Table 3 Classification results on LGG dataset.

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

Method

ACC

F1

AUC

KNN

0.729 ± 0.034

0.738 ± 0.033

0.799 ± 0.038

SVM

0.754 ± 0.046

0.757 ± 0.050

0.754 ± 0.046

Lasso

0.761 ± 0.018

0.767 ± 0.022

0.823 ± 0.027

RF

0.748 ± 0.012

0.742 ± 0.010

0.823 ± 0.010

XGBoost

0.756 ± 0.040

0.767 ± 0.032

0.840 ± 0.023

NN

0.737 ± 0.023

0.748 ± 0.024

0.810 ± 0.037

GRridge

0.746 ± 0.038

0.756 ± 0.036

0.826 ± 0.044

block PLSDA

0.759 ± 0.025

0.738 ± 0.031

0.825 ± 0.023

block sPLSDA

0.685 ± 0.027

0.662 ± 0.030

0.730 ± 0.026

NN_NN

0.740 ± 0.039

0.756 ± 0.036

0.824 ± 0.036

NN_VCDN

0.740 ± 0.030

0.771 ± 0.021

0.826 ± 0.031

MOGONET_NN (Ours)

0.804 ± 0.025

0.811 ± 0.023

0.832 ± 0.029

MOGONET (Ours)

0.816 ± 0.016

0.814 ± 0.014

0.840 ± 0.027

Back to article page