Fig. 2: Performance comparison of multi-omics data classification via MOGONET and single-omics data classification via GCN (n = 5 experiments for each model). | Nature Communications

Fig. 2: Performance comparison of multi-omics data classification via MOGONET and single-omics data classification via GCN (n = 5 experiments for each model).

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

Fig. 2

a Results of the ROSMAP dataset. b Results of the LGG dataset. c Results of the BRCA dataset. Means of evaluation metrics with standard deviations from different experiments are shown in the figure, where the error bar represents plus/minus one standard deviation. mRNA, meth, and miRNA refer to single-omics data classification via GCN with mRNA expression data, DNA methylation data, and miRNA expression data, respectively. mRNA + meth, mRNA + miRNA, and meth + miRNA refer to classification with two types of omics data. mRNA + meth + miRNA refers to classification with three types of omics data. Source data are provided as a Source Data file.

Back to article page