medchem

Filter compound libraries with medicinal chemistry rules and structural alerts.

Updated Jul 1, 2026
One-click install
npx skills add https://github.com/jasrajtulsi/GRAD-SCOPE --skill medchem-jasrajtulsi
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: medchem
Source: https://github.com/jasrajtulsi/GRAD-SCOPE/tree/main/.claude/skills/medchem
Command: npx skills add https://github.com/jasrajtulsi/GRAD-SCOPE --skill medchem-jasrajtulsi

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

Medchem removes the manual burden of screening large compound libraries by applying medicinal chemistry rules, structural alerts, complexity filters, and curated functional group checks consistently.

Core Features & Use Cases

  • Rule-based triage: Apply Lipinski, Veber, CNS, lead-like, and fragment-style filters to assess drug-likeness and developability.
  • Structural alert screening: Flag PAINS, NIBR, Brenk, and other unwanted motifs to catch problematic compounds early.
  • Library-wide workflows: Process CSV, TSV, SDF, or SMILES inputs, generate pass/fail tables, and support hit-to-lead, lead optimization, and CNS-focused filtering workflows.

Quick Start

Ask the skill to filter an attached molecule file using medchem rules, alerts, or the query language and return the passing compounds with reasons and summary metrics.

Frequently Asked Questions about medchem

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

FAQPage Schema
How do I filter compound libraries for PAINS and structural alerts?

Filter compound libraries for PAINS and structural alerts by applying medicinal chemistry rules to catch problematic motifs early. This process screens inputs like SMILES or SDF files and generates pass/fail tables with severity annotations for hit-to-lead workflows.

What is the best way to triage SMILES files for drug-likeness?

Triage SMILES files for drug-likeness by applying rule-based filters like Lipinski, Veber, and lead-like criteria. This evaluates developability and outputs boolean results alongside summary metrics for batch compound curation.

Can I use RDKit and pandas to batch process CSV files for CNS profiling?

Yes, you can batch process CSV files for CNS profiling using RDKit and pandas. The workflow applies CNS-focused filtering rules to assess drug-likeness and executes parallel processing to produce summary reports and pass/fail tables.

Does medchem support processing large SDF inputs in parallel?

Yes, processing large SDF inputs supports parallel batch execution using medchem and datamol. This enables efficient library-wide triage by applying complexity thresholds and structural alerts to generate curated pass/fail result tables.

How do I apply a query language to filter molecules in a text file?

Apply a query language to filter molecules in a text file by defining structural and complexity criteria. The workflow processes the text inputs, returning passing compounds alongside documented failure reasons and severity annotations.