tooluniverse-chemical-compound-retrieval

Retrieves chemical compound profiles from PubChem and ChEMBL with cross-database validation.

Updated Mar 13, 2026
One-click install
npx skills add https://github.com/matt-grain/pharma-catalyst --skill tooluniverse-chemical-compound-retrieval-matt-grain
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: tooluniverse-chemical-compound-retrieval
Source: https://github.com/matt-grain/pharma-catalyst/tree/main/.claude/skills/tooluniverse-chemical-compound-retrieval
Command: npx skills add https://github.com/matt-grain/pharma-catalyst --skill tooluniverse-chemical-compound-retrieval-matt-grain

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires tooluniverse.

What problem does it solve? Looking up chemical compound data across PubChem and ChEMBL manually is slow and error-prone, especially when resolving ambiguous names, cross-referencing identifiers, and assembling complete profiles with properties, bioactivity, and drug information. ## Core Features & Use Cases - Identity Disambiguation: Resolves compounds by name, SMILES, InChI, or CID, cross-references PubChem CIDs with ChEMBL IDs, and handles naming collisions and salt forms. - Comprehensive Compound Profiles: Retrieves molecular descriptors, Lipinski drug-likeness assessment, bioactivity data, protein targets, drug labels, patents, and similar compounds, then formats them into a structured report with a data quality tier. - Fallback Handling: Automatically falls back from PubChem to ChEMBL (and vice versa) when lookups fail, and marks missing data explicitly instead of omitting sections. - Use Case: A medicinal chemist asks "What proteins does gefitinib target?" and receives a full compound profile with ChEMBL bioactivity data, target list, and drug-likeness metrics. ## Quick Start Ask the assistant to retrieve a complete compound profile for a drug or chemical by name, SMILES, or PubChem CID, such as requesting a full profile of metformin.

Frequently Asked Questions about tooluniverse-chemical-compound-retrieval

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I look up a chemical compound by name in PubChem using Python?▼

Use the ToolUniverse library's PubChem_get_CID_by_compound_name tool to resolve a compound name to its PubChem CID, then call PubChem_get_compound_properties_by_CID to retrieve molecular formula, weight, LogP, and SMILES.

How to cross-reference PubChem CID with ChEMBL ID?▼

Search ChEMBL by compound name using ChEMBL_search_compounds and extract the molecule_chembl_id from the top result. With the ChEMBL ID you can then fetch bioactivity data, protein targets, and assay metadata.

Can I search PubChem compounds by SMILES structure?▼

Yes, PubChem_get_CID_by_SMILES converts a SMILES string to a CID. You can also run PubChem_search_compounds_by_similarity with a similarity threshold or PubChem_search_compounds_by_substructure for structural queries.

What happens when a compound is not found in PubChem?▼

The workflow falls back to ChEMBL_search_compounds, extracts the SMILES from the result, and resolves the CID via PubChem_get_CID_by_SMILES. If all lookups fail, it suggests verifying spelling or trying synonyms.

Does this handle compounds with no bioactivity data?▼

Yes, the profile report always includes a bioactivity section, displaying "No bioactivity screening data available" when none exists. Missing ChEMBL IDs are noted as N/A and failed API calls are marked as retrieval failed.