首页 > 最新文献

Digital discovery最新文献

英文 中文
CatScore: evaluating asymmetric catalyst design at high efficiency CatScore:评估高效不对称催化剂设计
IF 6.2 Q1 CHEMISTRY, MULTIDISCIPLINARY Pub Date : 2024-07-11 DOI: 10.1039/D4DD00114A
Bing Yan and Kyunghyun Cho

Asymmetric catalysis plays a crucial role in advancing medicine and materials science. However, the prevailing experiment-driven methods for catalyst evaluation are both resource-heavy and time-consuming. To address this challenge, we present CatScore – a learning-centric metric designed for the automatic evaluation of catalyst design models at both instance and system levels. This approach harnesses the power of deep learning to predict product selectivity as a function of reactants and the proposed catalyst. The predicted selectivity serves as a quantitative score, enabling a swift and precise assessment of a catalyst's activity. On an instance level, CatScore's predictions correlate closely with experimental outcomes, demonstrating a Spearman's ρ = 0.84, which surpasses the density functional theory (DFT) based linear free energy relationships (LFERs) metric with ρ = 0.55 and round-trip accuracy metrics at ρ = 0.24. Importantly, when ranking catalyst candidates, CatScore achieves a mean reciprocal ranking significantly superior to traditional LFER methods, marking a considerable reduction in labor and time investments needed to find top-performing catalysts.

不对称催化在推动医学和材料科学发展方面发挥着至关重要的作用。然而,目前用于催化剂评估的实验驱动方法既耗费资源又耗费时间。为了应对这一挑战,我们提出了 CatScore--一种以学习为中心的度量方法,设计用于在实例和系统层面自动评估催化剂设计模型。这种方法利用深度学习的强大功能,将产物选择性作为反应物和拟议催化剂的函数进行预测。预测的选择性可作为量化评分,从而对催化剂的活性进行快速、精确的评估。在实例层面上,CatScore 的预测与实验结果密切相关,显示出 Spearman's ρ = 0.84,超过了密度泛函理论(DFT)的 ρ = 0.54 和往返精度指标 ρ = 0.24。重要的是,在对候选催化剂进行排名时,CatScore 的平均倒数排名明显优于传统的 DFT 方法,大大减少了寻找性能最佳催化剂所需的人力和时间投入。
{"title":"CatScore: evaluating asymmetric catalyst design at high efficiency","authors":"Bing Yan and Kyunghyun Cho","doi":"10.1039/D4DD00114A","DOIUrl":"10.1039/D4DD00114A","url":null,"abstract":"<p >Asymmetric catalysis plays a crucial role in advancing medicine and materials science. However, the prevailing experiment-driven methods for catalyst evaluation are both resource-heavy and time-consuming. To address this challenge, we present CatScore – a learning-centric metric designed for the automatic evaluation of catalyst design models at both instance and system levels. This approach harnesses the power of deep learning to predict product selectivity as a function of reactants and the proposed catalyst. The predicted selectivity serves as a quantitative score, enabling a swift and precise assessment of a catalyst's activity. On an instance level, CatScore's predictions correlate closely with experimental outcomes, demonstrating a Spearman's <em>ρ</em> = 0.84, which surpasses the density functional theory (DFT) based linear free energy relationships (LFERs) metric with <em>ρ</em> = 0.55 and round-trip accuracy metrics at <em>ρ</em> = 0.24. Importantly, when ranking catalyst candidates, CatScore achieves a mean reciprocal ranking significantly superior to traditional LFER methods, marking a considerable reduction in labor and time investments needed to find top-performing catalysts.</p>","PeriodicalId":72816,"journal":{"name":"Digital discovery","volume":" 8","pages":" 1624-1637"},"PeriodicalIF":6.2,"publicationDate":"2024-07-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://pubs.rsc.org/en/content/articlepdf/2024/dd/d4dd00114a?page=search","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141613719","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Towards informatics-driven design of nuclear waste forms 实现信息学驱动的新型核废料形式设计
IF 6.2 Q1 CHEMISTRY, MULTIDISCIPLINARY Pub Date : 2024-07-09 DOI: 10.1039/D4DD00096J
Vinay I. Hegde, Miroslava Peterson, Sarah I. Allec, Xiaonan Lu, Thiruvillamalai Mahadevan, Thanh Nguyen, Jayani Kalahe, Jared Oshiro, Robert J. Seffens, Ethan K. Nickerson, Jincheng Du, Brian J. Riley, John D. Vienna and James E. Saal

