Drug development is a wide scientific field that faces many challenges these days. Among them are extremely high development costs, long development times, as well as a low number of new drugs that are approved each year. To solve these problems, new and innovate technologies are needed that make the drug discovery process of small-molecules more time and cost-efficient, and which allow to target previously undruggable target classes such as protein-protein interactions. Structure-based virtual screenings have become a leading contender in this context. In this review, we give an introduction to the foundations of structure-based virtual screenings, and survey their progress in the past few years. We outline key principles, recent success stories, new methods, available software, and promising future research directions. Virtual screenings have an enormous potential for the development of new small-molecule drugs, and are already starting to transform early-stage drug discovery.
translated by 谷歌翻译
Artificial intelligence (AI) in the form of deep learning bears promise for drug discovery and chemical biology, $\textit{e.g.}$, to predict protein structure and molecular bioactivity, plan organic synthesis, and design molecules $\textit{de novo}$. While most of the deep learning efforts in drug discovery have focused on ligand-based approaches, structure-based drug discovery has the potential to tackle unsolved challenges, such as affinity prediction for unexplored protein targets, binding-mechanism elucidation, and the rationalization of related chemical kinetic properties. Advances in deep learning methodologies and the availability of accurate predictions for protein tertiary structure advocate for a $\textit{renaissance}$ in structure-based approaches for drug discovery guided by AI. This review summarizes the most prominent algorithmic concepts in structure-based deep learning for drug discovery, and forecasts opportunities, applications, and challenges ahead.
translated by 谷歌翻译
蛋白质 - 配体相互作用(PLIS)是生化研究的基础,其鉴定对于估计合理治疗设计的生物物理和生化特性至关重要。目前,这些特性的实验表征是最准确的方法,然而,这是非常耗时和劳动密集型的。在这种情况下已经开发了许多计算方法,但大多数现有PLI预测大量取决于2D蛋白质序列数据。在这里,我们提出了一种新颖的并行图形神经网络(GNN),以集成PLI预测的知识表示和推理,以便通过专家知识引导的深度学习,并通过3D结构数据通知。我们开发了两个不同的GNN架构,GNNF是采用不同特种的基础实现,以增强域名认识,而GNNP是一种新颖的实现,可以预测未经分子间相互作用的先验知识。综合评价证明,GNN可以成功地捕获配体和蛋白质3D结构之间的二元相互作用,对于GNNF的测试精度和0.958,用于预测蛋白质 - 配体络合物的活性。这些模型进一步适用于回归任务以预测实验结合亲和力,PIC50对于药物效力和功效至关重要。我们在实验亲和力上达到0.66和0.65的Pearson相关系数,分别在PIC50和GNNP上进行0.50和0.51,优于基于2D序列的模型。我们的方法可以作为可解释和解释的人工智能(AI)工具,用于预测活动,效力和铅候选的生物物理性质。为此,我们通过筛选大型复合库并将我们的预测与实验测量数据进行比较来展示GNNP对SARS-COV-2蛋白靶标的实用性。
