Neural potentials of proteins extrapolate beyond training data.
Neural potentials of proteins extrapolate beyond training data.
复制标题
DOI：
10.1063/5.0147240
复制
发表时间：
2023-08
期刊：
影响因子：
--
通讯作者：
Geemi P Wellawatte;Glen M. Hocky;A. White
中科院分区：
文献类型：
--
作者：
Geemi P Wellawatte;Glen M. Hocky;A. White
我们评估了神经网络（NN）粗粒度（CG）力场与传统CG分子力学力场的比较。我们得出结论，当使用有限的数据进行训练时，神经网络力场能够从自由能表面的未知区域进行外推和采样。我们的结果来自88个神经网络力场，这些力场是在来自四个蛋白质映射轨迹的簇状自由能表面的不同组合上训练的。我们使用了一种称为总变异相似性的统计度量来评估来自映射原子模拟的参考自由能面和来自训练过的神经网络力场的CG模拟之间的一致性。我们的结论支持这样一个假设，即用蛋白质自由能表面的一个区域的样本训练的神经网络CG力场确实可以外推到看不见的区域。此外，发现力匹配误差仅与力场重建正确自由能面的能力弱相关。
We evaluate neural network (NN) coarse-grained (CG) force fields compared to traditional CG molecular mechanics force fields. We conclude that NN force fields are able to extrapolate and sample from unseen regions of the free energy surface when trained with limited data. Our results come from 88 NN force fields trained on different combinations of clustered free energy surfaces from four protein mapped trajectories. We used a statistical measure named total variation similarity to assess the agreement between reference free energy surfaces from mapped atomistic simulations and CG simulations from trained NN force fields. Our conclusions support the hypothesis that NN CG force fields trained with samples from one region of the proteins' free energy surface can, indeed, extrapolate to unseen regions. Additionally, the force matching error was found to only be weakly correlated with a force field's ability to reconstruct the correct free energy surface.