英语原文共 17 页，剩余内容已隐藏，支付完成后下载完整资料
xTargetCrys: protein crystallization prediction by fusing multi-view features with two-layered SVM
Targetcrys:融合双层 SVM 多视图特征的蛋白质结晶预测
Jun Hu, Ke Han, Yang Li, Jing-Yu Yang, Hong-Bin Shen amp; Dong-Jun Yu
胡军、柯寒、杨莉、杨靖宇、沈洪斌、董军宇
Amino Acids
氨基酸
The Forum for Amino Acid, Peptide and Protein Research
氨基酸、肽和蛋白质研究
ISSN 0939-4451
Issn 0939-4451
Amino Acids
氨基酸
DOI 10.1007/s00726-016-2274-4
Doi 10.1007 / s00726-016-2274-4
Your article is protected by copyright and all rights are held exclusively by Springer-Verlag Wien. This e-offprint is for personal use only and shall not be self-archived in electronic repositories. If you wish to self-archive your article, please use the accepted manuscript version for posting on your own website. You may further deposit the accepted manuscript version in any repository, provided it is only made publicly available 12 months after official publication or later and provided acknowledgement is given to the original source of publication and a link is inserted to the published article on Springers website. The link must be accompanied by the following text: 'The final publication is available at link.springer.com”.
你的文章受版权保护，所有权利由施普林格-维恩公司独家拥有。本电子版仅供个人使用，不得自行存档在电子仓库里。如果您希望自我存档您的文章，请使用认可的原稿版本张贴在您自己的网站上。你可以进一步将认可的原稿版本存放在任何存储库中，但必须在正式出版后 12 个月或以后才公开提供，而且必须确认原始出版来源，并在施普林格网站上插入已出版文章的链接。该链接必须附有以下文字:“最终出版物可在 link.springer.com 公布”。
Amino Acids
氨基酸
DOI 10.1007/s00726-016-2274-4
Doi 10.1007 / s00726-016-2274-4
ORIGINAL ARTICLE
原文
TargetCrys: protein crystallization prediction by fusing multi‑view features with two‑layered SVM
Targetcrys:融合双层 SVM 多视图特征的蛋白质结晶预测
Jun Hu1 ·Ke Han1 ·Yang Li1 ·Jing‑Yu Yang1 ·Hong‑Bin Shen2 ·Dong‑Jun Yu1
胡军 1 柯寒1 杨莉1杨靖宇 1 沈洪斌 2 董军宇 1
Received: 30 July 2015 / Accepted: 7 June 2016
copy; Springer-V erlag Wien 2016
收到日期:2015 年 7 月 30 日/接受日期:2016年 6 月 7 日
copy;_Springer-V erlag Wien 2016
Abstract The accurate prediction of whether a pro-tein will crystallize plays a crucial role in improving the success rate of protein crystallization projects. A com-mon critical problem in the development of machine-learning-based protein crystallization predictors is how to effectively utilize protein features extracted from dif-ferent views. In this study, we aimed to improve the effi-ciency of fusing multi-view protein features by proposing
摘要准确预测蛋白质结晶是否会结晶，对提高蛋白质结晶工程的成功率起着至关重要的作用。基于机器学习的蛋白质结晶预测器研究中的一个关键问题是如何有效地利用从不同角度提取的蛋白质特征。为了提高融合多视点蛋白质特征的效率，本文提出了一种新的融合多视点蛋白质特征的方法
a new two-layered SVM (2L-SVM) which switches the feature-level fusion problem to a decision-level fusion problem: the SVMs in the 1st layer of the 2L-SVM are trained on each of the multi-view feature sets; then, the outputs of the 1st layer SVMs, which are the “interme-diate” decisions made based on the respective feature sets, are further ensembled by a 2nd layer SVM. Based on the proposed 2L-SVM, we implemented a sequence-based protein crystallization predictor called TargetCrys. Experimental results on several benchmark datasets dem-onstrated the efficacy of the proposed 2L-SVM for fus-ing multi-view features. We also compared TargetCrys with existing sequence-based protein crystallization pre-dictors and demonstrated that the proposed TargetCrys outperformed most of the existing predictors and is com-petitive with the state-of-the-art predictors. The Target-Crys webserver and datasets used in this study are freely
将特征层融合问题转化为决策层融合问题的新型两层支持向量机(2l-SVM):将 2l-SVM 的第一层支持向量机分别对每一个多视图特征集进行训练，然后将第一层支持向量机的输出，即基于各个特征集的“间隔”决策，进一步集成到第二层。基于所提出的 2L-SVM，我们实现了一个基于序列的蛋白质结晶预测器 TargetCrys。在多个基准数据集上的实验结果表明，该方法能够有效地处理多视点特征。我们还将 TargetCrys 与现有的基于序列的蛋白质结晶预测器进行了比较，证明了所提出的 TargetCrys 优于大多数现有的预测器，并且与最先进的预测器相匹配。本研究使用的 Target-Crys 网络服务器和数据集是免费的。
Handling Editor: S. C. E. Tosatto.
处理编辑:S.C.e.Tosatto。
* Dong‑Jun Yu
*董军宇
njyudj@njust.edu.cn; njyudj@126.com @ njust. edu. cn; njyudj@126. com
1、School of Computer Science and Engineering, Nanjing University of Science and Technology, Xiaolingwei 200, Nanjing 210094, China
南京科技大学计算机科学与工程学院，南京210094，小灵威200，
2、Department of Automation, Shanghai Jiao Tong University, Dongchuan Road 800, Shanghai 200240, China
上海交通大学自动化系，上海市东川路800号，邮编：200240
available for academic use at: http://csbio.njust.edu.cn/ bioinf/TargetCrys.
可供学术用途:http://csbio.njust.edu.cn/ bioinf/TargetCrys.
Keywords Protein crystallization prediction ·Multi-view feature fusion ·Support vector machine ·Machine learning
关键词蛋白质结晶预测多视图特征融合支持向量机机器学习
Introduction
引言
It has become widely accepted that a close relationship exists between protein structure and function (Tramontano and Cozzetto 2004; Gromiha 2010; Zhang 2014). Knowing the accurate structure of a protein is vitally important for deter-mining its functionalities and interactions with other biologi-cal molecules (Chou 2004; Roy and Zhang 2012; Hu et al. 2014a). Due to the rapid development of technological break-throughs and the explosion in gene sequence data (Rung and Brazma 2013), a large volume of protein sequences without determined structures have been accumulated. The large gap between protein sequences and structures has inspired the launch of structural genomics initiatives (SGI) (Todd et al. 2005) that aim to describe the tertiary structures of every protein encoded by a given genome and narrow the gap betwee
剩余内容已隐藏，支付完成后下载完整资料
资料编号：[409787]，资料为PDF文档或Word文档，PDF文档可免费转换为Word
以上是毕业论文外文翻译，课题毕业论文、任务书、文献综述、开题报告、程序设计、图纸设计等资料可联系客服协助查找。
