How does it handle large molecular datasets?

The skill utilizes parallel processing via the `n_jobs` parameter, enabling efficient filtering of large datasets across multiple CPU cores.

What is the Medchem Query Language?

It is a specialized syntax that allows you to combine multiple chemical rules and property thresholds (like complexity or MW) into single, human-readable logic strings.

What is the primary purpose of the Medchem skill?

The Medchem skill is designed for molecular prioritization in drug discovery, allowing users to apply hundreds of medicinal chemistry rules and filters to compound libraries.

Can I filter out toxic or reactive compounds?

Yes, the skill includes specialized structural alerts like PAINS (Pan-Assay Interference Compounds), NIBR filters, and Lilly Demerits to identify potentially problematic molecules.

Which drug-likeness rules does it support?

It supports many standard rules including Lipinski's Rule of Five, Veber, Oprea, CNS-likeness, Lead-like (soft and strict), Rule of Three, and Reos rules.

Medchem Scientific Discovery

Name: Medchem Scientific Discovery
Author: jimmc414

byjimmc414

•

324

データサイエンスとML

Applies medicinal chemistry filters and drug-likeness rules to prioritize compound libraries for autonomous discovery.

概要

Medchem provides a comprehensive suite of tools for molecular filtering and prioritization within Claude Code. It enables researchers to programmatically apply established drug-likeness rules such as Lipinski's Rule of Five, detect problematic structural patterns like PAINS alerts, and calculate molecular complexity metrics. Designed for high-throughput workflows, this skill facilitates autonomous chemical discovery by triaging large compound libraries, assessing lead optimization candidates, and ensuring chemical quality through rigorous medicinal chemistry standards.

主な機能

Molecular complexity and synthetic accessibility scoring
Functional group and hinge-binder detection
324 GitHub stars
Established drug-likeness rules (Lipinski, Veber, CNS, Lead-like)
Medchem Query Language for complex multi-criteria filtering
Structural alert detection (PAINS, NIBR, Lilly Demerits)

ユースケース

High-throughput screening and triage of large compound libraries
Filtering molecules for specific pharmaceutical properties like CNS permeability
Lead optimization and refinement of medicinal chemistry leads

概要

主な機能

Molecular complexity and synthetic accessibility scoring
Functional group and hinge-binder detection
324 GitHub stars
Established drug-likeness rules (Lipinski, Veber, CNS, Lead-like)
Medchem Query Language for complex multi-criteria filtering
Structural alert detection (PAINS, NIBR, Lilly Demerits)

ユースケース

High-throughput screening and triage of large compound libraries
Filtering molecules for specific pharmaceutical properties like CNS permeability
Lead optimization and refinement of medicinal chemistry leads