Development and Implementation of an enterprise-wide Predictive Model for Early absorption, distribution, Metabolism and Excretion Properties

• DOI: 10.4155/fmc-2021-0138
• Publication Date: 2021-09-16T09:19:42Z
• Authors: Kiran Kumar; Vladimir Chupakhin; Ann Vos; Denise Morrison; Dmitrii Rassokhin; Martin J Dellwo; Keith McCormick; Eric Paternoster; Hugo Ceulemans; Renee L DesJarlais
• Keywords: Models, Molecular; 0301 basic medicine; 03 medical and health sciences; Cytochrome P-450 Enzyme System; Drug Development; Cytochrome P-450 Enzyme Inhibitors; Humans; 3. Good health

Background: Accurate prediction of absorption, distribution, metabolism and excretion (ADME) properties can facilitate the identification of promising drug candidates. Methodology & Results: The authors present the Janssen generic Target Product Profile (gTPP) model, which predicts 18 early ADME properties, employs a graph convolutional neural network algorithm and was trained on between 1000-10,000 internal data points per predicted parameter. gTPP demonstrated stronger predictive power than pretrained commercial ADME models and automatic model builders. Through a novel logging method, the authors report gTPP usage for more than 200 Janssen drug discovery scientists. Conclusion: The investigators successfully enabled the rapid and systematic implementation of predictive ML tools across a drug discovery pipeline in all therapeutic areas. This experience provides useful guidance for other large-scale AI/ML deployment efforts.