pubchem-database

Access PubChem data for chemical search, property retrieval, and bioactivity analysis.

18|1|Updated Dec 27, 2025
One-click install
npx skills add https://github.com/LogauaEngstrom/claude-scientific-skills --skill pubchem-database-logauaengstrom
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: pubchem-database
Source: https://github.com/LogauaEngstrom/claude-scientific-skills/tree/main/scientific-skills/pubchem-database
Command: npx skills add https://github.com/LogauaEngstrom/claude-scientific-skills --skill pubchem-database-logauaengstrom

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

Provide programmatic access to PubChem data and tools for chemical search, property retrieval, and bioactivity analysis, enabling researchers to automate cheminformatics workflows.

Core Features & Use Cases

  • Search for compounds by name, CID, SMILES, InChI, or molecular formula and retrieve comprehensive properties.
  • Perform similarity and substructure searches to identify related compounds or motifs.
  • Retrieve bioactivity data, synonyms, and drug-related annotations via PUG-View.
  • Convert between formats (SDF, JSON) and access 2D structure representations.
  • Utilize helper scripts for batch processing and rapid exploratory analysis.

Quick Start

Run the example workflow by executing the scripts/compound_search.py to search for aspirin and display its properties.

Frequently Asked Questions about pubchem-database

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

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

To retrieve chemical properties from PubChem, provide a compound name, CID, SMILES, or InChI string as input. The Skill queries the PubChem database to fetch comprehensive properties and format the results for cheminformatics workflows.

Can I perform batch chemical searches and bioactivity queries on PubChem at scale?

Yes, you can query PubChem at scale using built-in helper scripts for batch processing. The Skill applies rate limiting and error handling to automate bioactivity queries and property retrieval across large compound sets.

How do similarity and substructure searches work in PubChem for cheminformatics analysis?

Similarity and substructure searches in PubChem identify related compounds or chemical motifs from a query structure. The Skill uses PubChemPy to programmatically execute these searches and return matching compounds.

Does PubChemPy handle rate limiting and error handling for automated data extraction?

Yes, PubChemPy includes built-in rate limiting and error handling for automated data extraction. This ensures stable programmatic access to PubChem data when retrieving properties, synonyms, or drug annotations via PUG-View.

What is the best way to convert PubChem compound data into SDF or JSON formats?

The best way to convert PubChem compound data is by using the Skill's format conversion capabilities. It retrieves 2D structure representations and converts compound data between SDF and JSON formats for analysis.

Why do my automated PubChem requests fail when processing large compound sets?

Automated PubChem requests fail when processing large compound sets due to API rate limits. The Skill mitigates this by applying built-in rate limiting and error handling to manage request frequency during batch workflows.