What format do the molecules need to be in?

The skill primarily works with SMILES strings and RDKit-compatible molecule objects via the datamol library.

Does it detect specific problematic patterns like PAINS?

Yes, it includes filters for Pan-Assay Interference Compounds (PAINS), NIBR filters, and Lilly Demerits to identify potentially problematic structural alerts.

Can I process large chemical libraries efficiently?

Yes, the skill supports parallelization using n_jobs=-1, allowing for high-performance processing of thousands of molecules simultaneously.

What specific drug-likeness rules does this skill support?

It supports a wide range of rules including Lipinski's Rule of Five, Veber's rules, Oprea, CNS-likeness, and lead-like criteria (both soft and strict).

Is it possible to combine multiple filtering criteria?

Yes, you can use the Medchem Query Language or RuleFilters to combine various rules, alerts, and complexity constraints into a single workflow.

MedChem Molecular Triage

Name: MedChem Molecular Triage
Author: BbgnsurfTech

byBbgnsurfTech

•

Data Science & ML

Applies medicinal chemistry rules and structural filters to prioritize and triage molecular libraries for drug discovery.

MedChem is a specialized Python skill designed for molecular filtering and prioritization within drug discovery workflows. It provides a comprehensive suite of established drug-likeness rules (such as Lipinski's Rule of Five and Veber's rules), structural alerts like PAINS patterns, and complexity metrics to assess synthetic accessibility. By enabling automated screening of large chemical libraries, this skill helps researchers and developers detect problematic functional groups, calculate molecular properties, and identify high-quality lead candidates efficiently and at scale.

Key Features

01Structural alert detection (PAINS, NIBR filters, Lilly Demerits)

02Molecular complexity and synthetic accessibility scoring

03Drug-likeness rule application (Lipinski, Veber, CNS, lead-like)

04Medchem Query Language for complex filtering logic

053 GitHub stars

06Functional group and chemical entity identification

Use Cases

01Detecting reactive or problematic functional groups in chemical datasets

02Lead optimization and refinement of candidate molecules

03Initial triage of large compound libraries for drug discovery

What are Skills?·How to Install

Install with 🐟 Skill.Fish

npx skillfish add bbgnsurftech/claude-skills-collection medchem

For use in Claude.ai and ChatGPT

Download Skill