English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Biomedical research has revealed the crucial role of miRNAs in theprogression of many diseases, and computational prediction methods areincreasingly proposed for assisting biological experiments to verifymiRNA-disease associations (MDAs). However, the generalizability andexplainability are currently underemphasized. It's significant to generalizeeffective predictions to entities with fewer or no existing MDAs and reveal howthe prediction scores are derived. In this study, our work contributes to data,model, and result analysis. First, for better formulation of the MDA issue, weintegrate multi-source data into a heterogeneous graph with a broader learningand prediction scope, and we split massive verified MDAs into independenttraining, validation, and test sets as a benchmark. Second, we construct anend-to-end data-driven model that performs node feature encoding, graphstructure learning, and binary prediction sequentially, with a heterogeneousgraph transformer as the central module. Finally, computational experimentsillustrate that our method outperforms existing state-of-the-art methods,achieving better evaluation metrics and alleviating the neglect of unknownmiRNAs and diseases effectively. Case studies further demonstrate that we canmake reliable MDA detections on diseases without MDA records, and thepredictions can be explained in general and case by case.

Generalizable and explainable prediction of potential miRNA-disease associations based on heterogeneous graph learning