rdkit

Parse molecular formats and compute descriptors from SMILES strings.

15|2|Updated Dec 17, 2025
One-click install
npx skills add https://github.com/rubensliv/k-dense-ai --skill rdkit-rubensliv
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: rdkit
Source: https://github.com/rubensliv/k-dense-ai/tree/main/scientific-skills/rdkit
Command: npx skills add https://github.com/rubensliv/k-dense-ai --skill rdkit-rubensliv

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

RDKit-based tooling enables researchers to programmatically analyze, manipulate, and visualize molecular structures, reducing manual work and enabling reproducible workflows.

Core Features & Use Cases

  • Molecular I/O and parsing from SMILES, MOL, InChI, PDB, and more.
  • Descriptor calculation, fingerprinting, substructure searching, reaction modeling, and 2D/3D coordinate generation.
  • Use Case: In drug discovery, read candidate SMILES, compute descriptors, screen by fingerprints, perform substructure searches, and generate publication-quality drawings.

Quick Start

Provide a SMILES string and the Skill will parse it, compute descriptors, and render a 2D drawing.

Frequently Asked Questions about rdkit

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?

To parse SMILES strings and calculate molecular descriptors, you can use RDKit to programmatically read molecular formats and compute structural properties. It reads SMILES, MOL, InChI, and PDB inputs, then outputs calculated descriptor values for reproducible cheminformatics workflows.

What's the best way to perform substructure searches and fingerprint similarity screening for drug discovery?

The best way to perform substructure searches and fingerprint similarity screening is using RDKit's automated cheminformatics workflows. It matches substructure patterns and computes fingerprints to screen candidate molecules by structural similarity within Python scripts.

Can I generate 2D and 3D molecular coordinates for publication-quality visualization?

Yes, you can generate 2D and 3D molecular coordinates for publication-quality visualization. RDKit produces high-quality molecular depictions by computing coordinates from parsed structures, enabling clear structural drawings for research outputs.

Does RDKit support reading and writing multiple molecular formats like InChI and PDB?

RDKit supports reading and writing multiple molecular formats including SMILES, MOL, InChI, and PDB. This molecular I/O capability allows you to programmatically parse and manipulate diverse molecular structures for automated analysis pipelines.

How do I model chemical reactions and manipulate molecular structures programmatically?

To model chemical reactions and manipulate molecular structures programmatically, RDKit provides reaction modeling and structural manipulation functions. It enables automated cheminformatics workflows by allowing programmatic analysis of molecular structures and reaction transformations in Python.

When do I need cheminformatics workflows for molecular structure analysis?

You need cheminformatics workflows for molecular structure analysis when parsing molecular formats, computing descriptors, generating fingerprints, or performing substructure searches. RDKit satisfies these requirements for robust parsing and descriptor computation within Python scripts and notebooks.