Claude Skill MartBrowse skillsWhat is a Skill?
 
← Back to list

Medchem Compound Filtering

Triage compound libraries with medicinal chemistry rules (Lipinski, PAINS, NIBR) and the medchem query language.

Data & AnalyticsAdvanced★ 33,030⑂ 3,248AI score 8/10Last updated: Aug 9, 2026

What it does

Teaches Claude to drive the open-source medchem Python library for molecular filtering and prioritization in drug discovery.

  • Drug-likeness rules: Lipinski Rule of 5, Veber, CNS, lead-like and more, applied in batch via RuleFilters
  • Structural alerts: PAINS, Brenk, ChEMBL common alerts, and Novartis NIBR screening-deck curation
  • Complexity metrics: Bertz, SAS, QED, Whitlock compared against ZINC-15 percentile thresholds
  • Chemical group detection: privileged scaffolds, covalent warheads, rings-in-drugs catalogs
  • Query language: compose multi-criteria filters such as MATCHRULE("rule_of_five") AND NOT HASALERT("pains")

Return types (DataFrame vs boolean mask) and parallelization tips (n_jobs=-1) are documented, so large libraries are handled correctly.

Who it's for

  • Medicinal chemists working through hit-to-lead and lead optimization
  • Computational chemists and data scientists triaging virtual-screening output at scale
  • AI drug-discovery teams filtering generative-model molecules for alerts and synthetic tractability

Example uses

  1. Library triage: load SMILES from compounds.csv, apply Rule of 5 + Veber plus a PAINS exclusion, and write filtered_compounds.csv
  2. Lead-optimization gate: keep only candidates passing lead-like soft rules, NIBR severity < 10, and Bertz complexity below the 95th percentile
  3. Covalent hunting: select molecules matching the common_warhead_covalent_inhibitors group to build a covalent-inhibitor shortlist

· · · Install guide · · ·

Install in the Claude app (no terminal)
  1. Download the ZIP with the button below.
  2. In Claude, open Settings → Capabilities and turn on 'Code execution and file creation'. (one time)
  3. Go to Customize → Skills → + → 'Upload a skill' and upload the ZIP.
↓ Download ZIP
Install in Claude Code

Let Claude do it — paste this into Claude Code

Install the skill I found on Claude Skill Mart.
Copy the skills/medchem folder from the GitHub repo K-Dense-AI/scientific-agent-skills into my ~/.claude/skills/medchem/.
When it's done, tell me in one line what this skill can do.

Install with a command instead

git clone https://github.com/K-Dense-AI/scientific-agent-skills.git /tmp/scientific-agent-skills && mkdir -p ~/.claude/skills && cp -r /tmp/scientific-agent-skills/skills/medchem ~/.claude/skills/

⚠ This is a third-party skill. Check the source repository before installing.

  1. Open a terminal and confirm Python 3.9+ is available: python --version
  2. Install the library: uv pip install medchem datamol (or pip install medchem datamol)
  3. Optional — for the Eli Lilly demerit filter, run mamba install -c conda-forge lilly-medchem-rules in a conda environment
  4. Clone the skills repository: git clone https://github.com/K-Dense-AI/scientific-agent-skills.git
  5. Copy the skill into place: mkdir -p ~/.claude/skills && cp -r scientific-agent-skills/skills/medchem ~/.claude/skills/
  6. Restart Claude Code and try a prompt like "Apply Rule of 5 and a PAINS filter to this SMILES list" to trigger the skill.
View source on GitHub ↗License: MIT