Identifying the Characteristics of the Hypusination Sites Using SMOTE and SVM Algorithm with Feature Selection
文献类型：期刊论文
| 作者 | Sun, XiJun2; Li, JiaRui2; Wang, ShaoPeng2; Cai, Yu-Dong2; Gu, Lei1,3; Zhang, YuHang4; Huang, Tao4; , |
| 刊名 | CURRENT PROTEOMICS
 |
| 出版日期 | 2018 |
| 卷号 | 15期号:2页码:111-118 |
| 关键词 | Hypusination SMOTE mRMR marchine-learning feature selection SMO |
| ISSN号 | 1570-1646 |
| DOI | 10.2174/1570164614666171109120615 |
| 文献子类 | Article |
| 英文摘要 | Background: Hypusination is a unique modification on lysine residues in eukaryotic translation initiation factor 5A (eIF5A), which is essential and highly conserved in all kinds of eukaryotes. However, the mechanism of recognizing this particular hypusination site remains unclear. In this study, we first gave an attempt in uncovering the characteristics of the hypusination sites using computational methods. Method: The hypusination sites validated by experiments or predicted through sequence similarity that were retrieved from the UniProt database were selected for investigating. Each site was transformed into a peptide segment that contained the modification site and the residues around it. Four types of features were extracted from the peptide segments. Because the hypusination sites are much fewer than non-hypusination sites, the synthetic minority over-sampling technique (SMOTE) was performed to make the dataset containing them balanced. Then, some feature selection methods, including maximum relevance minimum redundancy (mRMR) and incremental feature selection (IFS), were used to analyze four types of features and build an optimal classifier that used support vector machine (SVM) as the prediction engine. Results: The obtained optimal SVM classifier harboring four amino acid features yielded a perfect Mathews' correlation coefficient (MCC) value of 1.000 on both training and testing sets, indicating these four features are hypusination specific characteristics. Conclusions: As a pioneer work, our analysis provides insight into the improvement of the understanding of hypusination mechanisms. |
| 学科主题 | Biochemistry & Molecular Biology |
| WOS关键词 | TRANSLATION INITIATION-FACTOR ; AMINO-ACID ; FACTOR 5A ; POSTTRANSLATIONAL MODIFICATIONS ; PROTEIN ; PREDICTION ; EIF5A ; IDENTIFICATION ; BINDING ; EXPRESSION |
| 语种 | 英语 |
| WOS记录号 | WOS:000427494700004 |
| 出版者 | BENTHAM SCIENCE PUBL LTD |
| 版本 | 出版稿 |
| 源URL | [http://202.127.25.144/handle/331004/680]  |
| 专题 | 中国科学院上海生命科学研究院营养科学研究所 |
| 作者单位 | 1.Harvard Med Sch, Cell Biol Dept, Boston, MA 02215 USA; 2.Shanghai Univ, Coll Life Sci, Shanghai 200444, Peoples R China; 3.Boston Childrens Hosp, Boston, MA 02215 USA; 4.Chinese Acad Sci, Shanghai Inst Biol Sci, Inst Hlth Sci, Shanghai 200031, Peoples R China, |
| 推荐引用方式 GB/T 7714 | Sun, XiJun,Li, JiaRui,Wang, ShaoPeng,et al. Identifying the Characteristics of the Hypusination Sites Using SMOTE and SVM Algorithm with Feature Selection[J]. CURRENT PROTEOMICS,2018,15(2):111-118. |
| APA | Sun, XiJun.,Li, JiaRui.,Wang, ShaoPeng.,Cai, Yu-Dong.,Gu, Lei.,...&,.(2018).Identifying the Characteristics of the Hypusination Sites Using SMOTE and SVM Algorithm with Feature Selection.CURRENT PROTEOMICS,15(2),111-118. |
| MLA | Sun, XiJun,et al."Identifying the Characteristics of the Hypusination Sites Using SMOTE and SVM Algorithm with Feature Selection".CURRENT PROTEOMICS 15.2(2018):111-118. |
入库方式： OAI收割
来源：上海营养与健康研究所
浏览0
下载0
收藏0
其他版本
除非特别说明，本系统中所有内容都受版权保护，并保留所有权利。