Multi-Omics Integration for Clinical Decision-Making: Methods, Models, and Applications

Advances in high-throughput technologies have enabled the comprehensive molecular profiling of patients across multiple biological layers, including genomics, epigenomics, transcriptomics, proteomics, and metabolomics. More recently, single-cell and spatially resolved multi-omics approaches have further increased biological resolution, enabling the characterization of cellular heterogeneity and tissue organization. These developments have generated unprecedented opportunities to improve precision medicine by identifying clinically actionable biomarkers and molecular signatures. However, translating multi-omics data into clinically meaningful insights remains challenging due to data heterogeneity, high dimensionality, limited sample sizes, missing values and the need of robust and interpretable integration strategies. Effective multi-omics integration is therefore essential to enable reliable diagnosis, prognosis, patient stratification, and therapy selection, ultimately supporting evidence-based clinical decision-making.This Research Topic aims to advance the use of multi-omics integration for clinical decision-making by bringing together methodological innovations, computational frameworks, and translational applications with demonstrated clinical relevance. We seek contributions that develop computational approaches for multi-omics integration, including machine learning, artificial intelligence, network-based methods, and statistical modeling, particularly when their clinical utility, interpretability, robustness, and reproducibility are clearly demonstrated. Equally encouraged are studies applying integrative multi-omics workflows to clinically characterized cohorts, showing their value in improving diagnosis, prognosis, patient stratification, or therapeutic decision-making. Special emphasis will be placed on studies that demonstrate translational potential, including validation across datasets or cohorts when available, integration of molecular and clinical variables, and generation of interpretable and actionable insights that may support clinical decision-making.Information for authors: This Research Topic does not accept Case Reports, but we welcome all the other article types addressing, but not limited to, the following topics:- Novel computational and statistical methods for multi-omics integration- Machine learning and artificial intelligence approaches for multi-omics-based prediction- Interpretable multi-omics models- Multi-omics biomarker discovery and validation- Patient stratification and disease subtyping using integrative approaches- Multi-omics integration for diagnosis, prognosis, and therapy selection- Integration of multi-omics with clinical, imaging, or digital health data- Network-based approaches for multi-omics analysis- Translational studies demonstrating clinical utility of integrative modelsStudies focusing on clinically relevant complex diseases, including cancer, neurological, cardiovascular, metabolic, and immune-mediated disorders, are particularly encouraged.To promote reproducibility and transparency, authors are strongly encouraged to share data, code, and computational workflows. Topic editors: Jessica Gliozzo, Cristian Iperi Source: https://www.frontiersin.org/research-topics/78756/multi-omics-integration-for-clinical-decision-making-methods-models-and-applications