Artificial Intelligence in Drug Metabolism and Transport: From Multi-Omics Insights to Clinical and Pharmacological Validation

Artificial intelligence (AI) is transforming pharmaceutical research by enabling the integration and interpretation of increasingly complex biological and pharmacological datasets. Recent advances in machine learning, deep learning, generative AI, and large language models (LLMs), together with high-throughput multi-omics technologies—including genomics, transcriptomics, proteomics, metabolomics, epigenomics, and single-cell omics—have created unprecedented opportunities to better understand the molecular mechanisms governing drug metabolism and transport.These computational approaches are improving the prediction of drug-metabolizing enzymes, transporter functions, pharmacokinetic behavior, drug-drug interactions, toxicity, and inter-individual variability in therapeutic response. AI is also accelerating biomarker discovery, knowledge extraction from biomedical literature, and the development of predictive models that support precision medicine.Despite these remarkable advances, major challenges remain in translating AI-generated predictions into clinically actionable pharmacological knowledge. Model interpretability, reproducibility, experimental validation, regulatory acceptance, and clinical implementation remain essential barriers to the broader adoption of AI in drug metabolism and transport research.This Research Topic aims to provide a multidisciplinary forum for cutting-edge research at the interface of artificial intelligence, computational pharmacology, and drug metabolism and transport. We seek contributions that demonstrate how AI can accelerate mechanistic understanding, improve predictive performance, and facilitate the translation of computational discoveries into experimentally and clinically validated pharmacological applications.Particular emphasis will be placed on studies integrating multi-omics data with AI to investigate drug-metabolizing enzymes, membrane transporters, pharmacogenomics, and systems pharmacology. We welcome research that combines computational innovation with rigorous in vitro, in vivo, and clinical validation to improve confidence in AI-assisted drug development and pharmacokinetic and dosing decision-making.The Research Topic also encourages studies focusing on explainable and trustworthy AI, AI-assisted biomarker discovery for metabolizing enzyme or transporter activity, physiologically based pharmacokinetic (PBPK) modeling, in vitro–in vivo extrapolation (IVIVE), model-informed precision dosing, digital twins, and regulatory applications of AI in pharmacology. By bringing together computational scientists, pharmacologists, pharmaceutical researchers, clinicians, and regulatory experts, this collection aims to promote interdisciplinary collaboration and accelerate the responsible implementation of AI across the drug development continuum.We welcome Original Research Articles, Review Articles, Mini Reviews, Methods, Data Reports, Database Articles, Software Articles, Perspectives, and Opinion articles describing innovative applications of artificial intelligence in drug metabolism and transport. Invited sub-themes include, but are not limited to:• AI prediction of drug-metabolizing enzymes (CYP450s, UGTs, FMOs, GSTs), metabolic pathways, drug–drug interactions, and computational toxicology.• Machine learning for ABC and SLC transporters, transporter-mediated drug disposition, and transporter biomarkers.• Integration of genomics, transcriptomics, proteomics, metabolomics, epigenomics, lipidomics, and single-cell omics for precision pharmacology.• ADME prediction, PBPK, PK/PD modeling, AI-enhanced IVIVE, and model-informed precision dosing.• Explainable, trustworthy, ethical, and privacy-preserving AI, including federated learning.• Generative AI, Large Language Models (LLMs), knowledge graphs, literature mining, automated hypothesis generation, and drug repurposing driven by metabolism/transporter mechanisms.• Experimental, preclinical, and clinical validation of AI-generated hypotheses on drug metabolism/transport mechanisms and associated biomarkers.• Regulatory science, AI-enabled decision support, databases, software platforms, benchmark datasets, and open-source computational tools.Studies on clinical or model-informed dosing, precision medicine, or biomarker applications are welcome only when directly tied to metabolism or transport mechanisms (e.g., transporter- or enzyme-based dose individualization). Submissions centered on therapeutic efficacy, treatment outcomes, or drug interventions without a metabolism/transport mechanistic link are outside the scope of this Research Topic.This Research Topic seeks to bridge computational innovation with experimental and clinical pharmacology, fostering the development of robust, interpretable, and clinically translatable AI approaches that advance drug metabolism and transport research while supporting precision medicine and next-generation drug development.Topic Editor Michael McCoy works and has stocks in Takeda Development Centers America. The other Topic Editors declare no competing interests with regard to the Research Topic subject. Topic editors: Dr. Krishna Sanka, Michael McCoy, Sayed Abdi Source: https://www.frontiersin.org/research-topics/85160/artificial-intelligence-in-drug-metabolism-and-transport-from-multi-omics-insights-to-clinical-and-pharmacological-validation