Skip to main content

Table 11 Dataset D on IBD: classification performance of Ph-CNN compared to other classifiers on Healthy vs. CDf classification task

From: Phylogenetic convolutional neural networks in metagenomics

CDf

Ph-CNN

LSVM

p

MCC

min CI

max CI

MCC

min CI

max CI

65

0.613

0.555

0.665

0.419

0.363

0.472

130

0.617

0.549

0.601

0.326

0.252

0.394

195

0.630

0.560

0.682

0.647

0.595

0.691

259

0.572

0.501

0.620

0.595

0.545

0.642

 

MLPNN

RF

p

MCC

min CI

max CI

MCC

min CI

max CI

65

0.610

0.549

0.666

0.677

0.618

0.728

130

0.620

0.551

0.685

0.706

0.648

0.758

195

0.601

0.534

0.667

0.739

0.685

0.788

259

0.648

0.589

0.703

0.720

0.667

0.768

  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)