datamol

Parse and standardize molecular structures for cheminformatics workflows.

Updated Jul 1, 2026
One-click install
npx skills add https://github.com/jasrajtulsi/GRAD-SCOPE --skill datamol-jasrajtulsi
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: datamol
Source: https://github.com/jasrajtulsi/GRAD-SCOPE/tree/main/.claude/skills/datamol
Command: npx skills add https://github.com/jasrajtulsi/GRAD-SCOPE --skill datamol-jasrajtulsi

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

Datamol reduces the manual overhead of cheminformatics by giving you a simpler, Pythonic way to parse, clean, analyze, compare, and visualize molecular data.

Core Features & Use Cases

  • Molecule parsing and standardization: Convert SMILES, InChI, SELFIES, SDF, CSV, and Excel inputs into native RDKit molecules and clean them with sensible defaults.
  • Analysis and featurization: Compute descriptors, fingerprints, similarity matrices, clusters, scaffolds, fragments, and 3D conformers for drug discovery and molecular modeling workflows.
  • I/O and visualization: Read and write common chemistry file formats, handle batch workflows, and generate publication-ready molecule grids and conformer views.
  • Use case: A researcher can load a compound library, standardize every structure, filter invalid entries, compare scaffold families, and export labeled images for a report.

Quick Start

Ask for help using datamol on your molecule files, and I will load the data, standardize structures, compute descriptors or fingerprints, and return a concise analysis.

Frequently Asked Questions about datamol

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

FAQPage Schema
How do I standardize molecular structures from SMILES and SDF files for cheminformatics workflows?

You can standardize molecular structures by parsing SMILES, InChI, SELFIES, and SDF inputs into native RDKit molecules, applying sensible defaults to clean and normalize the chemical data for reliable downstream analysis.

What is the best way to compute molecular descriptors and fingerprints for drug discovery analysis?

To compute molecular descriptors and fingerprints, you can process standardized RDKit molecules in parallel, generating the necessary chemical features and similarity matrices for molecular modeling and drug discovery workflows.

Can I batch process a compound library from Excel or CSV and filter invalid molecular entries?

Yes, you can load compound libraries directly from CSV or Excel files, convert them into native RDKit molecules, and automatically filter out invalid entries during the standardization process for batch computation.

Does this approach support generating 3D conformers and scaffolds for molecular visualization?

Generating 3D conformers and scaffolds is supported, allowing you to analyze scaffold families, perform fragmentation, and generate publication-ready molecule grids and conformer views for molecular analysis reports.

Do I need RDKit installed to parse reactions and perform molecular clustering?

Yes, RDKit is required because the operations rely on RDKit-backed datamol functions, native Mol object handling, and fsspec-enabled I/O to reliably parse reactions and compute molecular clusters.