Bacteria classification using minimal absent words

Abstract

Bacteria classification has been deeply investigated with different tools for many purposes, such as early diagnosis, metagenomics, phylogenetics. Classification methods based on ribosomal DNA sequences are considered a reference in this area. We present a new classificatier for bacteria species based on a dissimilarity measure of purely combinatorial nature. This measure is based on the notion of Minimal Absent Words, a combinatorial definition that recently found applications in bioinformatics. We can therefore incorporate this measure into a probabilistic neural network in order to classify bacteria species. Our approach is motivated by the fact that there is a vast literature on the combinatorics of Minimal Absent Words in relation with the degree of repetitiveness of a sequence. We ran our experiments on a public dataset of Ribosomal RNA Sequences from the complex 16S. Our approach showed a very high score in the accuracy of the classification, proving hence that our method is comparable with the standard tools available for the automatic classification of bacteria species.