogue +upstream_changes: accepted +author: upstream +validated: false +--- + +[ + { + "id": "chembl_web_services", + "name": "ChEMBL Web Services", + "type": "api", + "url": "https://www.ebi.ac.uk/chembl/ws", + "description": "REST API for bioactive molecules, targets, and bioassays.", + "tags": [ + "api" + ], + "tasks": [], + "modalities": [], + "organism": [], + "api": true + }, + { + "id": "clinicaltrials_gov_api", + "name": "ClinicalTrials.gov API", + "type": "api", + "url": "https://clinicaltrials.gov/api/gui", + "description": "API for querying clinical trial metadata and results.", + "tags": [ + "api" + ], + "tasks": [], + "modalities": [], + "organism": [], + "api": true + }, + { + "id": "ensembl_rest_api", + "name": "Ensembl REST API", + "type": "api", + "url": "https://rest.ensembl.org/", + "description": "API for genomic annotations, variants, genes, and comparative genomics.", + "tags": [ + "api" + ], + "tasks": [], + "modalities": [], + "organism": [], + "api": true + }, + { + "id": "kegg_rest_api", + "name": "KEGG REST API", + "type": "api", + "url": "https://www.kegg.jp/kegg/rest/keggapi.html", + "description": "API for accessing KEGG pathways, compounds, genes, and reactions.", + "tags": [ + "api" + ], + "tasks": [], + "modalities": [], + "organism": [], + "api": true + }, + { + "id": "ncbi_e_utilities", + "name": "NCBI E-utilities", + "type": "api", + "url": "https://www.ncbi.nlm.nih.gov/books/NBK25501/", + "description": "Unified APIs for accessing NCBI databases (Gene, GEO, SRA, PubChem, etc).", + "tags": [ + "api" + ], + "tasks": [], + "modalities": [], + "organism": [], + "api": true + }, + { + "id": "open_targets_platform_api", + "name": "Open Targets Platform API", + "type": "api", + "url": "https://platform.opentargets.org/api", + "description": "API for target–disease associations integrating genetics, genomics, and drug data.", + "tags": [ + "api" + ], + "tasks": [], + "modalities": [], + "organism": [], + "api": true + }, + { + "id": "pubmed_e_utilities_esearch_efetch", + "name": "PubMed E-utilities (esearch/efetch)", + "type": "api", + "url": "https://www.nlm.nih.gov/dataguide/edirect/esearch.html", + "description": "APIs for searching and retrieving biomedical literature from PubMed.", + "tags": [ + "api" + ], + "tasks": [], + "modalities": [], + "organism": [], + "api": true + }, + { + "id": "uniprot_rest_api", + "name": "UniProt REST API", + "type": "api", + "url": "https://www.uniprot.org/help/api", + "description": "Programmatic access to protein sequence and functional annotation data.", + "tags": [ + "api" + ], + "tasks": [], + "modalities": [], + "organism": [], + "api": true + }, + { + "id": "1000_genomes_project", + "name": "1000 Genomes Project", + "type": "benchmark", + "url": "https://www.internationalgenome.org/", + "description": "Reference panel of human genetic variation from 2,504 individuals across 26 populations.", + "tags": [ + "benchmarks-and-datasets" + ], + "tasks": [], + "modalities": [], + "organism": [], + "api": false + }, + { + "id": "bace", + "name": "BACE", + "type": "benchmark", + "url": "https://www.kaggle.com/datasets/gokturkkoch/bace", + "description": "Binary classification and regression dataset for β-secretase 1 (BACE-1) inhibitor binding affinity.", + "tags": [ + "benchmarks-and-datasets" + ], + "tasks": [], + "modalities": [], + "organism": [], + "api": false + }, + { + "id": "beat_aml", + "name": "BEAT AML", + "type": "benchmark", + "url": "https://biodev.github.io/BeatAML2/", + "description": "Functional ex vivo drug sensitivity measurements paired with genomics for acute myeloid leukemia.", + "tags": [ + "benchmarks-and-datasets" + ], + "tasks": [], + "modalities": [], + "organism": [], + "api": false + }, + { + "id": "bento", + "name": "Bento", + "type": "benchmark", + "url": "https://github.com/LigandPro/Bento", + "description": "Protein-ligand docking benchmark covering rigid, flexible, de novo, blind, induced-fit, and covalent docking tasks.", + "tags": [ + "benchmarks-and-datasets" + ], + "tasks": [], + "modalities": [], + "organism": [], + "api": false + }, + { + "id": "bindingdb_curated_sets", + "name": "BindingDB Curated Sets", + "type": "benchmark", + "url": "https://www.bindingdb.org/rwd/bind/chemsearch/marvin/SDFdownload.jsp?all_download=yes", + "description": "Curated binding affinity datasets for protein–ligand interaction benchmarking.", + "tags": [ + "benchmarks-and-datasets" + ], + "tasks": [], + "modalities": [], + "organism": [], + "api": false + }, + { + "id": "cancer_therapeutics_response_portal_ctrp", + "name": "Cancer Therapeutics Response Portal (CTRP)", + "type": "benchmark", + "url": "https://portals.broadinstitute.org/ctrp/", + "description": "Drug sensitivity profiles across ~900 cancer cell lines for >400 compounds.", + "tags": [ + "benchmarks-and-datasets" + ], + "tasks": [], + "modalities": [], + "organism": [], + "api": false + }, + { + "id": "clintox", + "name": "ClinTox", + "type": "benchmark", + "url": "https://tdcommons.ai/single_pred_tasks/tox/#clintox", + "description": "Clinical toxicity dataset contrasting FDA-approved drugs with those that failed clinical trials due to toxicity.", + "tags": [ + "benchmarks-and-datasets" + ], + "tasks": [], + "modalities": [], + "organism": [], + "api": false + }, + { + "id": "cptac_clinical_proteomic_tumor_analysis_consortium", + "name": "CPTAC (Clinical Proteomic Tumor Analysis Consortium)", + "type": "benchmark", + "url": "https://proteomics.cancer.gov/programs/cptac", + "description": "Multi-omic proteogenomic datasets for multiple cancer types linking proteomics with genomics.", + "tags": [ + "benchmarks-and-datasets" + ], + "tasks": [], + "modalities": [], + "organism": [], + "api": false + }, + { + "id": "crossdocked2020", + "name": "CrossDocked2020", + "type": "benchmark", + "url": "https://arxiv.org/abs/2001.01037", + "description": "Large-scale dataset for structure-based virtual screening.", + "tags": [ + "benchmarks-and-datasets" + ], + "tasks": [], + "modalities": [], + "organism": [], + "api": false + }, + { + "id": "dud_e_directory_of_useful_decoys_enhanced", + "name": "DUD-E (Directory of Useful Decoys, Enhanced)", + "type": "benchmark", + "url": "http://dude.docking.org/", + "description": "Structure-based virtual screening benchmark with active ligands and challenging decoy sets across diverse protein targets.", + "tags": [ + "benchmarks-and-datasets" + ], + "tasks": [], + "modalities": [], + "organism": [], + "api": false + }, + { + "id": "flip_fitness_landscape_inference_for_proteins", + "name": "FLIP (Fitness Landscape Inference for Proteins)", + "type": "benchmark", + "url": "https://github.com/J-SNACKKB/FLIP", + "description": "Benchmark collection of protein fitness landscape datasets for evaluating protein ML models.", + "tags": [ + "benchmarks-and-datasets" + ], + "tasks": [], + "modalities": [], + "organism": [], + "api": false + }, + { + "id": "guacamol", + "name": "GuacaMol", + "type": "benchmark", + "url": "https://github.com/BenevolentAI/guacamol", + "description": "Benchmark suite for generative molecular design models.", + "tags": [ + "benchmarks-and-datasets" + ], + "tasks": [], + "modalities": [], + "organism": [], + "api": false + }, + { + "id": "jump_cell_painting_datasets", + "name": "JUMP Cell Painting Datasets", + "type": "benchmark", + "url": "https://github.com/jump-cellpainting/datasets", + "description": "Consortium-scale cell imaging perturbation datasets (chemical and genetic) for phenotypic profiling and drug discovery research.", + "tags": [ + "benchmarks-and-datasets" + ], + "tasks": [], + "modalities": [], + "organism": [], + "api": false + }, + { + "id": "lincs_l1000", + "name": "LINCS L1000", + "type": "benchmark", + "url": "https://lincsproject.org/LINCS/tools/workflows/find-the-best-place-to-obtain-the-lincs-l1000-data", + "description": "Gene expression profiles (978 landmark genes) for >20,000 chemical and genetic perturbations across cell lines.", + "tags": [ + "benchmarks-and-datasets" + ], + "tasks": [], + "modalities": [], + "organism": [], + "api": false + }, + { + "id": "moleculenet", + "name": "MoleculeNet", + "type": "benchmark", + "url": "http://moleculenet.ai/", + "description": "Benchmark datasets for molecular machine learning.", + "tags": [ + "benchmarks-and-datasets" + ], + "tasks": [], + "modalities": [], + "organism": [], + "api": false + }, + { + "id": "moses", + "name": "MOSES", + "type": "benchmark", + "url": "https://github.com/molecularsets/moses", + "description": "Benchmarking platform for molecular generation models.", + "tags": [ + "benchmarks-and-datasets" + ], + "tasks": [], + "modalities": [], + "organism": [], + "api": false + }, + { + "id": "ogb_open_graph_benchmark", + "name": "OGB (Open Graph Benchmark)", + "type": "benchmark", + "url": "https://ogb.stanford.edu/", + "description": "Large-scale graph ML benchmark suite including biological datasets such as ogbl-ppa (protein-protein associations) and ogbg-molhiv.", + "tags": [ + "benchmarks-and-datasets" + ], + "tasks": [], + "modalities": [], + "organism": [], + "api": false + }, + { + "id": "openbiolink", + "name": "OpenBioLink", + "type": "benchmark", + "url": "https://github.com/OpenBioLink/OpenBioLink", + "description": "Benchmark datasets for biological knowledge graph completion.", + "tags": [ + "benchmarks-and-datasets" + ], + "tasks": [], + "modalities": [], + "organism": [], + "api": false + }, + { + "id": "pharmgkb", + "name": "PharmGKB", + "type": "benchmark", + "url": "https://www.pharmgkb.org/", + "description": "Curated pharmacogenomics dataset linking genetic variants to drug response phenotypes across thousands of drugs.", + "tags": [ + "benchmarks-and-datasets" + ], + "tasks": [], + "modalities": [], + "organism": [], + "api": false + }, + { + "id": "pk_db", + "name": "PK-DB", + "type": "benchmark", + "url": "https://pk-db.com/", + "description": "Open database of experimental pharmacokinetics (PK) and ADME data from clinical and preclinical studies.", + "tags": [ + "benchmarks-and-datasets" + ], + "tasks": [], + "modalities": [], + "organism": [], + "api": false + }, + { + "id": "prism", + "name": "PRISM", + "type": "benchmark", + "url": "https://depmap.org/portal/prism/", + "description": "Cancer drug sensitivity profiling of >4,500 drugs across >900 cancer cell lines using pooled-cell-line barcoding.", + "tags": [ + "benchmarks-and-datasets" + ], + "tasks": [], + "modalities": [], + "organism": [], + "api": false + }, + { + "id": "proteingym", + "name": "ProteinGym", + "type": "benchmark", + "url": "https://github.com/OATML-Markslab/ProteinGym", + "description": "Large-scale benchmark of deep mutational scanning assays for evaluating protein fitness landscape models.", + "tags": [ + "benchmarks-and-datasets" + ], + "tasks": [], + "modalities": [], + "organism": [], + "api": false + }, + { + "id": "qm9", + "name": "QM9", + "type": "benchmark", + "url": "https://figshare.com/collections/Quantum_chemistry_structures_and_properties_of_134_kilo_molecules/978904", + "description": "Quantum chemistry properties for 134K stable small organic molecules computed at DFT level.", + "tags": [ + "benchmarks-and-datasets" + ], + "tasks": [], + "modalities": [], + "organism": [], + "api": false + }, + { + "id": "scib_single_cell_integration_benchmarks", + "name": "scIB (Single-cell Integration Benchmarks)", + "type": "benchmark", + "url": "https://github.com/theislab/scib", + "description": "Comprehensive benchmarking framework for single-cell data integration methods.", + "tags": [ + "benchmarks-and-datasets" + ], + "tasks": [], + "modalities": [], + "organism": [], + "api": false + }, + { + "id": "scperturb", + "name": "scPerturb", + "type": "benchmark", + "url": "https://github.com/sanderlab/scPerturb", + "description": "Curated and continuously updated single-cell perturbation data resource spanning CRISPR and drug perturbation studies.", + "tags": [ + "benchmarks-and-datasets" + ], + "tasks": [], + "modalities": [], + "organism": [], + "api": false + }, + { + "id": "sider_side_effect_resource", + "name": "SIDER (Side Effect Resource)", + "type": "benchmark", + "url": "http://sideeffects.embl.de/", + "description": "Database of 1,430 approved drugs with their recorded adverse drug reactions across 27 system-organ classes.", + "tags": [ + "benchmarks-and-datasets" + ], + "tasks": [], + "modalities": [], + "organism": [], + "api": false + }, + { + "id": "tabula_muris", + "name": "Tabula Muris", + "type": "benchmark", + "url": "https://tabula-muris.ds.czbiohub.org/", + "description": "Comprehensive single-cell atlas of 20 mouse organs and tissues, enabling cross-tissue and cross-species comparisons.", + "tags": [ + "benchmarks-and-datasets" + ], + "tasks": [], + "modalities": [], + "organism": [], + "api": false + }, + { + "id": "tabula_sapiens", + "name": "Tabula Sapiens", + "type": "benchmark", + "url": "https://tabula-sapiens-portal.ds.czbiohub.org/", + "description": "Comprehensive human single-cell atlas of ~500K cells from 24 organs and tissues across multiple donors.", + "tags": [ + "benchmarks-and-datasets" + ], + "tasks": [], + "modalities": [], + "organism": [], + "api": false + }, + { + "id": "tape_tasks_assessing_protein_embeddings", + "name": "TAPE (Tasks Assessing Protein Embeddings)", + "type": "benchmark", + "url": "https://github.com/songlab-cal/tape", + "description": "Benchmark suite of five biologically meaningful semi-supervised learning tasks for evaluating protein representations.", + "tags": [ + "benchmarks-and-datasets" + ], + "tasks": [], + "modalities": [], + "organism": [], + "api": false + }, + { + "id": "the_cancer_genome_atlas_tcga", + "name": "The Cancer Genome Atlas (TCGA)", + "type": "benchmark", + "url": "https://www.cancer.gov/about-nci/organization/ccg/research/structural-genomics/tcga", + "description": "Comprehensive multi-omics (genomics, transcriptomics, proteomics, methylation) dataset for 33 cancer types across ~11,000 patients.", + "tags": [ + "benchmarks-and-datasets" + ], + "tasks": [], + "modalities": [], + "organism": [], + "api": false + }, + { + "id": "therapeutics_data_commons_tdc", + "name": "Therapeutics Data Commons (TDC)", + "type": "benchmark", + "url": "https://tdcommons.ai/", + "description": "Unified benchmark suite covering ADMET, drug-target interaction, drug response, and more.", + "tags": [ + "benchmarks-and-datasets" + ], + "tasks": [], + "modalities": [], + "organism": [], + "api": false + }, + { + "id": "tox21", + "name": "Tox21", + "type": "benchmark", + "url": "https://tripod.nih.gov/tox21/challenge/", + "description": "12,707 compounds tested in 12 nuclear receptor and stress-response pathway biochemical assays for toxicity prediction.", + "tags": [ + "benchmarks-and-datasets" + ], + "tasks": [], + "modalities": [], + "organism": [], + "api": false + }, + { + "id": "uk_biobank", + "name": "UK Biobank", + "type": "benchmark", + "url": "https://www.ukbiobank.ac.uk/", + "description": "Large-scale biomedical database of ~500K participants with genetic, imaging, and health data for population genetics and disease studies.", + "tags": [ + "benchmarks-and-datasets" + ], + "tasks": [], + "modalities": [], + "organism": [], + "api": false + }, + { + "id": "10x_genomics_dataset", + "name": "10x Genomics Dataset", + "type": "database", + "url": "https://www.10xgenomics.com/resources/datasets", + "description": "Collection of single-cell datasets.", + "tags": [ + "genome" + ], + "tasks": [], + "modalities": [ + "Genomics" + ], + "organism": [], + "api": false + }, + { + "id": "alphafold_protein_structure_database", + "name": "AlphaFold Protein Structure Database", + "type": "database", + "url": "https://alphafold.ebi.ac.uk/api-docs", + "description": "3D protein structure predictions.", + "tags": [ + "protein" + ], + "tasks": [], + "modalities": [ + "Protein" + ], + "organism": [], + "api": false + }, + { + "id": "bindingdb", + "name": "BindingDB", + "type": "database", + "url": "https://www.bindingdb.org/rwd/bind/index.jsp", + "description": "Compounds and target database.", + "tags": [ + "chemical-protein-interaction", + "interaction" + ], + "tasks": [], + "modalities": [ + "Protein", + "Small Molecule" + ], + "organism": [], + "api": false + }, + { + "id": "biocyc", + "name": "BioCyc", + "type": "database", + "url": "https://biocyc.org/", + "description": "Collection of pathway/genome databases across thousands of organisms.", + "tags": [ + "pathway" + ], + "tasks": [], + "modalities": [ + "Pathway" + ], + "organism": [], + "api": false + }, + { + "id": "biogrid", + "name": "BioGRID", + "type": "database", + "url": "https://thebiogrid.org/", + "description": "Protein, genetic, and chemical interactions.", + "tags": [ + "interaction", + "protein-protein-interaction" + ], + "tasks": [], + "modalities": [ + "Protein" + ], + "organism": [], + "api": false + }, + { + "id": "cancer_cell_line_encyclopedia", + "name": "Cancer Cell Line Encyclopedia", + "type": "database", + "url": "https://sites.broadinstitute.org/ccle/", + "description": "Database of ~1000 cancer cell lines.", + "tags": [ + "drug-cell-line-response", + "interaction" + ], + "tasks": [], + "modalities": [ + "Gene Expression", + "Small Molecule" + ], + "organism": [], + "api": false + }, + { + "id": "catalogue_of_somatic_mutations_in_cancer_cosmic", + "name": "Catalogue Of Somatic Mutations In Cancer (COSMIC)", + "type": "database", + "url": "https://cancer.sanger.ac.uk/cosmic", + "description": "Resource on somatic mutations in cancers.", + "tags": [ + "genome" + ], + "tasks": [], + "modalities": [ + "Genomics" + ], + "organism": [], + "api": false + }, + { + "id": "cath_database", + "name": "CATH database", + "type": "database", + "url": "https://www.cathdb.info/", + "description": "Hierarchical classification of protein domain structures.", + "tags": [ + "protein" + ], + "tasks": [], + "modalities": [ + "Protein" + ], + "organism": [], + "api": false + }, + { + "id": "cbioportal", + "name": "cBioPortal", + "type": "database", + "url": "https://www.cbioportal.org/", + "description": "Cancer genomics database; aggregating many patient datasets.", + "tags": [ + "genome" + ], + "tasks": [], + "modalities": [ + "Genomics" + ], + "organism": [], + "api": false + }, + { + "id": "cellminer_cross_database_cellminercdb", + "name": "CellMiner Cross Database (CellMinerCDB)", + "type": "database", + "url": "https://discover.nci.nih.gov/cellminercdb/", + "description": "Integrates multiple cancer cell line databases.", + "tags": [ + "drug-cell-line-response", + "interaction" + ], + "tasks": [], + "modalities": [ + "Gene Expression", + "Small Molecule" + ], + "organism": [], + "api": false + }, + { + "id": "chebi", + "name": "ChEBI", + "type": "database", + "url": "https://www.ebi.ac.uk/chebi/", + "description": "Database focused on small chemical compounds.", + "tags": [ + "compound" + ], + "tasks": [], + "modalities": [ + "Small Molecule" + ], + "organism": [], + "api": false + }, + { + "id": "chembl", + "name": "ChEMBL", + "type": "database", + "url": "https://www.ebi.ac.uk/chembl/", + "description": "Bioactive molecules with drug-like properties.", + "tags": [ + "compound" + ], + "tasks": [], + "modalities": [ + "Small Molecule" + ], + "organism": [], + "api": false + }, + { + "id": "chemspider", + "name": "ChemSpider", + "type": "database", + "url": "http://www.chemspider.com/", + "description": "Chemical structure database.", + "tags": [ + "compound" + ], + "tasks": [], + "modalities": [ + "Small Molecule" + ], + "organism": [], + "api": false + }, + { + "id": "clinicaltrials_gov", + "name": "ClinicalTrials.gov", + "type": "database", + "url": "https://clinicaltrials.gov/", + "description": "Privately and publicly funded clinical studies.", + "tags": [ + "clinical-trial" + ], + "tasks": [], + "modalities": [ + "Clinical" + ], + "organism": [], + "api": false + }, + { + "id": "comparative_toxicogenomics_database", + "name": "Comparative Toxicogenomics Database", + "type": "database", + "url": "http://ctdbase.org/", + "description": "Chemical-gene interactions, chemical-disease and gene-disease associations, chemical-phenotype associations.", + "tags": [ + "drug-gene-interaction", + "interaction" + ], + "tasks": [], + "modalities": [ + "Gene", + "Small Molecule" + ], + "organism": [], + "api": false + }, + { + "id": "critical_assessment_of_structure_prediction_casp", + "name": "Critical Assessment of Structure Prediction (CASP)", + "type": "database", + "url": "https://predictioncenter.org/", + "description": "Assessing methods for protein structure prediction.", + "tags": [ + "protein" + ], + "tasks": [], + "modalities": [ + "Protein" + ], + "organism": [], + "api": false + }, + { + "id": "cz_cellxgene", + "name": "CZ CELLxGENE", + "type": "database", + "url": "https://cellxgene.cziscience.com/", + "description": "Single-cell dataset repository and interactive explorer from the Chan Zuckerberg Initiative.", + "tags": [ + "scrna" + ], + "tasks": [], + "modalities": [ + "Single Cell" + ], + "organism": [], + "api": false + }, + { + "id": "davis_kinase_inhibitors_db", + "name": "Davis kinase inhibitors DB", + "type": "database", + "url": "http://staff.cs.utu.fi/~aijrinas/dti/", + "description": "Experimental kinase inhibitor binding affinity dataset for protein–ligand interaction research.", + "tags": [ + "chemical-protein-interaction", + "interaction" + ], + "tasks": [], + "modalities": [ + "Protein", + "Small Molecule" + ], + "organism": [], + "api": false + }, + { + "id": "dependency_map_depmap", + "name": "Dependency Map (DepMap)", + "type": "database", + "url": "https://depmap.org/portal/", + "description": "CRISPR-Cas9 screens in cancer cell lines.", + "tags": [ + "genome" + ], + "tasks": [], + "modalities": [ + "Genomics" + ], + "organism": [], + "api": false + }, + { + "id": "dgidb", + "name": "DGIdb", + "type": "database", + "url": "https://www.dgidb.org/", + "description": "Drug-gene interactions and the druggable genome.", + "tags": [ + "drug-gene-interaction", + "interaction" + ], + "tasks": [], + "modalities": [ + "Gene", + "Small Molecule" + ], + "organism": [], + "api": false + }, + { + "id": "diseases", + "name": "DISEASES", + "type": "database", + "url": "https://diseases.jensenlab.org/", + "description": "Gene–disease association database integrating evidence from text mining, curated databases, and experimental data.", + "tags": [ + "disease" + ], + "tasks": [], + "modalities": [ + "Disease" + ], + "organism": [], + "api": false + }, + { + "id": "disgenet", + "name": "DisGeNET", + "type": "database", + "url": "https://www.disgenet.org/", + "description": "Database of gene-disease associations integrating expert-curated and GWAS data.", + "tags": [ + "disease" + ], + "tasks": [], + "modalities": [ + "Disease" + ], + "organism": [], + "api": false + }, + { + "id": "drkg", + "name": "DRKG", + "type": "database", + "url": "https://github.com/gnn4dr/DRKG", + "description": "Large-scale biological knowledge graph for drug discovery.", + "tags": [ + "interaction", + "knowledge-graph" + ], + "tasks": [], + "modalities": [ + "Knowledge Graph" + ], + "organism": [], + "api": false + }, + { + "id": "drug_mechanism_database_drugmechdb", + "name": "Drug Mechanism Database (DrugMechDB)", + "type": "database", + "url": "https://github.com/SuLab/DrugMechDB/tree/2.0.1", + "description": "Mechanisms of action from drug to disease.", + "tags": [ + "interaction", + "knowledge-graph" + ], + "tasks": [], + "modalities": [ + "Knowledge Graph" + ], + "organism": [], + "api": false + }, + { + "id": "drug_repurposing_hub", + "name": "Drug Repurposing Hub", + "type": "database", + "url": "https://repo-hub.broadinstitute.org/repurposing#download-data", + "description": "Collections of drug repurposing data (drug, MoA, target, etc).", + "tags": [ + "compound" + ], + "tasks": [], + "modalities": [ + "Small Molecule" + ], + "organism": [], + "api": false + }, + { + "id": "drugbank", + "name": "DrugBank", + "type": "database", + "url": "https://go.drugbank.com/", + "description": "Database of drugs and targets (University of Alberta).", + "tags": [ + "disease" + ], + "tasks": [], + "modalities": [ + "Disease" + ], + "organism": [], + "api": false + }, + { + "id": "drugcentral", + "name": "DrugCentral", + "type": "database", + "url": "http://drugcentral.org/", + "description": "Online drug compendium with drug mode of action and indication information.", + "tags": [ + "compound" + ], + "tasks": [], + "modalities": [ + "Small Molecule" + ], + "organism": [], + "api": false + }, + { + "id": "drugtargetcommons", + "name": "DrugTargetCommons", + "type": "database", + "url": "https://drugtargetcommons.fimm.fi/", + "description": "Community platform for curating and integrating experimental bioactivity data across drugs and targets.", + "tags": [ + "compound" + ], + "tasks": [], + "modalities": [ + "Small Molecule" + ], + "organism": [], + "api": false + }, + { + "id": "encode", + "name": "ENCODE", + "type": "database", + "url": "https://www.encodeproject.org/", + "description": "Encyclopedia of DNA Elements; regulatory and functional genomic elements across the genome.", + "tags": [ + "genome" + ], + "tasks": [], + "modalities": [ + "Genomics" + ], + "organism": [], + "api": false + }, + { + "id": "ensembl", + "name": "Ensembl", + "type": "database", + "url": "https://www.ensembl.org/", + "description": "Genome browser and annotation database for vertebrate and other eukaryotic genomes.", + "tags": [ + "genome" + ], + "tasks": [], + "modalities": [ + "Genomics" + ], + "organism": [], + "api": false + }, + { + "id": "eu_drug_regulating_authorities_clinical_trials_db_eudract", + "name": "EU Drug Regulating Authorities Clinical Trials DB (EudraCT)", + "type": "database", + "url": "https://eudract.ema.europa.eu/", + "description": "European clinical trial database.", + "tags": [ + "clinical-trial" + ], + "tasks": [], + "modalities": [ + "Clinical" + ], + "organism": [], + "api": false + }, + { + "id": "fantom5", + "name": "FANTOM5", + "type": "database", + "url": "https://fantom.gsc.riken.jp/5/", + "description": "Functional annotation of mammalian genome; comprehensive atlas of active enhancers, promoters, and transcription start sites across human and mouse cell types.", + "tags": [ + "genome" + ], + "tasks": [], + "modalities": [ + "Genomics" + ], + "organism": [], + "api": false + }, + { + "id": "genbank", + "name": "GenBank", + "type": "database", + "url": "https://www.ncbi.nlm.nih.gov/genbank/", + "description": "NCBI's database of genetic sequences.", + "tags": [ + "genome" + ], + "tasks": [], + "modalities": [ + "Genomics" + ], + "organism": [], + "api": false + }, + { + "id": "gene_expression_omnibus", + "name": "Gene Expression Omnibus", + "type": "database", + "url": "https://www.ncbi.nlm.nih.gov/geo/", + "description": "Public functional genomics database.", + "tags": [ + "scrna" + ], + "tasks": [], + "modalities": [ + "Single Cell" + ], + "organism": [], + "api": false + }, + { + "id": "genomics_of_drug_sensitivity_in_cancer_gdsc", + "name": "Genomics of Drug Sensitivity in Cancer (GDSC)", + "type": "database", + "url": "https://www.cancerrxgene.org/", + "description": "Drug sensitivity for ~1000 human cancer cell lines and hundreds of compounds.", + "tags": [ + "benchmarks-and-datasets", + "drug-cell-line-response", + "interaction" + ], + "tasks": [], + "modalities": [ + "Gene Expression", + "Small Molecule" + ], + "organism": [], + "api": false + }, + { + "id": "gnomad", + "name": "gnomAD", + "type": "database", + "url": "https://gnomad.broadinstitute.org/", + "description": "Genome Aggregation Database; genetic variation from large-scale sequencing projects.", + "tags": [ + "genome" + ], + "tasks": [], + "modalities": [ + "Genomics" + ], + "organism": [], + "api": false + }, + { + "id": "hetionet", + "name": "Hetionet", + "type": "database", + "url": "https://github.com/hetio/hetionet", + "description": "Heterogeneous network integrating genes, diseases, drugs, pathways, and more.", + "tags": [ + "interaction", + "knowledge-graph" + ], + "tasks": [], + "modalities": [ + "Knowledge Graph" + ], + "organism": [], + "api": false + }, + { + "id": "hippie", + "name": "HIPPIE", + "type": "database", + "url": "http://cbdm-01.zdv.uni-mainz.de/~mschaefer/hippie/", + "description": "Human protein-protein interaction database.", + "tags": [ + "interaction", + "protein-protein-interaction" + ], + "tasks": [], + "modalities": [ + "Protein" + ], + "organism": [], + "api": false + }, + { + "id": "hmdb_human_metabolome_database", + "name": "HMDB (Human Metabolome Database)", + "type": "database", + "url": "https://hmdb.ca/", + "description": "Comprehensive database of small molecule metabolites found in the human body.", + "tags": [ + "compound" + ], + "tasks": [], + "modalities": [ + "Small Molecule" + ], + "organism": [], + "api": false + }, + { + "id": "human_cell_atlas", + "name": "Human Cell Atlas", + "type": "database", + "url": "https://www.humancellatlas.org/", + "description": "Open global atlas of all cells in the human body.", + "tags": [ + "scrna" + ], + "tasks": [], + "modalities": [ + "Single Cell" + ], + "organism": [], + "api": false + }, + { + "id": "human_genome_resources_at_ncbi", + "name": "Human Genome Resources at NCBI", + "type": "database", + "url": "https://www.ncbi.nlm.nih.gov/projects/genome/guide/human/index.shtml", + "description": "Database for genomics, proteomics, transcriptomics, and systems biology.", + "tags": [ + "genome" + ], + "tasks": [], + "modalities": [ + "Genomics" + ], + "organism": [], + "api": false + }, + { + "id": "human_phenotype_ontology_hpo", + "name": "Human Phenotype Ontology (HPO)", + "type": "database", + "url": "https://hpo.jax.org/", + "description": "Standardized vocabulary of phenotypic abnormalities in human disease, linking genes, variants, and clinical features.", + "tags": [ + "disease" + ], + "tasks": [], + "modalities": [ + "Disease" + ], + "organism": [], + "api": false + }, + { + "id": "icd10", + "name": "ICD10", + "type": "database", + "url": "https://icd.who.int/browse10/2019/en", + "description": "International Classification of Diseases, 10th revision.", + "tags": [ + "clinical-trial" + ], + "tasks": [], + "modalities": [ + "Clinical" + ], + "organism": [], + "api": false + }, + { + "id": "intact", + "name": "IntAct", + "type": "database", + "url": "https://www.ebi.ac.uk/intact/home", + "description": "Open-source molecular interaction database and analysis system from EMBL-EBI.", + "tags": [ + "interaction", + "protein-protein-interaction" + ], + "tasks": [], + "modalities": [ + "Protein" + ], + "organism": [], + "api": false + }, + { + "id": "interpro", + "name": "InterPro", + "type": "database", + "url": "https://www.ebi.ac.uk/interpro/", + "description": "Protein families, domains, and functional sites database integrating 14 member databases including Pfam and PROSITE.", + "tags": [ + "protein" + ], + "tasks": [], + "modalities": [ + "Protein" + ], + "organism": [], + "api": false + }, + { + "id": "jaspar", + "name": "JASPAR", + "type": "database", + "url": "http://jaspar.genereg.net/", + "description": "Database of transcription factor binding profiles.", + "tags": [ + "genome" + ], + "tasks": [], + "modalities": [ + "Genomics" + ], + "organism": [], + "api": false + }, + { + "id": "kegg_compound", + "name": "KEGG COMPOUND", + "type": "database", + "url": "https://www.genome.jp/kegg/compound/", + "description": "Collection of small molecules and biopolymers.", + "tags": [ + "compound" + ], + "tasks": [], + "modalities": [ + "Small Molecule" + ], + "organism": [], + "api": false + }, + { + "id": "kegg_drug", + "name": "KEGG DRUG", + "type": "database", + "url": "https://www.genome.jp/kegg/drug/", + "description": "Comprehensive, approved drug information.", + "tags": [ + "disease" + ], + "tasks": [], + "modalities": [ + "Disease" + ], + "organism": [], + "api": false + }, + { + "id": "kegg_pathway", + "name": "KEGG PATHWAY", + "type": "database", + "url": "https://www.genome.jp/kegg/pathway.html", + "description": "Collection of pathway maps.", + "tags": [ + "pathway" + ], + "tasks": [], + "modalities": [ + "Pathway" + ], + "organism": [], + "api": false + }, + { + "id": "kinase_inhibitor_bioactivity_data_kiba", + "name": "Kinase Inhibitor Bioactivity Data (KIBA)", + "type": "database", + "url": "https://janeliascicomp.github.io/KIBA/", + "description": "Integrated bioactivity scores for kinase inhibitors combining Ki, Kd, and IC50 measurements.", + "tags": [ + "chemical-protein-interaction", + "interaction" + ], + "tasks": [], + "modalities": [ + "Protein", + "Small Molecule" + ], + "organism": [], + "api": false + }, + { + "id": "lipid_maps", + "name": "LIPID MAPS", + "type": "database", + "url": "https://www.lipidmaps.org/databases/lmsd/overview", + "description": "Database of lipids.", + "tags": [ + "compound" + ], + "tasks": [], + "modalities": [ + "Small Molecule" + ], + "organism": [], + "api": false + }, + { + "id": "massbank", + "name": "MassBank", + "type": "database", + "url": "http://www.massbank.jp/", + "description": "Open source databases and tools for mass spectrometry reference spectra.", + "tags": [ + "mass-spectra" + ], + "tasks": [], + "modalities": [ + "Mass Spectra" + ], + "organism": [], + "api": false + }, + { + "id": "mgnify", + "name": "MGnify", + "type": "database", + "url": "https://www.ebi.ac.uk/metagenomics/", + "description": "Resource for metagenomic and metatranscriptomic data.", + "tags": [ + "genome" + ], + "tasks": [], + "modalities": [ + "Genomics" + ], + "organism": [], + "api": false + }, + { + "id": "mimic_iv", + "name": "MIMIC-IV", + "type": "database", + "url": "https://mimic.mit.edu/", + "description": "Freely accessible critical care database.", + "tags": [ + "clinical-trial" + ], + "tasks": [], + "modalities": [ + "Clinical" + ], + "organism": [], + "api": false + }, + { + "id": "mirbase", + "name": "miRBase", + "type": "database", + "url": "https://www.mirbase.org/", + "description": "Reference repository for microRNA gene annotations, sequences, and experimentally validated targets.", + "tags": [ + "gene-regulatory-network", + "interaction" + ], + "tasks": [], + "modalities": [ + "Gene Expression" + ], + "organism": [], + "api": false + }, + { + "id": "mona_massbank_of_north_america", + "name": "MoNA MassBank of North America", + "type": "database", + "url": "https://mona.fiehnlab.ucdavis.edu/", + "description": "Meta-database of metabolite mass spectra, metadata, and associated compounds.", + "tags": [ + "mass-spectra" + ], + "tasks": [], + "modalities": [ + "Mass Spectra" + ], + "organism": [], + "api": false + }, + { + "id": "msigdb_molecular_signatures_database", + "name": "MSigDB (Molecular Signatures Database)", + "type": "database", + "url": "https://www.gsea-msigdb.org/gsea/msigdb", + "description": "Curated gene sets derived from pathways and biological processes.", + "tags": [ + "pathway" + ], + "tasks": [], + "modalities": [ + "Pathway" + ], + "organism": [], + "api": false + }, + { + "id": "nci60", + "name": "NCI60", + "type": "database", + "url": "https://dtp.cancer.gov/discovery_development/nci-60/", + "description": "Focuses on 60 cancer cell lines and many drugs.", + "tags": [ + "benchmarks-and-datasets", + "drug-cell-line-response", + "interaction" + ], + "tasks": [], + "modalities": [ + "Gene Expression", + "Small Molecule" + ], + "organism": [], + "api": false + }, + { + "id": "nextprot", + "name": "NeXtProt", + "type": "database", + "url": "https://www.nextprot.org/", + "description": "Expert knowledge base on human proteins with deep functional annotation, complementary to UniProt.", + "tags": [ + "protein" + ], + "tasks": [], + "modalities": [ + "Protein" + ], + "organism": [], + "api": false + }, + { + "id": "oadb_observed_antibody_space_database", + "name": "OADB (Observed Antibody Space Database)", + "type": "database", + "url": "http://opig.stats.ox.ac.uk/webapps/oas/", + "description": "Database of antibody sequences from immune repertoire sequencing.", + "tags": [ + "protein" + ], + "tasks": [], + "modalities": [ + "Protein" + ], + "organism": [], + "api": false + }, + { + "id": "omim_online_mendelian_inheritance_in_man", + "name": "OMIM (Online Mendelian Inheritance in Man)", + "type": "database", + "url": "https://www.omim.org/", + "description": "Comprehensive database of human genes and genetic disorders.", + "tags": [ + "disease" + ], + "tasks": [], + "modalities": [ + "Disease" + ], + "organism": [], + "api": false + }, + { + "id": "omnipath", + "name": "OmniPath", + "type": "database", + "url": "https://omnipathdb.org/", + "description": "Comprehensive resource integrating protein interactions, signaling pathways, gene regulatory networks, and miRNA targets from over 100 databases.", + "tags": [ + "pathway" + ], + "tasks": [], + "modalities": [ + "Pathway" + ], + "organism": [], + "api": false + }, + { + "id": "open_targets_platform", + "name": "Open Targets Platform", + "type": "database", + "url": "https://platform.opentargets.org/", + "description": "Systematic target identification and prioritization platform integrating genetics, genomics, and drug data for drug discovery.", + "tags": [ + "disease" + ], + "tasks": [], + "modalities": [ + "Disease" + ], + "organism": [], + "api": false + }, + { + "id": "pathwaycommons", + "name": "PathwayCommons", + "type": "database", + "url": "https://www.pathwaycommons.org/", + "description": "Database of pathways and interactions.", + "tags": [ + "pathway" + ], + "tasks": [], + "modalities": [ + "Pathway" + ], + "organism": [], + "api": false + }, + { + "id": "pdbbind", + "name": "PDBBind", + "type": "database", + "url": "https://www.pdbbind-plus.org.cn/", + "description": "Binding affinity data for biomolecular complexes.", + "tags": [ + "chemical-protein-interaction", + "interaction" + ], + "tasks": [], + "modalities": [ + "Protein", + "Small Molecule" + ], + "organism": [], + "api": false + }, + { + "id": "pfam", + "name": "Pfam", + "type": "database", + "url": "https://www.ebi.ac.uk/interpro/entry/pfam/", + "description": "Database of protein families described by multiple sequence alignments and hidden Markov models.", + "tags": [ + "protein" + ], + "tasks": [], + "modalities": [ + "Protein" + ], + "organism": [], + "api": false + }, + { + "id": "primekg", + "name": "PrimeKG", + "type": "database", + "url": "https://github.com/mims-harvard/PrimeKG", + "description": "Multi-modal precision medicine knowledge graph integrating clinical, genetic, and drug data.", + "tags": [ + "interaction", + "knowledge-graph" + ], + "tasks": [], + "modalities": [ + "Knowledge Graph" + ], + "organism": [], + "api": false + }, + { + "id": "protein_data_bank_pdb", + "name": "PROTEIN DATA BANK (PDB)", + "type": "database", + "url": "https://www.rcsb.org/", + "description": "3D structures of proteins, nucleic acids, complexes.", + "tags": [ + "protein" + ], + "tasks": [], + "modalities": [ + "Protein" + ], + "organism": [], + "api": false + }, + { + "id": "pubchem", + "name": "PubChem", + "type": "database", + "url": "https://pubchem.ncbi.nlm.nih.gov/", + "description": "One of the largest chemical databases (compounds, genes, and proteins).", + "tags": [ + "compound" + ], + "tasks": [], + "modalities": [ + "Small Molecule" + ], + "organism": [], + "api": false + }, + { + "id": "rcsb_protein_data_bank", + "name": "RCSB Protein Data Bank", + "type": "database", + "url": "https://www.rcsb.org/", + "description": "Repository for structural data of biological molecules.", + "tags": [ + "protein" + ], + "tasks": [], + "modalities": [ + "Protein" + ], + "organism": [], + "api": false + }, + { + "id": "reactome", + "name": "Reactome", + "type": "database", + "url": "https://reactome.org/", + "description": "Expert-curated, peer-reviewed pathway database with detailed reaction mechanisms.", + "tags": [ + "pathway" + ], + "tasks": [], + "modalities": [ + "Pathway" + ], + "organism": [], + "api": false + }, + { + "id": "regnetwork", + "name": "RegNetwork", + "type": "database", + "url": "http://www.regnetworkweb.org/", + "description": "Database of gene regulatory networks covering transcription factor–target gene and miRNA–gene interaction data across multiple species.", + "tags": [ + "gene-regulatory-network", + "interaction" + ], + "tasks": [], + "modalities": [ + "Gene Expression" + ], + "organism": [], + "api": false + }, + { + "id": "rfam", + "name": "Rfam", + "type": "database", + "url": "https://rfam.org/", + "description": "Database of RNA families with sequence alignments and consensus structures.", + "tags": [ + "genome" + ], + "tasks": [], + "modalities": [ + "Genomics" + ], + "organism": [], + "api": false + }, + { + "id": "rhea", + "name": "Rhea", + "type": "database", + "url": "https://www.rhea-db.org/", + "description": "Database of chemical reactions.", + "tags": [ + "compound" + ], + "tasks": [], + "modalities": [ + "Small Molecule" + ], + "organism": [], + "api": false + }, + { + "id": "roadmap_epigenomics", + "name": "ROADMAP Epigenomics", + "type": "database", + "url": "http://www.roadmapepigenomics.org/", + "description": "Reference