garywei944/ChemFlow
Uncover meaningful structures of latent spaces learned by generative models with flows!
ChemFlow helps drug discovery scientists and computational chemists design new molecules by exploring chemical spaces more effectively. It takes in existing molecular datasets (like MOSES, ZINC250K, ChEMBL) and, using a generative model, helps you generate novel molecules with desired properties, perform multi-objective optimization, and navigate chemical structures for specific tasks. This is ideal for researchers in medicinal chemistry or materials science seeking to discover compounds.
No commits in the last 6 months.
Use this if you need to generate and optimize new chemical compounds with specific characteristics or explore the relationship between molecular structures and their properties.
Not ideal if your primary goal is simply to analyze existing molecular data without the need for generative design or complex chemical space traversal.
Stars
43
Forks
8
Language
Python
License
MIT
Category
Last pushed
May 10, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/generative-ai/garywei944/ChemFlow"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
simmzx/SynFrag
Synthetic Accessibility via Fragment Assembly Generation
Dunni3/FlowMol
Mixed continous/categorical flow-matching model for de novo molecule generation.
ALPHAPhoenix007/MatterGen
MatterGen is an AI-powered material property prediction system that analyzes molecular...
Gruz2520/3DGAN-for-MOF
3DGAN для генерации металло-органических каркасов со свойствами адсорбции газов. 3DGAN for the...