[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M74MS59T46Q77JNDTSQWJCTB":3,"skill-same:01M74MS59T46Q77JNDTSQWJCTB":63},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":16,"categories":17,"keywords":18,"publishedAt":19,"linkOnly":20,"markdownContent":21,"markdownBody":22,"frontMatter":23,"refName":24,"commitSha":25,"skillDirectory":26,"forksCount":27,"repositoryHtmlUrl":28,"repositoryHomepageUrl":29,"ownerHtmlUrl":30,"ownerBlogUrl":6,"ownerDescription":31,"updatedAt":32,"install":33,"resources":46},"01M74MS59T46Q77JNDTSQWJCTB","chembl-database",null,"Query the ChEMBL database for bioactive molecules, drug targets, bioactivity data, approved drugs, and chemical structures. Use when the user asks about compounds, targets, IC50\u002FKi values, drug mechanisms, or structure searches.","pengqianhan\u002FAI-Human-Research-OS","pengqianhan","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F4286531?v=4","01M74M3DT9HNZ6HPAK8TX69EX9","PengqianHan","01M74M3DTVSN2GXW0JH2W396FK",3,"MIT","https:\u002F\u002Fgithub.com\u002Fpengqianhan\u002FAI-Human-Research-OS\u002Fblob\u002Fmain\u002Fresearch-skills-hub\u002Fscience-skills\u002Fchembl_database\u002FSKILL.md",[],[],"2026-11-11 15:11:14",false,"---\nname: chembl-database\ndescription: >\n  Query the ChEMBL database for bioactive molecules, drug targets, bioactivity\n  data, approved drugs, and chemical structures. Use when the user asks about\n  compounds, targets, IC50\u002FKi values, drug mechanisms, or structure searches.\n---\n\n# ChEMBL Database Query\n\n## Prerequisites\n\n1.  **`uv`**: Read the `uv` skill and follow its Setup instructions to ensure\n    `uv` is installed and on PATH.\n2.  **User Notification**: If .licenses\u002Fchembl_database_LICENSE.txt does not\n    already exist in the workspace root directory then (1) prominently notify\n    the user to check the terms at\n    https:\u002F\u002Fchembl.gitbook.io\u002Fchembl-interface-documentation\u002Fabout, then (2)\n    create the file recording the notification text and timestamp.\n\n## Core Rules\n\n-   [!IMPORTANT] **Use the Utility Scripts**: You MUST ALWAYS use the provided\n    utility script `scripts\u002Fchembl_api.py` for all ChEMBL API interactions,\n    including checking status. NEVER use `curl` or custom Python requests to\n    query the ChEMBL API directly. This ensures rate limit is enfoced and also\n    retries on network errors.\n\n-   **Output to File (Required)**: The `--output` flag is **required** for every\n    subcommand. All JSON results are written to the specified file. After\n    running the command, read the output file with jq or your own code to\n    extract the data. List results are typically wrapped in a JSON array keyed\n    by the endpoint name (e.g., `molecules`, `activities`).\n\n-   **Notification**: If this skill is used, ensure this is mentioned in the\n    output.\n\n## Utility Script\n\nAll ChEMBL API queries use one script with subcommands:\n\n```bash\nuv run scripts\u002Fchembl_api.py \u003Csubcommand> --output \u003Cfile> [options]\n```\n\n--------------------------------------------------------------------------------\n\n### 1. Check API Status\n\n```bash\nuv run scripts\u002Fchembl_api.py status --output \u002Ftmp\u002Fstatus.json\n```\n\n--------------------------------------------------------------------------------\n\n### 2. Molecule Queries\n\n**Fetch by ChEMBL ID:** `bash uv run scripts\u002Fchembl_api.py molecule --id\nCHEMBL25 --output \u002Ftmp\u002Fmol.json`\n\n**Search by name:** `bash uv run scripts\u002Fchembl_api.py molecule --search\n\"aspirin\" --limit 3 --output \u002Ftmp\u002Fmol_search.json`\n\n**Batch fetch:** `bash uv run scripts\u002Fchembl_api.py molecule --ids\n\"CHEMBL25;CHEMBL1642\" --limit 10 --output \u002Ftmp\u002Fmol_batch.json`\n\n**Filter by properties:** `bash uv run scripts\u002Fchembl_api.py molecule --filter\nmolecule_properties__mw_freebase__lte=500 --limit 5 --output\n\u002Ftmp\u002Fmol_filter.json`\n\n**Filter by range:** `bash uv run scripts\u002Fchembl_api.py molecule --filter\nmolecule_properties__mw_freebase__range=150,200 --limit 5 --output\n\u002Ftmp\u002Fmol_range.json`\n\n**Download SDF structure file:** `bash uv run scripts\u002Fchembl_api.py molecule\n--id CHEMBL25 --dl_format sdf --output \u002Ftmp\u002Faspirin.sdf`\n\n> **Tip**: SDF\u002FMOL files can be passed directly to tools like PyMOL or RDKit for\n> 3D visualization and analysis.