Skip to main content

Table 6 Thw performance of HFE vs. MetAML when applied to the CRC and IBD datasets provided by Pasolli et al. [12], in terms of mean AUC and standard deviation

From: Taxonomy-aware feature engineering for microbiome classification

 

CRCMetAML

IBDMetAML

RF

 

RF

 

Mean

Std.

#Features

Mean

Std.

#Features

MetAML-RF

0.874

0.102

490

0.891

0.100

434

MetAML-RF-Enet:Emb

0.870

0.108

70

0.898

0.103

125

MetAML-RF-Lasso:Emb

0.769

0.135

90

0.883

0.118

70

HFE

0.910

0.093

34

0.919

0.090

26