[Upstream sync] inoue0426/awesome-computational-biology (github) — 17 added, 6 modified #67
upstream/inoue0426-awesome-computational-biology/catalogue/.github/workflows/ai4bio-schema-check.yml
Vendored
+61
@@ -0,0 +1,61 @@
|
|||||||
|
---
|
||||||
|
title: "Ai4Bio Schema Check"
|
||||||
|
task: ""
|
||||||
|
lineage_type: import
|
||||||
|
upstream_source: https://github.com/inoue0426/awesome-computational-biology/blob/7a064bf0/.github/workflows/ai4bio-schema-check.yml
|
||||||
|
upstream_sha: 7a064bf0
|
||||||
|
imported_at: 2026-08-08
|
||||||
|
prompt_class: unknown
|
||||||
|
upstream_changes: accepted
|
||||||
|
author: upstream
|
||||||
|
validated: false
|
||||||
|
---
|
||||||
|
|
||||||
|
name: AI4Bio Schema Check
|
||||||
|
|
||||||
|
on:
|
||||||
|
pull_request:
|
||||||
|
paths:
|
||||||
|
- data/resources.yml
|
||||||
|
- data/enrichment.yml
|
||||||
|
- 'data/enrichment.*.yml'
|
||||||
|
- data/vocabulary.yml
|
||||||
|
- docs/data/resource.schema.json
|
||||||
|
- scripts/enrichment_fragments.py
|
||||||
|
- scripts/validate_resources.py
|
||||||
|
- scripts/build_resources_v2.py
|
||||||
|
push:
|
||||||
|
branches: [main]
|
||||||
|
paths:
|
||||||
|
- data/resources.yml
|
||||||
|
- data/enrichment.yml
|
||||||
|
- 'data/enrichment.*.yml'
|
||||||
|
- data/vocabulary.yml
|
||||||
|
- docs/data/resource.schema.json
|
||||||
|
- scripts/enrichment_fragments.py
|
||||||
|
- scripts/validate_resources.py
|
||||||
|
- scripts/build_resources_v2.py
|
||||||
|
|
||||||
|
permissions:
|
||||||
|
contents: read
|
||||||
|
|
||||||
|
jobs:
|
||||||
|
validate:
|
||||||
|
runs-on: ubuntu-latest
|
||||||
|
steps:
|
||||||
|
- uses: actions/checkout@v4
|
||||||
|
- uses: astral-sh/setup-uv@v3
|
||||||
|
- name: Validate schema and enrichment
|
||||||
|
run: uv run --with pyyaml python scripts/validate_resources.py
|
||||||
|
- name: Build enriched artifacts
|
||||||
|
run: uv run --with pyyaml python scripts/build_resources_v2.py
|
||||||
|
- name: Verify enriched artifacts are committed
|
||||||
|
run: |
|
||||||
|
if git diff --quiet; then
|
||||||
|
echo "AI4Bio artifacts are in sync."
|
||||||
|
exit 0
|
||||||
|
fi
|
||||||
|
echo "Generated AI4Bio artifacts are out of date. Run:"
|
||||||
|
echo " uv run --with pyyaml python scripts/build_resources_v2.py"
|
||||||
|
git status --short
|
||||||
|
exit 1
|
||||||
Vendored
+43
@@ -0,0 +1,43 @@
|
|||||||
|
---
|
||||||
|
title: "Landscape Ui Check"
|
||||||
|
task: ""
|
||||||
|
lineage_type: import
|
||||||
|
upstream_source: https://github.com/inoue0426/awesome-computational-biology/blob/7a064bf0/.github/workflows/landscape-ui-check.yml
|
||||||
|
upstream_sha: 7a064bf0
|
||||||
|
imported_at: 2026-08-08
|
||||||
|
prompt_class: unknown
|
||||||
|
upstream_changes: accepted
|
||||||
|
author: upstream
|
||||||
|
validated: false
|
||||||
|
---
|
||||||
|
|
||||||
|
name: Landscape UI Check
|
||||||
|
|
||||||
|
on:
|
||||||
|
pull_request:
|
||||||
|
paths:
|
||||||
|
- docs/landscape.html
|
||||||
|
- docs/landscape.css
|
||||||
|
- docs/landscape.js
|
||||||
|
- .github/workflows/landscape-ui-check.yml
|
||||||
|
push:
|
||||||
|
branches: [main]
|
||||||
|
paths:
|
||||||
|
- docs/landscape.html
|
||||||
|
- docs/landscape.css
|
||||||
|
- docs/landscape.js
|
||||||
|
- .github/workflows/landscape-ui-check.yml
|
||||||
|
|
||||||
|
permissions:
|
||||||
|
contents: read
|
||||||
|
|
||||||
|
jobs:
|
||||||
|
ui-check:
|
||||||
|
runs-on: ubuntu-latest
|
||||||
|
steps:
|
||||||
|
- uses: actions/checkout@v4
|
||||||
|
- uses: actions/setup-node@v4
|
||||||
|
with:
|
||||||
|
node-version: 'lts/*'
|
||||||
|
- name: Check landscape JavaScript syntax
|
||||||
|
run: node --check docs/landscape.js
|
||||||
Vendored
+9
-4
@@ -2,9 +2,9 @@
|
|||||||
title: "Sync Resources"
|
title: "Sync Resources"
|
||||||
task: ""
|
task: ""
|
||||||
lineage_type: import
|
lineage_type: import
|
||||||
upstream_source: https://github.com/inoue0426/awesome-computational-biology/blob/12d87583/.github/workflows/sync_resources.yml
|
upstream_source: https://github.com/inoue0426/awesome-computational-biology/blob/7a064bf0/.github/workflows/sync_resources.yml
|
||||||
upstream_sha: 12d87583
|
upstream_sha: 7a064bf0
|
||||||
imported_at: 2026-06-26
|
imported_at: 2026-08-08
|
||||||
prompt_class: unknown
|
prompt_class: unknown
|
||||||
upstream_changes: accepted
|
upstream_changes: accepted
|
||||||
author: upstream
|
author: upstream
|
||||||
@@ -20,6 +20,8 @@ on:
|
|||||||
paths:
|
paths:
|
||||||
- README.md
|
- README.md
|
||||||
- data/resources.yml
|
- data/resources.yml
|
||||||
|
- data/enrichment.yml
|
||||||
|
- 'data/enrichment.*.yml'
|
||||||
- scripts/*.py
|
- scripts/*.py
|
||||||
- scripts/**/*.py
|
- scripts/**/*.py
|
||||||
|
|
||||||
@@ -55,7 +57,10 @@ jobs:
|
|||||||
|
|
||||||
- name: Sync From README
|
- name: Sync From README
|
||||||
if: contains(steps.changes.outputs.changed, 'README.md')
|
if: contains(steps.changes.outputs.changed, 'README.md')
|
||||||
run: uv run python scripts/sync_resources_from_readme.py
|
run: uv run --with pyyaml python scripts/sync_resources_from_readme.py
|
||||||
|
|
||||||
|
- name: Validate Resource Schema
|
||||||
|
run: uv run --with pyyaml python scripts/validate_resources.py
|
||||||
|
|
||||||
- name: Build Artifacts
|
- name: Build Artifacts
|
||||||
run: uv run --with pyyaml python scripts/build_resources.py
|
run: uv run --with pyyaml python scripts/build_resources.py
|
||||||
|
|||||||
@@ -2,9 +2,9 @@
|
|||||||
title: "Awesome Computational Biology [](https://awesome.re)"
|
title: "Awesome Computational Biology [](https://awesome.re)"
|
||||||
task: ""
|
task: ""
|
||||||
lineage_type: import
|
lineage_type: import
|
||||||
upstream_source: https://github.com/inoue0426/awesome-computational-biology/blob/478be843/README.md
|
upstream_source: https://github.com/inoue0426/awesome-computational-biology/blob/7a064bf0/README.md
|
||||||
upstream_sha: 478be843
|
upstream_sha: 7a064bf0
|
||||||
imported_at: 2026-07-17
|
imported_at: 2026-08-08
|
||||||
prompt_class: catalogue
|
prompt_class: catalogue
|
||||||
upstream_changes: accepted
|
upstream_changes: accepted
|
||||||
author: upstream
|
author: upstream
|
||||||
@@ -70,6 +70,7 @@ Browse and search the resources via the [GitHub Pages UI](https://inoue0426.gith
|
|||||||
- [Machine Learning Tasks and Models](#machine-learning-tasks-and-models)
|
- [Machine Learning Tasks and Models](#machine-learning-tasks-and-models)
|
||||||
- [Drug Discovery](#drug-discovery)
|
- [Drug Discovery](#drug-discovery)
|
||||||
- [Drug Response Prediction](#drug-response-prediction)
|
- [Drug Response Prediction](#drug-response-prediction)
|
||||||
|
- [Drug Perturbation](#drug-perturbation)
|
||||||
- [Drug Repurposing](#drug-repurposing)
|
- [Drug Repurposing](#drug-repurposing)
|
||||||
- [Drug Target Interaction](#drug-target-interaction)
|
- [Drug Target Interaction](#drug-target-interaction)
|
||||||
- [Compound-Protein Interaction](#compound-protein-interaction)
|
- [Compound-Protein Interaction](#compound-protein-interaction)
|
||||||
@@ -340,10 +341,15 @@ Browse and search the resources via the [GitHub Pages UI](https://inoue0426.gith
|
|||||||
- [RECOVER](https://github.com/RECOVERcoalition/Recover) — Machine learning framework for predicting synergistic drug combination responses across cell lines.
|
- [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.
|
- [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.
|
- [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.
|
- [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 Perturbation
|
||||||
|
|
||||||
|
- [CellOT](https://github.com/bunnech/cellot) — Neural optimal transport framework for predicting single-cell responses to drug and genetic perturbations.
|
||||||
|
- [CMonge](https://github.com/AI4SCR/conditional-monge-gap) — Conditional optimal transport model for generalizable single-cell perturbation response prediction across drugs and doses.
|
||||||
- [chemCPA](https://github.com/theislab/chemCPA) — Compositional perturbation autoencoder for predicting single-cell transcriptional responses to unseen drug perturbations and dose combinations.
|
- [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.
|
- [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.
|
- [PRNet](https://github.com/Perturbation-Response-Prediction/PRnet) — Deep generative model for predicting transcriptional responses to novel chemical perturbations for drug discovery.