Informatics-driven approaches, such as machine learning and sequential experimental design, have shown the potential to drastically impact next-generation materials discovery and design. In this perspective, we present a few guiding principles for applying informatics-based methods towards the design of novel nuclear waste forms. We advocate for adopting a system design approach, and describe the effective usage of data-driven methods in every stage of such a design process. We demonstrate how this approach can optimally leverage physics-based simulations, machine learning surrogates, and experimental synthesis and characterization, within a feedback-driven closed-loop sequential learning framework. We discuss the importance of incorporating domain knowledge into the representation of materials, the construction and curation of datasets, the development of predictive property models, and the design and execution of experiments. We illustrate the application of this approach by successfully designing and validating Na- and Nd-containing phosphate-based ceramic waste forms. Finally, we discuss open challenges in such informatics-driven workflows and present an outlook for their widespread application for the cleanup of nuclear wastes.

信息学驱动的方法,如机器学习和顺序实验设计,已显示出对下一代材料的发现和设计产生巨大影响的潜力。在这一视角中,我们提出了一些将基于信息学的方法应用于新型核废料设计的指导原则。我们主张采用系统设计方法,并介绍了在设计过程的每个阶段有效使用数据驱动方法的情况。我们展示了这种方法如何在一个反馈驱动的闭环顺序学习框架内优化利用基于物理的模拟、机器学习代理以及实验综合和表征。我们讨论了将领域知识纳入材料表征、数据集构建和管理、预测性属性模型开发以及实验设计和执行的重要性。我们通过成功设计和验证含Na和Nd的磷酸盐基陶瓷废物形式来说明这种方法的应用。最后,我们讨论了这种信息学驱动的工作流程所面临的挑战,并对其在核废料清理领域的广泛应用进行了展望。
{"title":"Towards informatics-driven design of nuclear waste forms","authors":"Vinay I. Hegde, Miroslava Peterson, Sarah I. Allec, Xiaonan Lu, Thiruvillamalai Mahadevan, Thanh Nguyen, Jayani Kalahe, Jared Oshiro, Robert J. Seffens, Ethan K. Nickerson, Jincheng Du, Brian J. Riley, John D. Vienna and James E. Saal","doi":"10.1039/D4DD00096J","DOIUrl":"10.1039/D4DD00096J","url":null,"abstract":"<p >Informatics-driven approaches, such as machine learning and sequential experimental design, have shown the potential to drastically impact next-generation materials discovery and design. In this perspective, we present a few guiding principles for applying informatics-based methods towards the design of novel nuclear waste forms. We advocate for adopting a system design approach, and describe the effective usage of data-driven methods in every stage of such a design process. We demonstrate how this approach can optimally leverage physics-based simulations, machine learning surrogates, and experimental synthesis and characterization, within a feedback-driven closed-loop sequential learning framework. We discuss the importance of incorporating domain knowledge into the representation of materials, the construction and curation of datasets, the development of predictive property models, and the design and execution of experiments. We illustrate the application of this approach by successfully designing and validating Na- and Nd-containing phosphate-based ceramic waste forms. Finally, we discuss open challenges in such informatics-driven workflows and present an outlook for their widespread application for the cleanup of nuclear wastes.</p>","PeriodicalId":72816,"journal":{"name":"Digital discovery","volume":" 8","pages":" 1450-1466"},"PeriodicalIF":6.2,"publicationDate":"2024-07-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://pubs.rsc.org/en/content/articlepdf/2024/dd/d4dd00096j?page=search","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141572260","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Machine learning of stability scores from kinetic data† 从动力学数据对稳定性评分进行机器学习
IF 6.2 Q1 CHEMISTRY, MULTIDISCIPLINARY Pub Date : 2024-07-01 DOI: 10.1039/D4DD00036F
Veerupaksh Singla, Qiyuan Zhao and Brett M. Savoie

The absence of computational methods to predict stressor-specific degradation susceptibilities represents a significant and costly challenge to the introduction of new materials into applications. Here, a machine-learning framework is developed that predicts stressor-specific stability scores from computationally generated reaction data. The thermal degradation of alkanes was studied as an exemplary system to demonstrate the approach. The half-lives of ∼32k alkanes were simulated under pyrolysis conditions using 59 model reactions. Using a hinge-loss function, these half-life data were used to train machine learning models to predict a scalar representing the relative stability based only on the molecular graph. These models were successful in transferability case studies using distinct training and testing splits to recapitulate known stability trends with respect to the degree of branching and alkane size. Even the simplest models showed excellent performance in these case studies, demonstrating the relative ease with which thermal stability can be learned. The stability score is also shown to be useful in a design study, where it is used as part of the objective function of a genetic algorithm to guide the search for more stable species. This work provides a framework for converting kinetic reaction data into stability scores that provide actionable design information and opens avenues for exploring more complex chemistries and stressors.

