Held on 31 March 2020.

After the success of the current P450 models it is time to introduce additional enzyme systems to StarDrop and include enzymes from both modification and conjugation phase. In this webinar, presented by Mario Oeren and Matt Segall, we introduce two additional sets of models, one set for the Flavin-containing Monooxygenase (FMO), which work in conjunction with the P450s, and one set for Uridine Diphosphate Glucuronosyltransferase (UGT), which is responsible for the conjugation of around 15 per cent of current hepatically cleared drugs.

_{To hear the narration, please increase your speaker volume.}

Preprint Paper.

Peter Hunt¹, Layla Hosseini-Gerami², Tomas Chrien¹, Jeffrey Plante³, David J. Ponting³, Matthew Segall¹

¹Optibrium Ltd. ²Department of Chemistry, Cambridge. ³Lhasa Ltd

Abstract

The acid dissociation constant (pK_a) has an important influence on molecular properties crucial to compound development in synthesis, formulation and optimisation of absorption, distribution, metabolism and excretion properties. We will present a method that combines quantum mechanical calculations, at a semi-empirical level of theory, with machine learning to accurately predict pK_a for a diverse range of mono- and polyprotic compounds. The resulting model has been tested on two external data sets, one specifically used to test pK_a prediction methods (SAMPL6) and the second covering known drugs containing basic functionalities. Both sets were predicted with excellent accuracy (root-mean-square errors of 0.7 – 1.0 log units), comparable to other methodologies using much higher level of theory and computational cost.

You can download the paper as a PDF