Predicting gastrointestinal drug effects using contextualized metabolic models.

Marouen Ben Guebila,Ines Thiele,Radhakrishnan Mahadevan

doi:10.1371/journal.pcbi.1007100

Abstract

Gastrointestinal side effects are among the most common classes of adverse reactions associated with orally absorbed drugs. These effects decrease patient compliance with the treatment and induce undesirable physiological effects. The prediction of drug action on the gut wall based on in vitro data solely can improve the safety of marketed drugs and first-in-human trials of new chemical entities. We used publicly available data of drug-induced gene expression changes to build drug-specific small intestine epithelial cell metabolic models. The combination of measured in vitro gene expression and in silico predicted metabolic rates in the gut wall was used as features for a multilabel support vector machine to predict the occurrence of side effects. We showed that combining local gut wall-specific metabolism with gene expression performs better than gene expression alone, which indicates the role of small intestine metabolism in the development of adverse reactions. Furthermore, we reclassified FDA-labeled drugs with respect to their genetic and metabolic profiles to show hidden similarities between seemingly different drugs. The linkage of xenobiotics to their transcriptomic and metabolic profiles could take pharmacology far beyond the usual indication-based classifications.

Highlights

Side effects are unintended effects of administered drugs that lead to a decrease in the efficacy of treatment, lower patient compliance, and eventually the cessation of treatment with the development of adverse physiological consequences
We developed context-specific metabolic models of the enterocyte constrained by druginduced gene expression and trained a machine learning classifier using metabolic reaction rates as features to predict the occurrence of side effects
We clustered the compounds based on their metabolic and transcriptomic features to find similarities between their physiological effects

Summary

Introduction

Side effects are unintended effects of administered drugs that lead to a decrease in the efficacy of treatment, lower patient compliance, and eventually the cessation of treatment with the development of adverse physiological consequences. Identifying compounds that can cause serious gastrointestinal adverse reactions from the ones that have benign effects solely using in vitro data could help optimizing drugs in the preclinical phase before first-in-human trials and decrease the failure rates of new chemical entities. The prediction of side effects have been addressed mainly through a target-based approach wherein the inhibition of a specific target induces the desired effect and suppresses all physiological processes involving the target protein [5]. With the availability of genome-wide transcriptome profiles of more than 20,000 compounds in the connectivity map [6], new approaches have considered linking off-target effects rather than target effects to adverse reactions. Recent efforts have combined druginduced gene expression with chemical structures and Gene Ontology (GO) processes as features to predict side effects accurately [8]. Metabolic genes are among the most predictive features for the classification [8]

Methods

Results

Discussion

Conclusion