Skip to main content
Fig. 3 | BMC Bioinformatics

Fig. 3

From: DectICO: an alignment-free supervised metagenomic classification method based on feature extraction and dynamic selection

Fig. 3

Comparison of classification performance between DectICO and the non-dynamic feature-selection-based method on the asthma and IBD datasets. The comparisons of the average LOOCV accuracies of the 20 classifiers between those trained by DectICO and those by the non-dynamic feature-selection-based method are presented. a and b correspond to the asthma and IBD metagenomes, respectively. The solid lines with the square tags represent the classification performances of DectICO, while the dotted lines with the rounded tags correspond to the non-dynamic feature-selection-based method. The framework of this figure is the same as Fig. 2

Back to article page