In atomistic simulations of solids, ability to classify crystal phases and lattice defects in the presence of thermal fluctuations is essential for gaining deeper insights into the simulated dynamics. The need for accurate and efficient characterization methods is especially acute in presently emerging large-scale simulations of multi-phase systems far from equilibrium. Taking the perspective that delineating order and disorder features from ubiquitous thermal vibrations is akin to extracting signal from noise, we consider classification of ordered phases and identification of disordered crystal defects to be fundamentally the same problem and address them both with a unified approach: a denoising score function that removes thermal noise and recovers any underlying crystalline order-disorder. Built on a rotationally equivariant graph neural network (NequIP), the denoiser was trained entirely with synthetically noised structures and requires no simulation data during training. To demonstrate its denoising capabilities, the denoiser is shown to effectively remove thermal vibrations of BCC, FCC, and HCP crystal structures without impacting the underlying disordered defects, including point defects, dislocations, grain boundaries, and liquid disorder. In particular the denoiser was applied to two relatively complex MD simulations that present practical challenges: a Cu solidification trajectory involving a polymorphic nucleus, and a trajectory of BCC Ta undergoing plastic deformation resulting in dislocation networks and point defect clusters. In both cases the denoiser facilitates or trivializes the subsequent characterization of the order-disorder features. Lastly, we outline future work to extend our denoising model to more complex crystal structures and to multi-element systems.
translated by 谷歌翻译
这项工作介绍了神经性等因素的外部潜力(NEQUIP),E(3) - 用于学习分子动力学模拟的AB-INITIO计算的用于学习网状体电位的e(3)的神经网络方法。虽然大多数当代对称的模型使用不变的卷曲,但仅在标量上采取行动,Nequip采用E(3) - 几何张量的相互作用,举起Quivariant卷曲,导致了更多的信息丰富和忠实的原子环境代表。该方法在挑战和多样化的分子和材料集中实现了最先进的准确性,同时表现出显着的数据效率。 Nequip优先于现有型号,最多三个数量级的培训数据,挑战深度神经网络需要大量培训套装。该方法的高数据效率允许使用高阶量子化学水平的理论作为参考的精确潜力构建,并且在长时间尺度上实现高保真分子动力学模拟。
translated by 谷歌翻译
Data-driven interatomic potentials have emerged as a powerful class of surrogate models for {\it ab initio} potential energy surfaces that are able to reliably predict macroscopic properties with experimental accuracy. In generating accurate and transferable potentials the most time-consuming and arguably most important task is generating the training set, which still requires significant expert user input. To accelerate this process, this work presents \text{\it hyperactive learning} (HAL), a framework for formulating an accelerated sampling algorithm specifically for the task of training database generation. The key idea is to start from a physically motivated sampler (e.g., molecular dynamics) and add a biasing term that drives the system towards high uncertainty and thus to unseen training configurations. Building on this framework, general protocols for building training databases for alloys and polymers leveraging the HAL framework will be presented. For alloys, ACE potentials for AlSi10 are created by fitting to a minimal HAL-generated database containing 88 configurations (32 atoms each) with fast evaluation times of <100 microsecond/atom/cpu-core. These potentials are demonstrated to predict the melting temperature with excellent accuracy. For polymers, a HAL database is built using ACE, able to determine the density of a long polyethylene glycol (PEG) polymer formed of 200 monomer units with experimental accuracy by only fitting to small isolated PEG polymers with sizes ranging from 2 to 32.
