MorganCThomas/MolScore

An automated scoring function to facilitate and standardize the evaluation of goal-directed generative models for de novo molecular design

64
/ 100
Established

When designing new drug molecules, you need a way to automatically evaluate how well your generated compounds meet specific goals, like desired properties or activity. This tool takes your generated molecular structures (SMILES strings) and applies a customizable set of scoring functions, providing a combined score for each molecule. It's for medicinal chemists or computational drug designers who are creating new molecules using generative AI and need to assess their quality systematically.

225 stars. Available on PyPI.

Use this if you are using generative models to design novel drug candidates and need an automated, standardized way to score, evaluate, and benchmark the generated molecules against multiple desired properties.

Not ideal if you are manually designing molecules without generative models or if you only need to evaluate a single molecular property without combining multiple objectives.

drug-discovery medicinal-chemistry molecular-design computational-chemistry hit-to-lead
Maintenance 10 / 25
Adoption 10 / 25
Maturity 25 / 25
Community 19 / 25

How are scores calculated?

Stars

225

Forks

34

Language

Python

License

MIT

Last pushed

Jan 20, 2026

Commits (30d)

0

Dependencies

15

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/generative-ai/MorganCThomas/MolScore"

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