|
||||||
|
|
||||||
#### Drug Repurposing
|
#### Drug Repurposing
|
||||||
|
|
||||||
|
|||||||
@@ -2,9 +2,9 @@
|
|||||||
title: "Cspell"
|
title: "Cspell"
|
||||||
task: ""
|
task: ""
|
||||||
lineage_type: import
|
lineage_type: import
|
||||||
upstream_source: https://github.com/inoue0426/awesome-computational-biology/blob/12d87583/cspell.json
|
upstream_source: https://github.com/inoue0426/awesome-computational-biology/blob/7a064bf0/cspell.json
|
||||||
upstream_sha: 12d87583
|
upstream_sha: 7a064bf0
|
||||||
imported_at: 2026-06-26
|
imported_at: 2026-08-08
|
||||||
prompt_class: unknown
|
prompt_class: unknown
|
||||||
upstream_changes: accepted
|
upstream_changes: accepted
|
||||||
author: upstream
|
author: upstream
|
||||||
@@ -157,7 +157,21 @@ validated: false
|
|||||||
"Pacc",
|
"Pacc",
|
||||||
"multiomics",
|
"multiomics",
|
||||||
"Pathomic",
|
"Pathomic",
|
||||||
"PLIP"
|
"PLIP",
|
||||||
|
"Omni",
|
||||||
|
"Bento",
|
||||||
|
"FFPE",
|
||||||
|
"Xenium",
|
||||||
|
"Zyme",
|
||||||
|
"Neur",
|
||||||
|
"Imageomics",
|
||||||
|
"AESTETIK",
|
||||||
|
"CellOT",
|
||||||
|
"CMonge",
|
||||||
|
"bowang",
|
||||||
|
"ctheodoris",
|
||||||
|
"OpenAI",
|
||||||
|
"GPT"
|
||||||
],
|
],
|
||||||
"ignorePaths": [
|
"ignorePaths": [
|
||||||
"node_modules/**"
|
"node_modules/**"
|
||||||
|
|||||||
+56
@@ -0,0 +1,56 @@
|
|||||||
|
---
|
||||||
|
title: "Provenance-backed single-cell and biomedical benchmark enrichment batch."
|
||||||
|
task: ""
|
||||||
|
lineage_type: import
|
||||||
|
upstream_source: https://github.com/inoue0426/awesome-computational-biology/blob/7a064bf0/data/enrichment.benchmark-v2.yml
|
||||||
|
upstream_sha: 7a064bf0
|
||||||
|
imported_at: 2026-08-08
|
||||||
|
prompt_class: catalogue
|
||||||
|
upstream_changes: accepted
|
||||||
|
author: upstream
|
||||||
|
validated: false
|
||||||
|
---
|
||||||
|
|
||||||
|
# Provenance-backed single-cell and biomedical benchmark enrichment batch.
|
||||||
|
resources:
|
||||||
|
scmulan:
|
||||||
|
entities: [cell, gene]
|
||||||
|
methods: [language-model, transformer]
|
||||||
|
modalities: [epigenomics, multi-omics, proteomics, single-cell-rna-seq, transcriptomics]
|
||||||
|
tasks: [foundation-model-pretraining, representation-learning]
|
||||||
|
github: https://github.com/SuperBianC/scMulan
|
||||||
|
last_checked: 2026-08-08
|
||||||
|
metadata_sources:
|
||||||
|
- https://github.com/SuperBianC/scMulan
|
||||||
|
|
||||||
|
proteingym:
|
||||||
|
entities: [protein]
|
||||||
|
modalities: [protein-sequence]
|
||||||
|
tasks: [regression]
|
||||||
|
github: https://github.com/OATML-Markslab/ProteinGym
|
||||||
|
last_checked: 2026-08-08
|
||||||
|
metadata_sources:
|
||||||
|
- https://github.com/OATML-Markslab/ProteinGym
|
||||||
|
|
||||||
|
lincs_l1000:
|
||||||
|
entities: [cell, compound, gene]
|
||||||
|
modalities: [transcriptomics]
|
||||||
|
tasks: [perturbation-prediction]
|
||||||
|
last_checked: 2026-08-08
|
||||||
|
metadata_sources:
|
||||||
|
- https://lincsproject.org/LINCS/tools/workflows/find-the-best-place-to-obtain-the-lincs-l1000-data
|
||||||
|
|
||||||
|
prism:
|
||||||
|
entities: [cell, drug]
|
||||||
|
tasks: [drug-response-prediction]
|
||||||
|
last_checked: 2026-08-08
|
||||||
|
metadata_sources:
|
||||||
|
- https://depmap.org/portal/prism/
|
||||||
|
|
||||||
|
pharmgkb:
|
||||||
|
entities: [drug, gene, phenotype, variant]
|
||||||
|
modalities: [clinical, genomics]
|
||||||
|
tasks: [drug-response-prediction]
|
||||||
|
last_checked: 2026-08-08
|
||||||
|
metadata_sources:
|
||||||
|
- https://www.pharmgkb.org/
|
||||||
+91
@@ -0,0 +1,91 @@
|
|||||||
|
---
|
||||||
|
title: "Provenance-backed database and API enrichment batch."
|
||||||
|
task: ""
|
||||||
|
lineage_type: import
|
||||||
|
upstream_source: https://github.com/inoue0426/awesome-computational-biology/blob/7a064bf0/data/enrichment.database-api-v1.yml
|
||||||
|
upstream_sha: 7a064bf0
|
||||||
|
imported_at: 2026-08-08
|
||||||
|
prompt_class: catalogue
|
||||||
|
upstream_changes: accepted
|
||||||
|
author: upstream
|
||||||
|
validated: false
|
||||||
|
---
|
||||||
|
|
||||||
|
# Provenance-backed database and API enrichment batch.
|
||||||
|
resources:
|
||||||
|
chembl_web_services:
|
||||||
|
entities: [molecule, protein]
|
||||||
|
modalities: [chemical-structure]
|
||||||
|
documentation: https://www.ebi.ac.uk/chembl/api/data/docs
|
||||||
|
last_checked: 2026-08-08
|
||||||
|
metadata_sources:
|
||||||
|
- https://www.ebi.ac.uk/chembl/api/data/docs
|
||||||
|
|
||||||
|
clinicaltrials_gov_api:
|
||||||
|
entities: [disease, drug]
|
||||||
|
modalities: [clinical]
|
||||||
|
documentation: https://clinicaltrials.gov/data-api/api
|
||||||
|
last_checked: 2026-08-08
|
||||||
|
metadata_sources:
|
||||||
|
- https://clinicaltrials.gov/data-api/api
|
||||||
|
|
||||||
|
ensembl_rest_api:
|
||||||
|
entities: [gene, genome, transcript, variant]
|
||||||
|
modalities: [genomics]
|
||||||
|
documentation: https://rest.ensembl.org/
|
||||||
|
last_checked: 2026-08-08
|
||||||
|
metadata_sources:
|
||||||
|
- https://rest.ensembl.org/
|
||||||
|
|
||||||
|
kegg_rest_api:
|
||||||
|
entities: [compound, gene, pathway]
|
||||||
|
documentation: https://www.kegg.jp/kegg/rest/keggapi.html
|
||||||
|
last_checked: 2026-08-08
|
||||||
|
metadata_sources:
|
||||||
|
- https://www.kegg.jp/kegg/rest/keggapi.html
|
||||||
|
|
||||||
|
ncbi_e_utilities:
|
||||||
|
entities: [gene, genome, protein, transcript, variant]
|
||||||
|
modalities: [genomics, transcriptomics]
|
||||||
|
documentation: https://www.ncbi.nlm.nih.gov/books/NBK25501/
|
||||||
|
last_checked: 2026-08-08
|
||||||
|
metadata_sources:
|
||||||
|
- https://www.ncbi.nlm.nih.gov/books/NBK25501/
|
||||||
|
|
||||||
|
open_targets_platform_api:
|
||||||
|
entities: [disease, drug, gene, variant]
|
||||||
|
modalities: [genomics, knowledge-graph]
|
||||||
|
documentation: https://platform.opentargets.org/api
|
||||||
|
last_checked: 2026-08-08
|
||||||
|
metadata_sources:
|
||||||
|
- https://platform.opentargets.org/api
|
||||||
|
|
||||||
|
pubmed_e_utilities_esearch_efetch:
|
||||||
|
documentation: https://www.ncbi.nlm.nih.gov/books/NBK25501/
|
||||||
|
last_checked: 2026-08-08
|
||||||
|
metadata_sources:
|
||||||
|
- https://www.ncbi.nlm.nih.gov/books/NBK25501/
|
||||||
|
|
||||||
|
uniprot_rest_api:
|
||||||
|
entities: [protein]
|
||||||
|
modalities: [protein-sequence, proteomics]
|
||||||
|
documentation: https://www.uniprot.org/help/api
|
||||||
|
last_checked: 2026-08-08
|
||||||
|
metadata_sources:
|
||||||
|
- https://www.uniprot.org/help/api
|
||||||
|
|
||||||
|
drugbank:
|
||||||
|
entities: [disease, drug, protein]
|
||||||
|
modalities: [chemical-structure]
|
||||||
|
last_checked: 2026-08-08
|
||||||
|
metadata_sources:
|
||||||
|
- https://go.drugbank.com/
|
||||||
|
|
||||||
|
string:
|
||||||
|
entities: [protein]
|
||||||
|
modalities: [knowledge-graph, proteomics]
|
||||||
|
documentation: https://string-db.org/help/api/
|
||||||
|
last_checked: 2026-08-08
|
||||||
|
metadata_sources:
|
||||||
|
- https://string-db.org/
|
||||||
|
- https://string-db.org/help/api/
|
||||||
+73
@@ -0,0 +1,73 @@
|
|||||||
|
---
|
||||||
|
title: "Provenance-backed foundation model enrichment batch 2."
