Jump to main content
Jump to site search
Access to RSC content Close the message box

Continue to access RSC content when you are not at your institution. Follow our step-by-step guide.

Issue 3, 2018
Previous Article Next Article

Deep learning for chemical reaction prediction

Author affiliations


Reaction predictor is an application for predicting chemical reactions and reaction pathways. It uses deep learning to predict and rank elementary reactions by first identifying electron sources and sinks, pairing those sources and sinks to propose elementary reactions, and finally ranking the reactions by favorability. Global reactions can be identified by chaining together these elementary reaction predictions. We carefully curated a data set consisting of over 11 000 elementary reactions, covering a broad range of advanced organic chemistry. Using this data for training, we demonstrate an 80% top-5 recovery rate on a separate, challenging benchmark set of reactions drawn from modern organic chemistry literature. A fundamental problem of synthetic chemistry is the identification of unknown products observed via mass spectrometry. Reaction predictor includes a pathway search feature that can help identify such products through multi-target mass search. Finally, we discuss an alternative approach to predicting electron sources and sinks using recurrent neural networks, specifically long short-term memory (LSTM) architectures, operating directly on SMILES strings. This approach has shown promising preliminary results.

Graphical abstract: Deep learning for chemical reaction prediction

Back to tab navigation

Article information

29 Sep 2017
01 Dec 2017
First published
01 Dec 2017

Mol. Syst. Des. Eng., 2018,3, 442-452
Article type

Deep learning for chemical reaction prediction

D. Fooshee, A. Mood, E. Gutman, M. Tavakoli, G. Urban, F. Liu, N. Huynh, D. Van Vranken and P. Baldi, Mol. Syst. Des. Eng., 2018, 3, 442
DOI: 10.1039/C7ME00107J

Social activity

Search articles by author