Molecular Transformers
AI for chemical reaction prediction and synthesis planning
README
Molecular Transformer This is the code for the "Molecular Transformer: A Model for Uncertainty-Calibrated Chemical Reaction Prediction" paper published in ACS Central Science. The preprint presented at the ML for Molecules Materials workshop at Neurips 2018 can be found on ChemRxiv. To implement our models we were based on OpenNMT-py (v0.4.1). A trained model was made available online through a graphical user interface on the IBM RXN for Chemistry platform. Install requirements Create a new…
- Repository
- github.com/pschwllr/moleculartransformer
Source attribution
- GitHub — github.com/pschwllr/moleculartransformer
- Awesome AI for Science — github.com/pschwllr/moleculartransformer
Related resources
AstraZeneca's industrial-grade retrosynthetic planning tool using MCTS to recursively decompose molecules into purchasable precursors, with multi-step route scoring and support for custom one-step models (v4.0, 2024)
Generative AI system for antibiotic discovery that searches billions of synthesizable molecules by combining molecular building blocks through real chemical reactions, experimentally validating novel compounds active against drug-resistant bacteria