蛋白质侧链预测是蛋白质结构预测以及蛋白质设计中非常重要的子问题,而旋转异构体库的构造是进行侧链预测的基础,为预测提供搜索空间.现有的旋转异构体库考虑的是单个氨基酸的统计信息,没有考虑与之相邻的氨基酸对其构象产生的影响.本文提出一种基于隐马尔科夫模型的旋转异构体库构造方法,将相邻氨基酸的构象信息也考虑进来,产生与序列相关的旋转异构体库.并采用蛋白质预测程序Rosetta对CASP8中的12个自由建模蛋白质在本文提出的旋转异构体库基础上进行侧链预测,与基于经典的旋转异构体库的侧链预测结果相比,在预测精度上有了一定的提高.%Side-chain prediction is an important subproblem of protein structure prediction and design. Construction of retainer library is the basis for protein side-chain prediction because it provides searching space for prediction. However, the state-of-the-art rotamer libraries focus on the statistical information of individual amino acids, igonring the affection of its adjacent amino acid. This article presents a sequence depedent rotamer library. The conformation information of adjacent amino acids is also taken into account, producing a sequence depedent library. Test of 12 free modeling targets of CASP8 based on our rotamer library is conducted. Comparing with side-chain prediction based on the state-of-the-art rotamer library, our library helps to improve the prediction accuracy to a certain extent.
展开▼
