A computational model for predicting fusion peptide of retroviruses

Sijia Wu; Jiuqiang Han; Ruiling Liu; Jun Liu; Hongqiang Lv

doi:10.1016/j.compbiolchem.2016.02.013

A computational model for predicting fusion peptide of retroviruses

Comput Biol Chem. 2016 Apr:61:245-50. doi: 10.1016/j.compbiolchem.2016.02.013. Epub 2016 Mar 2.

Authors

Sijia Wu¹, Jiuqiang Han², Ruiling Liu¹, Jun Liu³, Hongqiang Lv¹

Affiliations

¹ School of Electronic and Information Engineering, Xi'an Jiaotong University, Xi'an, China.
² School of Electronic and Information Engineering, Xi'an Jiaotong University, Xi'an, China. Electronic address: jqhan@mail.xjtu.edu.cn.
³ School of Electrical Engineering, Xi'an Jiaotong University, Xi'an, China.

PMID: 26963379
DOI: 10.1016/j.compbiolchem.2016.02.013

Abstract

As a pivotal domain within envelope protein, fusion peptide (FP) plays a crucial role in pathogenicity and therapeutic intervention. Taken into account the limited FP annotations in NCBI database and absence of FP prediction software, it is urgent and desirable to develop a bioinformatics tool to predict new putative FPs (np-FPs) in retroviruses. In this work, a sequence-based FP model was proposed by combining Hidden Markov Method with similarity comparison. The classification accuracies are 91.97% and 92.31% corresponding to 10-fold and leave-one-out cross-validation. After scanning sequences without FP annotations, this model discovered 53,946 np-FPs. The statistical results on FPs or np-FPs reveal that FP is a conserved and hydrophobic domain. The FP software programmed for windows environment is available at https://sourceforge.net/projects/fptool/files/?source=navbar.

Keywords: Fusion peptide domain prediction; Hidden Markov Method; Similarity comparison.

Publication types

Research Support, Non-U.S. Gov't

MeSH terms

Models, Biological*
Peptides / metabolism*
Recombinant Fusion Proteins / metabolism*
Retroviridae / metabolism*

Substances

Peptides
Recombinant Fusion Proteins