medchem

Filter compound libraries with medicinal chemistry rules and structural alerts.

1|Updated Mar 19, 2026
One-click install
npx skills add https://github.com/JosephWoodall/noosphere --skill medchem-josephwoodall
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: medchem
Source: https://github.com/JosephWoodall/noosphere/tree/main/.agent/skills/medchem
Command: npx skills add https://github.com/JosephWoodall/noosphere --skill medchem-josephwoodall

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

Medicinal chemistry filtering to triage large compound libraries by applying drug-likeness rules, structural alerts, PAINS checks, and complexity metrics to prioritize candidates for further development.

Core Features & Use Cases

  • Rule-based filtering: Apply Ro5/Ro3/CNS/lead-like and other rules to molecules to identify drug-like candidates.
  • Structural alerts and PAINS: Flag common problematic patterns and remove high-risk compounds.
  • Complexity and constraints: Compute complexity metrics and apply property constraints to guide lead optimization.
  • Workflow integration: Use the provided Python API and the filter script to batch-process libraries.

Quick Start

Filter a sample molecule list using the medchem RuleFilters and CommonAlertsFilters to obtain passes and flags for screening.

Frequently Asked Questions about medchem

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

FAQPage Schema
How do I apply Lipinski and Veber rules to filter a compound library for drug discovery?

To apply Lipinski and Veber rules for drug discovery, use the medchem Skill to filter compound libraries by drug-likeness. It evaluates large libraries in parallel, ranking candidates by Ro5, Ro3, CNS, and lead-like properties to identify suitable molecules for early screening workflows.

What is the best way to run PAINS checks and structural alerts on large molecule datasets?

Running PAINS checks and structural alerts on large datasets is best handled by batch processing scripts using the medchem and RDKit libraries. The Skill flags common problematic patterns and removes high-risk compounds, enabling fast library triage across extensive molecular collections.

Can I use pandas and datamol to compute complexity metrics for lead optimization?

Yes, you can use pandas and datamol to compute complexity metrics for lead optimization. The Skill integrates these dependencies to apply property constraints, calculating molecular complexity to guide decisions during hit-to-lead and lead-optimization workflows.

How do I batch process medicinal chemistry rules for early screening workflows?

Batch processing medicinal chemistry rules for early screening is done using the Skill's provided Python API and filter scripts. It supports modular operation across medchem.rules, medchem.structural, and medchem.constraints to parallelize evaluation across large compound libraries.

Does the medchem Skill support evaluating compound libraries for CNS drug-likeness?

Yes, the medchem Skill supports evaluating compound libraries for CNS drug-likeness. It applies rule-based filtering to identify drug-like candidates suitable for central nervous system targets, running parallelized evaluations across large molecular datasets for early drug discovery.