medchem

Triage compound libraries with medicinal chemistry rules and structural alerts.

13|3|Updated Jun 10, 2026

Search Tags:#drug discovery #medicinal chemistry #compound filtering #molecular filtering #复杂性评估

Ready to run

npx skills add https://github.com/tassiovale/claude-code-kit --skill medchem-tassiovale

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: medchem
Source: https://github.com/tassiovale/claude-code-kit/tree/main/skills/medchem
Command: npx skills add https://github.com/tassiovale/claude-code-kit --skill medchem-tassiovale

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

The medchem Skill allows users to efficiently triage and prioritize compound libraries in drug discovery by applying drug-likeness rules, structural alerts, and complexity metrics.

Core Features & Use Cases

Medicinal Chemistry Rules: Apply Lipinski's Rule of Five and other drug-likeness rules to compounds.
Structural Alert Filters: Apply filters for common alert patterns like PAINS and NIBR.
Complexity Metrics: Assess compound complexity against precomputed ZINC-15 thresholds.
Use Case: Use this Skill to quickly assess a compound library for drug-likeness and structural integrity before further experimentation.

Quick Start

Apply medchem to your compounds using the 'filter_molecules.py' script with the --rules and --complexity flags.

Frequently Asked Questions about medchem

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

FAQPage Schema

How do I filter a compound library for drug discovery using medicinal chemistry rules?▼

You can filter a compound library for drug discovery by applying drug-likeness rules, structural alerts, and complexity metrics. This Skill uses the 'filter_molecules.py' script with flags like --rules and --complexity to triage compounds before further experimentation.

What are structural alert filters for compound screening and how do they work?▼

Structural alert filters identify and remove compounds with common problematic patterns like PAINS and NIBR. Applying these filters during early drug discovery ensures structural integrity and prevents selecting compounds with known assay interference or toxicity risks.

Can I assess molecular complexity against ZINC-15 thresholds for compound libraries?▼

Yes, you can assess compound complexity against precomputed ZINC-15 thresholds. This complexity metrics evaluation helps prioritize molecules in drug design by flagging overly complex structures that may hinder successful synthesis or optimization.

Do I need RDKit and datamol to apply Lipinski's Rule of Five to compounds?▼

Yes, you need Python, RDKit, and datamol installed to apply Lipinski's Rule of Five and other medicinal chemistry rules. These dependencies handle the molecular operations required to evaluate drug-likeness and execute the filtering scripts.

What is the best way to triage compounds in early drug design using Python?▼

The best way to triage compounds is by applying multiple medicinal chemistry filters simultaneously. This Skill combines Lipinski's Rule of Five, structural alert filters, and complexity metrics to quickly assess a compound library's drug-likeness before experimental steps.

When should I not use automated molecular filtering for compound libraries?▼

Automated molecular filtering is designed for early stage compound triage and should not replace detailed experimental validation. It is intended to prioritize libraries by drug-likeness and structural integrity, not to provide final confirmation of a compound's biological activity or safety.