MarkusFerdinandDablander/ECFP-Sort-and-Slice

Sort & Slice: A Simple and Superior Alternative to Hash-Based Folding for Extended-Connectivity Fingerprints (ECFPs)

37
/ 100
Emerging

When analyzing chemical compounds, this project helps you transform RDKit molecule objects into a numerical representation called Extended-Connectivity Fingerprints (ECFPs). It takes your RDKit molecule objects as input and produces a vector of numbers, making it easier to use these chemical structures in machine learning models for tasks like predicting molecular properties. Medicinal chemists, computational chemists, and cheminformaticians who work with molecular data for drug discovery or materials science would use this.

No commits in the last 6 months.

Use this if you need to generate high-quality, vectorial ECFPs for molecular property prediction and other cheminformatics applications, aiming for better predictive performance than traditional methods.

Not ideal if you primarily work with other molecular representations or do not use RDKit for handling chemical structures.

cheminformatics drug-discovery molecular-modeling property-prediction computational-chemistry
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 5 / 25
Maturity 16 / 25
Community 16 / 25

How are scores calculated?

Stars

10

Forks

6

Language

Jupyter Notebook

License

MIT

Last pushed

Feb 13, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/MarkusFerdinandDablander/ECFP-Sort-and-Slice"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.