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
Copyright Status
Unknown
Socpus ID
85049725898 (Scopus)
Source API URL
https://api.elsevier.com/content/abstract/scopus_id/85049725898
STARS Citation
Huang, Hsin Hsiung; Hao, Shuai; Alarcon, Saul; and Yang, Jie, "Comparisons Of Classification Methods For Viral Genomes And Protein Families Using Alignment-Free Vectorization" (2018). Scopus Export 2015-2019. 8317.
https://stars.library.ucf.edu/scopus2015/8317