epigenome maps for 111 primary human cell types and tissues, including histone modifications, chromatin accessibility, and DNA methylation.", + "tags": [ + "genome" + ], + "tasks": [], + "modalities": [ + "Genomics" + ], + "organism": [], + "api": false + }, + { + "id": "sabdab", + "name": "SAbDab", + "type": "database", + "url": "https://opig.stats.ox.ac.uk/webapps/sabdab-sabpred/sabdab", + "description": "Structural Antibody Database containing all antibody structures in the PDB.", + "tags": [ + "protein" + ], + "tasks": [], + "modalities": [ + "Protein" + ], + "organism": [], + "api": false + }, + { + "id": "signor_2_0", + "name": "SIGNOR 2.0", + "type": "database", + "url": "https://signor.uniroma2.it/", + "description": "Database of causal signaling interactions and pathways, with signed and directed relationships between proteins.", + "tags": [ + "pathway" + ], + "tasks": [], + "modalities": [ + "Pathway" + ], + "organism": [], + "api": false + }, + { + "id": "single_cell_expression_atlas", + "name": "Single Cell Expression Atlas", + "type": "database", + "url": "https://www.ebi.ac.uk/gxa/sc/home", + "description": "Public database for single-cell RNA.", + "tags": [ + "scrna" + ], + "tasks": [], + "modalities": [ + "Single Cell" + ], + "organism": [], + "api": false + }, + { + "id": "single_cell_portal", + "name": "Single Cell PORTAL", + "type": "database", + "url": "https://singlecell.broadinstitute.org/single_cell", + "description": "Public database for single-cell RNA.", + "tags": [ + "scrna" + ], + "tasks": [], + "modalities": [ + "Single Cell" + ], + "organism": [], + "api": false + }, + { + "id": "snap", + "name": "SNAP", + "type": "database", + "url": "https://snap.stanford.edu/biodata/datasets/10002/10002-ChG-Miner.html", + "description": "Dataset of drug-gene interactions.", + "tags": [ + "drug-gene-interaction", + "interaction" + ], + "tasks": [], + "modalities": [ + "Gene", + "Small Molecule" + ], + "organism": [], + "api": false + }, + { + "id": "stitch", + "name": "STITCH", + "type": "database", + "url": "http://stitch.embl.de/", + "description": "Chemical-protein interactions.", + "tags": [ + "chemical-protein-interaction", + "interaction" + ], + "tasks": [], + "modalities": [ + "Protein", + "Small Molecule" + ], + "organism": [], + "api": false + }, + { + "id": "string", + "name": "STRING", + "type": "database", + "url": "https://string-db.org/", + "description": "PPI networks for multiple organisms.", + "tags": [ + "interaction", + "protein-protein-interaction" + ], + "tasks": [], + "modalities": [ + "Protein" + ], + "organism": [], + "api": false + }, + { + "id": "the_genotype_tissue_expression_gtex", + "name": "The Genotype-Tissue Expression (GTEx)", + "type": "database", + "url": "https://gtexportal.org/home/", + "description": "Human gene expression and regulation resource.", + "tags": [ + "genome" + ], + "tasks": [], + "modalities": [ + "Genomics" + ], + "organism": [], + "api": false + }, + { + "id": "the_human_protein_atlas", + "name": "THE HUMAN PROTEIN ATLAS", + "type": "database", + "url": "https://www.proteinatlas.org/", + "description": "Comprehensive human protein database (cells, tissues, organs).", + "tags": [ + "protein" + ], + "tasks": [], + "modalities": [ + "Protein" + ], + "organism": [], + "api": false + }, + { + "id": "therapeutic_target_database", + "name": "Therapeutic Target Database", + "type": "database", + "url": "https://idrblab.net/ttd/full-data-download", + "description": "Drug-target, target-disease, and drug-disease datasets.", + "tags": [ + "compound" + ], + "tasks": [], + "modalities": [ + "Small Molecule" + ], + "organism": [], + "api": false + }, + { + "id": "trrust_v2", + "name": "TRRUST v2", + "type": "database", + "url": "https://www.grnpedia.org/trrust/", + "description": "Manually curated database of human and mouse transcriptional regulatory interactions between transcription factors and their target genes, expanded with literature-derived evidence.", + "tags": [ + "gene-regulatory-network", + "interaction" + ], + "tasks": [], + "modalities": [ + "Gene Expression" + ], + "organism": [], + "api": false + }, + { + "id": "ucsc_genome_browser", + "name": "UCSC Genome Browser", + "type": "database", + "url": "https://genome.ucsc.edu/", + "description": "UCSC's genome browser.", + "tags": [ + "genome" + ], + "tasks": [], + "modalities": [ + "Genomics" + ], + "organism": [], + "api": false + }, + { + "id": "uniclust", + "name": "Uniclust", + "type": "database", + "url": "https://uniclust.mmseqs.com/", + "description": "Clustered protein sequence databases.", + "tags": [ + "protein" + ], + "tasks": [], + "modalities": [ + "Protein" + ], + "organism": [], + "api": false + }, + { + "id": "uniprot", + "name": "UniProt", + "type": "database", + "url": "https://www.uniprot.org/", + "description": "Functional information on proteins.", + "tags": [ + "protein" + ], + "tasks": [], + "modalities": [ + "Protein" + ], + "organism": [], + "api": false + }, + { + "id": "uniref", + "name": "UniRef", + "type": "database", + "url": "https://www.uniprot.org/uniref/", + "description": "Non-redundant sequence database clustering UniProtKB entries at multiple sequence identity thresholds.", + "tags": [ + "protein" + ], + "tasks": [], + "modalities": [ + "Protein" + ], + "organism": [], + "api": false + }, + { + "id": "wikipathways", + "name": "WikiPathways", + "type": "database", + "url": "https://wikipathways.org/", + "description": "Database of biological pathways.", + "tags": [ + "pathway" + ], + "tasks": [], + "modalities": [ + "Pathway" + ], + "organism": [], + "api": false + }, + { + "id": "zinc_ligand_discovery_database", + "name": "ZINC ligand discovery database", + "type": "database", + "url": "https://zinc.docking.org/", + "description": "Free database of commercially-available compounds for virtual screening.", + "tags": [ + "compound" + ], + "tasks": [], + "modalities": [ + "Small Molecule" + ], + "organism": [], + "api": false + }, + { + "id": "ai4chem_chemllm_7b_chat", + "name": "AI4Chem/ChemLLM-7B-Chat", + "type": "model", + "url": "https://huggingface.co/AI4Chem/ChemLLM-7B-Chat", + "description": "LLM for chemical & molecular science.", + "tags": [ + "llm-for-biology" + ], + "tasks": [ + "Language Modeling" + ], + "modalities": [ + "Text" + ], + "organism": [], + "api": false + }, + { + "id": "alphafold3", + "name": "AlphaFold3", + "type": "model", + "url": "https://github.com/google-deepmind/alphafold3", + "description": "Predicts structures of proteins, nucleic acids, small molecules, and their complexes.", + "tags": [ + "foundation-models", + "protein-foundation-models", + "protein-structure-prediction-and-design" + ], + "tasks": [ + "Foundation Model", + "Protein Structure Prediction" + ], + "modalities": [ + "Protein" + ], + "organism": [], + "api": false + }, + { + "id": "ankh", + "name": "Ankh", + "type": "model", + "url": "https://github.com/agemagician/Ankh", + "description": "Efficient protein language model optimized for downstream prediction tasks including secondary structure, localization, and function annotation.", + "tags": [ + "foundation-models", + "pre-trained-embedding", + "protein-foundation-models" + ], + "tasks": [ + "Foundation Model" + ], + "modalities": [ + "Protein" + ], + "organism": [], + "api": false + }, + { + "id": "babel", + "name": "BABEL", + "type": "model", + "url": "https://github.com/wukevin/babel", + "description": "Cross-modality translation model enabling prediction between scRNA-seq and scATAC-seq profiles without requiring paired single-cell measurements.", + "tags": [ + "foundation-models", + "multi-omics-foundation-models", + "single-cell-foundation-models" + ], + "tasks": [ + "Foundation Model" + ], + "modalities": [ + "Multi-Omics", + "Single Cell" + ], + "organism": [], + "api": false + }, + { + "id": "basenji", + "name": "Basenji", + "type": "model", + "url": "https://github.com/calico/basenji", + "description": "Sequential regulatory activity prediction from DNA sequences.", + "tags": [ + "foundation-models", + "genomics-foundation-models" + ], + "tasks": [ + "Foundation Model" + ], + "modalities": [ + "Genomics" + ], + "organism": [], + "api": false + }, + { + "id": "biogpt", + "name": "BioGPT", + "type": "model", + "url": "https://github.com/microsoft/BioGPT", + "description": "LLM for biomedical text generation.", + "tags": [ + "llm-for-biology" + ], + "tasks": [ + "Language Modeling" + ], + "modalities": [ + "Text" + ], + "organism": [], + "api": false + }, + { + "id": "biomedclip", + "name": "BiomedCLIP", + "type": "model", + "url": "https://huggingface.co/microsoft/BiomedCLIP-PubMedBERT_256-vit_g_14", + "description": "CLIP-based vision-language foundation model for biomedical images and text trained on PubMed figure–caption pairs.", + "tags": [ + "foundation-models", + "multi-modal-foundation-models" + ], + "tasks": [ + "Foundation Model" + ], + "modalities": [ + "Multi-Modal" + ], + "organism": [], + "api": false + }, + { + "id": "biomedlm", + "name": "BioMedLM", + "type": "model", + "url": "https://huggingface.co/stanford-crfm/BioMedLM", + "description": "2.7B parameter GPT-2-style language model trained exclusively on biomedical literature from PubMed for biomedical question answering and text generation.", + "tags": [ + "llm-for-biology" + ], + "tasks": [ + "Language Modeling" + ], + "modalities": [ + "Text" + ], + "organism": [], + "api": false + }, + { + "id": "boltz_1", + "name": "Boltz-1", + "type": "model", + "url": "https://github.com/jwohlwend/boltz", + "description": "Open-source all-atom biomolecular structure prediction model for proteins, nucleic acids, small molecules, and their complexes achieving AlphaFold3-level accuracy.", + "tags": [ + "foundation-models", + "protein-foundation-models", + "protein-structure-prediction-and-design" + ], + "tasks": [ + "Foundation Model", + "Protein Structure Prediction" + ], + "modalities": [ + "Protein" + ], + "organism": [], + "api": false + }, + { + "id": "borzoi", + "name": "Borzoi", + "type": "model", + "url": "https://github.com/calico/borzoi", + "description": "Extended successor to Enformer for predicting RNA-seq coverage from long genomic sequence windows (524 kb) with improved resolution.", + "tags": [ + "foundation-models", + "genomics-foundation-models" + ], + "tasks": [ + "Foundation Model" + ], + "modalities": [ + "Genomics" + ], + "organism": [], + "api": false + }, + { + "id": "bulkformer", + "name": "BulkFormer", + "type": "model", + "url": "https://github.com/KangBoming/BulkFormer", + "description": "Foundation model for bulk RNA-seq data; learns general transcriptomic representations.", + "tags": [ + "foundation-models", + "single-cell-foundation-models", + "transcriptomics-foundation-models" + ], + "tasks": [ + "Foundation Model" + ], + "modalities": [ + "Single Cell", + "Transcriptomics" + ], + "organism": [], + "api": false + }, + { + "id": "caduceus", + "name": "Caduceus", + "type": "model", + "url": "https://github.com/kuleshov-group/caduceus", + "description": "Bidirectional equivariant long-range DNA sequence model based on Mamba.", + "tags": [ + "foundation-models", + "genomics-foundation-models" + ], + "tasks": [ + "Foundation Model" + ], + "modalities": [ + "Genomics" + ], + "organism": [], + "api": false + }, + { + "id": "cancerfoundation", + "name": "CancerFoundation", + "type": "model", + "url": "https://github.com/BoevaLab/CancerFoundation", + "description": "Single-cell RNA-seq foundation model trained exclusively on a curated dataset of malignant cells to learn cancer-specific embeddings.", + "tags": [ + "foundation-models", + "single-cell-foundation-models", + "transcriptomics-foundation-models" + ], + "tasks": [ + "Foundation Model" + ], + "modalities": [ + "Single Cell", + "Transcriptomics" + ], + "organism": [], + "api": false + }, + { + "id": "cassia", + "name": "CASSIA", + "type": "model", + "url": "https://github.com/ElliotXie/CASSIA", + "description": "Multi-agent LLM for reference-free, interpretable cell-type annotation of single-cell RNA-seq data, with dedicated annotation, validation, scoring, and reporting agents.", + "tags": [ + "llm-for-biology" + ], + "tasks": [ + "Language Modeling" + ], + "modalities": [ + "Text" + ], + "organism": [], + "api": false + }, + { + "id": "cellplm", + "name": "CellPLM", + "type": "model", + "url": "https://github.com/OmicsML/CellPLM", + "description": "Cell pre-trained language model with inter-cell transformer architecture for diverse single-cell analysis tasks.", + "tags": [ + "foundation-models", + "single-cell-foundation-models", + "transcriptomics-foundation-models" + ], + "tasks": [ + "Foundation Model" + ], + "modalities": [ + "Single Cell", + "Transcriptomics" + ], + "organism": [], + "api": false + }, + { + "id": "chai_1", + "name": "Chai-1", + "type": "model", + "url": "https://github.com/chaidiscovery/chai-lab", + "description": "Unified molecular structure prediction model covering proteins, nucleic acids, small molecules, and complexes.", + "tags": [ + "foundation-models", + "protein-foundation-models", + "protein-structure-prediction-and-design" + ], + "tasks": [ + "Foundation Model", + "Protein Structure Prediction" + ], + "modalities": [ + "Protein" + ], + "organism": [], + "api": false + }, + { + "id": "chatdrug", + "name": "ChatDrug", + "type": "model", + "url": "https://github.com/chao1224/ChatDrug", + "description": "LLM-based conversational pipeline for drug discovery, using natural language prompts for iterative drug editing and optimization.", + "tags": [ + "llm-for-biology" + ], + "tasks": [ + "Language Modeling" + ], + "modalities": [ + "Text" + ], + "organism": [], + "api": false + }, + { + "id": "chemberta_2", + "name": "ChemBERTa-2", + "type": "model", + "url": "https://github.com/seyonechithrananda/bert-loves-chemistry", + "description": "RoBERTa-based molecular language model pretrained on SMILES for small-molecule representation learning.", + "tags": [ + "compound-embedding", + "compound-foundation-models", + "foundation-models" + ], + "tasks": [ + "Foundation Model" + ], + "modalities": [ + "Small Molecule" + ], + "organism": [], + "api": false + }, + { + "id": "chemcpa", + "name": "chemCPA", + "type": "model", + "url": "https://github.com/theislab/chemCPA", + "description": "Compositional perturbation autoencoder for predicting single-cell transcriptional responses to unseen drug perturbations and dose combinations.", + "tags": [ + "drug-discovery", + "drug-response-prediction" + ], + "tasks": [ + "Drug Discovery", + "Drug Response Prediction" + ], + "modalities": [ + "Small Molecule" + ], + "organism": [], + "api": false + }, + { + "id": "chief", + "name": "CHIEF", + "type": "model", + "url": "https://github.com/hms-dbmi/CHIEF", + "description": "Clinical Histopathology Imaging Evaluation Foundation model integrating histology images and clinical context for pan-cancer analysis.", + "tags": [ + "foundation-models", + "multi-modal-foundation-models" + ], + "tasks": [ + "Foundation Model" + ], + "modalities": [ + "Multi-Modal" + ], + "organism": [], + "api": false + }, + { + "id": "clawbio", + "name": "ClawBio", + "type": "model", + "url": "https://github.com/ClawBio/ClawBio", + "description": "Bioinformatics-native AI agent skill library with local-first pharmacogenomics, ancestry PCA, semantic similarity, nutrigenomics, and metagenomics skills.", + "tags": [ + "llm-for-biology" + ], + "tasks": [ + "Language Modeling" + ], + "modalities": [ + "Text" + ], + "organism": [], + "api": false + }, + { + "id": "concerto", + "name": "Concerto", + "type": "model", + "url": "https://github.com/melobio/Concerto-reproducibility", + "description": "Contrastive self-supervised learning framework for single-cell multimodal data integration, batch correction, and reference-query mapping.", + "tags": [ + "foundation-models", + "multi-omics-foundation-models", + "single-cell-foundation-models" + ], + "tasks": [ + "Foundation Model" + ], + "modalities": [ + "Multi-Omics", + "Single Cell" + ], + "organism": [], + "api": false + }, + { + "id": "conch", + "name": "CONCH", + "type": "model", + "url": "https://github.com/mahmoodlab/CONCH", + "description": "Vision-language foundation model for computational pathology trained with contrastive captioning on pathology image–text pairs.", + "tags": [ + "foundation-models", + "single-cell-foundation-models", + "spatial-foundation-models" + ], + "tasks": [ + "Foundation Model" + ], + "modalities": [ + "Single Cell", + "Spatial Transcriptomics" + ], + "organism": [], + "api": false + }, + { + "id": "cyclecdr", + "name": "cycleCDR", + "type": "model", + "url": "https://github.com/hliulab/cycleCDR", + "description": "Interpretable cycle-consistency framework for modeling cellular responses to drug perturbations.", + "tags": [ + "drug-discovery", + "drug-response-prediction" + ], + "tasks": [ + "Drug Discovery", + "Drug Response Prediction" + ], + "modalities": [ + "Small Molecule" + ], + "organism": [], + "api": false + }, + { + "id": "deepaeg", + "name": "DeepAEG", + "type": "model", + "url": "https://github.com/zhejiangzhuque/DeepAEG", + "description": "GNN embedding + attention mechanism.", + "tags": [ + "drug-discovery", + "drug-response-prediction" + ], + "tasks": [ + "Drug Discovery", + "Drug Response Prediction" + ], + "modalities": [ + "Small Molecule" + ], + "organism": [], + "api": false + }, + { + "id": "deepdsc", + "name": "DeepDSC", + "type": "model", + "url": "https://ieeexplore-ieee-org.ezp2.lib.umn.edu/stamp/stamp.jsp?tp=&arnumber=8723620&tag=1", + "description": "Autoencoder + fully connected NN.", + "tags": [ + "drug-discovery", + "drug-response-prediction" + ], + "tasks": [ + "Drug Discovery", + "Drug Response Prediction" + ], + "modalities": [ + "Small Molecule" + ], + "organism": [], + "api": false + }, + { + "id": "deepdta", + "name": "DeepDTA", + "type": "model", + "url": "https://github.com/hkmztrk/DeepDTA", + "description": "Deep learning model using CNNs on protein sequences and drug SMILES.", + "tags": [ + "drug-discovery", + "drug-target-interaction" + ], + "tasks": [ + "Drug Discovery", + "Drug Target Interaction" + ], + "modalities": [ + "Protein", + "Small Molecule" + ], + "organism": [], + "api": false + }, + { + "id": "deeppurpose", + "name": "DeepPurpose", + "type": "model", + "url": "https://github.com/kexinhuang12345/DeepPurpose", + "description": "Deep learning library for drug repurposing.", + "tags": [ + "drug-discovery", + "drug-repurposing" + ], + "tasks": [ + "Drug Discovery", + "Drug Repurposing" + ], + "modalities": [ + "Small Molecule" + ], + "organism": [], + "api": false + }, + { + "id": "deepsea", + "name": "DeepSEA", + "type": "model", + "url": "http://deepsea.princeton.edu/", + "description": "Deep learning framework for predicting chromatin effects of sequence alterations with single-nucleotide sensitivity across thousands of chromatin features.", + "tags": [ + "foundation-models", + "genomics-foundation-models" + ], + "tasks": [ + "Foundation Model" + ], + "modalities": [ + "Genomics" + ], + "organism": [], + "api": false + }, + { + "id": "dgdrp", + "name": "DGDRP", + "type": "model", + "url": "https://github.com/minwoopak/heteronet", + "description": "Multi-view embedding neural network.", + "tags": [ + "drug-discovery", + "drug-response-prediction" + ], + "tasks": [ + "Drug Discovery", + "Drug Response Prediction" + ], + "modalities": [ + "Small Molecule" + ], + "organism": [], + "api": false + }, + { + "id": "diffdock", + "name": "DiffDock", + "type": "model", + "url": "https://github.com/gcorso/DiffDock", + "description": "Diffusion generative model for molecular docking, predicting the binding pose of small molecules to protein targets.", + "tags": [ + "drug-discovery", + "molecular-generation" + ], + "tasks": [ + "Drug Discovery", + "Molecular Generation" + ], + "modalities": [ + "Small Molecule" + ], + "organism": [], + "api": false + }, + { + "id": "diffsbdd", + "name": "DiffSBDD", + "type": "model", + "url": "https://github.com/arneschneuing/DiffSBDD", + "description": "Equivariant diffusion model for structure-based drug design that generates molecules and binding conformations for protein targets.", + "tags": [ + "drug-discovery", + "molecular-generation" + ], + "tasks": [ + "Drug Discovery", + "Molecular Generation" + ], + "modalities": [ + "Small Molecule" + ], + "organism": [], + "api": false + }, + { + "id": "dnabert", + "name": "DNABERT", + "type": "model", + "url": "https://github.com/jerryji1993/DNABERT", + "description": "Pre-trained bidirectional encoder for DNA sequence analysis.", + "tags": [ + "foundation-models", + "genomics-foundation-models" + ], + "tasks": [ + "Foundation Model" + ], + "modalities": [ + "Genomics" + ], + "organism": [], + "api": false + }, + { + "id": "dnabert_2", + "name": "DNABERT-2", + "type": "model", + "url": "https://github.com/Zhihan1996/DNABERT_2", + "description": "Improved genome foundation model with efficient tokenization.", + "tags": [ + "foundation-models", + "genomics-foundation-models" + ], + "tasks": [ + "Foundation Model" + ], + "modalities": [ + "Genomics" + ], + "organism": [], + "api": false + }, + { + "id": "drgat", + "name": "drGAT", + "type": "model", + "url": "https://github.com/inoue0426/drGAT", + "description": "Attention-based model for drug response prediction with gene explainability.", + "tags": [ + "drug-discovery", + "drug-response-prediction" + ], + "tasks": [ + "Drug Discovery", + "Drug Response Prediction" + ], + "modalities": [ + "Small Molecule" + ], + "organism": [], + "api": false + }, + { + "id": "drugban", + "name": "DrugBAN", + "type": "model", + "url": "https://github.com/peizhenbai/DrugBAN", + "description": "Bilinear attention network for interpretable DTI prediction.", + "tags": [ + "drug-discovery", + "drug-target-interaction" + ], + "tasks": [ + "Drug Discovery", + "Drug Target Interaction" + ], + "modalities": [ + "Protein", + "Small Molecule" + ], + "organism": [], + "api": false + }, + { + "id": "druml", + "name": "DRUML", + "type": "model", + "url": "https://github.com/CutillasLab/DRUMLR", + "description": "Ensemble machine learning framework combining standard ML with deep learning to systematically rank anti-cancer drugs from proteomics and RNA-seq data.", + "tags": [ + "drug-discovery", + "drug-response-prediction" + ], + "tasks": [ + "Drug Discovery", + "Drug Response Prediction" + ], + "modalities": [ + "Small Molecule" + ], + "organism": [], + "api": false + }, + { + "id": "dtinet", + "name": "DTINet", + "type": "model", + "url": "https://github.com/luoyunan/DTINet", + "description": "Network-based framework integrating heterogeneous biological data for DTI prediction.", + "tags": [ + "drug-discovery", + "drug-target-interaction" + ], + "tasks": [ + "Drug Discovery", + "Drug Target Interaction" + ], + "modalities": [ + "Protein", + "Small Molecule" + ], + "organism": [], + "api": false + }, + { + "id": "enformer", + "name": "Enformer", + "type": "model", + "url": "https://github.com/deepmind/deepmind-research/tree/master/enformer", + "description": "Transformer model predicting gene expression from DNA sequence.", + "tags": [ + "foundation-models", + "genomics-foundation-models" + ], + "tasks": [ + "Foundation Model" + ], + "modalities": [ + "Genomics" + ], + "organism": [], + "api": false + }, + { + "id": "esm3", + "name": "ESM3", + "type": "model", + "url": "https://github.com/evolutionaryscale/esm", + "description": "Multimodal protein language model that jointly reasons over sequence, structure, and function for generative protein design and engineering.", + "tags": [ + "foundation-models", + "protein-foundation-models", + "protein-structure-prediction-and-design" + ], + "tasks": [ + "Foundation Model", + "Protein Structure Prediction" + ], + "modalities": [ + "Protein" + ], + "organism": [], + "api": false + }, + { + "id": "esmfold", + "name": "ESMFold", + "type": "model", + "url": "https://github.com/facebookresearch/esm", + "description": "Fast protein structure prediction using language model embeddings.", + "tags": [ + "foundation-models", + "protein-foundation-models", + "protein-structure-prediction-and-design" + ], + "tasks": [ + "Foundation Model", + "Protein Structure Prediction" + ], + "modalities": [ + "Protein" + ], + "organism": [], + "api": false + }, + { + "id": "evo", + "name": "Evo", + "type": "model", + "url": "https://github.com/evo-design/evo", + "description": "Long-context genomic foundation model (up to 1M tokens).", + "tags": [ + "foundation-models", + "genomics-foundation-models" + ], + "tasks": [ + "Foundation Model" + ], + "modalities": [ + "Genomics" + ], + "organism": [], + "api": false + }, + { + "id": "evodiff", + "name": "EvoDiff", + "type": "model", + "url": "https://github.com/microsoft/evodiff", + "description": "Discrete diffusion framework for protein sequence generation trained on evolutionary-scale data, supporting unconditional generation, disordered region design, and functional motif scaffolding. [ [paper-2023](https://www.biorxiv.org/content/10.1101/2023.09.11.556673v1) ]", + "tags": [ + "foundation-models", + "protein-foundation-models", + "protein-structure-prediction-and-design" + ], + "tasks": [ + "Foundation Model", + "Protein Structure Prediction" + ], + "modalities": [ + "Protein" + ], + "organism": [], + "api": false + }, + { + "id": "evolutionary_scale_modeling_esm", + "name": "Evolutionary Scale Modeling (ESM)", + "type": "model", + "url": "https://github.com/facebookresearch/esm", + "description": "Protein embeddings.", + "tags": [ + "foundation-models", + "pre-trained-embedding", + "protein-foundation-models" + ], + "tasks": [ + "Foundation Model" + ], + "modalities": [ + "Protein" + ], + "organism": [], + "api": false + }, + { + "id": "gears", + "name": "GEARS", + "type": "model", + "url": "https://github.com/snap-stanford/GEARS", + "description": "Graph-based model for predicting transcriptional responses to single and combinatorial genetic perturbations using biological priors.", + "tags": [ + "foundation-models", + "single-cell-foundation-models", + "transcriptomics-foundation-models" + ], + "tasks": [ + "Foundation Model" + ], + "modalities": [ + "Single Cell", + "Transcriptomics" + ], + "organism": [], + "api": false + }, + { + "id": "genecompass", + "name": "GeneCompass", + "type": "model", + "url": "https://github.com/xCompass-AI/GeneCompass", + "description": "Large-scale foundation model integrating DNA regulatory sequences and single-cell transcriptomics from 120M+ cells across multiple species for gene regulation prediction.", + "tags": [ + "foundation-models", + "multi-omics-foundation-models", + "single-cell-foundation-models" + ], + "tasks": [ + "Foundation Model" + ], + "modalities": [ + "Multi-Omics", + "Single Cell" + ], + "organism": [], + "api": false + }, + { + "id": "geneformer", + "name": "Geneformer", + "type": "model", + "url": "https://huggingface.co/ctheodoris/Geneformer", + "description": "Context-aware, attention-based deep learning model pretrained on a large corpus of single-cell transcriptomes.", + "tags": [ + "foundation-models", + "single-cell-foundation-models", + "transcriptomics-foundation-models" + ], + "tasks": [ + "Foundation Model" + ], + "modalities": [ + "Single Cell", + "Transcriptomics" + ], + "organism": [], + "api": false + }, + { + "id": "genegpt", + "name": "GeneGPT", + "type": "model", + "url": "https://github.com/ncbi/GeneGPT", + "description": "LLM for biomedical information, integrated with various APIs.", + "tags": [ + "llm-for-biology" + ], + "tasks": [ + "Language Modeling" + ], + "modalities": [ + "Text" + ], + "organism": [], + "api": false + }, + { + "id": "genept", + "name": "GenePT", + "type": "model", + "url": "https://github.com/yiqunchen/GenePT", + "description": "Foundation LLM for single-cell data.", + "tags": [ + "llm-for-biology" + ], + "tasks": [ + "Language Modeling" + ], + "modalities": [ + "Text" + ], + "organism": [], + "api": false + }, + { + "id": "gigapath", + "name": "GigaPath", + "type": "model", + "url": "https://github.com/prov-gigapath/prov-gigapath", + "description": "Slide-level digital pathology foundation model pretrained on 1.3 billion pathology image tokens from whole-slide images.", + "tags": [ + "foundation-models", + "single-cell-foundation-models", + "spatial-foundation-models" + ], + "tasks": [ + "Foundation Model" + ], + "modalities": [ + "Single Cell", + "Spatial Transcriptomics" + ], + "organism": [], + "api": false + }, + { + "id": "glue", + "name": "GLUE", + "type": "model", + "url": "https://github.com/gao-lab/GLUE", + "description": "Graph-Linked Unified Embedding framework for unpaired single-cell multi-omics data integration across RNA, ATAC, methylation, and protein modalities.", + "tags": [ + "foundation-models", + "multi-omics-foundation-models", + "single-cell-foundation-models" + ], + "tasks": [ + "Foundation Model" + ], + "modalities": [ + "Multi-Omics", + "Single Cell" + ], + "organism": [], + "api": false + }, + { + "id": "gpn_genomic_pre_trained_network", + "name": "GPN (Genomic Pre-trained Network)", + "type": "model", + "url": "https://github.com/songlab-cal/gpn", + "description": "Masked language model for DNA sequences enabling zero-shot variant effect prediction without requiring functional annotations.", + "tags": [ + "foundation-models", + "genomics-foundation-models" + ], + "tasks": [ + "Foundation Model" + ], + "modalities": [ + "Genomics" + ], + "organism": [], + "api": false + }, + { + "id": "graphdta", + "name": "GraphDTA", + "type": "model", + "url": "https://github.com/thinng/GraphDTA", + "description": "Graph neural network–based DTI prediction using molecular graphs.", + "tags": [ + "drug-discovery", + "drug-target-interaction" + ], + "tasks": [ + "Drug Discovery", + "Drug Target Interaction" + ], + "modalities": [ + "Protein", + "Small Molecule" + ], + "organism": [], + "api": false + }, + { + "id": "grover", + "name": "GROVER", + "type": "model", + "url": "https://github.com/tencent-ailab/grover", + "description": "Self-supervised graph transformer for large-scale molecular representation learning from unlabeled compounds.", + "tags": [ + "compound-embedding", + "compound-foundation-models", + "foundation-models" + ], + "tasks": [ + "Foundation Model" + ], + "modalities": [ + "Small Molecule" + ], + "organism": [], + "api": false + }, + { + "id": "hidra", + "name": "HiDRA", + "type": "model", + "url": "https://github.com/bsml320/HiDRA", + "description": "Hierarchical network model incorporating gene and pathway-level information for cancer drug response prediction.", + "tags": [ + "drug-discovery", + "drug-response-prediction" + ], + "tasks": [ + "Drug Discovery", + "Drug Response Prediction" + ], + "modalities": [ + "Small Molecule" + ], + "organism": [], + "api": false + }, + { + "id": "hyenadna", + "name": "HyenaDNA", + "type": "model", + "url": "https://github.com/HazyResearch/hyena-dna", + "description": "Long-range genomic foundation model handling sequences up to 1M tokens with sub-quadratic attention.", + "tags": [ + "foundation-models", + "genomics-foundation-models" + ], + "tasks": [ + "Foundation Model" + ], + "modalities": [ + "Genomics" + ], + "organism": [], + "api": false + }, + { + "id": "jamie", + "name": "JAMIE", + "type": "model", + "url": "https://github.com/Oafish1/JAMIE", + "description": "Joint variational autoencoder for multimodal single-cell data imputation and embedding.", + "tags": [ + "foundation-models", + "multi-omics-foundation-models", + "single-cell-foundation-models" + ], + "tasks": [ + "Foundation Model" + ], + "modalities": [ + "Multi-Omics", + "Single Cell" + ], + "organism": [], + "api": false + }, + { + "id": "jtvae", + "name": "JTVAE", + "type": "model", + "url": "https://github.com/wengong-jin/icml18-jtnn", + "description": "Junction tree variational autoencoder for molecular graph generation that guarantees chemical validity via a hierarchical tree decomposition.", + "tags": [ + "drug-discovery", + "molecular-generation" + ], + "tasks": [ + "Drug Discovery", + "Molecular Generation" + ], + "modalities": [ + "Small Molecule" + ], + "organism": [], + "api": false + }, + { + "id": "matcha", + "name": "Matcha", + "type": "model", + "url": "https://github.com/LigandPro/Matcha", + "description": "Multi-stage Riemannian flow matching model for physically valid molecular docking with scoring, pose filtering, and benchmarks.", + "tags": [ + "drug-discovery", + "molecular-generation" + ], + "tasks": [ + "Drug Discovery", + "Molecular Generation" + ], + "modalities": [ + "Small Molecule" + ], + "organism": [], + "api": false + }, + { + "id": "mcpinn", + "name": "MCPINN", + "type": "model", + "url": "https://github.com/mhlee0903/multi_channels_PINN", + "description": "Drug discovery via compound-protein interaction and machine learning.", + "tags": [ + "compound-protein-interaction", + "drug-discovery" + ], + "tasks": [ + "Compound-Protein Interaction", + "Drug Discovery" + ], + "modalities": [ + "Protein", + "Small Molecule" + ], + "organism": [], + "api": false + }, + { + "id": "midas", + "name": "MIDAS", + "type": "model", + "url": "https://github.com/labomics/midas", + "description": "Mosaic integration and differential accessibility model for single-cell multi-omics data that handles arbitrary missing-modality combinations across transcriptomics, chromatin accessibility, and proteomics.", + "tags": [ + "foundation-models", + "multi-omics-foundation-models", + "single-cell-foundation-models" + ], + "tasks": [ + "Foundation Model" + ], + "modalities": [ + "Multi-Omics", + "Single Cell" + ], + "organism": [], + "api": false + }, + { + "id": "mira", + "name": "MIRA", + "type": "model", + "url": "https://github.com/cistrome/MIRA", + "description": "Probabilistic multimodal topic model jointly modeling single-cell transcriptomics and chromatin accessibility for regulatory network inference.", + "tags": [ + "foundation-models", + "multi-omics-foundation-models", + "single-cell-foundation-models" + ], + "tasks": [ + "Foundation Model" + ], + "modalities": [ + "Multi-Omics", + "Single Cell" + ], + "organism": [], + "api": false + }, + { + "id": "mofa", + "name": "MOFA+", + "type": "model", + "url": "https://github.com/bioFAM/MOFA2", + "description": "Multi-Omics Factor Analysis framework identifying shared axes of variation across bulk and single-cell datasets including RNA, ATAC, proteomics, methylation, and copy number.", + "tags": [ + "foundation-models", + "multi-omics-foundation-models", + "single-cell-foundation-models" + ], + "tasks": [ + "Foundation Model" + ], + "modalities": [ + "Multi-Omics", + "Single Cell" + ], + "organism": [], + "api": false + }, + { + "id": "mofgcn", + "name": "MOFGCN", + "type": "model", + "url": "https://github.com/weiba/MOFGCN/tree/main", + "description": "GCN + heterogeneous network.", + "tags": [ + "drug-discovery", + "drug-response-prediction" + ], + "tasks": [ + "Drug Discovery", + "Drug Response Prediction" + ], + "modalities": [ + "Small Molecule" + ], + "organism": [], + "api": false + }, + { + "id": "mol2vec", + "name": "Mol2Vec", + "type": "model", + "url": "https://github.com/samoturk/mol2vec", + "description": "Unsupervised molecular embedding method inspired by Word2Vec for learning vector representations of chemical substructures.", + "tags": [ + "compound-embedding", + "compound-foundation-models", + "foundation-models" + ], + "tasks": [ + "Foundation Model" + ], + "modalities": [ + "Small Molecule" + ], + "organism": [], + "api": false + }, + { + "id": "molecular_transformer", + "name": "Molecular Transformer", + "type": "model", + "url": "https://github.com/pschwllr/MolecularTransformer", + "description": "Sequence-to-sequence model for retrosynthesis prediction.", + "tags": [ + "drug-discovery", + "molecular-generation" + ], + "tasks": [ + "Drug Discovery", + "Molecular Generation" + ], + "modalities": [ + "Small Molecule" + ], + "organism": [], + "api": false + }, + { + "id": "molformer", + "name": "MolFormer", + "type": "model", + "url": "https://github.com/IBM/molformer", + "description": "Linear attention transformer pretrained on millions of SMILES strings for efficient molecular embeddings.", + "tags": [ + "compound-embedding", + "compound-foundation-models", + "foundation-models" + ], + "tasks": [ + "Foundation Model" + ], + "modalities": [ + "Small Molecule" + ], + "organism": [], + "api": false + }, + { + "id": "molgpt", + "name": "MolGPT", + "type": "model", + "url": "https://github.com/devalab/molgpt", + "description": "Transformer-based model for molecular generation.", + "tags": [ + "drug-discovery", + "molecular-generation" + ], + "tasks": [ + "Drug Discovery", + "Molecular Generation" + ], + "modalities": [ + "Small Molecule" + ], + "organism": [], + "api": false + }, + { + "id": "molt5", + "name": "MolT5", + "type": "model", + "url": "https://github.com/blender-nlp/MolT5", + "description": "Language model for molecular tasks bridging text and SMILES, enabling molecule captioning and text-driven molecule generation.", + "tags": [ + "llm-for-biology" + ], + "tasks": [ + "Language Modeling" + ], + "modalities": [ + "Text" + ], + "organism": [], + "api": false + }, + { + "id": "moltrans", + "name": "MolTrans", + "type": "model", + "url": "https://github.com/kexinhuang12345/MolTrans", + "description": "Transformer-based DTI model leveraging molecular substructures.", + "tags": [ + "drug-discovery", + "drug-target-interaction" + ], + "tasks": [ + "Drug Discovery", + "Drug Target Interaction" + ], + "modalities": [ + "Protein", + "Small Molecule" + ], + "organism": [], + "api": false + }, + { + "id": "multigrate", + "name": "Multigrate", + "type": "model", + "url": "https://github.com/theislab/multigrate", + "description": "Asymmetric multi-omics variational autoencoder for integrating single-cell data across RNA, ATAC, and protein modalities with missing-modality support.", + "tags": [ + "foundation-models", + "multi-omics-foundation-models", + "single-cell-foundation-models" + ], + "tasks": [ + "Foundation Model" + ], + "modalities": [ + "Multi-Omics", + "Single Cell" + ], + "organism": [], + "api": false + }, + { + "id": "multivi", + "name": "MultiVI", + "type": "model", + "url": "https://github.com/scverse/scvi-tools", + "description": "Multi-modal variational autoencoder for integrating paired and unpaired single-cell RNA-seq and ATAC-seq measurements into a unified latent space.", + "tags": [ + "foundation-models", + "multi-omics-foundation-models", + "single-cell-foundation-models" + ], + "tasks": [ + "Foundation Model" + ], + "modalities": [ + "Multi-Omics", + "Single Cell" + ], + "organism": [], + "api": false + }, + { + "id": "musk", + "name": "MUSK", + "type": "model", + "url": "https://github.com/lilab-stanford/MUSK", + "description": "Vision-language foundation model for precision oncology analyzing multimodal paired text and pathology image data for biomarker prediction and retrieval.", + "tags": [ + "foundation-models", + "multi-modal-foundation-models" + ], + "tasks": [ + "Foundation Model" + ], + "modalities": [ + "Multi-Modal" + ], + "organism": [], + "api": false + }, + { + "id": "neodti", + "name": "NeoDTI", + "type": "model", + "url": "https://github.com/FangpingWan/NeoDTI", + "description": "Library for drug-target interaction prediction.", + "tags": [ + "drug-discovery", + "drug-target-interaction" + ], + "tasks": [ + "Drug Discovery", + "Drug Target Interaction" + ], + "modalities": [ + "Protein", + "Small Molecule" + ], + "organism": [], + "api": false + }, + { + "id": "nicheformer", + "name": "Nicheformer", + "type": "model", + "url": "https://github.com/theislab/nicheformer", + "description": "Foundation model for single-cell and spatial omics using a transformer architecture with positional embeddings to encode spatial cell information.", + "tags": [ + "foundation-models", + "single-cell-foundation-models", + "spatial-foundation-models" + ], + "tasks": [ + "Foundation Model" + ], + "modalities": [ + "Single Cell", + "Spatial Transcriptomics" + ], + "organism": [], + "api": false + }, + { + "id": "nucleotide_transformer", + "name": "Nucleotide Transformer", + "type": "model", + "url": "https://github.com/instadeepai/nucleotide-transformer", + "description": "Foundation model for genomic sequences across multiple species.", + "tags": [ + "foundation-models", + "genomics-foundation-models" + ], + "tasks": [ + "Foundation Model" + ], + "modalities": [ + "Genomics" + ], + "organism": [], + "api": false + }, + { + "id": "omegafold", + "name": "OmegaFold", + "type": "model", + "url": "https://github.com/HeliXonProtein/OmegaFold", + "description": "High-resolution de novo protein structure prediction from sequence.", + "tags": [ + "foundation-models", + "protein-foundation-models", + "protein-structure-prediction-and-design" + ], + "tasks": [ + "Foundation Model", + "Protein Structure Prediction" + ], + "modalities": [ + "Protein" + ], + "organism": [], + "api": false + }, + { + "id": "openfold", + "name": "OpenFold", + "type": "model", + "url": "https://github.com/aqlaboratory/openfold", + "description": "Trainable, memory-efficient