rdkit

Parse molecules and compute descriptors, fingerprints, and substructure searches with RDKit.

33.0k|3.2k|Updated Oct 19, 2025
One-click install
npx skills add https://github.com/K-Dense-AI/scientific-agent-skills --skill rdkit-k-dense-ai
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: rdkit
Source: https://github.com/K-Dense-AI/scientific-agent-skills/tree/main/scientific-skills/rdkit
Command: npx skills add https://github.com/K-Dense-AI/scientific-agent-skills --skill rdkit-k-dense-ai

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

RDKit-based tooling enables reproducible cheminformatics workflows by programmatically parsing molecules, computing descriptors, generating fingerprints, performing substructure searches, and simulating reactions for scalable research.

Core Features & Use Cases

  • Reading and writing chemical structures from SMILES, MOL files, InChI, and more, enabling seamless data integration.
  • Computing descriptors (MW, LogP, TPSA), generating fingerprints (Morgan, RDKit, etc.), performing substructure searches, and handling chemical reactions.
  • Use Case: accelerate drug-discovery pipelines by filtering large compound databases using descriptor thresholds and similarity searches.

Quick Start

Load a molecule with RDKit and compute a quick set of descriptors and a fingerprint to begin analysis.

Frequently Asked Questions about rdkit

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

FAQPage Schema
How do I compute molecular descriptors like LogP and TPSA from SMILES strings?

You can compute molecular descriptors like LogP and TPSA from SMILES strings by programmatically parsing the molecules and calculating property values using RDKit APIs. This enables reproducible cheminformatics workflows for scalable research and drug discovery pipelines.

What is the best way to perform substructure searches on large compound databases?

Performing substructure searches on large compound databases is best handled by programmatically parsing molecular structures and querying them with RDKit APIs. This approach filters compounds using descriptor thresholds and similarity searches to accelerate drug-discovery pipelines.

How do I generate molecular fingerprints such as Morgan fingerprints for similarity searching?

Generating molecular fingerprints such as Morgan fingerprints for similarity searching involves programmatically parsing molecules and computing the fingerprint vectors using RDKit APIs. This supports reproducible cheminformatics workflows for scalable molecular analytics.

Can I read and write chemical structures from MOL files and InChI formats programmatically?

Yes, you can read and write chemical structures from MOL files and InChI formats programmatically using RDKit I/O APIs. This enables seamless data integration for reproducible cheminformatics workflows covering drug discovery and academic research.

Does RDKit handle chemical reaction processing and simulation for scalable research?

RDKit does handle chemical reaction processing and simulation for scalable research by providing robust APIs for reaction handling with robust error handling. This supports reproducible cheminformatics workflows in drug discovery and materials science.