translated by 谷歌翻译
在三维分子结构上运行的计算方法有可能解决生物学和化学的重要问题。特别地,深度神经网络的重视,但它们在生物分子结构域中的广泛采用受到缺乏系统性能基准或统一工具包的限制,用于与分子数据相互作用。为了解决这个问题,我们呈现Atom3D,这是一个新颖的和现有的基准数据集的集合,跨越几个密钥的生物分子。我们为这些任务中的每一个实施多种三维分子学习方法,并表明它们始终如一地提高了基于单维和二维表示的方法的性能。结构的具体选择对于性能至关重要,具有涉及复杂几何形状的任务的三维卷积网络,在需要详细位置信息的系统中表现出良好的图形网络,以及最近开发的设备越多的网络显示出显着承诺。我们的结果表明,许多分子问题符合三维分子学习的增益,并且有可能改善许多仍然过分曝光的任务。为了降低进入并促进现场进一步发展的障碍,我们还提供了一套全面的DataSet处理,模型培训和在我们的开源ATOM3D Python包中的评估工具套件。所有数据集都可以从https://www.atom3d.ai下载。
translated by 谷歌翻译
与靶蛋白具有高结合亲和力的药物样分子的产生仍然是药物发现中的一项困难和资源密集型任务。现有的方法主要采用强化学习,马尔可夫采样或以高斯过程为指导的深层生成模型,在生成具有高结合亲和力的分子时,通过基于计算量的物理学方法计算出的高结合亲和力。我们提出了对分子(豪华轿车)的潜在构成主义,它通过类似于Inceptionism的技术显着加速了分子的产生。豪华轿车采用序列的两个神经网络采用变异自动编码器生成的潜在空间和性质预测,从而使基于梯度的分子特性更快地基于梯度的反相比。综合实验表明,豪华轿车在基准任务上具有竞争力,并且在产生具有高结合亲和力的类似药物的化合物的新任务上,其最先进的技术表现出了最先进的技术,可针对两个蛋白质靶标达到纳摩尔范围。我们通过对绝对结合能的基于更准确的基于分子动力学的计算来证实这些基于对接的结果,并表明我们生成的类似药物的化合物之一的预测$ k_d $(结合亲和力的量度)为$ 6 \ cdot 10^ {-14} $ m针对人类雌激素受体,远远超出了典型的早期药物候选物和大多数FDA批准的药物的亲和力。代码可从https://github.com/rose-stl-lab/limo获得。
translated by 谷歌翻译
准确的蛋白质结合亲和力预测在药物设计和许多其他分子识别问题中至关重要。尽管基于机器学习技术的亲和力预测取得了许多进步,但由于蛋白质 - 配体结合取决于原子和分子的动力学,它们仍然受到限制。为此,我们策划了一个包含3,218个动态蛋白质配合物的MD数据集,并进一步开发了DynaFormer,这是一个基于图的深度学习框架。 DynaFormer可以通过考虑相互作用的各种几何特征来完全捕获动态结合规则。我们的方法显示出优于迄今报告的方法。此外,我们通过将模型与基于结构的对接整合在一起,对热休克蛋白90(HSP90)进行了虚拟筛选。我们对其他基线进行了基准测试,表明我们的方法可以鉴定具有最高实验效力的分子。我们预计大规模的MD数据集和机器学习模型将形成新的协同作用,为加速药物发现和优化提供新的途径。
translated by 谷歌翻译
蛋白质RNA相互作用对各种细胞活性至关重要。已经开发出实验和计算技术来研究相互作用。由于先前数据库的限制,尤其是缺乏蛋白质结构数据,大多数现有的计算方法严重依赖于序列数据,只有一小部分使用结构信息。最近,alphafold彻底改变了整个蛋白质和生物领域。可预应学,在即将到来的年份,也将显着促进蛋白质-RNA相互作用预测。在这项工作中,我们对该字段进行了彻底的审查,调查绑定站点和绑定偏好预测问题,并覆盖常用的数据集,功能和模型。我们还指出了这一领域的潜在挑战和机遇。本调查总结了过去的RBP-RNA互动领域的发展,并预见到了alphafold时代未来的发展。
translated by 谷歌翻译
虽然最近在许多科学领域都变得无处不在,但对其评估的关注较少。对于分子生成模型,最先进的是孤立或与其输入有关的输出。但是,它们的生物学和功能特性(例如配体 - 靶标相互作用)尚未得到解决。在这项研究中,提出了一种新型的生物学启发的基准,用于评估分子生成模型。具体而言,设计了三个不同的参考数据集,并引入了与药物发现过程直接相关的一组指标。特别是我们提出了一个娱乐指标,将药物目标亲和力预测和分子对接应用作为评估生成产量的互补技术。虽然所有三个指标均在测试的生成模型中均表现出一致的结果,但对药物目标亲和力结合和分子对接分数进行了更详细的比较,表明单峰预测器可能会导致关于目标结合在分子水平和多模式方法的错误结论,而多模式的方法是错误的结论。因此优选。该框架的关键优点是,它通过明确关注配体 - 靶标相互作用,将先前的物理化学域知识纳入基准测试过程,从而创建了一种高效的工具,不仅用于评估分子生成型输出,而且还用于丰富富含分子生成的输出。一般而言,药物发现过程。
translated by 谷歌翻译
