School of Pharmaceutical Sciences, University of Geneva, Rue Michel Servet 1, 1206 Genève, Switzerland.
Institute of Pharmaceutical Sciences of Western Switzerland (ISPSO), University of Geneva, 1206 Genève, Switzerland.
J Chem Phys. 2024 May 7;160(17). doi: 10.1063/5.0202156.
Several enhanced sampling techniques rely on the definition of collective variables to effectively explore free energy landscapes. The existing variables that describe the progression along a reactive pathway offer an elegant solution but face a number of limitations. In this paper, we address these challenges by introducing a new path-like collective variable called the "deep-locally non-linear-embedding," which is inspired by principles of the locally linear embedding technique and is trained on a reactive trajectory. The variable mimics the ideal reaction coordinate by automatically generating a non-linear combination of features through a differentiable generalized autoencoder that combines a neural network with a continuous k-nearest neighbor selection. Among the key advantages of this method is its capability to automatically choose the metric for searching neighbors and to learn the path from state A to state B without the need to handpick landmarks a priori. We demonstrate the effectiveness of DeepLNE by showing that the progression along the path variable closely approximates the ideal reaction coordinate in toy models, such as the Müller-Brown potential and alanine dipeptide. Then, we use it in the molecular dynamics simulations of an RNA tetraloop, where we highlight its capability to accelerate transitions and estimate the free energy of folding.
几种增强采样技术依赖于对集体变量的定义来有效地探索自由能景观。现有的描述反应途径进展的变量提供了一种优雅的解决方案，但面临着许多限制。在本文中，我们通过引入一种新的路径样集体变量来解决这些挑战，称为“深度局部非线性嵌入”，该变量受到局部线性嵌入技术原理的启发，并在反应轨迹上进行训练。该变量通过通过可微分广义自动编码器自动生成特征的非线性组合来模拟理想的反应坐标，该自动编码器将神经网络与连续的 k-最近邻选择相结合。该方法的一个关键优势是，它能够自动选择搜索邻居的度量标准，并学习从状态 A 到状态 B 的路径，而无需事先挑选地标。我们通过展示在玩具模型（如 Müller-Brown 势能和丙氨酸二肽）中，沿着路径变量的进展如何接近理想的反应坐标，证明了 DeepLNE 的有效性。然后，我们在 RNA 四环的分子动力学模拟中使用它，突出其加速转变和估计折叠自由能的能力。