\n\n--------------------------------------------------------------------------------\n\n### 3. Target Queries\n\n**Search for targets:** `bash uv run scripts\u002Fchembl_api.py target --search\n\"EGFR\" --limit 5 --output \u002Ftmp\u002Ftargets.json`\n\n**Fetch by ID:** `bash uv run scripts\u002Fchembl_api.py target --id CHEMBL203\n--output \u002Ftmp\u002Fegfr.json`\n\n--------------------------------------------------------------------------------\n\n### 4. Bioactivity Data\n\n**Fetch activity by ID:** `bash uv run scripts\u002Fchembl_api.py activity --id 31863\n--output \u002Ftmp\u002Fact.json`\n\n**Search activities:** `bash uv run scripts\u002Fchembl_api.py activity --search\n\"EGFR\" --limit 5 --output \u002Ftmp\u002Fact_search.json`\n\n**Filter activities for a target:** `bash uv run scripts\u002Fchembl_api.py activity\n--filter target_chembl_id=CHEMBL203 standard_type=IC50 --limit 10 --output\n\u002Ftmp\u002Fegfr_ic50.json`\n\n**Normalize bioactivity units to nM:** `bash uv run scripts\u002Fchembl_api.py\nactivity --filter target_chembl_id=CHEMBL203 standard_type=IC50 --limit 5\n--normalize --output \u002Ftmp\u002Fegfr_normalized.json`\n\n> **Important**: Bioactivity values come in various units (nM, µM, pM). Use\n> `--normalize` to convert all values to nM for consistent comparison. Each\n> record will include `normalized_value_nM` and `normalization_note`.\n\n--------------------------------------------------------------------------------\n\n### 5. Drug Information\n\n**Fetch drug details:** `bash uv run scripts\u002Fchembl_api.py drug --id CHEMBL25\n--output \u002Ftmp\u002Fdrug.json`\n\n**Drug indications:** `bash uv run scripts\u002Fchembl_api.py drug_indication\n--filter molecule_chembl_id=CHEMBL25 --limit 10 --output \u002Ftmp\u002Findications.json`\n\n**Filter indications by phase:** `bash uv run scripts\u002Fchembl_api.py\ndrug_indication --filter molecule_chembl_id=CHEMBL25 max_phase_for_ind=4.0\n--limit 10 --output \u002Ftmp\u002Fapproved_indications.json`\n\n**Drug warnings:** `bash uv run scripts\u002Fchembl_api.py drug_warning --limit 5\n--output \u002Ftmp\u002Fwarnings.json`\n\n**Mechanisms of action:** `bash uv run scripts\u002Fchembl_api.py mechanism --filter\nmolecule_chembl_id=CHEMBL25 --limit 5 --output \u002Ftmp\u002Fmech.json`\n\n--------------------------------------------------------------------------------\n\n### 6. Structure-Based Searches\n\n> **Note**: Both similarity and substructure searches are performed\n> **server-side** on ChEMBL's pre-indexed database. They do not require a local\n> RDKit installation.\n\n**Similarity search (SMILES + threshold):** `bash uv run scripts\u002Fchembl_api.py\nsimilarity --smiles \"CC(=O)Oc1ccccc1C(=O)O\" --similarity 85 --limit 5 --output\n\u002Ftmp\u002Fsimilar.json`\n\n**Substructure search (SMILES):** `bash uv run scripts\u002Fchembl_api.py\nsubstructure --smiles \"c1ccccc1\" --limit 5 --output \u002Ftmp\u002Fsubstruct.json`\n\n--------------------------------------------------------------------------------\n\n### 7. Compound Image\n\nDownload a 2D structure image (SVG by default, scalable for publication):\n\n```bash\nuv run scripts\u002Fchembl_api.py image --id CHEMBL25 --output \u002Ftmp\u002Fchembl25.svg\n```\n\n*Options:*\n\n-   `--dimensions`: Image size in pixels (max 500, default 500).\n-   `--engine`: Rendering engine (default: rdkit).\n-   `--img_format`: Output format — `svg` (default, vector) or `png` (raster).