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

Molfeat Molecular Featurization Hub

Turns SMILES structures into ML-ready feature vectors using 100+ featurizers such as ECFP, MACCS, descriptors and ChemBERTa embeddings.

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

What it does

Guides Claude in writing and running code with the Python library molfeat 0.11.0 to convert chemical structures (SMILES strings or RDKit/datamol Mol objects) into numerical representations for machine learning.

  • Calculators: per-molecule features, e.g. FPCalculator("ecfp", radius=3, fpSize=2048)
  • Transformers: scikit-learn compatible batch transformers with parallelism via n_jobs=-1
  • Pretrained transformers: ChemBERTa, ChemGPT, GIN, Graphormer embeddings with caching
  • ModelStore search over 100+ featurizers, YAML state save/reload for reproducibility, ignore_errors=True for bad SMILES, chunked processing for large libraries
  • Three reference files (API reference, featurizer catalog, examples) loaded only on demand to save context

Who it's for

  • Medicinal/computational chemists building QSAR/QSPR property models
  • Teams doing virtual screening or similarity search over large compound libraries
  • Data scientists wiring molecular data into scikit-learn or PyTorch pipelines
  • Anyone benchmarking several featurizers to pick the best representation

Example uses

  1. Build a QSAR model — "Featurize the SMILES column of my IC50 dataset with ecfp and train a Random Forest regressor" → generates Calculator + MoleculeTransformer + sklearn Pipeline code.
  2. Benchmark embeddings — "Compute ecfp, desc2D and ChemBERTa-77M-MLM features and compare cross-validation scores in a table" → runs all three and summarizes results.
  3. Similarity search — "Find the 20 most similar compounds to this molecule in a 100k library using MACCS keys" → writes chunked featurization plus Tanimoto similarity code.

· · · 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/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 /tmp/sci-skills && mkdir -p ~/.claude/skills && cp -r /tmp/sci-skills/skills/molfeat ~/.claude/skills/

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

  1. Check your Python version: molfeat 0.11.0 supports only Python 3.9–3.10. Run python --version, and create a dedicated env if needed: conda create -n molfeat python=3.10.
  2. Create the skills folder: mkdir -p ~/.claude/skills
  3. Clone the repository: git clone https://github.com/K-Dense-AI/scientific-agent-skills.git /tmp/sci-skills
  4. Copy the skill: cp -r /tmp/sci-skills/skills/molfeat ~/.claude/skills/ and verify the references folder came along.
  5. Install the library: activate your Python environment and run pip install "molfeat==0.11.0", or pip install "molfeat[transformer]==0.11.0" for deep-learning models.
  6. Verify: restart Claude Code and ask "use molfeat to convert these SMILES into ecfp fingerprints" to confirm the skill triggers.
View source on GitHub ↗License: MIT