| 引用本文: | 罗升,吕强.距离约束的HMC采样算法在蛋白质结构预测中的运用[J].生物信息学,2016,14(2):117-122. |
| LUO Sheng,L Qiang.Distance constrains model based hybrid monte carlo sampling algorithm in protein structure prediction[J].Chinese Journal of Bioinformatics,2016,14(2):117-122. |
|
| 摘要: |
| 蛋白质结构预测中,采样是指在构象空间中生成具有最小自由能的状态。传统的采样方法是对自由度直接赋值。这种方法在处理较少的残基时能取得好的效果。但是对于包含100个残基以上的蛋白质结构,由于构象空间的急剧增长,难以得到理想的结构。本文引入深度学习中的HMC(Hybrid Monte Carlo)采样方法,以概率分布为依据对蛋白质的自由度进行采样,能够对包含100、200甚至更多个残基的蛋白质结构进行采样。并且,在采样的过程中加入残基间的距离约束,使得一个结构中,相对于Rosetta的ab initio最多有75%(平均40% )的残基对得到优化,满足距离约束。 |
| 关键词: 距离约束 HMC 采样 结构预测 蛋白质 |
| DOI：10.3969/j.issn.1672-5565.2016.02.09 |
| 分类号:TP391 |
| 文献标识码:A |
| 基金项目:国家自然科学基金项目(No.61170125)。 |
|
| Distance constrains model based hybrid monte carlo sampling algorithm in protein structure prediction |
|
LUO Sheng1,L Qiang2
|
|
(1. School of Computer Science & Technology, Soochow University, Suzhou 215006, China;2. Provincial Key Laboratory for Computer Information Processing Technology of Jiangsu, Suzhou 215006, China)
|
| Abstract: |
| Sampling is defined as searching the conformational space for the status with the minimum free energy in protein structure prediction. In this paper, the Hybrid Monte Carlo(HMC) method from deep learning algorithms is introduced to better sample the conformational space of protein structures with 0,0, or even more residues according to the probability distributions, while traditional sampling methods succeed in cases that proteins usually have less residues by assigning each value of free degrees directly. But they often fail the situation in which proteins have more than 100 residues, because of the large conformational space. In addition, residue distance constrains are added to the sampling algorithm to optimize a maximum 75 percent (40 percent on average) of residue pairs in each structure compare with ab initio in Rosetta. |
| Key words: Distance constrain HMC Sampling Structure prediction Protein |
