The field of precision prevention and population health is experiencing transformative growth due to the increasing availability of high-dimensional multi-omics data, including genomics, transcriptomics, epigenomics, proteomics, metabolomics, microbiome, and imaging. At the same time, rapid advances in exposure science provide increasingly granular environmental data—covering climate and weather, air pollution, built environment, and chemical mixtures—enabling exposome-informed assessment of chronic disease risk. However, translating the wealth of exposome and multi-omics information into actionable public health and clinical insights remains challenging. Fragmented approaches often overlook nonlinear, multisystem interactions central to immune regulation, inflammation, and chronic disease persistence, impeding robust biomarker identification and risk-stratified prevention. Recent studies demonstrate that artificial intelligence (AI), particularly machine learning and deep learning, can address these challenges by integrating complex datasets, uncovering latent biological patterns, and improving interpretability for translational research. Nonetheless, effective strategies for harmonizing exposome and multi-omics data and extracting clinically and epidemiologically meaningful insights remain underdeveloped, and a concerted effort is needed to move beyond fragmented or purely computational methods.
This Research Topic aims to advance the field by highlighting innovative AI-enabled integrative strategies in exposome and multi-omics data analysis, with the objective of accelerating biomarker discovery and enhancing the precision of chronic disease prediction and prevention. Central goals include the development and validation of new computational frameworks, the elucidation of immune-mediated mechanisms linking environmental exposures to chronic disease heterogeneity, and improved prediction of disease onset and progression across populations. By bridging computational modeling with biological experimentation, clinical translation, and real-world data, this Topic seeks to address questions surrounding the reliability, interpretability, generalizability, and translational value of AI-driven biomarker identification. Key objectives also encompass advancing exposure-informed risk stratification and providing guidance for precision prevention strategies that are implementable in public health practice.
This Research Topic is dedicated to the development and application of AI-based exposome–multi-omics integration methods with a focus on chronic disease and population health. We welcome studies that combine computational, experimental, translational, and population-based approaches, while emphasizing methodological rigor, external validation, and real-world relevance. To gather further insights into these rapidly evolving areas, we welcome articles addressing, but not limited to, the following themes:
• Deep learning applications in immunogenomics, immunometabolomics, microbiome science, and environmental health analytics
• AI and machine learning frameworks for exposome–multi-omics integration
• Biomarker discovery and molecular risk stratification using integrated omics and exposure data
• Integration of geospatial/climate/pollution/built-environment data with single-cell, spatial, imaging, and other omics layers
• Predictive modeling of chronic disease onset, progression, exacerbations, and intervention response
• Causal inference, mediation, transportability, fairness, and implementation for precision public health
Article types include Original Research, Reviews, Mini-Reviews, Perspectives, and Clinical, Translational, or Population-Based Studies.
The field of precision prevention and population health is experiencing transformative growth due to the increasing availability of high-dimensional multi-omics data, including genomics, transcriptomics, epigenomics, proteomics, metabolomics, microbiome, and imaging. At the same time, rapid advances in exposure science provide increasingly granular environmental data—covering climate and weather, air pollution, built environment, and chemical mixtures—enabling exposome-informed assessment of chronic disease risk. However, translating the wealth of exposome and multi-omics information into actionable public health and clinical insights remains challenging. Fragmented approaches often overlook nonlinear, multisystem interactions central to immune regulation, inflammation, and chronic disease persistence, impeding robust biomarker identification and risk-stratified prevention. Recent studies demonstrate that artificial intelligence (AI), particularly machine learning and deep learning, can address these challenges by integrating complex datasets, uncovering latent biological patterns, and improving interpretability for translational research. Nonetheless, effective strategies for harmonizing exposome and multi-omics data and extracting clinically and epidemiologically meaningful insights remain underdeveloped, and a concerted effort is needed to move beyond fragmented or purely computational methods.
This Research Topic aims to advance the field by highlighting innovative AI-enabled integrative strategies in exposome and multi-omics data analysis, with the objective of accelerating biomarker discovery and enhancing the precision of chronic disease prediction and prevention. Central goals include the development and validation of new computational frameworks, the elucidation of immune-mediated mechanisms linking environmental exposures to chronic disease heterogeneity, and improved prediction of disease onset and progression across populations. By bridging computational modeling with biological experimentation, clinical translation, and real-world data, this Topic seeks to address questions surrounding the reliability, interpretability, generalizability, and translational value of AI-driven biomarker identification. Key objectives also encompass advancing exposure-informed risk stratification and providing guidance for precision prevention strategies that are implementable in public health practice.
This Research Topic is dedicated to the development and application of AI-based exposome–multi-omics integration methods with a focus on chronic disease and population health. We welcome studies that combine computational, experimental, translational, and population-based approaches, while emphasizing methodological rigor, external validation, and real-world relevance. To gather further insights into these rapidly evolving areas, we welcome articles addressing, but not limited to, the following themes:
• Deep learning applications in immunogenomics, immunometabolomics, microbiome science, and environmental health analytics
• AI and machine learning frameworks for exposome–multi-omics integration
• Biomarker discovery and molecular risk stratification using integrated omics and exposure data
• Integration of geospatial/climate/pollution/built-environment data with single-cell, spatial, imaging, and other omics layers
• Predictive modeling of chronic disease onset, progression, exacerbations, and intervention response
• Causal inference, mediation, transportability, fairness, and implementation for precision public health
Article types include Original Research, Reviews, Mini-Reviews, Perspectives, and Clinical, Translational, or Population-Based Studies.