Prediction of chemical reaction yields using deep learning

Philippe Schwaller,Teodoro Laino,Jean-Louis Reymond,Alain C Vaucher

doi:10.1088/2632-2153/abc81d

Philippe Schwaller, Teodoro Laino + Show 2 more

Open Access

https://doi.org/10.1088/2632-2153/abc81d

Copy DOI

Abstract

Artificial intelligence is driving one of the most important revolutions in organic chemistry. Multiple platforms, including tools for reaction prediction and synthesis planning based on machine learning, have successfully become part of the organic chemists’ daily laboratory, assisting in domain-specific synthetic problems. Unlike reaction prediction and retrosynthetic models, the prediction of reaction yields has received less attention in spite of the enormous potential of accurately predicting reaction conversion rates. Reaction yields models, describing the percentage of the reactants converted to the desired products, could guide chemists and help them select high-yielding reactions and score synthesis routes, reducing the number of attempts. So far, yield predictions have been predominantly performed for high-throughput experiments using a categorical (one-hot) encoding of reactants, concatenated molecular fingerprints, or computed chemical descriptors. Here, we extend the application of natural language processing architectures to predict reaction properties given a text-based representation of the reaction, using an encoder transformer model combined with a regression layer. We demonstrate outstanding prediction performance on two high-throughput experiment reactions sets. An analysis of the yields reported in the open-source USPTO data set shows that their distribution differs depending on the mass scale, limiting the data set applicability in reaction yields predictions.

Highlights

Multiple platforms, including tools for reaction prediction and synthesis planning based on machine learning, successfully became part of the organic chemists’ daily laboratory, assisting in domain-specific synthetic problems
Chemical reactions in organic chemistry are described by writing the structural formula of reactants and products separated by an arrow, representing the chemical transformation by specifying how the atoms rearrange between one or several reactant molecules and one or several product molecules [1]
Reaction yields are usually reported as a percentage of the theoretical chemical conversion, i.e., the percentage of the reactant molecules successfully converted to the desired product compared to the theoretical value

Summary

Introduction

Chemical reactions in organic chemistry are described by writing the structural formula of reactants and products separated by an arrow, representing the chemical transformation by specifying how the atoms rearrange between one or several reactant molecules and one or several product molecules [1]. Logistic, and energetic considerations drive chemists to prefer chemical transformations capable of converting all reactant molecules into products with the highest yield possible. Reaction yields are usually reported as a percentage of the theoretical chemical conversion, i.e., the percentage of the reactant molecules successfully converted to the desired product compared to the theoretical value. It is not uncommon for chemists to synthesise a molecule in a dozen or more reaction steps. It is not surprising that designing new reactions with yields higher than existing ones attracts much e↵ort in organic chemistry research.

Objectives

Results

Conclusion