缺乏预测特定应力降解敏感性的计算方法是将新材料引入应用领域所面临的一项重大挑战,而且成本高昂。本文开发了一种机器学习框架,可从计算生成的反应数据中预测特定应激源的稳定性得分。研究了烷烃的热降解作为示范系统,以展示该方法。在热解条件下,使用 59 个模型反应模拟了 ~32k 烷烃的半衰期。利用铰链损失函数,这些半衰期数据被用来训练机器学习模型,以预测一个仅基于分子图的代表相对稳定性的标量。这些模型在可移植性案例研究中取得了成功,使用了不同的训练和测试分区,再现了与支化程度和烷烃大小有关的已知稳定性趋势。在这些案例研究中,即使是最简单的模型也表现出了卓越的性能,这表明热稳定性的学习相对容易。在一项设计研究中,稳定性得分也被证明是有用的,它被用作遗传算法目标函数的一部分,以引导搜索更稳定的物种。这项工作提供了一个将动力学反应数据转化为稳定性分数的框架,从而提供了可操作的设计信息,并为探索更复杂的化学性质和应激源开辟了途径。
{"title":"Machine learning of stability scores from kinetic data†","authors":"Veerupaksh Singla, Qiyuan Zhao and Brett M. Savoie","doi":"10.1039/D4DD00036F","DOIUrl":"10.1039/D4DD00036F","url":null,"abstract":"<p >The absence of computational methods to predict stressor-specific degradation susceptibilities represents a significant and costly challenge to the introduction of new materials into applications. Here, a machine-learning framework is developed that predicts stressor-specific stability scores from computationally generated reaction data. The thermal degradation of alkanes was studied as an exemplary system to demonstrate the approach. The half-lives of ∼32k alkanes were simulated under pyrolysis conditions using 59 model reactions. Using a hinge-loss function, these half-life data were used to train machine learning models to predict a scalar representing the relative stability based only on the molecular graph. These models were successful in transferability case studies using distinct training and testing splits to recapitulate known stability trends with respect to the degree of branching and alkane size. Even the simplest models showed excellent performance in these case studies, demonstrating the relative ease with which thermal stability can be learned. The stability score is also shown to be useful in a design study, where it is used as part of the objective function of a genetic algorithm to guide the search for more stable species. This work provides a framework for converting kinetic reaction data into stability scores that provide actionable design information and opens avenues for exploring more complex chemistries and stressors.</p>","PeriodicalId":72816,"journal":{"name":"Digital discovery","volume":" 9","pages":" 1729-1737"},"PeriodicalIF":6.2,"publicationDate":"2024-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://pubs.rsc.org/en/content/articlepdf/2024/dd/d4dd00036f?page=search","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141501240","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Deep-learning enabled photonic nanostructure discovery in arbitrarily large shape sets via linked latent space representation learning† 通过关联潜空间表征学习,在任意大的形状集中发现深度学习支持的光子纳米结构
IF 6.2 Q1 CHEMISTRY, MULTIDISCIPLINARY Pub Date : 2024-07-01 DOI: 10.1039/D4DD00107A
Sudhanshu Singh, Rahul Kumar, Soumyashree S. Panda and Ravi S. Hegde

The vast array of shapes achievable through modern nanofabrication technologies presents a challenge in selecting the most optimal design for achieving a desired optical response. While data-driven techniques, such as deep learning, hold promise for inverse design, their applicability is often limited as they typically explore only smaller subsets of the extensive range of shapes feasible with nanofabrication. Additionally, these models are often regarded as ‘black boxes,’ lacking transparency in revealing the underlying relationship between the shape and optical response. Here, we introduce a methodology tailored to address the challenges posed by large, complex, and diverse sets of nanostructures. Specifically, we demonstrate our approach in the context of periodic silicon metasurfaces operating in the visible wavelength range, considering large and diverse shape set variations. Our paired variational autoencoder method facilitates the creation of rich, continuous, and parameter-aligned latent space representations of the shape–response relationship. We showcase the practical utility of our approach in two key areas: (1) enabling multiple-solution inverse design and (2) conducting sensitivity analyses on a shape's optical response to nanofabrication-induced distortions. This methodology represents a significant advancement in data-driven design techniques, further unlocking the application potential of nanophotonics.

