simmzx/SynFrag
Synthetic Accessibility via Fragment Assembly Generation
SynFrag helps medicinal chemists and drug discovery scientists quickly assess how easy or difficult it will be to synthesize a potential drug molecule. You provide a molecule's chemical structure (SMILES string), and it predicts a "Synthetic Accessibility" score. This score helps you decide if a compound is feasible to create in the lab or if you should explore alternative designs, much like an experienced synthetic chemist would.
Available on PyPI.
Use this if you need to rapidly screen many candidate molecules for their synthetic feasibility during early-stage drug discovery, prioritizing those that are easier to make.
Not ideal if you need a detailed, step-by-step retrosynthesis plan, as SynFrag focuses on overall synthetic accessibility, not specific reaction pathways.
Stars
21
Forks
3
Language
Python
License
MIT
Category
Last pushed
Feb 01, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/generative-ai/simmzx/SynFrag"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related tools
Dunni3/FlowMol
Mixed continous/categorical flow-matching model for de novo molecule generation.
garywei944/ChemFlow
Uncover meaningful structures of latent spaces learned by generative models with flows!
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...