datamol

Wrap RDKit for SMILES parsing, descriptor calculation, and fingerprint generation.

Updated Jan 10, 2026
One-click install
npx skills add https://github.com/robinbarvaag/poynt --skill datamol-robinbarvaag
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: datamol
Source: https://github.com/robinbarvaag/poynt/tree/main/.github/skills/datamol
Command: npx skills add https://github.com/robinbarvaag/poynt --skill datamol-robinbarvaag

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

This Skill simplifies complex molecular operations in drug discovery, enabling faster analysis and development by providing a user-friendly interface to powerful cheminformatics tools.

Core Features & Use Cases

  • Molecule Handling: Parse, standardize, and convert molecular formats (SMILES, SDF, etc.).
  • Descriptor & Fingerprint Calculation: Compute a wide range of molecular descriptors and fingerprints for analysis and ML.
  • 3D Conformer Generation: Generate and analyze 3D structures for molecular modeling.
  • Clustering & Similarity: Group similar molecules and find diverse subsets.
  • Scaffold & Fragment Analysis: Identify core structures and break down molecules into fragments.
  • Visualization: Create images of molecules, conformers, and SAR series.
  • Use Case: Quickly analyze a library of drug candidates by calculating their Lipinski's Rule of Five properties, generating ECFP fingerprints, and clustering them to identify distinct chemical series.

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 parse SMILES strings and calculate molecular descriptors in Python?

SMILES parsing and molecular descriptor calculation are handled by wrapping RDKit in a Pythonic interface, returning native rdkit.Chem.Mol objects for seamless integration. This simplifies complex molecular operations for faster drug discovery analysis.

Can I generate 3D conformers and ECFP fingerprints for a library of drug candidates?

3D conformer generation and fingerprint calculation are natively supported for analyzing drug candidate libraries. You can compute a wide range of molecular descriptors and generate ECFP fingerprints to facilitate machine learning and molecular modeling tasks.

Does this cheminformatics approach require a separate RDKit installation to process SDF files?

Processing SDF files and other molecular formats relies on RDKit as the underlying engine. The Skill provides a user-friendly wrapper around RDKit, returning native rdkit.Chem.Mol objects, ensuring seamless integration with your existing RDKit workflow.

What is the best way to cluster similar molecules and identify diverse chemical series?

Clustering similar molecules to identify diverse chemical series is a built-in feature for drug discovery. By calculating fingerprints and descriptors, you can group similar molecules, find diverse subsets, and perform scaffold and fragment analysis on your library.

How do I standardize molecular formats and visualize SAR series in cheminformatics?

Molecule standardization and visualization of SAR series are core features facilitating drug discovery. You can convert molecular formats like SMILES and SDF, standardize structures, and create images of molecules and conformers for detailed analysis.

Why use a Pythonic wrapper for RDKit instead of native RDKit for molecule processing?

A Pythonic wrapper simplifies complex molecular operations and parallel processing that native RDKit requires manual setup for. It accelerates drug discovery by providing a user-friendly interface to standard cheminformatics tasks while returning native rdkit.Chem.Mol objects.