J.Med.Chem publish; Predicting Regioselectivity of AO, CYP, FMO and UGT Metabolism Using Quantum Mechanical Simulations and Machine Learning

Oct 17, 2022

J. Med. Chem, publish; Predicting Regioselectivity of AO, CYP, FMO and UGT Metabolism Using Quantum Mechanical Simulations and Machine Learning.

Mario Öeren,† Peter J. Walton, †, ‡ James Suri, †, § David J. Ponting, ^ Peter A. Hunt, † Matthew D. Segall †


† Optibrium Limited, Cambridge Innovation Park, Denny End Road, Cambridge, CB25 9PB, UK
‡ School of Chemistry, University of Nottingham, University Park, Nottingham, NG7 2RD, UK
§ School of Chemistry, University of St Andrews, North Haugh, St Andrews, KY16 9ST, UK
^ Lhasa Limited, Granary Wharf House, 2 Canal Wharf, Leeds, LS11 5PS, UK

J. Med. Chem, DOI: 10.1021/acs.jmedchem.1c00313


Abstract – Unexpected metabolism in modification and conjugation phases can lead to the failure of many late-stage drug candidates or even withdrawals of approved drugs. Thus, it is critical to predict the sites of metabolism (SoM) for enzymes, which are known to interact with drug-like molecules, in the early stages of the research. The study presents methods for predicting the isoform-specific metabolism for human AOs, FMOs and UGTs and general CYP metabolism for pre-clinical species. The models use semi-empirical quantum mechanical simulations, validated using experimentally obtained data and DFT calculations, to estimate the reactivity of each SoM in the context of the whole molecule. Ligand-based models, trained and tested using high-quality regioselectivity data, combine the reactivity of the potential SoM with the orientation and steric effects of the binding pockets of the different enzyme isoforms. The resulting models achieve kappa values of up to 0.94 and AUC of up to 0.92.

Introduction – The characterisation of xenobiotic metabolism using in silico methods enables chemists to predict sites of metabolism (SoM) of potential drug candidates, agrochemicals, nutritional supplements, and cosmetics. Therefore, optimising the structure of new chemical entities can be more cost-effective and toxic metabolites can be identified early in the project. [1, 2] Historically, predictive models have targeted the metabolism by human isoforms of the Cytochrome P450 (CYP) family of enzymes due to their irrefutable importance in the metabolism of drug-like compounds in the modification phase (Phase I). [3] However, studies on how to predict metabolism for other modification phase enzymes, such as Aldehyde Oxidases (AO) [4, 5] and Flavin-containing Monooxygenases (FMO) [6], and conjugation phase (Phase II) enzymes, such as Uridine 5’-diphospho-glucuronosyltransferases (UGT) [7, 8, 9, 10, 11], are increasing in prevalence

Read the full paper >

Download PDF >