datamol

Convert SMILES strings to RDKit molecule objects for cheminformatics tasks.

557|98|Updated Nov 7, 2025
One-click install
npx skills add https://github.com/jimmc414/Kosmos --skill datamol-jimmc414
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: datamol
Source: https://github.com/jimmc414/Kosmos/tree/main/kosmos-claude-scientific-skills/scientific-skills/datamol
Command: npx skills add https://github.com/jimmc414/Kosmos --skill datamol-jimmc414

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

This Skill simplifies complex molecular operations in cheminformatics, making standard drug discovery tasks like molecule parsing, standardization, descriptor calculation, and similarity searching more accessible and efficient.

Core Features & Use Cases

  • Molecule Handling: Easily convert between SMILES, SELFIES, and RDKit molecule objects. Standardize and sanitize molecular structures.
  • Data Processing: Read and write molecular data from various file formats (SDF, CSV, Excel) and cloud storage.
  • Analysis & ML: Compute molecular descriptors, generate fingerprints, perform clustering, and prepare data for machine learning models.
  • Use Case: A medicinal chemist needs to process a library of 10,000 compounds, calculate their molecular weight and LogP, filter them based on Lipinski's Rule of Five, and then select a diverse subset for further testing. This Skill automates this entire pipeline.

Quick Start

Use the datamol skill to convert the SMILES string 'CCO' into an RDKit molecule object.

Frequently Asked Questions about datamol

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

FAQPage Schema
How do I convert SMILES strings into RDKit molecule objects for cheminformatics processing?

You can convert SMILES strings to RDKit molecule objects using a Pythonic interface that abstracts RDKit for simplified cheminformatics processing, enabling efficient molecule parsing, standardization, and sanitization of molecular structures.

How do I calculate molecular descriptors and filter compounds by Lipinski's Rule of Five?

Calculating molecular descriptors and filtering compounds by Lipinski's Rule of Five involves computing properties like molecular weight and LogP, then applying threshold filters to select compliant molecules for downstream drug discovery testing.

Can I process large-scale molecular libraries from SDF and CSV files in batch?

Yes, batch processing of large-scale molecular libraries is supported, allowing you to read and write molecular data from SDF, CSV, and Excel formats, including remote file I/O for cloud storage data handling.

What is the best way to generate molecular fingerprints and perform similarity clustering for compound selection?

Generating molecular fingerprints and performing similarity clustering for compound selection is done by computing fingerprint representations, calculating molecular similarity, and grouping compounds to extract a diverse subset for testing.

Do I need to know RDKit to perform 3D conformer analysis and molecule standardization?

No, extensive RDKit knowledge is not required to perform 3D conformer analysis and molecule standardization, as the interface abstracts RDKit complexities to provide a simplified Pythonic cheminformatics experience.