rdkit

Analyze and manipulate molecular structures with RDKit in Python.

1|Updated Mar 11, 2026
One-click install
npx skills add https://github.com/SciMate-AI/scicli --skill rdkit-scimate-ai
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: rdkit
Source: https://github.com/SciMate-AI/scicli/tree/main/internal/skills/bundled/claude-scientific-skills/skills/rdkit
Command: npx skills add https://github.com/SciMate-AI/scicli --skill rdkit-scimate-ai

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

RDKit provides a robust, programmable toolkit to analyze, process, and manipulate molecular structures within Python, reducing manual cheminformatics tasks and enabling reproducible research workflows.

Core Features & Use Cases

  • Read/write molecular structures from a variety of formats, calculate descriptors (MW, LogP, TPSA), generate fingerprints, perform substructure searches, run reactions, and create 2D/3D coordinates.
  • Use in drug discovery, materials research, and academic cheminformatics pipelines to automate property prediction, similarity screening, scaffold analysis, and visualization.
  • Practical scenario: build a pipeline that imports a SMILES dataset, computes descriptors, screens for Lipinski-like properties, and exports filtered candidates for synthesis.

Quick Start

Install RDKit and run a simple script to read a SMILES string, compute descriptors, and print results.

Frequently Asked Questions about rdkit

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

FAQPage Schema
How do I calculate molecular descriptors like MW, LogP, and TPSA from SMILES strings in Python?

Calculate molecular descriptors by reading SMILES strings with RDKit's Python modules, then using the Descriptors module to compute properties like MW, LogP, and TPSA for drug discovery pipelines.

What is the best way to perform substructure searching and similarity screening on a molecular dataset?

The best way to perform substructure searching and similarity screening is to generate molecular fingerprints from your dataset and use RDKit's substructure matching functions to identify and filter candidate molecules based on specific scaffold patterns.

Can I use RDKit to generate 2D and 3D coordinates for molecular visualization?

Yes, you can use RDKit to generate 2D and 3D coordinates for molecular visualization. The toolkit provides functions within its Chem and AllChem modules to compute coordinates and render molecular structures for research analysis.

Does RDKit support reading and writing multiple molecular file formats for cheminformatics pipelines?

RDKit supports reading and writing a variety of molecular structure formats, enabling robust I/O for cheminformatics pipelines. It ensures proper sanitization and structural validation during the import and export of chemical data.

How do I screen a SMILES dataset for Lipinski-like properties to filter drug discovery candidates?

To screen a SMILES dataset for Lipinski-like properties, build a Python pipeline that imports the data, computes the relevant physicochemical descriptors using RDKit, applies Lipinski filters, and exports the filtered candidates for synthesis.

What are the limitations of using RDKit for reactions and scaffold analysis in cheminformatics?

While RDKit handles reactions, fingerprinting, and scaffold analysis robustly within Python, its 3D coordinate generation and reaction predictions may require additional sanitization steps and careful validation against experimental data for accurate research results.