|
||||||
|
task: ""
|
||||||
|
lineage_type: import
|
||||||
|
upstream_source: https://github.com/inoue0426/awesome-computational-biology/blob/7a064bf0/data/enrichment.foundation-models-v2.yml
|
||||||
|
upstream_sha: 7a064bf0
|
||||||
|
imported_at: 2026-08-08
|
||||||
|
prompt_class: catalogue
|
||||||
|
upstream_changes: accepted
|
||||||
|
author: upstream
|
||||||
|
validated: false
|
||||||
|
---
|
||||||
|
|
||||||
|
# Provenance-backed foundation model enrichment batch 2.
|
||||||
|
resources:
|
||||||
|
nicheformer:
|
||||||
|
entities: [cell, gene, tissue]
|
||||||
|
methods: [self-supervised-learning, transformer]
|
||||||
|
modalities: [single-cell-rna-seq, spatial-transcriptomics, transcriptomics]
|
||||||
|
tasks: [foundation-model-pretraining, representation-learning]
|
||||||
|
year: 2024
|
||||||
|
github: https://github.com/theislab/nicheformer
|
||||||
|
paper: https://doi.org/10.1101/2024.04.15.589472
|
||||||
|
last_checked: 2026-08-08
|
||||||
|
metadata_sources:
|
||||||
|
- https://github.com/theislab/nicheformer
|
||||||
|
- https://doi.org/10.1101/2024.04.15.589472
|
||||||
|
|
||||||
|
genept:
|
||||||
|
entities: [cell, gene]
|
||||||
|
methods: [language-model]
|
||||||
|
modalities: [single-cell-rna-seq, transcriptomics]
|
||||||
|
tasks: [batch-correction, classification, representation-learning]
|
||||||
|
year: 2023
|
||||||
|
github: https://github.com/yiqunchen/GenePT
|
||||||
|
paper: https://www.biorxiv.org/content/10.1101/2023.10.16.562533v2
|
||||||
|
last_checked: 2026-08-08
|
||||||
|
metadata_sources:
|
||||||
|
- https://github.com/yiqunchen/GenePT
|
||||||
|
- https://www.biorxiv.org/content/10.1101/2023.10.16.562533v2
|
||||||
|
|
||||||
|
scgpt_spatial:
|
||||||
|
entities: [cell, gene, tissue]
|
||||||
|
methods: [generative-model, self-supervised-learning, transformer]
|
||||||
|
modalities: [multi-omics, single-cell-rna-seq, spatial-transcriptomics]
|
||||||
|
tasks: [foundation-model-pretraining, imputation, representation-learning]
|
||||||
|
year: 2025
|
||||||
|
github: https://github.com/bowang-lab/scGPT-spatial
|
||||||
|
paper: https://www.biorxiv.org/content/10.1101/2025.02.05.636714v1
|
||||||
|
last_checked: 2026-08-08
|
||||||
|
metadata_sources:
|
||||||
|
- https://github.com/bowang-lab/scGPT-spatial
|
||||||
|
- https://www.biorxiv.org/content/10.1101/2025.02.05.636714v1
|
||||||
|
|
||||||
|
scprint:
|
||||||
|
entities: [cell, gene]
|
||||||
|
methods: [self-supervised-learning, transformer]
|
||||||
|
modalities: [single-cell-rna-seq, transcriptomics]
|
||||||
|
tasks:
|
||||||
|
- batch-correction
|
||||||
|
- cell-type-annotation
|
||||||
|
- foundation-model-pretraining
|
||||||
|
- gene-regulatory-network-inference
|
||||||
|
- imputation
|
||||||
|
- representation-learning
|
||||||
|
year: 2025
|
||||||
|
github: https://github.com/cantinilab/scPRINT
|
||||||
|
documentation: https://www.jkobject.com/scPRINT/
|
||||||
|
paper: https://www.nature.com/articles/s41467-025-58699-1
|
||||||
|
last_checked: 2026-08-08
|
||||||
|
metadata_sources:
|
||||||
|
- https://github.com/cantinilab/scPRINT
|
||||||
|
- https://www.nature.com/articles/s41467-025-58699-1
|
||||||
+62
@@ -0,0 +1,62 @@
|
|||||||
|
---
|
||||||
|
title: "Provenance-backed molecular model and benchmark enrichment batch."
|
||||||
|
task: ""
|
||||||
|
lineage_type: import
|
||||||
|
upstream_source: https://github.com/inoue0426/awesome-computational-biology/blob/7a064bf0/data/enrichment.molecular-v2.yml
|
||||||
|
upstream_sha: 7a064bf0
|
||||||
|
imported_at: 2026-08-08
|
||||||
|
prompt_class: catalogue
|
||||||
|
upstream_changes: accepted
|
||||||
|
author: upstream
|
||||||
|
validated: false
|
||||||
|
---
|
||||||
|
|
||||||
|
# Provenance-backed molecular model and benchmark enrichment batch.
|
||||||
|
resources:
|
||||||
|
chemberta_2:
|
||||||
|
entities: [molecule]
|
||||||
|
methods: [language-model, self-supervised-learning, transformer]
|
||||||
|
modalities: [chemical-structure]
|
||||||
|
tasks: [representation-learning]
|
||||||
|
github: https://github.com/seyonechithrananda/bert-loves-chemistry
|
||||||
|
last_checked: 2026-08-08
|
||||||
|
metadata_sources:
|
||||||
|
- https://github.com/seyonechithrananda/bert-loves-chemistry
|
||||||
|
|
||||||
|
molformer:
|
||||||
|
entities: [molecule]
|
||||||
|
methods: [language-model, self-supervised-learning, transformer]
|
||||||
|
modalities: [chemical-structure]
|
||||||
|
tasks: [representation-learning]
|
||||||
|
github: https://github.com/IBM/molformer
|
||||||
|
last_checked: 2026-08-08
|
||||||
|
metadata_sources:
|
||||||
|
- https://github.com/IBM/molformer
|
||||||
|
|
||||||
|
grover:
|
||||||
|
entities: [molecule]
|
||||||
|
methods: [graph-neural-network, self-supervised-learning, transformer]
|
||||||
|
modalities: [chemical-structure]
|
||||||
|
tasks: [representation-learning]
|
||||||
|
github: https://github.com/tencent-ailab/grover
|
||||||
|
last_checked: 2026-08-08
|
||||||
|
metadata_sources:
|
||||||
|
- https://github.com/tencent-ailab/grover
|
||||||
|
|
||||||
|
moleculenet:
|
||||||
|
entities: [molecule]
|
||||||
|
modalities: [chemical-structure]
|
||||||
|
tasks: [classification, regression]
|
||||||
|
github: https://github.com/deepchem/moleculenet
|
||||||
|
last_checked: 2026-08-08
|
||||||
|
metadata_sources:
|
||||||
|
- https://github.com/deepchem/moleculenet
|
||||||
|
|
||||||
|
guacamol:
|
||||||
|
entities: [molecule]
|
||||||
|
modalities: [chemical-structure]
|
||||||
|
tasks: [molecular-generation]
|
||||||
|
github: https://github.com/BenevolentAI/guacamol
|
||||||
|
last_checked: 2026-08-08
|
||||||
|
metadata_sources:
|
||||||
|
- https://github.com/BenevolentAI/guacamol
|
||||||
+92
@@ -0,0 +1,92 @@
|
|||||||
|
---
|
||||||
|
title: "Provenance-backed drug-response and pharmacogenomics enrichment batch."
|
||||||
|
task: ""
|
||||||
|
lineage_type: import
|
||||||
|
upstream_source: https://github.com/inoue0426/awesome-computational-biology/blob/7a064bf0/data/enrichment.pharmacogenomics-v1.yml
|
||||||
|
upstream_sha: 7a064bf0
|
||||||
|
imported_at: 2026-08-08
|
||||||
|
prompt_class: catalogue
|
||||||
|
upstream_changes: accepted
|
||||||
|
author: upstream
|
||||||
|
validated: false
|
||||||
|
---
|
||||||
|
|
||||||
|
# Provenance-backed drug-response and pharmacogenomics enrichment batch.
|
||||||
|
resources:
|
||||||
|
beat_aml:
|
||||||
|
entities: [cell, disease, drug, gene]
|
||||||
|
modalities: [genomics]
|
||||||
|
tasks: [drug-response-prediction]
|
||||||
|
last_checked: 2026-08-08
|
||||||
|
metadata_sources:
|
||||||
|
- https://biodev.github.io/BeatAML2/
|
||||||
|
|
||||||
|
cancer_therapeutics_response_portal_ctrp:
|
||||||
|
entities: [cell, drug]
|
||||||
|
tasks: [drug-response-prediction]
|
||||||
|
last_checked: 2026-08-08
|
||||||
|
metadata_sources:
|
||||||
|
- https://portals.broadinstitute.org/ctrp/
|
||||||
|
|
||||||
|
bindingdb_curated_sets:
|
||||||
|
entities: [molecule, protein]
|
||||||
|
modalities: [chemical-structure]
|
||||||
|
tasks: [drug-target-interaction]
|
||||||
|
last_checked: 2026-08-08
|
||||||
|
metadata_sources:
|
||||||
|
- https://www.bindingdb.org/
|
||||||
|
|
||||||
|
bace:
|
||||||
|
entities: [molecule, protein]
|
||||||
|
modalities: [chemical-structure]
|
||||||
|
tasks: [classification, regression]
|
||||||
|
last_checked: 2026-08-08
|
||||||
|
metadata_sources:
|
||||||
|
- https://www.kaggle.com/datasets/gokturkkoch/bace
|
||||||
|
|
||||||
|
clintox:
|
||||||
|
entities: [drug]
|
||||||
|
modalities: [clinical]
|
||||||
|
tasks: [classification]
|
||||||
|
last_checked: 2026-08-08
|
||||||
|
metadata_sources:
|
||||||
|
- https://tdcommons.ai/single_pred_tasks/tox/#clintox
|
||||||
|
|
||||||
|
sider_side_effect_resource:
|
||||||
|
entities: [drug, phenotype]
|
||||||
|
modalities: [clinical]
|
||||||
|
last_checked: 2026-08-08
|
||||||
|
metadata_sources:
|
||||||
|
- http://sideeffects.embl.de/
|
||||||
|
|
||||||
|
pk_db:
|
||||||
|
entities: [drug]
|
||||||
|
modalities: [clinical]
|
||||||
|
last_checked: 2026-08-08
|
||||||
|
metadata_sources:
|
||||||
|
- https://pk-db.com/
|
||||||
|
|
||||||
|
scperturb:
|
||||||
|
entities: [cell, drug, gene]
|
||||||
|
modalities: [single-cell-rna-seq]
|
||||||
|
tasks: [perturbation-prediction]
|
||||||
|
github: https://github.com/sanderlab/scPerturb
|
||||||
|
last_checked: 2026-08-08
|
||||||
|
metadata_sources:
|
||||||
|
- https://github.com/sanderlab/scPerturb
|
||||||
|
|
||||||
|
genomics_of_drug_sensitivity_in_cancer_gdsc:
|
||||||
|
entities: [cell, drug, gene]
|
||||||
|
modalities: [genomics]
|
||||||
|
tasks: [drug-response-prediction]
|
||||||
|
last_checked: 2026-08-08
|
||||||
|
metadata_sources:
|
||||||
|
- https://www.cancerrxgene.org/
|
||||||
|
|
||||||
|
cellminer_cross_database_cellminercdb:
|
||||||
|
entities: [cell, drug, gene]
|
||||||
|
modalities: [genomics]
|
||||||
|
tasks: [drug-response-prediction]
|
||||||
|
last_checked: 2026-08-08
|
||||||
|
metadata_sources:
|
||||||
|
- https://discover.nci.nih.gov/cellminercdb/
|
||||||
+62
@@ -0,0 +1,62 @@
|
|||||||
|
---
|
||||||
|
title: "Provenance-backed protein and drug-discovery enrichment batch."