促性腺营养蛋白释放激素受体(GNRH1R)是治疗子宫疾病的有前途的治疗靶标。迄今为止,在临床研究中可以使用几个GNRH1R拮抗剂,而不满足多个财产约束。为了填补这一空白,我们旨在开发一个基于学习的框架,以促进有效,有效地发现具有理想特性的新的口服小型分子药物靶向GNRH1R。在目前的工作中,首先通过充分利用已知活性化合物和靶蛋白的结构的信息,首先提出了配体和结构组合模型,即LS-Molgen,首先提出了分子生成的方法,该信息通过其出色的性能证明了这一点。比分别基于配体或结构方法。然后,进行了A中的计算机筛选,包括活性预测,ADMET评估,分子对接和FEP计算,其中约30,000个生成的新型分子被缩小到8,以进行实验合成和验证。体外和体内实验表明,其中三个表现出有效的抑制活性(化合物5 IC50 = 0.856 nm,化合物6 IC50 = 0.901 nm,化合物7 IC50 = 2.54 nm对GNRH1R,并且化合物5在基本PK属性中表现良好例如半衰期,口服生物利用度和PPB等。我们认为,提议的配体和结构组合结合的分子生成模型和整个计算机辅助工作流程可能会扩展到从头开始的类似任务或铅优化的类似任务。
translated by 谷歌翻译
SARS-COV-2是一种积极的单链RNA基于大分子,自2022年6月以来,已导致超过630万人死亡。此外,通过封锁扰乱了全球供应链,该病毒对全球经济造成了毁灭性的破坏。为该病毒及其各种变体设计和开发药物至关重要。在本文中,我们使用了一个内部研究框架来重新利用现有的治疗剂,以找到可以治愈COVID-19的药物样生物活性分子。我们使用了从Chembl数据库中检索到的分子的Lipinski规则,以发现针对SARS冠状病毒3Cl蛋白酶的133种吸毒生物活性分子。在标准IC50的基础上,数据集分为三类活动性,无效和中间体。我们的比较分析表明,提出的额外树回收剂(ETR)集成模型改善了结果,同时相对于其他最先进的机器学习模型,可以预测化学化合物的准确生物活性。使用ADMET分析,我们确定了13个具有化学ID的新型生物活性分子187460,190743,222234,222628,222735,222769,222840,222840,222893,2255515,358279,358279,33535,363535,363535,365134 and 422688.88.88.88.88.88.88.88.88.88。 SARS-COV-2 3Cl蛋白酶。这些候选分子进一步研究了结合亲和力。为此,我们进行了分子对接和简短列出的六个具有Chembl IDS 187460、222769、225515、358279、363535和36513的生物活性分子。这些分子可以是SARS-COV-2-2。预计药物学家社区可能会使用这些有希望的化合物进行进一步的体外分析。
translated by 谷歌翻译
最近,基于深度神经网络(DNN)的药物 - 目标相互作用(DTI)模型以高精度突出显示,具有实惠的计算成本。然而,模型在硅药物发现的实践中仍然是一个具有挑战性的问题。我们提出了两项​​关键策略,以提高DTI模型的概括。首先是通过用神经网络参数化的物理通知方程来预测原子原子对相互作用,并提供蛋白质 - 配体复合物作为其总和的总结合亲和力。通过增强更广泛的绑定姿势和配体来培训数据,我们进一步改善了模型泛化。我们验证了我们的模型,PIGNET,在评分职能(CASF)2016的比较评估中,展示了比以前的方法更优于对接和筛选力。我们的物理信息策略还通过可视化配体副结构的贡献来解释预测的亲和力,为进一步配体优化提供了见解。
translated by 谷歌翻译
人工智能(AI)在过去十年中一直在改变药物发现的实践。各种AI技术已在广泛的应用中使用,例如虚拟筛选和药物设计。在本调查中,我们首先概述了药物发现,并讨论了相关的应用,可以减少到两个主要任务,即分子性质预测和分子产生。然后,我们讨论常见的数据资源,分子表示和基准平台。此外,为了总结AI在药物发现中的进展情况,我们介绍了在调查的论文中包括模型架构和学习范式的相关AI技术。我们预计本调查将作为有兴趣在人工智能和药物发现界面工作的研究人员的指南。我们还提供了GitHub存储库(HTTPS:///github.com/dengjianyuan/survey_survey_au_drug_discovery),其中包含文件和代码,如适用,作为定期更新的学习资源。
translated by 谷歌翻译
机器学习在虚拟筛选中显示出巨大的潜力,用于药物发现。目前正在加速基于对接的虚拟筛选的努力不考虑使用其他先前开发的目标的现有数据。为了利用其他目标的知识并利用现有数据,在这项工作中,我们将多任务学习应用于基于对接的虚拟筛选问题。通过两个大型对接数据集,广泛实验结果表明,多任务学习可以实现对接分数预测的更好性能。通过在多个目标上学习知识,由多任务学习训练的模型显示了适应新目标的更好能力。额外的实证研究表明,药物发现中的其他问题,例如实验药物 - 目标亲和预测,也可能受益于多任务学习。我们的结果表明,多任务学习是基于对接的虚拟筛选和加速药物发现过程的有前途的机器学习方法。
translated by 谷歌翻译
Molecular machine learning has been maturing rapidly over the last few years.Improved methods and the presence of larger datasets have enabled machine learning algorithms to make increasingly accurate predictions about molecular properties. However, algorithmic progress has been limited due to the lack of a standard benchmark to compare the efficacy of proposed methods; most new algorithms are benchmarked on different datasets making it challenging to gauge the quality of proposed methods. This work introduces MoleculeNet, a large scale benchmark for molecular machine learning. MoleculeNet curates multiple public datasets, establishes metrics for evaluation, and offers high quality open-source implementations of multiple previously proposed molecular featurization and learning algorithms (released as part of the DeepChem
