From 83e1be9256aac075a2a7eb86a94ab0bcf89123ff Mon Sep 17 00:00:00 2001 From: promptadmin Date: Mon, 31 Aug 2026 23:14:14 +0000 Subject: [PATCH 1/5] [upstream-sync] README.md from inoue0426/awesome-computational-biology@c6f07d90 [catalogue] --- .../catalogue/README.md | 17 ++++++++++++----- 1 file changed, 12 insertions(+), 5 deletions(-) diff --git a/upstream/inoue0426-awesome-computational-biology/catalogue/README.md b/upstream/inoue0426-awesome-computational-biology/catalogue/README.md index 77368fd..94e95c4 100644 --- a/upstream/inoue0426-awesome-computational-biology/catalogue/README.md +++ b/upstream/inoue0426-awesome-computational-biology/catalogue/README.md @@ -2,9 +2,9 @@ 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/7a064bf0/README.md -upstream_sha: 7a064bf0 -imported_at: 2026-08-08 +upstream_source: https://github.com/inoue0426/awesome-computational-biology/blob/c6f07d90/README.md +upstream_sha: c6f07d90 +imported_at: 2026-08-31 prompt_class: catalogue upstream_changes: accepted author: upstream @@ -75,6 +75,7 @@ Browse and search the resources via the [GitHub Pages UI](https://inoue0426.gith - [Drug Target Interaction](#drug-target-interaction) - [Compound-Protein Interaction](#compound-protein-interaction) - [Molecular Generation](#molecular-generation) + - [Protein Property Prediction](#protein-property-prediction) - [LLM for Biology](#llm-for-biology) - [Foundation Models](#foundation-models) - [Single-cell Foundation Models](#single-cell-foundation-models) @@ -159,6 +160,7 @@ Browse and search the resources via the [GitHub Pages UI](https://inoue0426.gith - [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. +- [OncoKB](https://www.oncokb.org/) — Precision oncology knowledge base of cancer genes, variants, and therapeutic implications. - [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. @@ -316,7 +318,7 @@ Browse and search the resources via the [GitHub Pages UI](https://inoue0426.gith - [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. +- [DeepTalk](https://github.com/JiangBioLab/DeepTalk) — Graph attention network for deciphering cell-cell communication from spatial transcriptomics. - [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. @@ -383,6 +385,10 @@ Browse and search the resources via the [GitHub Pages UI](https://inoue0426.gith - [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. +### Protein Property Prediction + +- [NbBayesLM](https://github.com/FairuzShadmaniShishir/NbBayesLM) — Bayesian neural network integrating protein language model embeddings and physicochemical features to predict nanobody thermostability with uncertainty estimates. [Paper](https://www.frontiersin.org/journals/bioinformatics/articles/10.3389/fbinf.2026.1832968/full) + ### LLM for Biology - [AI4Chem/ChemLLM-7B-Chat](https://huggingface.co/AI4Chem/ChemLLM-7B-Chat) — LLM for chemical & molecular science. @@ -439,7 +445,7 @@ Browse and search the resources via the [GitHub Pages UI](https://inoue0426.gith - [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. +- [MIDAS](https://github.com/labomics/midas) — Mosaic integration and differential accessibility model for single-cell multi-omics 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. @@ -521,6 +527,7 @@ If you use this list in papers, slides, or documentation, please cite this repos To keep quality high, additions should meet all of the following: - The resource is trustworthy and relevant to computational biology. +- The resource has clear value to the scope and audience of this collection; highly specialized resources with limited relevance beyond a narrow application context may be declined even when technically sound. - 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). -- 2.54.0 From 76d448b99ff795064002506b53348ff824321b71 Mon Sep 17 00:00:00 2001 From: promptadmin Date: Mon, 31 Aug 2026 23:14:16 +0000 Subject: [PATCH 2/5] [upstream-sync] cspell.json from inoue0426/awesome-computational-biology@c6f07d90 [unknown] --- .../catalogue/cspell.json | 11 +++++++---- 1 file changed, 7 insertions(+), 4 deletions(-) diff --git a/upstream/inoue0426-awesome-computational-biology/catalogue/cspell.json b/upstream/inoue0426-awesome-computational-biology/catalogue/cspell.json index 407c31a..fc803bd 100644 --- a/upstream/inoue0426-awesome-computational-biology/catalogue/cspell.json +++ b/upstream/inoue0426-awesome-computational-biology/catalogue/cspell.json @@ -2,9 +2,9 @@ title: "Cspell" task: "" lineage_type: import -upstream_source: https://github.com/inoue0426/awesome-computational-biology/blob/7a064bf0/cspell.json -upstream_sha: 7a064bf0 -imported_at: 2026-08-08 +upstream_source: https://github.com/inoue0426/awesome-computational-biology/blob/c6f07d90/cspell.json +upstream_sha: c6f07d90 +imported_at: 2026-08-31 prompt_class: unknown upstream_changes: accepted author: upstream @@ -59,6 +59,7 @@ validated: false "eukaryotic", "metabolites", "OMIM", + "OncoKB", "Mendelian", "DisGeNET", "GWAS", @@ -171,7 +172,9 @@ validated: