Improved Statistical Sampling and Accuracy with Accelerated Molecular Dynamics on Rotatable Torsions
Improved Statistical Sampling and Accuracy with Accelerated Molecular Dynamics on Rotatable Torsions
复制标题
DOI：
10.1021/ct3004194
复制
发表时间：
2012-11-01
影响因子：
5.5
通讯作者：
Hamelberg, Donald
中科院分区：
文献类型：
--
作者：
Doshi, Urmi;Hamelberg, Donald
在改进的抽样技术中，由于统计权重的较大变化和有效抽样大小的减小，重新加权的系综属性的精度经常降低。为了缓解这种重加权问题，这里我们提出了一种通用加速分子动力学(AMD)方法，其中只有可旋转的二面体受到AMD(RaMD)的影响，而不是典型的实现中所有二面体都被提升(ALL-AMD)。不可旋转和不适当的二面体对于构象变化或不同的旋转体状态是略微重要的。不对它们进行加速，避免了由于偏离最小能量构象而导致势能的急剧增加，从而提高了RAMD的精度。我们给出了两个模型二肽Ace-Ala-NME和Ace-Trp-NME的基准研究，分别用正常MD、ALL-AMD和RaMD模拟。我们利用一种理论对两种形式的AMD的性能进行了系统的比较，该理论允许对有效采样点的数量和相关的不确定度进行定量估计。我们的结果表明，在相同的加速水平和模拟长度下，RaMD与ALL-AMD一样，导致有效样本量的损失显著减少，从而提高了Phi-psi空间的采样精度。根据多肽和加速程度的不同，RaMD产生的精度与ALL-AMD相当，模拟长度从模拟长度的5到1000倍缩短。与全AMD相比，这种在速度和准确度上的改进是非常显著的，这表明RaMD是一种很有前途的大分子生物采样方法。
In enhanced sampling techniques, the precision of the reweighted ensemble properties is often decreased due to large variation in statistical weights and reduction in the effective sampling size. To abate this reweighting problem, here, we propose a general accelerated molecular dynamics (aMD) approach in which only the rotatable dihedrals are subjected to aMD (RaMD), unlike the typical implementation wherein all dihedrals are boosted,(all-aMD). Nonrotatable and improper dihedrals are marginally important to conformational changes or the different rotameric states. Not accelerating them avoids the sharp increases in the potential energies due to small deviations from their minimum energy conformations and leads to improvement in the precision of RaMD. We present benchmark studies on two model dipeptides, Ace-Ala-Nme and Ace-Trp-Nme, simulated with normal MD, all-aMD, and RaMD. We carry out a systematic comparison between the performances of both forms of aMD using a theory that allows quantitative estimation of the effective number of sampled points and the associated uncertainty. Our results indicate that, for the same level of acceleration and simulation length, as used in all-aMD, RaMD results in significantly less loss in the effective sample size and, hence, increased accuracy in the sampling of phi-psi space. RaMD yields an accuracy comparable to that of all-aMD, from simulation lengths 5 to 1000 times shorter, depending on the peptide and the acceleration level. Such improvement in speed and accuracy over all-aMD is highly remarkable, suggesting RaMD as a promising method for sampling larger biomolecules.