现代纳米制造技术可实现的形状种类繁多,这给选择最佳设计以实现所需的光学响应带来了挑战。虽然深度学习等数据驱动技术有望实现逆向设计,但其适用性往往受到限制,因为它们通常只能探索纳米制造技术所能实现的大量形状中较小的子集。此外,这些模型通常被视为 "黑盒子",在揭示形状与光学响应之间的内在关系方面缺乏透明度。在此,我们介绍了一种专门针对大型、复杂、多样的纳米结构所带来的挑战而量身定制的方法。具体来说,我们在可见光波长范围内工作的周期性硅元表面上演示了我们的方法,并考虑了大量不同的形状集变化。我们的配对变异自动编码器方法有助于创建丰富、连续和参数对齐的形状-响应关系潜在空间表示。我们在两个关键领域展示了我们方法的实用性:1) 实现多方案逆向设计;2)对形状对纳米加工引起的变形的光学响应进行敏感性分析。这种方法代表了数据驱动设计技术的重大进步,进一步释放了纳米光子学的应用潜力。
{"title":"Deep-learning enabled photonic nanostructure discovery in arbitrarily large shape sets via linked latent space representation learning†","authors":"Sudhanshu Singh, Rahul Kumar, Soumyashree S. Panda and Ravi S. Hegde","doi":"10.1039/D4DD00107A","DOIUrl":"10.1039/D4DD00107A","url":null,"abstract":"<p >The vast array of shapes achievable through modern nanofabrication technologies presents a challenge in selecting the most optimal design for achieving a desired optical response. While data-driven techniques, such as deep learning, hold promise for inverse design, their applicability is often limited as they typically explore only smaller subsets of the extensive range of shapes feasible with nanofabrication. Additionally, these models are often regarded as ‘black boxes,’ lacking transparency in revealing the underlying relationship between the shape and optical response. Here, we introduce a methodology tailored to address the challenges posed by large, complex, and diverse sets of nanostructures. Specifically, we demonstrate our approach in the context of periodic silicon metasurfaces operating in the visible wavelength range, considering large and diverse shape set variations. Our paired variational autoencoder method facilitates the creation of rich, continuous, and parameter-aligned latent space representations of the shape–response relationship. We showcase the practical utility of our approach in two key areas: (1) enabling multiple-solution inverse design and (2) conducting sensitivity analyses on a shape's optical response to nanofabrication-induced distortions. This methodology represents a significant advancement in data-driven design techniques, further unlocking the application potential of nanophotonics.</p>","PeriodicalId":72816,"journal":{"name":"Digital discovery","volume":" 8","pages":" 1612-1623"},"PeriodicalIF":6.2,"publicationDate":"2024-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://pubs.rsc.org/en/content/articlepdf/2024/dd/d4dd00107a?page=search","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141524881","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Physics-driven discovery and bandgap engineering of hybrid perovskites† 混合过氧化物的物理驱动发现和带隙工程学
IF 6.2 Q1 CHEMISTRY, MULTIDISCIPLINARY Pub Date : 2024-06-28 DOI: 10.1039/D4DD00080C
Sheryl L. Sanchez, Elham Foadian, Maxim Ziatdinov, Jonghee Yang, Sergei V. Kalinin, Yongtao Liu and Mahshid Ahmadi

