Riis S K, Krogh A
Electronics Institute, Technical University of Denmark, Lyngby, Denmark.
J Comput Biol. 1996 Spring;3(1):163-83. doi: 10.1089/cmb.1996.3.163.
The prediction of protein secondary structure by use of carefully structured neural networks and multiple sequence alignments has been investigated. Separate networks are used for predicting the three secondary structures alpha-helix, beta-strand, and coil. The networks are designed using a priori knowledge of amino acid properties with respect to the secondary structure and the characteristic periodicity in alpha-helices. Since these single-structure networks all have less than 600 adjustable weights, overfitting is avoided. To obtain a three-state prediction of alpha-helix, beta-strand, or coil, ensembles of single-structure networks are combined with another neural network. This method gives an overall prediction accuracy of 66.3% when using 7-fold cross-validation on a database of 126 nonhomologous globular proteins. Applying the method to multiple sequence alignments of homologous proteins increases the prediction accuracy significantly to 71.3% with corresponding Matthew's correlation coefficients C alpha = 0.59, C beta = 0.52, and Cc = 0.50. More than 72% of the residues in the database are predicted with an accuracy of 80%. It is shown that the network outputs can be interpreted as estimated probabilities of correct prediction, and, therefore, these numbers indicate which residues are predicted with high confidence.
人们研究了使用精心构建的神经网络和多序列比对来预测蛋白质二级结构的方法。使用单独的网络来预测三种二级结构：α螺旋、β链和无规卷曲。这些网络是利用氨基酸特性与二级结构以及α螺旋中特征周期性的先验知识设计的。由于这些单结构网络的可调权重均少于600个，因此避免了过拟合。为了获得α螺旋、β链或无规卷曲的三态预测，将单结构网络的集合与另一个神经网络相结合。在一个包含126个非同源球状蛋白质的数据库上进行7折交叉验证时，该方法的总体预测准确率为66.3%。将该方法应用于同源蛋白质的多序列比对时，预测准确率显著提高到71.3%，相应的马修斯相关系数Cα = 0.59、Cβ = 0.52和Cc = 0.50。数据库中超过72%的残基预测准确率达到80%。结果表明，网络输出可以解释为正确预测的估计概率，因此，这些数字表明哪些残基的预测具有较高的可信度。
