skills.rest
xjtulyc
xjtulycCOMMUNITY
Explore all skills by this author →
WebsiteGitHub

rdkit-cheminformatics

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

33|6|Updated Mar 17, 2026
Search Tags:#cheminformatics#substructure search#rdkit#morgan fingerprints#tanimoto similarity#murcko scaffolds
One-click install
npx skills add https://github.com/xjtulyc/awesome-rosetta-skills --skill rdkit-cheminformatics-xjtulyc
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: rdkit-cheminformatics
Source: https://github.com/xjtulyc/awesome-rosetta-skills/tree/main/skills/02-chemistry/rdkit-cheminformatics
Command: npx skills add https://github.com/xjtulyc/awesome-rosetta-skills --skill rdkit-cheminformatics-xjtulyc

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill eliminates the manual, error-prone work of converting chemical structure inputs into analysis-ready representations and then performing similarity, substructure, and scaffold-based discovery.

Core Features & Use Cases

  • Molecule parsing from common formats: Convert SMILES, InChI, and SDF/MOL inputs into RDKit Mol objects for downstream analysis.
  • Drug-likeness and physicochemical descriptor calculation: Compute properties like MW, LogP, TPSA, HBD/HBA, rotatable bonds, and ring counts, including Lipinski and Veber rule checks.
  • Similarity and library screening: Generate Morgan (ECFP) fingerprints and compute Tanimoto similarity for search, clustering, and chemical space exploration.
  • Scaffold and substructure workflows: Decompose Murcko scaffolds for scaffold frequency analysis and run SMARTS substructure queries for targeted filtering.
  • Chemical space visualization: Project fingerprint matrices into 2D using PCA for interpretable mapping of chemical diversity.

Quick Start

Use the rdkit-cheminformatics Skill to parse your compound SMILES list, compute Morgan fingerprints, filter by Tanimoto similarity against a query molecule, and return the ranked hit table.

Frequently Asked Questions about rdkit-cheminformatics

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

FAQPage Schema
How do I compute Tanimoto similarity for virtual screening against a compound library?▼

Compute Tanimoto similarity by parsing molecular representations into Morgan fingerprints, then calculating bulk or pairwise similarity against a query molecule to return a ranked hit table for virtual screening.

How do I calculate drug-likeness descriptors and apply Lipinski rules to a SMILES list?▼

Calculate drug-likeness by parsing SMILES into molecular objects and computing physicochemical descriptors like MW, LogP, TPSA, HBD/HBA, enabling Lipinski and Veber rule checks to filter compounds.

What is the best way to perform Murcko scaffold decomposition for frequency analysis?▼

Murcko scaffold decomposition extracts core scaffolds from parsed molecules, enabling scaffold frequency analysis to identify common structural frameworks across a compound library.

Can I use SMARTS substructure queries to filter molecules from SDF or MOL files?▼

Yes, parse SDF or MOL files into molecular objects and run SMARTS substructure query matching to perform targeted hit finding and filter compounds containing specific structural motifs.

How do I visualize chemical space using PCA projection of molecular fingerprints?▼

Visualize chemical space by generating Morgan fingerprints for a compound set, projecting the fingerprint matrix into 2D using PCA, and plotting the results to map chemical diversity.

Does this cheminformatics workflow support InChI inputs alongside standard SMILES strings?▼

Yes, the workflow parses multiple chemical structure formats including InChI, SMILES, and SDF/MOL inputs, converting them into molecular objects for downstream cheminformatics analysis.

Related Skills

Explore More Education & Research Skills→
learningmatter-mitlearningmatter-mit
144

drug-db-pubchem

Retrieve PubChem compound identifiers and metadata via PUG-REST queries.

Official
Intermediate
learningmatter-mitlearningmatter-mit
144

drug-binding-site-definition

Compute docking box center and dimensions from ligand, residues, or JSON.

Official
Intermediate
itallstartedwithaideaitallstartedwithaidea
31

cheminformatics

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

Community
Advanced
sanand0sanand0
8

molfeat

Convert chemical structures into machine learning-ready numerical representations.

Community
Intermediate