\n\n--------------------------------------------------------------------------------\n\n### 8. Cross-Referencing with Other Databases\n\nChEMBL integrates with UniProt, Ensembl, PubChem, and other databases. Common\ncross-referencing patterns:\n\n**Find a ChEMBL target from a UniProt accession:** `bash uv run\nscripts\u002Fchembl_api.py target --filter target_components__accession=P00533\n--limit 5 --output \u002Ftmp\u002Funiprot_target.json`\n\n**Resolve any ChEMBL ID to its entity type:** `bash uv run scripts\u002Fchembl_api.py\nchembl_id_lookup --id CHEMBL203 --output \u002Ftmp\u002Flookup.json`\n\n**Look up cross-reference sources:** `bash uv run scripts\u002Fchembl_api.py\nxref_source --limit 10 --output \u002Ftmp\u002Fxrefs.json`\n\n> **Tip**: Use the `target_component` endpoint to find UniProt accessions, gene\n> names, and protein sequences for any ChEMBL target.\n\n--------------------------------------------------------------------------------\n\n### 9. Pagination\n\nAll list endpoints support `--limit` and `--offset` for pagination:\n\n```bash\n# First page: 2 results starting at offset 0\nuv run scripts\u002Fchembl_api.py molecule --limit 2 --offset 0 --output \u002Ftmp\u002Fpage1.json\n\n# Second page: next 2 results starting at offset 2\nuv run scripts\u002Fchembl_api.py molecule --limit 2 --offset 2 --output \u002Ftmp\u002Fpage2.json\n```\n\nThe response includes `page_meta` with `total_count`, `limit`, `offset`, `next`,\nand `previous` links. Use successive `--offset` values to page through large\nresult sets.\n\n--------------------------------------------------------------------------------\n\n### 10. Other Endpoints\n\nAll remaining endpoints follow the same pattern:\n\n```bash\nuv run scripts\u002Fchembl_api.py \u003Csubcommand> --output \u003Cfile> [--id ID | --ids ID1;ID2 | --search QUERY] [--limit N] [--offset N] [--filter KEY=VAL ...]\n```\n\n**Key subcommands at a glance:**\n\n-   `molecule` (searchable: true): Molecules\u002Fcompounds — the primary entry point\n-   `target` (searchable: true): Drug targets (proteins, organisms, etc.)\n-   `activity` (searchable: true): Bioactivity data (IC50, Ki, EC50, etc.)\n-   `drug` (searchable: false): Approved drugs\n-   `mechanism` (searchable: false): Mechanisms of action\n-   `assay` (searchable: true): Assay descriptions\n-   `similarity` (searchable: false): Similarity search (special)\n-   `substructure` (searchable: false): Substructure search (special)\n-   `image` (searchable: false): Compound image download (special)\n\n**Full subcommand list:**\n\n-   `activity_supp` (searchable: false): Supplementary activity data\n-   `assay_class` (searchable: false): Assay classifications\n-   `atc_class` (searchable: false): ATC drug classifications\n-   `binding_site` (searchable: false): Binding site information\n-   `biotherapeutic` (searchable: false): Biotherapeutic molecules\n-   `cell_line` (searchable: false): Cell line details\n-   `chembl_id_lookup` (searchable: true): ChEMBL ID resolution\n-   `chembl_release` (searchable: false): Database release info\n-   `compound_record` (searchable: false): Compound records\n-   `compound_structural_alert` (searchable: false): Structural alerts\n-   `document` (searchable: true): Literature documents\n-   `document_similarity` (searchable: false): Document similarity\n-   `drug_indication` (searchable: false): Drug indications\n-   `drug_warning` (searchable: false): Drug safety warnings\n-   `go_slim` (searchable: false): GO slim terms\n-   `metabolism` (searchable: false): Metabolism data\n-   `molecule_form` (searchable: false): Molecule forms (salts\u002Fparents)\n-   `organism` (searchable: false): Organisms\n-   `protein_classification` (searchable: true): Protein classifications\n-   `source` (searchable: false): Data sources\n-   `target_component` (searchable: false): Target protein components\n-   `target_relation` (searchable: false): Target relationships\n-   `tissue` (searchable: false): Tissue types\n-   `xref_source` (searchable: false): Cross-reference sources\n-   `status` (searchable: false): API status check (special)\n\n## Common Options\n\n-   `--output FILE`: **Required.