medchem

Apply drug-likeness rules and structural alerts to chemical compounds.

Updated Mar 10, 2026

Search Tags:#drug discovery #medicinal chemistry #cheminformatics #drug likeness #structural alerts #compound filtering

Ready to run

npx skills add https://github.com/felixboehm/biochem-allergy --skill medchem-felixboehm

💬 Prompt for ChatGPT / Claude Chat▼

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

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

This Skill streamlines drug discovery by providing robust tools to filter and prioritize chemical compounds based on medicinal chemistry rules and structural properties, saving researchers time and resources.

Core Features & Use Cases

Drug-Likeness & Lead-Likeness: Apply established rules (Lipinski, Veber, Oprea) to assess compound quality.
Structural Alert Filtering: Detect problematic substructures (PAINS, NIBR, Lilly Demerits) that can cause assay interference or toxicity.
Use Case: A medicinal chemist can use this Skill to quickly filter a library of 10,000 compounds, removing those with known liabilities and identifying a smaller, high-quality set for further experimental validation.

Quick Start

Use the medchem skill to apply the Rule of Five and common alerts filter to a list of SMILES strings.

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-likeness using Python?▼

To filter a compound library for drug-likeness, you can apply established rules like Lipinski, Veber, and Oprea using Python libraries such as RDKit and datamol. This systematically evaluates small molecules to assess compound quality.

What are structural alerts in medicinal chemistry and how do I detect them?▼

Structural alerts in medicinal chemistry are problematic substructures that can cause assay interference or toxicity. You detect them by applying PAINS, NIBR, and Lilly Demerits filters to chemical compounds during lead optimization.

Can I use RDKit and datamol to triage a large compound library for drug discovery?▼

Yes, you can use RDKit and datamol to triage a large compound library for drug discovery. The process applies medicinal chemistry filters and drug-likeness rules to identify a smaller, high-quality set for experimental validation.

What is the best way to prioritize chemical compounds for lead optimization?▼

The best way to prioritize chemical compounds for lead optimization is to assess molecular properties by applying drug-likeness rules and structural alert filters. This removes compounds with known liabilities and prioritizes high-quality candidates.

Does applying medicinal chemistry filters require a specific list of SMILES strings?▼

Applying medicinal chemistry filters requires a list of SMILES strings as input data. You use these chemical compound representations to apply the Rule of Five and common alerts filters for systematic evaluation.