iUMRG: multi-layered network-guided propagation modeling for the inference of susceptibility genes and potential drugs against uveal melanoma

Uveal melanoma (UM) is the most common primary malignant intraocular tumor. The use of precision medicine for UM to enable personalized diagnosis, prognosis, and treatment requires computer-aided strategies and predictive tools that can identify novel high-confidence susceptibility genes (HSGs) and potential therapeutic drugs. This study proposes iUMRG, a computational framework using propagation modeling on integrated multi-layered molecular networks, for systematic inference of UM susceptibility genes. Under leave-one-out cross-validation, iUMRG achieved superior performance with AUROC 0.8825 on experimentally verified SGs. Using these SGs as seeds, genome-wide screening detected candidate HSGs; multi-perspective validation indicated most of the top 50 candidates were associated with UM carcinogenesis, progression, and outcome. Drug repositioning on the HSGs revealed 17 potential targets and 10 potential drugs, six of which have been approved for UM treatment. iUMRG is an effective supplementary tool for UM precision medicine that may aid new therapy development and SG discovery.