|
||||||
|
task: ""
|
||||||
|
lineage_type: import
|
||||||
|
upstream_source: https://github.com/inoue0426/awesome-computational-biology/blob/7a064bf0/data/enrichment.protein-drug-v1.yml
|
||||||
|
upstream_sha: 7a064bf0
|
||||||
|
imported_at: 2026-08-08
|
||||||
|
prompt_class: catalogue
|
||||||
|
upstream_changes: accepted
|
||||||
|
author: upstream
|
||||||
|
validated: false
|
||||||
|
---
|
||||||
|
|
||||||
|
# Provenance-backed protein and drug-discovery enrichment batch.
|
||||||
|
resources:
|
||||||
|
esmfold:
|
||||||
|
entities: [protein]
|
||||||
|
methods: [language-model, transformer]
|
||||||
|
modalities: [molecular-structure, protein-sequence]
|
||||||
|
tasks: [representation-learning, structure-prediction]
|
||||||
|
year: 2023
|
||||||
|
github: https://github.com/facebookresearch/esm
|
||||||
|
last_checked: 2026-08-08
|
||||||
|
metadata_sources:
|
||||||
|
- https://github.com/facebookresearch/esm
|
||||||
|
|
||||||
|
proteinmpnn:
|
||||||
|
entities: [protein]
|
||||||
|
methods: [graph-neural-network, message-passing-neural-network]
|
||||||
|
modalities: [molecular-structure, protein-sequence]
|
||||||
|
tasks: [protein-sequence-design]
|
||||||
|
year: 2022
|
||||||
|
github: https://github.com/dauparas/ProteinMPNN
|
||||||
|
last_checked: 2026-08-08
|
||||||
|
metadata_sources:
|
||||||
|
- https://github.com/dauparas/ProteinMPNN
|
||||||
|
|
||||||
|
diffdock:
|
||||||
|
entities: [molecule, protein]
|
||||||
|
methods: [diffusion, geometric-deep-learning]
|
||||||
|
modalities: [molecular-structure]
|
||||||
|
tasks: [docking]
|
||||||
|
year: 2023
|
||||||
|
github: https://github.com/gcorso/DiffDock
|
||||||
|
paper: https://openreview.net/forum?id=kKF8_K-mBbS
|
||||||
|
last_checked: 2026-08-08
|
||||||
|
metadata_sources:
|
||||||
|
- https://github.com/gcorso/DiffDock
|
||||||
|
- https://openreview.net/forum?id=kKF8_K-mBbS
|
||||||
|
|
||||||
|
uni_mol:
|
||||||
|
entities: [molecule, protein]
|
||||||
|
methods: [self-supervised-learning, transformer]
|
||||||
|
modalities: [chemical-structure, molecular-structure]
|
||||||
|
tasks: [docking, representation-learning]
|
||||||
|
year: 2023
|
||||||
|
github: https://github.com/deepmodeling/Uni-Mol
|
||||||
|
paper: https://openreview.net/forum?id=6K2RM6wVqKu
|
||||||
|
last_checked: 2026-08-08
|
||||||
|
metadata_sources:
|
||||||
|
- https://github.com/deepmodeling/Uni-Mol
|
||||||
|
- https://openreview.net/forum?id=6K2RM6wVqKu
|
||||||
+64
@@ -0,0 +1,64 @@
|
|||||||
|
---
|
||||||
|
title: "Provenance-backed protein model enrichment batch."
|
||||||
|
task: ""
|
||||||
|
lineage_type: import
|
||||||
|
upstream_source: https://github.com/inoue0426/awesome-computational-biology/blob/7a064bf0/data/enrichment.protein-v2.yml
|
||||||
|
upstream_sha: 7a064bf0
|
||||||
|
imported_at: 2026-08-08
|
||||||
|
prompt_class: catalogue
|
||||||
|
upstream_changes: accepted
|
||||||
|
author: upstream
|
||||||
|
validated: false
|
||||||
|
---
|
||||||
|
|
||||||
|
# Provenance-backed protein model enrichment batch.
|
||||||
|
resources:
|
||||||
|
esm3:
|
||||||
|
entities: [protein]
|
||||||
|
methods: [generative-model, language-model, transformer]
|
||||||
|
modalities: [molecular-structure, protein-sequence]
|
||||||
|
tasks: [protein-sequence-design, representation-learning]
|
||||||
|
github: https://github.com/evolutionaryscale/esm
|
||||||
|
last_checked: 2026-08-08
|
||||||
|
metadata_sources:
|
||||||
|
- https://github.com/evolutionaryscale/esm
|
||||||
|
|
||||||
|
evolutionary_scale_modeling_esm:
|
||||||
|
entities: [protein]
|
||||||
|
methods: [language-model, self-supervised-learning, transformer]
|
||||||
|
modalities: [protein-sequence]
|
||||||
|
tasks: [representation-learning]
|
||||||
|
github: https://github.com/facebookresearch/esm
|
||||||
|
last_checked: 2026-08-08
|
||||||
|
metadata_sources:
|
||||||
|
- https://github.com/facebookresearch/esm
|
||||||
|
|
||||||
|
prottrans:
|
||||||
|
entities: [protein]
|
||||||
|
methods: [language-model, self-supervised-learning, transformer]
|
||||||
|
modalities: [protein-sequence]
|
||||||
|
tasks: [representation-learning]
|
||||||
|
github: https://github.com/agemagician/ProtTrans
|
||||||
|
last_checked: 2026-08-08
|
||||||
|
metadata_sources:
|
||||||
|
- https://github.com/agemagician/ProtTrans
|
||||||
|
|
||||||
|
progen2:
|
||||||
|
entities: [protein]
|
||||||
|
methods: [generative-model, language-model, transformer]
|
||||||
|
modalities: [protein-sequence]
|
||||||
|
tasks: [protein-sequence-design, representation-learning]
|
||||||
|
github: https://github.com/salesforce/progen
|
||||||
|
last_checked: 2026-08-08
|
||||||
|
metadata_sources:
|
||||||
|
- https://github.com/salesforce/progen
|
||||||
|
|
||||||
|
alphafold3:
|
||||||
|
entities: [molecule, protein, protein-complex]
|
||||||
|
methods: [diffusion]
|
||||||
|
modalities: [molecular-structure, protein-sequence]
|
||||||
|
tasks: [structure-prediction]
|
||||||
|
github: https://github.com/google-deepmind/alphafold3
|
||||||
|
last_checked: 2026-08-08
|
||||||
|
metadata_sources:
|
||||||
|
- https://github.com/google-deepmind/alphafold3
|
||||||
+110
@@ -0,0 +1,110 @@
|
|||||||
|
---
|
||||||
|
title: "Provenance-backed spatial transcriptomics and imaging enrichment batch."
|
||||||
|
task: ""
|
||||||
|
lineage_type: import
|
||||||
|
upstream_source: https://github.com/inoue0426/awesome-computational-biology/blob/7a064bf0/data/enrichment.spatial-imaging-v1.yml
