Does this skill require any specific Python libraries?

Yes, to use this skill, you typically need to install 'pubchempy' and 'requests' in your Python environment.

What is the PubChem Database skill?

It is a specialized capability for Claude to query the PubChem database for chemical structures, properties, and bioactivities using Python-based tools like PubChemPy.

Are there rate limits for PubChem API queries?

Yes, PubChem suggests a maximum of 5 requests per second and 400 per minute. This skill provides guidelines on implementing delays and batching to respect these limits.

Can I search for compounds using SMILES strings?

Yes, the skill supports searching by various identifiers including common names, Compound IDs (CID), SMILES, InChI, and molecular formulas.

PubChem Database Integration

Name: PubChem Database Integration
Author: BbgnsurfTech

byBbgnsurfTech

•

数据科学与机器学习

Accesses and queries the PubChem database via PUG-REST API and PubChemPy for comprehensive chemical informatics and compound analysis.

关于

This skill enables Claude to interact directly with the world's largest chemical database, containing over 110 million compounds. It facilitates complex cheminformatics workflows including searching by chemical name, structure (SMILES/InChI), or molecular formula, retrieving detailed molecular properties like LogP and TPSA, and performing similarity or substructure searches. It is an essential tool for researchers, medicinal chemists, and data scientists performing drug-likeness screening, bioactivity analysis, or chemical identifier conversion within their development environment.

主要功能

Direct access to bioactivity data, assay summaries, and biological targets
Structural similarity and substructure search capabilities using Tanimoto metrics
Batch processing and format conversion between various chemical identifiers
3 GitHub stars
Detailed molecular property retrieval including MW, LogP, TPSA, and hydrogen bonding
Comprehensive compound search by name, CID, SMILES, InChI, and formula

使用场景

Identifying structurally related compounds for lead optimization in medicinal chemistry
Conducting drug-likeness screening using Lipinski’s Rule of Five
Mapping chemical libraries and converting identifier formats for large datasets

关于

主要功能

Direct access to bioactivity data, assay summaries, and biological targets
Structural similarity and substructure search capabilities using Tanimoto metrics
Batch processing and format conversion between various chemical identifiers
3 GitHub stars
Detailed molecular property retrieval including MW, LogP, TPSA, and hydrogen bonding
Comprehensive compound search by name, CID, SMILES, InChI, and formula

使用场景

Identifying structurally related compounds for lead optimization in medicinal chemistry
Conducting drug-likeness screening using Lipinski’s Rule of Five
Mapping chemical libraries and converting identifier formats for large datasets