Rodriguez Perez, Raquel and Gerebtzoff, Gregori (2021) Identification of bile salt export pump inhibitors using machine learning: Predictive safety from an industry perspective. Artificial Intelligence in the Life Sciences, 1. ISSN 26673185

Abstract

Bile salt export pump (BSEP) is a transporter that moves bile salts from hepatocytes into bile canaliculi. BSEP inhibition can result in the toxic accumulation of bile salts in the liver, which has been identified as a risk factor of drug-induced liver injury (DILI). Since DILI is a frequent cause of drug withdrawals from the market or failings in drug development, in vitro BSEP activity is measured with the [3H]taurocholate uptake assay and a half-maximal inhibitory concentration (IC50) higher than 30µM is advised. Herein, a machine learning classification model was developed to accurately detect BSEP inhibitors and help in the prioritization of in vitro testing. The model is currently used for the detection of BSEP liabilities, and prioritization of compounds and chemical series. Moreover, regression models for short-term and long-term predictions were also built and evaluated. This work illustrates how predictive safety can help in the early detection of potential toxicity and support decision making by leveraging Novartis historical experimental data.

Item Type:	Article
Keywords:	Predictive safety, Machine learning, Model evaluation, Decision-making, Drug-induced liver injury (DILI), Liver toxicity, Bile salt export pump
Date Deposited:	25 Jan 2022 00:45
Last Modified:	25 Jan 2022 00:45
URI:	https://oak.novartis.com/id/eprint/46443