Learning the Language of Chemical Reactions – Atom by Atom. Linguistics-Inspired Machine Learning Methods for Chemical Reaction Tasks - PhDData

Access database of worldwide thesis

Learning the Language of Chemical Reactions – Atom by Atom. Linguistics-Inspired Machine Learning Methods for Chemical Reaction Tasks

The thesis was published by Schwaller, Philippe, in September 2022, University of Bern.


Over the last hundred years, not much has changed how organic chemistry is conducted. In most laboratories, the current state is still trial-and-error experiments guided by human expertise acquired over decades. What if, given all the knowledge published, we could develop an artificial intelligence-based assistant to accelerate the discovery of novel molecules? Although many approaches were recently developed to generate novel molecules in silico, only a few studies complete the full design-make-test cycle, including the synthesis and the experimental assessment. One reason is that the synthesis part can be tedious, time-consuming, and requires years of experience to perform successfully. Hence, the synthesis is one of the critical limiting factors in molecular discovery.

In this thesis, I take advantage of similarities between human language and organic chemistry to apply linguistic methods to chemical reactions, and develop artificial intelligence-based tools for accelerating chemical synthesis. First, I investigate reaction prediction models focusing on small data sets of challenging stereo- and regioselective carbohydrate reactions. Second, I develop a multi-step synthesis planning tool predicting reactants and suitable reagents (e.g. catalysts and solvents). Both forward prediction and retrosynthesis approaches use black-box models. Hence, I then study methods to provide more information about the models’ predictions. I develop a reaction classification model that labels chemical reaction and facilitates the communication of reaction concepts. As a side product of the classification models, I obtain reaction fingerprints that enable efficient similarity searches in chemical reaction space. Moreover, I study approaches for predicting reaction yields. Lastly, after I approached all chemical reaction tasks with atom-mapping independent models, I demonstrate the generation of accurate atom-mapping from the patterns my models have learned while being trained self-supervised on chemical reactions.

My PhD thesis’s leitmotif is the use of the attention-based Transformer architecture to molecules and reactions represented with a text notation. It is like atoms are my letters, molecules my words, and reactions my sentences. With this analogy, I teach my neural network models the language of chemical reactions – atom by atom. While exploring the link between organic chemistry and language, I make an essential step towards the automation of chemical synthesis, which could significantly reduce the costs and time required to discover and create new molecules and materials.

The full thesis can be downloaded at :

Read the last PhD tips