open-source reproduction of AlphaFold2 enabling custom protein structure prediction workflows.", + "tags": [ + "foundation-models", + "protein-foundation-models", + "protein-structure-prediction-and-design" + ], + "tasks": [ + "Foundation Model", + "Protein Structure Prediction" + ], + "modalities": [ + "Protein" + ], + "organism": [], + "api": false + }, + { + "id": "paccmannrl", + "name": "PaccMannRL", + "type": "model", + "url": "https://github.com/PaccMann/paccmann_generator", + "description": "Reinforcement learning-based generative model for de novo hit-like anticancer molecule design from transcriptomic data.", + "tags": [ + "drug-discovery", + "molecular-generation" + ], + "tasks": [ + "Drug Discovery", + "Molecular Generation" + ], + "modalities": [ + "Small Molecule" + ], + "organism": [], + "api": false + }, + { + "id": "pathomicfusion", + "name": "PathomicFusion", + "type": "model", + "url": "https://github.com/mahmoodlab/PathomicFusion", + "description": "Integrated framework fusing histopathology and genomic features via CNN, GNN, and attention gating for cancer diagnosis and prognosis.", + "tags": [ + "foundation-models", + "multi-modal-foundation-models" + ], + "tasks": [ + "Foundation Model" + ], + "modalities": [ + "Multi-Modal" + ], + "organism": [], + "api": false + }, + { + "id": "phikon", + "name": "Phikon", + "type": "model", + "url": "https://huggingface.co/owkin/phikon", + "description": "ViT-based pathology foundation model pretrained with iBOT self-supervision on TCGA whole-slide images.", + "tags": [ + "foundation-models", + "single-cell-foundation-models", + "spatial-foundation-models" + ], + "tasks": [ + "Foundation Model" + ], + "modalities": [ + "Single Cell", + "Spatial Transcriptomics" + ], + "organism": [], + "api": false + }, + { + "id": "plip", + "name": "PLIP", + "type": "model", + "url": "https://github.com/PathologyFoundation/plip", + "description": "Vision-language foundation model for pathology trained with contrastive learning on pathology image–text pairs for image classification and text-to-image retrieval.", + "tags": [ + "foundation-models", + "multi-modal-foundation-models" + ], + "tasks": [ + "Foundation Model" + ], + "modalities": [ + "Multi-Modal" + ], + "organism": [], + "api": false + }, + { + "id": "porpoise", + "name": "PORPOISE", + "type": "model", + "url": "https://github.com/mahmoodlab/PORPOISE", + "description": "Pan-cancer integrative histology-genomic analysis framework using multimodal deep learning for patient stratification.", + "tags": [ + "foundation-models", + "multi-modal-foundation-models" + ], + "tasks": [ + "Foundation Model" + ], + "modalities": [ + "Multi-Modal" + ], + "organism": [], + "api": false + }, + { + "id": "prnet", + "name": "PRNet", + "type": "model", + "url": "https://github.com/Perturbation-Response-Prediction/PRnet", + "description": "Deep generative model for predicting transcriptional responses to novel chemical perturbations for drug discovery.", + "tags": [ + "drug-discovery", + "drug-response-prediction" + ], + "tasks": [ + "Drug Discovery", + "Drug Response Prediction" + ], + "modalities": [ + "Small Molecule" + ], + "organism": [], + "api": false + }, + { + "id": "progen2", + "name": "ProGen2", + "type": "model", + "url": "https://github.com/salesforce/progen", + "description": "Protein language model trained on diverse protein families for sequence generation and fitness prediction.", + "tags": [ + "foundation-models", + "pre-trained-embedding", + "protein-foundation-models" + ], + "tasks": [ + "Foundation Model" + ], + "modalities": [ + "Protein" + ], + "organism": [], + "api": false + }, + { + "id": "proteinmpnn", + "name": "ProteinMPNN", + "type": "model", + "url": "https://github.com/dauparas/ProteinMPNN", + "description": "Deep learning model for protein sequence design given backbone structure.", + "tags": [ + "foundation-models", + "protein-foundation-models", + "protein-structure-prediction-and-design" + ], + "tasks": [ + "Foundation Model", + "Protein Structure Prediction" + ], + "modalities": [ + "Protein" + ], + "organism": [], + "api": false + }, + { + "id": "prottrans", + "name": "ProtTrans", + "type": "model", + "url": "https://github.com/agemagician/ProtTrans", + "description": "Suite of protein language models (ProtBERT, ProtT5, ProtXLNet) trained on billions of protein sequences from UniRef and BFD.", + "tags": [ + "foundation-models", + "pre-trained-embedding", + "protein-foundation-models" + ], + "tasks": [ + "Foundation Model" + ], + "modalities": [ + "Protein" + ], + "organism": [], + "api": false + }, + { + "id": "recover", + "name": "RECOVER", + "type": "model", + "url": "https://github.com/RECOVERcoalition/Recover", + "description": "Machine learning framework for predicting synergistic drug combination responses across cell lines.", + "tags": [ + "drug-discovery", + "drug-response-prediction" + ], + "tasks": [ + "Drug Discovery", + "Drug Response Prediction" + ], + "modalities": [ + "Small Molecule" + ], + "organism": [], + "api": false + }, + { + "id": "reinvent", + "name": "REINVENT", + "type": "model", + "url": "https://github.com/MolecularAI/Reinvent", + "description": "Reinforcement learning for de novo drug design.", + "tags": [ + "drug-discovery", + "molecular-generation" + ], + "tasks": [ + "Drug Discovery", + "Molecular Generation" + ], + "modalities": [ + "Small Molecule" + ], + "organism": [], + "api": false + }, + { + "id": "release", + "name": "ReLeaSE", + "type": "model", + "url": "https://github.com/isayev/ReLeaSE", + "description": "Deep reinforcement learning framework for de novo drug design combining a generative and predictive model.", + "tags": [ + "drug-discovery", + "molecular-generation" + ], + "tasks": [ + "Drug Discovery", + "Molecular Generation" + ], + "modalities": [ + "Small Molecule" + ], + "organism": [], + "api": false + }, + { + "id": "rfdiffusion", + "name": "RFdiffusion", + "type": "model", + "url": "https://github.com/RosettaCommons/RFdiffusion", + "description": "Generative model for protein backbone design using diffusion.", + "tags": [ + "foundation-models", + "protein-foundation-models", + "protein-structure-prediction-and-design" + ], + "tasks": [ + "Foundation Model", + "Protein Structure Prediction" + ], + "modalities": [ + "Protein" + ], + "organism": [], + "api": false + }, + { + "id": "rosettafold", + "name": "RoseTTAFold", + "type": "model", + "url": "https://github.com/RosettaCommons/RoseTTAFold", + "description": "Three-track neural network for protein structure prediction.", + "tags": [ + "foundation-models", + "protein-foundation-models", + "protein-structure-prediction-and-design" + ], + "tasks": [ + "Foundation Model", + "Protein Structure Prediction" + ], + "modalities": [ + "Protein" + ], + "organism": [], + "api": false + }, + { + "id": "saprot", + "name": "SaProt", + "type": "model", + "url": "https://github.com/westlake-reup/SaProt", + "description": "Structure-aware protein language model using structure-aware tokens that encode both sequence and backbone geometry for improved function prediction.", + "tags": [ + "foundation-models", + "protein-foundation-models", + "protein-structure-prediction-and-design" + ], + "tasks": [ + "Foundation Model", + "Protein Structure Prediction" + ], + "modalities": [ + "Protein" + ], + "organism": [], + "api": false + }, + { + "id": "saturn", + "name": "SATURN", + "type": "model", + "url": "https://github.com/snap-stanford/SATURN", + "description": "Transformer-based model integrating gene expression and protein sequences via a protein language model to learn unified multi-species cell embeddings.", + "tags": [ + "foundation-models", + "single-cell-foundation-models", + "transcriptomics-foundation-models" + ], + "tasks": [ + "Foundation Model" + ], + "modalities": [ + "Single Cell", + "Transcriptomics" + ], + "organism": [], + "api": false + }, + { + "id": "scarches", + "name": "scArches", + "type": "model", + "url": "https://github.com/theislab/scarches", + "description": "Transfer learning framework for mapping new single-cell datasets onto pre-trained reference atlases across batches, conditions, and modalities.", + "tags": [ + "domain-alignment", + "foundation-models", + "single-cell-foundation-models" + ], + "tasks": [ + "Domain Alignment", + "Foundation Model" + ], + "modalities": [ + "Single Cell" + ], + "organism": [], + "api": false + }, + { + "id": "scbert", + "name": "scBERT", + "type": "model", + "url": "https://github.com/TencentAILabHealthcare/scBERT", + "description": "BERT-based foundation model pretrained on large-scale scRNA-seq data for cell type annotation.", + "tags": [ + "foundation-models", + "single-cell-foundation-models", + "transcriptomics-foundation-models" + ], + "tasks": [ + "Foundation Model" + ], + "modalities": [ + "Single Cell", + "Transcriptomics" + ], + "organism": [], + "api": false + }, + { + "id": "scbutterfly", + "name": "scButterfly", + "type": "model", + "url": "https://github.com/BioX-NKU/scButterfly", + "description": "Dual-aligned variational autoencoder for single-cell cross-modality translation between paired and unpaired multiomics data.", + "tags": [ + "foundation-models", + "multi-omics-foundation-models", + "single-cell-foundation-models" + ], + "tasks": [ + "Foundation Model" + ], + "modalities": [ + "Multi-Omics", + "Single Cell" + ], + "organism": [], + "api": false + }, + { + "id": "scfoundation", + "name": "scFoundation", + "type": "model", + "url": "https://github.com/biomap-research/scFoundation", + "description": "Large-scale foundation model for single-cell gene expression, enabling multiple downstream tasks.", + "tags": [ + "foundation-models", + "single-cell-foundation-models", + "transcriptomics-foundation-models" + ], + "tasks": [ + "Foundation Model" + ], + "modalities": [ + "Single Cell", + "Transcriptomics" + ], + "organism": [], + "api": false + }, + { + "id": "scgpt", + "name": "scGPT", + "type": "model", + "url": "https://github.com/bowang-lab/scGPT", + "description": "Transformer-based foundation model pretrained on millions of single-cell profiles.", + "tags": [ + "foundation-models", + "single-cell-foundation-models", + "transcriptomics-foundation-models" + ], + "tasks": [ + "Foundation Model" + ], + "modalities": [ + "Single Cell", + "Transcriptomics" + ], + "organism": [], + "api": false + }, + { + "id": "scgpt_spatial", + "name": "scGPT-spatial", + "type": "model", + "url": "https://github.com/bowang-lab/scGPT-spatial", + "description": "Extension of scGPT for spatial transcriptomics with continual pretraining and a mixture-of-experts decoder for spatial gene expression analysis.", + "tags": [ + "foundation-models", + "single-cell-foundation-models", + "spatial-foundation-models" + ], + "tasks": [ + "Foundation Model" + ], + "modalities": [ + "Single Cell", + "Spatial Transcriptomics" + ], + "organism": [], + "api": false + }, + { + "id": "scmulan", + "name": "scMulan", + "type": "model", + "url": "https://github.com/SuperBianC/scMulan", + "description": "Single-cell multi-omic language model pretrained on ~10M cells spanning transcriptomics, epigenomics, and proteomics for cross-omics transfer tasks.", + "tags": [ + "foundation-models", + "multi-omics-foundation-models", + "single-cell-foundation-models" + ], + "tasks": [ + "Foundation Model" + ], + "modalities": [ + "Multi-Omics", + "Single Cell" + ], + "organism": [], + "api": false + }, + { + "id": "scpair", + "name": "scPair", + "type": "model", + "url": "https://github.com/quon-titative-biology/scPair", + "description": "Bidirectional feedforward network for single-cell multimodal analysis with cross-modality prediction leveraging single-cell atlases.", + "tags": [ + "foundation-models", + "multi-omics-foundation-models", + "single-cell-foundation-models" + ], + "tasks": [ + "Foundation Model" + ], + "modalities": [ + "Multi-Omics", + "Single Cell" + ], + "organism": [], + "api": false + }, + { + "id": "scprint", + "name": "scPRINT", + "type": "model", + "url": "https://github.com/cantinilab/scPRINT", + "description": "Pretrained on 50M cells for scRNA-seq denoising & zero imputation.", + "tags": [ + "llm-for-biology" + ], + "tasks": [ + "Language Modeling" + ], + "modalities": [ + "Text" + ], + "organism": [], + "api": false + }, + { + "id": "sei", + "name": "Sei", + "type": "model", + "url": "https://github.com/FunctionLab/sei-framework", + "description": "Sequence-to-function framework learning a genome-wide regulatory activity code from DNA sequences for variant effect prediction.", + "tags": [ + "foundation-models", + "genomics-foundation-models" + ], + "tasks": [ + "Foundation Model" + ], + "modalities": [ + "Genomics" + ], + "organism": [], + "api": false + }, + { + "id": "spatialglue", + "name": "SpatialGlue", + "type": "model", + "url": "https://github.com/zhanglabtools/SpatialGlue", + "description": "Graph attention network for spatial multi-omics integration jointly embedding spatial transcriptomics with chromatin accessibility or proteomics.", + "tags": [ + "foundation-models", + "multi-omics-foundation-models", + "single-cell-foundation-models" + ], + "tasks": [ + "Foundation Model" + ], + "modalities": [ + "Multi-Omics", + "Single Cell" + ], + "organism": [], + "api": false + }, + { + "id": "targetdiff", + "name": "TargetDiff", + "type": "model", + "url": "https://github.com/guanjq/targetdiff", + "description": "3D equivariant diffusion model for structure-based drug design.", + "tags": [ + "drug-discovery", + "molecular-generation" + ], + "tasks": [ + "Drug Discovery", + "Molecular Generation" + ], + "modalities": [ + "Small Molecule" + ], + "organism": [], + "api": false + }, + { + "id": "tgsa", + "name": "TGSA", + "type": "model", + "url": "https://github.com/violet-sto/TGSA", + "description": "Tumor gene set and attention-based model leveraging biological pathway knowledge for drug response prediction.", + "tags": [ + "drug-discovery", + "drug-response-prediction" + ], + "tasks": [ + "Drug Discovery", + "Drug Response Prediction" + ], + "modalities": [ + "Small Molecule" + ], + "organism": [], + "api": false + }, + { + "id": "toad", + "name": "TOAD", + "type": "model", + "url": "https://github.com/mahmoodlab/TOAD", + "description": "Tumor Origin Assessment via Deep-learning; weakly-supervised multi-task model predicting cancer primary origin from H&E whole-slide images.", + "tags": [ + "foundation-models", + "multi-modal-foundation-models" + ], + "tasks": [ + "Foundation Model" + ], + "modalities": [ + "Multi-Modal" + ], + "organism": [], + "api": false + }, + { + "id": "tosica", + "name": "TOSICA", + "type": "model", + "url": "https://github.com/JackieHanlaopo/TOSICA", + "description": "Transformer-based framework for one-stop interpretable cell-type annotation supporting cross-dataset and cross-species transfer.", + "tags": [ + "domain-alignment", + "foundation-models", + "single-cell-foundation-models" + ], + "tasks": [ + "Domain Alignment", + "Foundation Model" + ], + "modalities": [ + "Single Cell" + ], + "organism": [], + "api": false + }, + { + "id": "totalvi", + "name": "totalVI", + "type": "model", + "url": "https://github.com/scverse/scvi-tools", + "description": "Probabilistic framework for joint analysis of paired scRNA-seq and protein (CITE-seq) data enabling multi-modal cell state representation across single-cell datasets.", + "tags": [ + "foundation-models", + "multi-omics-foundation-models", + "single-cell-foundation-models" + ], + "tasks": [ + "Foundation Model" + ], + "modalities": [ + "Multi-Omics", + "Single Cell" + ], + "organism": [], + "api": false + }, + { + "id": "transformercpi", + "name": "TransformerCPI", + "type": "model", + "url": "https://github.com/lifanchen-simm/transformerCPI", + "description": "CPI prediction using Transformer.", + "tags": [ + "compound-protein-interaction", + "drug-discovery" + ], + "tasks": [ + "Compound-Protein Interaction", + "Drug Discovery" + ], + "modalities": [ + "Protein", + "Small Molecule" + ], + "organism": [], + "api": false + }, + { + "id": "transigen", + "name": "TranSiGen", + "type": "model", + "url": "https://github.com/myzhengSIMM/TranSiGen", + "description": "Dual-VAE architecture for ligand-based virtual screening, drug response prediction, and drug repurposing using chemical-induced transcriptional profiles.", + "tags": [ + "drug-discovery", + "drug-repurposing" + ], + "tasks": [ + "Drug Discovery", + "Drug Repurposing" + ], + "modalities": [ + "Small Molecule" + ], + "organism": [], + "api": false + }, + { + "id": "uce", + "name": "UCE", + "type": "model", + "url": "https://github.com/snap-stanford/UCE", + "description": "Universal Cell Embeddings: zero-shot single-cell embedding model trained on 36M cells across species, tissues, and assays without fine-tuning.", + "tags": [ + "foundation-models", + "single-cell-foundation-models", + "transcriptomics-foundation-models" + ], + "tasks": [ + "Foundation Model" + ], + "modalities": [ + "Single Cell", + "Transcriptomics" + ], + "organism": [], + "api": false + }, + { + "id": "uni", + "name": "UNI", + "type": "model", + "url": "https://github.com/mahmoodlab/UNI", + "description": "General-purpose self-supervised pathology foundation model trained on 100K+ whole-slide images for diverse computational pathology tasks.", + "tags": [ + "foundation-models", + "single-cell-foundation-models", + "spatial-foundation-models" + ], + "tasks": [ + "Foundation Model" + ], + "modalities": [ + "Single Cell", + "Spatial Transcriptomics" + ], + "organism": [], + "api": false + }, + { + "id": "uni_mol", + "name": "Uni-Mol", + "type": "model", + "url": "https://github.com/deepmodeling/Uni-Mol", + "description": "3D molecular pretraining framework for universal representation learning on molecules and protein pockets.", + "tags": [ + "compound-embedding", + "compound-foundation-models", + "foundation-models" + ], + "tasks": [ + "Foundation Model" + ], + "modalities": [ + "Small Molecule" + ], + "organism": [], + "api": false + }, + { + "id": "unitednet", + "name": "UnitedNet", + "type": "model", + "url": "https://github.com/LiuLab-Bioelectronics-Harvard/UnitedNet", + "description": "Interpretable multi-task deep neural network for single-cell multi-omics integration spanning transcriptomics, chromatin accessibility, and proteomics.", + "tags": [ + "foundation-models", + "multi-omics-foundation-models", + "single-cell-foundation-models" + ], + "tasks": [ + "Foundation Model" + ], + "modalities": [ + "Multi-Omics", + "Single Cell" + ], + "organism": [], + "api": false + }, + { + "id": "virchow", + "name": "Virchow", + "type": "model", + "url": "https://huggingface.co/paige-ai/Virchow", + "description": "Million-slide digital pathology foundation model using a vision transformer and self-supervised distillation for tile-level pathology image representation.", + "tags": [ + "foundation-models", + "multi-modal-foundation-models" + ], + "tasks": [ + "Foundation Model" + ], + "modalities": [ + "Multi-Modal" + ], + "organism": [], + "api": false + }, + { + "id": "autozyme", + "name": "AutoZyme", + "type": "toolkit", + "url": "https://github.com/ElliotXie/autozyme", + "description": "Autonomous agentic framework that speeds up bioinformatics software (e.g. Scanpy, Seurat) on CPUs while preserving the original results.", + "tags": [ + "preprocessing-tools" + ], + "tasks": [ + "Preprocessing" + ], + "modalities": [], + "organism": [], + "api": false + }, + { + "id": "biopython", + "name": "Biopython", + "type": "toolkit", + "url": "https://biopython.org/", + "description": "Collection of Python tools for biological computation including sequence analysis, structure parsing, and database access.", + "tags": [ + "preprocessing-tools" + ], + "tasks": [ + "Preprocessing" + ], + "modalities": [], + "organism": [], + "api": false + }, + { + "id": "casper", + "name": "CaSpER", + "type": "toolkit", + "url": "https://github.com/akdess/CaSpER", + "description": "CNV identification and visualization by integrative analysis of single-cell or bulk RNA-seq data.", + "tags": [ + "preprocessing-tools" + ], + "tasks": [ + "Preprocessing" + ], + "modalities": [], + "organism": [], + "api": false + }, + { + "id": "cellcharter", + "name": "CellCharter", + "type": "toolkit", + "url": "https://github.com/CSOgroup/cellcharter", + "description": "Identification and characterization of spatial cell niches from spatial transcriptomics using VAEs and Gaussian mixture models.", + "tags": [ + "preprocessing-tools" + ], + "tasks": [ + "Preprocessing" + ], + "modalities": [], + "organism": [], + "api": false + }, + { + "id": "cellchat", + "name": "CellChat", + "type": "toolkit", + "url": "https://github.com/sqjin/CellChat", + "description": "Inference and analysis of cell-cell communication ligand-receptor networks from single-cell transcriptomics data.", + "tags": [ + "preprocessing-tools" + ], + "tasks": [ + "Preprocessing" + ], + "modalities": [], + "organism": [], + "api": false + }, + { + "id": "celltypist", + "name": "CellTypist", + "type": "toolkit", + "url": "https://github.com/Teichlab/celltypist", + "description": "Automated cell type annotation for scRNA-seq.", + "tags": [ + "preprocessing-tools" + ], + "tasks": [ + "Preprocessing" + ], + "modalities": [], + "organism": [], + "api": false + }, + { + "id": "chatspatial", + "name": "ChatSpatial", + "type": "toolkit", + "url": "https://github.com/cafferychen777/ChatSpatial", + "description": "MCP server for spatial transcriptomics analysis via natural language.", + "tags": [ + "preprocessing-tools" + ], + "tasks": [ + "Preprocessing" + ], + "modalities": [], + "organism": [], + "api": false + }, + { + "id": "chemistry_development_kit", + "name": "Chemistry Development Kit", + "type": "toolkit", + "url": "https://github.com/cdk/cdk", + "description": "Cheminformatics software & machine learning tools.", + "tags": [ + "preprocessing-tools" + ], + "tasks": [ + "Preprocessing" + ], + "modalities": [], + "organism": [], + "api": false + }, + { + "id": "commot", + "name": "COMMOT", + "type": "toolkit", + "url": "https://github.com/zcang/COMMOT", + "description": "Optimal transport-based framework for screening cell-cell communication in spatial transcriptomics.", + "tags": [ + "preprocessing-tools" + ], + "tasks": [ + "Preprocessing" + ], + "modalities": [], + "organism": [], + "api": false + }, + { + "id": "deepchem", + "name": "DeepChem", + "type": "toolkit", + "url": "https://github.com/deepchem/deepchem", + "description": "Deep learning library for drug discovery, quantum chemistry, and materials science.", + "tags": [ + "preprocessing-tools" + ], + "tasks": [ + "Preprocessing" + ], + "modalities": [], + "organism": [], + "api": false + }, + { + "id": "deeptalk", + "name": "DeepTalk", + "type": "toolkit", + "url": "https://github.com/JiangBioLab/DeepTalk", + "description": "Graph attention network for deciphering cell-cell communication from spatial transcriptomics data.", + "tags": [ + "preprocessing-tools" + ], + "tasks": [ + "Preprocessing" + ], + "modalities": [], + "organism": [], + "api": false + }, + { + "id": "doubletfinder", + "name": "DoubletFinder", + "type": "toolkit", + "url": "https://github.com/chris-mcginnis-ucsf/DoubletFinder", + "description": "Machine learning approach for detecting multiplet (doublet) artifacts in single-cell RNA-seq data.", + "tags": [ + "preprocessing-tools" + ], + "tasks": [ + "Preprocessing" + ], + "modalities": [], + "organism": [], + "api": false + }, + { + "id": "flashdeconv", + "name": "FlashDeconv", + "type": "toolkit", + "url": "https://github.com/cafferychen777/flashdeconv", + "description": "High-performance spatial transcriptomics deconvolution (~1M spots in ~3 min).", + "tags": [ + "preprocessing-tools" + ], + "tasks": [ + "Preprocessing" + ], + "modalities": [], + "organism": [], + "api": false + }, + { + "id": "gromacs", + "name": "GROMACS", + "type": "toolkit", + "url": "https://www.gromacs.org/", + "description": "Molecular dynamics simulation package for biochemical molecules.", + "tags": [ + "preprocessing-tools" + ], + "tasks": [ + "Preprocessing" + ], + "modalities": [], + "organism": [], + "api": false + }, + { + "id": "harmony", + "name": "Harmony", + "type": "toolkit", + "url": "https://github.com/immunogenomics/harmony", + "description": "Fast and scalable integration of single-cell data across datasets, conditions, technologies, and species.", + "tags": [ + "preprocessing-tools" + ], + "tasks": [ + "Preprocessing" + ], + "modalities": [], + "organism": [], + "api": false + }, + { + "id": "kallisto", + "name": "kallisto", + "type": "toolkit", + "url": "https://pachterlab.github.io/kallisto/", + "description": "Near-optimal RNA-seq quantification using pseudoalignment for fast transcript abundance estimation.", + "tags": [ + "preprocessing-tools" + ], + "tasks": [ + "Preprocessing" + ], + "modalities": [], + "organism": [], + "api": false + }, + { + "id": "linger", + "name": "LINGER", + "type": "toolkit", + "url": "https://github.com/Durenlab/LINGER", + "description": "Neural network for gene regulatory network inference from single-cell multiome (RNA+ATAC-seq) data with bulk data pretraining.", + "tags": [ + "preprocessing-tools" + ], + "tasks": [ + "Preprocessing" + ], + "modalities": [], + "organism": [], + "api": false + }, + { + "id": "mdanalysis", + "name": "MDAnalysis", + "type": "toolkit", + "url": "https://www.mdanalysis.org/", + "description": "Python library for analyzing and altering molecular dynamics simulation trajectories.", + "tags": [ + "preprocessing-tools" + ], + "tasks": [ + "Preprocessing" + ], + "modalities": [], + "organism": [], + "api": false + }, + { + "id": "mogonet", + "name": "MOGONET", + "type": "toolkit", + "url": "https://github.com/txWang/MOGONET", + "description": "Multi-omics graph convolutional network framework for patient classification and biomarker identification.", + "tags": [ + "preprocessing-tools" + ], + "tasks": [ + "Preprocessing" + ], + "modalities": [], + "organism": [], + "api": false + }, + { + "id": "monocle3", + "name": "Monocle3", + "type": "toolkit", + "url": "https://cole-trapnell-lab.github.io/monocle3/", + "description": "Single-cell trajectory analysis tool for learning developmental trajectories and ordering cells in pseudotime.", + "tags": [ + "preprocessing-tools" + ], + "tasks": [ + "Preprocessing" + ], + "modalities": [], + "organism": [], + "api": false + }, + { + "id": "ncem", + "name": "NCEM", + "type": "toolkit", + "url": "https://github.com/theislab/ncem", + "description": "GNN-based model for learning intercellular communication from spatial graphs of cells.", + "tags": [ + "preprocessing-tools" + ], + "tasks": [ + "Preprocessing" + ], + "modalities": [], + "organism": [], + "api": false + }, + { + "id": "numbat", + "name": "Numbat", + "type": "toolkit", + "url": "https://github.com/kharchenkolab/numbat", + "description": "Haplotype-aware copy number variation inference from single-cell RNA-seq using hidden Markov models.", + "tags": [ + "preprocessing-tools" + ], + "tasks": [ + "Preprocessing" + ], + "modalities": [], + "organism": [], + "api": false + }, + { + "id": "openmm", + "name": "OpenMM", + "type": "toolkit", + "url": "https://openmm.org/", + "description": "High-performance toolkit for molecular simulation and GPU-accelerated MD.", + "tags": [ + "preprocessing-tools" + ], + "tasks": [ + "Preprocessing" + ], + "modalities": [], + "organism": [], + "api": false + }, + { + "id": "rdkit", + "name": "RDKit", + "type": "toolkit", + "url": "https://github.com/rdkit/rdkit", + "description": "Cheminformatics software & machine learning toolkit.", + "tags": [ + "preprocessing-tools" + ], + "tasks": [ + "Preprocessing" + ], + "modalities": [], + "organism": [], + "api": false + }, + { + "id": "scanpy", + "name": "Scanpy", + "type": "toolkit", + "url": "https://scanpy.readthedocs.io/en/stable/", + "description": "Python library for scRNA-seq analysis.", + "tags": [ + "preprocessing-tools" + ], + "tasks": [ + "Preprocessing" + ], + "modalities": [], + "organism": [], + "api": false + }, + { + "id": "scenic", + "name": "SCENIC", + "type": "toolkit", + "url": "https://github.com/aertslab/SCENIC", + "description": "Single-cell regulatory network inference and clustering linking transcription factors to co-expressed gene modules.", + "tags": [ + "preprocessing-tools" + ], + "tasks": [ + "Preprocessing" + ], + "modalities": [], + "organism": [], + "api": false + }, + { + "id": "scipenn", + "name": "sciPENN", + "type": "toolkit", + "url": "https://github.com/jlakkis/sciPENN", + "description": "RNN-based method for simultaneous protein expression prediction, uncertainty estimation, and cell-type label transfer from CITE-seq and scRNA-seq data.", + "tags": [ + "preprocessing-tools" + ], + "tasks": [ + "Preprocessing" + ], + "modalities": [], + "organism": [], + "api": false + }, + { + "id": "scvelo", + "name": "scVelo", + "type": "toolkit", + "url": "https://github.com/theislab/scvelo", + "description": "RNA velocity estimation for single-cell transcriptomics, inferring the direction and speed of cell differentiation.", + "tags": [ + "preprocessing-tools" + ], + "tasks": [ + "Preprocessing" + ], + "modalities": [], + "organism": [], + "api": false + }, + { + "id": "scvi_tools", + "name": "scvi-tools", + "type": "toolkit", + "url": "https://scvi-tools.org/", + "description": "Probabilistic models for single-cell omics data analysis.", + "tags": [ + "preprocessing-tools" + ], + "tasks": [ + "Preprocessing" + ], + "modalities": [], + "organism": [], + "api": false + }, + { + "id": "seurat", + "name": "Seurat", + "type": "toolkit", + "url": "https://satijalab.org/seurat/", + "description": "R library for scRNA-seq analysis.", + "tags": [ + "preprocessing-tools" + ], + "tasks": [ + "Preprocessing" + ], + "modalities": [], + "organism": [], + "api": false + }, + { + "id": "squidpy", + "name": "Squidpy", + "type": "toolkit", + "url": "https://squidpy.readthedocs.io/", + "description": "Python library for spatial single-cell analysis.", + "tags": [ + "preprocessing-tools" + ], + "tasks": [ + "Preprocessing" + ], + "modalities": [], + "organism": [], + "api": false + }, + { + "id": "stagate", + "name": "STAGATE", + "type": "toolkit", + "url": "https://github.com/RucDongLab/STAGATE", + "description": "Adaptive graph attention auto-encoder for spatial domain identification in spatial transcriptomics.", + "tags": [ + "preprocessing-tools" + ], + "tasks": [ + "Preprocessing" + ], + "modalities": [], + "organism": [], + "api": false + }, + { + "id": "star", + "name": "STAR", + "type": "toolkit", + "url": "https://github.com/alexdobin/STAR", + "description": "Ultrafast universal RNA-seq aligner with support for spliced alignment and single-cell quantification via STARsolo.", + "tags": [ + "preprocessing-tools" + ], + "tasks": [ + "Preprocessing" + ], + "modalities": [], + "organism": [], + "api": false + }, + { + "id": "tigon", + "name": "TIGON", + "type": "toolkit", + "url": "https://github.com/yutongo/TIGON", + "description": "Neural optimal transport method for reconstructing growth and dynamic trajectories from single-cell transcriptomics.", + "tags": [ + "preprocessing-tools" + ], + "tasks": [ + "Preprocessing" + ], + "modalities": [], + "organism": [], + "api": false + } +] diff --git a/upstream/inoue0426-awesome-computational-biology/catalogue/data/resources.yml b/upstream/inoue0426-awesome-computational-biology/catalogue/data/resources.yml new file mode 100644 index 0000000..4bd0311 --- /dev/null +++ b/upstream/inoue0426-awesome-computational-biology/catalogue/data/resources.yml @@ -0,0 +1,3153 @@ +--- +title: "Awesome Computational Biology - machine-readable resource list" +task: "" +lineage_type: import +upstream_source: https://github.com/inoue0426/awesome-computational-biology/blob/12d87583/data/resources.yml +upstream_sha: 12d87583 +imported_at: 2026-06-26 +prompt_class: catalogue +upstream_changes: accepted +author: upstream +validated: false +--- + +# Awesome Computational Biology - machine-readable resource list +# Fields +# id : unique slug (required) +# name : display name (required) +# type : category, e.g. database | tool | model | benchmark | api (required) +# url : canonical URL (required) +# description : one-line description (required) +# license : SPDX identifier or free-text (optional) +# api : true | false - whether a programmatic API is available (default: false) +# updated : last-known update date as string YYYY-MM-DD (optional) +# tasks : list of ML/bio tasks (optional) +# modalities : list of data modalities (optional) +# tags : additional free-form tags (optional) +# organism : list of organisms covered (optional) +# paper : DOI or URL to primary publication (optional) + +resources: + - id: chembl_web_services + name: "ChEMBL Web Services" + type: api + url: https://www.ebi.ac.uk/chembl/ws + description: "REST API for bioactive molecules, targets, and bioassays." + tags: [api] + tasks: [] + modalities: [] + organism: [] + api: true + + - id: clinicaltrials_gov_api + name: "ClinicalTrials.gov API" + type: api + url: https://clinicaltrials.gov/api/gui + description: "API for querying clinical trial metadata and results." + tags: [api] + tasks: [] + modalities: [] + organism: [] + api: true + + - id: ensembl_rest_api + name: "Ensembl REST API" + type: api + url: https://rest.ensembl.org/ + description: "API for genomic annotations, variants, genes, and comparative genomics." + tags: [api] + tasks: [] + modalities: [] + organism: [] + api: true + + - id: kegg_rest_api + name: "KEGG REST API" + type: api + url: https://www.kegg.jp/kegg/rest/keggapi.html + description: "API for accessing KEGG pathways, compounds, genes, and reactions." + tags: [api] + tasks: [] + modalities: [] + organism: [] + api: true + + - id: ncbi_e_utilities + name: "NCBI E-utilities" + type: api + url: https://www.ncbi.nlm.nih.gov/books/NBK25501/ + description: "Unified APIs for accessing NCBI databases (Gene, GEO, SRA, PubChem, etc)." + tags: [api] + tasks: [] + modalities: [] + organism: [] + api: true + + - id: open_targets_platform_api + name: "Open Targets Platform API" + type: api + url: https://platform.opentargets.org/api + description: "API for target–disease associations integrating genetics, genomics, and drug data." + tags: [api] + tasks: [] + modalities: [] + organism: [] + api: true + + - id: pubmed_e_utilities_esearch_efetch + name: "PubMed E-utilities (esearch/efetch)" + type: api + url: https://www.nlm.nih.gov/dataguide/edirect/esearch.html + description: "APIs for searching and retrieving biomedical literature from PubMed." + tags: [api] + tasks: [] + modalities: [] + organism: [] + api: true + + - id: uniprot_rest_api + name: "UniProt REST API" + type: api + url: https://www.uniprot.org/help/api + description: "Programmatic access to protein sequence and functional annotation data." + tags: [api] + tasks: [] + modalities: [] + organism: [] + api: true + + - id: 1000_genomes_project + name: "1000 Genomes Project" + type: benchmark + url: https://www.internationalgenome.org/ + description: "Reference panel of human genetic variation from 2,504 individuals across 26 populations." + tags: [benchmarks-and-datasets] + tasks: [] + modalities: [] + organism: [] + api: false + + - id: bace + name: "BACE" + type: benchmark + url: https://www.kaggle.com/datasets/gokturkkoch/bace + description: "Binary classification and regression dataset for β-secretase 1 (BACE-1) inhibitor binding affinity." + tags: [benchmarks-and-datasets] + tasks: [] + modalities: [] + organism: [] + api: false + + - id: beat_aml + name: "BEAT AML" + type: benchmark + url: https://biodev.github.io/BeatAML2/ + description: "Functional ex vivo drug sensitivity measurements paired with genomics for acute myeloid leukemia." + tags: [benchmarks-and-datasets] + tasks: [] + modalities: [] + organism: [] + api: false + + - id: bento + name: "Bento" + type: benchmark + url: https://github.com/LigandPro/Bento + description: "Protein-ligand docking benchmark covering rigid, flexible, de novo, blind, induced-fit, and covalent docking tasks." + tags: [benchmarks-and-datasets] + tasks: [] + modalities: [] + organism: [] + api: false + + - id: bindingdb_curated_sets + name: "BindingDB Curated Sets" + type: benchmark + url: https://www.bindingdb.org/rwd/bind/chemsearch/marvin/SDFdownload.jsp?all_download=yes + description: "Curated binding affinity datasets for protein–ligand interaction benchmarking." + tags: [benchmarks-and-datasets] + tasks: [] + modalities: [] + organism: [] + api: false + + - id: cancer_therapeutics_response_portal_ctrp + name: "Cancer Therapeutics Response Portal (CTRP)" + type: benchmark + url: https://portals.broadinstitute.org/ctrp/ + description: "Drug sensitivity profiles across ~900 cancer cell lines for >400 compounds." + tags: [benchmarks-and-datasets] + tasks: [] + modalities: [] + organism: [] + api: false + + - id: clintox + name: "ClinTox" + type: benchmark + url: https://tdcommons.ai/single_pred_tasks/tox/#clintox + description: "Clinical toxicity dataset contrasting FDA-approved drugs with those that failed clinical trials due to toxicity." + tags: [benchmarks-and-datasets] + tasks: [] + modalities: [] + organism: [] + api: false + + - id: cptac_clinical_proteomic_tumor_analysis_consortium + name: "CPTAC (Clinical Proteomic Tumor Analysis Consortium)" + type: benchmark + url: https://proteomics.cancer.gov/programs/cptac + description: "Multi-omic proteogenomic datasets for multiple cancer types linking proteomics with genomics." + tags: [benchmarks-and-datasets] + tasks: [] + modalities: [] + organism: [] + api: false + + - id: crossdocked2020 + name: "CrossDocked2020" + type: benchmark + url: https://arxiv.org/abs/2001.01037 + description: "Large-scale dataset for structure-based virtual screening." + tags: [benchmarks-and-datasets] + tasks: [] + modalities: [] + organism: [] + api: false + + - id: dud_e_directory_of_useful_decoys_enhanced + name: "DUD-E (Directory of Useful Decoys, Enhanced)" + type: benchmark + url: http://dude.docking.org/ + description: "Structure-based virtual screening benchmark with active ligands and challenging decoy sets across diverse protein targets." + tags: [benchmarks-and-datasets] + tasks: [] + modalities: [] + organism: [] + api: false + + - id: flip_fitness_landscape_inference_for_proteins + name: "FLIP (Fitness Landscape Inference for Proteins)" + type: benchmark + url: https://github.com/J-SNACKKB/FLIP + description: "Benchmark collection of protein fitness landscape datasets for evaluating protein ML models." + tags: [benchmarks-and-datasets] + tasks: [] + modalities: [] + organism: [] + api: false + + - id: guacamol + name: "GuacaMol" + type: benchmark + url: https://github.com/BenevolentAI/guacamol + description: "Benchmark suite for generative molecular design models." + tags: [benchmarks-and-datasets] + tasks: [] + modalities: [] + organism: [] + api: false + + - id: jump_cell_painting_datasets + name: "JUMP Cell Painting Datasets" + type: benchmark + url: https://github.com/jump-cellpainting/datasets + description: "Consortium-scale cell imaging perturbation datasets (chemical and genetic) for phenotypic profiling and drug discovery research." + tags: [benchmarks-and-datasets] + tasks: [] + modalities: [] + organism: [] + api: false + + - id: lincs_l1000 + name: "LINCS L1000" + type: benchmark + url: https://lincsproject.org/LINCS/tools/workflows/find-the-best-place-to-obtain-the-lincs-l1000-data + description: "Gene expression profiles (978 landmark genes) for >20,000 chemical and genetic perturbations across cell lines." + tags: [benchmarks-and-datasets] + tasks: [] + modalities: [] + organism: [] + api: false + + - id: moleculenet + name: "MoleculeNet" + type: benchmark + url: http://moleculenet.ai/ + description: "Benchmark datasets for molecular machine learning." + tags: [benchmarks-and-datasets] + tasks: [] + modalities: [] + organism: [] + api: false + + - id: moses + name: "MOSES" + type: benchmark + url: https://github.com/molecularsets/moses + description: "Benchmarking platform for molecular generation models." + tags: [benchmarks-and-datasets] + tasks: [] + modalities: [] + organism: [] + api: false + + - id: ogb_open_graph_benchmark + name: "OGB (Open Graph Benchmark)" + type: benchmark + url: https://ogb.stanford.edu/ + description: "Large-scale graph ML benchmark suite including biological datasets such as ogbl-ppa (protein-protein associations) and ogbg-molhiv." + tags: [benchmarks-and-datasets] + tasks: [] + modalities: [] + organism: [] + api: false + + - id: openbiolink + name: "OpenBioLink" + type: benchmark + url: https://github.com/OpenBioLink/OpenBioLink + description: "Benchmark datasets for biological knowledge graph completion." + tags: [benchmarks-and-datasets] + tasks: [] + modalities: [] + organism: [] + api: false + + - id: pharmgkb + name: "PharmGKB" + type: benchmark + url: https://www.pharmgkb.org/ + description: "Curated pharmacogenomics dataset linking genetic variants to drug response phenotypes across thousands of drugs." + tags: [benchmarks-and-datasets] + tasks: [] + modalities: [] + organism: [] + api: false + + - id: pk_db + name: "PK-DB" + type: benchmark + url: https://pk-db.com/ + description: "Open database of experimental pharmacokinetics (PK) and ADME data from clinical and preclinical studies." + tags: [benchmarks-and-datasets] + tasks: [] + modalities: [] + organism: [] + api: false + + - id: prism + name: "PRISM" + type: benchmark + url: https://depmap.org/portal/prism/ + description: "Cancer drug sensitivity profiling of >4,500 drugs across >900 cancer cell lines using pooled-cell-line barcoding." + tags: [benchmarks-and-datasets] + tasks: [] + modalities: [] + organism: [] + api: false + + - id: proteingym + name: "ProteinGym" + type: benchmark + url: https://github.com/OATML-Markslab/ProteinGym + description: "Large-scale benchmark of deep mutational scanning assays for evaluating protein fitness landscape models." + tags: [benchmarks-and-datasets] + tasks: [] + modalities: [] + organism: [] + api: false + + - id: qm9 + name: "QM9" + type: benchmark + url: https://figshare.com/collections/Quantum_chemistry_structures_and_properties_of_134_kilo_molecules/978904 + description: "Quantum chemistry properties for 134K stable small organic molecules computed at DFT level." + tags: [benchmarks-and-datasets] + tasks: [] + modalities: [] + organism: [] + api: false + + - id: scib_single_cell_integration_benchmarks + name: "scIB (Single-cell Integration Benchmarks)" + type: benchmark + url: https://github.com/theislab/scib + description: "Comprehensive benchmarking framework for single-cell data integration methods." + tags: [benchmarks-and-datasets] + tasks: [] + modalities: [] + organism: [] + api: false + + - id: scperturb + name: "scPerturb" + type: benchmark + url: https://github.com/sanderlab/scPerturb + description: "Curated and continuously updated single-cell perturbation data resource spanning CRISPR and drug perturbation studies." + tags: [benchmarks-and-datasets] + tasks: [] + modalities: [] + organism: [] + api: false + + - id: sider_side_effect_resource + name: "SIDER (Side Effect Resource)" + type: benchmark + url: http://sideeffects.embl.de/ + description: "Database of 1,430 approved drugs with their recorded adverse drug reactions across 27 system-organ classes." + tags: [benchmarks-and-datasets] + tasks: [] + modalities: [] + organism: [] + api: false + + - id: tabula_muris + name: "Tabula Muris" + type: benchmark + url: https://tabula-muris.ds.czbiohub.org/ + description: "Comprehensive single-cell atlas of 20 mouse organs and tissues, enabling cross-tissue and cross-species comparisons." + tags: [benchmarks-and-datasets] + tasks: [] + modalities: [] + organism: [] + api: false + + - id: tabula_sapiens + name: "Tabula Sapiens" + type: benchmark + url: https://tabula-sapiens-portal.ds.czbiohub.org/ + description: "Comprehensive human single-cell atlas of ~500K cells from 24 organs and tissues across multiple donors." + tags: [benchmarks-and-datasets] + tasks: [] + modalities: [] + organism: [] + api: false + + - id: tape_tasks_assessing_protein_embeddings + name: "TAPE (Tasks Assessing Protein Embeddings)" + type: benchmark + url: https://github.com/songlab-cal/tape + description: "Benchmark suite of five biologically meaningful semi-supervised learning tasks for evaluating protein representations." + tags: [benchmarks-and-datasets] + tasks: [] + modalities: [] + organism: [] + api: false + + - id: the_cancer_genome_atlas_tcga + name: "The Cancer Genome Atlas (TCGA)" + type: benchmark + url: https://www.cancer.gov/about-nci/organization/ccg/research/structural-genomics/tcga + description: "Comprehensive multi-omics (genomics, transcriptomics, proteomics, methylation) dataset for 33 cancer types across ~11,000 patients." + tags: [benchmarks-and-datasets] + tasks: [] + modalities: [] + organism: [] + api: false + + - id: therapeutics_data_commons_tdc + name: "Therapeutics Data Commons (TDC)" + type: benchmark + url: https://tdcommons.ai/ + description: "Unified benchmark suite covering ADMET, drug-target interaction, drug response, and more." + tags: [benchmarks-and-datasets] + tasks: [] + modalities: [] + organism: [] + api: false + + - id: tox21 + name: "Tox21" + type: benchmark + url: https://tripod.nih.gov/tox21/challenge/ + description: "12,707 compounds tested in 12 nuclear receptor and stress-response pathway biochemical assays for toxicity prediction." + tags: [benchmarks-and-datasets] + tasks: [] + modalities: [] + organism: [] + api: false + + - id: uk_biobank + name: "UK Biobank" + type: benchmark + url: https://www.ukbiobank.ac.uk/ + description: "Large-scale biomedical database of ~500K participants with genetic, imaging, and health data for population genetics and disease studies." + tags: [benchmarks-and-datasets] + tasks: [] + modalities: [] + organism: [] + api: false + + - id: 10x_genomics_dataset + name: "10x Genomics Dataset" + type: database + url: https://www.10xgenomics.com/resources/datasets + description: "Collection of single-cell datasets." + tags: [genome] + tasks: [] + modalities: [Genomics] + organism: [] + api: false + + - id: alphafold_protein_structure_database + name: "AlphaFold Protein Structure Database" + type: database + url: https://alphafold.ebi.ac.uk/api-docs + description: "3D protein structure predictions." + tags: [protein] + tasks: [] + modalities: [Protein] + organism: [] + api: false + + - id: bindingdb + name: "BindingDB" + type: database + url: https://www.bindingdb.org/rwd/bind/index.jsp + description: "Compounds and target database." + tags: [chemical-protein-interaction, interaction] + tasks: [] + modalities: [Protein, Small Molecule] + organism: [] + api: false + + - id: biocyc + name: "BioCyc" + type: database + url: https://biocyc.org/ + description: "Collection of pathway/genome databases across thousands of organisms." + tags: [pathway] + tasks: [] + modalities: [Pathway] + organism: [] + api: false + + - id: biogrid + name: "BioGRID" + type: database + url: https://thebiogrid.org/ + description: "Protein, genetic, and chemical interactions." + tags: [interaction, protein-protein-interaction] + tasks: [] + modalities: [Protein] + organism: [] + api: false + + - id: cancer_cell_line_encyclopedia + name: "Cancer Cell Line Encyclopedia" + type: database + url: https://sites.broadinstitute.org/ccle/ + description: "Database of ~1000 cancer cell lines." + tags: [drug-cell-line-response, interaction] + tasks: [] + modalities: [Gene Expression, Small Molecule] + organism: [] + api: false + + - id: catalogue_of_somatic_mutations_in_cancer_cosmic + name: "Catalogue Of Somatic Mutations In Cancer (COSMIC)" + type: database + url: https://cancer.sanger.ac.uk/cosmic + description: "Resource on somatic mutations in cancers." + tags: [genome] + tasks: [] + modalities: [Genomics] + organism: [] + api: false + + - id: cath_database + name: "CATH database" + type: database + url: https://www.cathdb.info/ + description: "Hierarchical classification of protein domain structures." + tags: [protein] + tasks: [] + modalities: [Protein] + organism: [] + api: false + + - id: cbioportal + name: "cBioPortal" + type: database + url: https://www.cbioportal.org/ + description: "Cancer genomics database; aggregating many patient datasets." + tags: [genome] + tasks: [] + modalities: [Genomics] + organism: [] + api: false + + - id: cellminer_cross_database_cellminercdb + name: "CellMiner Cross Database (CellMinerCDB)" + type: database + url: https://discover.nci.nih.gov/cellminercdb/ + description: "Integrates multiple cancer cell line databases." + tags: [drug-cell-line-response, interaction] + tasks: [] + modalities: [Gene Expression, Small Molecule] + organism: [] + api: false + + - id: chebi + name: "ChEBI" + type: database + url: https://www.ebi.ac.uk/chebi/ + description: "Database focused on small chemical compounds." + tags: [compound] + tasks: [] + modalities: [Small Molecule] + organism: [] + api: false + + - id: chembl + name: "ChEMBL" + type: database + url: https://www.ebi.ac.uk/chembl/ + description: "Bioactive molecules with drug-like properties." + tags: [compound] + tasks: [] + modalities: [Small Molecule] + organism: [] + api: false + + - id: chemspider + name: "ChemSpider" + type: database + url: http://www.chemspider.com/ + description: "Chemical structure database." + tags: [compound] + tasks: [] + modalities: [Small Molecule] + organism: [] + api: false + + - id: clinicaltrials_gov + name: "ClinicalTrials.gov" + type: database + url: https://clinicaltrials.gov/ + description: "Privately and publicly funded clinical studies." + tags: [clinical-trial] + tasks: [] + modalities: [Clinical] + organism: [] + api: false + + - id: comparative_toxicogenomics_database + name: "Comparative Toxicogenomics Database" + type: database + url: http://ctdbase.org/ + description: "Chemical-gene interactions, chemical-disease and gene-disease associations, chemical-phenotype associations." + tags: [drug-gene-interaction, interaction] + tasks: [] + modalities: [Gene, Small Molecule] + organism: [] + api: false + + - id: critical_assessment_of_structure_prediction_casp + name: "Critical Assessment of Structure Prediction (CASP)" + type: database + url: https://predictioncenter.org/ + description: "Assessing methods for protein structure prediction." + tags: [protein] + tasks: [] + modalities: [Protein] + organism: [] + api: false + + - id: cz_cellxgene + name: "CZ CELLxGENE" + type: database + url: https://cellxgene.cziscience.com/ + description: "Single-cell dataset repository and interactive explorer from the Chan Zuckerberg Initiative." + tags: [scrna] + tasks: [] + modalities: [Single Cell] + organism: [] + api: false + + - id: davis_kinase_inhibitors_db + name: "Davis kinase inhibitors DB" + type: database + url: http://staff.cs.utu.fi/~aijrinas/dti/ + description: "Experimental kinase inhibitor binding affinity dataset for protein–ligand interaction research." + tags: [chemical-protein-interaction, interaction] + tasks: [] + modalities: [Protein, Small Molecule] + organism: [] + api: false + + - id: dependency_map_depmap + name: "Dependency Map (DepMap)" + type: database + url: https://depmap.org/portal/ + description: "CRISPR-Cas9 screens in cancer cell lines." + tags: [genome] + tasks: [] + modalities: [Genomics] + organism: [] + api: false + + - id: dgidb + name: "DGIdb" + type: database + url: https://www.dgidb.org/ + description: "Drug-gene interactions and the druggable genome." + tags: [drug-gene-interaction, interaction] + tasks: [] + modalities: [Gene, Small Molecule] + organism: [] + api: false + + - id: diseases + name: "DISEASES" + type: database + url: https://diseases.jensenlab.org/ + description: "Gene–disease association database integrating evidence from text mining, curated databases, and experimental data." + tags: [disease] + tasks: [] + modalities: [Disease] + organism: [] + api: false + + - id: disgenet + name: "DisGeNET" + type: database + url: https://www.disgenet.org/ + description: "Database of gene-disease associations integrating expert-curated and GWAS data." + tags: [disease] + tasks: [] + modalities: [Disease] + organism: [] + api: false + + - id: drkg + name: "DRKG" + type: database + url: https://github.com/gnn4dr/DRKG + description: "Large-scale biological knowledge graph for drug discovery." + tags: [interaction, knowledge-graph] + tasks: [] + modalities: [Knowledge Graph] + organism: [] + api: false + + - id: drug_mechanism_database_drugmechdb + name: "Drug Mechanism Database (DrugMechDB)" + type: database + url: https://github.com/SuLab/DrugMechDB/tree/2.0.1 + description: "Mechanisms of action from drug to disease." + tags: [interaction, knowledge-graph] + tasks: [] + modalities: [Knowledge Graph] + organism: [] + api: false + + - id: drug_repurposing_hub + name: "Drug Repurposing Hub" + type: database + url: https://repo-hub.broadinstitute.org/repurposing#download-data + description: "Collections of drug repurposing data (drug, MoA, target, etc)." + tags: [compound] + tasks: [] + modalities: [Small Molecule] + organism: [] + api: false + + - id: drugbank + name: "DrugBank" + type: database + url: https://go.drugbank.com/ + description: "Database of drugs and targets (University of Alberta)." + tags: [disease] + tasks: [] + modalities: [Disease] + organism: [] + api: false + + - id: drugcentral + name: "DrugCentral" + type: database + url: http://drugcentral.org/ + description: "Online drug compendium with drug mode of action and indication information." + tags: [compound] + tasks: [] + modalities: [Small Molecule] + organism: [] + api: false + + - id: drugtargetcommons + name: "DrugTargetCommons" + type: database + url: https://drugtargetcommons.fimm.fi/ + description: "Community platform for curating and integrating experimental bioactivity data across drugs and targets." + tags: [compound] + tasks: [] + modalities: [Small Molecule] + organism: [] + api: false + + - id: encode + name: "ENCODE" + type: database + url: https://www.encodeproject.org/ + description: "Encyclopedia of DNA Elements; regulatory and functional genomic elements across the genome." + tags: [genome] + tasks: [] + modalities: [Genomics] + organism: [] + api: false + + - id: ensembl + name: "Ensembl" + type: database + url: https://www.ensembl.org/ + description: "Genome browser and annotation database for vertebrate and other eukaryotic genomes." + tags: [genome] + tasks: [] + modalities: [Genomics] + organism: [] + api: false + + - id: eu_drug_regulating_authorities_clinical_trials_db_eudract + name: "EU Drug Regulating Authorities Clinical Trials DB (EudraCT)" + type: database + url: https://eudract.ema.europa.eu/ + description: "European clinical trial database." + tags: [clinical-trial] + tasks: [] + modalities: [Clinical] + organism: [] + api: false + + - id: fantom5 + name: "FANTOM5" + type: database + url: https://fantom.gsc.riken.jp/5/ + description: "Functional annotation of mammalian genome; comprehensive atlas of active enhancers, promoters, and transcription start sites across human and mouse cell types." + tags: [genome] + tasks: [] + modalities: [Genomics] + organism: [] + api: false + + - id: genbank + name: "GenBank" + type: database + url: https://www.ncbi.nlm.nih.gov/genbank/ + description: "NCBI's database of genetic sequences." + tags: [genome] + tasks: [] + modalities: [Genomics] + organism: [] + api: false + + - id: gene_expression_omnibus + name: "Gene Expression Omnibus" + type: database + url: https://www.ncbi.nlm.nih.gov/geo/ + description: "Public functional genomics database." + tags: [scrna] + tasks: [] + modalities: [Single Cell] + organism: [] + api: false + + - id: genomics_of_drug_sensitivity_in_cancer_gdsc + name: "Genomics of Drug Sensitivity in Cancer (GDSC)" + type: database + url: https://www.cancerrxgene.org/ + description: "Drug sensitivity for ~1000 human cancer cell lines and hundreds of compounds." + tags: [benchmarks-and-datasets, drug-cell-line-response, interaction] + tasks: [] + modalities: [Gene Expression, Small Molecule] + organism: [] + api: false + + - id: gnomad + name: "gnomAD" + type: database + url: https://gnomad.broadinstitute.org/ + description: "Genome Aggregation Database; genetic variation from large-scale sequencing projects." + tags: [genome] + tasks: [] + modalities: [Genomics] + organism: [] + api: false + + - id: hetionet + name: "Hetionet" + type: database + url: https://github.com/hetio/hetionet + description: "Heterogeneous network integrating genes, diseases, drugs, pathways, and more." + tags: [interaction, knowledge-graph] + tasks: [] + modalities: [Knowledge Graph] + organism: [] + api: false + + - id: hippie + name: "HIPPIE" + type: database + url: http://cbdm-01.zdv.uni-mainz.de/~mschaefer/hippie/ + description: "Human protein-protein interaction database." + tags: [interaction, protein-protein-interaction] + tasks: [] + modalities: [Protein] + organism: [] + api: false + + - id: hmdb_human_metabolome_database + name: "HMDB (Human Metabolome Database)" + type: database + url: https://hmdb.ca/ + description: "Comprehensive database of small molecule metabolites found in the human body." + tags: [compound] + tasks: [] + modalities: [Small Molecule] + organism: [] + api: false + + - id: human_cell_atlas + name: "Human Cell Atlas" + type: database + url: https://www.humancellatlas.org/ + description: "Open global atlas of all cells in the human body." + tags: [scrna] + tasks: [] + modalities: [Single Cell] + organism: [] + api: false + + - id: human_genome_resources_at_ncbi + name: "Human Genome Resources at NCBI" + type: database + url: https://www.ncbi.nlm.nih.gov/projects/genome/guide/human/index.shtml + description: "Database for genomics, proteomics, transcriptomics, and systems biology." + tags: [genome] + tasks: [] + modalities: [Genomics] + organism: [] + api: false + + - id: human_phenotype_ontology_hpo + name: "Human Phenotype Ontology (HPO)" + type: database + url: https://hpo.jax.org/ + description: "Standardized vocabulary of phenotypic abnormalities in human disease, linking genes, variants, and clinical features." + tags: [disease] + tasks: [] + modalities: [Disease] + organism: [] + api: false + + - id: icd10 + name: "ICD10" + type: database + url: https://icd.who.int/browse10/2019/en + description: "International Classification of Diseases, 10th revision." + tags: [clinical-trial] + tasks: [] + modalities: [Clinical] + organism: [] + api: false + + - id: intact + name: "IntAct" + type: database + url: https://www.ebi.ac.uk/intact/home + description: "Open-source molecular interaction database and analysis system from EMBL-EBI." + tags: [interaction, protein-protein-interaction] + tasks: [] + modalities: [Protein] + organism: [] + api: false + + - id: interpro + name: "InterPro" + type: database + url: https://www.ebi.ac.uk/interpro/ + description: "Protein families, domains, and functional sites database integrating 14 member databases including Pfam and PROSITE." + tags: [protein] + tasks: [] + modalities: [Protein] + organism: [] + api: false + + - id: jaspar + name: "JASPAR" + type: database + url: http://jaspar.genereg.net/ + description: "Database of transcription factor binding profiles." + tags: [genome] + tasks: [] + modalities: [Genomics] + organism: [] + api: false + + - id: kegg_compound + name: "KEGG COMPOUND" + type: database + url: https://www.genome.jp/kegg/compound/ + description: "Collection of small molecules and biopolymers." + tags: [compound] + tasks: [] + modalities: [Small Molecule] + organism: [] + api: false + + - id: kegg_drug + name: "KEGG DRUG" + type: database + url: https://www.genome.jp/kegg/drug/ + description: "Comprehensive, approved drug information." + tags: [disease] + tasks: [] + modalities: [Disease] + organism: [] + api: false + + - id: kegg_pathway + name: "KEGG PATHWAY" + type: database + url: https://www.genome.jp/kegg/pathway.html + description: "Collection of pathway maps." + tags: [pathway] + tasks: [] + modalities: [Pathway] + organism: [] + api: false + + - id: kinase_inhibitor_bioactivity_data_kiba + name: "Kinase Inhibitor Bioactivity Data (KIBA)" + type: database + url: https://janeliascicomp.github.io/KIBA/ + description: "Integrated bioactivity scores for kinase inhibitors combining Ki, Kd, and IC50 measurements." + tags: [chemical-protein-interaction, interaction] + tasks: [] + modalities: [Protein, Small Molecule] + organism: [] + api: false + + - id: lipid_maps + name: "LIPID MAPS" + type: database + url: https://www.lipidmaps.org/databases/lmsd/overview + description: "Database of lipids." + tags: [compound] + tasks: [] + modalities: [Small Molecule] + organism: [] + api: false + + - id: massbank + name: "MassBank" + type: database + url: http://www.massbank.jp/ + description: "Open source databases and tools for mass spectrometry reference spectra." + tags: [mass-spectra] + tasks: [] + modalities: [Mass Spectra] + organism: [] + api: false + + - id: mgnify + name: "MGnify" + type: database + url: https://www.ebi.ac.uk/metagenomics/ + description: "Resource for metagenomic and metatranscriptomic data." + tags: [genome] + tasks: [] + modalities: [Genomics] + organism: [] + api: false + + - id: mimic_iv + name: "MIMIC-IV" + type: database + url: https://mimic.mit.edu/ + description: "Freely accessible critical care database." + tags: [clinical-trial] + tasks: [] + modalities: [Clinical] + organism: [] + api: false + + - id: mirbase + name: "miRBase" + type: database + url: https://www.mirbase.org/ + description: "Reference repository for microRNA gene annotations, sequences, and experimentally validated targets." + tags: [gene-regulatory-network, interaction] + tasks: [] + modalities: [Gene Expression] + organism: [] + api: false + + - id: mona_massbank_of_north_america + name: "MoNA MassBank of North America" + type: database + url: https://mona.fiehnlab.ucdavis.edu/ + description: "Meta-database of metabolite mass spectra, metadata, and associated compounds." + tags: [mass-spectra] + tasks: [] + modalities: [Mass Spectra] + organism: [] + api: false + + - id: msigdb_molecular_signatures_database + name: "MSigDB (Molecular Signatures Database)" + type: database + url: https://www.gsea-msigdb.org/gsea/msigdb + description: "Curated gene sets derived from pathways and biological processes." + tags: [pathway] + tasks: [] + modalities: [Pathway] + organism: [] + api: false + + - id: nci60 + name: "NCI60" + type: database + url: https://dtp.cancer.gov/discovery_development/nci-60/ + description: "Focuses on 60 cancer cell lines and many drugs." + tags: [benchmarks-and-datasets, drug-cell-line-response, interaction] + tasks: [] + modalities: [Gene Expression, Small Molecule] + organism: [] + api: false + + - id: nextprot + name: "NeXtProt" + type: database + url: https://www.nextprot.org/ + description: "Expert knowledge base on human proteins with deep functional annotation, complementary to UniProt." + tags: [protein] + tasks: [] + modalities: [Protein] + organism: [] + api: false + + - id: oadb_observed_antibody_space_database + name: "OADB (Observed Antibody Space Database)" + type: database + url: http://opig.stats.ox.ac.uk/webapps/oas/ + description: "Database of antibody sequences from immune repertoire sequencing." + tags: [protein] + tasks: [] + modalities: [Protein] + organism: [] + api: false + + - id: omim_online_mendelian_inheritance_in_man + name: "OMIM (Online Mendelian Inheritance in Man)" + type: database + url: https://www.omim.org/ + description: "Comprehensive database of human genes and genetic disorders." + tags: [disease] + tasks: [] + modalities: [Disease] + organism: [] + api: false + + - id: omnipath + name: "OmniPath" + type: database + url: https://omnipathdb.org/ + description: "Comprehensive resource integrating protein interactions, signaling pathways, gene regulatory networks, and miRNA targets from over 100 databases." + tags: [pathway] + tasks: [] + modalities: [Pathway] + organism: [] + api: false + + - id: open_targets_platform + name: "Open Targets Platform" + type: database + url: https://platform.opentargets.org/ + description: "Systematic target identification and prioritization platform integrating genetics, genomics, and drug data for drug discovery." + tags: [disease] + tasks: [] + modalities: [Disease] + organism: [] + api: false + + - id: pathwaycommons + name: "PathwayCommons" + type: database + url: https://www.pathwaycommons.org/ + description: "Database of pathways and interactions." + tags: [pathway] + tasks: [] + modalities: [Pathway] + organism: [] + api: false + + - id: pdbbind + name: "PDBBind" + type: database + url: https://www.pdbbind-plus.org.cn/ + description: "Binding affinity data for biomolecular complexes." + tags: [chemical-protein-interaction, interaction] + tasks: [] + modalities: [Protein, Small Molecule] + organism: [] + api: false + + - id: pfam + name: "Pfam" + type: database + url: https://www.ebi.ac.uk/interpro/entry/pfam/ + description: "Database of protein families described by multiple sequence alignments and hidden Markov models." + tags: [protein] + tasks: [] + modalities: [Protein] + organism: [] + api: false + + - id: primekg + name: "PrimeKG" + type: database + url: https://github.com/mims-harvard/PrimeKG + description: "Multi-modal precision medicine knowledge graph integrating clinical, genetic, and drug data." + tags: [interaction, knowledge-graph] + tasks: [] + modalities: [Knowledge Graph] + organism: [] + api: false + + - id: protein_data_bank_pdb + name: "PROTEIN DATA BANK (PDB)" + type: database + url: https://www.rcsb.org/ + description: "3D structures of proteins, nucleic acids, complexes." + tags: [protein] + tasks: [] + modalities: [Protein] + organism: [] + api: false + + - id: pubchem + name: "PubChem" + type: database + url: https://pubchem.ncbi.nlm.nih.gov/ + description: "One of the largest chemical databases (compounds, genes, and proteins)." + tags: [compound] + tasks: [] + modalities: [Small Molecule] + organism: [] + api: false + + - id: rcsb_protein_data_bank + name: "RCSB Protein Data Bank" + type: database + url: https://www.rcsb.org/ + description: "Repository for structural data of biological molecules." + tags: [protein] + tasks: [] + modalities: [Protein] + organism: [] + api: false + + - id: reactome + name: "Reactome" + type: database + url: https://reactome.org/ + description: "Expert-curated, peer-reviewed pathway database with detailed reaction mechanisms." + tags: [pathway] + tasks: [] + modalities: [Pathway] + organism: [] + api: false + + - id: regnetwork + name: "RegNetwork" + type: database + url: http://www.regnetworkweb.org/ + description: "Database of gene regulatory networks covering transcription factor–target gene and miRNA–gene interaction data across multiple species." + tags: [gene-regulatory-network, interaction] + tasks: [] + modalities: [Gene Expression] + organism: [] + api: false + + - id: rfam + name: "Rfam" + type: database + url: https://rfam.org/ + description: "Database of RNA families with sequence alignments and consensus structures." + tags: [genome] + tasks: [] + modalities: [Genomics] + organism: [] + api: false + + - id: rhea + name: "Rhea" + type: database + url: https://www.rhea-db.org/ + description: "Database of chemical reactions." + tags: [compound] + tasks: [] + modalities: [Small Molecule] + organism: [] + api: false + + - id: roadmap_epigenomics + name: "ROADMAP Epigenomics" + type: database + url: http://www.roadmapepigenomics.org/ + description: "Reference epigenome maps for 111 primary human cell types and tissues, including histone modifications, chromatin accessibility, and DNA methylation." + tags: [genome] + tasks: [] + modalities: [Genomics] + organism: [] + api: false + + - id: sabdab + name: "SAbDab" + type: database + url: https://opig.stats.ox.ac.uk/webapps/sabdab-sabpred/sabdab + description: "Structural Antibody Database containing all antibody structures in the PDB." + tags: [protein] + tasks: [] + modalities: [Protein] + organism: [] + api: false + + - id: signor_2_0 + name: "SIGNOR 2.0" + type: database + url: https://signor.uniroma2.it/ + description: "Database of causal signaling interactions and pathways, with signed and directed relationships between proteins." + tags: [pathway] + tasks: [] + modalities: [Pathway] + organism: [] + api: false + + - id: single_cell_expression_atlas + name: "Single Cell Expression Atlas" + type: database + url: https://www.ebi.ac.uk/gxa/sc/home + description: "Public database for single-cell RNA." + tags: [scrna] + tasks: [] + modalities: [Single Cell] + organism: [] + api: false + + - id: single_cell_portal + name: "Single Cell PORTAL" + type: database + url: https://singlecell.broadinstitute.org/single_cell + description: "Public database for single-cell RNA." + tags: [scrna] + tasks: [] + modalities: [Single Cell] + organism: [] + api: false + + - id: snap + name: "SNAP" + type: database + url: https://snap.stanford.edu/biodata/datasets/10002/10002-ChG-Miner.html + description: "Dataset of drug-gene interactions." + tags: [drug-gene-interaction, interaction] + tasks: [] + modalities: [Gene, Small Molecule] + organism: [] + api: false + + - id: stitch + name: "STITCH" + type: database + url: http://stitch.embl.de/ + description: "Chemical-protein interactions." + tags: [chemical-protein-interaction, interaction] + tasks: [] + modalities: [Protein, Small Molecule] + organism: [] + api: false + + - id: string + name: "STRING" + type: database + url: https://string-db.org/ + description: "PPI networks for multiple organisms." + tags: [interaction, protein-protein-interaction] + tasks: [] + modalities: [Protein] + organism: [] + api: false + + - id: the_genotype_tissue_expression_gtex + name: "The Genotype-Tissue Expression (GTEx)" + type: database + url: https://gtexportal.org/home/ + description: "Human gene expression and regulation resource." + tags: [genome] + tasks: [] + modalities: [Genomics] + organism: [] + api: false + + - id: the_human_protein_atlas + name: "THE HUMAN PROTEIN ATLAS" + type: database + url: https://www.proteinatlas.org/ + description: "Comprehensive human protein database (cells, tissues, organs)." + tags: [protein] + tasks: [] + modalities: [Protein] + organism: [] + api: false + + - id: therapeutic_target_database + name: "Therapeutic Target Database" + type: database + url: https://idrblab.net/ttd/full-data-download + description: "Drug-target, target-disease, and drug-disease datasets." + tags: [compound] + tasks: [] + modalities: [Small Molecule] + organism: [] + api: false + + - id: trrust_v2 + name: "TRRUST v2" + type: database + url: https://www.grnpedia.org/trrust/ + description: "Manually curated database of human and mouse transcriptional regulatory interactions between transcription factors and their target genes, expanded with literature-derived evidence." + tags: [gene-regulatory-network, interaction] + tasks: [] + modalities: [Gene Expression] + organism: [] + api: false + + - id: ucsc_genome_browser + name: "UCSC Genome Browser" + type: database + url: https://genome.ucsc.edu/ + description: "UCSC's genome browser." + tags: [genome] + tasks: [] + modalities: [Genomics] + organism: [] + api: false + + - id: uniclust + name: "Uniclust" + type: database + url: https://uniclust.mmseqs.com/ + description: "Clustered protein sequence databases." + tags: [protein] + tasks: [] + modalities: [Protein] + organism: [] + api: false + + - id: uniprot + name: "UniProt" + type: database + url: https://www.uniprot.org/ + description: "Functional information on proteins." + tags: [protein] + tasks: [] + modalities: [Protein] + organism: [] + api: false + + - id: uniref + name: "UniRef" + type: database + url: https://www.uniprot.org/uniref/ + description: "Non-redundant sequence database clustering UniProtKB entries at multiple sequence identity thresholds." + tags: [protein] + tasks: [] + modalities: [Protein] + organism: [] + api: false + + - id: wikipathways + name: "WikiPathways" + type: database + url: https://wikipathways.org/ + description: "Database of biological pathways." + tags: [pathway] + tasks: [] + modalities: [Pathway] + organism: [] + api: false + + - id: zinc_ligand_discovery_database + name: "ZINC ligand discovery database" + type: database + url: https://zinc.docking.org/ + description: "Free database of commercially-available compounds for virtual screening." + tags: [compound] + tasks: [] + modalities: [Small Molecule] + organism: [] + api: false + + - id: ai4chem_chemllm_7b_chat + name: "AI4Chem/ChemLLM-7B-Chat" + type: model + url: https://huggingface.co/AI4Chem/ChemLLM-7B-Chat + description: "LLM for chemical & molecular science." + tags: [llm-for-biology] + tasks: [Language Modeling] + modalities: [Text] + organism: [] + api: false + + - id: alphafold3 + name: "AlphaFold3" + type: model + url: https://github.com/google-deepmind/alphafold3 + description: "Predicts structures of proteins, nucleic acids, small molecules, and their complexes." + tags: [foundation-models, protein-foundation-models, protein-structure-prediction-and-design] + tasks: [Foundation Model, Protein Structure Prediction] + modalities: [Protein] + organism: [] + api: false + + - id: ankh + name: "Ankh" + type: model + url: https://github.com/agemagician/Ankh + description: "Efficient protein language model optimized for downstream prediction tasks including secondary structure, localization, and function annotation." + tags: [foundation-models, pre-trained-embedding, protein-foundation-models] + tasks: [Foundation Model] + modalities: [Protein] + organism: [] + api: false + + - id: babel + name: "BABEL" + type: model + url: https://github.com/wukevin/babel + description: "Cross-modality translation model enabling prediction between scRNA-seq and scATAC-seq profiles without requiring paired single-cell measurements." + tags: [foundation-models, multi-omics-foundation-models, single-cell-foundation-models] + tasks: [Foundation Model] + modalities: [Multi-Omics, Single Cell] + organism: [] + api: false + + - id: basenji + name: "Basenji" + type: model + url: https://github.com/calico/basenji + description: "Sequential regulatory activity prediction from DNA sequences." + tags: [foundation-models, genomics-foundation-models] + tasks: [Foundation Model] + modalities: [Genomics] + organism: [] + api: false + + - id: biogpt + name: "BioGPT" + type: model + url: https://github.com/microsoft/BioGPT + description: "LLM for biomedical text generation." + tags: [llm-for-biology] + tasks: [Language Modeling] + modalities: [Text] + organism: [] + api: false + + - id: biomedclip + name: "BiomedCLIP" + type: model + url: https://huggingface.co/microsoft/BiomedCLIP-PubMedBERT_256-vit_g_14 + description: "CLIP-based vision-language foundation model for biomedical images and text trained on PubMed figure–caption pairs." + tags: [foundation-models, multi-modal-foundation-models] + tasks: [Foundation Model] + modalities: [Multi-Modal] + organism: [] + api: false + + - id: biomedlm + name: "BioMedLM" + type: model + url: https://huggingface.co/stanford-crfm/BioMedLM + description: "2.7B parameter GPT-2-style language model trained exclusively on biomedical literature from PubMed for biomedical question answering and text generation." + tags: [llm-for-biology] + tasks: [Language Modeling] + modalities: [Text] + organism: [] + api: false + + - id: boltz_1 + name: "Boltz-1" + type: model + url: https://github.com/jwohlwend/boltz + description: "Open-source all-atom biomolecular structure prediction model for proteins, nucleic acids, small molecules, and their complexes achieving AlphaFold3-level accuracy." + tags: [foundation-models, protein-foundation-models, protein-structure-prediction-and-design] + tasks: [Foundation Model, Protein Structure Prediction] + modalities: [Protein] + organism: [] + api: false + + - id: borzoi + name: "Borzoi" + type: model + url: https://github.com/calico/borzoi + description: "Extended successor to Enformer for predicting RNA-seq coverage from long genomic sequence windows (524 kb) with improved resolution." + tags: [foundation-models, genomics-foundation-models] + tasks: [Foundation Model] + modalities: [Genomics] + organism: [] + api: false + + - id: bulkformer + name: "BulkFormer" + type: model + url: https://github.com/KangBoming/BulkFormer + description: "Foundation model for bulk RNA-seq data; learns general transcriptomic representations." + tags: [foundation-models, single-cell-foundation-models, transcriptomics-foundation-models] + tasks: [Foundation Model] + modalities: [Single Cell, Transcriptomics] + organism: [] + api: false + + - id: caduceus + name: "Caduceus" + type: model + url: https://github.com/kuleshov-group/caduceus + description: "Bidirectional equivariant long-range DNA sequence model based on Mamba." + tags: [foundation-models, genomics-foundation-models] + tasks: [Foundation Model] + modalities: [Genomics] + organism: [] + api: false + + - id: cancerfoundation + name: "CancerFoundation" + type: model + url: https://github.com/BoevaLab/CancerFoundation + description: "Single-cell RNA-seq foundation model trained exclusively on a curated dataset of malignant cells to learn cancer-specific embeddings." + tags: [foundation-models, single-cell-foundation-models, transcriptomics-foundation-models] + tasks: [Foundation Model] + modalities: [Single Cell, Transcriptomics] + organism: [] + api: false + + - id: cassia + name: "CASSIA" + type: model + url: https://github.com/ElliotXie/CASSIA + description: "Multi-agent LLM for reference-free, interpretable cell-type annotation of single-cell RNA-seq data, with dedicated annotation, validation, scoring, and reporting agents." + tags: [llm-for-biology] + tasks: [Language Modeling] + modalities: [Text] + organism: [] + api: false + + - id: cellplm + name: "CellPLM" + type: model + url: https://github.com/OmicsML/CellPLM + description: "Cell pre-trained language model with inter-cell transformer architecture for diverse single-cell analysis tasks." + tags: [foundation-models, single-cell-foundation-models, transcriptomics-foundation-models] + tasks: [Foundation Model] + modalities: [Single Cell, Transcriptomics] + organism: [] + api: false + + - id: chai_1 + name: "Chai-1" + type: model + url: https://github.com/chaidiscovery/chai-lab + description: "Unified molecular structure prediction model covering proteins, nucleic acids, small molecules, and complexes." + tags: [foundation-models, protein-foundation-models, protein-structure-prediction-and-design] + tasks: [Foundation Model, Protein Structure Prediction] + modalities: [Protein] + organism: [] + api: false + + - id: chatdrug + name: "ChatDrug" + type: model + url: https://github.com/chao1224/ChatDrug + description: "LLM-based conversational pipeline for drug discovery, using natural language prompts for iterative drug editing and optimization." + tags: [llm-for-biology] + tasks: [Language Modeling] + modalities: [Text] + organism: [] + api: false + + - id: chemberta_2 + name: "ChemBERTa-2" + type: model + url: https://github.com/seyonechithrananda/bert-loves-chemistry + description: "RoBERTa-based molecular language model pretrained on SMILES for small-molecule representation learning." + tags: [compound-embedding, compound-foundation-models, foundation-models] + tasks: [Foundation Model] + modalities: [Small Molecule] + organism: [] + api: false + + - id: chemcpa + name: "chemCPA" + type: model + url: https://github.com/theislab/chemCPA + description: "Compositional perturbation autoencoder for predicting single-cell transcriptional responses to unseen drug perturbations and dose combinations." + tags: [drug-discovery, drug-response-prediction] + tasks: [Drug Discovery, Drug Response Prediction] + modalities: [Small Molecule] + organism: [] + api: false + + - id: chief + name: "CHIEF" + type: model + url: https://github.com/hms-dbmi/CHIEF + description: "Clinical Histopathology Imaging Evaluation Foundation model integrating histology images and clinical context for pan-cancer analysis." + tags: [foundation-models, multi-modal-foundation-models] + tasks: [Foundation Model] + modalities: [Multi-Modal] + organism: [] + api: false + + - id: clawbio + name: "ClawBio" + type: model + url: https://github.com/ClawBio/ClawBio + description: "Bioinformatics-native AI agent skill library with local-first pharmacogenomics, ancestry PCA, semantic similarity, nutrigenomics, and metagenomics skills." + tags: [llm-for-biology] + tasks: [Language Modeling] + modalities: [Text] + organism: [] + api: false + + - id: concerto + name: "Concerto" + type: model + url: https://github.com/melobio/Concerto-reproducibility + description: "Contrastive self-supervised learning framework for single-cell multimodal data integration, batch correction, and reference-query mapping." + tags: [foundation-models, multi-omics-foundation-models, single-cell-foundation-models] + tasks: [Foundation Model] + modalities: [Multi-Omics, Single Cell] + organism: [] + api: false + + - id: conch + name: "CONCH" + type: model + url: https://github.com/mahmoodlab/CONCH + description: "Vision-language foundation model for computational pathology trained with contrastive captioning on pathology image–text pairs." + tags: [foundation-models, single-cell-foundation-models, spatial-foundation-models] + tasks: [Foundation Model] + modalities: [Single Cell, Spatial Transcriptomics] + organism: [] + api: false + + - id: cyclecdr + name: "cycleCDR" + type: model + url: https://github.com/hliulab/cycleCDR + description: "Interpretable cycle-consistency framework for modeling cellular responses to drug perturbations." + tags: [drug-discovery, drug-response-prediction] + tasks: [Drug Discovery, Drug Response Prediction] + modalities: [Small Molecule] + organism: [] + api: false + + - id: deepaeg + name: "DeepAEG" + type: model + url: https://github.com/zhejiangzhuque/DeepAEG + description: "GNN embedding + attention mechanism." + tags: [drug-discovery, drug-response-prediction] + tasks: [Drug Discovery, Drug Response Prediction] + modalities: [Small Molecule] + organism: [] + api: false + + - id: deepdsc + name: "DeepDSC" + type: model + url: https://ieeexplore-ieee-org.ezp2.lib.umn.edu/stamp/stamp.jsp?tp=&arnumber=8723620&tag=1 + description: "Autoencoder + fully connected NN." + tags: [drug-discovery, drug-response-prediction] + tasks: [Drug Discovery, Drug Response Prediction] + modalities: [Small Molecule] + organism: [] + api: false + + - id: deepdta + name: "DeepDTA" + type: model + url: https://github.com/hkmztrk/DeepDTA + description: "Deep learning model using CNNs on protein sequences and drug SMILES." + tags: [drug-discovery, drug-target-interaction] + tasks: [Drug Discovery, Drug Target Interaction] + modalities: [Protein, Small Molecule] + organism: [] + api: false + + - id: deeppurpose + name: "DeepPurpose" + type: model + url: https://github.com/kexinhuang12345/DeepPurpose + description: "Deep learning library for drug repurposing." + tags: [drug-discovery, drug-repurposing] + tasks: [Drug Discovery, Drug Repurposing] + modalities: [Small Molecule] + organism: [] + api: false + + - id: deepsea + name: "DeepSEA" + type: model + url: http://deepsea.princeton.edu/ + description: "Deep learning framework for predicting chromatin effects of sequence alterations with single-nucleotide sensitivity across thousands of chromatin features." + tags: [foundation-models, genomics-foundation-models] + tasks: [Foundation Model] + modalities: [Genomics] + organism: [] + api: false + + - id: dgdrp + name: "DGDRP" + type: model + url: https://github.com/minwoopak/heteronet + description: "Multi-view embedding neural network." + tags: [drug-discovery, drug-response-prediction] + tasks: [Drug Discovery, Drug Response Prediction] + modalities: [Small Molecule] + organism: [] + api: false + + - id: diffdock + name: "DiffDock" + type: model + url: https://github.com/gcorso/DiffDock + description: "Diffusion generative model for molecular docking, predicting the binding pose of small molecules to protein targets." + tags: [drug-discovery, molecular-generation] + tasks: [Drug Discovery, Molecular Generation] + modalities: [Small Molecule] + organism: [] + api: false + + - id: diffsbdd + name: "DiffSBDD" + type: model + url: https://github.com/arneschneuing/DiffSBDD + description: "Equivariant diffusion model for structure-based drug design that generates molecules and binding conformations for protein targets." + tags: [drug-discovery, molecular-generation] + tasks: [Drug Discovery, Molecular Generation] + modalities: [Small Molecule] + organism: [] + api: false + + - id: dnabert + name: "DNABERT" + type: model + url: https://github.com/jerryji1993/DNABERT + description: "Pre-trained bidirectional encoder for DNA sequence analysis." + tags: [foundation-models, genomics-foundation-models] + tasks: [Foundation Model] + modalities: [Genomics] + organism: [] + api: false + + - id: dnabert_2 + name: "DNABERT-2" + type: model + url: https://github.com/Zhihan1996/DNABERT_2 + description: "Improved genome foundation model with efficient tokenization." + tags: [foundation-models, genomics-foundation-models] + tasks: [Foundation Model] + modalities: [Genomics] + organism: [] + api: false + + - id: drgat + name: "drGAT" + type: model + url: https://github.com/inoue0426/drGAT + description: "Attention-based model for drug response prediction with gene explainability." + tags: [drug-discovery, drug-response-prediction] + tasks: [Drug Discovery, Drug Response Prediction] + modalities: [Small Molecule] + organism: [] + api: false + + - id: drugban + name: "DrugBAN" + type: model + url: https://github.com/peizhenbai/DrugBAN + description: "Bilinear attention network for interpretable DTI prediction." + tags: [drug-discovery, drug-target-interaction] + tasks: [Drug Discovery, Drug Target Interaction] + modalities: [Protein, Small Molecule] + organism: [] + api: false + + - id: druml + name: "DRUML" + type: model + url: https://github.com/CutillasLab/DRUMLR + description: "Ensemble machine learning framework combining standard ML with deep learning to systematically rank anti-cancer drugs from proteomics and RNA-seq data." + tags: [drug-discovery, drug-response-prediction] + tasks: [Drug Discovery, Drug Response Prediction] + modalities: [Small Molecule] + organism: [] + api: false + + - id: dtinet + name: "DTINet" + type: model + url: https://github.com/luoyunan/DTINet + description: "Network-based framework integrating heterogeneous biological data for DTI prediction." + tags: [drug-discovery, drug-target-interaction] + tasks: [Drug Discovery, Drug Target Interaction] + modalities: [Protein, Small Molecule] + organism: [] + api: false + + - id: enformer + name: "Enformer" + type: model + url: https://github.com/deepmind/deepmind-research/tree/master/enformer + description: "Transformer model predicting gene expression from DNA sequence." + tags: [foundation-models, genomics-foundation-models] + tasks: [Foundation Model] + modalities: [Genomics] + organism: [] + api: false + + - id: esm3 + name: "ESM3" + type: model + url: https://github.com/evolutionaryscale/esm + description: "Multimodal protein language model that jointly reasons over sequence, structure, and function for generative protein design and engineering." + tags: [foundation-models, protein-foundation-models, protein-structure-prediction-and-design] + tasks: [Foundation Model, Protein Structure Prediction] + modalities: [Protein] + organism: [] + api: false + + - id: esmfold + name: "ESMFold" + type: model + url: https://github.com/facebookresearch/esm + description: "Fast protein structure prediction using language model embeddings." + tags: [foundation-models, protein-foundation-models, protein-structure-prediction-and-design] + tasks: [Foundation Model, Protein Structure Prediction] + modalities: [Protein] + organism: [] + api: false + + - id: evo + name: "Evo" + type: model + url: https://github.com/evo-design/evo + description: "Long-context genomic foundation model (up to 1M tokens)." + tags: [foundation-models, genomics-foundation-models] + tasks: [Foundation Model] + modalities: [Genomics] + organism: [] + api: false + + - id: evodiff + name: "EvoDiff" + type: model + url: https://github.com/microsoft/evodiff + description: "Discrete diffusion framework for protein sequence generation trained on evolutionary-scale data, supporting unconditional generation, disordered region design, and functional motif scaffolding. [ [paper-2023](https://www.biorxiv.org/content/10.1101/2023.09.11.556673v1) ]" + tags: [foundation-models, protein-foundation-models, protein-structure-prediction-and-design] + tasks: [Foundation Model, Protein Structure Prediction] + modalities: [Protein] + organism: [] + api: false + + - id: evolutionary_scale_modeling_esm + name: "Evolutionary Scale Modeling (ESM)" + type: model + url: https://github.com/facebookresearch/esm + description: "Protein embeddings." + tags: [foundation-models, pre-trained-embedding, protein-foundation-models] + tasks: [Foundation Model] + modalities: [Protein] + organism: [] + api: false + + - id: gears + name: "GEARS" + type: model + url: https://github.com/snap-stanford/GEARS + description: "Graph-based model for predicting transcriptional responses to single and combinatorial genetic perturbations using biological priors." + tags: [foundation-models, single-cell-foundation-models, transcriptomics-foundation-models] + tasks: [Foundation Model] + modalities: [Single Cell, Transcriptomics] + organism: [] + api: false + + - id: genecompass + name: "GeneCompass" + type: model + url: https://github.com/xCompass-AI/GeneCompass + description: "Large-scale foundation model integrating DNA regulatory sequences and single-cell transcriptomics from 120M+ cells across multiple species for gene regulation prediction." + tags: [foundation-models, multi-omics-foundation-models, single-cell-foundation-models] + tasks: [Foundation Model] + modalities: [Multi-Omics, Single Cell] + organism: [] + api: false + + - id: geneformer + name: "Geneformer" + type: model + url: https://huggingface.co/ctheodoris/Geneformer + description: "Context-aware, attention-based deep learning model pretrained on a large corpus of single-cell transcriptomes." + tags: [foundation-models, single-cell-foundation-models, transcriptomics-foundation-models] + tasks: [Foundation Model] + modalities: [Single Cell, Transcriptomics] + organism: [] + api: false + + - id: genegpt + name: "GeneGPT" + type: model + url: https://github.com/ncbi/GeneGPT + description: "LLM for biomedical information, integrated with various APIs." + tags: [llm-for-biology] + tasks: [Language Modeling] + modalities: [Text] + organism: [] + api: false + + - id: genept + name: "GenePT" + type: model + url: https://github.com/yiqunchen/GenePT + description: "Foundation LLM for single-cell data." + tags: [llm-for-biology] + tasks: [Language Modeling] + modalities: [Text] + organism: [] + api: false + + - id: gigapath + name: "GigaPath" + type: model + url: https://github.com/prov-gigapath/prov-gigapath + description: "Slide-level digital pathology foundation model pretrained on 1.3 billion pathology image tokens from whole-slide images." + tags: [foundation-models, single-cell-foundation-models, spatial-foundation-models] + tasks: [Foundation Model] + modalities: [Single Cell, Spatial Transcriptomics] + organism: [] + api: false + + - id: glue + name: "GLUE" + type: model + url: https://github.com/gao-lab/GLUE + description: "Graph-Linked Unified Embedding framework for unpaired single-cell multi-omics data integration across RNA, ATAC, methylation, and protein modalities." + tags: [foundation-models, multi-omics-foundation-models, single-cell-foundation-models] + tasks: [Foundation Model] + modalities: [Multi-Omics, Single Cell] + organism: [] + api: false + + - id: gpn_genomic_pre_trained_network + name: "GPN (Genomic Pre-trained Network)" + type: model + url: https://github.com/songlab-cal/gpn + description: "Masked language model for DNA sequences enabling zero-shot variant effect prediction without requiring functional annotations." + tags: [foundation-models, genomics-foundation-models] + tasks: [Foundation Model] + modalities: [Genomics] + organism: [] + api: false + + - id: graphdta + name: "GraphDTA" + type: model + url: https://github.com/thinng/GraphDTA + description: "Graph neural network–based DTI prediction using molecular graphs." + tags: [drug-discovery, drug-target-interaction] + tasks: [Drug Discovery, Drug Target Interaction] + modalities: [Protein, Small Molecule] + organism: [] + api: false + + - id: grover + name: "GROVER" + type: model + url: https://github.com/tencent-ailab/grover + description: "Self-supervised graph transformer for large-scale molecular representation learning from unlabeled compounds." + tags: [compound-embedding, compound-foundation-models, foundation-models] + tasks: [Foundation Model] + modalities: [Small Molecule] + organism: [] + api: false + + - id: hidra + name: "HiDRA" + type: model + url: https://github.com/bsml320/HiDRA + description: "Hierarchical network model incorporating gene and pathway-level information for cancer drug response prediction." + tags: [drug-discovery, drug-response-prediction] + tasks: [Drug Discovery, Drug Response Prediction] + modalities: [Small Molecule] + organism: [] + api: false + + - id: hyenadna + name: "HyenaDNA" + type: model + url: https://github.com/HazyResearch/hyena-dna + description: "Long-range genomic foundation model handling sequences up to 1M tokens with sub-quadratic attention." + tags: [foundation-models, genomics-foundation-models] + tasks: [Foundation Model] + modalities: [Genomics] + organism: [] + api: false + + - id: jamie + name: "JAMIE" + type: model + url: https://github.com/Oafish1/JAMIE + description: "Joint variational autoencoder for multimodal single-cell data imputation and embedding." + tags: [foundation-models, multi-omics-foundation-models, single-cell-foundation-models] + tasks: [Foundation Model] + modalities: [Multi-Omics, Single Cell] + organism: [] + api: false + + - id: jtvae + name: "JTVAE" + type: model + url: https://github.com/wengong-jin/icml18-jtnn + description: "Junction tree variational autoencoder for molecular graph generation that guarantees chemical validity via a hierarchical tree decomposition." + tags: [drug-discovery, molecular-generation] + tasks: [Drug Discovery, Molecular Generation] + modalities: [Small Molecule] + organism: [] + api: false + + - id: matcha + name: "Matcha" + type: model + url: https://github.com/LigandPro/Matcha + description: "Multi-stage Riemannian flow matching model for physically valid molecular docking with scoring, pose filtering, and benchmarks." + tags: [drug-discovery, molecular-generation] + tasks: [Drug Discovery, Molecular Generation] + modalities: [Small Molecule] + organism: [] + api: false + + - id: mcpinn + name: "MCPINN" + type: model + url: https://github.com/mhlee0903/multi_channels_PINN + description: "Drug discovery via compound-protein interaction and machine learning." + tags: [compound-protein-interaction, drug-discovery] + tasks: [Compound-Protein Interaction, Drug Discovery] + modalities: [Protein, Small Molecule] + organism: [] + api: false + + - id: midas + name: "MIDAS" + type: model + url: https://github.com/labomics/midas + description: "Mosaic integration and differential accessibility model for single-cell multi-omics data that handles arbitrary missing-modality combinations across transcriptomics, chromatin accessibility, and proteomics." + tags: [foundation-models, multi-omics-foundation-models, single-cell-foundation-models] + tasks: [Foundation Model] + modalities: [Multi-Omics, Single Cell] + organism: [] + api: false + + - id: mira + name: "MIRA" + type: model + url: https://github.com/cistrome/MIRA + description: "Probabilistic multimodal topic model jointly modeling single-cell transcriptomics and chromatin accessibility for regulatory network inference." + tags: [foundation-models, multi-omics-foundation-models, single-cell-foundation-models] + tasks: [Foundation Model] + modalities: [Multi-Omics, Single Cell] + organism: [] + api: false + + - id: mofa + name: "MOFA+" + type: model + url: https://github.com/bioFAM/MOFA2 + description: "Multi-Omics Factor Analysis framework identifying shared axes of variation across bulk and single-cell datasets including RNA, ATAC, proteomics, methylation, and copy number." + tags: [foundation-models, multi-omics-foundation-models, single-cell-foundation-models] + tasks: [Foundation Model] + modalities: [Multi-Omics, Single Cell] + organism: [] + api: false + + - id: mofgcn + name: "MOFGCN" + type: model + url: https://github.com/weiba/MOFGCN/tree/main + description: "GCN + heterogeneous network." + tags: [drug-discovery, drug-response-prediction] + tasks: [Drug Discovery, Drug Response Prediction] + modalities: [Small Molecule] + organism: [] + api: false + + - id: mol2vec + name: "Mol2Vec" + type: model + url: https://github.com/samoturk/mol2vec + description: "Unsupervised molecular embedding method inspired by Word2Vec for learning vector representations of chemical substructures." + tags: [compound-embedding, compound-foundation-models, foundation-models] + tasks: [Foundation Model] + modalities: [Small Molecule] + organism: [] + api: false + + - id: molecular_transformer + name: "Molecular Transformer" + type: model + url: https://github.com/pschwllr/MolecularTransformer + description: "Sequence-to-sequence model for retrosynthesis prediction." + tags: [drug-discovery, molecular-generation] + tasks: [Drug Discovery, Molecular Generation] + modalities: [Small Molecule] + organism: [] + api: false + + - id: molformer + name: "MolFormer" + type: model + url: https://github.com/IBM/molformer + description: "Linear attention transformer pretrained on millions of SMILES strings for efficient molecular embeddings." + tags: [compound-embedding, compound-foundation-models, foundation-models] + tasks: [Foundation Model] + modalities: [Small Molecule] + organism: [] + api: false + + - id: molgpt + name: "MolGPT" + type: model + url: https://github.com/devalab/molgpt + description: "Transformer-based model for molecular generation." + tags: [drug-discovery, molecular-generation] + tasks: [Drug Discovery, Molecular Generation] + modalities: [Small Molecule] + organism: [] + api: false + + - id: molt5 + name: "MolT5" + type: model + url: https://github.com/blender-nlp/MolT5 + description: "Language model for molecular tasks bridging text and SMILES, enabling molecule captioning and text-driven molecule generation." + tags: [llm-for-biology] + tasks: [Language Modeling] + modalities: [Text] + organism: [] + api: false + + - id: moltrans + name: "MolTrans" + type: model + url: https://github.com/kexinhuang12345/MolTrans + description: "Transformer-based DTI model leveraging molecular substructures." + tags: [drug-discovery, drug-target-interaction] + tasks: [Drug Discovery, Drug Target Interaction] + modalities: [Protein, Small Molecule] + organism: [] + api: false + + - id: multigrate + name: "Multigrate" + type: model + url: https://github.com/theislab/multigrate + description: "Asymmetric multi-omics variational autoencoder for integrating single-cell data across RNA, ATAC, and protein modalities with missing-modality support." + tags: [foundation-models, multi-omics-foundation-models, single-cell-foundation-models] + tasks: [Foundation Model] + modalities: [Multi-Omics, Single Cell] + organism: [] + api: false + + - id: multivi + name: "MultiVI" + type: model + url: https://github.com/scverse/scvi-tools + description: "Multi-modal variational autoencoder for integrating paired and unpaired single-cell RNA-seq and ATAC-seq measurements into a unified latent space." + tags: [foundation-models, multi-omics-foundation-models, single-cell-foundation-models] + tasks: [Foundation Model] + modalities: [Multi-Omics, Single Cell] + organism: [] + api: false + + - id: musk + name: "MUSK" + type: model + url: https://github.com/lilab-stanford/MUSK + description: "Vision-language foundation model for precision oncology analyzing multimodal paired text and pathology image data for biomarker prediction and retrieval." + tags: [foundation-models, multi-modal-foundation-models] + tasks: [Foundation Model] + modalities: [Multi-Modal] + organism: [] + api: false + + - id: neodti + name: "NeoDTI" + type: model + url: https://github.com/FangpingWan/NeoDTI + description: "Library for drug-target interaction prediction." + tags: [drug-discovery, drug-target-interaction] + tasks: [Drug Discovery, Drug Target Interaction] + modalities: [Protein, Small Molecule] + organism: [] + api: false + + - id: nicheformer + name: "Nicheformer" + type: model + url: https://github.com/theislab/nicheformer + description: "Foundation model for single-cell and spatial omics using a transformer architecture with positional embeddings to encode spatial cell information." + tags: [foundation-models, single-cell-foundation-models, spatial-foundation-models] + tasks: [Foundation Model] + modalities: [Single Cell, Spatial Transcriptomics] + organism: [] + api: false + + - id: nucleotide_transformer + name: "Nucleotide Transformer" + type: model + url: https://github.com/instadeepai/nucleotide-transformer + description: "Foundation model for genomic sequences across multiple species." + tags: [foundation-models, genomics-foundation-models] + tasks: [Foundation Model] + modalities: [Genomics] + organism: [] + api: false + + - id: omegafold + name: "OmegaFold" + type: model + url: https://github.com/HeliXonProtein/OmegaFold + description: "High-resolution de novo protein structure prediction from sequence." + tags: [foundation-models, protein-foundation-models, protein-structure-prediction-and-design] + tasks: [Foundation Model, Protein Structure Prediction] + modalities: [Protein] + organism: [] + api: false + + - id: openfold + name: "OpenFold" + type: model + url: https://github.com/aqlaboratory/openfold + description: "Trainable, memory-efficient open-source reproduction of AlphaFold2 enabling custom protein structure prediction workflows." + tags: [foundation-models, protein-foundation-models, protein-structure-prediction-and-design] + tasks: [Foundation Model, Protein Structure Prediction] + modalities: [Protein] + organism: [] + api: false + + - id: paccmannrl + name: "PaccMannRL" + type: model + url: https://github.com/PaccMann/paccmann_generator + description: "Reinforcement learning-based generative model for de novo hit-like anticancer molecule design from transcriptomic data." + tags: [drug-discovery, molecular-generation] + tasks: [Drug Discovery, Molecular Generation] + modalities: [Small Molecule] + organism: [] + api: false + + - id: pathomicfusion + name: "PathomicFusion" + type: model + url: https://github.com/mahmoodlab/PathomicFusion + description: "Integrated framework fusing histopathology and genomic features via CNN, GNN, and attention gating for cancer diagnosis and prognosis." + tags: [foundation-models, multi-modal-foundation-models] + tasks: [Foundation Model] + modalities: [Multi-Modal] + organism: [] + api: false + + - id: phikon + name: "Phikon" + type: model + url: https://huggingface.co/owkin/phikon + description: "ViT-based pathology foundation model pretrained with iBOT self-supervision on TCGA whole-slide images." + tags: [foundation-models, single-cell-foundation-models, spatial-foundation-models] + tasks: [Foundation Model] + modalities: [Single Cell, Spatial Transcriptomics] + organism: [] + api: false + + - id: plip + name: "PLIP" + type: model + url: https://github.com/PathologyFoundation/plip + description: "Vision-language foundation model for pathology trained with contrastive learning on pathology image–text pairs for image classification and text-to-image retrieval." + tags: [foundation-models, multi-modal-foundation-models] + tasks: [Foundation Model] + modalities: [Multi-Modal] + organism: [] + api: false + + - id: porpoise + name: "PORPOISE" + type: model + url: https://github.com/mahmoodlab/PORPOISE + description: "Pan-cancer integrative histology-genomic analysis framework using multimodal deep learning for patient stratification." + tags: [foundation-models, multi-modal-foundation-models] + tasks: [Foundation Model] + modalities: [Multi-Modal] + organism: [] + api: false + + - id: prnet + name: "PRNet" + type: model + url: https://github.com/Perturbation-Response-Prediction/PRnet + description: "Deep generative model for predicting transcriptional responses to novel chemical perturbations for drug discovery." + tags: [drug-discovery, drug-response-prediction] + tasks: [Drug Discovery, Drug Response Prediction] + modalities: [Small Molecule] + organism: [] + api: false + + - id: progen2 + name: "ProGen2" + type: model + url: https://github.com/salesforce/progen + description: "Protein language model trained on diverse protein families for sequence generation and fitness prediction." + tags: [foundation-models, pre-trained-embedding, protein-foundation-models] + tasks: [Foundation Model] + modalities: [Protein] + organism: [] + api: false + + - id: proteinmpnn + name: "ProteinMPNN" + type: model + url: https://github.com/dauparas/ProteinMPNN + description: "Deep learning model for protein sequence design given backbone structure." + tags: [foundation-models, protein-foundation-models, protein-structure-prediction-and-design] + tasks: [Foundation Model, Protein Structure Prediction] + modalities: [Protein] + organism: [] + api: false + + - id: prottrans + name: "ProtTrans" + type: model + url: https://github.com/agemagician/ProtTrans + description: "Suite of protein language models (ProtBERT, ProtT5, ProtXLNet) trained on billions of protein sequences from UniRef and BFD." + tags: [foundation-models, pre-trained-embedding, protein-foundation-models] + tasks: [Foundation Model] + modalities: [Protein] + organism: [] + api: false + + - id: recover + name: "RECOVER" + type: model + url: https://github.com/RECOVERcoalition/Recover + description: "Machine learning framework for predicting synergistic drug combination responses across cell lines." + tags: [drug-discovery, drug-response-prediction] + tasks: [Drug Discovery, Drug Response Prediction] + modalities: [Small Molecule] + organism: [] + api: false + + - id: reinvent + name: "REINVENT" + type: model + url: https://github.com/MolecularAI/Reinvent + description: "Reinforcement learning for de novo drug design." + tags: [drug-discovery, molecular-generation] + tasks: [Drug Discovery, Molecular Generation] + modalities: [Small Molecule] + organism: [] + api: false + + - id: release + name: "ReLeaSE" + type: model + url: https://github.com/isayev/ReLeaSE + description: "Deep reinforcement learning framework for de novo drug design combining a generative and predictive model." + tags: [drug-discovery, molecular-generation] + tasks: [Drug Discovery, Molecular Generation] + modalities: [Small Molecule] + organism: [] + api: false + + - id: rfdiffusion + name: "RFdiffusion" + type: model + url: https://github.com/RosettaCommons/RFdiffusion + description: "Generative model for protein backbone design using diffusion." + tags: [foundation-models, protein-foundation-models, protein-structure-prediction-and-design] + tasks: [Foundation Model, Protein Structure Prediction] + modalities: [Protein] + organism: [] + api: false + + - id: rosettafold + name: "RoseTTAFold" + type: model + url: https://github.com/RosettaCommons/RoseTTAFold + description: "Three-track neural network for protein structure prediction." + tags: [foundation-models, protein-foundation-models, protein-structure-prediction-and-design] + tasks: [Foundation Model, Protein Structure Prediction] + modalities: [Protein] + organism: [] + api: false + + - id: saprot + name: "SaProt" + type: model + url: https://github.com/westlake-reup/SaProt + description: "Structure-aware protein language model using structure-aware tokens that encode both sequence and backbone geometry for improved function prediction." + tags: [foundation-models, protein-foundation-models, protein-structure-prediction-and-design] + tasks: [Foundation Model, Protein Structure Prediction] + modalities: [Protein] + organism: [] + api: false + + - id: saturn + name: "SATURN" + type: model + url: https://github.com/snap-stanford/SATURN + description: "Transformer-based model integrating gene expression and protein sequences via a protein language model to learn unified multi-species cell embeddings." + tags: [foundation-models, single-cell-foundation-models, transcriptomics-foundation-models] + tasks: [Foundation Model] + modalities: [Single Cell, Transcriptomics] + organism: [] + api: false + + - id: scarches + name: "scArches" + type: model + url: https://github.com/theislab/scarches + description: "Transfer learning framework for mapping new single-cell datasets onto pre-trained reference atlases across batches, conditions, and modalities." + tags: [domain-alignment, foundation-models, single-cell-foundation-models] + tasks: [Domain Alignment, Foundation Model] + modalities: [Single Cell] + organism: [] + api: false + + - id: scbert + name: "scBERT" + type: model + url: https://github.com/TencentAILabHealthcare/scBERT + description: "BERT-based foundation model pretrained on large-scale scRNA-seq data for cell type annotation." + tags: [foundation-models, single-cell-foundation-models, transcriptomics-foundation-models] + tasks: [Foundation Model] + modalities: [Single Cell, Transcriptomics] + organism: [] + api: false + + - id: scbutterfly + name: "scButterfly" + type: model + url: https://github.com/BioX-NKU/scButterfly + description: "Dual-aligned variational autoencoder for single-cell cross-modality translation between paired and unpaired multiomics data." + tags: [foundation-models, multi-omics-foundation-models, single-cell-foundation-models] + tasks: [Foundation Model] + modalities: [Multi-Omics, Single Cell] + organism: [] + api: false + + - id: scfoundation + name: "scFoundation" + type: model + url: https://github.com/biomap-research/scFoundation + description: "Large-scale foundation model for single-cell gene expression, enabling multiple downstream tasks." + tags: [foundation-models, single-cell-foundation-models, transcriptomics-foundation-models] + tasks: [Foundation Model] + modalities: [Single Cell, Transcriptomics] + organism: [] + api: false + + - id: scgpt + name: "scGPT" + type: model + url: https://github.com/bowang-lab/scGPT + description: "Transformer-based foundation model pretrained on millions of single-cell profiles." + tags: [foundation-models, single-cell-foundation-models, transcriptomics-foundation-models] + tasks: [Foundation Model] + modalities: [Single Cell, Transcriptomics] + organism: [] + api: false + + - id: scgpt_spatial + name: "scGPT-spatial" + type: model + url: https://github.com/bowang-lab/scGPT-spatial + description: "Extension of scGPT for spatial transcriptomics with continual pretraining and a mixture-of-experts decoder for spatial gene expression analysis." + tags: [foundation-models, single-cell-foundation-models, spatial-foundation-models] + tasks: [Foundation Model] + modalities: [Single Cell, Spatial Transcriptomics] + organism: [] + api: false + + - id: scmulan + name: "scMulan" + type: model + url: https://github.com/SuperBianC/scMulan + description: "Single-cell multi-omic language model pretrained on ~10M cells spanning transcriptomics, epigenomics, and proteomics for cross-omics transfer tasks." + tags: [foundation-models, multi-omics-foundation-models, single-cell-foundation-models] + tasks: [Foundation Model] + modalities: [Multi-Omics, Single Cell] + organism: [] + api: false + + - id: scpair + name: "scPair" + type: model + url: https://github.com/quon-titative-biology/scPair + description: "Bidirectional feedforward network for single-cell multimodal analysis with cross-modality prediction leveraging single-cell atlases." + tags: [foundation-models, multi-omics-foundation-models, single-cell-foundation-models] + tasks: [Foundation Model] + modalities: [Multi-Omics, Single Cell] + organism: [] + api: false + + - id: scprint + name: "scPRINT" + type: model + url: https://github.com/cantinilab/scPRINT + description: "Pretrained on 50M cells for scRNA-seq denoising & zero imputation." + tags: [llm-for-biology] + tasks: [Language Modeling] + modalities: [Text] + organism: [] + api: false + + - id: sei + name: "Sei" + type: model + url: https://github.com/FunctionLab/sei-framework + description: "Sequence-to-function framework learning a genome-wide regulatory activity code from DNA sequences for variant effect prediction." + tags: [foundation-models, genomics-foundation-models] + tasks: [Foundation Model] + modalities: [Genomics] + organism: [] + api: false + + - id: spatialglue + name: "SpatialGlue" + type: model + url: https://github.com/zhanglabtools/SpatialGlue + description: "Graph attention network for spatial multi-omics integration jointly embedding spatial transcriptomics with chromatin accessibility or proteomics." + tags: [foundation-models, multi-omics-foundation-models, single-cell-foundation-models] + tasks: [Foundation Model] + modalities: [Multi-Omics, Single Cell] + organism: [] + api: false + + - id: targetdiff + name: "TargetDiff" + type: model + url: https://github.com/guanjq/targetdiff + description: "3D equivariant diffusion model for structure-based drug design." + tags: [drug-discovery, molecular-generation] + tasks: [Drug Discovery, Molecular Generation] + modalities: [Small Molecule] + organism: [] + api: false + + - id: tgsa + name: "TGSA" + type: model + url: https://github.com/violet-sto/TGSA + description: "Tumor gene set and attention-based model leveraging biological pathway knowledge for drug response prediction." + tags: [drug-discovery, drug-response-prediction] + tasks: [Drug Discovery, Drug Response Prediction] + modalities: [Small Molecule] + organism: [] + api: false + + - id: toad + name: "TOAD" + type: model + url: https://github.com/mahmoodlab/TOAD + description: "Tumor Origin Assessment via Deep-learning; weakly-supervised multi-task model predicting cancer primary origin from H&E whole-slide images." + tags: [foundation-models, multi-modal-foundation-models] + tasks: [Foundation Model] + modalities: [Multi-Modal] + organism: [] + api: false + + - id: tosica + name: "TOSICA" + type: model + url: https://github.com/JackieHanlaopo/TOSICA + description: "Transformer-based framework for one-stop interpretable cell-type annotation supporting cross-dataset and cross-species transfer." + tags: [domain-alignment, foundation-models, single-cell-foundation-models] + tasks: [Domain Alignment, Foundation Model] + modalities: [Single Cell] + organism: [] + api: false + + - id: totalvi + name: "totalVI" + type: model + url: https://github.com/scverse/scvi-tools + description: "Probabilistic framework for joint analysis of paired scRNA-seq and protein (CITE-seq) data enabling multi-modal cell state representation across single-cell datasets." + tags: [foundation-models, multi-omics-foundation-models, single-cell-foundation-models] + tasks: [Foundation Model] + modalities: [Multi-Omics, Single Cell] + organism: [] + api: false + + - id: transformercpi + name: "TransformerCPI" + type: model + url: https://github.com/lifanchen-simm/transformerCPI + description: "CPI prediction using Transformer." + tags: [compound-protein-interaction, drug-discovery] + tasks: [Compound-Protein Interaction, Drug Discovery] + modalities: [Protein, Small Molecule] + organism: [] + api: false + + - id: transigen + name: "TranSiGen" + type: model + url: https://github.com/myzhengSIMM/TranSiGen + description: "Dual-VAE architecture for ligand-based virtual screening, drug response prediction, and drug repurposing using chemical-induced transcriptional profiles." + tags: [drug-discovery, drug-repurposing] + tasks: [Drug Discovery, Drug Repurposing] + modalities: [Small Molecule] + organism: [] + api: false + + - id: uce + name: "UCE" + type: model + url: https://github.com/snap-stanford/UCE + description: "Universal Cell Embeddings: zero-shot single-cell embedding model trained on 36M cells across species, tissues, and assays without fine-tuning." + tags: [foundation-models, single-cell-foundation-models, transcriptomics-foundation-models] + tasks: [Foundation Model] + modalities: [Single Cell, Transcriptomics] + organism: [] + api: false + + - id: uni + name: "UNI" + type: model + url: https://github.com/mahmoodlab/UNI + description: "General-purpose self-supervised pathology foundation model trained on 100K+ whole-slide images for diverse computational pathology tasks." + tags: [foundation-models, single-cell-foundation-models, spatial-foundation-models] + tasks: [Foundation Model] + modalities: [Single Cell, Spatial Transcriptomics] + organism: [] + api: false + + - id: uni_mol + name: "Uni-Mol" + type: model + url: https://github.com/deepmodeling/Uni-Mol + description: "3D molecular pretraining framework for universal representation learning on molecules and protein pockets." + tags: [compound-embedding, compound-foundation-models, foundation-models] + tasks: [Foundation Model] + modalities: [Small Molecule] + organism: [] + api: false + + - id: unitednet + name: "UnitedNet" + type: model + url: https://github.com/LiuLab-Bioelectronics-Harvard/UnitedNet + description: "Interpretable multi-task deep neural network for single-cell multi-omics integration spanning transcriptomics, chromatin accessibility, and proteomics." + tags: [foundation-models, multi-omics-foundation-models, single-cell-foundation-models] + tasks: [Foundation Model] + modalities: [Multi-Omics, Single Cell] + organism: [] + api: false + + - id: virchow + name: "Virchow" + type: model + url: https://huggingface.co/paige-ai/Virchow + description: "Million-slide digital pathology foundation model using a vision transformer and self-supervised distillation for tile-level pathology image representation." + tags: [foundation-models, multi-modal-foundation-models] + tasks: [Foundation Model] + modalities: [Multi-Modal] + organism: [] + api: false + + - id: autozyme + name: "AutoZyme" + type: toolkit + url: https://github.com/ElliotXie/autozyme + description: "Autonomous agentic framework that speeds up bioinformatics software (e.g. Scanpy, Seurat) on CPUs while preserving the original results." + tags: [preprocessing-tools] + tasks: [Preprocessing] + modalities: [] + organism: [] + api: false + + - id: biopython + name: "Biopython" + type: toolkit + url: https://biopython.org/ + description: "Collection of Python tools for biological computation including sequence analysis, structure parsing, and database access." + tags: [preprocessing-tools] + tasks: [Preprocessing] + modalities: [] + organism: [] + api: false + + - id: casper + name: "CaSpER" + type: toolkit + url: https://github.com/akdess/CaSpER + description: "CNV identification and visualization by integrative analysis of single-cell or bulk RNA-seq data." + tags: [preprocessing-tools] + tasks: [Preprocessing] + modalities: [] + organism: [] + api: false + + - id: cellcharter + name: "CellCharter" + type: toolkit + url: https://github.com/CSOgroup/cellcharter + description: "Identification and characterization of spatial cell niches from spatial transcriptomics using VAEs and Gaussian mixture models." + tags: [preprocessing-tools] + tasks: [Preprocessing] + modalities: [] + organism: [] + api: false + + - id: cellchat + name: "CellChat" + type: toolkit + url: https://github.com/sqjin/CellChat + description: "Inference and analysis of cell-cell communication ligand-receptor networks from single-cell transcriptomics data." + tags: [preprocessing-tools] + tasks: [Preprocessing] + modalities: [] + organism: [] + api: false + + - id: celltypist + name: "CellTypist" + type: toolkit + url: https://github.com/Teichlab/celltypist + description: "Automated cell type annotation for scRNA-seq." + tags: [preprocessing-tools] + tasks: [Preprocessing] + modalities: [] + organism: [] + api: false + + - id: chatspatial + name: "ChatSpatial" + type: toolkit + url: https://github.com/cafferychen777/ChatSpatial + description: "MCP server for spatial transcriptomics analysis via natural language." + tags: [preprocessing-tools] + tasks: [Preprocessing] + modalities: [] + organism: [] + api: false + + - id: chemistry_development_kit + name: "Chemistry Development Kit" + type: toolkit + url: https://github.com/cdk/cdk + description: "Cheminformatics software & machine learning tools." + tags: [preprocessing-tools] + tasks: [Preprocessing] + modalities: [] + organism: [] + api: false + + - id: commot + name: "COMMOT" + type: toolkit + url: https://github.com/zcang/COMMOT + description: "Optimal transport-based framework for screening cell-cell communication in spatial transcriptomics." + tags: [preprocessing-tools] + tasks: [Preprocessing] + modalities: [] + organism: [] + api: false + + - id: deepchem + name: "DeepChem" + type: toolkit + url: https://github.com/deepchem/deepchem + description: "Deep learning library for drug discovery, quantum chemistry, and materials science." + tags: [preprocessing-tools] + tasks: [Preprocessing] + modalities: [] + organism: [] + api: false + + - id: deeptalk + name: "DeepTalk" + type: toolkit + url: https://github.com/JiangBioLab/DeepTalk + description: "Graph attention network for deciphering cell-cell communication from spatial transcriptomics data." + tags: [preprocessing-tools] + tasks: [Preprocessing] + modalities: [] + organism: [] + api: false + + - id: doubletfinder + name: "DoubletFinder" + type: toolkit + url: https://github.com/chris-mcginnis-ucsf/DoubletFinder + description: "Machine learning approach for detecting multiplet (doublet) artifacts in single-cell RNA-seq data." + tags: [preprocessing-tools] + tasks: [Preprocessing] + modalities: [] + organism: [] + api: false + + - id: flashdeconv + name: "FlashDeconv" + type: toolkit + url: https://github.com/cafferychen777/flashdeconv + description: "High-performance spatial transcriptomics deconvolution (~1M spots in ~3 min)." + tags: [preprocessing-tools] + tasks: [Preprocessing] + modalities: [] + organism: [] + api: false + + - id: gromacs + name: "GROMACS" + type: toolkit + url: https://www.gromacs.org/ + description: "Molecular dynamics simulation package for biochemical molecules." + tags: [preprocessing-tools] + tasks: [Preprocessing] + modalities: [] + organism: [] + api: false + + - id: harmony + name: "Harmony" + type: toolkit + url: https://github.com/immunogenomics/harmony + description: "Fast and scalable integration of single-cell data across datasets, conditions, technologies, and species." + tags: [preprocessing-tools] + tasks: [Preprocessing] + modalities: [] + organism: [] + api: false + + - id: kallisto + name: "kallisto" + type: toolkit + url: https://pachterlab.github.io/kallisto/ + description: "Near-optimal RNA-seq quantification using pseudoalignment for fast transcript abundance estimation." + tags: [preprocessing-tools] + tasks: [Preprocessing] + modalities: [] + organism: [] + api: false + + - id: linger + name: "LINGER" + type: toolkit + url: https://github.com/Durenlab/LINGER + description: "Neural network for gene regulatory network inference from single-cell multiome (RNA+ATAC-seq) data with bulk data pretraining." + tags: [preprocessing-tools] + tasks: [Preprocessing] + modalities: [] + organism: [] + api: false + + - id: mdanalysis + name: "MDAnalysis" + type: toolkit + url: https://www.mdanalysis.org/ + description: "Python library for analyzing and altering molecular dynamics simulation trajectories." + tags: [preprocessing-tools] + tasks: [Preprocessing] + modalities: [] + organism: [] + api: false + + - id: mogonet + name: "MOGONET" + type: toolkit + url: https://github.com/txWang/MOGONET + description: "Multi-omics graph convolutional network framework for patient classification and biomarker identification." + tags: [preprocessing-tools] + tasks: [Preprocessing] + modalities: [] + organism: [] + api: false + + - id: monocle3 + name: "Monocle3" + type: toolkit + url: https://cole-trapnell-lab.github.io/monocle3/ + description: "Single-cell trajectory analysis tool for learning developmental trajectories and ordering cells in pseudotime." + tags: [preprocessing-tools] + tasks: [Preprocessing] + modalities: [] + organism: [] + api: false + + - id: ncem + name: "NCEM" + type: toolkit + url: https://github.com/theislab/ncem + description: "GNN-based model for learning intercellular communication from spatial graphs of cells." + tags: [preprocessing-tools] + tasks: [Preprocessing] + modalities: [] + organism: [] + api: false + + - id: numbat + name: "Numbat" + type: toolkit + url: https://github.com/kharchenkolab/numbat + description: "Haplotype-aware copy number variation inference from single-cell RNA-seq using hidden Markov models." + tags: [preprocessing-tools] + tasks: [Preprocessing] + modalities: [] + organism: [] + api: false + + - id: openmm + name: "OpenMM" + type: toolkit + url: https://openmm.org/ + description: "High-performance toolkit for molecular simulation and GPU-accelerated MD." + tags: [preprocessing-tools] + tasks: [Preprocessing] + modalities: [] + organism: [] + api: false + + - id: rdkit + name: "RDKit" + type: toolkit + url: https://github.com/rdkit/rdkit + description: "Cheminformatics software & machine learning toolkit." + tags: [preprocessing-tools] + tasks: [Preprocessing] + modalities: [] + organism: [] + api: false + + - id: scanpy + name: "Scanpy" + type: toolkit + url: https://scanpy.readthedocs.io/en/stable/ + description: "Python library for scRNA-seq analysis." + tags: [preprocessing-tools] + tasks: [Preprocessing] + modalities: [] + organism: [] + api: false + + - id: scenic + name: "SCENIC" + type: toolkit + url: https://github.com/aertslab/SCENIC + description: "Single-cell regulatory network inference and clustering linking transcription factors to co-expressed gene modules." + tags: [preprocessing-tools] + tasks: [Preprocessing] + modalities: [] + organism: [] + api: false + + - id: scipenn + name: "sciPENN" + type: toolkit + url: https://github.com/jlakkis/sciPENN + description: "RNN-based method for simultaneous protein expression prediction, uncertainty estimation, and cell-type label transfer from CITE-seq and scRNA-seq data." + tags: [preprocessing-tools] + tasks: [Preprocessing] + modalities: [] + organism: [] + api: false + + - id: scvelo + name: "scVelo" + type: toolkit + url: https://github.com/theislab/scvelo + description: "RNA velocity estimation for single-cell transcriptomics, inferring the direction and speed of cell differentiation." + tags: [preprocessing-tools] + tasks: [Preprocessing] + modalities: [] + organism: [] + api: false + + - id: scvi_tools + name: "scvi-tools" + type: toolkit + url: https://scvi-tools.org/ + description: "Probabilistic models for single-cell omics data analysis." + tags: [preprocessing-tools] + tasks: [Preprocessing] + modalities: [] + organism: [] + api: false + + - id: seurat + name: "Seurat" + type: toolkit + url: https://satijalab.org/seurat/ + description: "R library for scRNA-seq analysis." + tags: [preprocessing-tools] + tasks: [Preprocessing] + modalities: [] + organism: [] + api: false + + - id: squidpy + name: "Squidpy" + type: toolkit + url: https://squidpy.readthedocs.io/ + description: "Python library for spatial single-cell analysis." + tags: [preprocessing-tools] + tasks: [Preprocessing] + modalities: [] + organism: [] + api: false + + - id: stagate + name: "STAGATE" + type: toolkit + url: https://github.com/RucDongLab/STAGATE + description: "Adaptive graph attention auto-encoder for spatial domain identification in spatial transcriptomics." + tags: [preprocessing-tools] + tasks: [Preprocessing] + modalities: [] + organism: [] + api: false + + - id: star + name: "STAR" + type: toolkit + url: https://github.com/alexdobin/STAR + description: "Ultrafast universal RNA-seq aligner with support for spliced alignment and single-cell quantification via STARsolo." + tags: [preprocessing-tools] + tasks: [Preprocessing] + modalities: [] + organism: [] + api: false + + - id: tigon + name: "TIGON" + type: toolkit + url: https://github.com/yutongo/TIGON + description: "Neural optimal transport method for reconstructing growth and dynamic trajectories from single-cell transcriptomics." + tags: [preprocessing-tools] + tasks: [Preprocessing] + modalities: [] + organism: [] + api: false diff --git a/upstream/inoue0426-awesome-computational-biology/catalogue/docs/data/SCHEMA.md b/upstream/inoue0426-awesome-computational-biology/catalogue/docs/data/SCHEMA.md new file mode 100644 index 0000000..170de65 --- /dev/null +++ b/upstream/inoue0426-awesome-computational-biology/catalogue/docs/data/SCHEMA.md @@ -0,0 +1,81 @@ +--- +title: "Resource Data Schema (`docs/data/resources.json`)" +task: "" +lineage_type: import +upstream_source: https://github.com/inoue0426/awesome-computational-biology/blob/12d87583/docs/data/SCHEMA.md +upstream_sha: 12d87583 +imported_at: 2026-06-26 +prompt_class: catalogue +upstream_changes: accepted +author: upstream +validated: false +--- + +# Resource Data Schema (`docs/data/resources.json`) + +This document describes the JSON schema used by the GitHub Pages UI. + +## Source of truth and generation flow + +- **Canonical list source:** `README.md` (curated resource bullets) +- Generated from README to YAML: `scripts/sync_resources_from_readme.py` → `data/resources.yml` +- Built artifacts from YAML: `scripts/build_resources.py` → `data/resources.json`, `data/resources.csv`, and `docs/data/resources.json` + +When contributing new resources, update `README.md` first, then regenerate artifacts. + +## Top-level structure + +- `resources.json` is a JSON array. +- Each array item is one resource object. + +## Fields + +### Required fields + +| Field | Type | Notes | +|---|---|---| +| `id` | string | Unique slug. Use lowercase `snake_case`, stable over time. | +| `name` | string | Display name shown in README/UI. | +| `type` | string | Resource category. Current values: `api`, `benchmark`, `database`, `model`, `toolkit`. | +| `url` | string | Canonical landing page URL. | +| `description` | string | One-line, factual summary. | + +### Optional fields + +| Field | Type | Notes | +|---|---|---| +| `tags` | array of strings | Free-form tags. | +| `tasks` | array of strings | Task labels used by Task filter. | +| `modalities` | array of strings | Data modality labels used by Modality filter. | +| `organism` | array of strings | Organism labels. | +| `license` | string | SPDX identifier preferred when known. | +| `api` | boolean | Whether programmatic API access is available. Defaults to `false`. | +| `paper` | string | DOI or URL to preprint/peer-reviewed publication. | +| `updated` | string | Last-known update date, recommended `YYYY-MM-DD`. | + +## Naming and consistency guidance + +- `id` must be globally unique across all resources. +- Prefer concise, stable IDs (e.g., `open_targets_platform`, `alphafold3`). +- Keep `name` aligned with official project/database naming. +- Use short, objective descriptions (avoid marketing language). + +## Example object + +```json +{ + "id": "open_targets_platform", + "name": "Open Targets Platform", + "type": "database", + "url": "https://platform.opentargets.org/", + "description": "Target identification platform integrating genetics, genomics, and drug evidence.", + "tags": ["disease", "drug-discovery"], + "tasks": ["target-identification"], + "modalities": ["genomics"], + "organism": ["human"], + "license": "CC-BY-4.0", + "api": true, + "paper": "https://doi.org/10.1093/nar/gkac1045", + "updated": "2026-01-15" +} +``` diff --git a/upstream/inoue0426-awesome-computational-biology/catalogue/docs/data/resources.json b/upstream/inoue0426-awesome-computational-biology/catalogue/docs/data/resources.json new file mode 100644 index 0000000..dfee624 --- /dev/null +++ b/upstream/inoue0426-awesome-computational-biology/catalogue/docs/data/resources.json @@ -0,0 +1,4996 @@ +--- +title: "Resources" +task: "" +lineage_type: import +upstream_source: https://github.com/inoue0426/awesome-computational-biology/blob/12d87583/docs/data/resources.json +upstream_sha: 12d87583 +imported_at: 2026-06-26 +prompt_class: catalogue +upstream_changes: accepted +author: upstream +validated: false +--- + +[ + { + "id": "chembl_web_services", + "name": "ChEMBL Web Services", + "type": "api", + "url": "https://www.ebi.ac.uk/chembl/ws", + "description": "REST API for bioactive molecules, targets, and bioassays.", + "tags": [ + "api" + ], + "tasks": [], + "modalities": [], + "organism": [], + "api": true + }, + { + "id": "clinicaltrials_gov_api", + "name": "ClinicalTrials.gov API", + "type": "api", + "url": "https://clinicaltrials.gov/api/gui", + "description": "API for querying clinical trial metadata and results.", + "tags": [ + "api" + ], + "tasks": [], + "modalities": [], + "organism": [], + "api": true + }, + { + "id": "ensembl_rest_api", + "name": "Ensembl REST API", + "type": "api", + "url": "https://rest.ensembl.org/", + "description": "API for genomic annotations, variants, genes, and comparative genomics.", + "tags": [ + "api" + ], + "tasks": [], + "modalities": [], + "organism": [], + "api": true + }, + { + "id": "kegg_rest_api", + "name": "KEGG REST API", + "type": "api", + "url": "https://www.kegg.jp/kegg/rest/keggapi.html", + "description": "API for accessing KEGG pathways, compounds, genes, and reactions.", + "tags": [ + "api" + ], + "tasks": [], + "modalities": [], + "organism": [], + "api": true + }, + { + "id": "ncbi_e_utilities", + "name": "NCBI E-utilities", + "type": "api", + "url": "https://www.ncbi.nlm.nih.gov/books/NBK25501/", + "description": "Unified APIs for accessing NCBI databases (Gene, GEO, SRA, PubChem, etc).", + "tags": [ + "api" + ], + "tasks": [], + "modalities": [], + "organism": [], + "api": true + }, + { + "id": "open_targets_platform_api", + "name": "Open Targets Platform API", + "type": "api", + "url": "https://platform.opentargets.org/api", + "description": "API for target–disease associations integrating genetics, genomics, and drug data.", + "tags": [ + "api" + ], + "tasks": [], + "modalities": [], + "organism": [], + "api": true + }, + { + "id": "pubmed_e_utilities_esearch_efetch", + "name": "PubMed E-utilities (esearch/efetch)", + "type": "api", + "url": "https://www.nlm.nih.gov/dataguide/edirect/esearch.html", + "description": "APIs for searching and retrieving biomedical literature from PubMed.", + "tags": [ + "api" + ], + "tasks": [], + "modalities": [], + "organism": [], + "api": true + }, + { + "id": "uniprot_rest_api", + "name": "UniProt REST API", + "type": "api", + "url": "https://www.uniprot.org/help/api", + "description": "Programmatic access to protein sequence and functional annotation data.", + "tags": [ + "api" + ], + "tasks": [], + "modalities": [], + "organism": [], + "api": true + }, + { + "id": "1000_genomes_project", + "name": "1000 Genomes Project", + "type": "benchmark", + "url": "https://www.internationalgenome.org/", + "description": "Reference panel of human genetic variation from 2,504 individuals across 26 populations.", + "tags": [ + "benchmarks-and-datasets" + ], + "tasks": [], + "modalities": [], + "organism": [], + "api": false + }, + { + "id": "bace", + "name": "BACE", + "type": "benchmark", + "url": "https://www.kaggle.com/datasets/gokturkkoch/bace", + "description": "Binary classification and regression dataset for β-secretase 1 (BACE-1) inhibitor binding affinity.", + "tags": [ + "benchmarks-and-datasets" + ], + "tasks": [], + "modalities": [], + "organism": [], + "api": false + }, + { + "id": "beat_aml", + "name": "BEAT AML", + "type": "benchmark", + "url": "https://biodev.github.io/BeatAML2/", + "description": "Functional ex vivo drug sensitivity measurements paired with genomics for acute myeloid leukemia.", + "tags": [ + "benchmarks-and-datasets" + ], + "tasks": [], + "modalities": [], + "organism": [], + "api": false + }, + { + "id": "bento", + "name": "Bento", + "type": "benchmark", + "url": "https://github.com/LigandPro/Bento", + "description": "Protein-ligand docking benchmark covering rigid, flexible, de novo, blind, induced-fit, and covalent docking tasks.", + "tags": [ + "benchmarks-and-datasets" + ], + "tasks": [], + "modalities": [], + "organism": [], + "api": false + }, + { + "id": "bindingdb_curated_sets", + "name": "BindingDB Curated Sets", + "type": "benchmark", + "url": "https://www.bindingdb.org/rwd/bind/chemsearch/marvin/SDFdownload.jsp?all_download=yes", + "description": "Curated binding affinity datasets for protein–ligand interaction benchmarking.", + "tags": [ + "benchmarks-and-datasets" + ], + "tasks": [], + "modalities": [], + "organism": [], + "api": false + }, + { + "id": "cancer_therapeutics_response_portal_ctrp", + "name": "Cancer Therapeutics Response Portal (CTRP)", + "type": "benchmark", + "url": "https://portals.broadinstitute.org/ctrp/", + "description": "Drug sensitivity profiles across ~900 cancer cell lines for >400 compounds.", + "tags": [ + "benchmarks-and-datasets" + ], + "tasks": [], + "modalities": [], + "organism": [], + "api": false + }, + { + "id": "clintox", + "name": "ClinTox", + "type": "benchmark", + "url": "https://tdcommons.ai/single_pred_tasks/tox/#clintox", + "description": "Clinical toxicity dataset contrasting FDA-approved drugs with those that failed clinical trials due to toxicity.", + "tags": [ + "benchmarks-and-datasets" + ], + "tasks": [], + "modalities": [], + "organism": [], + "api": false + }, + { + "id": "cptac_clinical_proteomic_tumor_analysis_consortium", + "name": "CPTAC (Clinical Proteomic Tumor Analysis Consortium)", + "type": "benchmark", + "url": "https://proteomics.cancer.gov/programs/cptac", + "description": "Multi-omic proteogenomic datasets for multiple cancer types linking proteomics with genomics.", + "tags": [ + "benchmarks-and-datasets" + ], + "tasks": [], + "modalities": [], + "organism": [], + "api": false + }, + { + "id": "crossdocked2020", + "name": "CrossDocked2020", + "type": "benchmark", + "url": "https://arxiv.org/abs/2001.01037", + "description": "Large-scale dataset for structure-based virtual screening.", + "tags": [ + "benchmarks-and-datasets" + ], + "tasks": [], + "modalities": [], + "organism": [], + "api": false + }, + { + "id": "dud_e_directory_of_useful_decoys_enhanced", + "name": "DUD-E (Directory of Useful Decoys, Enhanced)", + "type": "benchmark", + "url": "http://dude.docking.org/", + "description": "Structure-based virtual screening benchmark with active ligands and challenging decoy sets across diverse protein targets.", + "tags": [ + "benchmarks-and-datasets" + ], + "tasks": [], + "modalities": [], + "organism": [], + "api": false + }, + { + "id": "flip_fitness_landscape_inference_for_proteins", + "name": "FLIP (Fitness Landscape Inference for Proteins)", + "type": "benchmark", + "url": "https://github.com/J-SNACKKB/FLIP", + "description": "Benchmark collection of protein fitness landscape datasets for evaluating protein ML models.", + "tags": [ + "benchmarks-and-datasets" + ], + "tasks": [], + "modalities": [], + "organism": [], + "api": false + }, + { + "id": "guacamol", + "name": "GuacaMol", + "type": "benchmark", + "url": "https://github.com/BenevolentAI/guacamol", + "description": "Benchmark suite for generative molecular design models.", + "tags": [ + "benchmarks-and-datasets" + ], + "tasks": [], + "modalities": [], + "organism": [], + "api": false + }, + { + "id": "jump_cell_painting_datasets", + "name": "JUMP Cell Painting Datasets", + "type": "benchmark", + "url": "https://github.com/jump-cellpainting/datasets", + "description": "Consortium-scale cell imaging perturbation datasets (chemical and genetic) for phenotypic profiling and drug discovery research.", + "tags": [ + "benchmarks-and-datasets" + ], + "tasks": [], + "modalities": [], + "organism": [], + "api": false + }, + { + "id": "lincs_l1000", + "name": "LINCS L1000", + "type": "benchmark", + "url": "https://lincsproject.org/LINCS/tools/workflows/find-the-best-place-to-obtain-the-lincs-l1000-data", + "description": "Gene expression profiles (978 landmark genes) for >20,000 chemical and genetic perturbations across cell lines.", + "tags": [ + "benchmarks-and-datasets" + ], + "tasks": [], + "modalities": [], + "organism": [], + "api": false + }, + { + "id": "moleculenet", + "name": "MoleculeNet", + "type": "benchmark", + "url": "http://moleculenet.ai/", + "description": "Benchmark datasets for molecular machine learning.", + "tags": [ + "benchmarks-and-datasets" + ], + "tasks": [], + "modalities": [], + "organism": [], + "api": false + }, + { + "id": "moses", + "name": "MOSES", + "type": "benchmark", + "url": "https://github.com/molecularsets/moses", + "description": "Benchmarking platform for molecular generation models.", + "tags": [ + "benchmarks-and-datasets" + ], + "tasks": [], + "modalities": [], + "organism": [], + "api": false + }, + { + "id": "ogb_open_graph_benchmark", + "name": "OGB (Open Graph Benchmark)", + "type": "benchmark", + "url": "https://ogb.stanford.edu/", + "description": "Large-scale graph ML benchmark suite including biological datasets such as ogbl-ppa (protein-protein associations) and ogbg-molhiv.", + "tags": [ + "benchmarks-and-datasets" + ], + "tasks": [], + "modalities": [], + "organism": [], + "api": false + }, + { + "id": "openbiolink", + "name": "OpenBioLink", + "type": "benchmark", + "url": "https://github.com/OpenBioLink/OpenBioLink", + "description": "Benchmark datasets for biological knowledge graph completion.", + "tags": [ + "benchmarks-and-datasets" + ], + "tasks": [], + "modalities": [], + "organism": [], + "api": false + }, + { + "id": "pharmgkb", + "name": "PharmGKB", + "type": "benchmark", + "url": "https://www.pharmgkb.org/", + "description": "Curated pharmacogenomics dataset linking genetic variants to drug response phenotypes across thousands of drugs.", + "tags": [ + "benchmarks-and-datasets" + ], + "tasks": [], + "modalities": [], + "organism": [], + "api": false + }, + { + "id": "pk_db", + "name": "PK-DB", + "type": "benchmark", + "url": "https://pk-db.com/", + "description": "Open database of experimental pharmacokinetics (PK) and ADME data from clinical and preclinical studies.", + "tags": [ + "benchmarks-and-datasets" + ], + "tasks": [], + "modalities": [], + "organism": [], + "api": false + }, + { + "id": "prism", + "name": "PRISM", + "type": "benchmark", + "url": "https://depmap.org/portal/prism/", + "description": "Cancer drug sensitivity profiling of >4,500 drugs across >900 cancer cell lines using pooled-cell-line barcoding.", + "tags": [ + "benchmarks-and-datasets" + ], + "tasks": [], + "modalities": [], + "organism": [], + "api": false + }, + { + "id": "proteingym", + "name": "ProteinGym", + "type": "benchmark", + "url": "https://github.com/OATML-Markslab/ProteinGym", + "description": "Large-scale benchmark of deep mutational scanning assays for evaluating protein fitness landscape models.", + "tags": [ + "benchmarks-and-datasets" + ], + "tasks": [], + "modalities": [], + "organism": [], + "api": false + }, + { + "id": "qm9", + "name": "QM9", + "type": "benchmark", + "url": "https://figshare.com/collections/Quantum_chemistry_structures_and_properties_of_134_kilo_molecules/978904", + "description": "Quantum chemistry properties for 134K stable small organic molecules computed at DFT level.", + "tags": [ + "benchmarks-and-datasets" + ], + "tasks": [], + "modalities": [], + "organism": [], + "api": false + }, + { + "id": "scib_single_cell_integration_benchmarks", + "name": "scIB (Single-cell Integration Benchmarks)", + "type": "benchmark", + "url": "https://github.com/theislab/scib", + "description": "Comprehensive benchmarking framework for single-cell data integration methods.", + "tags": [ + "benchmarks-and-datasets" + ], + "tasks": [], + "modalities": [], + "organism": [], + "api": false + }, + { + "id": "scperturb", + "name": "scPerturb", + "type": "benchmark", + "url": "https://github.com/sanderlab/scPerturb", + "description": "Curated and continuously updated single-cell perturbation data resource spanning CRISPR and drug perturbation studies.", + "tags": [ + "benchmarks-and-datasets" + ], + "tasks": [], + "modalities": [], + "organism": [], + "api": false + }, + { + "id": "sider_side_effect_resource", + "name": "SIDER (Side Effect Resource)", + "type": "benchmark", + "url": "http://sideeffects.embl.de/", + "description": "Database of 1,430 approved drugs with their recorded adverse drug reactions across 27 system-organ classes.", + "tags": [ + "benchmarks-and-datasets" + ], + "tasks": [], + "modalities": [], + "organism": [], + "api": false + }, + { + "id": "tabula_muris", + "name": "Tabula Muris", + "type": "benchmark", + "url": "https://tabula-muris.ds.czbiohub.org/", + "description": "Comprehensive single-cell atlas of 20 mouse organs and tissues, enabling cross-tissue and cross-species comparisons.", + "tags": [ + "benchmarks-and-datasets" + ], + "tasks": [], + "modalities": [], + "organism": [], + "api": false + }, + { + "id": "tabula_sapiens", + "name": "Tabula Sapiens", + "type": "benchmark", + "url": "https://tabula-sapiens-portal.ds.czbiohub.org/", + "description": "Comprehensive human single-cell atlas of ~500K cells from 24 organs and tissues across multiple donors.", + "tags": [ + "benchmarks-and-datasets" + ], + "tasks": [], + "modalities": [], + "organism": [], + "api": false + }, + { + "id": "tape_tasks_assessing_protein_embeddings", + "name": "TAPE (Tasks Assessing Protein Embeddings)", + "type": "benchmark", + "url": "https://github.com/songlab-cal/tape", + "description": "Benchmark suite of five biologically meaningful semi-supervised learning tasks for evaluating protein representations.", + "tags": [ + "benchmarks-and-datasets" + ], + "tasks": [], + "modalities": [], + "organism": [], + "api": false + }, + { + "id": "the_cancer_genome_atlas_tcga", + "name": "The Cancer Genome Atlas (TCGA)", + "type": "benchmark", + "url": "https://www.cancer.gov/about-nci/organization/ccg/research/structural-genomics/tcga", + "description": "Comprehensive multi-omics (genomics, transcriptomics, proteomics, methylation) dataset for 33 cancer types across ~11,000 patients.", + "tags": [ + "benchmarks-and-datasets" + ], + "tasks": [], + "modalities": [], + "organism": [], + "api": false + }, + { + "id": "therapeutics_data_commons_tdc", + "name": "Therapeutics Data Commons (TDC)", + "type": "benchmark", + "url": "https://tdcommons.ai/", + "description": "Unified benchmark suite covering ADMET, drug-target interaction, drug response, and more.", + "tags": [ + "benchmarks-and-datasets" + ], + "tasks": [], + "modalities": [], + "organism": [], + "api": false + }, + { + "id": "tox21", + "name": "Tox21", + "type": "benchmark", + "url": "https://tripod.nih.gov/tox21/challenge/", + "description": "12,707 compounds tested in 12 nuclear receptor and stress-response pathway biochemical assays for toxicity prediction.", + "tags": [ + "benchmarks-and-datasets" + ], + "tasks": [], + "modalities": [], + "organism": [], + "api": false + }, + { + "id": "uk_biobank", + "name": "UK Biobank", + "type": "benchmark", + "url": "https://www.ukbiobank.ac.uk/", + "description": "Large-scale biomedical database of ~500K participants with genetic, imaging, and health data for population genetics and disease studies.", + "tags": [ + "benchmarks-and-datasets" + ], + "tasks": [], + "modalities": [], + "organism": [], + "api": false + }, + { + "id": "10x_genomics_dataset", + "name": "10x Genomics Dataset", + "type": "database", + "url": "https://www.10xgenomics.com/resources/datasets", + "description": "Collection of single-cell datasets.", + "tags": [ + "genome" + ], + "tasks": [], + "modalities": [ + "Genomics" + ], + "organism": [], + "api": false + }, + { + "id": "alphafold_protein_structure_database", + "name": "AlphaFold Protein Structure Database", + "type": "database", + "url": "https://alphafold.ebi.ac.uk/api-docs", + "description": "3D protein structure predictions.", + "tags": [ + "protein" + ], + "tasks": [], + "modalities": [ + "Protein" + ], + "organism": [], + "api": false + }, + { + "id": "bindingdb", + "name": "BindingDB", + "type": "database", + "url": "https://www.bindingdb.org/rwd/bind/index.jsp", + "description": "Compounds and target database.", + "tags": [ + "chemical-protein-interaction", + "interaction" + ], + "tasks": [], + "modalities": [ + "Protein", + "Small Molecule" + ], + "organism": [], + "api": false + }, + { + "id": "biocyc", + "name": "BioCyc", + "type": "database", + "url": "https://biocyc.org/", + "description": "Collection of pathway/genome databases across thousands of organisms.", + "tags": [ + "pathway" + ], + "tasks": [], + "modalities": [ + "Pathway" + ], + "organism": [], + "api": false + }, + { + "id": "biogrid", + "name": "BioGRID", + "type": "database", + "url": "https://thebiogrid.org/", + "description": "Protein, genetic, and chemical interactions.", + "tags": [ + "interaction", + "protein-protein-interaction" + ], + "tasks": [], + "modalities": [ + "Protein" + ], + "organism": [], + "api": false + }, + { + "id": "cancer_cell_line_encyclopedia", + "name": "Cancer Cell Line Encyclopedia", + "type": "database", + "url": "https://sites.broadinstitute.org/ccle/", + "description": "Database of ~1000 cancer cell lines.", + "tags": [ + "drug-cell-line-response", + "interaction" + ], + "tasks": [], + "modalities": [ + "Gene Expression", + "Small Molecule" + ], + "organism": [], + "api": false + }, + { + "id": "catalogue_of_somatic_mutations_in_cancer_cosmic", + "name": "Catalogue Of Somatic Mutations In Cancer (COSMIC)", + "type": "database", + "url": "https://cancer.sanger.ac.uk/cosmic", + "description": "Resource on somatic mutations in cancers.", + "tags": [ + "genome" + ], + "tasks": [], + "modalities": [ + "Genomics" + ], + "organism": [], + "api": false + }, + { + "id": "cath_database", + "name": "CATH database", + "type": "database", + "url": "https://www.cathdb.info/", + "description": "Hierarchical classification of protein domain structures.", + "tags": [ + "protein" + ], + "tasks": [], + "modalities": [ + "Protein" + ], + "organism": [], + "api": false + }, + { + "id": "cbioportal", + "name": "cBioPortal", + "type": "database", + "url": "https://www.cbioportal.org/", + "description": "Cancer genomics database; aggregating many patient datasets.", + "tags": [ + "genome" + ], + "tasks": [], + "modalities": [ + "Genomics" + ], + "organism": [], + "api": false + }, + { + "id": "cellminer_cross_database_cellminercdb", + "name": "CellMiner Cross Database (CellMinerCDB)", + "type": "database", + "url": "https://discover.nci.nih.gov/cellminercdb/", + "description": "Integrates multiple cancer cell line databases.", + "tags": [ + "drug-cell-line-response", + "interaction" + ], + "tasks": [], + "modalities": [ + "Gene Expression", + "Small Molecule" + ], + "organism": [], + "api": false + }, + { + "id": "chebi", + "name": "ChEBI", + "type": "database", + "url": "https://www.ebi.ac.uk/chebi/", + "description": "Database focused on small chemical compounds.", + "tags": [ + "compound" + ], + "tasks": [], + "modalities": [ + "Small Molecule" + ], + "organism": [], + "api": false + }, + { + "id": "chembl", + "name": "ChEMBL", + "type": "database", + "url": "https://www.ebi.ac.uk/chembl/", + "description": "Bioactive molecules with drug-like properties.", + "tags": [ + "compound" + ], + "tasks": [], + "modalities": [ + "Small Molecule" + ], + "organism": [], + "api": false + }, + { + "id": "chemspider", + "name": "ChemSpider", + "type": "database", + "url": "http://www.chemspider.com/", + "description": "Chemical structure database.", + "tags": [ + "compound" + ], + "tasks": [], + "modalities": [ + "Small Molecule" + ], + "organism": [], + "api": false + }, + { + "id": "clinicaltrials_gov", + "name": "ClinicalTrials.gov", + "type": "database", + "url": "https://clinicaltrials.gov/", + "description": "Privately and publicly funded clinical studies.", + "tags": [ + "clinical-trial" + ], + "tasks": [], + "modalities": [ + "Clinical" + ], + "organism": [], + "api": false + }, + { + "id": "comparative_toxicogenomics_database", + "name": "Comparative Toxicogenomics Database", + "type": "database", + "url": "http://ctdbase.org/", + "description": "Chemical-gene interactions, chemical-disease and gene-disease associations, chemical-phenotype associations.", + "tags": [ + "drug-gene-interaction", + "interaction" + ], + "tasks": [], + "modalities": [ + "Gene", + "Small Molecule" + ], + "organism": [], + "api": false + }, + { + "id": "critical_assessment_of_structure_prediction_casp", + "name": "Critical Assessment of Structure Prediction (CASP)", + "type": "database", + "url": "https://predictioncenter.org/", + "description": "Assessing methods for protein structure prediction.", + "tags": [ + "protein" + ], + "tasks": [], + "modalities": [ + "Protein" + ], + "organism": [], + "api": false + }, + { + "id": "cz_cellxgene", + "name": "CZ CELLxGENE", + "type": "database", + "url": "https://cellxgene.cziscience.com/", + "description": "Single-cell dataset repository and interactive explorer from the Chan Zuckerberg Initiative.", + "tags": [ + "scrna" + ], + "tasks": [], + "modalities": [ + "Single Cell" + ], + "organism": [], + "api": false + }, + { + "id": "davis_kinase_inhibitors_db", + "name": "Davis kinase inhibitors DB", + "type": "database", + "url": "http://staff.cs.utu.fi/~aijrinas/dti/", + "description": "Experimental kinase inhibitor binding affinity dataset for protein–ligand interaction research.", + "tags": [ + "chemical-protein-interaction", + "interaction" + ], + "tasks": [], + "modalities": [ + "Protein", + "Small Molecule" + ], + "organism": [], + "api": false + }, + { + "id": "dependency_map_depmap", + "name": "Dependency Map (DepMap)", + "type": "database", + "url": "https://depmap.org/portal/", + "description": "CRISPR-Cas9 screens in cancer cell lines.", + "tags": [ + "genome" + ], + "tasks": [], + "modalities": [ + "Genomics" + ], + "organism": [], + "api": false + }, + { + "id": "dgidb", + "name": "DGIdb", + "type": "database", + "url": "https://www.dgidb.org/", + "description": "Drug-gene interactions and the druggable genome.", + "tags": [ + "drug-gene-interaction", + "interaction" + ], + "tasks": [], + "modalities": [ + "Gene", + "Small Molecule" + ], + "organism": [], + "api": false + }, + { + "id": "diseases", + "name": "DISEASES", + "type": "database", + "url": "https://diseases.jensenlab.org/", + "description": "Gene–disease association database integrating evidence from text mining, curated databases, and experimental data.", + "tags": [ + "disease" + ], + "tasks": [], + "modalities": [ + "Disease" + ], + "organism": [], + "api": false + }, + { + "id": "disgenet", + "name": "DisGeNET", + "type": "database", + "url": "https://www.disgenet.org/", + "description": "Database of gene-disease associations integrating expert-curated and GWAS data.", + "tags": [ + "disease" + ], + "tasks": [], + "modalities": [ + "Disease" + ], + "organism": [], + "api": false + }, + { + "id": "drkg", + "name": "DRKG", + "type": "database", + "url": "https://github.com/gnn4dr/DRKG", + "description": "Large-scale biological knowledge graph for drug discovery.", + "tags": [ + "interaction", + "knowledge-graph" + ], + "tasks": [], + "modalities": [ + "Knowledge Graph" + ], + "organism": [], + "api": false + }, + { + "id": "drug_mechanism_database_drugmechdb", + "name": "Drug Mechanism Database (DrugMechDB)", + "type": "database", + "url": "https://github.com/SuLab/DrugMechDB/tree/2.0.1", + "description": "Mechanisms of action from drug to disease.", + "tags": [ + "interaction", + "knowledge-graph" + ], + "tasks": [], + "modalities": [ + "Knowledge Graph" + ], + "organism": [], + "api": false + }, + { + "id": "drug_repurposing_hub", + "name": "Drug Repurposing Hub", + "type": "database", + "url": "https://repo-hub.broadinstitute.org/repurposing#download-data", + "description": "Collections of drug repurposing data (drug, MoA, target, etc).", + "tags": [ + "compound" + ], + "tasks": [], + "modalities": [ + "Small Molecule" + ], + "organism": [], + "api": false + }, + { + "id": "drugbank", + "name": "DrugBank", + "type": "database", + "url": "https://go.drugbank.com/", + "description": "Database of drugs and targets (University of Alberta).", + "tags": [ + "disease" + ], + "tasks": [], + "modalities": [ + "Disease" + ], + "organism": [], + "api": false + }, + { + "id": "drugcentral", + "name": "DrugCentral", + "type": "database", + "url": "http://drugcentral.org/", + "description": "Online drug compendium with drug mode of action and indication information.", + "tags": [ + "compound" + ], + "tasks": [], + "modalities": [ + "Small Molecule" + ], + "organism": [], + "api": false + }, + { + "id": "drugtargetcommons", + "name": "DrugTargetCommons", + "type": "database", + "url": "https://drugtargetcommons.fimm.fi/", + "description": "Community platform for curating and integrating experimental bioactivity data across drugs and targets.", + "tags": [ + "compound" + ], + "tasks": [], + "modalities": [ + "Small Molecule" + ], + "organism": [], + "api": false + }, + { + "id": "encode", + "name": "ENCODE", + "type": "database", + "url": "https://www.encodeproject.org/", + "description": "Encyclopedia of DNA Elements; regulatory and functional genomic elements across the genome.", + "tags": [ + "genome" + ], + "tasks": [], + "modalities": [ + "Genomics" + ], + "organism": [], + "api": false + }, + { + "id": "ensembl", + "name": "Ensembl", + "type": "database", + "url": "https://www.ensembl.org/", + "description": "Genome browser and annotation database for vertebrate and other eukaryotic genomes.", + "tags": [ + "genome" + ], + "tasks": [], + "modalities": [ + "Genomics" + ], + "organism": [], + "api": false + }, + { + "id": "eu_drug_regulating_authorities_clinical_trials_db_eudract", + "name": "EU Drug Regulating Authorities Clinical Trials DB (EudraCT)", + "type": "database", + "url": "https://eudract.ema.europa.eu/", + "description": "European clinical trial database.", + "tags": [ + "clinical-trial" + ], + "tasks": [], + "modalities": [ + "Clinical" + ], + "organism": [], + "api": false + }, + { + "id": "fantom5", + "name": "FANTOM5", + "type": "database", + "url": "https://fantom.gsc.riken.jp/5/", + "description": "Functional annotation of mammalian genome; comprehensive atlas of active enhancers, promoters, and transcription start sites across human and mouse cell types.", + "tags": [ + "genome" + ], + "tasks": [], + "modalities": [ + "Genomics" + ], + "organism": [], + "api": false + }, + { + "id": "genbank", + "name": "GenBank", + "type": "database", + "url": "https://www.ncbi.nlm.nih.gov/genbank/", + "description": "NCBI's database of genetic sequences.", + "tags": [ + "genome" + ], + "tasks": [], + "modalities": [ + "Genomics" + ], + "organism": [], + "api": false + }, + { + "id": "gene_expression_omnibus", + "name": "Gene Expression Omnibus", + "type": "database", + "url": "https://www.ncbi.nlm.nih.gov/geo/", + "description": "Public functional genomics database.", + "tags": [ + "scrna" + ], + "tasks": [], + "modalities": [ + "Single Cell" + ], + "organism": [], + "api": false + }, + { + "id": "genomics_of_drug_sensitivity_in_cancer_gdsc", + "name": "Genomics of Drug Sensitivity in Cancer (GDSC)", + "type": "database", + "url": "https://www.cancerrxgene.org/", + "description": "Drug sensitivity for ~1000 human cancer cell lines and hundreds of compounds.", + "tags": [ + "benchmarks-and-datasets", + "drug-cell-line-response", + "interaction" + ], + "tasks": [], + "modalities": [ + "Gene Expression", + "Small Molecule" + ], + "organism": [], + "api": false + }, + { + "id": "gnomad", + "name": "gnomAD", + "type": "database", + "url": "https://gnomad.broadinstitute.org/", + "description": "Genome Aggregation Database; genetic variation from large-scale sequencing projects.", + "tags": [ + "genome" + ], + "tasks": [], + "modalities": [ + "Genomics" + ], + "organism": [], + "api": false + }, + { + "id": "hetionet", + "name": "Hetionet", + "type": "database", + "url": "https://github.com/hetio/hetionet", + "description": "Heterogeneous network integrating genes, diseases, drugs, pathways, and more.", + "tags": [ + "interaction", + "knowledge-graph" + ], + "tasks": [], + "modalities": [ + "Knowledge Graph" + ], + "organism": [], + "api": false + }, + { + "id": "hippie", + "name": "HIPPIE", + "type": "database", + "url": "http://cbdm-01.zdv.uni-mainz.de/~mschaefer/hippie/", + "description": "Human protein-protein interaction database.", + "tags": [ + "interaction", + "protein-protein-interaction" + ], + "tasks": [], + "modalities": [ + "Protein" + ], + "organism": [], + "api": false + }, + { + "id": "hmdb_human_metabolome_database", + "name": "HMDB (Human Metabolome Database)", + "type": "database", + "url": "https://hmdb.ca/", + "description": "Comprehensive database of small molecule metabolites found in the human body.", + "tags": [ + "compound" + ], + "tasks": [], + "modalities": [ + "Small Molecule" + ], + "organism": [], + "api": false + }, + { + "id": "human_cell_atlas", + "name": "Human Cell Atlas", + "type": "database", + "url": "https://www.humancellatlas.org/", + "description": "Open global atlas of all cells in the human body.", + "tags": [ + "scrna" + ], + "tasks": [], + "modalities": [ + "Single Cell" + ], + "organism": [], + "api": false + }, + { + "id": "human_genome_resources_at_ncbi", + "name": "Human Genome Resources at NCBI", + "type": "database", + "url": "https://www.ncbi.nlm.nih.gov/projects/genome/guide/human/index.shtml", + "description": "Database for genomics, proteomics, transcriptomics, and systems biology.", + "tags": [ + "genome" + ], + "tasks": [], + "modalities": [ + "Genomics" + ], + "organism": [], + "api": false + }, + { + "id": "human_phenotype_ontology_hpo", + "name": "Human Phenotype Ontology (HPO)", + "type": "database", + "url": "https://hpo.jax.org/", + "description": "Standardized vocabulary of phenotypic abnormalities in human disease, linking genes, variants, and clinical features.", + "tags": [ + "disease" + ], + "tasks": [], + "modalities": [ + "Disease" + ], + "organism": [], + "api": false + }, + { + "id": "icd10", + "name": "ICD10", + "type": "database", + "url": "https://icd.who.int/browse10/2019/en", + "description": "International Classification of Diseases, 10th revision.", + "tags": [ + "clinical-trial" + ], + "tasks": [], + "modalities": [ + "Clinical" + ], + "organism": [], + "api": false + }, + { + "id": "intact", + "name": "IntAct", + "type": "database", + "url": "https://www.ebi.ac.uk/intact/home", + "description": "Open-source molecular interaction database and analysis system from EMBL-EBI.", + "tags": [ + "interaction", + "protein-protein-interaction" + ], + "tasks": [], + "modalities": [ + "Protein" + ], + "organism": [], + "api": false + }, + { + "id": "interpro", + "name": "InterPro", + "type": "database", + "url": "https://www.ebi.ac.uk/interpro/", + "description": "Protein families, domains, and functional sites database integrating 14 member databases including Pfam and PROSITE.", + "tags": [ + "protein" + ], + "tasks": [], + "modalities": [ + "Protein" + ], + "organism": [], + "api": false + }, + { + "id": "jaspar", + "name": "JASPAR", + "type": "database", + "url": "http://jaspar.genereg.net/", + "description": "Database of transcription factor binding profiles.", + "tags": [ + "genome" + ], + "tasks": [], + "modalities": [ + "Genomics" + ], + "organism": [], + "api": false + }, + { + "id": "kegg_compound", + "name": "KEGG COMPOUND", + "type": "database", + "url": "https://www.genome.jp/kegg/compound/", + "description": "Collection of small molecules and biopolymers.", + "tags": [ + "compound" + ], + "tasks": [], + "modalities": [ + "Small Molecule" + ], + "organism": [], + "api": false + }, + { + "id": "kegg_drug", + "name": "KEGG DRUG", + "type": "database", + "url": "https://www.genome.jp/kegg/drug/", + "description": "Comprehensive, approved drug information.", + "tags": [ + "disease" + ], + "tasks": [], + "modalities": [ + "Disease" + ], + "organism": [], + "api": false + }, + { + "id": "kegg_pathway", + "name": "KEGG