mol-ml

Generate Python code for molecular ML workflows using RDKit.

2|Updated Jan 7, 2026
One-click install
npx skills add https://github.com/mcox3406/claude-comp-chem-skills --skill mol-ml
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: mol-ml
Source: https://github.com/mcox3406/claude-comp-chem-skills/tree/main/mol-ml
Command: npx skills add https://github.com/mcox3406/claude-comp-chem-skills --skill mol-ml

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

This Skill addresses common challenges and pitfalls in building machine learning models with molecular data, ensuring robust and reliable results.

Core Features & Use Cases

  • Scaffold Splitting: Prevents data leakage by ensuring molecules with the same core structure are not present in both training and testing sets.
  • Fingerprint Selection Guidance: Recommends appropriate molecular fingerprints (e.g., Morgan, RDKit) based on the specific ML task (similarity search, QSAR, etc.).
  • Pitfall Avoidance: Highlights and provides solutions for common errors like ignoring fingerprint types, not handling parse failures, and feature matrix shape issues.
  • Use Case: When developing a QSAR model, use this Skill to perform a scaffold-based split and select the most informative Morgan fingerprints to avoid overestimating model performance.

Quick Start

Use the mol-ml skill to split a list of SMILES strings by scaffold, ensuring no data leakage between training and testing sets.

Frequently Asked Questions about mol-ml

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

FAQPage Schema
How do I prevent data leakage when splitting molecular data for machine learning?

To prevent data leakage in molecular machine learning, apply scaffold splitting to ensure molecules sharing the same core structure are separated into either the training or testing set, never both.

What is the best way to select molecular fingerprints for a QSAR model?

Selecting molecular fingerprints for QSAR models depends on the specific task, with Morgan and RDKit fingerprints being recommended choices provided by this Skill to ensure informative feature generation.

How do I generate molecular fingerprints from SMILES strings using RDKit?

Generate molecular fingerprints from SMILES strings using RDKit by parsing the strings, handling potential parse failures, and converting the molecules into feature matrices to avoid shape issues during model training.

Why does my molecular machine learning model overestimate performance on test data?

Molecular machine learning models overestimate performance when data leakage occurs from random splitting, which is mitigated by using scaffold splitting to segregate structurally similar molecules.

Do I need RDKit to perform scaffold splitting on molecular data?

Yes, RDKit is a required dependency for performing scaffold splitting on molecular data, as it provides the necessary cheminformatics functions to manipulate molecules and extract core structures.

What are common pitfalls when building machine learning workflows with molecular data?

Common pitfalls in molecular machine learning workflows include ignoring fingerprint types, failing to handle SMILES parse failures, and encountering feature matrix shape issues during model training.