PredictFP2: A New Computational Model to Predict Fusion Peptide Domain in All Retroviruses

doi:10.1109/TCBB.2019.2898943

	PredictFP2: A New Computational Model to Predict Fusion Peptide Domain in All Retroviruses
	Wu, Sijia 1; Wu, Xiaoming 1; Tian, Jie 2; Zhou, Xiaobo 3; Huang, Liyu 1
发表期刊	IEEE-ACM TRANSACTIONS ON COMPUTATIONAL BIOLOGY AND BIOINFORMATICS
ISSN	1545-5963
	2020-09-01
卷号	17 期号:5 页码:1714-1720
通讯作者	Wu, Sijia(wusjia@xidian.edu.cn) ; Huang, Liyu(huangly@mail.xidian.edu.cn)
摘要	Fusion peptide (FP) is a pivotal domain for the entry of retrovirus into host cells to continue self-replication. The crucial role indicates that FP is a promising drug target for therapeutic intervention. A FP model proposed in our previous work is relatively not efficient to predict FP in retroviruses. Thus in this work, we come up with a new computational model to predict FP domains in all the retroviruses. It basically predicts FP domains through recognizing their start and end sites separately with SVM method combing the hydrophobicity knowledge of the subdomain around furin cleavage site. The classification accuracy rates are 91.91, 91.20 and 89.13 percent respectively corresponding to jack-knife, 10-fold cross-validation and 5-fold cross-validation test. Second, this model discovered 69,753 and 493 putative FPs after scanning amino acid sequences and HERV DNA sequences both without FP annotations. Subsequently, a statistical analysis was performed on the 69,753 putative FP sequences, which confirms that FP is a hydrophobic domain. Lastly, we depicted the distribution of the 493 putative FP sequences on each human chromosome and each HERV family, which shows that FP of HERV probably has chromosome and family preference.
关键词	Benchmark testing Amino acids Support vector machines Computational modeling Predictive models Cells (biology) Databases Fusion peptide prediction FP distribution hydrophobicity retrovirus support vector machine
DOI	10.1109/TCBB.2019.2898943
收录类别	SCI
语种	英语
资助项目	National Key Research and Development Program of China[2017YFA0205202] ; China Postdoctoral Science Foundation[2018M643583] ; Fundamental Research Funds for the Central Universities - National Natural Science Foundation of China[61672422] ; Fundamental Research Funds for the Central Universities - National Natural Science Foundation of China[U1401255]
项目资助者	National Key Research and Development Program of China ; China Postdoctoral Science Foundation ; Fundamental Research Funds for the Central Universities - National Natural Science Foundation of China
WOS研究方向	Biochemistry & Molecular Biology ; Computer Science ; Mathematics
WOS类目	Biochemical Research Methods ; Computer Science, Interdisciplinary Applications ; Mathematics, Interdisciplinary Applications ; Statistics & Probability
WOS记录号	WOS:000576418300023
出版者	IEEE COMPUTER SOC
引用统计	被引频次：2[WOS] [WOS记录] [WOS相关记录]
文献类型	期刊论文
条目标识符	http://ir.ia.ac.cn/handle/173211/42076
专题	中国科学院分子影像重点实验室
通讯作者	Wu, Sijia; Huang, Liyu
作者单位	1.Xidian Univ, Sch Life Sci & Technol, Xian 710049, Shaanxi, Peoples R China 2.Chinese Acad Sci, Inst Automat, Beijing, Peoples R China 3.Wake Forest Sch Med, Dept Radiol, Med Ctr Blvd, Winston Salem, NC 27157 USA
推荐引用方式 GB/T 7714	Wu, Sijia,Wu, Xiaoming,Tian, Jie,et al. PredictFP2: A New Computational Model to Predict Fusion Peptide Domain in All Retroviruses[J]. IEEE-ACM TRANSACTIONS ON COMPUTATIONAL BIOLOGY AND BIOINFORMATICS,2020,17(5):1714-1720.
APA	Wu, Sijia,Wu, Xiaoming,Tian, Jie,Zhou, Xiaobo,&Huang, Liyu.(2020).PredictFP2: A New Computational Model to Predict Fusion Peptide Domain in All Retroviruses.IEEE-ACM TRANSACTIONS ON COMPUTATIONAL BIOLOGY AND BIOINFORMATICS,17(5),1714-1720.
MLA	Wu, Sijia,et al."PredictFP2: A New Computational Model to Predict Fusion Peptide Domain in All Retroviruses".IEEE-ACM TRANSACTIONS ON COMPUTATIONAL BIOLOGY AND BIOINFORMATICS 17.5(2020):1714-1720.