Table 4 Classification results on BRCA dataset.

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

Method

ACC

F1_weighted

F1_macro

KNN

0.742 ± 0.024

0.730 ± 0.023

0.682 ± 0.025

SVM

0.729 ± 0.018

0.702 ± 0.015

0.640 ± 0.017

Lasso

0.732 ± 0.012

0.698 ± 0.015

0.642 ± 0.026

RF

0.754 ± 0.009

0.733 ± 0.010

0.649 ± 0.013

XGBoost

0.781 ± 0.008

0.764 ± 0.010

0.701 ± 0.017

NN

0.754 ± 0.028

0.740 ± 0.034

0.668 ± 0.047

GRridge

0.745 ± 0.016

0.726 ± 0.019

0.656 ± 0.025

block PLSDA

0.642 ± 0.009

0.534 ± 0.014

0.369 ± 0.017

block sPLSDA

0.639 ± 0.008

0.522 ± 0.016

0.351 ± 0.022

NN_NN

0.796 ± 0.012

0.784 ± 0.014

0.723 ± 0.018

NN_VCDN

0.792 ± 0.010

0.781 ± 0.006

0.721 ± 0.018

MOGONET_NN (Ours)

0.805 ± 0.017

0.782 ± 0.030

0.737 ± 0.038

MOGONET (Ours)

0.829 ± 0.018

0.825 ± 0.016

0.774 ± 0.017

Back to article page