translated by 谷歌翻译
原子学模拟现在已经成为理解原子尺度材料变形机制的不可或缺的工具。定期使用大规模模拟来研究纳米级的多晶材料的行为。在这项工作中,我们提出了一种使用无监督机器学习算法的原子配置的晶粒分割方法,该算法基于其取向基于各个颗粒将原子簇簇簇。所提出的方法,称为oriSodata算法,基于迭代自组织数据分析技术,并被修改为在方向空间中工作。在两个未变形和变形状态下,在122粒纳米晶薄膜样品上证明了算法的工作。 ORISODATA算法也与开源可视化工具OVITO中可用的另外两种颗粒分段算法进行比较。结果表明,Orisodata算法能够正确地识别变形双胞胎以及由低角度晶界分开的区域。模型参数具有直观的物理含义,并与实验中使用的类似阈值相关,这不仅有助于获得最佳值,而且还有助于轻松解释和验证结果。
translated by 谷歌翻译
机器学习最近被出现为研究复杂现象的有希望的方法,其特征是丰富的数据集。特别地,以数据为中心的方法为手动检查可能错过的实验数据集中自动发现结构的可能性。在这里,我们介绍可解释的无监督监督的混合机学习方法,混合相关卷积神经网络(Hybrid-CCNN),并将其应用于使用基于Rydberg Atom阵列的可编程量子模拟器产生的实验数据。具体地,我们应用Hybrid-CCNN以通过可编程相互作用分析在方形格子上的新量子阶段。初始无监督的维度降低和聚类阶段首先揭示了五个不同的量子相位区域。在第二个监督阶段,我们通过培训完全解释的CCNN来细化这些相界并通过训练每个阶段提取相关的相关性。在条纹相中的每个相捕获量子波动中专门识别的特征空间加权和相关的相关性并鉴定两个先前未检测到的相,菱形和边界有序相位。这些观察结果表明,具有机器学习的可编程量子模拟器的组合可用作有关相关量子态的详细探索的强大工具。
translated by 谷歌翻译
A generalized understanding of protein dynamics is an unsolved scientific problem, the solution of which is critical to the interpretation of the structure-function relationships that govern essential biological processes. Here, we approach this problem by constructing coarse-grained molecular potentials based on artificial neural networks and grounded in statistical mechanics. For training, we build a unique dataset of unbiased all-atom molecular dynamics simulations of approximately 9 ms for twelve different proteins with multiple secondary structure arrangements. The coarse-grained models are capable of accelerating the dynamics by more than three orders of magnitude while preserving the thermodynamics of the systems. Coarse-grained simulations identify relevant structural states in the ensemble with comparable energetics to the all-atom systems. Furthermore, we show that a single coarse-grained potential can integrate all twelve proteins and can capture experimental structural features of mutated proteins. These results indicate that machine learning coarse-grained potentials could provide a feasible approach to simulate and understand protein dynamics.
translated by 谷歌翻译
计算催化和机器学习社区在开发用于催化剂发现和设计的机器学习模型方面取得了长足的进步。然而,跨越催化的化学空间的一般机器学习潜力仍然无法触及。一个重大障碍是在广泛的材料中获得访问培训数据的访问。缺乏数据的一类重要材料是氧化物,它抑制模型无法更广泛地研究氧气进化反应和氧化物电催化。为了解决这个问题,我们开发了开放的催化剂2022(OC22)数据集,包括62,521个密度功能理论(DFT)放松(〜9,884,504个单点计算),遍及一系列氧化物材料,覆盖范围,覆盖率和吸附物( *H, *o, *o, *o, *o, *o, * n, *c, *ooh, *oh, *oh2, *o2, *co)。我们定义广义任务,以预测催化过程中适用的总系统能量,发展几个图神经网络的基线性能(Schnet,Dimenet ++,Forcenet,Spinconv,Painn,Painn,Gemnet-DT,Gemnet-DT,Gemnet-OC),并提供预先定义的数据集分割以建立明确的基准,以实现未来的努力。对于所有任务,我们研究组合数据集是否会带来更好的结果,即使它们包含不同的材料或吸附物。具体而言,我们在Open Catalyst 2020(OC20)数据集和OC22上共同训练模型,或OC22上的微调OC20型号。在最一般的任务中,Gemnet-OC看到通过微调来提高了约32%的能量预测,通过联合训练的力预测提高了约9%。令人惊讶的是,OC20和较小的OC22数据集的联合培训也将OC20的总能量预测提高了约19%。数据集和基线模型是开源的,公众排行榜将遵循,以鼓励社区的持续发展,以了解总能源任务和数据。
translated by 谷歌翻译
