datamol

Name: datamol
Availability: InStock
Author: K-Dense

Simplify RDKit-based cheminformatics workflows with a Pythonic wrapper.

33.0k|3.2k|Updated Oct 19, 2025

Search Tags:#cheminformatics #parallel-processing #fingerprints #conformers #datamol #descriptors #rdkit

Ready to run

npx skills add https://github.com/K-Dense-AI/scientific-agent-skills --skill datamol-k-dense-ai

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: datamol
Source: https://github.com/K-Dense-AI/scientific-agent-skills/tree/main/scientific-skills/datamol
Command: npx skills add https://github.com/K-Dense-AI/scientific-agent-skills --skill datamol-k-dense-ai

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Datamol provides a Pythonic, lightweight abstraction layer over RDKit to simplify molecular cheminformatics tasks, enabling researchers to perform standardization, descriptor calculation, fingerprinting, 3D conformer handling, and batch data workflows with minimal boilerplate.

Core Features & Use Cases

Molecular format conversions (SMILES, InChI, SELFIES)
Descriptor and fingerprint computations, clustering, and simple data pipelines
3D conformer generation and analysis with parallel processing
Reading/writing common molecule data formats (SDF, CSV/Excel, cloud-backed files)
Use Case: Build end-to-end chemoinformatics pipelines for drug discovery, including data cleaning, feature extraction, and downstream modeling.

Quick Start

Install datamol and run a small molecule descriptor workflow to verify the setup.

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 datasets?▼

Molecular descriptor and fingerprint calculations are handled by wrapping RDKit to provide a Pythonic API for cheminformatics workflows. You can compute features and process small- to medium-scale drug discovery datasets with minimal boilerplate.

What is the best way to run parallel processing for 3D conformer generation?▼

Parallel processing for 3D conformer generation is simplified through a cohesive Python API that abstracts RDKit workflows. This allows you to generate and analyze 3D conformers across batches of molecules efficiently.

How do I standardize molecules and convert between SMILES, InChI, and SELFIES formats?▼

Molecule standardization and format conversions between SMILES, InChI, and SELFIES are supported through datamol's Pythonic wrapper. It handles molecule parsing and standardization tasks directly within your cheminformatics pipeline.

Can I read and write SDF files and cloud-backed molecule data using a Pythonic RDKit wrapper?▼

Reading and writing common molecule data formats including SDF, CSV, Excel, and cloud-backed files is fully supported. The API integrates molecule IO operations into batch data pipelines for end-to-end cheminformatics processing.

Does datamol require installing RDKit separately for cheminformatics tasks?▼

Datamol acts as a lightweight Pythonic abstraction layer built over RDKit to simplify cheminformatics tasks. It relies on RDKit's underlying functionality to perform molecule parsing, standardization, descriptor generation, and clustering.

Why use a Pythonic wrapper for RDKit instead of native RDKit for batch cheminformatics pipelines?▼

A Pythonic wrapper reduces boilerplate when building batch data pipelines for molecule standardization and feature extraction. It streamlines RDKit's complex API into a cohesive interface suited for end-to-end drug discovery modeling.