Machine learning and structure-based modeling for the prediction of UDP-glucuronosyltransferase inhibition

Balint Dudas; Youcef Bagdad; Milan Picard; David Perahia; Maria A Miteva

doi:10.1016/j.isci.2022.105290

Machine learning and structure-based modeling for the prediction of UDP-glucuronosyltransferase inhibition

iScience. 2022 Oct 6;25(11):105290. doi: 10.1016/j.isci.2022.105290. eCollection 2022 Nov 18.

Authors

Balint Dudas^{1

2}, Youcef Bagdad¹, Milan Picard¹, David Perahia², Maria A Miteva¹

Affiliations

¹ Inserm U1268 MCTR, CiTCoM UMR 8038 CNRS - Université Paris Cité, Paris, France.
² Laboratoire de Biologie et Pharmacologie Appliquée (LBPA), UMR8113, Ecole Normale Supérieure Paris-Saclay, Gif-sur-Yvette, France.

Abstract

UDP-glucuronosyltransferases (UGTs) are responsible for 35% of the phase II drug metabolism. In this study, we focused on UGT1A1, which is a key UGT isoform. Strong inhibition of UGT1A1 may trigger adverse drug/herb-drug interactions, or result in disorders of endobiotic metabolism. Most of the current machine learning methods predicting the inhibition of drug metabolizing enzymes neglect protein structure and dynamics, both being essential for the recognition of various substrates and inhibitors. We performed molecular dynamics simulations on a homology model of the human UGT1A1 structure containing both the cofactor- (UDP-glucuronic acid) and substrate-binding domains to explore UGT conformational changes. Then, we created models for the prediction of UGT1A1 inhibitors by integrating information on UGT1A1 structure and dynamics, interactions with diverse ligands, and machine learning. These models can be helpful for further prediction of drug-drug interactions of drug candidates and safety treatments.

Keywords: Artificial intelligence; Bioinformatics; Computational chemistry; Drugs.