Can I perform structural similarity searches?

Yes, you can perform similarity searches to find structurally related compounds by providing a query SMILES and specifying a Tanimoto similarity threshold.

Does this skill require any external Python packages?

Yes, to use the full capabilities of this skill, you should have 'pubchempy' and 'requests' installed in your Python environment.

What molecular properties can I retrieve?

You can access a vast range of data including molecular weight, XLogP, TPSA, rotatable bond counts, charge, complexity, and hydrogen bond donor/acceptor counts.

Are there rate limits for PubChem API access?

Yes, PubChem requests are generally limited to 5 per second and 400 per minute. This skill includes best practices for handling these limits and managing requests efficiently.

How does this skill search for chemical compounds?

The skill supports flexible searching by chemical name, Compound ID (CID), SMILES strings, InChI, InChIKey, and molecular formulas using the PubChemPy library.

PubChem Database Explorer

Name: PubChem Database Explorer
Author: lifangda

bylifangda

•

Data Science & ML

Accesses the world's largest chemical database to retrieve compound properties, structures, and bioactivity data for cheminformatics workflows.

About

The PubChem Database skill integrates the world's largest freely available chemical repository into your development environment, providing access to over 110 million compounds and 270 million bioactivities. It allows for sophisticated chemical data retrieval using the PUG-REST API and PubChemPy, enabling searches by name, CID, SMILES, or InChI. This tool is essential for researchers and developers performing molecular property analysis, structural similarity searches, substructure motifs identification, and drug-likeness screening. By automating the extraction of molecular descriptors and bioassay results, it streamlines the bridge between raw chemical data and actionable scientific insights.

Key Features

Advanced similarity and substructure searches using Tanimoto coefficients
Comprehensive property retrieval including Molecular Weight, LogP, TPSA, and HBond counts
Multi-format search using names, CIDs, SMILES, InChI, and molecular formulas
16 GitHub stars
Automated chemical identifier conversion and 2D structure image generation
Direct access to biological activity data and assay results from screening programs

Use Cases

Building data pipelines for cheminformatics and machine learning model training
Automated screening of chemical libraries for drug-likeness and Lipinski compliance
Finding structurally related leads for drug discovery and lead optimization tasks

About

Key Features

Advanced similarity and substructure searches using Tanimoto coefficients
Comprehensive property retrieval including Molecular Weight, LogP, TPSA, and HBond counts
Multi-format search using names, CIDs, SMILES, InChI, and molecular formulas
16 GitHub stars
Automated chemical identifier conversion and 2D structure image generation
Direct access to biological activity data and assay results from screening programs

Use Cases

Building data pipelines for cheminformatics and machine learning model training
Automated screening of chemical libraries for drug-likeness and Lipinski compliance
Finding structurally related leads for drug discovery and lead optimization tasks