Skip to main content

Table 2 Dataset D: classification performance of Ph-CNN compared to other classifiers on Healthy vs. UCf classification task

From: Phylogenetic convolutional neural networks in metagenomics

UCf

Ph-CNN

LSVM

p

MCC

min CI

max CI

MCC

min CI

max CI

63

0.794

0.785

0.803

0.799

0.793

0.803

125

0.852

0.845

0.860

0.861

0.857

0.865

188

0.920

0.916

0.925

0.924

0.921

0.926

250

0.940

0.937

0.944

0.943

0.941

0.945

 

MLPNN

RF

p

MCC

min CI

max CI

MCC

min CI

max CI

63

0.701

0.692

0.721

0.729

0.723

0.736

125

0.838

0.834

0.842

0.843

0.837

0.849

188

0.865

0.861

0.869

0.902

0.899

0.906

250

0.898

0.894

0.901

0.903

0.900

0.907

  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)