距离和疏水模型辅助的蛋白质结构预测方法

Distance and Hydrophobic Model-assisted Protein Structure Prediction Method

预测蛋白质结构对药物设计和疾病诊断有着重要的科学意义.针对蛋白质结构从头预测问题,在进化算法框架下,提出一种距离和疏水模型辅助的蛋白质结构预测方法(Distance and Hydrophobic Model-assisted Protein Structure Prediction Method,DHM A).首先根据亲疏水性构建氨基酸的回转半径来指导构象空间采样,达到提高搜索效率的目的;然后,利用距离谱构建距离分布估计模型和疏水概率模型,指导种群更新,缓解能量函数不精确带来的误差.在10个测试蛋白的预测结果表明,DHM A具有良好的搜索性能和预测精度,是一种有效的蛋白质结构预测方法.

Protein structure prediction products an important scientific significance for drug design and disease diagnosis.For de novo protein structure,a distance and hydrophobic model-assisted protein structure prediction method(DHMA)is proposed within the framework of evolutionary algorithm in this study.The hydrophobic-polar feature of amino acids is firstly used to construct the radius of gyration for guiding the sampling of conformation,thus improving the search efficiency.Then,the distance distribution model and the hydrophobic probability model are constructed by distance profile to guide the population selection,and remitting the error caused by the inaccuracy of the energy function.The results of 10 test proteins show that DHMA equips good search performance and high-accuracy of prediction,and it is an effective protein structure prediction method.