Claude Skill MartBrowse skillsQuick linesLearn by videoTerminal guideWhat is a Skill?
 
← Back to list

Medchem Compound Filtering

Triage compound libraries with drug-likeness rules (Lipinski, Veber, CNS), PAINS/NIBR structural alerts, complexity metrics, and the medchem query language.

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

What it does

  • Wraps the datamol-io medchem library to filter and prioritize molecules for drug discovery.
  • Applies literature-derived rules (Ro5, Ro3, Veber, CNS, lead-like) to single molecules or whole libraries, returning pandas DataFrames with pass_all / pass_any columns.
  • Runs structural alert catalogs (PAINS, Brenk, ChEMBL common alerts, NIBR screening-deck rules with severity), ZINC-15 percentile complexity metrics (bertz, sas, qed, whitlock…), and chemical-group detection (privileged scaffolds, covalent warheads).
  • Builds multi-criteria filters with the medchem query language: MATCHRULE, HASALERT, HASPROP, HASGROUP, HASSUBSTRUCTURE combined with AND/OR/NOT.
  • Flags practical gotchas: DataFrame vs boolean-mask return types, n_jobs=-1 for libraries over 1000 molecules, and the optional conda-only Lilly demerit filter.

Who it's for

  • Medicinal chemists triaging hit-to-lead or lead-optimization candidates.
  • Cheminformatics and computational chemistry researchers cleaning large SMILES libraries.
  • AI drug-discovery engineers post-filtering generative-model output for alerts and synthesizability.

Example uses

  1. Apply Ro5 + Veber and exclude PAINS across tens of thousands of SMILES in compounds.csv, writing filtered_compounds.csv.
  2. Combine rule_of_leadlike_soft, NIBR severity < 10, and Bertz complexity below the 95th percentile into one pass mask for lead candidates.
  3. Use the common_warhead_covalent_inhibitors group to isolate molecules containing covalent warheads for separate review.

· · · Install guide · · ·

Try it now, no install

Paste this into Claude to use the skill without installing anything.

Read the instructions in this file and follow them to help me:
https://raw.githubusercontent.com/K-Dense-AI/scientific-agent-skills/HEAD/skills/medchem/SKILL.md

What I want: (describe your task here)

If Claude can't open the link, open it yourself and paste the contents instead.

↓ If it works for you, download the ZIP below and install it. Then it runs on its own — no pasting each time.

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 && mkdir -p ~/.claude/skills && cp -r scientific-agent-skills/skills/medchem ~/.claude/skills/

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

  1. Open a terminal and clone the repo: git clone https://github.com/K-Dense-AI/scientific-agent-skills.git
  2. Create the skills directory: mkdir -p ~/.claude/skills
  3. Copy just this skill: cp -r scientific-agent-skills/skills/medchem ~/.claude/skills/
  4. In a Python 3.9+ environment, install the dependencies: uv pip install medchem datamol (RDKit comes along automatically).
  5. (Optional) For the Eli Lilly demerit filter, run mamba install -c conda-forge lilly-medchem-rules.
  6. Restart Claude Code, then prompt something like "apply Lipinski rules and a PAINS filter to the SMILES column in this CSV" to trigger the skill.
View source on GitHub ↗License: MIT