Title

Comparisons Of Classification Methods For Viral Genomes And Protein Families Using Alignment-Free Vectorization

Keywords

family labels; Natural Vector; protein; statistical classification models; viral genomes

Abstract

In this paper, we propose a statistical classification method based on discriminant analysis using the first and second moments of positions of each nucleotide of the genome sequences as features, and compare its performances with other classification methods as well as natural vector for comparative genomic analysis. We examine the normality of the proposed features. The statistical classification models used including linear discriminant analysis, quadratic discriminant analysis, diagonal linear discriminant analysis, k-nearest-neighbor classifier, logistic regression, support vector machines, and classification trees. All these classifiers are tested on a viral genome dataset and a protein dataset for predicting viral Baltimore labels, viral family labels, and protein family labels.

Publication Date

8-28-2018

Publication Title

Statistical Applications in Genetics and Molecular Biology

Volume

17

Issue

4

Document Type

Article

Personal Identifier

scopus

DOI Link

https://doi.org/10.1515/sagmb-2018-0004

Socpus ID

85049725898 (Scopus)

Source API URL

https://api.elsevier.com/content/abstract/scopus_id/85049725898

This document is currently not available here.

Share

COinS