** Output file path for JSON results.\n-   `--id ID`: Fetch a single record by ID.\n-   `--ids ID1;ID2;...`: Batch fetch multiple records.\n-   `--search QUERY`: Free-text search (only for searchable endpoints, marked\n    ✓).\n-   `--limit N`: Max results to return (default: 5).\n-   `--offset N`: Pagination offset.\n-   `--filter KEY=VAL`: Filter parameters (can specify multiple).\n-   `--normalize`: (activity only) Normalize values to nM.\n-   `--dl_format sdf|mol`: (molecule only) Download structure file.\n\n## Reference\n\n-   **API Endpoints Reference**: See\n    [references\u002Fapi_endpoints.md](references\u002Fapi_endpoints.md) for the full list\n    of endpoints and filter operators.\n\n## Workflow\n\n1.  Use `status --output \u002Ftmp\u002Fstatus.json` to verify the API is available.\n2.  Search for targets, molecules, or drugs using the relevant subcommand.\n3.  Read the output JSON file to extract IDs and data.\n4.  Use IDs from search results to fetch detailed records.\n5.  Query `activity` with filters to get bioactivity data for targets\u002Fmolecules.\n    Use `--normalize` when comparing values across studies.\n6.  Use `similarity` or `substructure` for server-side structure-based queries.\n7.  Download compound images with `image` or structure files with `molecule\n    --dl_format sdf`.\n8.  Use `target --filter target_components__accession=\u003CUniProt>` to cross-\n    reference with UniProt.\n","# ChEMBL Database Query\n\n## Prerequisites\n\n1.  **`uv`**: Read the `uv` skill and follow its Setup instructions to ensure\n    `uv` is installed and on PATH.\n2.  **User Notification**: If .licenses\u002Fchembl_database_LICENSE.txt does not\n    already exist in the workspace root directory then (1) prominently notify\n    the user to check the terms at\n    https:\u002F\u002Fchembl.gitbook.io\u002Fchembl-interface-documentation\u002Fabout, then (2)\n    create the file recording the notification text and timestamp.\n\n## Core Rules\n\n-   [!IMPORTANT] **Use the Utility Scripts**: You MUST ALWAYS use the provided\n    utility script `scripts\u002Fchembl_api.py` for all ChEMBL API interactions,\n    including checking status. NEVER use `curl` or custom Python requests to\n    query the ChEMBL API directly. This ensures rate limit is enfoced and also\n    retries on network errors.\n\n-   **Output to File (Required)**: The `--output` flag is **required** for every\n    subcommand. All JSON results are written to the specified file. After\n    running the command, read the output file with jq or your own code to\n    extract the data. List results are typically wrapped in a JSON array keyed\n    by the endpoint name (e.g., `molecules`, `activities`).\n\n-   **Notification**: If this skill is used, ensure this is mentioned in the\n    output.\n\n## Utility Script\n\nAll ChEMBL API queries use one script with subcommands:\n\n```bash\nuv run scripts\u002Fchembl_api.py \u003Csubcommand> --output \u003Cfile> [options]\n```\n\n--------------------------------------------------------------------------------\n\n### 1. Check API Status\n\n```bash\nuv run scripts\u002Fchembl_api.py status --output \u002Ftmp\u002Fstatus.json\n```\n\n--------------------------------------------------------------------------------\n\n### 2. Molecule Queries\n\n**Fetch by ChEMBL ID:** `bash uv run scripts\u002Fchembl_api.py molecule --id\nCHEMBL25 --output \u002Ftmp\u002Fmol.json`\n\n**Search by name:** `bash uv run scripts\u002Fchembl_api.py molecule --search\n\"aspirin\" --limit 3 --output \u002Ftmp\u002Fmol_search.json`\n\n**Batch fetch:** `bash uv run scripts\u002Fchembl_api.py molecule --ids\n\"CHEMBL25;CHEMBL1642\" --limit 10 --output \u002Ftmp\u002Fmol_batch.json`\n\n**Filter by properties:** `bash uv run scripts\u002Fchembl_api.py molecule --filter\nmolecule_properties__mw_freebase__lte=500 --limit 5 --output\n\u002Ftmp\u002Fmol_filter.json`\n\n**Filter by range:** `bash uv run scripts\u002Fchembl_api.py molecule --filter\nmolecule_properties__mw_freebase__range=150,200 --limit 5 --output\n\u002Ftmp\u002Fmol_range.json`\n\n**Download SDF structure file:** `bash uv run scripts\u002Fchembl_api.py molecule\n--id CHEMBL25 --dl_format sdf --output \u002Ftmp\u002Faspirin.sdf`\n\n> **Tip**: SDF\u002FMOL files can be passed directly to tools like PyMOL or RDKit for\n> 3D visualization and analysis.