AI and multi-omics analysis in drug design, mechanism and safety

The integration of artificial intelligence (AI) and multi-omics analysis is rapidly transforming the landscape of drug research and development. In recent years, multi-omics technologies—including genomics, transcriptomics, proteomics, metabolomics, and single-cell or spatial omics—have generated unprecedented volumes of complex biological data. However, efficiently mining these data to uncover actionable insights for drug design, mechanism elucidation, and safety assessment remains a significant challenge. Although a multitude of computational approaches have emerged, such as advanced machine learning and deep learning algorithms, key gaps persist in linking multi-dimensional omics data to therapeutic outcomes and adverse effects. Ongoing debates focus on the interpretability of AI-driven discoveries, the robustness of predictive models across various biological platforms, and the ability to transition from in silico findings to practical, translatable therapeutic innovations. Current studies demonstrate promise in areas such as target identification, mechanism-of-action (MoA) discovery, and predictive safety assessment, yet crucial limitations remain regarding experimental validation, real-world applicability, and comprehensive integration of disparate data types.This Research Topic aims to showcase cutting-edge research and foster multi-disciplinary dialogue on how AI-powered multi-omics analyses can accelerate drug discovery, deepen mechanistic understanding, and enhance early-stage safety prediction. Key objectives include identifying novel computational frameworks for integrating heterogeneous omics datasets, developing interpretable models that reveal actionable drug mechanisms, and bridging the gap between algorithmic predictions and experimental or real-world validation in pharmacological contexts. We welcome contributions that address how AI and multi-omics can be synergistically leveraged to improve the efficiency, accuracy, and translational relevance of drug development, with an emphasis on integrative and mechanistically transparent approaches.To gather further insights into the evolving intersection of AI and multi-omics in pharmacology, this Research Topic will focus on original research, methods, reviews, perspectives and data/resource articles. We welcome articles addressing, but not limited to, the following themes:Multi-omics data integration strategies using AI methods for drug discoveryMachine learning approaches for target identification, compound screening, and hit-to-lead optimizationAI-driven elucidation of mechanism-of-action by combining omics signatures and phenotypic dataPredictive modeling of drug efficacy and safety, including adverse outcome pathways and toxicity risk assessmentExperimental and translational validation frameworks connecting AI/omics predictions to in vitro, organoid, or clinical findingsApproaches for enhancing model interpretability and trustworthiness in pharmacological settingsOpen multi-omics databases, tools, and AI resources enabling reproducible and transparent pharmacology researchIf the original input describes a list of article types, this should also be included in the new description at the end as an appendix. Topic editors: Bufu Tang, Yuhan Shi, Zhiyong Xu Source: https://www.frontiersin.org/research-topics/82576/ai-and-multi-omics-analysis-in-drug-design-mechanism-and-safety