分子动力学(MD)模拟是各种科学领域的主力,但受到高计算成本的限制。基于学习的力场在加速AB-Initio MD模拟方面取得了重大进展,但对于许多需要长期MD仿真的现实世界应用程序仍然不够快。在本文中,我们采用了一种不同的机器学习方法,使用图形群集将物理系统粗糙化,并使用图形神经网络使用非常大的时间整合步骤对系统演变进行建模。一个新型的基于分数的GNN改进模块解决了长期模拟不稳定性的长期挑战。尽管仅接受了简短的MD轨迹数据训练,但我们学到的模拟器仍可以推广到看不见的新型系统,并比训练轨迹更长的时间。需要10-100 ns级的长时间动力学的属性可以在多个刻度级的速度上准确恢复,而不是经典的力场。我们证明了方法对两个现实的复杂系统的有效性:(1)隐式溶剂中的单链粗粒聚合物; (2)多组分锂离子聚合物电解质系统。
translated by 谷歌翻译
电子密度$ \ rho(\ vec {r})$是用密度泛函理论(dft)计算地面能量的基本变量。除了总能量之外,$ \ rho(\ vec {r})$分布和$ \ rho(\ vec {r})$的功能通常用于捕获电子规模以功能材料和分子中的关键物理化学现象。方法提供对$ \ rho(\ vec {r})的可紊乱系统,其具有少量计算成本的复杂无序系统可以是对材料相位空间的加快探索朝向具有更好功能的新材料的逆设计的游戏更换者。我们为预测$ \ rho(\ vec {r})$。该模型基于成本图形神经网络,并且在作为消息传递图的一部分的特殊查询点顶点上预测了电子密度,但仅接收消息。该模型在多个数据组中进行测试,分子(QM9),液体乙烯碳酸酯电解质(EC)和Lixniymnzco(1-Y-Z)O 2锂离子电池阴极(NMC)。对于QM9分子,所提出的模型的准确性超过了从DFT获得的$ \ Rho(\ vec {r})$中的典型变异性,以不同的交换相关功能,并显示超出最先进的准确性。混合氧化物(NMC)和电解质(EC)数据集更好的精度甚至更好。线性缩放模型同时探测成千上万点的能力允许计算$ \ Rho(\ vec {r})$的大型复杂系统,比DFT快于允许筛选无序的功能材料。
translated by 谷歌翻译
SchNetPack is a versatile neural networks toolbox that addresses both the requirements of method development and application of atomistic machine learning. Version 2.0 comes with an improved data pipeline, modules for equivariant neural networks as well as a PyTorch implementation of molecular dynamics. An optional integration with PyTorch Lightning and the Hydra configuration framework powers a flexible command-line interface. This makes SchNetPack 2.0 easily extendable with custom code and ready for complex training task such as generation of 3d molecular structures.
translated by 谷歌翻译
Machine-learning models are increasingly used to predict properties of atoms in chemical systems. There have been major advances in developing descriptors and regression frameworks for this task, typically starting from (relatively) small sets of quantum-mechanical reference data. Larger datasets of this kind are becoming available, but remain expensive to generate. Here we demonstrate the use of a large dataset that we have "synthetically" labelled with per-atom energies from an existing ML potential model. The cheapness of this process, compared to the quantum-mechanical ground truth, allows us to generate millions of datapoints, in turn enabling rapid experimentation with atomistic ML models from the small- to the large-data regime. This approach allows us here to compare regression frameworks in depth, and to explore visualisation based on learned representations. We also show that learning synthetic data labels can be a useful pre-training task for subsequent fine-tuning on small datasets. In the future, we expect that our open-sourced dataset, and similar ones, will be useful in rapidly exploring deep-learning models in the limit of abundant chemical data.