\n\n--------------------------------------------------------------------------------\n\n### 3. Target Queries\n\n**Search for targets:** `bash uv run scripts\u002Fchembl_api.py target --search\n\"EGFR\" --limit 5 --output \u002Ftmp\u002Ftargets.json`\n\n**Fetch by ID:** `bash uv run scripts\u002Fchembl_api.py target --id CHEMBL203\n--output \u002Ftmp\u002Fegfr.json`\n\n--------------------------------------------------------------------------------\n\n### 4. Bioactivity Data\n\n**Fetch activity by ID:** `bash uv run scripts\u002Fchembl_api.py activity --id 31863\n--output \u002Ftmp\u002Fact.json`\n\n**Search activities:** `bash uv run scripts\u002Fchembl_api.py activity --search\n\"EGFR\" --limit 5 --output \u002Ftmp\u002Fact_search.json`\n\n**Filter activities for a target:** `bash uv run scripts\u002Fchembl_api.py activity\n--filter target_chembl_id=CHEMBL203 standard_type=IC50 --limit 10 --output\n\u002Ftmp\u002Fegfr_ic50.json`\n\n**Normalize bioactivity units to nM:** `bash uv run scripts\u002Fchembl_api.py\nactivity --filter target_chembl_id=CHEMBL203 standard_type=IC50 --limit 5\n--normalize --output \u002Ftmp\u002Fegfr_normalized.json`\n\n> **Important**: Bioactivity values come in various units (nM, µM, pM). Use\n> `--normalize` to convert all values to nM for consistent comparison. Each\n> record will include `normalized_value_nM` and `normalization_note`.\n\n--------------------------------------------------------------------------------\n\n### 5. Drug Information\n\n**Fetch drug details:** `bash uv run scripts\u002Fchembl_api.py drug --id CHEMBL25\n--output \u002Ftmp\u002Fdrug.json`\n\n**Drug indications:** `bash uv run scripts\u002Fchembl_api.py drug_indication\n--filter molecule_chembl_id=CHEMBL25 --limit 10 --output \u002Ftmp\u002Findications.json`\n\n**Filter indications by phase:** `bash uv run scripts\u002Fchembl_api.py\ndrug_indication --filter molecule_chembl_id=CHEMBL25 max_phase_for_ind=4.0\n--limit 10 --output \u002Ftmp\u002Fapproved_indications.json`\n\n**Drug warnings:** `bash uv run scripts\u002Fchembl_api.py drug_warning --limit 5\n--output \u002Ftmp\u002Fwarnings.json`\n\n**Mechanisms of action:** `bash uv run scripts\u002Fchembl_api.py mechanism --filter\nmolecule_chembl_id=CHEMBL25 --limit 5 --output \u002Ftmp\u002Fmech.json`\n\n--------------------------------------------------------------------------------\n\n### 6. Structure-Based Searches\n\n> **Note**: Both similarity and substructure searches are performed\n> **server-side** on ChEMBL's pre-indexed database. They do not require a local\n> RDKit installation.\n\n**Similarity search (SMILES + threshold):** `bash uv run scripts\u002Fchembl_api.py\nsimilarity --smiles \"CC(=O)Oc1ccccc1C(=O)O\" --similarity 85 --limit 5 --output\n\u002Ftmp\u002Fsimilar.json`\n\n**Substructure search (SMILES):** `bash uv run scripts\u002Fchembl_api.py\nsubstructure --smiles \"c1ccccc1\" --limit 5 --output \u002Ftmp\u002Fsubstruct.json`\n\n--------------------------------------------------------------------------------\n\n### 7. Compound Image\n\nDownload a 2D structure image (SVG by default, scalable for publication):\n\n```bash\nuv run scripts\u002Fchembl_api.py image --id CHEMBL25 --output \u002Ftmp\u002Fchembl25.svg\n```\n\n*Options:*\n\n-   `--dimensions`: Image size in pixels (max 500, default 500).\n-   `--engine`: Rendering engine (default: rdkit).\n-   `--img_format`: Output format — `svg` (default, vector) or `png` (raster).