由于它们在元素之间代表复杂互动的能力,变压器已成为许多应用中的选择方法。然而,将变压器架构扩展到非顺序数据,例如分子,并使其对小型数据集的训练仍然是一个挑战。在这项工作中,我们引入了一种用于分子性能预测的基于变压器的架构,其能够捕获分子的几何形状。我们通过分子几何形状的初始编码来修改经典位置编码器,以及学习的门控自我关注机制。我们进一步提出了一种增强方案,用于避免通过过次分辨率的架构引起的过度拟合的分子数据。所提出的框架优于最先进的方法,同时仅基于纯机器学习,即,即该方法不包含量子化学的域知识,并且在成对原子距离旁边没有使用延伸的几何输入。
translated by 谷歌翻译
Recently, graph neural networks (GNNs) have achieved remarkable performances for quantum mechanical problems. However, a graph convolution can only cover a localized region, and cannot capture long-range interactions of atoms. This behavior is contrary to theoretical interatomic potentials, which is a fundamental limitation of the spatial based GNNs. In this work, we propose a novel attention-based framework for molecular property prediction tasks. We represent a molecular conformation as a discrete atomic sequence combined by atom-atom distance attributes, named Geometry-aware Transformer (GeoT). In particular, we adopt a Transformer architecture, which has been widely used for sequential data. Our proposed model trains sequential representations of molecular graphs based on globally constructed attentions, maintaining all spatial arrangements of atom pairs. Our method does not suffer from cost intensive computations, such as angle calculations. The experimental results on several public benchmarks and visualization maps verified that keeping the long-range interatomic attributes can significantly improve the model predictability.
translated by 谷歌翻译
Graph neural networks have recently achieved great successes in predicting quantum mechanical properties of molecules. These models represent a molecule as a graph using only the distance between atoms (nodes). They do not, however, consider the spatial direction from one atom to another, despite directional information playing a central role in empirical potentials for molecules, e.g. in angular potentials. To alleviate this limitation we propose directional message passing, in which we embed the messages passed between atoms instead of the atoms themselves. Each message is associated with a direction in coordinate space. These directional message embeddings are rotationally equivariant since the associated directions rotate with the molecule. We propose a message passing scheme analogous to belief propagation, which uses the directional information by transforming messages based on the angle between them. Additionally, we use spherical Bessel functions and spherical harmonics to construct theoretically well-founded, orthogonal representations that achieve better performance than the currently prevalent Gaussian radial basis representations while using fewer than 1 /4 of the parameters. We leverage these innovations to construct the directional message passing neural network (DimeNet). DimeNet outperforms previous GNNs on average by 76 % on MD17 and by 31 % on QM9. Our implementation is available online. 1
translated by 谷歌翻译
变压器架构已成为许多域中的主导选择,例如自然语言处理和计算机视觉。然而,与主流GNN变体相比,它对图形水平预测的流行排行榜没有竞争表现。因此,它仍然是一个谜,变形金机如何对图形表示学习表现良好。在本文中,我们通过提出了基于标准变压器架构构建的Gragemer来解决这一神秘性,并且可以在广泛的图形表示学习任务中获得优异的结果,特别是在最近的OGB大规模挑战上。我们在图中利用变压器的关键洞察是有效地将图形的结构信息有效地编码到模型中。为此,我们提出了几种简单但有效的结构编码方法,以帮助Gramemormer更好的模型图形结构数据。此外,我们在数学上表征了Gramemormer的表现力,并展示了我们编码图形结构信息的方式,许多流行的GNN变体都可以被涵盖为GrameRormer的特殊情况。
translated by 谷歌翻译
通过定向消息传递通过方向消息通过的图形神经网络最近在多个分子特性预测任务上设置了最先进的技术。然而,它们依赖于通常不可用的原子位置信息,并获得它通常非常昂贵甚至不可能。在本文中,我们提出了合成坐标,使得能够使用高级GNN而不需要真正的分子配置。我们提出了两个距离作为合成坐标:使用个性化PageRank的对称变体指定分子配置的粗糙范围和基于图的距离的距离界限。为了利用距离和角度信息,我们提出了一种将正常图形神经网络转换为定向MPNN的方法。我们表明,通过这种转变,我们可以将正常图形神经网络的误差减少55%在锌基准。我们还通过在SMP和DimeNet ++模型中纳入合成坐标,在锌和自由QM9上设定了最新技术。我们的实现可在线获取。
translated by 谷歌翻译
3D空间中的空间结构对于确定分子特性是重要的。最近的论文使用几何深度学习来代表分子和预测性质。然而,这些论文在捕获输入原子的远程依赖性时在计算上昂贵;并且尚未考虑外部距离的不均匀性,因此未能学习不同尺度的上下文依赖表示。为了处理这些问题,我们引入了3D变压器,变压器的变型,用于结合3D空间信息的分子表示。 3D变压器在完全连接的图形上运行,在原子之间的直接连接。为了应对外部距离的不均匀性,我们开发了一种多尺度的自我关注模块,利用局部细粒度模式随着越来越多的上下文尺度来利用局部细粒度模式。由于不同尺寸的分子依赖于不同种类的空间特征,我们设计了一种自适应位置编码模块,用于针对小型和大分子采用不同的位置编码方法。最后,为了获得原子嵌入的分子表示,我们提出了一种殷勤最远的点采样算法,该算法在注意分数的帮助下选择一部分原子,克服虚拟节点的障碍和先前的距离 - 优势下采样方法。我们通过三个重要的科学域验证3D变压器:量子化学,物质科学和蛋白质组学。我们的实验表现出对晶体性能预测任务和蛋白质 - 配体结合亲和预测任务的最先进模型的显着改善,并且在量子化学分子数据集中显示了更好或更有竞争的性能。这项工作提供了明确的证据表明,生物化学任务可以从3D分子表示中获得一致的益处,不同的任务需要不同的位置编码方法。
translated by 谷歌翻译
