Mirpara: a svm-based software tool for prediction of most probable microrna coding regions in genome scale sequences
文献类型：期刊论文
| 作者 | Wu, Yonggan1,2,3; Wei, Bo1; Liu, Haizhou1; Li, Tianxian2; Rayner, Simon1 |
| 刊名 | Bmc bioinformatics
 |
| 出版日期 | 2011-04-19 |
| 卷号 | 12页码:14 |
| ISSN号 | 1471-2105 |
| DOI | 10.1186/1471-2105-12-107 |
| 通讯作者 | Rayner, simon(simon.rayner.cn@gmail.com) |
| 英文摘要 | Background: micrornas are a family of similar to 22 nt small rnas that can regulate gene expression at the post-transcriptional level. identification of these molecules and their targets can aid understanding of regulatory processes. recently, hts has become a common identification method but there are two major limitations associated with the technique. firstly, the method has low efficiency, with typically less than 1 in 10,000 sequences representing mirna reads and secondly the method preferentially targets highly expressed mirnas. if sequences are available, computational methods can provide a screening step to investigate the value of an hts study and aid interpretation of results. however, current methods can only predict mirnas for short fragments and have usually been trained against small datasets which don't always reflect the diversity of these molecules. results: we have developed a software tool, mirpara, that predicts most probable mature mirna coding regions from genome scale sequences in a species specific manner. we classified sequences from mirbase into animal, plant and overall categories and used a support vector machine to train three models based on an initial set of 77 parameters related to the physical properties of the pre-mirna and its mirnas. by applying parameter filtering we found a subset of similar to 25 parameters produced higher prediction ability compared to the full set. our software achieves an accuracy of up to 80% against experimentally verified mature mirnas, making it one of the most accurate methods available. conclusions: mirpara is an effective tool for locating mirnas coding regions in genome sequences and can be used as a screening step prior to hts experiments. it is available at http://www.whiov.ac.cn/bioinformatics/mirpara |
| WOS关键词 | SUPPORT VECTOR MACHINES ; DECOMPOSITION METHODS ; IDENTIFICATION ; DROSOPHILA ; RECOGNITION ; COMPLEX ; MIRNA ; TRANSCRIPTS ; PATHWAYS ; MIRBASE |
| WOS研究方向 | Biochemistry & Molecular Biology ; Biotechnology & Applied Microbiology ; Mathematical & Computational Biology |
| WOS类目 | Biochemical Research Methods ; Biotechnology & Applied Microbiology ; Mathematical & Computational Biology |
| 语种 | 英语 |
| WOS记录号 | WOS:000291355400001 |
| 出版者 | BIOMED CENTRAL LTD |
| URI标识 | http://www.irgrid.ac.cn/handle/1471x/2375905 |
| 专题 | 武汉病毒研究所 |
| 通讯作者 | Rayner, Simon |
| 作者单位 | 1.Chinese Acad Sci, Wuhan Inst Virol, Bioinformat Grp, State Key Lab Virol, Wuhan 430071, Hubei, Peoples R China 2.Chinese Acad Sci, State Key Lab Virol, Wuhan Inst Virol, Wuhan 430071, Hubei, Peoples R China 3.Texas Tech Univ, Dept Biol Sci, Lubbock, TX 79409 USA |
| 推荐引用方式 GB/T 7714 | Wu, Yonggan,Wei, Bo,Liu, Haizhou,et al. Mirpara: a svm-based software tool for prediction of most probable microrna coding regions in genome scale sequences[J]. Bmc bioinformatics,2011,12:14. |
| APA | Wu, Yonggan,Wei, Bo,Liu, Haizhou,Li, Tianxian,&Rayner, Simon.(2011).Mirpara: a svm-based software tool for prediction of most probable microrna coding regions in genome scale sequences.Bmc bioinformatics,12,14. |
| MLA | Wu, Yonggan,et al."Mirpara: a svm-based software tool for prediction of most probable microrna coding regions in genome scale sequences".Bmc bioinformatics 12(2011):14. |
入库方式： iSwitch采集
来源：武汉病毒研究所
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。