AI-Driven Genomic and Diagnostic Modeling in Breast Cancer

Breast cancer is a biologically heterogeneous disease in which genomic complexity, dynamic tumor evolution, and variable therapeutic response continue to challenge early detection, prognostication, and treatment selection. Recent advances in artificial intelligence have created new opportunities to integrate high-dimensional genomic, transcriptomic, epigenomic, pathological, radiological, and clinical data into more precise and scalable diagnostic and predictive models. These approaches are reshaping how breast cancer is classified, risk-stratified, and monitored across disease stages and molecular subtypes.This Research Topic aims to highlight emerging developments in AI-driven modeling frameworks, large language models (LLMs) and foundational models that improve the interpretation of breast cancer biology and support clinically relevant diagnostic decision-making. We welcome contributions focused on machine learning, deep learning, multimodal data fusion, and explainable AI approaches applied to biomarker discovery, molecular subtyping, early detection, prognosis prediction, treatment response assessment, and disease monitoring. Particular interest is given to studies that bridge computational innovation with translational and clinical relevance.This Research Topic is interested in, but not limited to:o AI-enabled integration of multi-omics data in breast cancero Predictive modeling using genomic, transcriptomic, or epigenomic signatureso AI applications in molecular subtyping and biomarker discoveryo Computational pathology and radiogenomic correlationo Diagnostic algorithms for screening, lesion characterization, and early detectiono Models for prognosis, recurrence risk, metastasis prediction, and therapeutic responseo AI approaches to treatment resistance and disease monitoringo Explainable, interpretable, and clinically actionable AI systemso External validation, reproducibility, bias mitigation, and model robustnesso Real-world implementation of AI-driven tools in breast cancer research and careo Federated learning and privacy-preserving AI for multi-institutional genomic studieso Liquid biopsy and circulating tumor DNA (ctDNA) analysis using AI-based frameworksAs data-driven oncology continues to expand, there remains a need for rigorous and biologically informed computational models that are not only accurate, but also transparent, generalizable, and clinically actionable. By bringing together research at the intersection of artificial intelligence, genomics, diagnostics, and breast cancer medicine, this collection seeks to provide a focused overview of current progress and critical barriers in the field, while identifying priorities for the next generation of clinically deployable precision diagnostic tools.Please note: Manuscripts consisting solely of bioinformatics, computational analysis, or predictions of public databases which are not accompanied by validation (independent clinical or patient cohort, or biological validation in vitro or in vivo, which are not based on public databases) are not suitable for publication in this journal. Topic editors: Dr Padmakala Sadagopan, Dirk Geerts, Ayyappan Gangadaran Source: https://www.frontiersin.org/research-topics/82012/ai-driven-genomic-and-diagnostic-modeling-in-breast-cancer