datamol

Parse, standardize, and analyze molecular structures with RDKit via Python.

Updated Mar 10, 2026
One-click install
npx skills add https://github.com/Yezez9/Research-Agent --skill datamol-yezez9
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: datamol
Source: https://github.com/Yezez9/Research-Agent/tree/main/scientific-skills/datamol
Command: npx skills add https://github.com/Yezez9/Research-Agent --skill datamol-yezez9

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

This Skill simplifies complex molecular operations for drug discovery and cheminformatics, making it easier to analyze, manipulate, and understand chemical structures.

Core Features & Use Cases

  • Molecule Handling: Parse, standardize, and convert molecular formats (SMILES, SDF, etc.).
  • Descriptor & Fingerprint Calculation: Compute molecular properties and fingerprints for similarity and ML.
  • Clustering & Visualization: Group similar molecules and visualize structures.
  • Use Case: Analyze a library of drug candidates by calculating their molecular weight, logP, and generating ECFP fingerprints, then cluster them to identify diverse structural groups.

Quick Start

Load molecules from 'compounds.sdf', standardize them, and compute their molecular weight and logP.

Frequently Asked Questions about datamol

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

FAQPage Schema
How do I calculate molecular descriptors and fingerprints for drug discovery?

This Skill processes batch molecular operations by wrapping RDKit to parse SMILES, standardize molecules, and generate ECFP fingerprints. It computes molecular descriptors like weight and logP, then clusters similar compounds to identify diverse structural groups for drug discovery workflows.

What is the best way to standardize molecules and parse SMILES for cheminformatics?

Molecule standardization normalizes chemical structures by parsing SMILES and converting formats like SDF to ensure consistent descriptor calculation. This Skill wraps RDKit to execute these cheminformatics operations, preparing a clean dataset for accurate property computation and clustering.

Can I process a library of drug candidates in batch and cluster them by structural similarity?

Yes, this Skill supports batch processing and remote file access via fsspec to load compound libraries, generate ECFP fingerprints, and cluster molecules by structural similarity. It outputs diverse structural groups, enabling efficient analysis of large drug candidate datasets.

Does this cheminformatics tool require installing RDKit separately to generate 3D conformers?

No, this Skill provides a Pythonic interface wrapping RDKit for 3D conformer generation and visualization without requiring direct RDKit setup. It manages the cheminformatics operations internally, allowing you to focus on molecular analysis and drug discovery workflows.

How do I compute molecular weight and logP for a list of compounds from an SDF file?

Load molecules from an SDF file, apply molecule standardization, and run descriptor calculation functions to compute molecular weight and logP. This Skill wraps RDKit to execute these standard cheminformatics workflows, outputting calculated properties for batch analysis of drug candidates.