medchem

Apply Lipinski, Veber, and PAINS filters to chemical compounds.

8|Updated Jan 13, 2026
One-click install
npx skills add https://github.com/hxk622/TokenDance --skill medchem-hxk622
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: medchem
Source: https://github.com/hxk622/TokenDance/tree/main/backend/app/skills/builtin/scientific/chemistry/medchem
Command: npx skills add https://github.com/hxk622/TokenDance --skill medchem-hxk622

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

This Skill streamlines the process of evaluating and prioritizing chemical compounds in drug discovery by applying established medicinal chemistry rules and filters.

Core Features & Use Cases

  • Drug-Likeness Assessment: Apply rules like Lipinski's Rule of Five and Veber's rules to predict oral bioavailability.
  • Structural Alert Filtering: Identify and remove problematic chemical substructures (e.g., PAINS, NIBR filters) that can lead to assay interference or toxicity.
  • Lead Optimization Filtering: Use stricter criteria to select promising candidates for further development.
  • Use Case: You have a library of 10,000 synthesized compounds. Use this Skill to quickly filter them down to a few hundred that meet basic drug-likeness criteria and are free from known problematic structural alerts, saving significant downstream experimental costs.

Quick Start

Use the medchem skill to apply the Rule of Five and common alerts filter to the provided molecule SMILES string 'CCO'.

Frequently Asked Questions about medchem

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

FAQPage Schema
How do I apply Lipinski's Rule of Five to filter molecules for drug discovery?

To apply Lipinski's Rule of Five for drug discovery, use this Skill to process chemical compounds and evaluate oral bioavailability. It applies established medicinal chemistry rules to filter molecules based on drug-likeness criteria.

What is the best way to identify PAINS structural alerts in a compound library?

Identifying PAINS structural alerts in a compound library involves applying specific filters to remove problematic substructures. This Skill applies PAINS and NIBR filters to detect assay interference or toxicity risks in molecules.

Can I use datamol and medchem libraries to prioritize compounds for lead optimization?

Yes, you can use the datamol and medchem libraries to prioritize compounds for lead optimization. This Skill utilizes these dependencies to apply stricter complexity metrics and drug-likeness rules for selecting promising candidates.

How do I filter a large library of synthesized compounds to reduce downstream experimental costs?

Filtering a large library of synthesized compounds reduces downstream experimental costs by applying medicinal chemistry rules. This Skill quickly triages thousands of molecules down to a few hundred meeting basic drug-likeness and structural alert criteria.

Does this molecular filtering approach support Veber's rules for predicting oral bioavailability?

Yes, this molecular filtering approach supports Veber's rules for predicting oral bioavailability. The Skill applies Veber's rules alongside Lipinski's criteria to assess the drug-likeness of chemical compounds.