MDHGI: Matrix Decomposition and Heterogeneous Graph Inference for miRNA-disease association prediction
Fig 5
The left graph shows the AUC of global LOOCV compared with HGIMDA, RLSMDA, HDMP, WBSMDA, and MCMDA. The right graph shows the AUC of local LOOCV compared with HGIMDA, RLSMDA, HDMP, WBSMDA, MCMDA, RWRMDA, MIDP, and MiRAI. As a result, MDHGI achieved AUCs of 0.8945 and 0.8240 in the global and local LOOCV, which exceed all the previous classical models.