\n\n--------------------------------------------------------------------------------\n\n### 8. Cross-Referencing with Other Databases\n\nChEMBL integrates with UniProt, Ensembl, PubChem, and other databases. Common\ncross-referencing patterns:\n\n**Find a ChEMBL target from a UniProt accession:** `bash uv run\nscripts\u002Fchembl_api.py target --filter target_components__accession=P00533\n--limit 5 --output \u002Ftmp\u002Funiprot_target.json`\n\n**Resolve any ChEMBL ID to its entity type:** `bash uv run scripts\u002Fchembl_api.py\nchembl_id_lookup --id CHEMBL203 --output \u002Ftmp\u002Flookup.json`\n\n**Look up cross-reference sources:** `bash uv run scripts\u002Fchembl_api.py\nxref_source --limit 10 --output \u002Ftmp\u002Fxrefs.json`\n\n> **Tip**: Use the `target_component` endpoint to find UniProt accessions, gene\n> names, and protein sequences for any ChEMBL target.\n\n--------------------------------------------------------------------------------\n\n### 9. Pagination\n\nAll list endpoints support `--limit` and `--offset` for pagination:\n\n```bash\n# First page: 2 results starting at offset 0\nuv run scripts\u002Fchembl_api.py molecule --limit 2 --offset 0 --output \u002Ftmp\u002Fpage1.json\n\n# Second page: next 2 results starting at offset 2\nuv run scripts\u002Fchembl_api.py molecule --limit 2 --offset 2 --output \u002Ftmp\u002Fpage2.json\n```\n\nThe response includes `page_meta` with `total_count`, `limit`, `offset`, `next`,\nand `previous` links. Use successive `--offset` values to page through large\nresult sets.\n\n--------------------------------------------------------------------------------\n\n### 10. Other Endpoints\n\nAll remaining endpoints follow the same pattern:\n\n```bash\nuv run scripts\u002Fchembl_api.py \u003Csubcommand> --output \u003Cfile> [--id ID | --ids ID1;ID2 | --search QUERY] [--limit N] [--offset N] [--filter KEY=VAL ...]\n```\n\n**Key subcommands at a glance:**\n\n-   `molecule` (searchable: true): Molecules\u002Fcompounds — the primary entry point\n-   `target` (searchable: true): Drug targets (proteins, organisms, etc.)\n-   `activity` (searchable: true): Bioactivity data (IC50, Ki, EC50, etc.)\n-   `drug` (searchable: false): Approved drugs\n-   `mechanism` (searchable: false): Mechanisms of action\n-   `assay` (searchable: true): Assay descriptions\n-   `similarity` (searchable: false): Similarity search (special)\n-   `substructure` (searchable: false): Substructure search (special)\n-   `image` (searchable: false): Compound image download (special)\n\n**Full subcommand list:**\n\n-   `activity_supp` (searchable: false): Supplementary activity data\n-   `assay_class` (searchable: false): Assay classifications\n-   `atc_class` (searchable: false): ATC drug classifications\n-   `binding_site` (searchable: false): Binding site information\n-   `biotherapeutic` (searchable: false): Biotherapeutic molecules\n-   `cell_line` (searchable: false): Cell line details\n-   `chembl_id_lookup` (searchable: true): ChEMBL ID resolution\n-   `chembl_release` (searchable: false): Database release info\n-   `compound_record` (searchable: false): Compound records\n-   `compound_structural_alert` (searchable: false): Structural alerts\n-   `document` (searchable: true): Literature documents\n-   `document_similarity` (searchable: false): Document similarity\n-   `drug_indication` (searchable: false): Drug indications\n-   `drug_warning` (searchable: false): Drug safety warnings\n-   `go_slim` (searchable: false): GO slim terms\n-   `metabolism` (searchable: false): Metabolism data\n-   `molecule_form` (searchable: false): Molecule forms (salts\u002Fparents)\n-   `organism` (searchable: false): Organisms\n-   `protein_classification` (searchable: true): Protein classifications\n-   `source` (searchable: false): Data sources\n-   `target_component` (searchable: false): Target protein components\n-   `target_relation` (searchable: false): Target relationships\n-   `tissue` (searchable: false): Tissue types\n-   `xref_source` (searchable: false): Cross-reference sources\n-   `status` (searchable: false): API status check (special)\n\n## Common Options\n\n-   `--output FILE`: **Required.