|
||||||
|
upstream_sha: 7a064bf0
|
||||||
|
imported_at: 2026-08-08
|
||||||
|
prompt_class: catalogue
|
||||||
|
upstream_changes: accepted
|
||||||
|
author: upstream
|
||||||
|
validated: false
|
||||||
|
---
|
||||||
|
|
||||||
|
# Provenance-backed spatial transcriptomics and imaging enrichment batch.
|
||||||
|
resources:
|
||||||
|
aestetik:
|
||||||
|
entities: [cell, gene, tissue]
|
||||||
|
methods: [autoencoder]
|
||||||
|
modalities: [histopathology, spatial-transcriptomics]
|
||||||
|
tasks: [representation-learning]
|
||||||
|
github: https://github.com/ratschlab/aestetik
|
||||||
|
last_checked: 2026-08-08
|
||||||
|
metadata_sources:
|
||||||
|
- https://github.com/ratschlab/aestetik
|
||||||
|
|
||||||
|
conch:
|
||||||
|
entities: [tissue]
|
||||||
|
methods: [contrastive-learning, transformer]
|
||||||
|
modalities: [histopathology, imaging]
|
||||||
|
tasks: [foundation-model-pretraining, representation-learning]
|
||||||
|
github: https://github.com/mahmoodlab/CONCH
|
||||||
|
last_checked: 2026-08-08
|
||||||
|
metadata_sources:
|
||||||
|
- https://github.com/mahmoodlab/CONCH
|
||||||
|
|
||||||
|
deepspot:
|
||||||
|
entities: [gene, tissue]
|
||||||
|
modalities: [histopathology, spatial-transcriptomics]
|
||||||
|
tasks: [regression]
|
||||||
|
github: https://github.com/ratschlab/DeepSpot
|
||||||
|
last_checked: 2026-08-08
|
||||||
|
metadata_sources:
|
||||||
|
- https://github.com/ratschlab/DeepSpot
|
||||||
|
|
||||||
|
deepspot_m:
|
||||||
|
entities: [gene, tissue]
|
||||||
|
modalities: [histopathology, spatial-transcriptomics, transcriptomics]
|
||||||
|
tasks: [foundation-model-pretraining, regression]
|
||||||
|
github: https://github.com/ratschlab/DeepSpotM
|
||||||
|
last_checked: 2026-08-08
|
||||||
|
metadata_sources:
|
||||||
|
- https://github.com/ratschlab/DeepSpotM
|
||||||
|
|
||||||
|
deepspot2cell:
|
||||||
|
entities: [cell, gene, tissue]
|
||||||
|
modalities: [histopathology, spatial-transcriptomics]
|
||||||
|
tasks: [regression]
|
||||||
|
github: https://github.com/ratschlab/DeepSpot2Cell
|
||||||
|
last_checked: 2026-08-08
|
||||||
|
metadata_sources:
|
||||||
|
- https://github.com/ratschlab/DeepSpot2Cell
|
||||||
|
|
||||||
|
gigapath:
|
||||||
|
entities: [tissue]
|
||||||
|
methods: [self-supervised-learning, transformer]
|
||||||
|
modalities: [histopathology, imaging]
|
||||||
|
tasks: [foundation-model-pretraining, representation-learning]
|
||||||
|
github: https://github.com/prov-gigapath/prov-gigapath
|
||||||
|
last_checked: 2026-08-08
|
||||||
|
metadata_sources:
|
||||||
|
- https://github.com/prov-gigapath/prov-gigapath
|
||||||
|
|
||||||
|
phikon:
|
||||||
|
entities: [tissue]
|
||||||
|
methods: [self-supervised-learning, transformer]
|
||||||
|
modalities: [histopathology, imaging]
|
||||||
|
tasks: [foundation-model-pretraining, representation-learning]
|
||||||
|
documentation: https://huggingface.co/owkin/phikon
|
||||||
|
last_checked: 2026-08-08
|
||||||
|
metadata_sources:
|
||||||
|
- https://huggingface.co/owkin/phikon
|
||||||
|
|
||||||
|
plip:
|
||||||
|
entities: [tissue]
|
||||||
|
methods: [contrastive-learning]
|
||||||
|
modalities: [histopathology, imaging]
|
||||||
|
tasks: [classification, representation-learning]
|
||||||
|
github: https://github.com/PathologyFoundation/plip
|
||||||
|
last_checked: 2026-08-08
|
||||||
|
metadata_sources:
|
||||||
|
- https://github.com/PathologyFoundation/plip
|
||||||
|
|
||||||
|
uni:
|
||||||
|
entities: [tissue]
|
||||||
|
methods: [self-supervised-learning, transformer]
|
||||||
|
modalities: [histopathology, imaging]
|
||||||
|
tasks: [foundation-model-pretraining, representation-learning]
|
||||||
|
github: https://github.com/mahmoodlab/UNI
|
||||||
|
last_checked: 2026-08-08
|
||||||
|
metadata_sources:
|
||||||
|
- https://github.com/mahmoodlab/UNI
|
||||||
|
|
||||||
|
hest_xenium_virtual_spatial_transcriptomics:
|
||||||
|
entities: [cell, gene, tissue]
|
||||||
|
modalities: [histopathology, spatial-transcriptomics, transcriptomics]
|
||||||
|
tasks: [regression]
|
||||||
|
documentation: https://huggingface.co/datasets/ratschlab/HEST_Xenium_virtual_spatial_transcriptomics
|
||||||
|
last_checked: 2026-08-08
|
||||||
|
metadata_sources:
|
||||||
|
- https://huggingface.co/datasets/ratschlab/HEST_Xenium_virtual_spatial_transcriptomics
|
||||||
@@ -0,0 +1,128 @@
|
|||||||
|
---
|
||||||
|
title: "AI4Bio landscape enrichment overlay"
|
||||||
|
task: ""
|
||||||
|
lineage_type: import
|
||||||
|
upstream_source: https://github.com/inoue0426/awesome-computational-biology/blob/7a064bf0/data/enrichment.yml
|
||||||
|
upstream_sha: 7a064bf0
|
||||||
|
imported_at: 2026-08-08
|
||||||
|
prompt_class: catalogue
|
||||||
|
upstream_changes: accepted
|
||||||
|
author: upstream
|
||||||
|
validated: false
|
||||||
|
---
|
||||||
|
|
||||||
|
# AI4Bio landscape enrichment overlay
|
||||||
|
#
|
||||||
|
# README.md remains the canonical source for resource membership and basic fields.
|
||||||
|
# Add richer, independently curated metadata here, keyed by the stable resource id.
|
||||||
|
# scripts/build_resources.py merges these fields into generated JSON/CSV artifacts.
|
||||||
|
#
|
||||||
|
# Enrichment values should be source-verifiable. Controlled vocabulary fields are
|
||||||
|
# validated against data/vocabulary.yml.
|
||||||
|
|
||||||
|
resources:
|
||||||
|
scgpt:
|
||||||
|
entities: [cell, gene]
|
||||||
|
methods: [generative-model, self-supervised-learning, transformer]
|
||||||
|
modalities: [multi-omics, single-cell-rna-seq, transcriptomics]
|
||||||
|
tasks:
|
||||||
|
- cell-type-annotation
|
||||||
|
- foundation-model-pretraining
|
||||||
|
- gene-regulatory-network-inference
|
||||||
|
- perturbation-prediction
|
||||||
|
- representation-learning
|
||||||
|
year: 2024
|
||||||
|
github: https://github.com/bowang-lab/scGPT
|
||||||
|
documentation: https://scgpt.readthedocs.io/en/latest/
|
||||||
|
paper: https://www.nature.com/articles/s41592-024-02201-0
|
||||||
|
last_checked: 2026-08-08
|
||||||
|
metadata_sources:
|
||||||
|
- https://github.com/bowang-lab/scGPT
|
||||||
|
- https://www.nature.com/articles/s41592-024-02201-0
|
||||||
|
|
||||||
|
geneformer:
|
||||||
|
entities: [cell, gene]
|
||||||
|
methods: [self-supervised-learning, transformer]
|
||||||
|
modalities: [single-cell-rna-seq, transcriptomics]
|
||||||
|
tasks:
|
||||||
|
- classification
|
||||||
|
- foundation-model-pretraining
|
||||||
|
- perturbation-prediction
|
||||||
|
- representation-learning
|
||||||
|
year: 2023
|
||||||
|
documentation: https://geneformer.readthedocs.io/
|
||||||
|
paper: https://www.nature.com/articles/s41586-023-06139-9
|
||||||
|
last_checked: 2026-08-08
|
||||||
|
metadata_sources:
|
||||||
|
- https://huggingface.co/ctheodoris/Geneformer
|
||||||
|
- https://www.nature.com/articles/s41586-023-06139-9
|
||||||
|
|
||||||
|
scfoundation:
|
||||||
|
entities: [cell, gene]
|
||||||
|
methods: [self-supervised-learning, transformer]
|
||||||
|
modalities: [single-cell-rna-seq, transcriptomics]
|
||||||
|
tasks:
|
||||||
|
- cell-type-annotation
|
||||||
|
- drug-response-prediction
|
||||||
|
- foundation-model-pretraining
|
||||||
|
- perturbation-prediction
|
||||||
|
- representation-learning
|
||||||
|
year: 2024
|
||||||
|
github: https://github.com/biomap-research/scFoundation
|
||||||
|
paper: https://www.nature.com/articles/s41592-024-02305-7
|
||||||
|
last_checked: 2026-08-08
|
||||||
|
metadata_sources:
|
||||||
|
- https://github.com/biomap-research/scFoundation
|
||||||
|
- https://www.nature.com/articles/s41592-024-02305-7
|
||||||
|
|
||||||
|
genecompass:
|
||||||
|
entities: [cell, gene]
|
||||||
|
methods: [self-supervised-learning, transformer]
|
||||||
|
modalities: [single-cell-rna-seq, transcriptomics]
|
||||||
|
tasks: [foundation-model-pretraining, representation-learning]
|
||||||
|
year: 2024
|
||||||
|
github: https://github.com/xCompass-AI/GeneCompass
|
||||||
|
paper: https://www.nature.com/articles/s41422-024-01034-y
|
||||||
|
last_checked: 2026-08-08
|
||||||
|
metadata_sources:
|
||||||
|
- https://github.com/xCompass-AI/GeneCompass
|
||||||
|
- https://www.nature.com/articles/s41422-024-01034-y
|
||||||
|
|
||||||
|
uce:
|
||||||
|
entities: [cell]
|
||||||
|
methods: [self-supervised-learning]
|
||||||
|
modalities: [single-cell-rna-seq, transcriptomics]
|
||||||
|
tasks: [foundation-model-pretraining, representation-learning]
|
||||||
|
year: 2026
|
||||||
|
github: https://github.com/snap-stanford/UCE
|
||||||
|
paper: https://www.nature.com/articles/s41586-026-10689-z
|
||||||
|
last_checked: 2026-08-08
|
||||||
|
metadata_sources:
|
||||||
|
- https://github.com/snap-stanford/UCE
|
||||||
|
- https://www.nature.com/articles/s41586-026-10689-z
|
||||||
|
|
||||||
|
cellplm:
|
||||||
|
entities: [cell, gene]
|
||||||
|
methods: [self-supervised-learning, transformer]
|
||||||
|
modalities: [single-cell-rna-seq, transcriptomics]
|
||||||
|
tasks: [foundation-model-pretraining, representation-learning]
|
||||||
|
year: 2023
|
||||||
|
github: https://github.com/OmicsML/CellPLM
|
||||||
|
paper: https://www.biorxiv.org/content/10.1101/2023.10.03.560734v1
|
||||||
|
last_checked: 2026-08-08
|
||||||
|
metadata_sources:
|
||||||
|
- https://github.com/OmicsML/CellPLM
|
||||||
|
- https://www.biorxiv.org/content/10.1101/2023.10.03.560734v1
|
||||||
|
|
||||||
|
scbert:
|
||||||
|
entities: [cell, gene]
|
||||||
|
methods: [language-model, self-supervised-learning, transformer]
|
||||||
|
modalities: [single-cell-rna-seq, transcriptomics]
|
||||||
|
tasks: [cell-type-annotation, classification, foundation-model-pretraining]
|
||||||
|
year: 2022
|
||||||
|
github: https://github.com/TencentAILabHealthcare/scBERT
|
||||||
|
paper: https://www.nature.com/articles/s42256-022-00534-z
|
||||||
|
last_checked: 2026-08-08
|
||||||
|
metadata_sources:
|
||||||
|
- https://github.com/TencentAILabHealthcare/scBERT
|
||||||
|
- https://www.nature.com/articles/s42256-022-00534-z
|
||||||
File diff suppressed because it is too large
Load Diff
@@ -2,9 +2,9 @@
|
|||||||
title: "Awesome Computational Biology - machine-readable resource list"
|
title: "Awesome Computational Biology - machine-readable resource list"
|
||||||
task: ""
|
task: ""
|
||||||
lineage_type: import
|
lineage_type: import
|
||||||
upstream_source: https://github.com/inoue0426/awesome-computational-biology/blob/478be843/data/resources.yml
|
upstream_source: https://github.com/inoue0426/awesome-computational-biology/blob/7a064bf0/data/resources.yml
|
||||||
upstream_sha: 478be843
|
upstream_sha: 7a064bf0
|
||||||
imported_at: 2026-07-17
|
imported_at: 2026-08-08
|
||||||
prompt_class: catalogue
|
prompt_class: catalogue
|
||||||
upstream_changes: accepted
|
upstream_changes: accepted
|
||||||
author: upstream
|
author: upstream
|
||||||
@@ -1678,6 +1678,17 @@ resources:
|
|||||||
organism: []
|
organism: []
|
||||||
api: false
|
api: false
|
||||||
|
|
||||||
|
- id: cellot
|
||||||
|
name: "CellOT"
|
||||||
|
type: model
|
||||||
|
url: https://github.com/bunnech/cellot
|
||||||
|
description: "Neural optimal transport framework for predicting single-cell responses to drug and genetic perturbations."
