Fig 1.
(A) shows the composition of the three-layer heterogeneous network (disease-gene-miRNA network), where yellow lines represent disease-gene connections, blue lines mean miRNA-gene connections. (B) shows the phenotype-gene-miRNA network, where purple lines represent phenotype-gene connections and blue lines mean miRNA-gene connections.
Fig 2.
The framework of GCSENet.
Fig 3.
Weighted feature processing for disease-gene and miRNA-gene.
Fig 4.
New feature component addition.
Table 1.
Prediction performance comparison with different GCSENet components.
Fig 5.
Comparison of ROC curves with different GCSENet components.
Fig 6.
Comparison of different ROC and AUPR curves in miRNA-disease association prediction.
Table 2.
Performance comparison with typical methods for miRNA-disease association prediction.
Fig 7.
AUROC comparison of miRNA-disease in 10-fold cross-validation.
(A) With different methods. (B) With different pos/neg ratios.
Table 3.
Performance comparison with various methods for miRNA-phenotype association prediction.
Fig 8.
AUROC of miRNA-phenotype in 10-fold cross-validation (A), and Precision-Recall curve of lung neoplasms, heart failure, breast cancer and glioblastoma (B).
Fig 9.
The number of predicted miRNAs verified in HMDD v3.0 by our model, including different top intervals.
Table 4.
Validation results of predicted associations for lung neoplasms as an unknown disease.
Table 5.
Validation results of predicted associations for heart failure as an unknown disease.
Table 6.
Validation results of predicted associations for breast cancer as an unknown disease.
Table 7.
Validation results of predicted associations for glioblastoma as an unknown disease.