Skip to main content

Table 14 Dataset D on IBD: 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 0.537 0.480 0.601 0.338 0.277 0.409
129 0.522 0.453 0.595 0.319 0.254 0.385
193 0.556 0.492 0.617 0.377 0.315 0.437
257 0.477 0.411 0.544 0.438 0.378 0.492
  MLPNN RF
p MCC min CI max CI MCC min CI max CI
63 0.526 0.475 0.581 0.552 0.492 0.612
125 0.558 0.493 0.623 0.563 0.516 0.609
188 0.459 0.388 0.527 0.566 0.516 0.616
250 0.529 0.462 0.598 0.539 0.482 0.596
  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)