|
||||||
|
tags: [drug-discovery, drug-perturbation]
|
||||||
|
tasks: [Drug Discovery, Drug Perturbation]
|
||||||
|
modalities: [Small Molecule]
|
||||||
|
organism: []
|
||||||
|
api: false
|
||||||
|
|
||||||
- id: cellplm
|
- id: cellplm
|
||||||
name: "CellPLM"
|
name: "CellPLM"
|
||||||
type: model
|
type: model
|
||||||
@@ -1727,8 +1738,8 @@ resources:
|
|||||||
type: model
|
type: model
|
||||||
url: https://github.com/theislab/chemCPA
|
url: https://github.com/theislab/chemCPA
|
||||||
description: "Compositional perturbation autoencoder for predicting single-cell transcriptional responses to unseen drug perturbations and dose combinations."
|
description: "Compositional perturbation autoencoder for predicting single-cell transcriptional responses to unseen drug perturbations and dose combinations."
|
||||||
tags: [drug-discovery, drug-response-prediction]
|
tags: [drug-discovery, drug-perturbation]
|
||||||
tasks: [Drug Discovery, Drug Response Prediction]
|
tasks: [Drug Discovery, Drug Perturbation]
|
||||||
modalities: [Small Molecule]
|
modalities: [Small Molecule]
|
||||||
organism: []
|
organism: []
|
||||||
api: false
|
api: false
|
||||||
@@ -1755,6 +1766,17 @@ resources:
|
|||||||
organism: []
|
organism: []
|
||||||
api: false
|
api: false
|
||||||
|
|
||||||
|
- id: cmonge
|
||||||
|
name: "CMonge"
|
||||||
|
type: model
|
||||||
|
url: https://github.com/AI4SCR/conditional-monge-gap
|
||||||
|
description: "Conditional optimal transport model for generalizable single-cell perturbation response prediction across drugs and doses."
|
||||||
|
tags: [drug-discovery, drug-perturbation]
|
||||||
|
tasks: [Drug Discovery, Drug Perturbation]
|
||||||
|
modalities: [Small Molecule]
|
||||||
|
organism: []
|
||||||
|
api: false
|
||||||
|
|
||||||
- id: concerto
|
- id: concerto
|
||||||
name: "Concerto"
|
name: "Concerto"
|
||||||
type: model
|
type: model
|
||||||
@@ -1782,8 +1804,8 @@ resources:
|
|||||||
type: model
|
type: model
|
||||||
url: https://github.com/hliulab/cycleCDR
|
url: https://github.com/hliulab/cycleCDR
|
||||||
description: "Interpretable cycle-consistency framework for modeling cellular responses to drug perturbations."
|
description: "Interpretable cycle-consistency framework for modeling cellular responses to drug perturbations."
|
||||||
tags: [drug-discovery, drug-response-prediction]
|
tags: [drug-discovery, drug-perturbation]
|
||||||
tasks: [Drug Discovery, Drug Response Prediction]
|
tasks: [Drug Discovery, Drug Perturbation]
|
||||||
modalities: [Small Molecule]
|
modalities: [Small Molecule]
|
||||||
organism: []
|
organism: []
|
||||||
api: false
|
api: false
|
||||||
@@ -2475,8 +2497,8 @@ resources:
|
|||||||
type: model
|
type: model
|
||||||
url: https://github.com/Perturbation-Response-Prediction/PRnet
|
url: https://github.com/Perturbation-Response-Prediction/PRnet
|
||||||
description: "Deep generative model for predicting transcriptional responses to novel chemical perturbations for drug discovery."
|
description: "Deep generative model for predicting transcriptional responses to novel chemical perturbations for drug discovery."
|
||||||
tags: [drug-discovery, drug-response-prediction]
|
tags: [drug-discovery, drug-perturbation]
|
||||||
tasks: [Drug Discovery, Drug Response Prediction]
|
tasks: [Drug Discovery, Drug Perturbation]
|
||||||
modalities: [Small Molecule]
|
modalities: [Small Molecule]
|
||||||
organism: []
|
organism: []
|
||||||
api: false
|
api: false
|
||||||
|
|||||||
@@ -0,0 +1,105 @@
|
|||||||
|
---
|
||||||
|
title: "Canonical vocabulary for new AI4Bio enrichment metadata."
|
||||||
|
task: ""
|
||||||
|
lineage_type: import
|
||||||
|
upstream_source: https://github.com/inoue0426/awesome-computational-biology/blob/7a064bf0/data/vocabulary.yml
|
||||||
|
upstream_sha: 7a064bf0
|
||||||
|
imported_at: 2026-08-08
|
||||||
|
prompt_class: unknown
|
||||||
|
upstream_changes: accepted
|
||||||
|
author: upstream
|
||||||
|
validated: false
|
||||||
|
---
|
||||||
|
|
||||||
|
# Canonical vocabulary for new AI4Bio enrichment metadata.
|
||||||
|
#
|
||||||
|
# These values are enforced only for fields explicitly added through
|
||||||
|
# data/enrichment.yml. README-derived legacy values remain backward compatible.
|
||||||
|
# Canonical terms use lowercase kebab-case.
|
||||||
|
|
||||||
|
version: 1
|
||||||
|
|
||||||
|
controlled_fields:
|
||||||
|
entities:
|
||||||
|
- cell
|
||||||
|
- compound
|
||||||
|
- disease
|
||||||
|
- drug
|
||||||
|
- gene
|
||||||
|
- genome
|
||||||
|
- molecule
|
||||||
|
- organism
|
||||||
|
- pathway
|
||||||
|
- phenotype
|
||||||
|
- protein
|
||||||
|
- protein-complex
|
||||||
|
- regulatory-element
|
||||||
|
- tissue
|
||||||
|
- transcript
|
||||||
|
- variant
|
||||||
|
|
||||||
|
methods:
|
||||||
|
- autoencoder
|
||||||
|
- contrastive-learning
|
||||||
|
- convolutional-neural-network
|
||||||
|
- diffusion
|
||||||
|
- generative-model
|
||||||
|
- geometric-deep-learning
|
||||||
|
- graph-neural-network
|
||||||
|
- knowledge-graph
|
||||||
|
- language-model
|
||||||
|
- message-passing-neural-network
|
||||||
|
- multi-agent-system
|
||||||
|
- optimal-transport
|
||||||
|
- recurrent-neural-network
|
||||||
|
- reinforcement-learning
|
||||||
|
- retrieval-augmented-generation
|
||||||
|
- self-supervised-learning
|
||||||
|
- state-space-model
|
||||||
|
- supervised-learning
|
||||||
|
- transformer
|
||||||
|
- unsupervised-learning
|
||||||
|
- variational-autoencoder
|
||||||
|
|
||||||
|
modalities:
|
||||||
|
- cell-painting
|
||||||
|
- chemical-structure
|
||||||
|
- clinical
|
||||||
|
- dna-sequence
|
||||||
|
- electronic-health-record
|
||||||
|
- epigenomics
|
||||||
|
- genomics
|
||||||
|
- histopathology
|
||||||
|
- imaging
|
||||||
|
- knowledge-graph
|
||||||
|
- metabolomics
|
||||||
|
- molecular-structure
|
||||||
|
- multi-omics
|
||||||
|
- protein-sequence
|
||||||
|
- proteomics
|
||||||
|
- rna-sequence
|
||||||
|
- single-cell-rna-seq
|
||||||
|
- spatial-transcriptomics
|
||||||
|
- transcriptomics
|
||||||
|
|
||||||
|
tasks:
|
||||||
|
- batch-correction
|
||||||
|
- cell-type-annotation
|
||||||
|
- classification
|
||||||
|
- dimensionality-reduction
|
||||||
|
- docking
|
||||||
|
- drug-response-prediction
|
||||||
|
- drug-target-interaction
|
||||||
|
- foundation-model-pretraining
|
||||||
|
- gene-regulatory-network-inference
|
||||||
|
- imputation
|
||||||
|
- link-prediction
|
||||||
|
- molecular-generation
|
||||||
|
- perturbation-prediction
|
||||||
|
- protein-function-prediction
|
||||||
|
- protein-sequence-design
|
||||||
|
- regression
|
||||||
|
- representation-learning
|
||||||
|
- structure-prediction
|
||||||
|
- trajectory-inference
|
||||||
|
- virtual-screening
|
||||||
@@ -0,0 +1,73 @@
|
|||||||
|
---
|
||||||
|
title: "AI4Bio Landscape Database"
|
||||||
|
task: ""
|
||||||
|
lineage_type: import
|
||||||
|
upstream_source: https://github.com/inoue0426/awesome-computational-biology/blob/7a064bf0/docs/AI4BIO_LANDSCAPE.md
|
||||||
|
upstream_sha: 7a064bf0
|
||||||
|
imported_at: 2026-08-08
|
||||||
|
prompt_class: catalogue
|
||||||
|
upstream_changes: accepted
|
||||||
|
author: upstream
|
||||||
|
validated: false
|
||||||
|
---
|
||||||
|
|
||||||
|
# AI4Bio Landscape Database
|
||||||
|
|
||||||
|
The landscape view treats the existing computational biology registry as a multidimensional database rather than a single hierarchical list.
