PREDICTING THE SECONDARY STRUCTURE OF GLOBULAR-PROTEINS USING NEURAL NETWORK MODELS
PREDICTING THE SECONDARY STRUCTURE OF GLOBULAR-PROTEINS USING NEURAL NETWORK MODELS
复制标题
DOI：
10.1016/0022-2836(88)90564-5
复制
发表时间：
1988-08-20
影响因子：
5.6
通讯作者：
SEJNOWSKI, TJ
中科院分区：
文献类型：
--
作者：
Qian, N;SEJNOWSKI, TJ
提出了一种基于非线性神经网络模型预测球状蛋白二级结构的新方法。网络模型从现有的蛋白质结构中学习如何预测局部氨基酸序列的二级结构。我们的方法在与相应的训练集非同源的蛋白质测试集上的平均成功率为64.3%。螺旋,度量。c . α =0.41, c . β =0.31, c . coil=0.41。这些质量指标均高于以往的方法。对n端序列前25个残基的预测精度明显较好。我们从真实和人工结构的计算实验中得出结论，对于非同源蛋白质，没有一种方法仅仅基于蛋白质序列中的局部信息可能产生明显更好的结果。我们的方法对同源蛋白的性能比对非同源蛋白的性能要好得多，但不如简单地假设同源序列具有相同的结构。
We present a new method for predicting the secondary structure of globular proteins based on non-linear neural network models. Network models learn from existing protein structures how to predict the secondary structure of local sequences of amino acids. The average success rate of our method on a testing set of proteins non-homologous with the corresponding training set was 64.3% on three types of secondary structure (.alpha.-helix, .beta.-sheet, and coil), with correlation coefficients of C.alpha.=0.41, C.beta.=0.31 and Ccoil=0.41. These quality indices are all higher than those of previous methods. The prediction accuracy for the first 25 residues of the N-terminal sequence was significantly better. We conclude from computational experiments on reals and artifical structures that no method based soley on local information in the protein sequence is likely to produce significantly better results for non-homologous proteins. The performance of our method of homologous proteins is much better than for non-homologous proteins, but is not as good as simply assuming that homologous sequences have identical structures.