Integrative AI for Multi-Scale Modeling of Host–Pathogen and Microbiome Interactions

Host–pathogen interactions constitute a complex, multiscale process extending from molecular dynamics at protein interfaces to systemic infection responses and clinical outcomes. Traditional experimental and computational approaches have yielded tremendous insights into infectious disease biology but remain limited in capturing the interconnected spatial and temporal scales underlying infection processes. Recent advances in artificial intelligence (AI), particularly physics-informed and mechanistically constrained frameworks, offer new opportunities to model infectious processes while incorporating biological and physical principles directly into learning systems. However, the integration of such approaches across scales, linking molecular modeling, cellular signaling, tissue responses, and ecological influences such as the microbiome, remains an emerging frontier. Despite major advances in molecular structure prediction, graph-based biological network modeling, and physics-informed neural networks, important challenges remain in achieving interpretable, biologically consistent, and seamlessly integrated models across molecular, cellular, and organismal scales.This Research Topic aims to bring together contributions that advance the development and application of mechanistic and physics-informed AI tools for the comprehensive modeling of host–pathogen interactions. Specifically, it seeks to explore strategies that integrate structural and molecular modeling of host–pathogen interactions, including protein–protein interactions, binding energetics, and conformational dynamics, with cellular, tissue-level, and ecological infection processes. The overarching goal is to establish interpretable, data-efficient, and biologically grounded AI systems that can bridge the molecular and systems biology of infection, elucidate mechanisms underlying pathogen–host-microbiome interactions and accelerate the development of new therapeutic and preventive strategies. Such integrative AI systems may accelerate the discovery of antimicrobial therapeutics, microbiome-preserving interventions, vaccines, and precision treatment strategies.To gather further insights into the multiscale modeling of infectious processes, immune responses, and therapeutic interactions, we welcome articles addressing, but not limited to, the following themes:o AI for structural and molecular modeling of host–pathogen interactions o Multi-scale coupling of molecular, cellular, and systemic dynamics in infection modelso Integration of multi-omics, single-cell, and spatial profiling data into infection modelingo Graph neural networks and hybrid approaches for signaling and immune network inferenceo Integration of microbiome composition, metabolism, and drug interactions into host–pathogen systemso Physics-informed dynamical AI models for infection progression and therapeutic responseo Computational frameworks for precision antimicrobial therapy and microbiome preservationo Generative AI and structure-guided design of antimicrobial agents, antibodies, vaccines, or microbiome-targeted therapeuticsTopic Editor Prof. Gene G. Olinger Jr. is a co-founder of Oyanalytica, a biostatistics and machine learning company. He is also a Distinguished Research Fellow at MRIGlobal, and support an NIH grant. Topic editors: Jianfei Dong, Gene Olinger, Haiqing Zhao, Jiabao Xu Source: https://www.frontiersin.org/research-topics/85752/integrative-ai-for-multi-scale-modeling-of-host-pathogen-and-microbiome-interactions