|
||||||
|
|
||||||
|
## Design goals
|
||||||
|
|
||||||
|
- Keep the current curated resource records and generation pipeline intact.
|
||||||
|
- Expose orthogonal facets so one resource can be explored by resource type, biological/ML task, data modality, organism, and domain tag.
|
||||||
|
- Make the landscape useful without introducing a server or build-time dependency.
|
||||||
|
- Keep the data model extensible for richer AI4Bio metadata over time.
|
||||||
|
|
||||||
|
## Current facet model
|
||||||
|
|
||||||
|
The landscape UI derives the following dimensions from `docs/data/resources.json`:
|
||||||
|
|
||||||
|
| Dimension | Source field | Example values |
|
||||||
|
|---|---|---|
|
||||||
|
| Resource type | `type` | `database`, `benchmark`, `model`, `toolkit`, `api` |
|
||||||
|
| Task | `tasks` | `drug-response-prediction`, `cell-type-annotation`, `molecular-generation` |
|
||||||
|
| Modality | `modalities` | `transcriptomics`, `spatial-transcriptomics`, `protein-sequence` |
|
||||||
|
| Organism | `organism` | `human`, `mouse`, `multi-species` |
|
||||||
|
| Domain/tag | `tags` | `drug-discovery`, `single-cell`, `foundation-model` |
|
||||||
|
|
||||||
|
These are deliberately treated as separate axes. A model can therefore be, for example, a `model` that performs `perturbation-prediction` on `single-cell-rna-seq` data for `human` and carry tags such as `drug-discovery` and `foundation-model`.
|
||||||
|
|
||||||
|
## Recommended schema evolution
|
||||||
|
|
||||||
|
The current schema is compatible with a richer landscape database. New fields should be added incrementally and only when they can be curated consistently.
|
||||||
|
|
||||||
|
Suggested fields:
|
||||||
|
|
||||||
|
| Field | Type | Purpose |
|
||||||
|
|---|---|---|
|
||||||
|
| `entities` | array of strings | Biological entities such as `gene`, `protein`, `compound`, `cell`, `disease` |
|
||||||
|
| `methods` | array of strings | Method families such as `transformer`, `gnn`, `diffusion`, `optimal-transport` |
|
||||||
|
| `organizations` | array of strings | Primary organizations responsible for the resource |
|
||||||
|
| `year` | integer | Initial public release/publication year |
|
||||||
|
| `github` | string | Source repository when distinct from the canonical landing page |
|
||||||
|
| `documentation` | string | Documentation URL |
|
||||||
|
| `maintenance_status` | string | Curated status such as `active`, `maintenance`, `archived`, `unknown` |
|
||||||
|
| `last_checked` | string | Date the metadata/link was last manually or automatically checked |
|
||||||
|
|
||||||
|
Avoid adding dynamic popularity metrics such as GitHub stars directly to canonical records unless a reproducible refresh pipeline is introduced. Such values become stale quickly and should be stored as generated metadata rather than curated facts.
|
||||||
|
|
||||||
|
## Canonical-source policy
|
||||||
|
|
||||||
|
At present, `README.md` is the canonical curated list, with generated YAML/JSON/CSV artifacts. The landscape page intentionally consumes `docs/data/resources.json` without changing that policy.
|
||||||
|
|
||||||
|
A future migration may make `data/resources.yml` the canonical source once all README-only categorization semantics can be represented explicitly in structured fields. That migration should be a separate change because it changes contribution workflow and source-of-truth semantics.
|
||||||
|
|
||||||
|
## Landscape page
|
||||||
|
|
||||||
|
Open `docs/landscape.html` through GitHub Pages. It provides:
|
||||||
|
|
||||||
|
- full-text search across names, descriptions, tasks, modalities, organisms, and tags;
|
||||||
|
- filters for type, task, modality, organism, and tag;
|
||||||
|
- summary counts for resources and major dimensions;
|
||||||
|
- frequency bars recalculated for the current filtered result set;
|
||||||
|
- direct resource and paper links;
|
||||||
|
- client-side rendering with no additional dependencies.
|
||||||
+72
@@ -0,0 +1,72 @@
|
|||||||
|
---
|
||||||
|
title: "Foundation Model Enrichment"
|
||||||
|
task: ""
|
||||||
|
lineage_type: import
|
||||||
|
upstream_source: https://github.com/inoue0426/awesome-computational-biology/blob/7a064bf0/docs/FOUNDATION_MODEL_ENRICHMENT.md
|
||||||
|
upstream_sha: 7a064bf0
|
||||||
|
imported_at: 2026-08-08
|
||||||
|
prompt_class: catalogue
|
||||||
|
upstream_changes: accepted
|
||||||
|
author: upstream
|
||||||
|
validated: false
|
||||||
|
---
|
||||||
|
|
||||||
|
# Foundation Model Enrichment
|
||||||
|
|
||||||
|
This document tracks the first curated metadata-enrichment pass for AI4Bio foundation models.
|
||||||
|
|
||||||
|
## Scope
|
||||||
|
|
||||||
|
The initial pass focuses on representative single-cell and transcriptomics foundation models already present in the resource registry, beginning with:
|
||||||
|
|
||||||
|
- scGPT
|
||||||
|
- Geneformer
|
||||||
|
|
||||||
|
The scope may be expanded incrementally once the curation rules below are validated in practice.
|
||||||
|
|
||||||
|
## Curation rules
|
||||||
|
|
||||||
|
Metadata must be supported by at least one primary or official source:
|
||||||
|
|
||||||
|
- official project repository or model card;
|
||||||
|
- official documentation;
|
||||||
|
- primary peer-reviewed publication or preprint.
|
||||||
|
|
||||||
|
Unknown or ambiguous metadata is omitted rather than inferred.
|
||||||
|
|
||||||
|
For each resource, curate fields where evidence is available:
|
||||||
|
|
||||||
|
- `entities`
|
||||||
|
- `methods`
|
||||||
|
- `organizations`
|
||||||
|
- `year`
|
||||||
|
- `github`
|
||||||
|
- `documentation`
|
||||||
|
- `maintenance_status`
|
||||||
|
- `last_checked`
|
||||||
|
- `metadata_sources`
|
||||||
|
|
||||||
|
`maintenance_status` should only be marked `active` when there is direct evidence of ongoing maintenance, such as a recent official release or repository activity. Otherwise use `unknown` or omit the field.
|
||||||
|
|
||||||
|
## Initial evidence targets
|
||||||
|
|
||||||
|
### scGPT
|
||||||
|
|
||||||
|
Primary evidence should include the official `bowang-lab/scGPT` repository and the Nature Methods publication.
|
||||||
|
|
||||||
|
### Geneformer
|
||||||
|
|
||||||
|
Primary evidence should include the official `ctheodoris/Geneformer` model repository/model card and the primary Nature publication.
|
||||||
|
|
||||||
|
## Completion criteria
|
||||||
|
|
||||||
|
A resource is considered enriched when:
|
||||||
|
|
||||||
|
1. all added metadata is supported by `metadata_sources`;
|
||||||
|
2. no unsupported organization, method, year, or maintenance claim is introduced;
|
||||||
|
3. generated JSON/CSV artifacts are regenerated and committed;
|
||||||
|
4. schema validation and resource-consistency CI checks pass.
|
||||||
|
|
||||||
|
## Provenance
|
||||||
|
|
||||||
|
This enrichment pass is being prepared with assistance from OpenAI GPT-5.6 Sol. Final metadata is intended to remain source-verifiable and reviewable through the recorded provenance URLs.
|
||||||
@@ -0,0 +1,21 @@
|
|||||||
|
---
|
||||||
|
title: "AI4Bio data files"
|
||||||
|
task: ""
|
||||||
|
lineage_type: import
|
||||||
|
upstream_source: https://github.com/inoue0426/awesome-computational-biology/blob/7a064bf0/docs/data/README.md
|
||||||
|
upstream_sha: 7a064bf0
|
||||||
|
imported_at: 2026-08-08
|
||||||
|
prompt_class: catalogue
|
||||||
|
upstream_changes: accepted
|
||||||
|
author: upstream
|
||||||
|
validated: false
|
||||||
|
---
|
||||||
|
|
||||||
|
# AI4Bio data files
|
||||||
|
|
||||||
|
- `resources.json`: generated merged resource registry consumed by GitHub Pages.
|
||||||
|
- `resource.schema.json`: JSON Schema 2020-12 contract for one resource object.
|
||||||
|
- `SCHEMA.md`: original schema notes.
|
||||||
|
- `SCHEMA_V2.md`: richer AI4Bio landscape schema and enrichment workflow.
|
||||||
|
|
||||||
|
The enriched build path is `scripts/build_resources_v2.py`, which combines `data/resources.yml` with `data/enrichment.yml` and runs `scripts/validate_resources.py` before writing artifacts.
|
||||||
@@ -0,0 +1,132 @@
|
|||||||
|
---
|
||||||
|
title: "AI4Bio Resource Schema v2"
|
||||||
|
task: ""
|
||||||
|
lineage_type: import
|
||||||
|
upstream_source: https://github.com/inoue0426/awesome-computational-biology/blob/7a064bf0/docs/data/SCHEMA_V2.md
|
||||||
|
upstream_sha: 7a064bf0
|
||||||
|
imported_at: 2026-08-08
|
||||||
|
prompt_class: catalogue
|
||||||
|
upstream_changes: accepted
|
||||||
|
author: upstream
|
||||||
|
validated: false
|
||||||
|
---
|
||||||
|
|
||||||
|
# AI4Bio Resource Schema v2
|
||||||
|
|
||||||
|
This document defines the richer landscape metadata layered on top of the curated Awesome Computational Biology list.
|
||||||
|
|
||||||
|
## Source model
|
||||||
|
|
||||||
|
The repository intentionally separates **membership/basic metadata** from **landscape enrichment**:
|
||||||
|
|
||||||
|
1. `README.md` is the canonical curated resource list.
|
||||||
|
2. `scripts/sync_resources_from_readme.py` derives `data/resources.yml` from README headings and bullets.
