蛋白质的神经电位可外推至训练数据之外。
Neural potentials of proteins extrapolate beyond training data.
机构信息
Department of Chemistry, University of Rochester, Rochester, New York 14627, USA.
Department of Chemistry, Simons Center for Computational Physical Chemistry, New York University, New York, New York 10003, USA.
出版信息
J Chem Phys. 2023 Aug 28;159(8). doi: 10.1063/5.0147240.
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.
我们评估了神经网络（NN）粗粒（CG）力场与传统 CG 分子力学力场。我们得出结论，当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见区域外推和采样。我们的结果来自于 88 个基于四种映射轨迹的蛋白质簇状自由能表面的不同组合训练的神经网络力场。我们使用了一种名为总变分相似度的统计度量来评估映射原子模拟的参考自由能表面与从训练的神经网络力场的 CG 模拟之间的一致性。我们的结论支持了这样一种假设，即从蛋白质自由能表面的一个区域采样训练的 NN CG 力场确实可以外推到未见区域。此外，发现力匹配误差与力场重建正确自由能表面的能力仅呈弱相关。
Zotero 插件