Explainable prediction of catalysing enzymes from reactions using multilayer perceptrons

Abstract

Assigning or proposing a catalysing enzyme given a chemical or biochemical reaction is of great interest to life sciences and chemistry alike. The exploration and design of metabolic pathways or the challenge of finding more sustainable enzyme-catalysed alternatives to traditional organic reactions are just two examples of tasks that require an association between reaction and enzyme. However, given the lack of large and balanced annotated data sets of enzyme-catalysed reactions, assigning an enzyme to a reaction still relies on expert-curated rules and databases. Here, we present a data-driven explainable human-in-the-loop machine learning approach to support and ultimately automate the association of a catalysing enzyme with a given biochemical reaction. In addition, the proposed method is capable of predicting enzymes as candidate catalysts for arbitrary organic reactions. Finally, the introduced explainability and visualisation methods can easily be generalised to support other machine-learning approaches involving chemical and biochemical reactions.

Machine Learning-Guided Protein Engineering

“…323 It can also help scientists to improve their algorithms by revealing mistakes and biases. 324 The use of XAI to explain deep learning networks has therefore recently attracted interest in areas of drug discovery, chemistry, and protein engineering including active ligand searching, 325 prediction of enzyme EC numbers, 326 and identifying residues that indicate transitions between active and inactive states in GPCR receptors. 327 In protein engineering, explainable AI is primarily applied for the analysis of predictions from ML models with the aim of obtaining novel biochemistry knowledge.…”