Integrating Multi-Omics, Artificial Intelligence and Computational Modeling: From Molecules to Models

Recent advances in multi-omics technologies have enabled comprehensive characterization of biological systems by capturing information from single genomics, proteomics, metabolomics, and simultaneous molecular layers. These approaches generate complex datasets to investigate modulation of biological processes in health and disease. However, despite the high throughput gained, translating large-scale molecular information into biologically meaningful insights remains a major challenge. In this context, artificial intelligence (AI), machine learning, and computational modeling are emerging as transformative tools capable of integrating heterogeneous datasets, identifying hidden patterns, and enabling the transition from molecular profiling toward predictive and mechanistic understanding of biological systems.The primary goal of this Research Topic is to address the growing gap between single molecule characterization, high-throughput multi-omics data generation and the ability to derive mechanistic, predictive, and clinically relevant models. While multi-omics studies have significantly expanded our understanding of molecular signatures associated with physiological and pathological conditions, major challenges remain in integrating diverse datasets, improving interpretability, and translating findings into actionable biological knowledge.This Research Topic aims to highlight innovative approaches that combine multi-omics data with AI-driven analytics and computational modeling frameworks. We seek contributions that develop predictive models, identify causal molecular interactions, simulate biological systems across scales, and improve biomarker discovery, therapeutic target identification, and precision medicine applications. Accordingly, we aim to foster interdisciplinary strategies to connect molecular complexity with robust computational models capable of advancing systems biology and translational research.This Research Topic welcomes original research articles, reviews, mini-reviews, perspectives, methods papers, and proof-of-concept studies focused on the integration of multi-omics, AI, and computational modeling.Topics of interest include, but are not limited to:• Multi-omics and data integration strategies• Machine learning and deep learning in omics analysis• Interpretable and explainable AI approaches• Computational modeling of biological systems• Network biology and pathway analysis• Causal inference in omics datasets• Biomarker discovery and precision medicine• Digital twins and predictive biology• Drug discovery and therapeutic target identification• Cross-scale modeling from molecular interactions to organism-level outcomes Topic editors: Michele Costanzo, Giovanni N Roviello Source: https://www.frontiersin.org/research-topics/80807/integrating-multi-omics-artificial-intelligence-and-computational-modeling-from-molecules-to-models