** Output file path for JSON results.\n-   `--id ID`: Fetch a single record by ID.\n-   `--ids ID1;ID2;...`: Batch fetch multiple records.\n-   `--search QUERY`: Free-text search (only for searchable endpoints, marked\n    ✓).\n-   `--limit N`: Max results to return (default: 5).\n-   `--offset N`: Pagination offset.\n-   `--filter KEY=VAL`: Filter parameters (can specify multiple).\n-   `--normalize`: (activity only) Normalize values to nM.\n-   `--dl_format sdf|mol`: (molecule only) Download structure file.\n\n## Reference\n\n-   **API Endpoints Reference**: See\n    [references\u002Fapi_endpoints.md](references\u002Fapi_endpoints.md) for the full list\n    of endpoints and filter operators.\n\n## Workflow\n\n1.  Use `status --output \u002Ftmp\u002Fstatus.json` to verify the API is available.\n2.  Search for targets, molecules, or drugs using the relevant subcommand.\n3.  Read the output JSON file to extract IDs and data.\n4.  Use IDs from search results to fetch detailed records.\n5.  Query `activity` with filters to get bioactivity data for targets\u002Fmolecules.\n    Use `--normalize` when comparing values across studies.\n6.  Use `similarity` or `substructure` for server-side structure-based queries.\n7.  Download compound images with `image` or structure files with `molecule\n    --dl_format sdf`.\n8.  Use `target --filter target_components__accession=\u003CUniProt>` to cross-\n    reference with UniProt.\n",{"name":5,"description":7},"main","e71245365df78e06cd166602744bf2491f79910e","research-skills-hub\u002Fscience-skills\u002Fchembl_database",0,"https:\u002F\u002Fgithub.com\u002Fpengqianhan\u002FAI-Human-Research-OS","https:\u002F\u002Fpengqianhan.github.io\u002FAI-Human-Research-OS\u002F","https:\u002F\u002Fgithub.com\u002Fpengqianhan","Ph.D. candidate of The University of Auckland, New Zealand","2026-11-14 18:08:16",{"source":8,"skillName":5,"commands":34,"prompt":44,"zipAvailable":45},[35,38,41],{"tool":36,"command":37},"npx","npx skills add pengqianhan\u002FAI-Human-Research-OS --skill chembl-database",{"tool":39,"command":40},"bunx","bunx skills add pengqianhan\u002FAI-Human-Research-OS --skill chembl-database",{"tool":42,"command":43},"pnpm","pnpm dlx skills add pengqianhan\u002FAI-Human-Research-OS --skill chembl-database","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fpengqianhan\u002FAI-Human-Research-OS\u002Fblob\u002Fmain\u002Fresearch-skills-hub\u002Fscience-skills\u002Fchembl_database\u002FSKILL.md",true,[47,53,57],{"path":48,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":51,"sourceHtmlUrl":52},"references\u002Fapi_endpoints.md","REFERENCE","参考文档",2832,"https:\u002F\u002Fgithub.com\u002Fpengqianhan\u002FAI-Human-Research-OS\u002Fblob\u002Fmain\u002Fresearch-skills-hub\u002Fscience-skills\u002Fchembl_database\u002Freferences\u002Fapi_endpoints.md",{"path":54,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":55,"sourceHtmlUrl":56},"references\u002Fcitation.bib",3639,"https:\u002F\u002Fgithub.com\u002Fpengqianhan\u002FAI-Human-Research-OS\u002Fblob\u002Fmain\u002Fresearch-skills-hub\u002Fscience-skills\u002Fchembl_database\u002Freferences\u002Fcitation.bib",{"path":58,"resourceType":59,"resourceTypeDesc":60,"sizeBytes":61,"sourceHtmlUrl":62},"scripts\u002Fchembl_api.py","SCRIPT","脚本",18842,"https:\u002F\u002Fgithub.com\u002Fpengqianhan\u002FAI-Human-Research-OS\u002Fblob\u002Fmain\u002Fresearch-skills-hub\u002Fscience-skills\u002Fchembl_database\u002Fscripts\u002Fchembl_api.py",[64,71,78,85,92,99],{"skillNo":65,"name":66,"nameZh":6,"description":67,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":68,"categories":69,"keywords":70,"publishedAt":19},"01M74MWYTHT498SVMN823896T7","workflow-skill-creator","Distills a completed user