Radical Predictor

Radical Predictor is a deep learning based software that predicts the outcome of raadical reactions. RMechRP offers two interfaces: (1) Single Step Predictor; and (2) Pathway Predictor. In the single step prediction, the trained deep learning models identify the reactive molecular orbitals and rank their mechanistic interactions based on their chemical plausibility. In the pathway search, the trained deep learning models produce the mechanistic pathways starting from a given set of reactants. The user can search for any desired target within the produced pathways.

Predict the full out come and chemical interpretation of a radical mechanistic reaction.

single step

Predict the mechanistic pathways starting from the input reactants.

pathway

Reference

If you use Radical Reaction Predictor, please cite the following reference:
@article{tavakoli2023ai, title={AI for Interpretable Chemistry: Predicting Radical Mechanistic Pathways via Contrastive Learning}, author={Tavakoli, Mohammadamin and Chiu, Yin Ting T and Shmakov, Alexander and Carlton, Ann Marie and Van Vranken, David and Baldi, Pierre}, journal={arXiv preprint arXiv:2311.01118}, year={2023} }