Supervised learning on molecules has incredible potential to be useful in chemistry, drug discovery, and materials science. Luckily, several promising and closely related neural network models invariant to molecular symmetries have already been described in the literature. These models learn a message passing algorithm and aggregation procedure to compute a function of their entire input graph. At this point, the next step is to find a particularly effective variant of this general approach and apply it to chemical prediction benchmarks until we either solve them or reach the limits of the approach. In this paper, we reformulate existing models into a single common framework we call Message Passing Neural Networks (MPNNs) and explore additional novel variations within this framework. Using MPNNs we demonstrate state of the art results on an important molecular property prediction benchmark; these results are strong enough that we believe future work should focus on datasets with larger molecules or more accurate ground truth labels.Recently, large scale quantum chemistry calculation and molecular dynamics simulations coupled with advances in high throughput experiments have begun to generate data at an unprecedented rate. Most classical techniques do not make effective use of the larger amounts of data that are now available. The time is ripe to apply more powerful and flexible machine learning methods to these problems, assuming we can find models with suitable inductive biases. The symmetries of atomic systems suggest neural networks that operate on graph structured data and are invariant to graph isomorphism might also be appropriate for molecules. Sufficiently successful models could someday help automate challenging chemical search problems in drug discovery or materials science.In this paper, our goal is to demonstrate effective machine learning models for chemical prediction problems
translated by 谷歌翻译
This technical report presents GPS++, the first-place solution to the Open Graph Benchmark Large-Scale Challenge (OGB-LSC 2022) for the PCQM4Mv2 molecular property prediction task. Our approach implements several key principles from the prior literature. At its core our GPS++ method is a hybrid MPNN/Transformer model that incorporates 3D atom positions and an auxiliary denoising task. The effectiveness of GPS++ is demonstrated by achieving 0.0719 mean absolute error on the independent test-challenge PCQM4Mv2 split. Thanks to Graphcore IPU acceleration, GPS++ scales to deep architectures (16 layers), training at 3 minutes per epoch, and large ensemble (112 models), completing the final predictions in 1 hour 32 minutes, well under the 4 hour inference budget allocated. Our implementation is publicly available at: https://github.com/graphcore/ogb-lsc-pcqm4mv2.
translated by 谷歌翻译
Models based on machine learning can enable accurate and fast molecular property predictions, which is of interest in drug discovery and material design. Various supervised machine learning models have demonstrated promising performance, but the vast chemical space and the limited availability of property labels make supervised learning challenging. Recently, unsupervised transformer-based language models pretrained on a large unlabelled corpus have produced state-of-the-art results in many downstream natural language processing tasks. Inspired by this development, we present molecular embeddings obtained by training an efficient transformer encoder model, MoLFormer, which uses rotary positional embeddings. This model employs a linear attention mechanism, coupled with highly distributed training, on SMILES sequences of 1.1 billion unlabelled molecules from the PubChem and ZINC datasets. We show that the learned molecular representation outperforms existing baselines, including supervised and self-supervised graph neural networks and language models, on several downstream tasks from ten benchmark datasets. They perform competitively on two others. Further analyses, specifically through the lens of attention, demonstrate that MoLFormer trained on chemical SMILES indeed learns the spatial relationships between atoms within a molecule. These results provide encouraging evidence that large-scale molecular language models can capture sufficient chemical and structural information to predict various distinct molecular properties, including quantum-chemical properties.
