A k-mer-based barcode DNA classification methodology based on spectral representation and a neural gas network

作者：

Highlights：

• We propose a new alignment-free method for the classification of DNA barcoding based on both a spectral representation and prototype-based unsupervised clustering.

• We investigate how much the characteristics of different species are related to their DNA barcoding spectral distribution.

• We compare the proposed method with six state-of-the-art machine learning classifiers and the results confirm our method overcome all the other classifiers when applied to short fragments.

摘要

Highlights•We propose a new alignment-free method for the classification of DNA barcoding based on both a spectral representation and prototype-based unsupervised clustering.•We investigate how much the characteristics of different species are related to their DNA barcoding spectral distribution.•We compare the proposed method with six state-of-the-art machine learning classifiers and the results confirm our method overcome all the other classifiers when applied to short fragments.

论文关键词：Alignment-free analysis,DNA barcode classification,k-Mer representation,Neural gas

论文评审过程：Received 27 August 2014, Revised 25 May 2015, Accepted 25 June 2015, Available online 4 July 2015, Version of Record 2 September 2015.

论文官网地址：https://doi.org/10.1016/j.artmed.2015.06.002