Knowledge-Guided Artificial Intelligence and Network Biology for RNA-Related Disease Mechanisms

RNA biology is central to gene regulation, cellular homeostasis, and disease progression through complex interactions among coding and non-coding RNAs, proteins, genomic elements, and cellular pathways. High-throughput sequencing, transcriptomics, single-cell technologies, and multi-omics profiling have produced extensive but heterogeneous datasets for studying these relationships. However, the scale, sparsity, context dependence, and uncertainty of RNA-associated data continue to challenge conventional analytical approaches. Recent studies have demonstrated the value of artificial intelligence, knowledge graphs, network biology, and graph neural networks for predicting RNA–disease associations, reconstructing regulatory networks, integrating molecular data, and identifying candidate biomarkers and therapeutic targets. Nevertheless, important gaps remain in the incorporation of reliable biological knowledge, the interpretability and reproducibility of predictive models, the validation of inferred mechanisms, and the transferability of computational findings across tissues, diseases, and experimental conditions. Knowledge-guided and network-based approaches may help address these limitations by combining data-driven learning with established biological relationships and functional principles.This Research Topic aims to advance the use of artificial intelligence and network biology for elucidating RNA-related disease mechanisms. It will examine how machine learning, graph representation learning, knowledge graphs, network modeling, and multi-omics integration can characterize RNA-associated interactions, regulatory processes, disease relationships, and molecular pathways. Contributions may address questions concerning how prior biological knowledge can improve model robustness and interpretability, how computational methods can distinguish causal or mechanistically relevant associations from correlations, and how predicted RNA biomarkers or therapeutic targets can be biologically validated. The Research Topic also seeks to promote methodological developments and biologically driven applications that strengthen the connection between computational predictions and experimentally testable hypotheses.To gather further insights into computational and network-based investigations of RNA-related disease mechanisms, this Research Topic will focus on studies involving RNA biology, disease-associated molecular interactions, regulatory systems, and translational applications, while excluding research without a clear connection to RNA-mediated mechanisms or biological interpretation. We welcome articles addressing, but not limited to, the following themes:• RNA–disease association prediction and prioritization• RNA–protein and RNA–RNA interaction modeling• Regulatory networks involving coding and non-coding RNAs• Functional analysis of disease-associated RNAs• Heterogeneous biological networks and knowledge graphs• Graph representation learning and graph neural networks for RNA biology• Knowledge-guided, explainable, and interpretable artificial intelligence• Integration of RNA-related transcriptomic, epigenomic, proteomic, and other multi-omics data• Computational identification of RNA biomarkers and therapeutic targets• Network-based analysis of RNA-mediated disease mechanisms• Methodological frameworks for model robustness, reproducibility, and biological validation• Applications to specific diseases, tissues, cell types, or disease progressionAppendix: We welcome Original Research, Methods, Reviews, and other relevant article types. Topic editors: Yue-Chao Li, Xinfei Wang, Mengmeng Wei, Yongteng Song Source: https://www.frontiersin.org/research-topics/85754/knowledge-guided-artificial-intelligence-and-network-biology-for-rna-related-disease-mechanisms