skills.rest
robotlearning123
robotlearning123COMMUNITY
Explore all skills by this author →
𝕏@wan73184085GitHub

datamol

Convert SMILES strings to molecule objects and compute molecular descriptors.

Updated Dec 17, 2025
Search Tags:#RDKit#datamol#molecule processing#molecular cheminformatics#cheminformatics tools
One-click install
npx skills add https://github.com/robotlearning123/claude-scientific-skills --skill datamol-robotlearning123
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: datamol
Source: https://github.com/robotlearning123/claude-scientific-skills/tree/main/scientific-skills/datamol
Command: npx skills add https://github.com/robotlearning123/claude-scientific-skills --skill datamol-robotlearning123

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires rdkit, fsspec, and includes scripts (resource) and references (resource) and assets (resource) components.

What problem does it solve?

Datamol addresses the complexity of molecular cheminformatics by providing a simplified interface and sensible defaults, enabling efficient molecule manipulation, analysis, and processing.

Core Features & Use Cases

  • Molecular Operations: Simplified interface for SMILES parsing, standardization, descriptors, fingerprints, clustering, 3D conformers, and parallel processing.
  • Data I/O: Read and write molecular files in various formats (SDF, SMILES, CSV, Excel, etc.) with support for remote file paths.
  • Descriptors & Properties: Compute a wide range of molecular descriptors for drug-like properties, flexibility, and stereochemistry.
  • Fingerprints & Similarity: Generate and compare molecular fingerprints for similarity analysis.
  • Clustering & Diversity: Cluster molecules based on similarity and select diverse subsets.
  • Scaffold Analysis: Extract Murcko scaffolds and analyze molecular frameworks.
  • Fragmentation: Break molecules into fragments for drug design and substructure analysis.
  • 3D Conformers: Generate and analyze 3D molecular conformers for virtual screening.
  • Visualization: Visualize molecules and conformers in various formats.
  • Chemical Reactions: Apply chemical reactions to molecules using SMARTS patterns.
  • Parallelization: Utilize parallel processing for efficient computation on large datasets.
  • Use Case: Utilize Datamol to perform virtual screening on a library of compounds to identify potential drug candidates.

Quick Start

To start using Datamol, import the library and convert a SMILES string to a molecule object: import datamol as dm; mol = dm.to_mol("CCO").

Frequently Asked Questions about datamol

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

FAQPage Schema
How do I simplify molecular cheminformatics tasks like molecule conversion and fingerprint generation?▼

Molecular cheminformatics tasks are simplified by providing a Pythonic interface for molecule conversion, property computation, and fingerprint generation with sensible defaults. It requires RDKit and fsspec to enable efficient molecule manipulation and analysis.

How do I read and write molecular files in SDF, SMILES, or Excel formats?▼

Reading and writing molecular files in SDF, SMILES, CSV, or Excel formats is handled by the Data I/O features, which also support remote file paths. This allows loading compound libraries directly from remote storage for virtual screening.

How do I compute molecular descriptors for drug-like properties and generate 3D conformers?▼

Computing molecular descriptors for drug-like properties and generating 3D conformers is done through a simplified interface for molecular operations. It supports descriptor computation, conformer generation, and parallel processing for large datasets.

Do I need RDKit to perform clustering, diversity selection, and scaffold analysis on molecules?▼

RDKit is required to perform clustering, diversity selection, and Murcko scaffold analysis on molecules. The library acts as a Pythonic wrapper over RDKit, extending its capabilities for fragment analysis and chemical reaction application using SMARTS patterns.

Can I use parallel processing for large-scale molecular fingerprint generation and similarity analysis?▼

Parallel processing is supported for large-scale molecular fingerprint generation and similarity analysis. This allows efficient computation on large compound libraries during virtual screening and drug discovery workflows.

What is the best way to apply chemical reactions to molecules using SMARTS patterns?▼

Applying chemical reactions to molecules using SMARTS patterns is streamlined through dedicated chemical reaction features. This functionality supports drug design and substructure analysis within computational chemistry workflows.

Related Skills

Explore More Software Engineering Skills→
tassiovaletassiovale
13

datamol

Parse, standardize, and compute molecular descriptors with Python and RDKit.

Community
Advanced
itallstartedwithaideaitallstartedwithaidea
31

cheminformatics

Convert SMILES/SDF molecular structures into computed descriptors and screening outputs.

Community
Advanced
xjtulycxjtulyc
33

rdkit-cheminformatics

Parse molecular representations and compute descriptors, fingerprints, similarity, scaffolds, and substructure matches.

Community
Advanced
ovachieverovachiever
52

rdkit

Analyze and manipulate molecules with RDKit for cheminformatics workflows.

Community
Advanced