translated by 谷歌翻译
Molecular dynamics (MD) has long been the de facto choice for simulating complex atomistic systems from first principles. Recently deep learning models become a popular way to accelerate MD. Notwithstanding, existing models depend on intermediate variables such as the potential energy or force fields to update atomic positions, which requires additional computations to perform back-propagation. To waive this requirement, we propose a novel model called DiffMD by directly estimating the gradient of the log density of molecular conformations. DiffMD relies on a score-based denoising diffusion generative model that perturbs the molecular structure with a conditional noise depending on atomic accelerations and treats conformations at previous timeframes as the prior distribution for sampling. Another challenge of modeling such a conformation generation process is that a molecule is kinetic instead of static, which no prior works have strictly studied. To solve this challenge, we propose an equivariant geometric Transformer as the score function in the diffusion process to calculate corresponding gradients. It incorporates the directions and velocities of atomic motions via 3D spherical Fourier-Bessel representations. With multiple architectural improvements, we outperform state-of-the-art baselines on MD17 and isomers of C7O2H10 datasets. This work contributes to accelerating material and drug discovery.
translated by 谷歌翻译
在分子动力学(MD)中,最近在量子机械数据上训练的神经网络(NN)潜力训练了巨大的成功。直接从实验数据学习NN电位的自上而下的方法在通过MD模拟背交时,通常面临着数值和计算挑战。我们介绍了可分辨率的轨迹重新重量(差异)方法,该方法通过MD模拟绕过差异,以对时间无关的可观察可观察。利用热力学扰动理论,避免爆炸梯度,并在自上而下学习的梯度计算中实现大约2次数量级加速。我们在基于多样化的实验可观察结果,表明了在学习NN电位学习NN电位的有效性,包括热力学,结构和机械性能的不同实验性观察。重要的是,衍射还概括了自下而上的结构粗晶体方法,例如迭代Boltzmann反转到任意潜力。呈现的方法构成了富有实验数据富集NN电位的重要里程碑,特别是当准确的自下而上数据不可用时。
translated by 谷歌翻译
对称考虑对于用于提供原子配置的有效数学表示的主要框架的核心,然后在机器学习模型中用于预测与每个结构相关的特性。在大多数情况下,模型依赖于以原子为中心的环境的描述,并且适合于学习可以分解成原子贡献的原子特性或全局观察到。然而,许多与量子机械计算相关的数量 - 最值得注意的是,以原子轨道基础写入时的单粒子哈密顿矩阵 - 与单个中心无关,但结构中有两个(或更多个)原子。我们讨论一系列结构描述符,以概括为N中心案例的非常成功的原子居中密度相关特征,特别是如何应用这种结构,以有效地学习(有效)单粒子汉密尔顿人的矩阵元素以原子为中心的轨道基础。这些N中心的特点是完全的,不仅在转换和旋转方面,而且还就与原子相关的指数的排列而言 - 并且适合于构建新类的对称适应的机器学习模型分子和材料的性质。
translated by 谷歌翻译
图神经网络(GNN)是机器学习中非常流行的方法,并且非常成功地应用于分子和材料的性质。众所周知,一阶GNN是不完整的,即存在不同的图形,但在通过GNN的镜头看到时似乎相同。因此,更复杂的方案旨在提高其分辨能力。但是,在分子(以及更一般的点云)上的应用,为问题添加了几何维度。构造分子图表表示原子的最直接和普遍的方法将原子视为图中的顶点,并在所选截止中的每对原子之间绘制一个键。键可以用原子之间的距离进行装饰,所得的“距离图NN”(DGNN)在经验上已证明了出色的分辨能力,并广泛用于化学ML,所有已知的不可区分的图都在完全连接的极限中解析。在这里,我们表明,即使对于由3D原子云引起的完全连接图的受限情况也不完整。我们构造了一对不同的点云对产生图形,对于任何截止半径,基于一阶Weisfeiler-Lehman测试都是等效的。这类退化的结构包括化学上可见的构型,为某些完善的GNN架构的原子学机器学习设定了最终的限制。在原子环境描述中明确使用角度或方向信息的模型可以解决这些变性。
translated by 谷歌翻译
The success of machine learning algorithms generally depends on data representation, and we hypothesize that this is because different representations can entangle and hide more or less the different explanatory factors of variation behind the data. Although specific domain knowledge can be used to help design representations, learning with generic priors can also be used, and the quest for AI is motivating the design of more powerful representation-learning algorithms implementing such priors. This paper reviews recent work in the area of unsupervised feature learning and deep learning, covering advances in probabilistic models, auto-encoders, manifold learning, and deep networks. This motivates longer-term unanswered questions about the appropriate objectives for learning good representations, for computing representations (i.e., inference), and the geometrical connections between representation learning, density estimation and manifold learning.
