What is the primary use of the RDKit skill?

The RDKit skill is used for computational chemistry tasks such as reading/writing molecular files, calculating chemical descriptors, and performing substructure searches.

Does this skill support 3D molecular modeling?

Yes, it provides patterns for 3D coordinate generation, conformer embedding, and geometry optimization using UFF or MMFF force fields.

Can I calculate drug-likeness parameters with this skill?

Absolutely. It includes workflows for calculating Lipinski's Rule of Five parameters like Molecular Weight, LogP, H-Bond Donors, and Acceptors.

When should I use RDKit instead of Datamol?

While Datamol offers a simpler interface for standard workflows, you should use this RDKit skill for advanced control, custom sanitization, and specialized algorithms.

How does RDKit handle chemical reactions?

It utilizes Reaction SMARTS to define transformations, allowing you to programmatically apply chemical reactions to specific reactants to generate products.

RDKit Cheminformatics Toolkit

Name: RDKit Cheminformatics Toolkit
Author: Microck

byMicrock

•

データサイエンスとML

Performs advanced molecular manipulation, chemical property calculation, and substructure analysis using the RDKit library.

概要

The RDKit Cheminformatics Toolkit skill enables Claude to execute complex chemical data processing tasks with high precision. It provides comprehensive guidance for handling molecular formats like SMILES, InChI, and SDF, while offering deep control over molecular sanitization, descriptor calculation (LogP, TPSA, MW), and fingerprinting for similarity searches. This skill is essential for researchers and developers working in drug discovery, computational chemistry, and molecular modeling who require standardized implementation patterns for RDKit's powerful Python APIs.

主な機能

Advanced substructure searching using SMARTS patterns
High-precision property calculation including MW, LogP, and TPSA
Molecular similarity analysis and Butina clustering
Molecular I/O for SMILES, SDF, InChI, and MolBlock formats
81 GitHub stars
2D and 3D coordinate generation with force field optimization

ユースケース

Automating the cleaning and standardization of large chemical datasets
Designing drug discovery pipelines and virtual screening workflows
Performing lead optimization via substructure analysis and property profiling

概要

主な機能

Advanced substructure searching using SMARTS patterns
High-precision property calculation including MW, LogP, and TPSA
Molecular similarity analysis and Butina clustering
Molecular I/O for SMILES, SDF, InChI, and MolBlock formats
81 GitHub stars
2D and 3D coordinate generation with force field optimization

ユースケース

Automating the cleaning and standardization of large chemical datasets
Designing drug discovery pipelines and virtual screening workflows
Performing lead optimization via substructure analysis and property profiling