版权说明 操作指南
首页 > 成果 > 详情

基于支持向量机的高维特征非线性快速筛选与肽QSAR建模

认领
导出
Link by 中国知网学术期刊 Link by 万方学术期刊
反馈
分享
QQ微信 微博
成果类型:
期刊论文
作者:
Dai Zhi-Jun;Zhou Wei;Yuan Zhe-Ming*
通讯作者:
Yuan Zhe-Ming
作者机构:
[Zhou Wei; Dai Zhi-Jun; Yuan Zhe-Ming] Hunan Agr Univ, Coll Biosafety Sci & Technol, Changsha 410128, Hunan, Peoples R China.
[Dai Zhi-Jun; Yuan Zhe-Ming] Hunan Prov Key Lab Crop Germplasm Innovat & Utili, Changsha 410128, Hunan, Peoples R China.
通讯机构:
[Yuan Zhe-Ming] H
Hunan Agr Univ, Coll Biosafety Sci & Technol, Changsha 410128, Hunan, Peoples R China.
语种:
中文
关键词:
高维特征;特征选择;肽;定量序效关系;支持向量机
关键词(英文):
Feature selection;High dimensional feature;Peptide;Quantitative sequence-activity relationship;Support vector machine
期刊:
物理化学学报
ISSN:
1000-6818
年:
2011
卷:
27
期:
7
页码:
1654-1660
基金类别:
Science Foundation for Distinguished Young Scholars of Hunan Province, ChinaNational Natural Science Foundation of China (NSFC)National Science Fund for Distinguished Young Scholars [10JJ1005]; Research Fund for the Doctoral Program of Higher Education of ChinaResearch Fund for the Doctoral Program of Higher Education of China (RFDP)Specialized Research Fund for the Doctoral Program of Higher Education (SRFDP) [200805370002]; Team Project for the Technology Innovation of Higher Education of Hunan Province, China
机构署名:
本校为第一且通讯机构
院系归属:
植物保护学院
摘要:
以氨基酸的531个物理化学性质参数直接表征肽的结构,基于支持向量回归发展了一种新的高维特征非线性快速筛选方法,将其应用于苦味二肽和血管紧张素转化酶抑制剂2个肽体系的定量序效关系(QSAR)建模,各筛选获得10个意义明确的保留描述子,以保留描述子建立支持向量回归模型,其拟合精度、留一法交叉测试精度和外部预测精度较文献报道结果均有较大幅度提升,优势明显;对所建模型进行了非线性回归显著性测验、单因子相对重要性显著性测验和单因子效应分析,增强了模型的可解释性.新方法在肽、蛋白质QSAR建模等高维数据回归预测领域有广泛应用前景.
摘要(英文):
Each amino acid residue of one peptide was characterized directly by 531 physicochemical property parameters. Based on support vector regression (SVR) we developed a new nonlinear rapid feature selection method for high dimensional data, which was applied to a quantitative sequenceactivity relationship (QSAR) study of two peptide systems (bitter tasting thresholds and angiotensin converting enzyme inhibitors). In both systems, 10 descriptors with clear meaning were reserved. We established a SVR model for both peptide systems using the reserved...

反馈

验证码:
看不清楚,换一个
确定
取消

成果认领

标题:
用户 作者 通讯作者
请选择
请选择
确定
取消

提示

该栏目需要登录且有访问权限才可以访问

如果您有访问权限,请直接 登录访问

如果您没有访问权限,请联系管理员申请开通

管理员联系邮箱:yun@hnwdkj.com