This is not the latest version of this item. The latest version can be found here.
Machine learning modeling of family wide enzyme-substrate specificity screens
Name
journal.pcbi.1009853.pdf
Description
Published version
Size
1.68 MB
Format
Adobe PDF
Checksum (MD5)
c12d56afcbfd191d042f58b583726206
Author(s)
Goldman, Samuel
Das, Ria
Yang, Kevin K
Coley, Connor W
Date Issued
February 2022
Journal
PLOS Computational Biology
Publisher
Public Library of Science (PLoS)
Citation
Goldman, Samuel, Das, Ria, Yang, Kevin K and Coley, Connor W. 2022. "Machine learning modeling of family wide enzyme-substrate specificity screens." PLOS Computational Biology, 18 (2).
Version
Final published version
Abstract
Biocatalysis is a promising approach to sustainably synthesize pharmaceuticals, complex natural products, and commodity chemicals at scale. However, the adoption of biocatalysis is limited by our ability to select enzymes that will catalyze their natural chemical transformation on non-natural substrates. While machine learning and in silico directed evolution are well-posed for this predictive modeling challenge, efforts to date have primarily aimed to increase activity against a single known substrate, rather than to identify enzymes capable of acting on new substrates of interest. To address this need, we curate 6 different high-quality enzyme family screens from the literature that each measure multiple enzymes against multiple substrates. We compare machine learning-based compound-protein interaction (CPI) modeling approaches from the literature used for predicting drug-target interactions. Surprisingly, comparing these interaction-based models against collections of independent (single task) enzyme-only or substrate-only models reveals that current CPI approaches are incapable of learning interactions between compounds and proteins in the current family level data regime. We further validate this observation by demonstrating that our no-interaction baseline can outperform CPI-based models from the literature used to guide the discovery of kinase inhibitors. Given the high performance of non-interaction based models, we introduce a new structure-based strategy for pooling residue representations across a protein sequence. Altogether, this work motivates a principled path forward in order to build and evaluate meaningful predictive models for biocatalysis and other drug discovery applications.
Terms of Use
Creative Commons Attribution 4.0 International license
Persistent DSpace Link
DOI of Published Version
10.1371/journal.pcbi.1009853
