pubchem-database

Query PubChem by name, CID, or SMILES to retrieve compound properties and bioactivities.

4|Updated Feb 22, 2026
One-click install
npx skills add https://github.com/GeneralReasoning/env-skillsbench --skill pubchem-database-generalreasoning
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: pubchem-database
Source: https://github.com/GeneralReasoning/env-skillsbench/tree/main/find-topk-similiar-chemicals/environment/skills/pubchem-database
Command: npx skills add https://github.com/GeneralReasoning/env-skillsbench --skill pubchem-database-generalreasoning

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires pubchempy, requests, and includes scripts (resource) and references (resource) components.

What problem does it solve?

PubChem is a vast chemical database; this Skill provides programmatic access to search by name, CID, or SMILES, and retrieve properties, perform similarity/substructure searches, and access bioactivity data via PUG-REST and PubChemPy.

Core Features & Use Cases

  • Search by name, CID, or SMILES and retrieve key properties (MW, formula, XLogP, TPSA, H-bond donors/acceptors, etc.).
  • Perform similarity and substructure searches to identify related compounds and motifs.
  • Access bioactivity data and assay annotations to support target discovery and lead prioritization.
  • Use cases: in drug discovery, identify analogs of a lead compound and compare their properties and activities.

Quick Start

Run a sample query to fetch aspirin's properties and print key fields.

Frequently Asked Questions about pubchem-database

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

FAQPage Schema
How do I retrieve compound properties from PubChem using a SMILES string?

You can retrieve compound properties by querying PubChem via PUG-REST using PubChemPy, passing a SMILES string to fetch molecular weight, formula, XLogP, TPSA, and H-bond donor/acceptor counts.

Can I perform a substructure search in PubChem to find related chemical motifs?

Yes, you can perform substructure and similarity searches against PubChem via PUG-REST, allowing you to identify related compounds and chemical motifs from a query structure using batch-friendly Python scripts.

How do I access PubChem bioactivity data for drug discovery target analysis?

Access PubChem bioactivity data and assay annotations by querying through PUG-REST, retrieving target discovery and lead prioritization information to support cheminformatics workflows.

What's the best way to batch query PubChem for multiple compound CIDs?

Batch querying PubChem for multiple CIDs is handled via rate-limited, batch-friendly utilities using PubChemPy and PUG-REST, parsing and annotating compound data programmatically with Python scripts.

Does querying PubChem with PUG-REST require managing API rate limits?

Yes, this approach relies on rate-limited utilities via PUG-REST and PubChemPy to manage request volumes when fetching compound data, properties, and bioactivities programmatically.

Can I search PubChem by compound name instead of CID or SMILES?

Yes, you can search PubChem by compound name, CID, or SMILES interchangeably using PUG-REST via PubChemPy, retrieving key molecular properties and bioactivity annotations for each matched compound.