translated by 谷歌翻译
分子财产预测是药物和材料行业的基本任务。从物理上讲,分子的特性取决于其自身的电子结构,可以通过schr \“ odinger方程来精确描述。但是,由于大多数分子的求解schr \“ odinger”方程非常具有挑战性量子多体系统的行为。虽然已证明深度学习方法在分子性质预测中有效,但我们设计了一种新颖的方法,即GEM-2,它全面考虑了分子中的远距离和多体相互作用。 GEM-2由两个相互作用的轨道组成:一个原子级轨道模拟任意两个原子之间的局部和全局相关性,以及一个对所有原子对之间的相关性建模的成对轨道,它们嵌入任何3或4个原子之间的信息。广泛的实验证明了GEM-2在量子化学和药物发现任务中的多种基线方法的优越性。
translated by 谷歌翻译
自我监督学习(SSL)是一种通过利用数据中固有的监督来学习数据表示的方法。这种学习方法是药物领域的焦点,由于耗时且昂贵的实验,缺乏带注释的数据。使用巨大未标记数据的SSL显示出在分子属性预测方面表现出色的性能,但存在一些问题。 (1)现有的SSL模型是大规模的;在计算资源不足的情况下实现SSL有限制。 (2)在大多数情况下,它们不利用3D结构信息进行分子表示学习。药物的活性与药物分子的结构密切相关。但是,大多数当前模型不使用3D信息或部分使用它。 (3)以前对分子进行对比学习的模型使用置换原子和键的增强。因此,具有不同特征的分子可以在相同的阳性样品中。我们提出了一个新颖的对比学习框架,用于分子属性预测的小规模3D图对比度学习(3DGCL),以解决上述问题。 3DGCL通过不改变药物语义的预训练过程来反映分子的结构来学习分子表示。仅使用1,128个样本用于预训练数据和100万个模型参数,我们在四个回归基准数据集中实现了最先进或可比性的性能。广泛的实验表明,基于化学知识的3D结构信息对于用于财产预测的分子表示学习至关重要。
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
基于合并和处理对称信息的神经网络架构的几何深度学习(GDL)已经成为人工智能最近的范式。GDL在分子建模应用中具有特定的承诺,其中存在具有不同对称性和抽象水平的各种分子表示。本综述提供了分子GDL的结构化和协调概述,突出了其在药物发现,化学合成预测和量子化学中的应用。重点是学习的分子特征的相关性及其对成熟的分子描述符的互补性。本综述概述了当前的挑战和机会,并提出了用于分子科学GDL的未来的预测。
translated by 谷歌翻译
偶极矩是一个物理量,指示分子的极性,并通过反映成分原子的电性能和分子的几何特性来确定。大多数用于表示传统图神经网络方法中图表表示的嵌入方式将分子视为拓扑图,从而为识别几何信息的目标造成了重大障碍。与现有的嵌入涉及均值的嵌入不同,该嵌入适当地处理分子的3D结构不同,我们的拟议嵌入直接表达了偶极矩局部贡献的物理意义。我们表明,即使对于具有扩展几何形状的分子并捕获更多的原子相互作用信息,开发的模型甚至可以合理地工作,从而显着改善了预测结果,准确性与AB-Initio计算相当。
translated by 谷歌翻译
The Transformer architecture has become a dominant choice in many domains, such as natural language processing and computer vision. Yet, it has not achieved competitive performance on popular leaderboards of graph-level prediction compared to mainstream GNN variants. Therefore, it remains a mystery how Transformers could perform well for graph representation learning. In this paper, we solve this mystery by presenting Graphormer, which is built upon the standard Transformer architecture, and could attain excellent results on a broad range of graph representation learning tasks, especially on the recent OGB Large-Scale Challenge. Our key insight to utilizing Transformer in the graph is the necessity of effectively encoding the structural information of a graph into the model. To this end, we propose several simple yet effective structural encoding methods to help Graphormer better model graph-structured data. Besides, we mathematically characterize the expressive power of Graphormer and exhibit that with our ways of encoding the structural information of graphs, many popular GNN variants could be covered as the special cases of Graphormer. The code and models of Graphormer will be made publicly available at https://github.com/Microsoft/Graphormer.
