Neural Networks for the Prediction of Organic Chemistry Reactions

By Jennifer N. Wei, David Kristjanson Duvenaud, Alán Aspuru-Guzik. 2016

379 citations recorded by the source corpus.

Reaction prediction remains one of the major challenges for organic chemistry and is a prerequisite for efficient synthetic planning. It is desirable to develop algorithms that, like humans, “learn” from being exposed to examples of the application of the rules of organic chemistry. We explore the use of neural networks for predicting reaction types, using a new reaction fingerprinting method. We combine this predictor with SMARTS transformations to build a system which, given a set of reagents and reactants, predicts the likely products. We test this method on problems from a popular organic chemistry textbook.

Subfields: Computational Theory and Mathematics, Inorganic Chemistry, Materials Chemistry, Model Architectures, Computational Chemistry & Drug Discovery

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computational Theory and Mathematics

1. Gisbert Schneider
2. Francesca Grisoni
3. Tommi S. Jaakkola
4. Philippe Schwaller
5. Regina Barzilay
6. Wengong Jin
7. Teodoro Laino
8. José Jiménez-Luna

In Inorganic Chemistry

1. Philippe Schwaller
2. Teodoro Laino
3. C. Bekas
4. Théophile Gaudin
5. Zhenpeng Zhou
6. Xiaocheng Li
7. Richard N. Zare
8. Alán Aspuru-Guzik

In Materials Chemistry

1. Gisbert Schneider
2. Francesca Grisoni
3. Tommi S. Jaakkola
4. Regina Barzilay
5. Philippe Schwaller
6. Wengong Jin
7. Teodoro Laino
8. Connor W. Coley

In Model Architectures

1. Regina Barzilay
2. Tommi S. Jaakkola
3. Günter Klambauer
4. Wengong Jin
5. Alán Aspuru-Guzik
6. Gisbert Schneider
7. Sepp Hochreiter
8. C. Bekas

In Computational Chemistry & Drug Discovery

1. Regina Barzilay
2. Tommi S. Jaakkola
3. Philippe Schwaller
4. Gisbert Schneider
5. Teodoro Laino
6. Connor W. Coley
7. Sepp Hochreiter
8. Günter Klambauer

Citations in the corpus

• Machine learning for a sustainable energy future (2022, background): “137,138 This is more apparent when investigating unexplored chemical spaces with undetermined equilibrium ground states; yet often the metastable phases exhibit superior properties as seen, for example, in photovoltaics 140 and ion conductors 141 .”
• Molecular Transformer: A Model for Uncertainty-Calibrated Chemical Reaction Prediction (2018, methodology): “Template-based methods [19, 20, 21] use a library of reaction templates or rules.”
• Accelerating the discovery of materials for clean energy in the era of smart automation (2018, methodology): “For example, the reaction outcomes for 16 simple reactions of alkene and alkyl halides were successfully predicted using this approach 237 .”
• Deep Learning for Deep Chemistry: Optimizing the Prediction of Chemical Patterns (2019, background): “…Montavon et al., 2013; Schütt et al., 2014; Alipanahi et al., 2015; Botu and Ramprasad, 2015b; De et al., 2016; Faber et al., 2016; Sadowski et al., 2016; Wei et al., 2016; Brockherde et al., 2017; Chmiela et al., 2017, 2018; Smith et al., 2017; Wu et al., 2017; Gómez-Bombarelli et al., 2018).”