|
||||||
|
3. `data/enrichment.yml` stores richer metadata keyed by stable resource `id`.
|
||||||
|
4. `data/vocabulary.yml` defines canonical terms for controlled enrichment dimensions.
|
||||||
|
5. `scripts/build_resources.py` merges base records and enrichment, validates them, and writes `data/resources.json`, `data/resources.csv`, and `docs/data/resources.json`.
|
||||||
|
|
||||||
|
This separation prevents hand-curated AI4Bio metadata from being erased by README synchronization.
|
||||||
|
|
||||||
|
## Core identity fields
|
||||||
|
|
||||||
|
These fields are required and may not be overridden by `data/enrichment.yml`:
|
||||||
|
|
||||||
|
| Field | Type | Meaning |
|
||||||
|
|---|---|---|
|
||||||
|
| `id` | string | Stable lowercase `snake_case` identifier |
|
||||||
|
| `name` | string | Official display name |
|
||||||
|
| `type` | enum | `api`, `benchmark`, `database`, `model`, `resource`, or `toolkit` |
|
||||||
|
| `url` | URL | Canonical landing page |
|
||||||
|
| `description` | string | Short factual description |
|
||||||
|
|
||||||
|
## Landscape dimensions
|
||||||
|
|
||||||
|
| Field | Type | Meaning |
|
||||||
|
|---|---|---|
|
||||||
|
| `tasks` | string[] | Biological or ML tasks performed |
|
||||||
|
| `modalities` | string[] | Input/output data modalities |
|
||||||
|
| `organism` | string[] | Covered organisms or species groups |
|
||||||
|
| `entities` | string[] | Biological entities: gene, protein, compound, cell, disease, etc. |
|
||||||
|
| `methods` | string[] | Method families: transformer, GNN, diffusion, optimal transport, etc. |
|
||||||
|
| `tags` | string[] | Broad domain and curation labels |
|
||||||
|
| `organizations` | string[] | Organizations maintaining or primarily responsible for the resource |
|
||||||
|
|
||||||
|
These dimensions are deliberately orthogonal. Do not encode a task as a modality or a biological entity as a resource type.
|
||||||
|
|
||||||
|
## Controlled vocabulary
|
||||||
|
|
||||||
|
New values added through `data/enrichment.yml` for `entities`, `methods`, `modalities`, and `tasks` must use canonical terms from `data/vocabulary.yml`.
|
||||||
|
|
||||||
|
Canonical terms use lowercase kebab-case, for example:
|
||||||
|
|
||||||
|
```yaml
|
||||||
|
entities: [cell, gene]
|
||||||
|
methods: [transformer, self-supervised-learning]
|
||||||
|
modalities: [single-cell-rna-seq, transcriptomics]
|
||||||
|
tasks: [foundation-model-pretraining, cell-type-annotation]
|
||||||
|
```
|
||||||
|
|
||||||
|
This rule is intentionally applied only to enrichment metadata. Existing README-derived values remain valid for backward compatibility and can be migrated separately without blocking routine resource updates.
|
||||||
|
|
||||||
|
When a required concept is missing, add a reusable canonical term to `data/vocabulary.yml` instead of inventing a one-off spelling in an enrichment record. `tags`, `organism`, and `organizations` remain free-form because their vocabularies are broader or context dependent.
|
||||||
|
|
||||||
|
## Provenance and lifecycle fields
|
||||||
|
|
||||||
|
| Field | Type | Meaning |
|
||||||
|
|---|---|---|
|
||||||
|
| `year` | integer | Initial public release or primary publication year |
|
||||||
|
| `github` | URL | Source repository when available |
|
||||||
|
| `documentation` | URL | Documentation landing page |
|
||||||
|
| `paper` | URL | Primary publication or preprint |
|
||||||
|
| `license` | string | SPDX identifier preferred |
|
||||||
|
| `api` | boolean | Programmatic API availability |
|
||||||
|
| `access` | enum | `open`, `registration`, `restricted`, `commercial`, `unknown` |
|
||||||
|
| `maintenance_status` | enum | `active`, `maintenance`, `archived`, `unknown` |
|
||||||
|
| `updated` | date | Last-known upstream update date |
|
||||||
|
| `last_checked` | date | Date this repository verified the metadata |
|
||||||
|
| `metadata_sources` | URL[] | Sources supporting enriched metadata |
|
||||||
|
|
||||||
|
`last_checked` is a curation timestamp, not an upstream release date. `updated` should only be populated when an upstream update date is known.
|
||||||
|
|
||||||
|
## Enrichment rules
|
||||||
|
|
||||||
|
`data/enrichment.yml` is a mapping keyed by resource id:
|
||||||
|
|
||||||
|
```yaml
|
||||||
|
resources:
|
||||||
|
example_resource:
|
||||||
|
entities: [gene, disease]
|
||||||
|
methods: [transformer]
|
||||||
|
organizations: [Example Lab]
|
||||||
|
year: 2025
|
||||||
|
github: https://github.com/example/project
|
||||||
|
documentation: https://example.org/docs
|
||||||
|
maintenance_status: active
|
||||||
|
access: open
|
||||||
|
last_checked: 2026-08-08
|
||||||
|
metadata_sources:
|
||||||
|
- https://example.org/about
|
||||||
|
```
|
||||||
|
|
||||||
|
Enrichment cannot override `id`, `name`, `type`, `url`, or `description`. A referenced id must already exist in `data/resources.yml`.
|
||||||
|
|
||||||
|
## Validation contract
|
||||||
|
|
||||||
|
`python scripts/validate_resources.py` checks:
|
||||||
|
|
||||||
|
- required fields and field types;
|
||||||
|
- stable id format and id uniqueness;
|
||||||
|
- allowed enum values;
|
||||||
|
- HTTP(S) URL shape;
|
||||||
|
- ISO `YYYY-MM-DD` dates;
|
||||||
|
- list uniqueness and non-empty values;
|
||||||
|
- enrichment references and forbidden identity overrides;
|
||||||
|
- controlled enrichment terms against `data/vocabulary.yml`;
|
||||||
|
- vocabulary uniqueness and lowercase kebab-case normalization;
|
||||||
|
- unknown field names.
|
||||||
|
|
||||||
|
The machine-readable resource counterpart is `docs/data/resource.schema.json` (JSON Schema 2020-12). Controlled vocabulary enforcement is performed at the enrichment layer because legacy README-derived values intentionally remain backward compatible.
|
||||||
|
|
||||||
|
## Curation guidance
|
||||||
|
|
||||||
|
Prefer verified metadata over exhaustive metadata. Unknown fields should be omitted rather than guessed. For facts likely to change, include `last_checked` and at least one `metadata_sources` URL. Dynamic popularity metrics such as GitHub stars should remain generated telemetry rather than canonical curated fields.
|
||||||
+53
@@ -0,0 +1,53 @@
|
|||||||
|
---
|
||||||
|
title: "Resource.Schema"
|
||||||
|
task: ""
|
||||||
|
lineage_type: import
|
||||||
|
upstream_source: https://github.com/inoue0426/awesome-computational-biology/blob/7a064bf0/docs/data/resource.schema.json
|
||||||
|
upstream_sha: 7a064bf0
|
||||||
|
imported_at: 2026-08-08
|
||||||
|
prompt_class: catalogue
|
||||||
|
upstream_changes: accepted
|
||||||
|
author: upstream
|
||||||
|
validated: false
|
||||||
|
---
|
||||||
|
|
||||||
|
{
|
||||||
|
"$schema": "https://json-schema.org/draft/2020-12/schema",
|
||||||
|
"$id": "https://inoue0426.github.io/awesome-computational-biology/data/resource.schema.json",
|
||||||
|
"title": "AI4Bio Resource",
|
||||||
|
"type": "object",
|
||||||
|
"required": ["id", "name", "type", "url", "description"],
|
||||||
|
"additionalProperties": false,
|
||||||
|
"properties": {
|
||||||
|
"id": {"type": "string", "pattern": "^[a-z0-9]+(?:_[a-z0-9]+)*$"},
|
||||||
|
"name": {"type": "string", "minLength": 1},
|
||||||
|
"type": {"enum": ["api", "benchmark", "database", "model", "resource", "toolkit"]},
|
||||||
|
"url": {"type": "string", "format": "uri", "pattern": "^https?://"},
|
||||||
|
"description": {"type": "string", "minLength": 1},
|
||||||
|
"tags": {"$ref": "#/$defs/stringArray"},
|
||||||
|
"tasks": {"$ref": "#/$defs/stringArray"},
|
||||||
|
"modalities": {"$ref": "#/$defs/stringArray"},
|
||||||
|
"organism": {"$ref": "#/$defs/stringArray"},
|
||||||
|
"entities": {"$ref": "#/$defs/stringArray"},
|
||||||
|
"methods": {"$ref": "#/$defs/stringArray"},
|
||||||
|
"organizations": {"$ref": "#/$defs/stringArray"},
|
||||||
|
"metadata_sources": {"type": "array", "items": {"type": "string", "format": "uri", "pattern": "^https?://"}, "uniqueItems": true},
|
||||||
|
"license": {"type": "string"},
|
||||||
|
"api": {"type": "boolean"},
|
||||||
|
"paper": {"type": "string", "format": "uri", "pattern": "^https?://"},
|
||||||
|
"github": {"type": "string", "format": "uri", "pattern": "^https://github\\.com/"},
|
||||||
|
"documentation": {"type": "string", "format": "uri", "pattern": "^https?://"},
|
||||||
|
"year": {"type": "integer", "minimum": 1900, "maximum": 2100},
|
||||||
|
"maintenance_status": {"enum": ["active", "maintenance", "archived", "unknown"]},
|
||||||
|
"access": {"enum": ["open", "registration", "restricted", "commercial", "unknown"]},
|
||||||
|
"updated": {"type": "string", "format": "date"},
|
||||||
|
"last_checked": {"type": "string", "format": "date"}
|
||||||
|
},
|
||||||
|
"$defs": {
|
||||||
|
"stringArray": {
|
||||||
|
"type": "array",
|
||||||
|
"items": {"type": "string", "minLength": 1},
|
||||||
|
"uniqueItems": true
|
||||||
|
}
|
||||||
|
}
|
||||||
|
}
|
||||||
+1053
-198
File diff suppressed because it is too large
Load Diff
Reference in New Issue
Block a user