false "bowang", "ctheodoris", "OpenAI", - "GPT" + "GPT", + "nanobody", + "thermostability" ], "ignorePaths": [ "node_modules/**" -- 2.54.0 From e68dccf95b0d9bf1900d348ed94a8e53e6b453b8 Mon Sep 17 00:00:00 2001 From: promptadmin Date: Mon, 31 Aug 2026 23:14:18 +0000 Subject: [PATCH 3/5] [upstream-sync] data/resources.json from inoue0426/awesome-computational-biology@c6f07d90 [catalogue] --- .../catalogue/data/resources.json | 499 +++++++++++++++--- 1 file changed, 430 insertions(+), 69 deletions(-) diff --git a/upstream/inoue0426-awesome-computational-biology/catalogue/data/resources.json b/upstream/inoue0426-awesome-computational-biology/catalogue/data/resources.json index 3a7a355..adc387b 100644 --- a/upstream/inoue0426-awesome-computational-biology/catalogue/data/resources.json +++ b/upstream/inoue0426-awesome-computational-biology/catalogue/data/resources.json @@ -2,9 +2,9 @@ title: "Resources" task: "" lineage_type: import -upstream_source: https://github.com/inoue0426/awesome-computational-biology/blob/7a064bf0/data/resources.json -upstream_sha: 7a064bf0 -imported_at: 2026-08-08 +upstream_source: https://github.com/inoue0426/awesome-computational-biology/blob/c6f07d90/data/resources.json +upstream_sha: c6f07d90 +imported_at: 2026-08-31 prompt_class: catalogue upstream_changes: accepted author: upstream @@ -899,10 +899,20 @@ validated: false ], "tasks": [], "modalities": [ - "Genomics" + "single-cell-rna-seq", + "genomics" ], "organism": [], - "api": false + "api": false, + "entities": [ + "cell", + "gene" + ], + "documentation": "https://www.10xgenomics.com/resources/datasets", + "last_checked": "2026-08-08", + "metadata_sources": [ + "https://www.10xgenomics.com/resources/datasets" + ] }, { "id": "alphafold_protein_structure_database", @@ -915,10 +925,20 @@ validated: false ], "tasks": [], "modalities": [ - "Protein" + "molecular-structure", + "protein-sequence" ], "organism": [], - "api": false + "api": false, + "entities": [ + "protein" + ], + "documentation": "https://alphafold.ebi.ac.uk/api-docs", + "last_checked": "2026-08-08", + "metadata_sources": [ + "https://alphafold.ebi.ac.uk/", + "https://alphafold.ebi.ac.uk/api-docs" + ] }, { "id": "bindingdb", @@ -932,11 +952,20 @@ validated: false ], "tasks": [], "modalities": [ - "Protein", - "Small Molecule" + "chemical-structure", + "molecular-structure" ], "organism": [], - "api": false + "api": false, + "entities": [ + "molecule", + "protein" + ], + "documentation": "https://www.bindingdb.org/rwd/bind/index.jsp", + "last_checked": "2026-08-08", + "metadata_sources": [ + "https://www.bindingdb.org/rwd/bind/index.jsp" + ] }, { "id": "biocyc", @@ -949,10 +978,20 @@ validated: false ], "tasks": [], "modalities": [ - "Pathway" + "genomics" ], "organism": [], - "api": false + "api": false, + "entities": [ + "gene", + "pathway", + "organism" + ], + "documentation": "https://biocyc.org/", + "last_checked": "2026-08-08", + "metadata_sources": [ + "https://biocyc.org/" + ] }, { "id": "biogrid", @@ -969,7 +1008,16 @@ validated: false "Protein" ], "organism": [], - "api": false + "api": false, + "entities": [ + "gene", + "protein" + ], + "documentation": "https://thebiogrid.org/", + "last_checked": "2026-08-08", + "metadata_sources": [ + "https://thebiogrid.org/" + ] }, { "id": "cancer_cell_line_encyclopedia", @@ -983,11 +1031,22 @@ validated: false ], "tasks": [], "modalities": [ - "Gene Expression", - "Small Molecule" + "genomics", + "transcriptomics" ], "organism": [], - "api": false + "api": false, + "entities": [ + "cell", + "gene", + "disease", + "drug" + ], + "documentation": "https://sites.broadinstitute.org/ccle/", + "last_checked": "2026-08-08", + "metadata_sources": [ + "https://sites.broadinstitute.org/ccle/" + ] }, { "id": "catalogue_of_somatic_mutations_in_cancer_cosmic", @@ -1000,10 +1059,20 @@ validated: false ], "tasks": [], "modalities": [ - "Genomics" + "genomics" ], "organism": [], - "api": false + "api": false, + "entities": [ + "disease", + "gene", + "variant" + ], + "documentation": "https://cancer.sanger.ac.uk/cosmic", + "last_checked": "2026-08-08", + "metadata_sources": [ + "https://cancer.sanger.ac.uk/cosmic" + ] }, { "id": "cath_database", @@ -1016,10 +1085,19 @@ validated: false ], "tasks": [], "modalities": [ - "Protein" + "molecular-structure", + "protein-sequence" ], "organism": [], - "api": false + "api": false, + "entities": [ + "protein" + ], + "documentation": "https://www.cathdb.info/", + "last_checked": "2026-08-08", + "metadata_sources": [ + "https://www.cathdb.info/" + ] }, { "id": "cbioportal", @@ -1032,10 +1110,23 @@ validated: false ], "tasks": [], "modalities": [ - "Genomics" + "genomics", + "clinical" ], "organism": [], - "api": false + "api": false, + "entities": [ + "disease", + "gene", + "variant" + ], + "github": "https://github.com/cBioPortal/cbioportal", + "documentation": "https://www.cbioportal.org/", + "last_checked": "2026-08-08", + "metadata_sources": [ + "https://www.cbioportal.org/", + "https://github.com/cBioPortal/cbioportal" + ] }, { "id": "cellminer_cross_database_cellminercdb", @@ -1092,10 +1183,20 @@ validated: false ], "tasks": [], "modalities": [ - "Small Molecule" + "chemical-structure" ], "organism": [], - "api": false + "api": false, + "entities": [ + "compound", + "molecule", + "protein" + ], + "documentation": "https://www.ebi.ac.uk/chembl/", + "last_checked": "2026-08-08", + "metadata_sources": [ + "https://www.ebi.ac.uk/chembl/" + ] }, { "id": "chemspider", @@ -1124,10 +1225,19 @@ validated: false ], "tasks": [], "modalities": [ - "Clinical" + "clinical" ], "organism": [], - "api": false + "api": false, + "entities": [ + "disease", + "drug" + ], + "documentation": "https://clinicaltrials.gov/", + "last_checked": "2026-08-08", + "metadata_sources": [ + "https://clinicaltrials.gov/" + ] }, { "id": "comparative_toxicogenomics_database", @@ -1141,11 +1251,20 @@ validated: false ], "tasks": [], "modalities": [ - "Gene", - "Small Molecule" + "knowledge-graph" ], "organism": [], - "api": false + "api": false, + "entities": [ + "compound", + "gene", + "disease" + ], + "documentation": "https://ctdbase.org/", + "last_checked": "2026-08-08", + "metadata_sources": [ + "https://ctdbase.org/" + ] }, { "id": "critical_assessment_of_structure_prediction_casp", @@ -1174,10 +1293,21 @@ validated: false ], "tasks": [], "modalities": [ - "Single Cell" + "single-cell-rna-seq", + "transcriptomics" ], "organism": [], - "api": false + "api": false, + "entities": [ + "cell", + "gene", + "tissue" + ], + "documentation": "https://cellxgene.cziscience.com/", + "last_checked": "2026-08-08", + "metadata_sources": [ + "https://cellxgene.cziscience.com/" + ] }, { "id": "davis_kinase_inhibitors_db", @@ -1208,10 +1338,21 @@ validated: false ], "tasks": [], "modalities": [ - "Genomics" + "genomics" ], "organism": [], - "api": false + "api": false, + "entities": [ + "cell", + "gene", + "disease", + "drug" + ], + "documentation": "https://depmap.org/portal/", + "last_checked": "2026-08-08", + "metadata_sources": [ + "https://depmap.org/portal/" + ] }, { "id": "dgidb", @@ -1225,11 +1366,19 @@ validated: false ], "tasks": [], "modalities": [ - "Gene", - "Small Molecule" + "knowledge-graph" ], "organism": [], - "api": false + "api": false, + "entities": [ + "drug", + "gene" + ], + "documentation": "https://www.dgidb.org/", + "last_checked": "2026-08-08", + "metadata_sources": [ + "https://www.dgidb.org/" + ] }, { "id": "diseases", @@ -1292,10 +1441,21 @@ validated: false ], "tasks": [], "modalities": [ - "Knowledge Graph" + "knowledge-graph" ], "organism": [], - "api": false + "api": false, + "entities": [ + "drug", + "disease", + "gene", + "pathway" + ], + "github": "https://github.com/SuLab/DrugMechDB", + "last_checked": "2026-08-08", + "metadata_sources": [ + "https://github.com/SuLab/DrugMechDB" + ] }, { "id": "drug_repurposing_hub", @@ -1308,10 +1468,20 @@ validated: false ], "tasks": [], "modalities": [ - "Small Molecule" + "chemical-structure" ], "organism": [], - "api": false + "api": false, + "entities": [ + "drug", + "protein", + "disease" + ], + "documentation": "https://repo-hub.broadinstitute.org/repurposing", + "last_checked": "2026-08-08", + "metadata_sources": [ + "https://repo-hub.broadinstitute.org/repurposing" + ] }, { "id": "drugbank", @@ -1349,10 +1519,20 @@ validated: false ], "tasks": [], "modalities": [ - "Small Molecule" + "chemical-structure" ], "organism": [], - "api": false + "api": false, + "entities": [ + "drug", + "protein", + "disease" + ], + "documentation": "https://drugcentral.org/", + "last_checked": "2026-08-08", + "metadata_sources": [ + "https://drugcentral.org/" + ] }, { "id": "drugtargetcommons", @@ -1365,10 +1545,19 @@ validated: false ], "tasks": [], "modalities": [ - "Small Molecule" + "chemical-structure" ], "organism": [], - "api": false + "api": false, + "entities": [ + "drug", + "protein" + ], + "documentation": "https://drugtargetcommons.fimm.fi/", + "last_checked": "2026-08-08", + "metadata_sources": [ + "https://drugtargetcommons.fimm.fi/" + ] }, { "id": "encode", @@ -1936,6 +2125,22 @@ validated: false "organism": [], "api": false }, + { + "id": "oncokb", + "name": "OncoKB", + "type": "database", + "url": "https://www.oncokb.org/", + "description": "Precision oncology knowledge base of cancer genes, variants, and therapeutic implications.", + "tags": [ + "genome" + ], + "tasks": [], + "modalities": [ + "Genomics" + ], + "organism": [], + "api": false + }, { "id": "open_targets_platform", "name": "Open Targets Platform", @@ -2383,10 +2588,18 @@ validated: false ], "tasks": [], "modalities": [ - "Protein" + "protein-sequence" ], "organism": [], - "api": false + "api": false, + "entities": [ + "protein" + ], + "documentation": "https://www.uniprot.org/", + "last_checked": "2026-08-08", + "metadata_sources": [ + "https://www.uniprot.org/" + ] }, { "id": "uniref", @@ -3995,7 +4208,7 @@ validated: false "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.", + "description": "Mosaic