Skip to main content

Table 6 Dataset D: classification performance of Ph-CNN compared to other classifiers on Healthy vs. iCDf classification task

From: Phylogenetic convolutional neural networks in metagenomics

iCDf Ph-CNN LSVM
p MCC min CI max CI MCC min CI max CI
62 0.781 0.772 0.790 0.804 0.799 0.808
124 0.863 0.854 0.871 0.861 0.858 0.865
186 0.922 0.918 0.926 0.921 0.919 0.924
247 0.944 0.941 0.947 0.941 0.939 0.942
  MLPNN RF
p MCC min CI max CI MCC min CI max CI
62 0.845 0.840 0.849 0.748 0.743 0.753
124 0.889 0.886 0.893 0.808 0.803 0.814
186 0.879 0.875 0.883 0.880 0.877 0.883
247 0.901 0.899 0.904 0.890 0.887 0.893
  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)