translated by 谷歌翻译
预测分子系统的结构和能量特性是分子模拟的基本任务之一,并且具有化学,生物学和医学的用例。在过去的十年中,机器学习算法的出现影响了各种任务的分子模拟,包括原子系统的财产预测。在本文中,我们提出了一种新的方法,用于将从简单分子系统获得的知识转移到更复杂的知识中,并具有明显的原子和自由度。特别是,我们专注于高自由能状态的分类。我们的方法依赖于(i)分子的新型超图表,编码所有相关信息来表征构象的势能,以及(ii)新的消息传递和汇总层来处理和对此类超图结构数据进行预测。尽管问题的复杂性,但我们的结果表明,从三丙氨酸转移到DECA-丙氨酸系统的转移学习中,AUC的AUC为0.92。此外,我们表明,相同的转移学习方法可以用无监督的方式分组,在具有相似的自由能值的簇中,deca-丙氨酸的各种二级结构。我们的研究代表了一个概念证明,即可以设计用于分子系统的可靠传输学习模型,为预测生物学相关系统的结构和能量性能的未开发途径铺平道路。
translated by 谷歌翻译
粗粒(CG)分子模拟已成为研究全原子模拟无法访问的时间和长度尺度上分子过程的标准工具。参数化CG力场以匹配全原子模拟,主要依赖于力匹配或相对熵最小化,这些熵最小化分别需要来自具有全原子或CG分辨率的昂贵模拟中的许多样本。在这里,我们提出了流量匹配,这是一种针对CG力场的新训练方法,它通过利用正常流量(一种生成的深度学习方法)来结合两种方法的优势。流量匹配首先训练标准化流程以表示CG概率密度,这等同于最小化相对熵而无需迭代CG模拟。随后,该流量根据学习分布生成样品和力,以通过力匹配来训练所需的CG能量模型。即使不需要全部原子模拟的力,流程匹配就数据效率的数量级优于经典力匹配,并产生CG模型,可以捕获小蛋白质的折叠和展开过渡。
translated by 谷歌翻译
在2015年和2019年之间,地平线的成员2020年资助的创新培训网络名为“Amva4newphysics”,研究了高能量物理问题的先进多变量分析方法和统计学习工具的定制和应用,并开发了完全新的。其中许多方法已成功地用于提高Cern大型Hadron撞机的地图集和CMS实验所执行的数据分析的敏感性;其他几个人,仍然在测试阶段,承诺进一步提高基本物理参数测量的精确度以及新现象的搜索范围。在本文中,在研究和开发的那些中,最相关的新工具以及对其性能的评估。
translated by 谷歌翻译
分子动力学/静态类型的原子模拟定期用于研究小规模的可塑性。现代模拟是用数万到数亿原子进行的,这些构型的快照是定期编写的,以进行进一步分析。材料行为的连续量表本构型模型可以从原子量表上的信息中受益,特别是在变形机制,总应变的适应以及单个晶粒中应力和应变场的分配。在这项工作中,我们使用统计数据挖掘和机器学习算法来开发一种方法,以自动对原子模拟中的连续性场变量进行分析。我们专注于三个重要的场变量:总应变,弹性应变和微功能。我们的结果表明,单个晶粒中的弹性应变表现出单峰对数正态分布,而总应变和微连续性场证明了多峰分布。用高斯混合模型鉴定了总应变分布的峰,并提出了规避过度拟合问题的方法。随后,我们根据晶粒中的变形机制评估了识别的峰,例如,有助于量化单个变形机制负责的应变。所有谷物上分布的总体统计数据是更高规模模型的重要输入,最终也有助于定量讨论信息传输到现象学模型的含义。
translated by 谷歌翻译