What is the PubChem Database skill for Claude?

It is a specialized capability that allows Claude to query the PubChem database to retrieve chemical information, structures, and biological activity data using Python-based tools.

What chemical identifiers can I use for searching?

The skill supports searching by chemical names, Compound IDs (CID), SMILES strings, InChI strings, InChIKeys, and molecular formulas.

Are there rate limits for using the PubChem API?

Yes, users should adhere to PubChem's PUG-REST limits, which include a maximum of 5 requests per second and 400 requests per minute to ensure reliable access.

Can I perform substructure searches with this skill?

Yes, you can search for compounds containing specific chemical motifs or functional groups using SMILES-based substructure queries via the included scripts.

Does this skill support batch processing for multiple compounds?

Absolutely; the skill includes patterns and helper scripts for batch searching multiple chemical identifiers and retrieving properties in a structured format like Pandas DataFrames.

PubChem Database

Name: PubChem Database
Author: K-Dense-AI

byK-Dense-AI

•

2,188

Ciencia de Datos y ML

Accesses the world's largest chemical database to search compounds, retrieve molecular properties, and perform structure-based searches.

Acerca de

The PubChem Database skill integrates Claude with the PubChem PUG-REST API and PubChemPy, allowing for seamless retrieval of data from over 110 million chemical compounds. It enables advanced cheminformatics tasks such as searching by SMILES or IUPAC names, extracting physical properties like molecular weight and XLogP, performing similarity and substructure searches, and accessing bioactivity data. This skill is ideal for researchers and developers building chemical informatics pipelines, screening for drug-likeness, or performing large-scale biological data analysis directly within their Claude-assisted environment.

Características Principales

Comprehensive molecular property retrieval for MW, LogP, TPSA, and bond counts
2,188 GitHub stars
Advanced similarity and substructure searches using Tanimoto metrics
Access to bioactivity data from over 270 million screening assays
Multi-format chemical search including Name, CID, SMILES, InChI, and Formula
Automated chemical identifier conversion and 2D structure visualization generation

Casos de Uso

Automating the conversion of large chemical datasets between SMILES, InChI, and CID formats
Identifying structurally similar compounds for lead optimization in drug discovery research
Screening chemical libraries for drug-likeness using Lipinski's Rule of Five criteria

Acerca de

Características Principales

Comprehensive molecular property retrieval for MW, LogP, TPSA, and bond counts
2,188 GitHub stars
Advanced similarity and substructure searches using Tanimoto metrics
Access to bioactivity data from over 270 million screening assays
Multi-format chemical search including Name, CID, SMILES, InChI, and Formula
Automated chemical identifier conversion and 2D structure visualization generation

Casos de Uso

Automating the conversion of large chemical datasets between SMILES, InChI, and CID formats
Identifying structurally similar compounds for lead optimization in drug discovery research
Screening chemical libraries for drug-likeness using Lipinski's Rule of Five criteria