licheng-xu-echo/RXNGraphormer

Official implementation of "A unified pre-trained deep learning framework for cross-task reaction performance prediction and synthesis planning"

55
/ 100
Established

This tool helps chemists and material scientists predict outcomes and plan syntheses for chemical reactions. You input chemical structures and reaction conditions, and it predicts properties like yield, regioselectivity, or enantioselectivity, or suggests precursors for a desired product (retrosynthesis) or products from given reactants (forward synthesis). It's designed for researchers needing to efficiently explore and optimize reaction pathways.

Available on PyPI.

Use this if you are a chemist or chemical engineer who needs to quickly evaluate potential reaction outcomes or design synthetic routes for new molecules without extensive lab work.

Not ideal if you need to simulate complex reaction mechanisms at an atomic level or require detailed quantum mechanical analysis of reaction intermediates.

organic-synthesis reaction-prediction retrosynthesis-planning chemical-research drug-discovery
Maintenance 6 / 25
Adoption 7 / 25
Maturity 25 / 25
Community 17 / 25

How are scores calculated?

Stars

35

Forks

10

Language

Jupyter Notebook

License

MIT

Last pushed

Jan 07, 2026

Commits (30d)

0

Dependencies

68

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/licheng-xu-echo/RXNGraphormer"

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