Dynamics of flexible molecules are often determined by an interplay between local chemical bond fluctuations and conformational changes driven by long-range electrostatics and van der Waals interactions. This interplay between interactions yields complex potential-energy surfaces (PES) with multiple minima and transition paths between them. In this work, we assess the performance of state-of-the-art Machine Learning (ML) models, namely sGDML, SchNet, GAP/SOAP, and BPNN for reproducing such PES, while using limited amounts of reference data. As a benchmark, we use the cis to trans thermal relaxation in an azobenzene molecule, where at least three different transition mechanisms should be considered. Although GAP/SOAP, SchNet, and sGDML models can globally achieve chemical accuracy of 1 kcal mol-1 with fewer than 1000 training points, predictions greatly depend on the ML method used as well as the local region of the PES being sampled. Within a given ML method, large differences can be found between predictions of close-to-equilibrium and transition regions, as well as for different transition mechanisms. We identify key challenges that the ML models face in learning long-range interactions and the intrinsic limitations of commonly used atom-based descriptors. All in all, our results suggest switching from learning the entire PES within a single model to using multiple local models with optimized descriptors, training sets, and architectures for different parts of complex PES.
Neural Network Interaction Potentials for para-Hydrogen with Flexible Molecules
$para$ -氢（$p$ H $\rm_2$）簇中分子杂质的研究是推进我们对分子内和分子间相互作用（包括它们对这种玻色子量子溶剂的超流响应的影响）的理解的关键。这包括用一种或非常少的$p$ H $\rm_2$标记、微溶剂化方案和基质分离。然而，玻色子$p$ H $\rm_2$环境和分子杂质的（ro-）振动运动之间的基本耦合仍然知之甚少。量子模拟可以提供必要的原子论的洞察力，但非常准确的描述所涉及的相互作用是必需的。在这里，我们提出了一个数据驱动的方法，用于生成$impurity\cdots p$ H $\rm_2$相互作用潜力的基础上，机器学习技术，保留了充分的灵活性的杂质。我们采用成熟的绝热受阻转子（AHR）平均技术，包括核自旋统计的影响，$p$ H $\rm_2$的自旋允许的转动量子数。在高维神经网络势（NNP）框架内嵌入该平均过程使得能够以自动化的方式以耦合簇精度生成高精度的AHR平均的NNP，即CCSD（T $^*$）-F12 a/aVTZcp。我们将这种方法应用于水和质子化水分子，分别作为准刚性和高柔性分子的代表性情况，并获得AHR平均的NNPs，可靠地描述H $\rm _2$ O $\cdots p$ H $\rm_2$和H $\rm _3$ O $^+\cdots p$ H $\rm_2$相互作用。使用路径积分模拟，我们表明的水合氢阳离子，伞状隧道反转有强烈的影响，…
RMC_POT (Reverse Monte Carlo using POTentials), a computer code for modeling the structure of disordered systems containing molecules of arbitrary complexity, using flexible molecular constraints and non-bonding potentials
QALPA: Property-guided diffusion modeling for efficient exploration of chemical spaces of flexible molecules
TUD Dresden University of Technology（德累斯顿工业大学）；Pfizer Worldwide R&D（辉瑞全球研发中心）；Center for Advanced Systems Understanding (CASUS)（高级系统理解中心（CASUS））；Helmholtz Zentrum Dresden-Rossendorf（亥姆霍兹德累斯顿罗森多夫研究中心）
Sculpting Molecules in Text-3D Space: A Flexible Substructure Aware Framework for Text-Oriented Molecular Optimization
Institute of Information Engineering, Chinese Academy of Sciences（中国科学院信息工程研究所）；Huawei Technologies（华为技术有限公司）；The University of Hong Kong（香港大学）；Harbin Institute of Technology（哈尔滨工业大学）；Academy of Mathematics and Systems Science, Chinese Academy of Sciences（中国科学院数学与系统科学研究院）
Nutmeg and SPICE: Models and Data for Biomolecular Machine Learning
Stanford University（斯坦福大学）；Molecular Sciences Software Institute（分子科学软件研究所）；Virginia Polytechnic Institute and State University（弗吉尼亚理工学院暨州立大学）；Sloan Kettering Institute（斯隆·凯特琳研究所）；Memorial Sloan Kettering Cancer Center（纪念斯隆·凯特琳癌症中心）
Hubbard models with ultracold shielded molecules in optical lattices
Institute for Molecules and Materials, Radboud University（分子与材料研究所，拉德堡德大学）；Department of Physics and Astronomy, Rice University（物理与天文系，莱斯大学）；Smalley-Curl Institute, Rice University（斯马利-柯尔研究所，莱斯大学）
