Fig 1.
The disease DAG of lung neoplasms.
The addresses of its ancestors are shown in a DAG structure.
Fig 2.
Flowchart of MDHGI model to predict the potential miRNA-disease associations based on the known associations in HMDD V2.0 database.
Fig 3.
The illustration of the inexact ALM algorithm.
Fig 4.
The potential association probability between the miRNA m and the disease d which can be calculated by summarizing all paths with the length equal to three (For example, m–m1–d1–d).
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.
Table 1.
Supplementary experiments with different weight parameters to miRNA-miRNA edges and disease-disease edges (bold fonts are original weights and results).
Table 2.
Prediction of the top 50 predicted miRNAs associated with Esophageal Neoplasms based on known associations in HMDD V2.0 database.
The prediction result was examined in dbDEMC and miR2Disease. The first column records top 1–25 related miRNAs. The third column records the top 26–50 related miRNAs.
Table 3.
Prediction of the top 50 predicted miRNAs associated with lymphoma based on known associations in HMDD V2.0 database.
The prediction result was examined in dbDEMC and miR2Disease. The first column records top 1–25 related miRNAs. The third column records the top 26–50 related miRNAs.
Table 4.
Prediction of the top 50 predicted miRNAs associated with lung neoplasms based on known associations in HMDD V2.0 database.
All known associations between the miRNAs and Lung Neoplasms were removed before the prediction process. The prediction result was examined in dbDEMC, miR2Disease and HMDD V2.0. The first column records top 1–25 related miRNAs. The third column records the top 26–50 related miRNAs.
Table 5.
Prediction of the top 50 predicted miRNAs associated with breast neoplasms based on known associations in HMDD V1.0 database.
The prediction result was examined in dbDEMC, miR2Disease and HMDD V2.0. The first column records top 1–25 related miRNAs. The third column records the top 26–50 related miRNAs.