skills.rest
silverstein
silversteinCOMMUNITY
Explore all skills by this author →
Website𝕏@matsilversteinGitHub

molfeat

Convert SMILES or RDKit molecules into numeric feature vectors for machine learning.

21|2|Updated Dec 8, 2025
Search Tags:#machine learning#virtual screening#rdkit#molecular featurization#qsar#ecfp#chembert a
One-click install
npx skills add https://github.com/silverstein/claude-scientific-skills-desktop --skill molfeat-silverstein
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: molfeat
Source: https://github.com/silverstein/claude-scientific-skills-desktop/tree/main/corpus/molfeat
Command: npx skills add https://github.com/silverstein/claude-scientific-skills-desktop --skill molfeat-silverstein

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

Molfeat eliminates the hard, error-prone step of converting chemical structures (like SMILES) into reliable numeric features for machine learning, so you can focus on modeling instead of featurization details.

Core Features & Use Cases

  • Molecular featurization at scale: Convert SMILES or RDKit molecules into fixed-length vectors for QSAR/QSPR, similarity search, and virtual screening.
  • 100+ featurizers in one unified workflow: Fingerprints (ECFP/MACCS/MAP4), 2D/3D descriptors (RDKit, Mordred), pharmacophore features, shape descriptors, and pretrained embeddings (e.g., ChemBERTa).
  • ML-ready tooling: Use calculators for single-molecule computation and scikit-learn compatible transformers for batch processing with parallelization and caching.
  • Use case: Build a QSAR model by featurizing a dataset of drug-like compounds with ECFP fingerprints, then training a regressor or classifier on the resulting feature matrix.

Quick Start

Featurize a list of SMILES with Molfeat’s ECFP representation to produce an array of numerical features suitable for training a machine learning model.

Frequently Asked Questions about molfeat

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

FAQPage Schema
How do I convert SMILES to numeric features for machine learning?▼

You can convert SMILES to numeric features for machine learning by computing fixed-size vectors like ECFP fingerprints or pretrained embeddings directly from the molecular structures using a featurization pipeline.

What molecular featurization methods work best for QSAR modeling?▼

Effective molecular featurization methods for QSAR modeling include ECFP fingerprints, 2D/3D descriptors, pharmacophore features, and pretrained molecular embeddings, which transform chemical structures into ML-ready numeric vectors.

Can I use RDKit molecules for batch featurization in scikit-learn?▼

Yes, you can use RDKit molecules for batch featurization in scikit-learn by utilizing compatible transformers that process chemical structures in parallel and return fixed-size numpy feature arrays.

Does molfeat support pretrained molecular embeddings like ChemBERTa?▼

Yes, molfeat supports pretrained molecular embeddings like ChemBERTa alongside 100+ other featurizers, allowing you to instantly generate numeric vectors from SMILES for representation learning and virtual screening.

What is the best way to calculate ECFP fingerprints for virtual screening?▼

The best way to calculate ECFP fingerprints for virtual screening is using a unified featurization workflow that accepts SMILES or RDKit molecules and outputs fixed-length numpy arrays optimized for similarity search.

Related Skills

Explore More Data & Analytics Skills→
SologaSologa
1

molfeat

Convert SMILES strings into over 100 molecular fingerprints and descriptors.

Community
Intermediate
shushuznshushuzn
4

molfeat

Convert SMILES or RDKit molecules into numerical feature vectors for machine learning.

Community
Intermediate
Lord1EgyptLord1Egypt
2

molfeat

Convert SMILES strings and RDKit molecules into numerical feature vectors.

Community
Advanced
pradyumnasagarpradyumnasagar
6

molecular-descriptors

Calculate molecular fingerprints and physicochemical descriptors from SMILES using RDKit.

Community
Advanced