用模式识别方法预测蛋白质的二级结构

PATTERN RECOGNITION METHODS FOR PREDICTING THE SECONDARY STRUCTURE OF PROTEINS

本文建立了用模式识别理论和技术在计算机上预测蛋白质二级结构的方法.特征的抽取和样本的选择是使用该方法的关键.这一方法与其他方法相比各有特色,预测精度也比较高,鉴于目前国内外将此方法用于蛋白结构预测的研究的还不多,我们拟进一步发展、完善这一方法.

This paper describes a statistical pattern recognition method for predicting the secondary structure of proteins. The method is powerful but conceptually simple. In this approach, 5 properties of the 20 amino acids are used to map peptide sequences into a multivariate property space. The method can be performed by microcomputers or minicomputer, and the feature extraction and sample selection are considered to be the key points of this method. The experiment results show that the pattern recognition methods for predicting the secondary structure of proteins is a fair good method. But it still needs to be improved.