translated by 谷歌翻译
越来越多的科学发现需要复杂而可扩展的工作流程。工作流程已成为``新应用程序'',其中多尺度计算活动包括多个和异构的可执行任务。特别是,将AI/ML模型引入传统的HPC工作流程已成为高度准确建模的推动力,与传统方法相比,通常会减少计算需求。本章将讨论将AI/ML模型集成到HPC计算的各种模式,从而导致不同类型的AI耦合HPC工作流程。激励了跨科学领域的AI/ML和HPC耦合的需求越来越多,然后以每种模式的许多生产级用例来体现。我们还讨论了极端尺度AI耦合的HPC广告系列的主要挑战 - 任务异质性,适应性,性能 - 以及旨在解决这些问题的几种框架和中间件解决方案。尽管HPC工作流程和AI/ML计算范例都是独立有效的,但我们强调了它们的整合和最终收敛如何导致一系列领域的科学性能的显着改善,最终导致了科学探索,否则就无法实现。
translated by 谷歌翻译
DNA-Encoded Library (DEL) technology has enabled significant advances in hit identification by enabling efficient testing of combinatorially-generated molecular libraries. DEL screens measure protein binding affinity though sequencing reads of molecules tagged with unique DNA-barcodes that survive a series of selection experiments. Computational models have been deployed to learn the latent binding affinities that are correlated to the sequenced count data; however, this correlation is often obfuscated by various sources of noise introduced in its complicated data-generation process. In order to denoise DEL count data and screen for molecules with good binding affinity, computational models require the correct assumptions in their modeling structure to capture the correct signals underlying the data. Recent advances in DEL models have focused on probabilistic formulations of count data, but existing approaches have thus far been limited to only utilizing 2-D molecule-level representations. We introduce a new paradigm, DEL-Dock, that combines ligand-based descriptors with 3-D spatial information from docked protein-ligand complexes. 3-D spatial information allows our model to learn over the actual binding modality rather than using only structured-based information of the ligand. We show that our model is capable of effectively denoising DEL count data to predict molecule enrichment scores that are better correlated with experimental binding affinity measurements compared to prior works. Moreover, by learning over a collection of docked poses we demonstrate that our model, trained only on DEL data, implicitly learns to perform good docking pose selection without requiring external supervision from expensive-to-source protein crystal structures.
