skills.rest
pradyumnasagar
pradyumnasagarCOMMUNITY
Explore all skills by this author →
𝕏@pradyumnasagarGitHub

scaffold-analysis

Analyze chemical libraries with Bemis-Murcko scaffolds, R-group decomposition, and MMP analysis.

6|2|Updated Jun 11, 2026
Search Tags:#chemoinformatics#scaffold analysis#SAR analysis#MMP analysis#R-group decomposition
One-click install
npx skills add https://github.com/pradyumnasagar/open-research-skills --skill scaffold-analysis-pradyumnasagar
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: scaffold-analysis
Source: https://github.com/pradyumnasagar/open-research-skills/tree/main/skills/chemoinformatics/scaffold-analysis
Command: npx skills add https://github.com/pradyumnasagar/open-research-skills --skill scaffold-analysis-pradyumnasagar

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires rdkit, mmpdb, scikit-learn, datamol, and includes scripts (resource) and references (resource) components.

What problem does it solve?

This Skill identifies and analyzes chemical libraries using Bemis-Murcko scaffolds, R-group decomposition, MMP analysis, and chemotype-aware ML train/test splits to find chemotype clusters, SAR transformation rules, and analog series.

Core Features & Use Cases

  • Scaffold Analysis: Identify and analyze compounds based on their chemical scaffolds.
  • R-Group Decomposition: Decompose series into R-groups for SAR analysis.
  • MMP Analysis: Perform matched molecular pair analysis for substructure transformation and activity changes.
  • ML Train/Test Splits: Balance QSAR splits based on chemical scaffold for better generalization.
  • Use Case: Use this Skill to determine the chemotype clusters in a library or to derive SAR transformation rules from a set of analog compounds.

Quick Start

Analyze the compounds in 'library.smi' and derive their Bemis-Murcko scaffolds and R-group information using the scaffold-analysis skill.

Frequently Asked Questions about scaffold-analysis

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

FAQPage Schema
How do I perform matched molecular pair analysis on a compound library?▼

Matched molecular pair (MMP) analysis identifies substructure transformations and their corresponding activity changes within a chemical library. This Skill uses mmpdb to derive SAR transformation rules from analog compounds.

How does Bemis-Murcko scaffold extraction work for chemotype clustering?▼

Bemis-Murcko scaffold extraction reduces compounds to their core ring systems and linkers, revealing chemotype clusters in a chemical library. This Skill identifies these frameworks to support virtual screening and retrosynthesis planning.

Can I use R-group decomposition for structure-activity relationship analysis?▼

R-group decomposition breaks down analog series into their core scaffolds and variable substituents. This Skill performs R-group decomposition to support structure-activity relationship (SAR) analysis and identify chemical transformations.

What is the best way to split QSAR datasets based on chemical scaffolds?▼

Chemotype-aware machine learning splits partition datasets by chemical scaffolds to improve model generalization. This Skill uses scikit-learn and datamol to balance train and test sets based on underlying Bemis-Murcko scaffolds.

Do I need rdkit and datamol to analyze chemical libraries for SAR?▼

Yes, this Skill relies on rdkit, datamol, mmpdb, and scikit-learn to process chemical libraries. These dependencies provide the necessary chemoinformatics functions for scaffold analysis, R-group decomposition, and matched molecular pair analysis.

Related Skills

learningmatter-mitlearningmatter-mit
144

drug-db-pubchem

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

Official
Intermediate
Zeyuyang-0420Zeyuyang-0420

molfeat

Generate molecular feature vectors from SMILES strings using molfeat.

Community
Advanced
felixboehmfelixboehm

molfeat

Convert chemical structures into machine learning-ready numerical formats.

Community
Intermediate
google-deepmindgoogle-deepmind
2.7k

chembl-database

Retrieve bioactive molecule, target, and activity data from the ChEMBL database.

Official
Intermediate