The unique aspect of hybrid perovskites is their tunability, allowing the engineering of the bandgap via substitution. From the application viewpoint, this allows creation of tandem cells between perovskites and silicon, or two or more perovskites, with associated increase of efficiency beyond the single-junction Shockley–Queisser limit. However, the concentration dependence of the optical bandgap in hybrid perovskite solid solutions can be non-linear and even non-monotonic, as determined by band alignments between endmembers, presence of defect states and Urbach tails, and phase separation. Exploring new compositions brings forth the joint problem of the discovery of the composition with the desired band gap and establishing the physical model of the band gap concentration dependence. Here we report the development of the experimental workflow based on structured Gaussian Process (sGP) models and custom sGP (c-sGP) that allow the joint discovery of the experimental behavior and the underpinning physical model. This approach is verified with simulated datasets with known ground truth and was found to accelerate the discovery of experimental behavior and the underlying physical model. The d/c-sGP approach utilizes a few calculated thin film bandgap data points to guide targeted explorations, minimizing the number of thin film preparation steps. Through iterative exploration, we demonstrate that the c-sGP algorithm that combined 5 bandgap models converges rapidly, revealing a relationship in the bandgap diagram of MA1−xGAxPb(I1−xBrx)3. This approach offers a promising method for efficiently understanding the physical model of band gap concentration dependence in binary systems, and this method can also be extended to ternary or higher dimensional systems.

混合型过氧化物的独特之处在于其可调谐性,可以通过置换实现带隙工程。从应用的角度来看,这允许在包晶石和硅或两种或多种包晶石之间创建串联电池,从而提高效率,超越单结肖克利-奎塞尔极限。然而,混合型包光体固溶体的光带隙与浓度的关系可能是非线性的,甚至是非单调的,这是由内部成员之间的带排列、缺陷态和乌尔巴赫尾的存在以及相分离决定的。探索新成分带来的共同问题是:发现具有理想带隙的成分,以及建立带隙浓度依赖性的物理模型。在此,我们报告了基于结构化高斯过程(sGP)模型和定制 sGP(c-sGP)的实验工作流程的开发情况,该流程允许联合发现实验行为和基础物理模型。这种方法通过具有已知地面实况的模拟数据集进行了验证,发现它能加速发现实验行为和基础物理模型。d/c-sGP 方法利用几个计算出的薄膜带隙数据点来指导有针对性的探索,最大限度地减少了薄膜制备步骤的数量。通过迭代探索,我们证明了结合 5 个带隙模型的 c-sGP 算法收敛迅速,揭示了 MA1-xGAxPb(I1-xBrx)3 带隙图中的关系。 这种方法为有效理解二元体系中带隙浓度依赖性的物理模型提供了一种很有前途的方法,这种方法还可以扩展到三元或更高维的体系。
{"title":"Physics-driven discovery and bandgap engineering of hybrid perovskites†","authors":"Sheryl L. Sanchez, Elham Foadian, Maxim Ziatdinov, Jonghee Yang, Sergei V. Kalinin, Yongtao Liu and Mahshid Ahmadi","doi":"10.1039/D4DD00080C","DOIUrl":"10.1039/D4DD00080C","url":null,"abstract":"<p >The unique aspect of hybrid perovskites is their tunability, allowing the engineering of the bandgap <em>via</em> substitution. From the application viewpoint, this allows creation of tandem cells between perovskites and silicon, or two or more perovskites, with associated increase of efficiency beyond the single-junction Shockley–Queisser limit. However, the concentration dependence of the optical bandgap in hybrid perovskite solid solutions can be non-linear and even non-monotonic, as determined by band alignments between endmembers, presence of defect states and Urbach tails, and phase separation. Exploring new compositions brings forth the joint problem of the discovery of the composition with the desired band gap and establishing the physical model of the band gap concentration dependence. Here we report the development of the experimental workflow based on structured Gaussian Process (sGP) models and custom sGP (c-sGP) that allow the joint discovery of the experimental behavior and the underpinning physical model. This approach is verified with simulated datasets with known ground truth and was found to accelerate the discovery of experimental behavior and the underlying physical model. The d/c-sGP approach utilizes a few calculated thin film bandgap data points to guide targeted explorations, minimizing the number of thin film preparation steps. Through iterative exploration, we demonstrate that the c-sGP algorithm that combined 5 bandgap models converges rapidly, revealing a relationship in the bandgap diagram of MA<small><sub>1−<em>x</em></sub></small>GA<small><sub><em>x</em></sub></small>Pb(I<small><sub>1−<em>x</em></sub></small>Br<small><sub><em>x</em></sub></small>)<small><sub>3</sub></small>. This approach offers a promising method for efficiently understanding the physical model of band gap concentration dependence in binary systems, and this method can also be extended to ternary or higher dimensional systems.</p>","PeriodicalId":72816,"journal":{"name":"Digital discovery","volume":" 8","pages":" 1577-1590"},"PeriodicalIF":6.2,"publicationDate":"2024-06-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://pubs.rsc.org/en/content/articlepdf/2024/dd/d4dd00080c?page=search","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141501241","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Uncertainty quantification for molecular property predictions with graph neural architecture search† 利用图神经结构搜索进行分子特性预测的不确定性量化
IF 6.2 Q1 CHEMISTRY, MULTIDISCIPLINARY Pub Date : 2024-06-25 DOI: 10.1039/D4DD00088A
Shengli Jiang, Shiyi Qin, Reid C. Van Lehn, Prasanna Balaprakash and Victor M. Zavala

