A general model to predict small molecule substrates of enzymes based on machine and deep learning
Journal article, 2023

For most proteins annotated as enzymes, it is unknown which primary and/or secondary reactions they catalyze. Experimental characterizations of potential substrates are time-consuming and costly. Machine learning predictions could provide an efficient alternative, but are hampered by a lack of information regarding enzyme non-substrates, as available training data comprises mainly positive examples. Here, we present ESP, a general machine-learning model for the prediction of enzyme-substrate pairs with an accuracy of over 91% on independent and diverse test data. ESP can be applied successfully across widely different enzymes and a broad range of metabolites included in the training data, outperforming models designed for individual, well-studied enzyme families. ESP represents enzymes through a modified transformer model, and is trained on data augmented with randomly sampled small molecules assigned as non-substrates. By facilitating easy in silico testing of potential substrates, the ESP web server may support both basic and applied science.

Author

Alexander Kroll

Heinrich Heine University Düsseldorf

Sahasra Ranjan

Indian Institute of Technology

Martin Engqvist

Enginzyme AB

Chalmers, Life Sciences, Systems and Synthetic Biology

Martin J. Lercher

Heinrich Heine University Düsseldorf

Nature Communications

2041-1723 (ISSN) 20411723 (eISSN)

Vol. 14 1 2787

Subject Categories

Bioinformatics (Computational Biology)

Bioinformatics and Systems Biology

DOI

10.1038/s41467-023-38347-2

PubMed

37188731

More information

Latest update

5/30/2024