预测蛋白质三维结构的拟物算法  

An Quasiphysical Algorithm for 3D Protein Structure Prediction

作　　者：黄文奇[1] 黄勤波[1] 石赫[2] 

机构地区：[1]华中科技大学计算机科学与技术学院,湖北武汉430074 [2]中国科学院数学与系统科学研究院,北京100080

出　　处：《武汉大学学报（理学版）》2004年第5期586-590,共5页Journal of Wuhan University:Natural Science Edition

基　　金：国家973计划资助项目(G1998030600);湖北省咸宁市白云山林场开发基金资助项目

摘　　要：研究了生物信息学中的一个重要问题,即蛋白质结构预测.并受物理世界的物体间相互作用的规律的启发,给出了该问题一个三维欧氏空间连续模型,它比离散模型有一定的优越性,使计算很自然地利用到了一个客观存在的"天然导引",这个"天然导引"即是疏水氨基酸之间的引力,然后根据这个连续模型找到了相应的拟物算法,最后还给出了实验结果,结果也证明了这个拟物算法在计算速度方面的优越性.An important problem in biology informatics is researched in this paper,that is, protein structure prediction. We are enlightened by the law of reciprocity among things in the physics world and give a continuous model in 3D Euclidean space, which gain an advantage over the discretion model in some aspects. The continuous model's strongpoint is that it utilizes the gravitation among hydrophobe amino acid. Then, a related quasiphysical algorithm is formulated according to the 3D continuous model. At last we give some experiment results which also proves the advantage of the quasiphysical algorithm in compute rapidity.

关 键 词：蛋白质 三维结构 拟物算法 结构预测 NP难度问题 折叠 引力势能 生物信息学 

分 类 号：TQ937[化学工程]