molecularsets/moses

Molecular Sets (MOSES): A Benchmarking Platform for Molecular Generation Models

51
/ 100
Established

MOSES is a benchmarking platform for scientists and researchers in drug discovery who use deep generative models to discover new molecules. It takes a large collection of molecular structures as input and evaluates the quality and diversity of newly generated molecular compounds. This helps standardize research on molecular generation and facilitates the comparison of different models.

958 stars. No commits in the last 6 months.

Use this if you are a cheminformatician or medicinal chemist developing or evaluating molecular generation models and need a standardized way to compare their performance.

Not ideal if you are looking for a tool to directly synthesize molecules or predict their properties without focusing on model comparison.

drug-discovery molecular-design cheminformatics medicinal-chemistry molecular-generation
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 25 / 25

How are scores calculated?

Stars

958

Forks

270

Language

Python

License

MIT

Last pushed

Jul 08, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/molecularsets/moses"

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