Fig. 3: Performance of MOGONET under different values of hyper-parameter k. | Nature Communications

Fig. 3: Performance of MOGONET under different values of hyper-parameter k.

From: MOGONET integrates multi-omics data using graph convolutional networks allowing patient classification and biomarker identification

Fig. 3

a Results of the ROSMAP dataset. b Results of the BRCA dataset. The dashed lines represent the results from the best performed existing multi-omics integration methods (GRridge for ROSMAP and XGBoost for BRCA). MOGONET outperformed the best existing methods under different k values. Source data are provided as a Source Data file.

Back to article page