What is the Medchem skill for Claude Code?

It is a specialized capability that allows Claude to utilize the medchem Python library to automate molecular filtering and assess drug-likeness in chemical datasets.

Does it detect problematic structural patterns?

Yes, it includes filters for PAINS (Pan-Assay Interference Compounds), structural alerts from ChEMBL, NIBR filters, and Eli Lilly demerit scores.

Can this skill handle large molecular libraries?

Yes, the skill is designed for scale and supports parallel processing (n_jobs=-1) to handle thousands of molecules efficiently.

Which medicinal chemistry rules are supported?

The skill supports a wide range of rules including Lipinski's Rule of Five, Veber, Oprea, CNS-like, Lead-like (soft and strict), Rule of Three, and Reos rules.

Medicinal Chemistry Toolkit

Name: Medicinal Chemistry Toolkit
Author: x-cmd

byx-cmd

•

データサイエンスとML

Applies medicinal chemistry filters, drug-likeness rules, and structural alerts for molecular prioritization in drug discovery.

The Medchem skill equips AI coding agents with the capability to perform advanced chemoinformatics tasks using the medchem Python library. It enables the automated application of industry-standard molecular filters—including Lipinski's Rule of Five, Veber rules, and PAINS filters—to efficiently triage compound libraries. By integrating structural alert detection, molecular complexity calculations, and a specialized query language, this skill helps developers and researchers identify high-quality drug candidates, detect problematic functional groups, and streamline lead optimization workflows within a medicinal chemistry context.

主な機能

018 GitHub stars

02Calculate molecular complexity and synthetic accessibility metrics

03Identify specific chemical groups and reactive functional moieties

04Apply drug-likeness rules like Lipinski, Veber, and CNS guidelines

05Utilize a specialized Medchem Query Language for complex filtering logic

06Detect PAINS patterns and structural alerts (NIBR, Lilly Demerits)

ユースケース

01High-throughput screening and initial triage of large compound libraries

02Lead optimization filtering using strict medicinal chemistry criteria

03Automated identification of toxic or reactive structural patterns in chemical datasets

主な機能

018 GitHub stars

02Calculate molecular complexity and synthetic accessibility metrics

03Identify specific chemical groups and reactive functional moieties

04Apply drug-likeness rules like Lipinski, Veber, and CNS guidelines

05Utilize a specialized Medchem Query Language for complex filtering logic

06Detect PAINS patterns and structural alerts (NIBR, Lilly Demerits)

ユースケース

01High-throughput screening and initial triage of large compound libraries

02Lead optimization filtering using strict medicinal chemistry criteria

03Automated identification of toxic or reactive structural patterns in chemical datasets