基于序列疏水值震荡的折叠速率预测

蛋白质折叠速率的正确预测对理解蛋白质的折叠机理非常重要。本文从伪氨基酸组成的方法出发，提出利用序列疏水值震荡的方法来提取蛋白质氨基酸的序列顺序信息，建立线性回归模型进行折叠速率预测。该方法不需要蛋白质的任何二级结构、三级结构信息或结构类信息，可直接从序列对蛋白质折叠速率进行预测。对含有62个蛋白质的数据集，经过Jack．knife交互检验验证，相关系数达到0．804，表示折叠速率预测值与实验值有很好的相关性，说明了氨基酸序列信息对蛋白质折叠速率影响重要。同其他方法相比，本文的方法具有计算简单，输入参数少等特点。

Prediction of Protein Folding-rate Based on the Hydrophobic Value Vibration

Prediction of protein folding rates is important in understanding the overall folding the mechanism. This article gives a new method, which adopted hydrophobic value vibration to extract the sequence order information, established the linear regression model to predict the protein folding rate. This method can predict protein folding rate from amino acid sequence without any knowledge of the tertiary or secondary structure, or structural class infor- mation. Using Jackknife cross test to check the 62 proteins, the correlation coefficient is 0. 804. It means that the predicted folding rates correlated well with the experimental values and the result implies that the sequence order information plays an important role in protein folding. Compared with other models, this method has advantages feath- ers in simple computation, less parameters and so on.