PATHWAY", + "type": "database", + "url": "https://www.genome.jp/kegg/pathway.html", + "description": "Collection of pathway maps.", + "tags": [ + "pathway" + ], + "tasks": [], + "modalities": [ + "Pathway" + ], + "organism": [], + "api": false + }, + { + "id": "kinase_inhibitor_bioactivity_data_kiba", + "name": "Kinase Inhibitor Bioactivity Data (KIBA)", + "type": "database", + "url": "https://janeliascicomp.github.io/KIBA/", + "description": "Integrated bioactivity scores for kinase inhibitors combining Ki, Kd, and IC50 measurements.", + "tags": [ + "chemical-protein-interaction", + "interaction" + ], + "tasks": [], + "modalities": [ + "Protein", + "Small Molecule" + ], + "organism": [], + "api": false + }, + { + "id": "lipid_maps", + "name": "LIPID MAPS", + "type": "database", + "url": "https://www.lipidmaps.org/databases/lmsd/overview", + "description": "Database of lipids.", + "tags": [ + "compound" + ], + "tasks": [], + "modalities": [ + "Small Molecule" + ], + "organism": [], + "api": false + }, + { + "id": "massbank", + "name": "MassBank", + "type": "database", + "url": "http://www.massbank.jp/", + "description": "Open source databases and tools for mass spectrometry reference spectra.", + "tags": [ + "mass-spectra" + ], + "tasks": [], + "modalities": [ + "Mass Spectra" + ], + "organism": [], + "api": false + }, + { + "id": "mgnify", + "name": "MGnify", + "type": "database", + "url": "https://www.ebi.ac.uk/metagenomics/", + "description": "Resource for metagenomic and metatranscriptomic data.", + "tags": [ + "genome" + ], + "tasks": [], + "modalities": [ + "Genomics" + ], + "organism": [], + "api": false + }, + { + "id": "mimic_iv", + "name": "MIMIC-IV", + "type": "database", + "url": "https://mimic.mit.edu/", + "description": "Freely accessible critical care database.", + "tags": [ + "clinical-trial" + ], + "tasks": [], + "modalities": [ + "Clinical" + ], + "organism": [], + "api": false + }, + { + "id": "mirbase", + "name": "miRBase", + "type": "database", + "url": "https://www.mirbase.org/", + "description": "Reference repository for microRNA gene annotations, sequences, and experimentally validated targets.", + "tags": [ + "gene-regulatory-network", + "interaction" + ], + "tasks": [], + "modalities": [ + "Gene Expression" + ], + "organism": [], + "api": false + }, + { + "id": "mona_massbank_of_north_america", + "name": "MoNA MassBank of North America", + "type": "database", + "url": "https://mona.fiehnlab.ucdavis.edu/", + "description": "Meta-database of metabolite mass spectra, metadata, and associated compounds.", + "tags": [ + "mass-spectra" + ], + "tasks": [], + "modalities": [ + "Mass Spectra" + ], + "organism": [], + "api": false + }, + { + "id": "msigdb_molecular_signatures_database", + "name": "MSigDB (Molecular Signatures Database)", + "type": "database", + "url": "https://www.gsea-msigdb.org/gsea/msigdb", + "description": "Curated gene sets derived from pathways and biological processes.", + "tags": [ + "pathway" + ], + "tasks": [], + "modalities": [ + "Pathway" + ], + "organism": [], + "api": false + }, + { + "id": "nci60", + "name": "NCI60", + "type": "database", + "url": "https://dtp.cancer.gov/discovery_development/nci-60/", + "description": "Focuses on 60 cancer cell lines and many drugs.", + "tags": [ + "benchmarks-and-datasets", + "drug-cell-line-response", + "interaction" + ], + "tasks": [], + "modalities": [ + "Gene Expression", + "Small Molecule" + ], + "organism": [], + "api": false + }, + { + "id": "nextprot", + "name": "NeXtProt", + "type": "database", + "url": "https://www.nextprot.org/", + "description": "Expert knowledge base on human proteins with deep functional annotation, complementary to UniProt.", + "tags": [ + "protein" + ], + "tasks": [], + "modalities": [ + "Protein" + ], + "organism": [], + "api": false + }, + { + "id": "oadb_observed_antibody_space_database", + "name": "OADB (Observed Antibody Space Database)", + "type": "database", + "url": "http://opig.stats.ox.ac.uk/webapps/oas/", + "description": "Database of antibody sequences from immune repertoire sequencing.", + "tags": [ + "protein" + ], + "tasks": [], + "modalities": [ + "Protein" + ], + "organism": [], + "api": false + }, + { + "id": "omim_online_mendelian_inheritance_in_man", + "name": "OMIM (Online Mendelian Inheritance in Man)", + "type": "database", + "url": "https://www.omim.org/", + "description": "Comprehensive database of human genes and genetic disorders.", + "tags": [ + "disease" + ], + "tasks": [], + "modalities": [ + "Disease" + ], + "organism": [], + "api": false + }, + { + "id": "omnipath", + "name": "OmniPath", + "type": "database", + "url": "https://omnipathdb.org/", + "description": "Comprehensive resource integrating protein interactions, signaling pathways, gene regulatory networks, and miRNA targets from over 100 databases.", + "tags": [ + "pathway" + ], + "tasks": [], + "modalities": [ + "Pathway" + ], + "organism": [], + "api": false + }, + { + "id": "open_targets_platform", + "name": "Open Targets Platform", + "type": "database", + "url": "https://platform.opentargets.org/", + "description": "Systematic target identification and prioritization platform integrating genetics, genomics, and drug data for drug discovery.", + "tags": [ + "disease" + ], + "tasks": [], + "modalities": [ + "Disease" + ], + "organism": [], + "api": false + }, + { + "id": "pathwaycommons", + "name": "PathwayCommons", + "type": "database", + "url": "https://www.pathwaycommons.org/", + "description": "Database of pathways and interactions.", + "tags": [ + "pathway" + ], + "tasks": [], + "modalities": [ + "Pathway" + ], + "organism": [], + "api": false + }, + { + "id": "pdbbind", + "name": "PDBBind", + "type": "database", + "url": "https://www.pdbbind-plus.org.cn/", + "description": "Binding affinity data for biomolecular complexes.", + "tags": [ + "chemical-protein-interaction", + "interaction" + ], + "tasks": [], + "modalities": [ + "Protein", + "Small Molecule" + ], + "organism": [], + "api": false + }, + { + "id": "pfam", + "name": "Pfam", + "type": "database", + "url": "https://www.ebi.ac.uk/interpro/entry/pfam/", + "description": "Database of protein families described by multiple sequence alignments and hidden Markov models.", + "tags": [ + "protein" + ], + "tasks": [], + "modalities": [ + "Protein" + ], + "organism": [], + "api": false + }, + { + "id": "primekg", + "name": "PrimeKG", + "type": "database", + "url": "https://github.com/mims-harvard/PrimeKG", + "description": "Multi-modal precision medicine knowledge graph integrating clinical, genetic, and drug data.", + "tags": [ + "interaction", + "knowledge-graph" + ], + "tasks": [], + "modalities": [ + "Knowledge Graph" + ], + "organism": [], + "api": false + }, + { + "id": "protein_data_bank_pdb", + "name": "PROTEIN DATA BANK (PDB)", + "type": "database", + "url": "https://www.rcsb.org/", + "description": "3D structures of proteins, nucleic acids, complexes.", + "tags": [ + "protein" + ], + "tasks": [], + "modalities": [ + "Protein" + ], + "organism": [], + "api": false + }, + { + "id": "pubchem", + "name": "PubChem", + "type": "database", + "url": "https://pubchem.ncbi.nlm.nih.gov/", + "description": "One of the largest chemical databases (compounds, genes, and proteins).", + "tags": [ + "compound" + ], + "tasks": [], + "modalities": [ + "Small Molecule" + ], + "organism": [], + "api": false + }, + { + "id": "rcsb_protein_data_bank", + "name": "RCSB Protein Data Bank", + "type": "database", + "url": "https://www.rcsb.org/", + "description": "Repository for structural data of biological molecules.", + "tags": [ + "protein" + ], + "tasks": [], + "modalities": [ + "Protein" + ], + "organism": [], + "api": false + }, + { + "id": "reactome", + "name": "Reactome", + "type": "database", + "url": "https://reactome.org/", + "description": "Expert-curated, peer-reviewed pathway database with detailed reaction mechanisms.", + "tags": [ + "pathway" + ], + "tasks": [], + "modalities": [ + "Pathway" + ], + "organism": [], + "api": false + }, + { + "id": "regnetwork", + "name": "RegNetwork", + "type": "database", + "url": "http://www.regnetworkweb.org/", + "description": "Database of gene regulatory networks covering transcription factor–target gene and miRNA–gene interaction data across multiple species.", + "tags": [ + "gene-regulatory-network", + "interaction" + ], + "tasks": [], + "modalities": [ + "Gene Expression" + ], + "organism": [], + "api": false + }, + { + "id": "rfam", + "name": "Rfam", + "type": "database", + "url": "https://rfam.org/", + "description": "Database of RNA families with sequence alignments and consensus structures.", + "tags": [ + "genome" + ], + "tasks": [], + "modalities": [ + "Genomics" + ], + "organism": [], + "api": false + }, + { + "id": "rhea", + "name": "Rhea", + "type": "database", + "url": "https://www.rhea-db.org/", + "description": "Database of chemical reactions.", + "tags": [ + "compound" + ], + "tasks": [], + "modalities": [ + "Small Molecule" + ], + "organism": [], + "api": false + }, + { + "id": "roadmap_epigenomics", + "name": "ROADMAP Epigenomics", + "type": "database", + "url": "http://www.roadmapepigenomics.org/", + "description": "Reference epigenome maps for 111 primary human cell types and tissues, including histone modifications, chromatin accessibility, and DNA methylation.", + "tags": [ + "genome" + ], + "tasks": [], + "modalities": [ + "Genomics" + ], + "organism": [], + "api": false + }, + { + "id": "sabdab", + "name": "SAbDab", + "type": "database", + "url": "https://opig.stats.ox.ac.uk/webapps/sabdab-sabpred/sabdab", + "description": "Structural Antibody Database containing all antibody structures in the PDB.", + "tags": [ + "protein" + ], + "tasks": [], + "modalities": [ + "Protein" + ], + "organism": [], + "api": false + }, + { + "id": "signor_2_0", + "name": "SIGNOR 2.0", + "type": "database", + "url": "https://signor.uniroma2.it/", + "description": "Database of causal signaling interactions and pathways, with signed and directed relationships between proteins.", + "tags": [ + "pathway" + ], + "tasks": [], + "modalities": [ + "Pathway" + ], + "organism": [], + "api": false + }, + { + "id": "single_cell_expression_atlas", + "name": "Single Cell Expression Atlas", + "type": "database", + "url": "https://www.ebi.ac.uk/gxa/sc/home", + "description": "Public database for single-cell RNA.", + "tags": [ + "scrna" + ], + "tasks": [], + "modalities": [ + "Single Cell" + ], + "organism": [], + "api": false + }, + { + "id": "single_cell_portal", + "name": "Single Cell PORTAL", + "type": "database", + "url": "https://singlecell.broadinstitute.org/single_cell", + "description": "Public database for single-cell RNA.", + "tags": [ + "scrna" + ], + "tasks": [], + "modalities": [ + "Single Cell" + ], + "organism": [], + "api": false + }, + { + "id": "snap", + "name": "SNAP", + "type": "database", + "url": "https://snap.stanford.edu/biodata/datasets/10002/10002-ChG-Miner.html", + "description": "Dataset of drug-gene interactions.", + "tags": [ + "drug-gene-interaction", + "interaction" + ], + "tasks": [], + "modalities": [ + "Gene", + "Small Molecule" + ], + "organism": [], + "api": false + }, + { + "id": "stitch", + "name": "STITCH", + "type": "database", + "url": "http://stitch.embl.de/", + "description": "Chemical-protein interactions.", + "tags": [ + "chemical-protein-interaction", + "interaction" + ], + "tasks": [], + "modalities": [ + "Protein", + "Small Molecule" + ], + "organism": [], + "api": false + }, + { + "id": "string", + "name": "STRING", + "type": "database", + "url": "https://string-db.org/", + "description": "PPI networks for multiple organisms.", + "tags": [ + "interaction", + "protein-protein-interaction" + ], + "tasks": [], + "modalities": [ + "Protein" + ], + "organism": [], + "api": false + }, + { + "id": "the_genotype_tissue_expression_gtex", + "name": "The Genotype-Tissue Expression (GTEx)", + "type": "database", + "url": "https://gtexportal.org/home/", + "description": "Human gene expression and regulation resource.", + "tags": [ + "genome" + ], + "tasks": [], + "modalities": [ + "Genomics" + ], + "organism": [], + "api": false + }, + { + "id": "the_human_protein_atlas", + "name": "THE HUMAN PROTEIN ATLAS", + "type": "database", + "url": "https://www.proteinatlas.org/", + "description": "Comprehensive human protein database (cells, tissues, organs).", + "tags": [ + "protein" + ], + "tasks": [], + "modalities": [ + "Protein" + ], + "organism": [], + "api": false + }, + { + "id": "therapeutic_target_database", + "name": "Therapeutic Target Database", + "type": "database", + "url": "https://idrblab.net/ttd/full-data-download", + "description": "Drug-target, target-disease, and drug-disease datasets.", + "tags": [ + "compound" + ], + "tasks": [], + "modalities": [ + "Small Molecule" + ], + "organism": [], + "api": false + }, + { + "id": "trrust_v2", + "name": "TRRUST v2", + "type": "database", + "url": "https://www.grnpedia.org/trrust/", + "description": "Manually curated database of human and mouse transcriptional regulatory interactions between transcription factors and their target genes, expanded with literature-derived evidence.", + "tags": [ + "gene-regulatory-network", + "interaction" + ], + "tasks": [], + "modalities": [ + "Gene Expression" + ], + "organism": [], + "api": false + }, + { + "id": "ucsc_genome_browser", + "name": "UCSC Genome Browser", + "type": "database", + "url": "https://genome.ucsc.edu/", + "description": "UCSC's genome browser.", + "tags": [ + "genome" + ], + "tasks": [], + "modalities": [ + "Genomics" + ], + "organism": [], + "api": false + }, + { + "id": "uniclust", + "name": "Uniclust", + "type": "database", + "url": "https://uniclust.mmseqs.com/", + "description": "Clustered protein sequence databases.", + "tags": [ + "protein" + ], + "tasks": [], + "modalities": [ + "Protein" + ], + "organism": [], + "api": false + }, + { + "id": "uniprot", + "name": "UniProt", + "type": "database", + "url": "https://www.uniprot.org/", + "description": "Functional information on proteins.", + "tags": [ + "protein" + ], + "tasks": [], + "modalities": [ + "Protein" + ], + "organism": [], + "api": false + }, + { + "id": "uniref", + "name": "UniRef", + "type": "database", + "url": "https://www.uniprot.org/uniref/", + "description": "Non-redundant sequence database clustering UniProtKB entries at multiple sequence identity thresholds.", + "tags": [ + "protein" + ], + "tasks": [], + "modalities": [ + "Protein" + ], + "organism": [], + "api": false + }, + { + "id": "wikipathways", + "name": "WikiPathways", + "type": "database", + "url": "https://wikipathways.org/", + "description": "Database of biological pathways.", + "tags": [ + "pathway" + ], + "tasks": [], + "modalities": [ + "Pathway" + ], + "organism": [], + "api": false + }, + { + "id": "zinc_ligand_discovery_database", + "name": "ZINC ligand discovery database", + "type": "database", + "url": "https://zinc.docking.org/", + "description": "Free database of commercially-available compounds for virtual screening.", + "tags": [ + "compound" + ], + "tasks": [], + "modalities": [ + "Small Molecule" + ], + "organism": [], + "api": false + }, + { + "id": "ai4chem_chemllm_7b_chat", + "name": "AI4Chem/ChemLLM-7B-Chat", + "type": "model", + "url": "https://huggingface.co/AI4Chem/ChemLLM-7B-Chat", + "description": "LLM for chemical & molecular science.", + "tags": [ + "llm-for-biology" + ], + "tasks": [ + "Language Modeling" + ], + "modalities": [ + "Text" + ], + "organism": [], + "api": false + }, + { + "id": "alphafold3", + "name": "AlphaFold3", + "type": "model", + "url": "https://github.com/google-deepmind/alphafold3", + "description": "Predicts structures of proteins, nucleic acids, small molecules, and their complexes.", + "tags": [ + "foundation-models", + "protein-foundation-models", + "protein-structure-prediction-and-design" + ], + "tasks": [ + "Foundation Model", + "Protein Structure Prediction" + ], + "modalities": [ + "Protein" + ], + "organism": [], + "api": false + }, + { + "id": "ankh", + "name": "Ankh", + "type": "model", + "url": "https://github.com/agemagician/Ankh", + "description": "Efficient protein language model optimized for downstream prediction tasks including secondary structure, localization, and function annotation.", + "tags": [ + "foundation-models", + "pre-trained-embedding", + "protein-foundation-models" + ], + "tasks": [ + "Foundation Model" + ], + "modalities": [ + "Protein" + ], + "organism": [], + "api": false + }, + { + "id": "babel", + "name": "BABEL", + "type": "model", + "url": "https://github.com/wukevin/babel", + "description": "Cross-modality translation model enabling prediction between scRNA-seq and scATAC-seq profiles without requiring paired single-cell measurements.", + "tags": [ + "foundation-models", + "multi-omics-foundation-models", + "single-cell-foundation-models" + ], + "tasks": [ + "Foundation Model" + ], + "modalities": [ + "Multi-Omics", + "Single Cell" + ], + "organism": [], + "api": false + }, + { + "id": "basenji", + "name": "Basenji", + "type": "model", + "url": "https://github.com/calico/basenji", + "description": "Sequential regulatory activity prediction from DNA sequences.", + "tags": [ + "foundation-models", + "genomics-foundation-models" + ], + "tasks": [ + "Foundation Model" + ], + "modalities": [ + "Genomics" + ], + "organism": [], + "api": false + }, + { + "id": "biogpt", + "name": "BioGPT", + "type": "model", + "url": "https://github.com/microsoft/BioGPT", + "description": "LLM for biomedical text generation.", + "tags": [ + "llm-for-biology" + ], + "tasks": [ + "Language Modeling" + ], + "modalities": [ + "Text" + ], + "organism": [], + "api": false + }, + { + "id": "biomedclip", + "name": "BiomedCLIP", + "type": "model", + "url": "https://huggingface.co/microsoft/BiomedCLIP-PubMedBERT_256-vit_g_14", + "description": "CLIP-based vision-language foundation model for biomedical images and text trained on PubMed figure–caption pairs.", + "tags": [ + "foundation-models", + "multi-modal-foundation-models" + ], + "tasks": [ + "Foundation Model" + ], + "modalities": [ + "Multi-Modal" + ], + "organism": [], + "api": false + }, + { + "id": "biomedlm", + "name": "BioMedLM", + "type": "model", + "url": "https://huggingface.co/stanford-crfm/BioMedLM", + "description": "2.7B parameter GPT-2-style language model trained exclusively on biomedical literature from PubMed for biomedical question answering and text generation.", + "tags": [ + "llm-for-biology" + ], + "tasks": [ + "Language Modeling" + ], + "modalities": [ + "Text" + ], + "organism": [], + "api": false + }, + { + "id": "boltz_1", + "name": "Boltz-1", + "type": "model", + "url": "https://github.com/jwohlwend/boltz", + "description": "Open-source all-atom biomolecular structure prediction model for proteins, nucleic acids, small molecules, and their complexes achieving AlphaFold3-level accuracy.", + "tags": [ + "foundation-models", + "protein-foundation-models", + "protein-structure-prediction-and-design" + ], + "tasks": [ + "Foundation Model", + "Protein Structure Prediction" + ], + "modalities": [ + "Protein" + ], + "organism": [], + "api": false + }, + { + "id": "borzoi", + "name": "Borzoi", + "type": "model", + "url": "https://github.com/calico/borzoi", + "description": "Extended successor to Enformer for predicting RNA-seq coverage from long genomic sequence windows (524 kb) with improved resolution.", + "tags": [ + "foundation-models", + "genomics-foundation-models" + ], + "tasks": [ + "Foundation Model" + ], + "modalities": [ + "Genomics" + ], + "organism": [], + "api": false + }, + { + "id": "bulkformer", + "name": "BulkFormer", + "type": "model", + "url": "https://github.com/KangBoming/BulkFormer", + "description": "Foundation model for bulk RNA-seq data; learns general transcriptomic representations.", + "tags": [ + "foundation-models", + "single-cell-foundation-models", + "transcriptomics-foundation-models" + ], + "tasks": [ + "Foundation Model" + ], + "modalities": [ + "Single Cell", + "Transcriptomics" + ], + "organism": [], + "api": false + }, + { + "id": "caduceus", + "name": "Caduceus", + "type": "model", + "url": "https://github.com/kuleshov-group/caduceus", + "description": "Bidirectional equivariant long-range DNA sequence model based on Mamba.", + "tags": [ + "foundation-models", + "genomics-foundation-models" + ], + "tasks": [ + "Foundation Model" + ], + "modalities": [ + "Genomics" + ], + "organism": [], + "api": false + }, + { + "id": "cancerfoundation", + "name": "CancerFoundation", + "type": "model", + "url": "https://github.com/BoevaLab/CancerFoundation", + "description": "Single-cell RNA-seq foundation model trained exclusively on a curated dataset of malignant cells to learn cancer-specific embeddings.", + "tags": [ + "foundation-models", + "single-cell-foundation-models", + "transcriptomics-foundation-models" + ], + "tasks": [ + "Foundation Model" + ], + "modalities": [ + "Single Cell", + "Transcriptomics" + ], + "organism": [], + "api": false + }, + { + "id": "cassia", + "name": "CASSIA", + "type": "model", + "url": "https://github.com/ElliotXie/CASSIA", + "description": "Multi-agent LLM for reference-free, interpretable cell-type annotation of single-cell RNA-seq data, with dedicated annotation, validation, scoring, and reporting agents.", + "tags": [ + "llm-for-biology" + ], + "tasks": [ + "Language Modeling" + ], + "modalities": [ + "Text" + ], + "organism": [], + "api": false + }, + { + "id": "cellplm", + "name": "CellPLM", + "type": "model", + "url": "https://github.com/OmicsML/CellPLM", + "description": "Cell pre-trained language model with inter-cell transformer architecture for diverse single-cell analysis tasks.", + "tags": [ + "foundation-models", + "single-cell-foundation-models", + "transcriptomics-foundation-models" + ], + "tasks": [ + "Foundation Model" + ], + "modalities": [ + "Single Cell", + "Transcriptomics" + ], + "organism": [], + "api": false + }, + { + "id": "chai_1", + "name": "Chai-1", + "type": "model", + "url": "https://github.com/chaidiscovery/chai-lab", + "description": "Unified molecular structure prediction model covering proteins, nucleic acids, small molecules, and complexes.", + "tags": [ + "foundation-models", + "protein-foundation-models", + "protein-structure-prediction-and-design" + ], + "tasks": [ + "Foundation Model", + "Protein Structure Prediction" + ], + "modalities": [ + "Protein" + ], + "organism": [], + "api": false + }, + { + "id": "chatdrug", + "name": "ChatDrug", + "type": "model", + "url": "https://github.com/chao1224/ChatDrug", + "description": "LLM-based conversational pipeline for drug discovery, using natural language prompts for iterative drug editing and optimization.", + "tags": [ + "llm-for-biology" + ], + "tasks": [ + "Language Modeling" + ], + "modalities": [ + "Text" + ], + "organism": [], + "api": false + }, + { + "id": "chemberta_2", + "name": "ChemBERTa-2", + "type": "model", + "url": "https://github.com/seyonechithrananda/bert-loves-chemistry", + "description": "RoBERTa-based molecular language model pretrained on SMILES for small-molecule representation learning.", + "tags": [ + "compound-embedding", + "compound-foundation-models", + "foundation-models" + ], + "tasks": [ + "Foundation Model" + ], + "modalities": [ + "Small Molecule" + ], + "organism": [], + "api": false + }, + { + "id": "chemcpa", + "name": "chemCPA", + "type": "model", + "url": "https://github.com/theislab/chemCPA", + "description": "Compositional perturbation autoencoder for predicting single-cell transcriptional responses to unseen drug perturbations and dose combinations.", + "tags": [ + "drug-discovery", + "drug-response-prediction" + ], + "tasks": [ + "Drug Discovery", + "Drug Response Prediction" + ], + "modalities": [ + "Small Molecule" + ], + "organism": [], + "api": false + }, + { + "id": "chief", + "name": "CHIEF", + "type": "model", + "url": "https://github.com/hms-dbmi/CHIEF", + "description": "Clinical Histopathology Imaging Evaluation Foundation model integrating histology images and clinical context for pan-cancer analysis.", + "tags": [ + "foundation-models", + "multi-modal-foundation-models" + ], + "tasks": [ + "Foundation Model" + ], + "modalities": [ + "Multi-Modal" + ], + "organism": [], + "api": false + }, + { + "id": "clawbio", + "name": "ClawBio", + "type": "model", + "url": "https://github.com/ClawBio/ClawBio", + "description": "Bioinformatics-native AI agent skill library with local-first pharmacogenomics, ancestry PCA, semantic similarity, nutrigenomics, and metagenomics skills.", + "tags": [ + "llm-for-biology" + ], + "tasks": [ + "Language Modeling" + ], + "modalities": [ + "Text" + ], + "organism": [], + "api": false + }, + { + "id": "concerto", + "name": "Concerto", + "type": "model", + "url": "https://github.com/melobio/Concerto-reproducibility", + "description": "Contrastive self-supervised learning framework for single-cell multimodal data integration, batch correction, and reference-query mapping.", + "tags": [ + "foundation-models", + "multi-omics-foundation-models", + "single-cell-foundation-models" + ], + "tasks": [ + "Foundation Model" + ], + "modalities": [ + "Multi-Omics", + "Single Cell" + ], + "organism": [], + "api": false + }, + { + "id": "conch", + "name": "CONCH", + "type": "model", + "url": "https://github.com/mahmoodlab/CONCH", + "description": "Vision-language foundation model for computational pathology trained with contrastive captioning on pathology image–text pairs.", + "tags": [ + "foundation-models", + "single-cell-foundation-models", + "spatial-foundation-models" + ], + "tasks": [ + "Foundation Model" + ], + "modalities": [ + "Single Cell", + "Spatial Transcriptomics" + ], + "organism": [], + "api": false + }, + { + "id": "cyclecdr", + "name": "cycleCDR", + "type": "model", + "url": "https://github.com/hliulab/cycleCDR", + "description": "Interpretable cycle-consistency framework for modeling cellular responses to drug perturbations.", + "tags": [ + "drug-discovery", + "drug-response-prediction" + ], + "tasks": [ + "Drug Discovery", + "Drug Response Prediction" + ], + "modalities": [ + "Small Molecule" + ], + "organism": [], + "api": false + }, + { + "id": "deepaeg", + "name": "DeepAEG", + "type": "model", + "url": "https://github.com/zhejiangzhuque/DeepAEG", + "description": "GNN embedding + attention mechanism.", + "tags": [ + "drug-discovery", + "drug-response-prediction" + ], + "tasks": [ + "Drug Discovery", + "Drug Response Prediction" + ], + "modalities": [ + "Small Molecule" + ], + "organism": [], + "api": false + }, + { + "id": "deepdsc", + "name": "DeepDSC", + "type": "model", + "url": "https://ieeexplore-ieee-org.ezp2.lib.umn.edu/stamp/stamp.jsp?tp=&arnumber=8723620&tag=1", + "description": "Autoencoder + fully connected NN.", + "tags": [ + "drug-discovery", + "drug-response-prediction" + ], + "tasks": [ + "Drug Discovery", + "Drug Response Prediction" + ], + "modalities": [ + "Small Molecule" + ], + "organism": [], + "api": false + }, + { + "id": "deepdta", + "name": "DeepDTA", + "type": "model", + "url": "https://github.com/hkmztrk/DeepDTA", + "description": "Deep learning model using CNNs on protein sequences and drug SMILES.", + "tags": [ + "drug-discovery", + "drug-target-interaction" + ], + "tasks": [ + "Drug Discovery", + "Drug Target Interaction" + ], + "modalities": [ + "Protein", + "Small Molecule" + ], + "organism": [], + "api": false + }, + { + "id": "deeppurpose", + "name": "DeepPurpose", + "type": "model", + "url": "https://github.com/kexinhuang12345/DeepPurpose", + "description": "Deep learning library for drug repurposing.", + "tags": [ + "drug-discovery", + "drug-repurposing" + ], + "tasks": [ + "Drug Discovery", + "Drug Repurposing" + ], + "modalities": [ + "Small Molecule" + ], + "organism": [], + "api": false + }, + { + "id": "deepsea", + "name": "DeepSEA", + "type": "model", + "url": "http://deepsea.princeton.edu/", + "description": "Deep learning framework for predicting chromatin effects of sequence alterations with single-nucleotide sensitivity across thousands of chromatin features.", + "tags": [ + "foundation-models", + "genomics-foundation-models" + ], + "tasks": [ + "Foundation Model" + ], + "modalities": [ + "Genomics" + ], + "organism": [], + "api": false + }, + { + "id": "dgdrp", + "name": "DGDRP", + "type": "model", + "url": "https://github.com/minwoopak/heteronet", + "description": "Multi-view embedding neural network.", + "tags": [ + "drug-discovery", + "drug-response-prediction" + ], + "tasks": [ + "Drug Discovery", + "Drug Response Prediction" + ], + "modalities": [ + "Small Molecule" + ], + "organism": [], + "api": false + }, + { + "id": "diffdock", + "name": "DiffDock", + "type": "model", + "url": "https://github.com/gcorso/DiffDock", + "description": "Diffusion generative model for molecular docking, predicting the binding pose of small molecules to protein targets.", + "tags": [ + "drug-discovery", + "molecular-generation" + ], + "tasks": [ + "Drug Discovery", + "Molecular Generation" + ], + "modalities": [ + "Small Molecule" + ], + "organism": [], + "api": false + }, + { + "id": "diffsbdd", + "name": "DiffSBDD", + "type": "model", + "url": "https://github.com/arneschneuing/DiffSBDD", + "description": "Equivariant diffusion model for structure-based drug design that generates molecules and binding conformations for protein targets.", + "tags": [ + "drug-discovery", + "molecular-generation" + ], + "tasks": [ + "Drug Discovery", + "Molecular Generation" + ], + "modalities": [ + "Small Molecule" + ], + "organism": [], + "api": false + }, + { + "id": "dnabert", + "name": "DNABERT", + "type": "model", + "url": "https://github.com/jerryji1993/DNABERT", + "description": "Pre-trained bidirectional encoder for DNA sequence analysis.", + "tags": [ + "foundation-models", + "genomics-foundation-models" + ], + "tasks": [ + "Foundation Model" + ], + "modalities": [ + "Genomics" + ], + "organism": [], + "api": false + }, + { + "id": "dnabert_2", + "name": "DNABERT-2", + "type": "model", + "url": "https://github.com/Zhihan1996/DNABERT_2", + "description": "Improved genome foundation model with efficient tokenization.", + "tags": [ + "foundation-models", + "genomics-foundation-models" + ], + "tasks": [ + "Foundation Model" + ], + "modalities": [ + "Genomics" + ], + "organism": [], + "api": false + }, + { + "id": "drgat", + "name": "drGAT", + "type": "model", + "url": "https://github.com/inoue0426/drGAT", + "description": "Attention-based model for drug response prediction with gene explainability.", + "tags": [ + "drug-discovery", + "drug-response-prediction" + ], + "tasks": [ + "Drug Discovery", + "Drug Response Prediction" + ], + "modalities": [ + "Small Molecule" + ], + "organism": [], + "api": false + }, + { + "id": "drugban", + "name": "DrugBAN", + "type": "model", + "url": "https://github.com/peizhenbai/DrugBAN", + "description": "Bilinear attention network for interpretable DTI prediction.", + "tags": [ + "drug-discovery", + "drug-target-interaction" + ], + "tasks": [ + "Drug Discovery", + "Drug Target Interaction" + ], + "modalities": [ + "Protein", + "Small Molecule" + ], + "organism": [], + "api": false + }, + { + "id": "druml", + "name": "DRUML", + "type": "model", + "url": "https://github.com/CutillasLab/DRUMLR", + "description": "Ensemble machine learning framework combining standard ML with deep learning to systematically rank anti-cancer drugs from proteomics and RNA-seq data.", + "tags": [ + "drug-discovery", + "drug-response-prediction" + ], + "tasks": [ + "Drug Discovery", + "Drug Response Prediction" + ], + "modalities": [ + "Small Molecule" + ], + "organism": [], + "api": false + }, + { + "id": "dtinet", + "name": "DTINet", + "type": "model", + "url": "https://github.com/luoyunan/DTINet", + "description": "Network-based framework integrating heterogeneous biological data for DTI prediction.", + "tags": [ + "drug-discovery", + "drug-target-interaction" + ], + "tasks": [ + "Drug Discovery", + "Drug Target Interaction" + ], + "modalities": [ + "Protein", + "Small Molecule" + ], + "organism": [], + "api": false + }, + { + "id": "enformer", + "name": "Enformer", + "type": "model", + "url": "https://github.com/deepmind/deepmind-research/tree/master/enformer", + "description": "Transformer model predicting gene expression from DNA sequence.", + "tags": [ + "foundation-models", + "genomics-foundation-models" + ], + "tasks": [ + "Foundation Model" + ], + "modalities": [ + "Genomics" + ], + "organism": [], + "api": false + }, + { + "id": "esm3", + "name": "ESM3", + "type": "model", + "url": "https://github.com/evolutionaryscale/esm", + "description": "Multimodal protein language model that jointly reasons over sequence, structure, and function for generative protein design and engineering.", + "tags": [ + "foundation-models", + "protein-foundation-models", + "protein-structure-prediction-and-design" + ], + "tasks": [ + "Foundation Model", + "Protein Structure Prediction" + ], + "modalities": [ + "Protein" + ], + "organism": [], + "api": false + }, + { + "id": "esmfold", + "name": "ESMFold", + "type": "model", + "url": "https://github.com/facebookresearch/esm", + "description": "Fast protein structure prediction using language model embeddings.", + "tags": [ + "foundation-models", + "protein-foundation-models", + "protein-structure-prediction-and-design" + ], + "tasks": [ + "Foundation Model", + "Protein Structure Prediction" + ], + "modalities": [ + "Protein" + ], + "organism": [], + "api": false + }, + { + "id": "evo", + "name": "Evo", + "type": "model", + "url": "https://github.com/evo-design/evo", + "description": "Long-context genomic foundation model (up to 1M tokens).", + "tags": [ + "foundation-models", + "genomics-foundation-models" + ], + "tasks": [ + "Foundation Model" + ], + "modalities": [ + "Genomics" + ], + "organism": [], + "api": false + }, + { + "id": "evodiff", + "name": "EvoDiff", + "type": "model", + "url": "https://github.com/microsoft/evodiff", + "description": "Discrete diffusion framework for protein sequence generation trained on evolutionary-scale data, supporting unconditional generation, disordered region design, and functional motif scaffolding. [ [paper-2023](https://www.biorxiv.org/content/10.1101/2023.09.11.556673v1) ]", + "tags": [ + "foundation-models", + "protein-foundation-models", + "protein-structure-prediction-and-design" + ], + "tasks": [ + "Foundation Model", + "Protein Structure Prediction" + ], + "modalities": [ + "Protein" + ], + "organism": [], + "api": false + }, + { + "id": "evolutionary_scale_modeling_esm", + "name": "Evolutionary Scale Modeling (ESM)", + "type": "model", + "url": "https://github.com/facebookresearch/esm", + "description": "Protein embeddings.", + "tags": [ + "foundation-models", + "pre-trained-embedding", + "protein-foundation-models" + ], + "tasks": [ + "Foundation Model" + ], + "modalities": [ + "Protein" + ], + "organism": [], + "api": false + }, + { + "id": "gears", + "name": "GEARS", + "type": "model", + "url": "https://github.com/snap-stanford/GEARS", + "description": "Graph-based model for predicting transcriptional responses to single and combinatorial genetic perturbations using biological priors.", + "tags": [ + "foundation-models", + "single-cell-foundation-models", + "transcriptomics-foundation-models" + ], + "tasks": [ + "Foundation Model" + ], + "modalities": [ + "Single Cell", + "Transcriptomics" + ], + "organism": [], + "api": false + }, + { + "id": "genecompass", + "name": "GeneCompass", + "type": "model", + "url": "https://github.com/xCompass-AI/GeneCompass", + "description": "Large-scale foundation model integrating DNA regulatory sequences and single-cell transcriptomics from 120M+ cells across multiple species for gene regulation prediction.", + "tags": [ + "foundation-models", + "multi-omics-foundation-models", + "single-cell-foundation-models" + ], + "tasks": [ + "Foundation Model" + ], + "modalities": [ + "Multi-Omics", + "Single Cell" + ], + "organism": [], + "api": false + }, + { + "id": "geneformer", + "name": "Geneformer", + "type": "model", + "url": "https://huggingface.co/ctheodoris/Geneformer", + "description": "Context-aware, attention-based deep learning model pretrained on a large corpus of single-cell transcriptomes.", + "tags": [ + "foundation-models", + "single-cell-foundation-models", + "transcriptomics-foundation-models" + ], + "tasks": [ + "Foundation Model" + ], + "modalities": [ + "Single Cell", + "Transcriptomics" + ], + "organism": [], + "api": false + }, + { + "id": "genegpt", + "name": "GeneGPT", + "type": "model", + "url": "https://github.com/ncbi/GeneGPT", + "description": "LLM for biomedical information, integrated with various APIs.", + "tags": [ + "llm-for-biology" + ], + "tasks": [ + "Language Modeling" + ], + "modalities": [ + "Text" + ], + "organism": [], + "api": false + }, + { + "id": "genept", + "name": "GenePT", + "type": "model", + "url": "https://github.com/yiqunchen/GenePT", + "description": "Foundation LLM for single-cell data.", + "tags": [ + "llm-for-biology" + ], + "tasks": [ + "Language Modeling" + ], + "modalities": [ + "Text" + ], + "organism": [], + "api": false + }, + { + "id": "gigapath", + "name": "GigaPath", + "type": "model", + "url": "https://github.com/prov-gigapath/prov-gigapath", + "description": "Slide-level digital pathology foundation model pretrained on 1.3 billion pathology image tokens from whole-slide images.", + "tags": [ + "foundation-models", + "single-cell-foundation-models", + "spatial-foundation-models" + ], + "tasks": [ + "Foundation Model" + ], + "modalities": [ + "Single Cell", + "Spatial Transcriptomics" + ], + "organism": [], + "api": false + }, + { + "id": "glue", + "name": "GLUE", + "type": "model", + "url": "https://github.com/gao-lab/GLUE", + "description": "Graph-Linked Unified Embedding framework for unpaired single-cell multi-omics data integration across RNA, ATAC, methylation, and protein modalities.", + "tags": [ + "foundation-models", + "multi-omics-foundation-models", + "single-cell-foundation-models" + ], + "tasks": [ + "Foundation Model" + ], + "modalities": [ + "Multi-Omics", + "Single Cell" + ], + "organism": [], + "api": false + }, + { + "id": "gpn_genomic_pre_trained_network", + "name": "GPN (Genomic Pre-trained Network)", + "type": "model", + "url": "https://github.com/songlab-cal/gpn", + "description": "Masked language model for DNA sequences enabling zero-shot variant effect prediction without requiring functional annotations.", + "tags": [ + "foundation-models", + "genomics-foundation-models" + ], + "tasks": [ + "Foundation Model" + ], + "modalities": [ + "Genomics" + ], + "organism": [], + "api": false + }, + { + "id": "graphdta", + "name": "GraphDTA", + "type": "model", + "url": "https://github.com/thinng/GraphDTA", + "description": "Graph neural network–based DTI prediction using molecular graphs.", + "tags": [ + "drug-discovery", + "drug-target-interaction" + ], + "tasks": [ + "Drug Discovery", + "Drug Target Interaction" + ], + "modalities": [ + "Protein", + "Small Molecule" + ], + "organism": [], + "api": false + }, + { + "id": "grover", + "name": "GROVER", + "type": "model", + "url": "https://github.com/tencent-ailab/grover", + "description": "Self-supervised graph transformer for large-scale molecular representation learning from unlabeled compounds.", + "tags": [ + "compound-embedding", + "compound-foundation-models", + "foundation-models" + ], + "tasks": [ + "Foundation Model" + ], + "modalities": [ + "Small Molecule" + ], + "organism": [], + "api": false + }, + { + "id": "hidra", + "name": "HiDRA", + "type": "model", + "url": "https://github.com/bsml320/HiDRA", + "description": "Hierarchical network model incorporating gene and pathway-level information for cancer drug response prediction.", + "tags": [ + "drug-discovery", + "drug-response-prediction" + ], + "tasks": [ + "Drug Discovery", + "Drug Response Prediction" + ], + "modalities": [ + "Small Molecule" + ], + "organism": [], + "api": false + }, + { + "id": "hyenadna", + "name": "HyenaDNA", + "type": "model", + "url": "https://github.com/HazyResearch/hyena-dna", + "description": "Long-range genomic foundation model handling sequences up to 1M tokens with sub-quadratic attention.", + "tags": [ + "foundation-models", + "genomics-foundation-models" + ], + "tasks": [ + "Foundation Model" + ], + "modalities": [ + "Genomics" + ], + "organism": [], + "api": false + }, + { + "id": "jamie", + "name": "JAMIE", + "type": "model", + "url": "https://github.com/Oafish1/JAMIE", + "description": "Joint variational autoencoder for multimodal single-cell data imputation and embedding.", + "tags": [ + "foundation-models", + "multi-omics-foundation-models", + "single-cell-foundation-models" + ], + "tasks": [ + "Foundation Model" + ], + "modalities": [ + "Multi-Omics", + "Single Cell" + ], + "organism": [], + "api": false + }, + { + "id": "jtvae", + "name": "JTVAE", + "type": "model", + "url": "https://github.com/wengong-jin/icml18-jtnn", + "description": "Junction tree variational autoencoder for molecular graph generation that guarantees chemical validity via a hierarchical tree decomposition.", + "tags": [ + "drug-discovery", + "molecular-generation" + ], + "tasks": [ + "Drug Discovery", + "Molecular Generation" + ], + "modalities": [ + "Small Molecule" + ], + "organism": [], + "api": false + }, + { + "id": "matcha", + "name": "Matcha", + "type": "model", + "url": "https://github.com/LigandPro/Matcha", + "description": "Multi-stage Riemannian flow matching model for physically valid molecular docking with scoring, pose filtering, and benchmarks.", + "tags": [ + "drug-discovery", + "molecular-generation" + ], + "tasks": [ + "Drug Discovery", + "Molecular Generation" + ], + "modalities": [ + "Small Molecule" + ], + "organism": [], + "api": false + }, + { + "id": "mcpinn", + "name": "MCPINN", + "type": "model", + "url": "https://github.com/mhlee0903/multi_channels_PINN", + "description": "Drug discovery via compound-protein interaction and machine learning.", + "tags": [ + "compound-protein-interaction", + "drug-discovery" + ], + "tasks": [ + "Compound-Protein Interaction", + "Drug Discovery" + ], + "modalities": [ + "Protein", + "Small Molecule" + ], + "organism": [], + "api": false + }, + { + "id": "midas", + "name": "MIDAS", + "type": "model", + "url": "https://github.com/labomics/midas", + "description": "Mosaic integration and differential accessibility model for single-cell multi-omics data that handles arbitrary missing-modality combinations across transcriptomics, chromatin accessibility, and proteomics.", + "tags": [ + "foundation-models", + "multi-omics-foundation-models", + "single-cell-foundation-models" + ], + "tasks": [ + "Foundation Model" + ], + "modalities": [ + "Multi-Omics", + "Single Cell" + ], + "organism": [], + "api": false + }, + { + "id": "mira", + "name": "MIRA", + "type": "model", + "url": "https://github.com/cistrome/MIRA", + "description": "Probabilistic multimodal topic model jointly modeling single-cell transcriptomics and chromatin accessibility for regulatory network inference.", + "tags": [ + "foundation-models", + "multi-omics-foundation-models", + "single-cell-foundation-models" + ], + "tasks": [ + "Foundation Model" + ], + "modalities": [ + "Multi-Omics", + "Single Cell" + ], + "organism": [], + "api": false + }, + { + "id": "mofa", + "name": "MOFA+", + "type": "model", + "url": "https://github.com/bioFAM/MOFA2", + "description": "Multi-Omics Factor Analysis framework identifying shared axes of variation across bulk and single-cell datasets including RNA, ATAC, proteomics, methylation, and copy number.", + "tags": [ + "foundation-models", + "multi-omics-foundation-models", + "single-cell-foundation-models" + ], + "tasks": [ + "Foundation Model" + ], + "modalities": [ + "Multi-Omics", + "Single Cell" + ], + "organism": [], + "api": false + }, + { + "id": "mofgcn", + "name": "MOFGCN", + "type": "model", + "url": "https://github.com/weiba/MOFGCN/tree/main", + "description": "GCN + heterogeneous network.", + "tags": [ + "drug-discovery", + "drug-response-prediction" + ], + "tasks": [ + "Drug Discovery", + "Drug Response Prediction" + ], + "modalities": [ + "Small Molecule" + ], + "organism": [], + "api": false + }, + { + "id": "mol2vec", + "name": "Mol2Vec", + "type": "model", + "url": "https://github.com/samoturk/mol2vec", + "description": "Unsupervised molecular embedding method inspired by Word2Vec for learning vector representations of chemical substructures.", + "tags": [ + "compound-embedding", + "compound-foundation-models", + "foundation-models" + ], + "tasks": [ + "Foundation Model" + ], + "modalities": [ + "Small Molecule" + ], + "organism": [], + "api": false + }, + { + "id": "molecular_transformer", + "name": "Molecular Transformer", + "type": "model", + "url": "https://github.com/pschwllr/MolecularTransformer", + "description": "Sequence-to-sequence model for retrosynthesis prediction.", + "tags": [ + "drug-discovery", + "molecular-generation" + ], + "tasks": [ + "Drug Discovery", + "Molecular Generation" + ], + "modalities": [ + "Small Molecule" + ], + "organism": [], + "api": false + }, + { + "id": "molformer", + "name": "MolFormer", + "type": "model", + "url": "https://github.com/IBM/molformer", + "description": "Linear attention transformer pretrained on millions of SMILES strings for efficient molecular embeddings.", + "tags": [ + "compound-embedding", + "compound-foundation-models", + "foundation-models" + ], + "tasks": [ + "Foundation Model" + ], + "modalities": [ + "Small Molecule" + ], + "organism": [], + "api": false + }, + { + "id": "molgpt", + "name": "MolGPT", + "type": "model", + "url": "https://github.com/devalab/molgpt", + "description": "Transformer-based model for molecular generation.", + "tags": [ + "drug-discovery", + "molecular-generation" + ], + "tasks": [ + "Drug Discovery", + "Molecular Generation" + ], + "modalities": [ + "Small Molecule" + ], + "organism": [], + "api": false + }, + { + "id": "molt5", + "name": "MolT5", + "type": "model", + "url": "https://github.com/blender-nlp/MolT5", + "description": "Language model for molecular tasks bridging text and SMILES, enabling molecule captioning and text-driven molecule generation.", + "tags": [ + "llm-for-biology" + ], + "tasks": [ + "Language Modeling" + ], + "modalities": [ + "Text" + ], + "organism": [], + "api": false + }, + { + "id": "moltrans", + "name": "MolTrans", + "type": "model", + "url": "https://github.com/kexinhuang12345/MolTrans", + "description": "Transformer-based DTI model leveraging molecular substructures.", + "tags": [ + "drug-discovery", + "drug-target-interaction" + ], + "tasks": [ + "Drug Discovery", + "Drug Target Interaction" + ], + "modalities": [ + "Protein", + "Small Molecule" + ], + "organism": [], + "api": false + }, + { + "id": "multigrate", + "name": "Multigrate", + "type": "model", + "url": "https://github.com/theislab/multigrate", + "description": "Asymmetric multi-omics variational autoencoder for integrating single-cell data across RNA, ATAC, and protein modalities with missing-modality support.", + "tags": [ + "foundation-models", + "multi-omics-foundation-models", + "single-cell-foundation-models" + ], + "tasks": [ + "Foundation Model" + ], + "modalities": [ + "Multi-Omics", + "Single Cell" + ], + "organism": [], + "api": false + }, + { + "id": "multivi", + "name": "MultiVI", + "type": "model", + "url": "https://github.com/scverse/scvi-tools", + "description": "Multi-modal variational autoencoder for integrating paired and unpaired single-cell RNA-seq and ATAC-seq measurements into a unified latent space.", + "tags": [ + "foundation-models", + "multi-omics-foundation-models", + "single-cell-foundation-models" + ], + "tasks": [ + "Foundation Model" + ], + "modalities": [ + "Multi-Omics", + "Single Cell" + ], + "organism": [], + "api": false + }, + { + "id": "musk", + "name": "MUSK", + "type": "model", + "url": "https://github.com/lilab-stanford/MUSK", + "description": "Vision-language foundation model for precision oncology analyzing multimodal paired text and pathology image data for biomarker prediction and retrieval.", + "tags": [ + "foundation-models", + "multi-modal-foundation-models" + ], + "tasks": [ + "Foundation Model" + ], + "modalities": [ + "Multi-Modal" + ], + "organism": [], + "api": false + }, + { + "id": "neodti", + "name": "NeoDTI", + "type": "model", + "url": "https://github.com/FangpingWan/NeoDTI", + "description": "Library for drug-target interaction prediction.", + "tags": [ + "drug-discovery", + "drug-target-interaction" + ], + "tasks": [ + "Drug Discovery", + "Drug Target Interaction" + ], + "modalities": [ + "Protein", + "Small Molecule" + ], + "organism": [], + "api": false + }, + { + "id": "nicheformer", + "name": "Nicheformer", + "type": "model", + "url": "https://github.com/theislab/nicheformer", + "description": "Foundation model for single-cell and spatial omics using a transformer architecture with positional embeddings to encode spatial cell information.", + "tags": [ + "foundation-models", + "single-cell-foundation-models", + "spatial-foundation-models" + ], + "tasks": [ + "Foundation Model" + ], + "modalities": [ + "Single Cell", + "Spatial Transcriptomics" + ], + "organism": [], + "api": false + }, + { + "id": "nucleotide_transformer", + "name": "Nucleotide Transformer", + "type": "model", + "url": "https://github.com/instadeepai/nucleotide-transformer", + "description": "Foundation model for genomic sequences across multiple species.", + "tags": [ + "foundation-models", + "genomics-foundation-models" + ], + "tasks": [ + "Foundation Model" + ], + "modalities": [ + "Genomics" + ], + "organism": [], + "api": false + }, + { + "id": "omegafold", + "name": "OmegaFold", + "type": "model", + "url": "https://github.com/HeliXonProtein/OmegaFold", + "description": "High-resolution de novo protein structure prediction from sequence.", + "tags": [ + "foundation-models", + "protein-foundation-models", + "protein-structure-prediction-and-design" + ], + "tasks": [ + "Foundation Model", + "Protein Structure Prediction" + ], + "modalities": [ + "Protein" + ], + "organism": [], + "api": false + }, + { + "id": "openfold", + "name": "OpenFold", + "type": "model", + "url": "https://github.com/aqlaboratory/openfold", + "description": "Trainable, memory-efficient open-source reproduction of AlphaFold2 enabling custom protein structure prediction workflows.", + "tags": [ + "foundation-models", + "protein-foundation-models", + "protein-structure-prediction-and-design" + ], + "tasks": [ + "Foundation Model", + "Protein Structure Prediction" + ], + "modalities": [ + "Protein" + ], + "organism": [], + "api": false + }, + { + "id": "paccmannrl", + "name": "PaccMannRL", + "type": "model", + "url": "https://github.com/PaccMann/paccmann_generator", + "description": "Reinforcement learning-based generative model for de novo hit-like anticancer molecule design from transcriptomic data.", + "tags": [ + "drug-discovery", + "molecular-generation" + ], + "tasks": [ + "Drug Discovery", + "Molecular Generation" + ], + "modalities": [ + "Small Molecule" + ], + "organism": [], + "api": false + }, + { + "id": "pathomicfusion", + "name": "PathomicFusion", + "type": "model", + "url": "https://github.com/mahmoodlab/PathomicFusion", + "description": "Integrated framework fusing histopathology and genomic features via CNN, GNN, and attention gating for cancer diagnosis and prognosis.", + "tags": [ + "foundation-models", + "multi-modal-foundation-models" + ], + "tasks": [ + "Foundation Model" + ], + "modalities": [ + "Multi-Modal" + ], + "organism": [], + "api": false + }, + { + "id": "phikon", + "name": "Phikon", + "type": "model", + "url": "https://huggingface.co/owkin/phikon", + "description": "ViT-based pathology foundation model pretrained with iBOT self-supervision on TCGA whole-slide images.", + "tags": [ + "foundation-models", + "single-cell-foundation-models", + "spatial-foundation-models" + ], + "tasks": [ + "Foundation Model" + ], + "modalities": [ + "Single Cell", + "Spatial Transcriptomics" + ], + "organism": [], + "api": false + }, + { + "id": "plip", + "name": "PLIP", + "type": "model", + "url": "https://github.com/PathologyFoundation/plip", + "description": "Vision-language foundation model for pathology trained with contrastive learning on pathology image–text pairs for image classification and text-to-image retrieval.", + "tags": [ + "foundation-models", + "multi-modal-foundation-models" + ], + "tasks": [ + "Foundation Model" + ], + "modalities": [ + "Multi-Modal" + ], + "organism": [], + "api": false + }, + { + "id": "porpoise", + "name": "PORPOISE", + "type": "model", + "url": "https://github.com/mahmoodlab/PORPOISE", + "description": "Pan-cancer integrative histology-genomic analysis framework using multimodal deep learning for patient stratification.", + "tags": [ + "foundation-models", + "multi-modal-foundation-models" + ], + "tasks": [ + "Foundation Model" + ], + "modalities": [ + "Multi-Modal" + ], + "organism": [], + "api": false + }, + { + "id": "prnet", + "name": "PRNet", + "type": "model", + "url": "https://github.com/Perturbation-Response-Prediction/PRnet", + "description": "Deep generative model for predicting transcriptional responses to novel chemical perturbations for drug discovery.", + "tags": [ + "drug-discovery", + "drug-response-prediction" + ], + "tasks": [ + "Drug Discovery", + "Drug Response Prediction" + ], + "modalities": [ + "Small Molecule" + ], + "organism": [], + "api": false + }, + { + "id": "progen2", + "name": "ProGen2", + "type": "model", + "url": "https://github.com/salesforce/progen", + "description": "Protein language model trained on diverse protein families for sequence generation and fitness prediction.", + "tags": [ + "foundation-models", + "pre-trained-embedding", + "protein-foundation-models" + ], + "tasks": [ + "Foundation Model" + ], + "modalities": [ + "Protein" + ], + "organism": [], + "api": false + }, + { + "id": "proteinmpnn", + "name": "ProteinMPNN", + "type": "model", + "url": "https://github.com/dauparas/ProteinMPNN", + "description": "Deep learning model for protein sequence design given backbone structure.", + "tags": [ + "foundation-models", + "protein-foundation-models", + "protein-structure-prediction-and-design" + ], + "tasks": [ + "Foundation Model", + "Protein Structure Prediction" + ], + "modalities": [ + "Protein" + ], + "organism": [], + "api": false + }, + { + "id": "prottrans", + "name": "ProtTrans", + "type": "model", + "url": "https://github.com/agemagician/ProtTrans", + "description": "Suite of protein language models (ProtBERT, ProtT5, ProtXLNet) trained on billions of protein sequences from UniRef and BFD.", + "tags": [ + "foundation-models", + "pre-trained-embedding", + "protein-foundation-models" + ], + "tasks": [ + "Foundation Model" + ], + "modalities": [ + "Protein" + ], + "organism": [], + "api": false + }, + { + "id": "recover", + "name": "RECOVER", + "type": "model", + "url": "https://github.com/RECOVERcoalition/Recover", + "description": "Machine learning framework for predicting synergistic drug combination responses across cell lines.", + "tags": [ + "drug-discovery", + "drug-response-prediction" + ], + "tasks": [ + "Drug Discovery", + "Drug Response Prediction" + ], + "modalities": [ + "Small Molecule" + ], + "organism": [], + "api": false + }, + { + "id": "reinvent", + "name": "REINVENT", + "type": "model", + "url": "https://github.com/MolecularAI/Reinvent", + "description": "Reinforcement learning for de novo drug design.", + "tags": [ + "drug-discovery", + "molecular-generation" + ], + "tasks": [ + "Drug Discovery", + "Molecular Generation" + ], + "modalities": [ + "Small Molecule" + ], + "organism": [], + "api": false + }, + { + "id": "release", + "name": "ReLeaSE", + "type": "model", + "url": "https://github.com/isayev/ReLeaSE", + "description": "Deep reinforcement learning framework for de novo drug design combining a generative and predictive model.", + "tags": [ + "drug-discovery", + "molecular-generation" + ], + "tasks": [ + "Drug Discovery", + "Molecular Generation" + ], + "modalities": [ + "Small Molecule" + ], + "organism": [], + "api": false + }, + { + "id": "rfdiffusion", + "name": "RFdiffusion", + "type": "model", + "url": "https://github.com/RosettaCommons/RFdiffusion", + "description": "Generative model for protein backbone design using diffusion.", + "tags": [ + "foundation-models", + "protein-foundation-models", + "protein-structure-prediction-and-design" + ], + "tasks": [ + "Foundation Model", + "Protein Structure Prediction" + ], + "modalities": [ + "Protein" + ], + "organism": [], + "api": false + }, + { + "id": "rosettafold", + "name": "RoseTTAFold", + "type": "model", + "url": "https://github.com/RosettaCommons/RoseTTAFold", + "description": "Three-track neural network for protein structure prediction.", + "tags": [ + "foundation-models", + "protein-foundation-models", + "protein-structure-prediction-and-design" + ], + "tasks": [ + "Foundation Model", + "Protein Structure Prediction" + ], + "modalities": [ + "Protein" + ], + "organism": [], + "api": false + }, + { + "id": "saprot", + "name": "SaProt", + "type": "model", + "url": "https://github.com/westlake-reup/SaProt", + "description": "Structure-aware protein language model using structure-aware tokens that encode both sequence and backbone geometry for improved function prediction.", + "tags": [ + "foundation-models", + "protein-foundation-models", + "protein-structure-prediction-and-design" + ], + "tasks": [ + "Foundation Model", + "Protein Structure Prediction" + ], + "modalities": [ + "Protein" + ], + "organism": [], + "api": false + }, + { + "id": "saturn", + "name": "SATURN", + "type": "model", + "url": "https://github.com/snap-stanford/SATURN", + "description": "Transformer-based model integrating gene expression and protein sequences via a protein language model to learn unified multi-species cell embeddings.", + "tags": [ + "foundation-models", + "single-cell-foundation-models", + "transcriptomics-foundation-models" + ], + "tasks": [ + "Foundation Model" + ], + "modalities": [ + "Single Cell", + "Transcriptomics" + ], + "organism": [], + "api": false + }, + { + "id": "scarches", + "name": "scArches", + "type": "model", + "url": "https://github.com/theislab/scarches", + "description": "Transfer learning framework for mapping new single-cell datasets onto pre-trained reference atlases across batches, conditions, and modalities.", + "tags": [ + "domain-alignment", + "foundation-models", + "single-cell-foundation-models" + ], + "tasks": [ + "Domain Alignment", + "Foundation Model" + ], + "modalities": [ + "Single Cell" + ], + "organism": [], + "api": false + }, + { + "id": "scbert", + "name": "scBERT", + "type": "model", + "url": "https://github.com/TencentAILabHealthcare/scBERT", + "description": "BERT-based foundation model pretrained on large-scale scRNA-seq data for cell type annotation.", + "tags": [ + "foundation-models", + "single-cell-foundation-models", + "transcriptomics-foundation-models" + ], + "tasks": [ + "Foundation Model" + ], + "modalities": [ + "Single Cell", + "Transcriptomics" + ], + "organism": [], + "api": false + }, + { + "id": "scbutterfly", + "name": "scButterfly", + "type": "model", + "url": "https://github.com/BioX-NKU/scButterfly", + "description": "Dual-aligned variational autoencoder for single-cell cross-modality translation between paired and unpaired multiomics data.", + "tags": [ + "foundation-models", + "multi-omics-foundation-models", + "single-cell-foundation-models" + ], + "tasks": [ + "Foundation Model" + ], + "modalities": [ + "Multi-Omics", + "Single Cell" + ], + "organism": [], + "api": false + }, + { + "id": "scfoundation", + "name": "scFoundation", + "type": "model", + "url": "https://github.com/biomap-research/scFoundation", + "description": "Large-scale foundation model for single-cell gene expression, enabling multiple downstream tasks.", + "tags": [ + "foundation-models", + "single-cell-foundation-models", + "transcriptomics-foundation-models" + ], + "tasks": [ + "Foundation Model" + ], + "modalities": [ + "Single Cell", + "Transcriptomics" + ], + "organism": [], + "api": false + }, + { + "id": "scgpt", + "name": "scGPT", + "type": "model", + "url": "https://github.com/bowang-lab/scGPT", + "description": "Transformer-based foundation model pretrained on millions of single-cell profiles.", + "tags": [ + "foundation-models", + "single-cell-foundation-models", + "transcriptomics-foundation-models" + ], + "tasks": [ + "Foundation Model" + ], + "modalities": [ + "Single Cell", + "Transcriptomics" + ], + "organism": [], + "api": false + }, + { + "id": "scgpt_spatial", + "name": "scGPT-spatial", + "type": "model", + "url": "https://github.com/bowang-lab/scGPT-spatial", + "description": "Extension of scGPT for spatial transcriptomics with continual pretraining and a mixture-of-experts decoder for spatial gene expression analysis.", + "tags": [ + "foundation-models", + "single-cell-foundation-models", + "spatial-foundation-models" + ], + "tasks": [ + "Foundation Model" + ], + "modalities": [ + "Single Cell", + "Spatial Transcriptomics" + ], + "organism": [], + "api": false + }, + { + "id": "scmulan", + "name": "scMulan", + "type": "model", + "url": "https://github.com/SuperBianC/scMulan", + "description": "Single-cell multi-omic language model pretrained on ~10M cells spanning transcriptomics, epigenomics, and proteomics for cross-omics transfer tasks.", + "tags": [ + "foundation-models", + "multi-omics-foundation-models", + "single-cell-foundation-models" + ], + "tasks": [ + "Foundation Model" + ], + "modalities": [ + "Multi-Omics", + "Single Cell" + ], + "organism": [], + "api": false + }, + { + "id": "scpair", + "name": "scPair", + "type": "model", + "url": "https://github.com/quon-titative-biology/scPair", + "description": "Bidirectional feedforward network for single-cell multimodal analysis with cross-modality prediction leveraging single-cell atlases.", + "tags": [ + "foundation-models", + "multi-omics-foundation-models", + "single-cell-foundation-models" + ], + "tasks": [ + "Foundation Model" + ], + "modalities": [ + "Multi-Omics", + "Single Cell" + ], + "organism": [], + "api": false + }, + { + "id": "scprint", + "name": "scPRINT", + "type": "model", + "url": "https://github.com/cantinilab/scPRINT", + "description": "Pretrained on 50M cells for scRNA-seq denoising & zero imputation.", + "tags": [ + "llm-for-biology" + ], + "tasks": [ + "Language Modeling" + ], + "modalities": [ + "Text" + ], + "organism": [], + "api": false + }, + { + "id": "sei", + "name": "Sei", + "type": "model", + "url": "https://github.com/FunctionLab/sei-framework", + "description": "Sequence-to-function framework learning a genome-wide regulatory activity code from DNA sequences for variant effect prediction.", + "tags": [ + "foundation-models", + "genomics-foundation-models" + ], + "tasks": [ + "Foundation Model" + ], + "modalities": [ + "Genomics" + ], + "organism": [], + "api": false + }, + { + "id": "spatialglue", + "name": "SpatialGlue", + "type": "model", + "url": "https://github.com/zhanglabtools/SpatialGlue", + "description": "Graph attention network for spatial multi-omics integration jointly embedding spatial transcriptomics with chromatin accessibility or proteomics.", + "tags": [ + "foundation-models", + "multi-omics-foundation-models", + "single-cell-foundation-models" + ], + "tasks": [ + "Foundation Model" + ], + "modalities": [ + "Multi-Omics", + "Single Cell" + ], + "organism": [], + "api": false + }, + { + "id": "targetdiff", + "name": "TargetDiff", + "type": "model", + "url": "https://github.com/guanjq/targetdiff", + "description": "3D equivariant diffusion model for structure-based drug design.", + "tags": [ + "drug-discovery", + "molecular-generation" + ], + "tasks": [ + "Drug Discovery", + "Molecular Generation" + ], + "modalities": [ + "Small Molecule" + ], + "organism": [], + "api": false + }, + { + "id": "tgsa", + "name": "TGSA", + "type": "model", + "url": "https://github.com/violet-sto/TGSA", + "description": "Tumor gene set and attention-based model leveraging biological pathway knowledge for drug response prediction.", + "tags": [ + "drug-discovery", + "drug-response-prediction" + ], + "tasks": [ + "Drug Discovery", + "Drug Response Prediction" + ], + "modalities": [ + "Small Molecule" + ], + "organism": [], + "api": false + }, + { + "id": "toad", + "name": "TOAD", + "type": "model", + "url": "https://github.com/mahmoodlab/TOAD", + "description": "Tumor Origin Assessment via Deep-learning; weakly-supervised multi-task model predicting cancer primary origin from H&E whole-slide images.", + "tags": [ + "foundation-models", + "multi-modal-foundation-models" + ], + "tasks": [ + "Foundation Model" + ], + "modalities": [ + "Multi-Modal" + ], + "organism": [], + "api": false + }, + { + "id": "tosica", + "name": "TOSICA", + "type": "model", + "url": "https://github.com/JackieHanlaopo/TOSICA", + "description": "Transformer-based framework for one-stop interpretable cell-type annotation supporting cross-dataset and cross-species transfer.", + "tags": [ + "domain-alignment", + "foundation-models", + "single-cell-foundation-models" + ], + "tasks": [ + "Domain Alignment", + "Foundation Model" + ], + "modalities": [ + "Single Cell" + ], + "organism": [], + "api": false + }, + { + "id": "totalvi", + "name": "totalVI", + "type": "model", + "url": "https://github.com/scverse/scvi-tools", + "description": "Probabilistic framework for joint analysis of paired scRNA-seq and protein (CITE-seq) data enabling multi-modal cell state representation across single-cell datasets.", + "tags": [ + "foundation-models", + "multi-omics-foundation-models", + "single-cell-foundation-models" + ], + "tasks": [ + "Foundation Model" + ], + "modalities": [ + "Multi-Omics", + "Single Cell" + ], + "organism": [], + "api": false + }, + { + "id": "transformercpi", + "name": "TransformerCPI", + "type": "model", + "url": "https://github.com/lifanchen-simm/transformerCPI", + "description": "CPI prediction using Transformer.", + "tags": [ + "compound-protein-interaction", + "drug-discovery" + ], + "tasks": [ + "Compound-Protein Interaction", + "Drug Discovery" + ], + "modalities": [ + "Protein", + "Small Molecule" + ], + "organism": [], + "api": false + }, + { + "id": "transigen", + "name": "TranSiGen", + "type": "model", + "url": "https://github.com/myzhengSIMM/TranSiGen", + "description": "Dual-VAE architecture for ligand-based virtual screening, drug response prediction, and drug repurposing using chemical-induced transcriptional profiles.", + "tags": [ + "drug-discovery", + "drug-repurposing" + ], + "tasks": [ + "Drug Discovery", + "Drug Repurposing" + ], + "modalities": [ + "Small Molecule" + ], + "organism": [], + "api": false + }, + { + "id": "uce", + "name": "UCE", + "type": "model", + "url": "https://github.com/snap-stanford/UCE", + "description": "Universal Cell Embeddings: zero-shot single-cell embedding model trained on 36M cells across species, tissues, and assays without fine-tuning.", + "tags": [ + "foundation-models", + "single-cell-foundation-models", + "transcriptomics-foundation-models" + ], + "tasks": [ + "Foundation Model" + ], + "modalities": [ + "Single Cell", + "Transcriptomics" + ], + "organism": [], + "api": false + }, + { + "id": "uni", + "name": "UNI", + "type": "model", + "url": "https://github.com/mahmoodlab/UNI", + "description": "General-purpose self-supervised pathology foundation model trained on 100K+ whole-slide images for diverse computational pathology tasks.", + "tags": [ + "foundation-models", + "single-cell-foundation-models", + "spatial-foundation-models" + ], + "tasks": [ + "Foundation Model" + ], + "modalities": [ + "Single Cell", + "Spatial Transcriptomics" + ], + "organism": [], + "api": false + }, + { + "id": "uni_mol", + "name": "Uni-Mol", + "type": "model", + "url": "https://github.com/deepmodeling/Uni-Mol", + "description": "3D molecular pretraining framework for universal representation learning on molecules and protein pockets.", + "tags": [ + "compound-embedding", + "compound-foundation-models", + "foundation-models" + ], + "tasks": [ + "Foundation Model" + ], + "modalities": [ + "Small Molecule" + ], + "organism": [], + "api": false + }, + { + "id": "unitednet", + "name": "UnitedNet", + "type": "model", + "url": "https://github.com/LiuLab-Bioelectronics-Harvard/UnitedNet", + "description": "Interpretable multi-task deep neural network for single-cell multi-omics integration spanning transcriptomics, chromatin accessibility, and proteomics.", + "tags": [ + "foundation-models", + "multi-omics-foundation-models", + "single-cell-foundation-models" + ], + "tasks": [ + "Foundation Model" + ], + "modalities": [ + "Multi-Omics", + "Single Cell" + ], + "organism": [], + "api": false + }, + { + "id": "virchow", + "name": "Virchow", + "type": "model", + "url": "https://huggingface.co/paige-ai/Virchow", + "description": "Million-slide digital pathology foundation model using a vision transformer and self-supervised distillation for tile-level pathology image representation.", + "tags": [ + "foundation-models", + "multi-modal-foundation-models" + ], + "tasks": [ + "Foundation Model" + ], + "modalities": [ + "Multi-Modal" + ], + "organism": [], + "api": false + }, + { + "id": "autozyme", + "name": "AutoZyme", + "type": "toolkit", + "url": "https://github.com/ElliotXie/autozyme", + "description": "Autonomous agentic framework that speeds up bioinformatics software (e.g. Scanpy, Seurat) on CPUs while preserving the original results.", + "tags": [ + "preprocessing-tools" + ], + "tasks": [ + "Preprocessing" + ], + "modalities": [], + "organism": [], + "api": false + }, + { + "id": "biopython", + "name": "Biopython", + "type": "toolkit", + "url": "https://biopython.org/", + "description": "Collection of Python tools for biological computation including sequence analysis, structure parsing, and database access.", + "tags": [ + "preprocessing-tools" + ], + "tasks": [ + "Preprocessing" + ], + "modalities": [], + "organism": [], + "api": false + }, + { + "id": "casper", + "name": "CaSpER", + "type": "toolkit", + "url": "https://github.com/akdess/CaSpER", + "description": "CNV identification and visualization by integrative analysis of single-cell or bulk RNA-seq data.", + "tags": [ + "preprocessing-tools" + ], + "tasks": [ + "Preprocessing" + ], + "modalities": [], + "organism": [], + "api": false + }, + { + "id": "cellcharter", + "name": "CellCharter", + "type": "toolkit", + "url": "https://github.com/CSOgroup/cellcharter", + "description": "Identification and characterization of spatial cell niches from spatial transcriptomics using VAEs and Gaussian mixture models.", + "tags": [ + "preprocessing-tools" + ], + "tasks": [ + "Preprocessing" + ], + "modalities": [], + "organism": [], + "api": false + }, + { + "id": "cellchat", + "name": "CellChat", + "type": "toolkit", + "url": "https://github.com/sqjin/CellChat", + "description": "Inference and analysis of cell-cell communication ligand-receptor networks from single-cell transcriptomics data.", + "tags": [ + "preprocessing-tools" + ], + "tasks": [ + "Preprocessing" + ], + "modalities": [], + "organism": [], + "api": false + }, + { + "id": "celltypist", + "name": "CellTypist", + "type": "toolkit", + "url": "https://github.com/Teichlab/celltypist", + "description": "Automated cell type annotation for scRNA-seq.", + "tags": [ + "preprocessing-tools" + ], + "tasks": [ + "Preprocessing" + ], + "modalities": [], + "organism": [], + "api": false + }, + { + "id": "chatspatial", + "name": "ChatSpatial", + "type": "toolkit", + "url": "https://github.com/cafferychen777/ChatSpatial", + "description": "MCP server for spatial transcriptomics analysis via natural language.", + "tags": [ + "preprocessing-tools" + ], + "tasks": [ + "Preprocessing" + ], + "modalities": [], + "organism": [], + "api": false + }, + { + "id": "chemistry_development_kit", + "name": "Chemistry Development Kit", + "type": "toolkit", + "url": "https://github.com/cdk/cdk", + "description": "Cheminformatics software & machine learning tools.", + "tags": [ + "preprocessing-tools" + ], + "tasks": [ + "Preprocessing" + ], + "modalities": [], + "organism": [], + "api": false + }, + { + "id": "commot", + "name": "COMMOT", + "type": "toolkit", + "url": "https://github.com/zcang/COMMOT", + "description": "Optimal transport-based framework for screening cell-cell communication in spatial transcriptomics.", + "tags": [ + "preprocessing-tools" + ], + "tasks": [ + "Preprocessing" + ], + "modalities": [], + "organism": [], + "api": false + }, + { + "id": "deepchem", + "name": "DeepChem", + "type": "toolkit", + "url": "https://github.com/deepchem/deepchem", + "description": "Deep learning library for drug discovery, quantum chemistry, and materials science.", + "tags": [ + "preprocessing-tools" + ], + "tasks": [ + "Preprocessing" + ], + "modalities": [], + "organism": [], + "api": false + }, + { + "id": "deeptalk", + "name": "DeepTalk", + "type": "toolkit", + "url": "https://github.com/JiangBioLab/DeepTalk", + "description": "Graph attention network for deciphering cell-cell communication from spatial transcriptomics data.", + "tags": [ + "preprocessing-tools" + ], + "tasks": [ + "Preprocessing" + ], + "modalities": [], + "organism": [], + "api": false + }, + { + "id": "doubletfinder", + "name": "DoubletFinder", + "type": "toolkit", + "url": "https://github.com/chris-mcginnis-ucsf/DoubletFinder", + "description": "Machine learning approach for detecting multiplet (doublet) artifacts in single-cell RNA-seq data.", + "tags": [ + "preprocessing-tools" + ], + "tasks": [ + "Preprocessing" + ], + "modalities": [], + "organism": [], + "api": false + }, + { + "id": "flashdeconv", + "name": "FlashDeconv", + "type": "toolkit", + "url": "https://github.com/cafferychen777/flashdeconv", + "description": "High-performance spatial transcriptomics deconvolution (~1M spots in ~3 min).", + "tags": [ + "preprocessing-tools" + ], + "tasks": [ + "Preprocessing" + ], + "modalities": [], + "organism": [], + "api": false + }, + { + "id": "gromacs", + "name": "GROMACS", + "type": "toolkit", + "url": "https://www.gromacs.org/", + "description": "Molecular dynamics simulation package for biochemical molecules.", + "tags": [ + "preprocessing-tools" + ], + "tasks": [ + "Preprocessing" + ], + "modalities": [], + "organism": [], + "api": false + }, + { + "id": "harmony", + "name": "Harmony", + "type": "toolkit", + "url": "https://github.com/immunogenomics/harmony", + "description": "Fast and scalable integration of single-cell data across datasets, conditions, technologies, and species.", + "tags": [ + "preprocessing-tools" + ], + "tasks": [ + "Preprocessing" + ], + "modalities": [], + "organism": [], + "api": false + }, + { + "id": "kallisto", + "name": "kallisto", + "type": "toolkit", + "url": "https://pachterlab.github.io/kallisto/", + "description": "Near-optimal RNA-seq quantification using pseudoalignment for fast transcript abundance estimation.", + "tags": [ + "preprocessing-tools" + ], + "tasks": [ + "Preprocessing" + ], + "modalities": [], + "organism": [], + "api": false + }, + { + "id": "linger", + "name": "LINGER", + "type": "toolkit", + "url": "https://github.com/Durenlab/LINGER", + "description": "Neural network for gene regulatory network inference from single-cell multiome (RNA+ATAC-seq) data with bulk data pretraining.", + "tags": [ + "preprocessing-tools" + ], + "tasks": [ + "Preprocessing" + ], + "modalities": [], + "organism": [], + "api": false + }, + { + "id": "mdanalysis", + "name": "MDAnalysis", + "type": "toolkit", + "url": "https://www.mdanalysis.org/", + "description": "Python library for analyzing and altering molecular dynamics simulation trajectories.", + "tags": [ + "preprocessing-tools" + ], + "tasks": [ + "Preprocessing" + ], + "modalities": [], + "organism": [], + "api": false + }, + { + "id": "mogonet", + "name": "MOGONET", + "type": "toolkit", + "url": "https://github.com/txWang/MOGONET", + "description": "Multi-omics graph convolutional network framework for patient classification and biomarker identification.", + "tags": [ + "preprocessing-tools" + ], + "tasks": [ + "Preprocessing" + ], + "modalities": [], + "organism": [], + "api": false + }, + { + "id": "monocle3", + "name": "Monocle3", + "type": "toolkit", + "url": "https://cole-trapnell-lab.github.io/monocle3/", + "description": "Single-cell trajectory analysis tool for learning developmental trajectories and ordering cells in pseudotime.", + "tags": [ + "preprocessing-tools" + ], + "tasks": [ + "Preprocessing" + ], + "modalities": [], + "organism": [], + "api": false + }, + { + "id": "ncem", + "name": "NCEM", + "type": "toolkit", + "url": "https://github.com/theislab/ncem", + "description": "GNN-based model for learning intercellular communication from spatial graphs of cells.", + "tags": [ + "preprocessing-tools" + ], + "tasks": [ + "Preprocessing" + ], + "modalities": [], + "organism": [], + "api": false + }, + { + "id": "numbat", + "name": "Numbat", + "type": "toolkit", + "url": "https://github.com/kharchenkolab/numbat", + "description": "Haplotype-aware copy number variation inference from single-cell RNA-seq using hidden Markov models.", + "tags": [ + "preprocessing-tools" + ], + "tasks": [ + "Preprocessing" + ], + "modalities": [], + "organism": [], + "api": false + }, + { + "id": "openmm", + "name": "OpenMM", + "type": "toolkit", + "url": "https://openmm.org/", + "description": "High-performance toolkit for molecular simulation and GPU-accelerated MD.", + "tags": [ + "preprocessing-tools" + ], + "tasks": [ + "Preprocessing" + ], + "modalities": [], + "organism": [], + "api": false + }, + { + "id": "rdkit", + "name": "RDKit", + "type": "toolkit", + "url": "https://github.com/rdkit/rdkit", + "description": "Cheminformatics software & machine learning toolkit.", + "tags": [ + "preprocessing-tools" + ], + "tasks": [ + "Preprocessing" + ], + "modalities": [], + "organism": [], + "api": false + }, + { + "id": "scanpy", + "name": "Scanpy", + "type": "toolkit", + "url": "https://scanpy.readthedocs.io/en/stable/", + "description": "Python library for scRNA-seq analysis.", + "tags": [ + "preprocessing-tools" + ], + "tasks": [ + "Preprocessing" + ], + "modalities": [], + "organism": [], + "api": false + }, + { + "id": "scenic", + "name": "SCENIC", + "type": "toolkit", + "url": "https://github.com/aertslab/SCENIC", + "description": "Single-cell regulatory network inference and clustering linking transcription factors to co-expressed gene modules.", + "tags": [ + "preprocessing-tools" + ], + "tasks": [ + "Preprocessing" + ], + "modalities": [], + "organism": [], + "api": false + }, + { + "id": "scipenn", + "name": "sciPENN", + "type": "toolkit", + "url": "https://github.com/jlakkis/sciPENN", + "description": "RNN-based method for simultaneous protein expression prediction, uncertainty estimation, and cell-type label transfer from CITE-seq and scRNA-seq data.", + "tags": [ + "preprocessing-tools" + ], + "tasks": [ + "Preprocessing" + ], + "modalities": [], + "organism": [], + "api": false + }, + { + "id": "scvelo", + "name": "scVelo", + "type": "toolkit", + "url": "https://github.com/theislab/scvelo", + "description": "RNA velocity estimation for single-cell transcriptomics, inferring the direction and speed of cell differentiation.", + "tags": [ + "preprocessing-tools" + ], + "tasks": [ + "Preprocessing" + ], + "modalities": [], + "organism": [], + "api": false + }, + { + "id": "scvi_tools", + "name": "scvi-tools", + "type": "toolkit", + "url": "https://scvi-tools.org/", + "description": "Probabilistic models for single-cell omics data analysis.", + "tags": [ + "preprocessing-tools" + ], + "tasks": [ + "Preprocessing" + ], + "modalities": [], + "organism": [], + "api": false + }, + { + "id": "seurat", + "name": "Seurat", + "type": "toolkit", + "url": "https://satijalab.org/seurat/", + "description": "R library for scRNA-seq analysis.", + "tags": [ + "preprocessing-tools" + ], + "tasks": [ + "Preprocessing" + ], + "modalities": [], + "organism": [], + "api": false + }, + { + "id": "squidpy", + "name": "Squidpy", + "type": "toolkit", + "url": "https://squidpy.readthedocs.io/", + "description": "Python library for spatial single-cell analysis.", + "tags": [ + "preprocessing-tools" + ], + "tasks": [ + "Preprocessing" + ], + "modalities": [], + "organism": [], + "api": false + }, + { + "id": "stagate", + "name": "STAGATE", + "type": "toolkit", + "url": "https://github.com/RucDongLab/STAGATE", + "description": "Adaptive graph attention auto-encoder for spatial domain identification in spatial transcriptomics.", + "tags": [ + "preprocessing-tools" + ], + "tasks": [ + "Preprocessing" + ], + "modalities": [], + "organism": [], + "api": false + }, + { + "id": "star", + "name": "STAR", + "type": "toolkit", + "url": "https://github.com/alexdobin/STAR", + "description": "Ultrafast universal RNA-seq aligner with support for spliced alignment and single-cell quantification via STARsolo.", + "tags": [ + "preprocessing-tools" + ], + "tasks": [ + "Preprocessing" + ], + "modalities": [], + "organism": [], + "api": false + }, + { + "id": "tigon", + "name": "TIGON", + "type": "toolkit", + "url": "https://github.com/yutongo/TIGON", + "description": "Neural optimal transport method for reconstructing growth and dynamic trajectories from single-cell transcriptomics.", + "tags": [ + "preprocessing-tools" + ], + "tasks": [ + "Preprocessing" + ], + "modalities": [], + "organism": [], + "api": false + } +] diff --git a/upstream/inoue0426-awesome-computational-biology/catalogue/scripts/requirements.txt b/upstream/inoue0426-awesome-computational-biology/catalogue/scripts/requirements.txt new file mode 100644 index 0000000..e391ca7 --- /dev/null +++ b/upstream/inoue0426-awesome-computational-biology/catalogue/scripts/requirements.txt @@ -0,0 +1,15 @@ +--- +title: "Requirements" +task: "" +lineage_type: import +upstream_source: https://github.com/inoue0426/awesome-computational-biology/blob/12d87583/scripts/requirements.txt +upstream_sha: 12d87583 +imported_at: 2026-06-26 +prompt_class: catalogue +upstream_changes: accepted +author: upstream +validated: false +--- + +PyYAML>=6.0 +matplotlib>=3.7