translated by 谷歌翻译
分子特性预测是与关键现实影响的深度学习的增长最快的应用之一。包括3D分子结构作为学习模型的输入可以提高它们对许多分子任务的性能。但是,此信息是不可行的,可以以几个现实世界应用程序所需的规模计算。我们建议预先训练模型,以推理仅给予其仅为2D分子图的分子的几何形状。使用来自自我监督学习的方法,我们最大化3D汇总向量和图形神经网络(GNN)的表示之间的相互信息,使得它们包含潜在的3D信息。在具有未知几何形状的分子上进行微调期间,GNN仍然产生隐式3D信息,并可以使用它来改善下游任务。我们表明3D预训练为广泛的性质提供了显着的改进,例如八个量子力学性能的22%的平均MAE。此外,可以在不同分子空间中的数据集之间有效地传送所学习的表示。
translated by 谷歌翻译
Models that accurately predict properties based on chemical structure are valuable tools in drug discovery. However, for many properties, public and private training sets are typically small, and it is difficult for the models to generalize well outside of the training data. Recently, large language models have addressed this problem by using self-supervised pretraining on large unlabeled datasets, followed by fine-tuning on smaller, labeled datasets. In this paper, we report MolE, a molecular foundation model that adapts the DeBERTa architecture to be used on molecular graphs together with a two-step pretraining strategy. The first step of pretraining is a self-supervised approach focused on learning chemical structures, and the second step is a massive multi-task approach to learn biological information. We show that fine-tuning pretrained MolE achieves state-of-the-art results on 9 of the 22 ADMET tasks included in the Therapeutic Data Commons.
translated by 谷歌翻译
3D相关的电感偏见,例如翻译不变性和旋转率偏差,对于在3D原子图(例如分子)上运行的图形神经网络是必不可少的。受到变压器在各个领域的成功的启发,我们研究了如何将这些电感偏置纳入变压器。在本文中,我们提出了Equibrouner,这是一个图形神经网络,利用了变压器体系结构的强度,并结合了基于不可减至表示(IRREPS)的$ SE(3)/e(3)$ - 均值功能。 IRREPS在通道尺寸中的编码均值信息而不使图形结构复杂化。简单性使我们能够通过用eproimiant对应物替换原始操作来直接合并它们。此外,为了更好地适应3D图,我们提出了一种新颖的模棱两可的图形注意力,该图都考虑了内容和几何信息,例如IRRERPS特征中包含的相对位置。为了提高注意力的表现力,我们用多层感知器的注意力取代了点产品的注意力,并包括非线性消息传递。我们在两个量子性能预测数据集(QM9和OC20)上进行基准测试。对于QM9,在接受相同数据分区训练的模型中,Equibourer在12个回归任务中的11个中取得了最佳结果。对于OC20,在使用IS2RE数据和IS2RS数据的培训设置下,Equibourer对最先进的模型进行了改进。复制所有主要结果的代码将很快获得。
translated by 谷歌翻译
分子的产生,尤其是从头开始产生3D分子几何形状(即3D \ textit {de Novo} Generation)已成为药物设计中的一项基本任务。现有的基于扩散的3D分子生成方法可能会遭受性能不令人满意的性能,尤其是在产生大分子时。同时,产生的分子缺乏足够的多样性。本文提出了一个新的扩散模型,以应对这两个挑战。首先,原子关系不在分子的3D点云表示中。因此,现有生成模型很难捕获潜在的原子间力和丰富的局部约束。为了应对这一挑战,我们建议增强潜在的原子间力,并进一步涉及双重模棱两可的编码器,以编码不同强度的原子质力。其次,现有的基于扩散的模型基本上是沿数据密度梯度的几何元素。这样的过程在Langevin动力学的中间步骤中缺乏足够的探索。为了解决这个问题,我们在每个扩散/反向步骤中引入了一个分布控制变量,以实施彻底的探索并进一步改善发电多样性。对多个基准测试的广泛实验表明,所提出的模型明显优于无条件和条件生成任务的现有方法。我们还进行案例研究以帮助了解产生分子的理化特性。
translated by 谷歌翻译
建模分子势能表面在科学中至关重要。图神经网络在该领域表现出了巨大的成功,尤其是那些使用旋转等级表示的人。但是,他们要么患有复杂的数学形式,要么缺乏理论支持和设计原则。为了避免使用模棱两可的表示,我们引入了一种新型的本地框架方法来分子表示学习并分析其表现力。借助框架上的框架和模棱两可的向量的投影,GNN可以将原子的局部环境映射到标量表示。也可以在框架上投影在本地环境中传递消息。我们进一步分析了何时以及如何构建此类本地框架。我们证明,当局部环境没有对称性时,局部框架总是存在的,就像分子动力学模拟中一样。对于对称分子,尽管只能构建退化框架,但我们发现,由于自由度降低,在某些常见情况下,局部框架方法仍可能达到高表达能力。仅使用标量表示,我们可以采用现有的简单和强大的GNN体系结构。我们的模型在实验中的表现优于一系列最先进的基线。更简单的体系结构也可以提高更高的可扩展性。与最快的基线相比,我们的模型仅需30%的推理时间。
translated by 谷歌翻译