Skip to main content

Table 12 Dataset D on IBD: classification performance of Ph-CNN compared to other classifiers on Healthy vs. CDr classification task

From: Phylogenetic convolutional neural networks in metagenomics

CDr

Ph-CNN

LSVM

p

MCC

min CI

max CI

MCC

min CI

max CI

65

0.241

0.172

0.311

0.138

0.073

0.198

129

0.232

0.167

0.295

0.089

0.028

0.151

193

0.202

0.131

0.273

0.169

0.101

0.236

257

0.218

0.158

0.278

0.178

0.107

0.251

 

MLPNN

RF

p

MCC

min CI

max CI

MCC

min CI

max CI

65

0.235

0.

0.306

0.488

0.437

0.541

129

0.275

0.199

0.348

0.432

0.373

0.485

193

0.243

0.172

0.315

0.402

0.341

0.464

257

0.233

0.160

0.305

0.398

0.331

0.464

  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)