AI-Integrated Multi-Omics for Neurodegeneration: Mechanistic Insights to Clinical Innovation

The field of neurodegeneration is witnessing rapid advancements thanks to the integration of multi-omics technologies alongside sophisticated artificial intelligence (AI) and machine learning (ML) tools. While genomics, transcriptomics, proteomics and metabolomics provide unprecedented layers of insight into diseases such as Alzheimer’s, Parkinson’s, and related disorders, the sheer scale and complexity of these datasets create substantial analytical challenges. Current research is pushing the limits of AI in fusing diverse omics data; however, achieving clinically meaningful biomarker discovery and mechanistic understanding remains an unmet need. Furthermore, questions regarding interpretability, reproducibility and generalizability of AI-driven insights continue to fuel debate within the scientific community.This Research Topic aims to spotlight innovative approaches where AI and ML are leveraged for integrative multi-omics analysis in neurodegeneration, with an emphasis on translating molecular-level discoveries into real-world clinical applications. We seek to address key objectives including improving model interpretability and biological relevance, facilitating the identification of robust biomarkers and developing frameworks that ensure reproducibility across cohorts and populations. By encouraging submissions that bridge computational advances with experimental and clinical research, this Research Topic intends to pave the way for more precise diagnostics, prognostics and personalized strategies in neurodegenerative diseases.To gather further insights into the integration of AI and ML for multi-omics analysis in neurodegeneration, we welcome articles addressing, but not limited to, the following themes:• Advanced AI/ML algorithms for integrating genomics, transcriptomics, proteomics, metabolomics, epigenomics, and other omics modalities in the context of neurodegenerative disease • Methods for multimodal data fusion, feature selection, and network analysis to enhance biological discovery and clinical interpretability • Approaches focusing on the development of interpretable and explainable models, such as interpretable neural networks or hybrid systems combining expert knowledge with machine learning • Validation of AI/ML-derived biomarkers using experimental models, patient cohorts, or cross-platform replication studies • Benchmarking studies evaluating reproducibility, transferability, and generalizability of computational models across different populations, cohorts, and technologies• Standards and best practices for harmonizing omics data preprocessing, model development, and reporting to enhance transparency and comparability• Translational frameworks linking molecular-level multi-omics discoveries to clinical diagnostics, prognostics, or personalized treatment approaches We encourage a wide range of submissions, including original research, methods papers, brief research reports, data reports, systematic reviews, mini reviews and perspectives. Topic editors: Gurkan Bebek, Filipa Blasco Lopes Source: https://www.frontiersin.org/research-topics/78552/ai-integrated-multi-omics-for-neurodegeneration-mechanistic-insights-to-clinical-innovation