scientific-cheminformatics

Compute molecular descriptors, Morgan fingerprints, and Lipinski Rule of 5 checks from SMILES strings.

3|1|Updated Feb 11, 2026
One-click install
npx skills add https://github.com/nahisaho/satori --skill scientific-cheminformatics
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: scientific-cheminformatics
Source: https://github.com/nahisaho/satori/tree/main/src/.github/skills/scientific-cheminformatics
Command: npx skills add https://github.com/nahisaho/satori --skill scientific-cheminformatics

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Enables automated molecular descriptor calculation, fingerprint generation, and drug-likeness assessment from SMILES to support cheminformatics workflows.

Core Features & Use Cases

  • Molecular Descriptors: compute properties such as MW, LogP, TPSA, HBA/HBD, Rotatable Bonds, and QED.
  • Fingerprints & Similarity: generate Morgan fingerprints and compute Tanimoto similarities for SAR analysis and library clustering.
  • Structure Alerts & Lipinski: detect toxicophores and evaluate Lipinski Rule of Five for drug-likeness.
  • Use Case: SAR exploration across small-molecule libraries to prioritize candidates for synthesis.

Quick Start

Provide a list of SMILES strings to compute descriptors, fingerprints, and Lipinski checks for SAR-ready data.

Frequently Asked Questions about scientific-cheminformatics

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

FAQPage Schema
How do I calculate molecular descriptors and Lipinski Rule of Five from SMILES strings?

To calculate molecular descriptors and Lipinski Rule of Five from SMILES strings, use RDKit to compute MW, LogP, TPSA, HBA/HBD, and rotatable bonds, enabling automated drug-likeness assessment for small-molecule libraries.

Can I detect toxicophores and structural alerts in compound libraries using RDKit?

You can detect toxicophores by applying structural alerts to SMILES strings, identifying potentially toxic functional groups within compound libraries to prioritize safer candidates for medicinal chemistry synthesis.

What is the best way to cluster small-molecule libraries by Tanimoto similarity for SAR analysis?

Clustering small-molecule libraries by Tanimoto similarity involves generating Morgan fingerprints from SMILES strings and computing pairwise similarity scores, enabling structure-activity relationship exploration and candidate prioritization.

How do I compute Tanimoto similarity for molecular fingerprints in cheminformatics?

Computing Tanimoto similarity requires generating Morgan fingerprints from SMILES strings using RDKit, then calculating similarity coefficients to quantify structural overlap for similarity clustering and SAR exploration.

Does RDKit support Murcko scaffold extraction and QED calculations for drug-likeness evaluation?

RDKit supports Murcko scaffold extraction and QED calculations, processing SMILES strings to output core molecular frameworks and quantitative drug-likeness estimates for small-molecule evaluation workflows.