tooluniverse-chemical-compound-retrieval

Retrieve chemical compound data from PubChem and ChEMBL with disambiguation, cross-referencing, and stereochemistry handling. Use for resolving compound names to SMILES/InChI/CID/ChEMBL IDs (including OPSIN deterministic IUPAC-name-to-structure parsing), fetching molecular properties, distinguishing

By mims-harvard · 403 installs

npx skills add mims-harvard/tooluniverse --skill tooluniverse-chemical-compound-retrieval

Source repository · Upstream listing

Chemical Compound Information Retrieval Retrieve comprehensive chemical compound data with proper disambiguation and cross database validation. LOOK UP DON'T GUESS : Never assume a CID, ChEMBL ID, or molecular property value. Always retrieve from PubChem/ChEMBL. English first : Always use English compound names in tool calls. Respond in user's language. Domain Reasoning: Disambiguation "Aspirin" = one compound. "Vitamin D" = multiple forms (D2/D3/active metabolite). For generic class names (steroids, vitamins, acids), present candidates and confirm before proceeding. Workflow Phase 1: Disambiguation Verify: CID + ChEMBL ID + canonical SMILES + stereochemistry + salt forms. Phase 2: Data Retrieval PubChem : PubChem get compound properties by CID , PubChemBioAssay get assay summary , PubChemTox get acute effects , PubChem get compound 2D image by CID ChEMBL : ChEMBL get compound record activities , ChEMBL get molecule targets , ChEMBL get assay activities Optional : PubChem get associated patents by CID , PubChem search compounds by similarity Phase 3: Report Compound Profile with: Identity (CID, ChEMBL ID, IUPAC, SMILES), Chemical Properties (MW, LogP, HBD, HBA, PSA, Lipinski), Bioactivity (targets, IC50/Ki), Drug Info (if approved), Data Sources. Fallback Chains Primary Fallback PubChem name lookup (systematic name) OPSIN name to structure → SMILES/InChIKey → PubChem get CID by SMILES PubChem name lookup ChEMBL search → SMILES → PubChem get CID by SMILES ChEMBL bioactivity PubChem bioassay summary Drug label Note "unavailable" Evidence Grading Grade Criteria Confirmed CID + ChEMBL cross match, InChI/SMILES agree Probable CID found, partial ChEMBL match Uncertain Single database only, or multiple CIDs Unverified No cross reference, single source Bioactivity : ChEMBL PubChem BioAssay for curated data. IC50/Ki < 100nM = potent, 100nM 1uM = moderate, 10uM = weak. Lipinski violations reduce oral bioavailability but don't disqualify. SMILES Verification Always verify novel SMILES: python3 src/tooluniverse/tools/smiles verifier.py smiles "SMILES STRING" . Invalid SMILES produce wrong results or cryptic errors. Tool Reference PubChem : PubChem get CID by compound name , PubChem get CID by SMILES , PubChem get compound properties by CID , PubChem get compound 2D image by CID , PubChemBioAssay get assay summary , PubChemTox get acute effects , PubChem get associated patents by CID , PubChem search compounds by similarity , PubChem search compounds by substructure ChEMBL : ChEMBL search drugs , ChEMBL get molecule , ChEMBL get activity , ChEMBL get target , ChEMBL search targets , ChEMBL search assays Name parsing : OPSIN name to structure (param name ) — deterministic IUPAC/systematic name → SMILES/InChI/InChIKey parser; the go to for resolving a systematic name to structure without a DB round trip. Trade/trivial names return parsed=false (use PubChem name lookup for those).