pubchem-database

Retrieve PubChem compound records, properties, and bioactivity data via REST queries.

21|2|Updated Dec 8, 2025
One-click install
npx skills add https://github.com/silverstein/claude-scientific-skills-desktop --skill pubchem-database-silverstein
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: pubchem-database
Source: https://github.com/silverstein/claude-scientific-skills-desktop/tree/main/corpus/pubchem-database
Command: npx skills add https://github.com/silverstein/claude-scientific-skills-desktop --skill pubchem-database-silverstein

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

PubChem data retrieval can be slow and error-prone when you need consistent molecule lookup, property extraction, structure searching, and bioactivity reporting across many compounds.

Core Features & Use Cases

  • Compound lookup by identifiers: Search by name, CID, SMILES, InChI, or molecular formula to reliably retrieve the right compound record.
  • Property and structure intelligence: Fetch key physicochemical properties (e.g., MW, XLogP, TPSA, H-bond counts) and convert among CID/SMILES/InChI/identifiers for downstream cheminformatics.
  • Structure-based discovery: Run similarity and substructure searches to find related or motif-containing compounds for candidate triage.
  • Bioactivity workflows: Retrieve assay summaries and compile active/inactive/inconclusive bioactivity outcomes for targets and screening contexts.

Quick Start

Use the pubchem-database skill to retrieve properties and key identifiers for aspirin by asking it to return molecular formula, molecular weight, canonical SMILES, XLogP, TPSA, and H-bond donor/acceptor counts.

Frequently Asked Questions about pubchem-database

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

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

To retrieve PubChem properties, query the database by name, CID, SMILES, or InChI to fetch molecular weight, XLogP, TPSA, and H-bond counts for downstream cheminformatics workflows.

Can I run substructure and similarity searches on PubChem to find related molecules?

Yes, you can run substructure and similarity searches on PubChem to find related or motif-containing compounds, enabling effective candidate triage for virtual screening tasks.

How do I compile bioactivity assay outcomes for specific targets and compounds from PubChem?

Compile bioactivity outcomes from PubChem by retrieving assay summaries and aggregating active, inactive, and inconclusive screening results for specific targets and compounds.

Does PubChemPy support rate-limit-aware querying for batch compound identifier resolution?

PubChemPy supports rate-limit-aware querying to ensure reliable compound identifier resolution and conversion among CID, SMILES, and InChI without exceeding PubChem REST request limits.

What is the best way to convert between CID, SMILES, and InChI identifiers for cheminformatics tasks?

The best way to convert identifiers is using PubChemPy-compatible querying to reliably map between CID, SMILES, and InChI formats, yielding structured results suitable for programmatic use.

Why does my PubChem REST API request fail when extracting PUG-View annotations?

PubChem REST API requests fail when rate limits are exceeded or identifiers are invalid, so applying rate-limit-aware request patterns and validating CIDs ensures successful PUG-View annotation retrieval.