E. E. Litsa, P. Das, and L. E. Kavraki, “Machine learning models in the prediction of drug metabolism: challenges and future perspectives,” Expert Opinion on Drug Metabolism & Toxicology, vol. 0, no. 0, pp. 1–3, 2021.
Metabolism can be the underlying cause of drug adverse effects and diminished efficacy. Metabolic reactions in the human body, mediated mainly by enzymes, may transform the administered drug into metabolites that exhibit different biological activity. As a general rule, metabolic reactions deactivate a drug; however, off-target effects or toxicity, resulting from the formed metabolites, cannot be excluded. On the flip side, metabolism is necessary for the formation of the active substance in the case of prodrugs. In scenarios where multiple drugs are co-administered, the presence of a drug may inhibit or further induce the clearance of another setting metabolism as one of the underlying causes of drug–drug interactions. As a result, the metabolic fate of a candidate drug needs to be thoroughly investigated during the drug development process.