workflow or interaction into a reusable agent skill. Use when the user asks to turn their workflow, interaction, or multi-step process into a skill, or when they say \"make this a skill\", \"create a skill from what we just did\", \"package this workflow\" or similar. Do not use for creating skills from scratch without an existing workflow (use a generic skill-creator for that).","https:\u002F\u002Fgithub.com\u002Fpengqianhan\u002FAI-Human-Research-OS\u002Fblob\u002Fmain\u002Fresearch-skills-hub\u002Fscience-skills\u002Fworkflow_skill_creator\u002FSKILL.md",[],[],{"skillNo":72,"name":73,"nameZh":6,"description":74,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":75,"categories":76,"keywords":77,"publishedAt":19},"01M74MWWVCFZ8HQS8840F1V1FT","uv","Checks whether the uv Python package manager is installed and installs it if missing. Ensures uv is on PATH. Use when another skill requires uv as a prerequisite.","https:\u002F\u002Fgithub.com\u002Fpengqianhan\u002FAI-Human-Research-OS\u002Fblob\u002Fmain\u002Fresearch-skills-hub\u002Fscience-skills\u002Fuv\u002FSKILL.md",[],[],{"skillNo":79,"name":80,"nameZh":6,"description":81,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":82,"categories":83,"keywords":84,"publishedAt":19},"01M74MWRH5BTSWZ2C5PCTD5FV9","uniprot-database","Access protein metadata, function, taxonomy, and sequences across UniProtKB, UniParc, and UniRef. Use when searching for proteins, mapping identifiers, or retrieving functional annotations and publications. Don't use for sequence alignment, protein folding, or sequence similarity search (use specialized skills for those tasks).","https:\u002F\u002Fgithub.com\u002Fpengqianhan\u002FAI-Human-Research-OS\u002Fblob\u002Fmain\u002Fresearch-skills-hub\u002Fscience-skills\u002Funiprot_database\u002FSKILL.md",[],[],{"skillNo":86,"name":87,"nameZh":6,"description":88,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":89,"categories":90,"keywords":91,"publishedAt":19},"01M74MWN1D3ER9F1FZPWH8HQC1","unibind-database","Queries the UniBind database for experimentally validated transcription factor (TF) binding sites. Use when retrieving direct TF-DNA interaction datasets, downloading binding site coordinates (BED\u002FFASTA) for local analysis, or listing available datasets by species, cell line, or TF name. Don't use to query specific intervals, locations, genes, motif models or expression data.","https:\u002F\u002Fgithub.com\u002Fpengqianhan\u002FAI-Human-Research-OS\u002Fblob\u002Fmain\u002Fresearch-skills-hub\u002Fscience-skills\u002Funibind_database\u002FSKILL.md",[],[],{"skillNo":93,"name":94,"nameZh":6,"description":95,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":96,"categories":97,"keywords":98,"publishedAt":19},"01M74MWHHB5QZY3NR2FYA1EK4N","ucsc-conservation-and-tfbs","Fetch Evolutionary Conservation scores (phyloP, phastCons) and Transcription Factor Binding Sites (TFBS) from the UCSC Genome Browser. Use when analyzing whether genomic variants or regions are evolutionarily conserved, functionally important, or bounded by TF regulators across major projects (ENCODE, JASPAR, ReMap).","https:\u002F\u002Fgithub.com\u002Fpengqianhan\u002FAI-Human-Research-OS\u002Fblob\u002Fmain\u002Fresearch-skills-hub\u002Fscience-skills\u002Fucsc_conservation_and_tfbs\u002FSKILL.md",[],[],{"skillNo":100,"name":101,"nameZh":6,"description":102,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":103,"categories":104,"keywords":105,"publishedAt":19},"01M74MWERYHSY87P21FDMVE6BA","string-database","Query the STRING database for protein-protein interactions (PPIs), functional enrichment, and homology. Use when the user asks about interactions between specific proteins, interaction evidence, confidence scores, protein interaction partners, or pathway enrichments.","https:\u002F\u002Fgithub.com\u002Fpengqianhan\u002FAI-Human-Research-OS\u002Fblob\u002Fmain\u002Fresearch-skills-hub\u002Fscience-skills\u002Fstring_database\u002FSKILL.md",[],[]]