Skip to main content

Table 13 Dataset D on IBD: 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 0.704 0.655 0.753 0.534 0.484 0.583
124 0.702 0.642 0.760 0.414 0.346 0.482
186 0.680 0.614 0.738 0.662 0.605 0.718
247 0.681 0.614 0.739 0.561 0.507 0.621
  MLPNN RF
p MCC min CI max CI MCC min CI max CI
62 0.679 0.622 0.739 0.787 0.746 0.831
124 0.690 0.634 0.743 0.811 0.766 0.854
186 0.685 0.630 0.742 0.791 0.741 0.836
247 0.708 0.652 0.764 0.775 0.730 0.820
  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)