TorchMD: A Deep Learning Framework for Molecular Simulations.

TorchMD: A Deep Learning Framework for Molecular Simulations.
复制标题

DOI:
10.1021/acs.jctc.0c01343
复制
发表时间:
2021-04-13
影响因子:
5.5
通讯作者:
De Fabritiis G
De Fabritiis G
中科院分区:
化学1区
文献类型:
--
作者:
Doerr S;Majewski M;Pérez A;Krämer A;Clementi C;Noe F;Giorgino T;De Fabritiis G

文献摘要

参考文献

被引文献

相似文献

分子动力学模拟通过依赖于经验势来提供分子的机械描述。这些潜力的质量和可转移性可以通过利用机器学习方法获得的数据驱动模型来提高。在这里,我们提出了TorchMD,一个混合经典和机器学习潜力的分子模拟框架。所有力的计算,包括键、角、二面角、Lennard-Jones和库仑相互作用,都表示为PyTorch数组和运算。此外,TorchMD可以学习和模拟神经网络潜力。我们使用标准的Amber全原子模拟来验证它,学习从头算势,进行端到端的训练,最后学习和模拟蛋白质折叠的粗粒度模型。我们相信,TorchMD提供了一个有用的工具集,以支持机器学习潜力的分子模拟。代码和数据可在.
Molecular dynamics simulations provide a mechanistic description of molecules by relying on empirical potentials. The quality and transferability of such potentials can be improved leveraging data-driven models derived with machine learning approaches. Here, we present TorchMD, a framework for molecular simulations with mixed classical and machine learning potentials. All force computations including bond, angle, dihedral, Lennard-Jones, and Coulomb interactions are expressed as PyTorch arrays and operations. Moreover, TorchMD enables learning and simulating neural network potentials. We validate it using standard Amber all-atom simulations, learning an ab initio potential, performing an end-to-end training, and finally learning and simulating a coarse-grained model for protein folding. We believe that TorchMD provides a useful tool set to support molecular simulations of machine learning potentials. Code and data are freely available at .
DOI: 10.1021/acscentsci.7b00572
发表时间: 2018-02-28
影响因子: 18.2
作者:
Gómez-Bombarelli R;Wei JN;Duvenaud D;Hernández-Lobato JM;Sánchez-Lengeling B;Sheberla D;Aguilera-Iparraguirre J;Hirzel TD;Adams RP;Aspuru-Guzik A
通讯作者: Aspuru-Guzik A
DOI: 10.1063/1.5126701
发表时间: 2020-01-31
影响因子: 4.4
作者:
Christensen, Anders S.;Bratholm, Lars A.;von Lilienfeld, O. Anatole
通讯作者: von Lilienfeld, O. Anatole
DOI: 10.1063/1.4993207
发表时间: 2017-09-14
影响因子: 4.4
作者:
McKiernan, Keri A.;Husic, Brooke E.;Pande, Vijay S.
通讯作者: Pande, Vijay S.
DOI: 10.1016/j.str.2009.09.001
发表时间: 2009-10-14
期刊: Structure (London, England : 1993)
影响因子: --
作者:
Lee EH;Hsin J;Sotomayor M;Comellas G;Schulten K
通讯作者: Schulten K
DOI: 10.1063/1.445869
发表时间: 1983-01-01
影响因子: 4.4
作者:
JORGENSEN, WL;CHANDRASEKHAR, J;KLEIN, ML
通讯作者: KLEIN, ML