integration and differential accessibility model for single-cell multi-omics that handles arbitrary missing-modality combinations across transcriptomics, chromatin accessibility, and proteomics.", "tags": [ "foundation-models", "multi-omics-foundation-models", @@ -4266,6 +4479,24 @@ validated: false "organism": [], "api": false }, + { + "id": "nbbayeslm", + "name": "NbBayesLM", + "type": "model", + "url": "https://github.com/FairuzShadmaniShishir/NbBayesLM", + "description": "Bayesian neural network integrating protein language model embeddings and physicochemical features to predict nanobody thermostability with uncertainty estimates. [Paper](https://www.frontiersin.org/journals/bioinformatics/articles/10.3389/fbinf.2026.1832968/full)", + "tags": [ + "protein-property-prediction" + ], + "tasks": [ + "Protein Property Prediction" + ], + "modalities": [ + "Protein" + ], + "organism": [], + "api": false + }, { "id": "neodti", "name": "NeoDTI", @@ -5444,9 +5675,23 @@ validated: false "tasks": [ "Preprocessing" ], - "modalities": [], + "modalities": [ + "dna-sequence", + "protein-sequence" + ], "organism": [], - "api": false + "api": false, + "entities": [ + "gene", + "protein" + ], + "github": "https://github.com/biopython/biopython", + "documentation": "https://biopython.org/wiki/Documentation", + "last_checked": "2026-08-08", + "metadata_sources": [ + "https://github.com/biopython/biopython", + "https://biopython.org/" + ] }, { "id": "casper", @@ -5476,9 +5721,22 @@ validated: false "tasks": [ "Preprocessing" ], - "modalities": [], + "modalities": [ + "spatial-transcriptomics" + ], "organism": [], - "api": false + "api": false, + "entities": [ + "cell", + "tissue" + ], + "github": "https://github.com/CSOgroup/cellcharter", + "documentation": "https://cellcharter.readthedocs.io/", + "last_checked": "2026-08-08", + "metadata_sources": [ + "https://github.com/CSOgroup/cellcharter", + "https://cellcharter.readthedocs.io/" + ] }, { "id": "cellchat", @@ -5492,9 +5750,20 @@ validated: false "tasks": [ "Preprocessing" ], - "modalities": [], + "modalities": [ + "single-cell-rna-seq" + ], "organism": [], - "api": false + "api": false, + "entities": [ + "cell", + "gene" + ], + "github": "https://github.com/sqjin/CellChat", + "last_checked": "2026-08-08", + "metadata_sources": [ + "https://github.com/sqjin/CellChat" + ] }, { "id": "celltypist", @@ -5506,11 +5775,24 @@ validated: false "preprocessing-tools" ], "tasks": [ - "Preprocessing" + "cell-type-annotation" + ], + "modalities": [ + "single-cell-rna-seq" ], - "modalities": [], "organism": [], - "api": false + "api": false, + "entities": [ + "cell", + "gene" + ], + "github": "https://github.com/Teichlab/celltypist", + "documentation": "https://celltypist.readthedocs.io/", + "last_checked": "2026-08-08", + "metadata_sources": [ + "https://github.com/Teichlab/celltypist", + "https://celltypist.readthedocs.io/" + ] }, { "id": "chatspatial", @@ -5572,16 +5854,30 @@ validated: false "tasks": [ "Preprocessing" ], - "modalities": [], + "modalities": [ + "chemical-structure", + "molecular-structure" + ], "organism": [], - "api": false + "api": false, + "entities": [ + "molecule", + "protein" + ], + "github": "https://github.com/deepchem/deepchem", + "documentation": "https://deepchem.readthedocs.io/", + "last_checked": "2026-08-08", + "metadata_sources": [ + "https://github.com/deepchem/deepchem", + "https://deepchem.readthedocs.io/" + ] }, { "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.", + "description": "Graph attention network for deciphering cell-cell communication from spatial transcriptomics.", "tags": [ "preprocessing-tools" ], @@ -5796,9 +6092,21 @@ validated: false "tasks": [ "Preprocessing" ], - "modalities": [], + "modalities": [ + "chemical-structure" + ], "organism": [], - "api": false + "api": false, + "entities": [ + "molecule" + ], + "github": "https://github.com/rdkit/rdkit", + "documentation": "https://www.rdkit.org/docs/", + "last_checked": "2026-08-08", + "metadata_sources": [ + "https://github.com/rdkit/rdkit", + "https://www.rdkit.org/docs/" + ] }, { "id": "scanpy", @@ -5812,9 +6120,22 @@ validated: false "tasks": [ "Preprocessing" ], - "modalities": [], + "modalities": [ + "single-cell-rna-seq" + ], "organism": [], - "api": false + "api": false, + "entities": [ + "cell", + "gene" + ], + "github": "https://github.com/scverse/scanpy", + "documentation": "https://scanpy.readthedocs.io/en/stable/", + "last_checked": "2026-08-08", + "metadata_sources": [ + "https://github.com/scverse/scanpy", + "https://scanpy.readthedocs.io/en/stable/" + ] }, { "id": "scenic", @@ -5876,9 +6197,23 @@ validated: false "tasks": [ "Preprocessing" ], - "modalities": [], + "modalities": [ + "single-cell-rna-seq", + "multi-omics" + ], "organism": [], - "api": false + "api": false, + "entities": [ + "cell", + "gene" + ], + "github": "https://github.com/scverse/scvi-tools", + "documentation": "https://docs.scvi-tools.org/", + "last_checked": "2026-08-08", + "metadata_sources": [ + "https://github.com/scverse/scvi-tools", + "https://docs.scvi-tools.org/" + ] }, { "id": "seqbench", @@ -5908,9 +6243,22 @@ validated: false "tasks": [ "Preprocessing" ], - "modalities": [], + "modalities": [ + "single-cell-rna-seq" + ], "organism": [], - "api": false + "api": false, + "entities": [ + "cell", + "gene" + ], + "github": "https://github.com/satijalab/seurat", + "documentation": "https://satijalab.org/seurat/", + "last_checked": "2026-08-08", + "metadata_sources": [ + "https://github.com/satijalab/seurat", + "https://satijalab.org/seurat/" + ] }, { "id": "squidpy", @@ -5924,9 +6272,22 @@ validated: false "tasks": [ "Preprocessing" ], - "modalities": [], + "modalities": [ + "spatial-transcriptomics" + ], "organism": [], - "api": false + "api": false, + "entities": [ + "cell", + "tissue" + ], + "github": "https://github.com/scverse/squidpy", + "documentation": "https://squidpy.readthedocs.io/", + "last_checked": "2026-08-08", + "metadata_sources": [ + "https://github.com/scverse/squidpy", + "https://squidpy.readthedocs.io/" + ] }, { "id": "stagate", -- 2.54.0 From f6429c2ab170910c0d780e35aeff7cdb27b6b887 Mon Sep 17 00:00:00 2001 From: promptadmin Date: Mon, 31 Aug 2026 23:14:20 +0000 Subject: [PATCH 4/5] [upstream-sync] data/resources.yml from inoue0426/awesome-computational-biology@c6f07d90 [catalogue] --- .../catalogue/data/resources.yml | 32 ++++++++++++++++--- 1 file changed, 27 insertions(+), 5 deletions(-) diff --git a/upstream/inoue0426-awesome-computational-biology/catalogue/data/resources.yml b/upstream/inoue0426-awesome-computational-biology/catalogue/data/resources.yml index 98e1aac..bfcb7c7 100644 --- a/upstream/inoue0426-awesome-computational-biology/catalogue/data/resources.yml +++ b/upstream/inoue0426-awesome-computational-biology/catalogue/data/resources.yml @@ -2,9 +2,9 @@ title: "Awesome Computational Biology - machine-readable resource list" task: "" lineage_type: import -upstream_source: https://github.com/inoue0426/awesome-computational-biology/blob/7a064bf0/data/resources.yml -upstream_sha: 7a064bf0 -imported_at: 2026-08-08 +upstream_source: https://github.com/inoue0426/awesome-computational-biology/blob/c6f07d90/data/resources.yml +upstream_sha: c6f07d90 +imported_at: 2026-08-31 prompt_class: catalogue upstream_changes: accepted author: upstream @@ -1183,6 +1183,17 @@ resources: organism: [] api: false + - id: oncokb + name: "OncoKB" + type: database + url: https://www.oncokb.org/ + description: "Precision oncology knowledge base of cancer genes, variants, and therapeutic implications." + tags: [genome] + tasks: [] + modalities: [Genomics] + organism: [] + api: false + - id: open_targets_platform name: "Open Targets Platform" type: database @@ -2243,7 +2254,7 @@ resources: 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." + description: "Mosaic integration and differential accessibility model for single-cell multi-omics 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] @@ -2382,6 +2393,17 @@ resources: organism: [] api: false + - id: nbbayeslm + name: "NbBayesLM" + type: model + url: https://github.com/FairuzShadmaniShishir/NbBayesLM + description: "Bayesian neural network integrating protein language model embeddings and physicochemical features to predict nanobody thermostability with uncertainty estimates. [Paper](https://www.frontiersin.org/journals/bioinformatics/articles/10.3389/fbinf.2026.1832968/full)" + tags: [protein-property-prediction] + tasks: [Protein Property Prediction] + modalities: [Protein] + organism: [] + api: false + - id: neodti name: "NeoDTI" type: model @@ -2980,7 +3002,7 @@ resources: name: "DeepTalk" type: toolkit url: https://github.com/JiangBioLab/DeepTalk - description: "Graph attention network for deciphering cell-cell communication from spatial transcriptomics data." + description: "Graph attention network for deciphering cell-cell communication from spatial transcriptomics." tags: [preprocessing-tools] tasks: [Preprocessing] modalities: [] -- 2.54.0 From 3ff519483899afb2674c54fed5276951bc14549c Mon Sep 17 00:00:00 2001 From: promptadmin Date: Mon, 31 Aug 2026 23:14:22 +0000 Subject: [PATCH 5/5] [upstream-sync] docs/data/resources.json from inoue0426/awesome-computational-biology@c6f07d90 [catalogue] --- .../catalogue/docs/data/resources.json | 499 +++++++++++++++--- 1 file changed, 430 insertions(+), 69 deletions(-) diff --git a/upstream/inoue0426-awesome-computational-biology/catalogue/docs/data/resources.json b/upstream/inoue0426-awesome-computational-biology/catalogue/docs/data/resources.json index adc957c..f47086f 100644 --- a/upstream/inoue0426-awesome-computational-biology/catalogue/docs/data/resources.json +++ b/upstream/inoue0426-awesome-computational-biology/catalogue/docs/data/resources.json @@ -2,9 +2,9 @@ title: "Resources" task: "" lineage_type: import -upstream_source: https://github.com/inoue0426/awesome-computational-biology/blob/7a064bf0/docs/data/resources.json -upstream_sha: 7a064bf0 -imported_at: 2026-08-08 +upstream_source: https://github.com/inoue0426/awesome-computational-biology/blob/c6f07d90/docs/data/resources.json +upstream_sha: c6f07d90 +imported_at: 2026-08-31 prompt_class: catalogue upstream_changes: accepted author: upstream @@ -899,10 +899,20 @@ validated: false ], "tasks": [], "modalities": [ - "Genomics" + "single-cell-rna-seq", + "genomics" ], "organism": [], - "api": false + "api": false, + "entities": [ + "cell", + "gene" + ], + "documentation": "https://www.10xgenomics.com/resources/datasets", + "last_checked": "2026-08-08", + "metadata_sources": [ + "https://www.10xgenomics.com/resources/datasets" + ] }, { "id": "alphafold_protein_structure_database", @@ -915,10 +925,20 @@ validated: false ], "tasks": [], "modalities": [ - "Protein" + "molecular-structure", + "protein-sequence" ], "organism": [], - "api": false + "api": false, + "entities": [ + "protein" + ], + "documentation": "https://alphafold.ebi.ac.uk/api-docs", + "last_checked": "2026-08-08", + "metadata_sources": [ + "https://alphafold.ebi.ac.uk/", + "https://alphafold.ebi.ac.uk/api-docs" + ] }, { "id": "bindingdb", @@ -932,11 +952,20 @@ validated: false ], "tasks": [], "modalities": [ - "Protein", - "Small Molecule" + "chemical-structure", + "molecular-structure" ], "organism": [], - "api": false + "api": false, + "entities": [ + "molecule", + "protein" + ], + "documentation": "https://www.bindingdb.org/rwd/bind/index.jsp", + "last_checked": "2026-08-08", + "metadata_sources": [ + "https://www.bindingdb.org/rwd/bind/index.jsp" + ] }, { "id": "biocyc", @@ -949,10 +978,20 @@ validated: false ], "tasks": [], "modalities": [ - "Pathway" + "genomics" ], "organism": [], - "api": false + "api": false, + "entities": [ + "gene", + "pathway", + "organism" + ], + "documentation": "https://biocyc.org/", + "last_checked": "2026-08-08", + "metadata_sources": [ + "https://biocyc.org/" + ] }, { "id": "biogrid", @@ -969,7 +1008,16 @@ validated: false "Protein" ], "organism": [], - "api": false + "api": false, + "entities": [ + "gene", + "protein" + ], + "documentation": "https://thebiogrid.org/", + "last_checked": "2026-08-08", + "metadata_sources": [ + "https://thebiogrid.org/" + ] }, { "id": "cancer_cell_line_encyclopedia", @@ -983,11 +1031,22 @@ validated: false ], "tasks": [], "modalities": [ - "Gene Expression", - "Small Molecule" + "genomics", + "transcriptomics" ], "organism": [], - "api": false + "api": false, + "entities": [ + "cell", + "gene", + "disease", + "drug" + ], + "documentation": "https://sites.broadinstitute.org/ccle/", + "last_checked": "2026-08-08", + "metadata_sources": [ + "https://sites.broadinstitute.org/ccle/" + ] }, { "id": "catalogue_of_somatic_mutations_in_cancer_cosmic", @@ -1000,10 +1059,20 @@ validated: false ], "tasks": [], "modalities": [ - "Genomics" + "genomics" ], "organism": [], - "api": false + "api": false, + "entities": [ + "disease", + "gene", + "variant" + ], + "documentation": "https://cancer.sanger.ac.uk/cosmic", + "last_checked": "2026-08-08", + "metadata_sources": [ + "https://cancer.sanger.ac.uk/cosmic" + ] }, { "id": "cath_database", @@ -1016,10 +1085,19 @@ validated: false ], "tasks": [], "modalities": [ - "Protein" + "molecular-structure", + "protein-sequence" ], "organism": [], - "api": false + "api": false, + "entities": [ + "protein" + ], + "documentation": "https://www.cathdb.info/", + "last_checked": "2026-08-08", + "metadata_sources": [ + "https://www.cathdb.info/" + ] }, { "id": "cbioportal", @@ -1032,10 +1110,23 @@ validated: false ], "tasks": [], "modalities": [ - "Genomics" + "genomics", + "clinical" ], "organism": [], - "api": false + "api": false, + "entities": [ + "disease", + "gene", + "variant" + ], + "github": "https://github.com/cBioPortal/cbioportal", + "documentation": "https://www.cbioportal.org/", + "last_checked": "2026-08-08", + "metadata_sources": [ + "https://www.cbioportal.org/", + "https://github.com/cBioPortal/cbioportal" + ] }, { "id": "cellminer_cross_database_cellminercdb", @@ -1092,10 +1183,20 @@ validated: false ], "tasks": [], "modalities": [ - "Small Molecule" + "chemical-structure" ], "organism": [], - "api": false + "api": false, + "entities": [ + "compound", + "molecule", + "protein" + ], + "documentation": "https://www.ebi.ac.uk/chembl/", + "last_checked": "2026-08-08", + "metadata_sources": [ + "https://www.ebi.ac.uk/chembl/" + ] }, { "id": "chemspider", @@ -1124,10 +1225,19 @@ validated: false ], "tasks": [], "modalities": [ - "Clinical" + "clinical" ], "organism": [], - "api": false + "api": false, + "entities": [ + "disease", + "drug" + ], + "documentation": "https://clinicaltrials.gov/", + "last_checked": "2026-08-08", + "metadata_sources": [ + "https://clinicaltrials.gov/" + ] }, { "id": "comparative_toxicogenomics_database", @@ -1141,11 +1251,20 @@ validated: false ], "tasks": [], "modalities": [ - "Gene", - "Small Molecule" + "knowledge-graph" ], "organism": [], - "api": false + "api": false, + "entities": [ + "compound", + "gene", + "disease" + ], + "documentation": "https://ctdbase.org/", + "last_checked": "2026-08-08", + "metadata_sources": [ + "https://ctdbase.org/" + ] }, { "id": "critical_assessment_of_structure_prediction_casp", @@ -1174,10 +1293,21 @@ validated: false ], "tasks": [], "modalities": [ - "Single Cell" + "single-cell-rna-seq", + "transcriptomics" ], "organism": [], - "api": false + "api": false, + "entities": [ + "cell", + "gene", + "tissue" + ], + "documentation": "https://cellxgene.cziscience.com/", + "last_checked": "2026-08-08", + "metadata_sources": [ + "https://cellxgene.cziscience.com/" + ] }, { "id": "davis_kinase_inhibitors_db", @@ -1208,10 +1338,21 @@ validated: false ], "tasks": [], "modalities": [ - "Genomics" + "genomics" ], "organism": [], - "api": false + "api": false, + "entities": [ + "cell", + "gene", + "disease", + "drug" + ], + "documentation": "https://depmap.org/portal/", + "last_checked": "2026-08-08", + "metadata_sources": [ + "https://depmap.org/portal/" + ] }, { "id": "dgidb", @@ -1225,11 +1366,19 @@ validated: false ], "tasks": [], "modalities": [ - "Gene", - "Small Molecule" + "knowledge-graph" ], "organism": [], - "api": false + "api": false, + "entities": [ + "drug", + "gene" + ], + "documentation": "https://www.dgidb.org/", + "last_checked": "2026-08-08", + "metadata_sources": [ + "https://www.dgidb.org/" + ] }, { "id": "diseases", @@ -1292,10 +1441,21 @@ validated: false ], "tasks": [], "modalities": [ - "Knowledge Graph" + "knowledge-graph" ], "organism": [], - "api": false + "api": false, + "entities": [ + "drug", + "disease", + "gene", + "pathway" + ], + "github": "https://github.com/SuLab/DrugMechDB", + "last_checked": "2026-08-08", + "metadata_sources": [ + "https://github.com/SuLab/DrugMechDB" + ] }, { "id": "drug_repurposing_hub", @@ -1308,10 +1468,20 @@ validated: false ], "tasks": [], "modalities": [ - "Small Molecule" + "chemical-structure" ], "organism": [], - "api": false + "api": false, + "entities": [ + "drug", + "protein", + "disease" + ], + "documentation": "https://repo-hub.broadinstitute.org/repurposing", + "last_checked": "2026-08-08", + "metadata_sources": [ + "https://repo-hub.broadinstitute.org/repurposing" + ] }, { "id": "drugbank", @@ -1349,10 +1519,20 @@ validated: false ], "tasks": [], "modalities": [ - "Small Molecule" + "chemical-structure" ], "organism": [], - "api": false + "api": false, + "entities": [ + "drug", + "protein", + "disease" + ], + "documentation": "https://drugcentral.org/", + "last_checked": "2026-08-08", + "metadata_sources": [ + "https://drugcentral.org/" + ] }, { "id": "drugtargetcommons", @@ -1365,10 +1545,19 @@ validated: false ], "tasks": [], "modalities": [ - "Small Molecule" + "chemical-structure" ], "organism": [], - "api": false + "api": false, + "entities": [ + "drug", + "protein" + ], + "documentation": "https://drugtargetcommons.fimm.fi/", + "last_checked": "2026-08-08", + "metadata_sources": [ + "https://drugtargetcommons.fimm.fi/" + ] }, { "id": "encode", @@ -1936,6 +2125,22 @@ validated: false "organism": [], "api": false }, + { + "id": "oncokb", + "name": "OncoKB", + "type": "database", + "url": "https://www.oncokb.org/", + "description": "Precision oncology knowledge base of cancer genes, variants, and therapeutic implications.", + "tags": [ + "genome" + ], + "tasks": [], + "modalities": [ + "Genomics" + ], + "organism": [], + "api": false + }, { "id": "open_targets_platform", "name": "Open Targets Platform", @@ -2383,10 +2588,18 @@ validated: false ], "tasks": [], "modalities": [ - "Protein" + "protein-sequence" ], "organism": [], - "api": false + "api": false, + "entities": [ + "protein" + ], + "documentation": "https://www.uniprot.org/", + "last_checked": "2026-08-08", + "metadata_sources": [ + "https://www.uniprot.org/" + ] }, { "id": "uniref", @@ -3995,7 +4208,7 @@ validated: false "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.", + "description": "Mosaic integration and differential accessibility model for single-cell multi-omics that handles arbitrary missing-modality combinations across transcriptomics, chromatin accessibility, and proteomics.", "tags": [ "foundation-models", "multi-omics-foundation-models", @@ -4266,6 +4479,24 @@ validated: false "organism": [], "api": false }, + { + "id": "nbbayeslm", + "name": "NbBayesLM", + "type": "model", + "url": "https://github.com/FairuzShadmaniShishir/NbBayesLM", + "description": "Bayesian neural network integrating protein language model embeddings and physicochemical features to predict nanobody thermostability with uncertainty estimates. [Paper](https://www.frontiersin.org/journals/bioinformatics/articles/10.3389/fbinf.2026.1832968/full)", + "tags": [ + "protein-property-prediction" + ], + "tasks": [ + "Protein Property Prediction" + ], + "modalities": [ + "Protein" + ], + "organism": [], + "api": false + }, { "id": "neodti", "name": "NeoDTI", @@ -5444,9 +5675,23 @@ validated: false "tasks": [ "Preprocessing" ], - "modalities": [], + "modalities": [ + "dna-sequence", + "protein-sequence" + ], "organism": [], - "api": false + "api": false, + "entities": [ + "gene", + "protein" + ], + "github": "https://github.com/biopython/biopython", + "documentation": "https://biopython.org/wiki/Documentation", + "last_checked": "2026-08-08", + "metadata_sources": [ + "https://github.com/biopython/biopython", + "https://biopython.org/" + ] }, { "id": "casper", @@ -5476,9 +5721,22 @@ validated: false "tasks": [ "Preprocessing" ], - "modalities": [], + "modalities": [ + "spatial-transcriptomics" + ], "organism": [], - "api": false + "api": false, + "entities": [ + "cell", + "tissue" + ], + "github": "https://github.com/CSOgroup/cellcharter", + "documentation": "https://cellcharter.readthedocs.io/", + "last_checked": "2026-08-08", + "metadata_sources": [ + "https://github.com/CSOgroup/cellcharter", + "https://cellcharter.readthedocs.io/" + ] }, { "id": "cellchat", @@ -5492,9 +5750,20 @@ validated: false "tasks": [ "Preprocessing" ], - "modalities": [], + "modalities": [ + "single-cell-rna-seq" + ], "organism": [], - "api": false + "api": false, + "entities": [ + "cell", + "gene" + ], + "github": "https://github.com/sqjin/CellChat", + "last_checked": "2026-08-08", + "metadata_sources": [ + "https://github.com/sqjin/CellChat" + ] }, { "id": "celltypist", @@ -5506,11 +5775,24 @@ validated: false "preprocessing-tools" ], "tasks": [ - "Preprocessing" + "cell-type-annotation" + ], + "modalities": [ + "single-cell-rna-seq" ], - "modalities": [], "organism": [], - "api": false + "api": false, + "entities": [ + "cell", + "gene" + ], + "github": "https://github.com/Teichlab/celltypist", + "documentation": "https://celltypist.readthedocs.io/", + "last_checked": "2026-08-08", + "metadata_sources": [ + "https://github.com/Teichlab/celltypist", + "https://celltypist.readthedocs.io/" + ] }, { "id": "chatspatial", @@ -5572,16 +5854,30 @@ validated: false "tasks": [ "Preprocessing" ], - "modalities": [], + "modalities": [ + "chemical-structure", + "molecular-structure" + ], "organism": [], - "api": false + "api": false, + "entities": [ + "molecule", + "protein" + ], + "github": "https://github.com/deepchem/deepchem", + "documentation": "https://deepchem.readthedocs.io/", + "last_checked": "2026-08-08", + "metadata_sources": [ + "https://github.com/deepchem/deepchem", + "https://deepchem.readthedocs.io/" + ] }, { "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.", + "description": "Graph attention network for deciphering cell-cell communication from spatial transcriptomics.", "tags": [ "preprocessing-tools" ], @@ -5796,9 +6092,21 @@ validated: false "tasks": [ "Preprocessing" ], - "modalities": [], + "modalities": [ + "chemical-structure" + ], "organism": [], - "api": false + "api": false, + "entities": [ + "molecule" + ], + "github": "https://github.com/rdkit/rdkit", + "documentation": "https://www.rdkit.org/docs/", + "last_checked": "2026-08-08", + "metadata_sources": [ + "https://github.com/rdkit/rdkit", + "https://www.rdkit.org/docs/" + ] }, { "id": "scanpy", @@ -5812,9 +6120,22 @@ validated: false "tasks": [ "Preprocessing" ], - "modalities": [], + "modalities": [ + "single-cell-rna-seq" + ], "organism": [], - "api": false + "api": false, + "entities": [ + "cell", + "gene" + ], + "github": "https://github.com/scverse/scanpy", + "documentation": "https://scanpy.readthedocs.io/en/stable/", + "last_checked": "2026-08-08", + "metadata_sources": [ + "https://github.com/scverse/scanpy", + "https://scanpy.readthedocs.io/en/stable/" + ] }, { "id": "scenic", @@ -5876,9 +6197,23 @@ validated: false "tasks": [ "Preprocessing" ], - "modalities": [], + "modalities": [ + "single-cell-rna-seq", + "multi-omics" + ], "organism": [], - "api": false + "api": false, + "entities": [ + "cell", + "gene" + ], + "github": "https://github.com/scverse/scvi-tools", + "documentation": "https://docs.scvi-tools.org/", + "last_checked": "2026-08-08", + "metadata_sources": [ + "https://github.com/scverse/scvi-tools", + "https://docs.scvi-tools.org/" + ] }, { "id": "seqbench", @@ -5908,9 +6243,22 @@ validated: false "tasks": [ "Preprocessing" ], - "modalities": [], + "modalities": [ + "single-cell-rna-seq" + ], "organism": [], - "api": false + "api": false, + "entities": [ + "cell", + "gene" + ], + "github": "https://github.com/satijalab/seurat", + "documentation": "https://satijalab.org/seurat/", + "last_checked": "2026-08-08", + "metadata_sources": [ + "https://github.com/satijalab/seurat", + "https://satijalab.org/seurat/" + ] }, { "id": "squidpy", @@ -5924,9 +6272,22 @@ validated: false "tasks": [ "Preprocessing" ], - "modalities": [], + "modalities": [ + "spatial-transcriptomics" + ], "organism": [], - "api": false + "api": false, + "entities": [ + "cell", + "tissue" + ], + "github": "https://github.com/scverse/squidpy", + "documentation": "https://squidpy.readthedocs.io/", + "last_checked": "2026-08-08", + "metadata_sources": [ + "https://github.com/scverse/squidpy", + "https://squidpy.readthedocs.io/" + ] }, { "id": "stagate", -- 2.54.0