A novel method of protein secondary structure prediction with high segment overlap measure: Support vector machine approach
A novel method of protein secondary structure prediction with high segment overlap measure: Support vector machine approach
复制标题
DOI：
10.1006/jmbi.2001.4580
复制
发表时间：
2001-04-27
影响因子：
5.6
通讯作者：
Sun, ZR
中科院分区：
文献类型：
--
作者：
Hua, SJ;Sun, ZR
介绍了一种基于支持向量机理论的蛋白质二级结构预测新方法。支持向量机是一种新的有监督模式分类方法，已成功应用于多种模式识别问题，包括目标识别、说话人识别、基于微阵列表达谱的基因功能预测等。在这些情况下，支持向量机的性能与包括神经网络在内的传统机器学习方法相匹配或显著优于。与以往的研究不同的是，我们首先构造了几个二进制分类器，然后在这些二进制分类器的基础上组装了三个二级结构状态(螺旋、片状和卷曲)的三级分类器。该方法在513条非同源多序列蛋白质链数据库上进行了7次交叉验证，获得了较好的片段重叠准确率SOV=76.2%，优于已有的方法。同时，三态总体预测精度Q(3)达到73.5%，至少可与现有单一预测方法相媲美。此外，支持向量机还具有许多吸引人的特点，包括有效避免过拟合、处理大的特征空间、对给定数据集的信息浓缩等。支持向量机方法可以方便地应用于生物学中的许多以太模式分类任务。(C)2001年学术出版社。
We have introduced a new method of protein secondary structure prediction which is based on the theory of support vector machine (SVM). SVM represents a new approach to supervised pattern classification which has been successfully applied to a wide range of pattern recognition problems, including object recognition, speaker identification, gene function prediction with microarray expression profile, etc. Ln these cases, the performance of SVM either matches or is significantly better than that of traditional machine learning approaches, including neural networks.The first use of the SVM approach to predict protein secondary structure is described here. Unlike the previous studies, we first constructed several binary classifiers, then assembled a tertiary classifier for three secondary structure states (helix, sheet and coil) based on these binary classifiers. The SVM method achieved a good performance of segment overlap accuracy SOV = 76.2 % through sevenfold cross validation on a database of 513 non-homologous protein chains with multiple sequence alignments, which out-performs existing methods. Meanwhile three-state overall per-residue accuracy Q(3) achieved 73.5%, which is at least comparable to existing single prediction methods. Furthermore a useful "reliability index" for the predictions was developed, hn addition, SVM has many attractive features, including effective avoidance of overfitting, the ability to handle large feature spaces, information condensing of the given data set, etc. The SVM method is conveniently applied to many ether pattern classification tasks in biology. (C) 2001 Academic Press.