translated by 谷歌翻译
The process of screening molecules for desirable properties is a key step in several applications, ranging from drug discovery to material design. During the process of drug discovery specifically, protein-ligand docking, or chemical docking, is a standard in-silico scoring technique that estimates the binding affinity of molecules with a specific protein target. Recently, however, as the number of virtual molecules available to test has rapidly grown, these classical docking algorithms have created a significant computational bottleneck. We address this problem by introducing Deep Surrogate Docking (DSD), a framework that applies deep learning-based surrogate modeling to accelerate the docking process substantially. DSD can be interpreted as a formalism of several earlier surrogate prefiltering techniques, adding novel metrics and practical training practices. Specifically, we show that graph neural networks (GNNs) can serve as fast and accurate estimators of classical docking algorithms. Additionally, we introduce FiLMv2, a novel GNN architecture which we show outperforms existing state-of-the-art GNN architectures, attaining more accurate and stable performance by allowing the model to filter out irrelevant information from data more efficiently. Through extensive experimentation and analysis, we show that the DSD workflow combined with the FiLMv2 architecture provides a 9.496x speedup in molecule screening with a <3% recall error rate on an example docking task. Our open-source code is available at https://github.com/ryienh/graph-dock.
translated by 谷歌翻译
Accurate determination of a small molecule candidate (ligand) binding pose in its target protein pocket is important for computer-aided drug discovery. Typical rigid-body docking methods ignore the pocket flexibility of protein, while the more accurate pose generation using molecular dynamics is hindered by slow protein dynamics. We develop a tiered tensor transform (3T) algorithm to rapidly generate diverse protein-ligand complex conformations for both pose and affinity estimation in drug screening, requiring neither machine learning training nor lengthy dynamics computation, while maintaining both coarse-grain-like coordinated protein dynamics and atomistic-level details of the complex pocket. The 3T conformation structures we generate are closer to experimental co-crystal structures than those generated by docking software, and more importantly achieve significantly higher accuracy in active ligand classification than traditional ensemble docking using hundreds of experimental protein conformations. 3T structure transformation is decoupled from the system physics, making future usage in other computational scientific domains possible.
translated by 谷歌翻译
Extended-connectivity fingerprints (ECFPs) are a novel class of topological fingerprints for molecular characterization. Historically, topological fingerprints were developed for substructure and similarity searching. ECFPs were developed specifically for structure-activity modeling. ECFPs are circular fingerprints with a number of useful qualities: they can be very rapidly calculated; they are not predefined and can represent an essentially infinite number of different molecular features (including stereochemical information); their features represent the presence of particular substructures, allowing easier interpretation of analysis results; and the ECFP algorithm can be tailored to generate different types of circular fingerprints, optimized for different uses. While the use of ECFPs has been widely adopted and validated, a description of their implementation has not previously been presented in the literature.
translated by 谷歌翻译
机器学习潜力是分子模拟的重要工具,但是由于缺乏高质量数据集来训练它们的发展,它们的开发阻碍了它们。我们描述了Spice数据集,这是一种新的量子化学数据集,用于训练与模拟与蛋白质相互作用的药物样的小分子相关的潜在。它包含超过110万个小分子,二聚体,二肽和溶剂化氨基酸的构象。它包括15个元素,带电和未充电的分子以及广泛的共价和非共价相互作用。它提供了在{\ omega} b97m-d3(bj)/def2-tzVPPD理论水平以及其他有用的数量(例如多极矩和键阶)上计算出的力和能量。我们在其上训练一组机器学习潜力,并证明它们可以在化学空间的广泛区域中实现化学精度。它可以作为创建可转移的,准备使用潜在功能用于分子模拟的宝贵资源。
translated by 谷歌翻译