Graph Neural Networks (GNNs) have emerged as a prominent class of data-driven methods for molecular property prediction. However, a key limitation of typical GNN models is their inability to quantify uncertainties in the predictions. This capability is crucial for ensuring the trustworthy use and deployment of models in downstream tasks. To that end, we introduce AutoGNNUQ, an automated uncertainty quantification (UQ) approach for molecular property prediction. AutoGNNUQ leverages architecture search to generate an ensemble of high-performing GNNs, enabling the estimation of predictive uncertainties. Our approach employs variance decomposition to separate data (aleatoric) and model (epistemic) uncertainties, providing valuable insights for reducing them. In our computational experiments, we demonstrate that AutoGNNUQ outperforms existing UQ methods in terms of both prediction accuracy and UQ performance on multiple benchmark datasets, and generalizes well to out-of-distribution datasets. Additionally, we utilize t-SNE visualization to explore correlations between molecular features and uncertainty, offering insight for dataset improvement. AutoGNNUQ has broad applicability in domains such as drug discovery and materials science, where accurate uncertainty quantification is crucial for decision-making.

图神经网络(GNN)已成为一类重要的数据驱动型分子特性预测方法。然而,典型 GNN 模型的一个主要局限是无法量化预测中的不确定性。这种能力对于确保在下游任务中可靠地使用和部署模型至关重要。为此,我们推出了用于分子特性预测的自动不确定性量化(UQ)方法 AutoGNNUQ。AutoGNNUQ 利用架构搜索生成高性能 GNN 集合,从而实现预测不确定性的估计。我们的方法采用方差分解法来分离数据不确定性和模型不确定性,为减少不确定性提供了宝贵的见解。在我们的计算实验中,我们证明了在多个基准数据集上,AutoGNNUQ 在预测准确性和 UQ 性能方面都优于现有的 UQ 方法,并能很好地泛化到分布外数据集。此外,我们还利用 t-SNE 可视化技术探索了分子特征与不确定性之间的相关性,为数据集的改进提供了启示。AutoGNNUQ 在药物发现和材料科学等领域具有广泛的适用性,在这些领域,准确的不确定性量化对决策至关重要。
{"title":"Uncertainty quantification for molecular property predictions with graph neural architecture search†","authors":"Shengli Jiang, Shiyi Qin, Reid C. Van Lehn, Prasanna Balaprakash and Victor M. Zavala","doi":"10.1039/D4DD00088A","DOIUrl":"10.1039/D4DD00088A","url":null,"abstract":"<p >Graph Neural Networks (GNNs) have emerged as a prominent class of data-driven methods for molecular property prediction. However, a key limitation of typical GNN models is their inability to quantify uncertainties in the predictions. This capability is crucial for ensuring the trustworthy use and deployment of models in downstream tasks. To that end, we introduce AutoGNNUQ, an automated uncertainty quantification (UQ) approach for molecular property prediction. AutoGNNUQ leverages architecture search to generate an ensemble of high-performing GNNs, enabling the estimation of predictive uncertainties. Our approach employs variance decomposition to separate data (aleatoric) and model (epistemic) uncertainties, providing valuable insights for reducing them. In our computational experiments, we demonstrate that AutoGNNUQ outperforms existing UQ methods in terms of both prediction accuracy and UQ performance on multiple benchmark datasets, and generalizes well to out-of-distribution datasets. Additionally, we utilize t-SNE visualization to explore correlations between molecular features and uncertainty, offering insight for dataset improvement. AutoGNNUQ has broad applicability in domains such as drug discovery and materials science, where accurate uncertainty quantification is crucial for decision-making.</p>","PeriodicalId":72816,"journal":{"name":"Digital discovery","volume":" 8","pages":" 1534-1553"},"PeriodicalIF":6.2,"publicationDate":"2024-06-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141501243","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Illuminating the property space in crystal structure prediction using Quality-Diversity algorithms† 利用质量多样性算法照亮晶体结构预测的属性空间
IF 6.2 Q1 CHEMISTRY, MULTIDISCIPLINARY Pub Date : 2024-06-19 DOI: 10.1039/D4DD00054D
Marta Wolinska, Aron Walsh and Antoine Cully

