Skip to main content

Table 7 Dataset D: classification performance of Ph-CNN compared to other classifiers on Healthy vs. iCDr classification task

From: Phylogenetic convolutional neural networks in metagenomics

iCDr Ph-CNN LSVM
p MCC min CI max CI MCC min CI max CI
65 0.753 0.744 0.763 0.773 0.769 0.779
129 0.830 0.823 0.837 0.834 0.830 0.837
193 0.884 0.878 0.889 0.893 0.891 0.896
257 0.910 0.905 0.915 0.907 0.904 0.909
  MLPNN RF
p MCC min CI max CI MCC min CI max CI
63 0.807 0.802 0.812 0.724 0.719 0.729
125 0.822 0.816 0.827 0.794 0.788 0.800
188 0.831 0.827 0.835 0.812 0.807 0.818
250 0.837 0.831 0.842 0.820 0.816 0.825
  1. The performance measure is MCC, with 95% studentized bootstrap confidence intervals (min CI, max CI). Models are computed for p={25%,50%,75% and 100%} of total number of features for each task. Comparing algorithms are linear Support Vector Machines (LSVM), Random Forest (RF) and MultiLayer Perceptron (MLPNN)