Using Machine Learning To Predict Suitable Conditions for Organic Reactions

By Hanyu Gao, Thomas J. Struble, Connor W. Coley, Yuran Wang, William H. Green Jr., Klavs F. Jensen. ACS Central Science, 2018

334 citations recorded by the source corpus.

Reaction condition recommendation is an essential element for the realization of computer-assisted synthetic planning. Accurate suggestions of reaction conditions are required for experimental validation and can have a significant effect on the success or failure of an attempted transformation. However, de novo condition recommendation remains a challenging and under-explored problem and relies heavily on chemists’ knowledge and experience. In this work, we develop a neural-network model to predict the chemical context (catalyst(s), solvent(s), reagent(s)), as well as the temperature most suitable for any particular organic reaction. Trained on ∼10 million examples from Reaxys, the model is able to propose conditions where a close match to the recorded catalyst, solvent, and reagent is found within the top-10 predictions 69.6% of the time, with top-10 accuracies for individual species reaching 80–90%. Temperature is accurately predicted within ±20 °C from the recorded temperature in 60–70% of test cases, with higher accuracy for cases with correct chemical context predictions. The utility of the model is illustrated through several examples spanning a range of common reaction classes. We also demonstrate that the model implicitly learns a continuous numerical embedding of solvent and reagent species that captures their functional similarity.

Subfields: Computational Theory and Mathematics, Materials Chemistry, Molecular Biology

View Paper: https://www.semanticscholar.org/paper/bb414c09ace7083c41c1164f5de4a901ddd8f146

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

In Materials Chemistry

In Molecular Biology

Citations in the corpus

A Deep Learning Approach to Antibiotic Discovery. (2020, positive): “However, emerging models in retrosynthesis and physicochemical property prediction may overcome these limitations in the near future (Coley et al., 2018; Gao et al., 2018).”
Deep Learning for Deep Chemistry: Optimizing the Prediction of Chemical Patterns (2019, methodology): “…2018a; Granda et al., 2018; Segler et al., 2018; Li and Eastgate, 2019), (v) improving catalytic technologies and analytical tools (Li et al., 2017; Gao et al., 2018; Huang et al., 2018; Durand and Fey, 2019; Freeze et al., 2019; Schleder et al., 2019), (vi) developing quantum algorithms for…”
A robotic platform for flow synthesis of organic compounds informed by AI planning (2019, methodology): “Reaction conditions are provided by a neural network model trained to propose a prioritized list of reagents, solvents, catalysts, and temperature most suitable for that transformation as previously reported ( 39 ).”