The identification of materials with exceptional properties is an essential objective to enable technological progress. We propose the application of Quality-Diversity algorithms to the field of crystal structure prediction. The objective of these algorithms is to identify a diverse set of high-performing solutions, which has been successful in a range of fields such as robotics, architecture and aeronautical engineering. As these methods rely on a high number of evaluations, we employ machine-learning surrogate models to compute the interatomic potential and material properties that are used to guide optimisation. Consequently, we also show the value of using neural networks to model crystal properties and enable the identification of novel composition–structure combinations. In this work, we specifically study the application of the MAP-Elites algorithm to predict polymorphs of TiO2. We rediscover the known ground state, in addition to a set of other polymorphs with distinct properties. We validate our method for C, SiO2 and SiC systems, where we show that the algorithm can uncover multiple local minima with distinct electronic and mechanical properties.

识别具有特殊性能的材料是实现技术进步的一个基本目标。我们建议将质量多样性算法应用于晶体结构预测领域。这些算法的目标是识别出一系列不同的高性能解决方案,这在机器人、建筑和航空工程等一系列领域都取得了成功。由于这些方法依赖于大量的评估,因此我们采用机器学习代用模型来计算原子间势能和材料特性,用于指导优化。因此,我们还展示了使用神经网络建立晶体属性模型的价值,并能识别新的成分结构组合。在这项工作中,我们特别研究了如何应用 MAP-Elites 算法预测二氧化钛的多晶体。我们重新发现了已知的基态,以及一系列具有独特性质的其他多晶体。我们对 C、SiO2 和 SiC 系统进行了验证,结果表明该算法可以发现具有不同电子和机械特性的多个局部最小值。
{"title":"Illuminating the property space in crystal structure prediction using Quality-Diversity algorithms†","authors":"Marta Wolinska, Aron Walsh and Antoine Cully","doi":"10.1039/D4DD00054D","DOIUrl":"10.1039/D4DD00054D","url":null,"abstract":"<p >The identification of materials with exceptional properties is an essential objective to enable technological progress. We propose the application of Quality-Diversity algorithms to the field of crystal structure prediction. The objective of these algorithms is to identify a diverse set of high-performing solutions, which has been successful in a range of fields such as robotics, architecture and aeronautical engineering. As these methods rely on a high number of evaluations, we employ machine-learning surrogate models to compute the interatomic potential and material properties that are used to guide optimisation. Consequently, we also show the value of using neural networks to model crystal properties and enable the identification of novel composition–structure combinations. In this work, we specifically study the application of the MAP-Elites algorithm to predict polymorphs of TiO<small><sub>2</sub></small>. We rediscover the known ground state, in addition to a set of other polymorphs with distinct properties. We validate our method for C, SiO<small><sub>2</sub></small> and SiC systems, where we show that the algorithm can uncover multiple local minima with distinct electronic and mechanical properties.</p>","PeriodicalId":72816,"journal":{"name":"Digital discovery","volume":" 8","pages":" 1554-1563"},"PeriodicalIF":6.2,"publicationDate":"2024-06-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://pubs.rsc.org/en/content/articlepdf/2024/dd/d4dd00054d?page=search","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141501244","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
rNets: a standalone package to visualize reaction networks† rNets:可视化反应网络的独立软件包
IF 6.2 Q1 CHEMISTRY, MULTIDISCIPLINARY Pub Date : 2024-06-19 DOI: 10.1039/D4DD00087K
Sergio Pablo-García, Raúl Pérez-Soto, Albert Sabadell-Rendón, Diego Garay-Ruiz, Vladyslav Nosylevskyi and Núria López

In the study of chemical processes, visualizing reaction networks is pivotal for identifying crucial compounds and transformations. Traditional methods, such as network schematics and reaction path linear plots, often struggle to effectively represent complex reaction networks due to their size and intricate connectivity. Alternatives capable of leading with complexity include graph methods, but they are not user-friendly, lacking simplicity and modularity, which hinders their integration with widely-used research software. This work introduces rNets an innovative tool designed for the efficient visualization of reaction networks with a user-friendly interface, modularity, and seamless integration with existing software packages. The effectiveness of rNets is demonstrated through its application in analyzing three catalytic reactions, showcasing its potential to significantly enhance research both in homogeneous and heterogeneous catalysis fields. This tool not only simplifies the visualization process but also opens new avenues for exploring complex reaction networks in diverse research contexts.

