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

Molfeat Molecular Featurization Hub

A guide skill for turning SMILES into 100+ ML-ready features with molfeat — ECFP, MACCS, descriptors and ChemBERTa embeddings.

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

What it does

  • Walks through converting SMILES/RDKit molecules into numerical features for ML using the molfeat library.
  • Separates the three layers clearly: molfeat.calc (per-molecule calculators), molfeat.trans (scikit-learn compatible, parallel batch transformers), and molfeat.trans.pretrained (deep embeddings like ChemBERTa, GIN, Graphormer).
  • Includes production tips: n_jobs=-1 parallelism, skipping invalid SMILES, saving/loading YAML featurizer state for reproducibility, chunked processing for big datasets, and npz-based embedding caching instead of pickle.
  • States constraints up front: Python 3.9–3.10, molfeat 0.11.0, datamol/PyTorch, optional extras, and MAP4 needing separate installation.

Who it's for

  • Cheminformatics and drug-discovery researchers building QSAR/QSPR models or virtual screens.
  • ML engineers training neural networks on molecular data.
  • Data scientists benchmarking multiple featurizers to pick the best representation.

Example uses

  1. Featurize a CSV of compound SMILES into 2048-bit ECFP and feed it into a Random Forest activity model.
  2. Search the ModelStore for ChemBERTa-77M-MLM, load it, and extract 768-dim embeddings for transfer learning.
  3. Process a 100K+ molecule library in chunks with ignore_errors=True, then export the exact featurizer config to YAML for reproducibility.

· · · 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/molfeat/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/molfeat folder from the GitHub repo K-Dense-AI/scientific-agent-skills into my ~/.claude/skills/molfeat/.
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/molfeat ~/.claude/skills/

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

  1. Create a Python 3.9 or 3.10 virtual environment (molfeat 0.11.0 will not install on 3.11+).
  2. Install the library: uv pip install "molfeat==0.11.0" (or plain pip install). Add uv pip install "molfeat[transformer]==0.11.0" if you need ChemBERTa/ChemGPT.
  3. Clone the skill repo: git clone https://github.com/K-Dense-AI/scientific-agent-skills.git
  4. Copy the skill folder: mkdir -p ~/.claude/skills && cp -r scientific-agent-skills/skills/molfeat ~/.claude/skills/
  5. Restart Claude Code, then ask something like "featurize these SMILES with ECFP" to trigger the skill.
  6. Verify the bundled references/ docs (available_featurizers.md, examples.md, api_reference.md) came along with the copy.
View source on GitHub ↗License: MIT