Fig. 1From: Inferring potential small molecule–miRNA association based on triple layer heterogeneous networkPerformance evaluation comparison between TLHNSMMA and SMiR–NBI in terms of ROC curve and AUC based on global LOOCV in Dataset 1 (left) and Dataset 2 (right). As a result, TLHNSMMA achieved AUCs of 0.9859 and 0.8149 for Dataset 1 and Dataset 2, respectively. The predictive performance of TLHNSMMA is better than SMiR–NBIBack to article page