Computational prediction of RNA modification site-disease associations: a systematic review

With the development of epitranscriptomics, studies have shown that RNA modification sites are closely related to many diseases. Because experimental validation is time-consuming and labor-intensive, an increasing number of studies have developed computational methods to predict potential associations between RNA modification sites and diseases. In this review, we summarize recent progress in predicting RNA modification site-disease associations, with a focus on common modifications such as m6A, m1A, and m7G. First, we systematically summarize commonly used databases and data sources and outline approaches for constructing similarity information for modification sites and diseases. We then review existing prediction methods-including network-based strategies, matrix completion, and machine learning-and discuss their typical advantages and limitations. Finally, we highlight key challenges in this field, including limited known associations, data imbalance, unclear definitions of negative samples, inconsistent evaluation standards across studies, and limited interpretability and experimental validation. We also suggest future directions, such as expanding high-quality datasets, integrating multi-omics data, establishing unified evaluation pipelines, and strengthening experimental validation. We hope this review provides a clear overview and practical guidance for studies on the associations between modification sites and diseases and supports the development of more reliable prediction methods.