pubchem-database

Query PubChem compounds by name, CID, SMILES, or InChI and retrieve properties.

Updated May 6, 2026
One-click install
npx skills add https://github.com/swaruplab/operon-enterprise --skill pubchem-database-swaruplab
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: pubchem-database
Source: https://github.com/swaruplab/operon-enterprise/tree/main/src-tauri/protocols/pubchem-database
Command: npx skills add https://github.com/swaruplab/operon-enterprise --skill pubchem-database-swaruplab

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

Programmatic access to PubChem data and bioactivity information is often needed for cheminformatics workflows, including property retrieval, identifier conversions, and data integration across pipelines.

Core Features & Use Cases

  • Query compounds by name, CID, SMILES, or InChI; retrieve properties such as molecular weight, XLogP, TPSA, and more.
  • Perform similarity and substructure searches to discover related compounds and motifs.
  • Access bioactivity data via PubChem assays and summaries; retrieve annotations via PUG-View for drugs and pharmacology.
  • Batch queries, property extraction, and format conversions with PubChemPy and requests integration.
  • Use case: build a pipeline to compare a list of candidates, fetch properties, and export to CSV for downstream analysis.

Quick Start

Query a compound by name (e.g., aspirin) and print its CID, canonical SMILES, and molecular weight.

Frequently Asked Questions about pubchem-database

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

FAQPage Schema
How do I retrieve molecular properties like XLogP and TPSA from PubChem using a compound name or SMILES?

You retrieve PubChem molecular properties by querying compounds via name, CID, SMILES, or InChI using the PubChem REST API and PubChemPy. This returns specific properties including molecular weight, XLogP, and TPSA for cheminformatics workflows.

Can I perform batch compound queries and export PubChem data to CSV for pipeline analysis?

Batch compound queries are supported through PubChemPy and requests integration, enabling you to fetch properties for multiple compounds and export the extracted data to CSV for downstream pipeline analysis.

How do I run similarity and substructure searches in PubChem to find related chemical motifs?

Similarity and substructure searches are executed via the PubChem REST API to discover related compounds and chemical motifs. You provide a query structure to retrieve matching compounds based on structural similarity.

Does this approach support accessing PubChem bioactivity data and pharmacology annotations via PUG-View?

Yes, accessing PubChem bioactivity data and pharmacology annotations is supported via PUG-View and PUG-REST. You can retrieve assay summaries and drug annotations programmatically for bioactivity analysis.

What are the rate limits when querying the PubChem REST API for identifier conversions?

The PubChem REST API enforces rate limits on requests to manage server load. This interface supports rate-limited requests to ensure compliant identifier conversions and property lookups during automated cheminformatics workflows.

How do I convert between chemical identifiers like CID, InChI, and canonical SMILES using PubChemPy?

Identifier conversions between CID, InChI, and canonical SMILES are handled by querying the PubChem REST API through PubChemPy. This allows seamless chemical data integration across different pipeline formats.