在化学过程研究中,反应网络的可视化对于识别关键化合物和转化至关重要。传统的方法,如网络示意图和反应路径线性图,由于体积庞大、连接错综复杂,往往难以有效地表现复杂的反应网络。能够应对复杂性的替代方法包括图方法,但这些方法对用户不友好,缺乏简洁性和模块化,这阻碍了它们与广泛使用的研究软件的整合。本文介绍的 rNets 是一种创新工具,设计用于高效可视化反应网络,具有用户友好界面、模块化和与现有软件包无缝集成的特点。rNets 在分析三个催化反应中的应用证明了它的有效性,展示了它在显著提高均相和异相催化领域研究水平方面的潜力。该工具不仅简化了可视化过程,还为在不同研究背景下探索复杂反应网络开辟了新途径。
{"title":"rNets: a standalone package to visualize reaction networks†","authors":"Sergio Pablo-García, Raúl Pérez-Soto, Albert Sabadell-Rendón, Diego Garay-Ruiz, Vladyslav Nosylevskyi and Núria López","doi":"10.1039/D4DD00087K","DOIUrl":"10.1039/D4DD00087K","url":null,"abstract":"<p >In the study of chemical processes, visualizing reaction networks is pivotal for identifying crucial compounds and transformations. Traditional methods, such as network schematics and reaction path linear plots, often struggle to effectively represent complex reaction networks due to their size and intricate connectivity. Alternatives capable of leading with complexity include graph methods, but they are not user-friendly, lacking simplicity and modularity, which hinders their integration with widely-used research software. This work introduces rNets an innovative tool designed for the efficient visualization of reaction networks with a user-friendly interface, modularity, and seamless integration with existing software packages. The effectiveness of rNets is demonstrated through its application in analyzing three catalytic reactions, showcasing its potential to significantly enhance research both in homogeneous and heterogeneous catalysis fields. This tool not only simplifies the visualization process but also opens new avenues for exploring complex reaction networks in diverse research contexts.</p>","PeriodicalId":72816,"journal":{"name":"Digital discovery","volume":" 8","pages":" 1564-1576"},"PeriodicalIF":6.2,"publicationDate":"2024-06-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://pubs.rsc.org/en/content/articlepdf/2024/dd/d4dd00087k?page=search","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141524997","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Predicting melting temperatures across the periodic table with machine learning atomistic potentials† 用机器学习原子势预测整个元素周期表的熔化温度
IF 6.2 Q1 CHEMISTRY, MULTIDISCIPLINARY Pub Date : 2024-06-18 DOI: 10.1039/D4DD00069B
Christopher M. Andolina and Wissam A. Saidi

Understanding how materials melt is crucial for their practical applications and development, thereby enabling us to predict their behavior in real-world environmental conditions. Accurate computation of melting temperatures (Tm) has been a long-standing pursuit involving various methods for classical potentials and first-principles calculations. However, finding literature Tm references for many elements using a clearly defined set of calculation parameters is rare. Herein we apply deep neural network atomistic potentials (DNPs), trained on density functional theory (DFT) generated datasets, to describe the melting temperature of 20 single-element materials across the Periodic Table using large-scale molecular dynamics simulations. Our results demonstrate high-fidelity with experimental observations and also with calculated reference melting temperatures, yielding an average deviation of less than 18%. We propose a straightforward elemental-group-specific relationship between Tm and cohesive energy for these calculated references to provide reliable DFT specific reference points, which we believe can be readily applied to many materials. Additionally, we compare DNP predictions for three representative elements at external pressures up to 30 GPa in molecular dynamics simulations, revealing reasonable consistency with experimental and DFT literature references despite the lack of explicit training at these high pressures. This work further extends our flexible approach to developing and modifying DNPs to create unique atomistic potentials tailored to describe atomically complex materials under extreme environmental conditions.

了解材料的熔化过程对其实际应用和发展至关重要,从而使我们能够预测其在实际环境条件下的行为。熔化温度(Tm)的精确计算是一项由来已久的工作,其中涉及各种经典电势和第一原理计算方法。然而,使用一套明确定义的计算参数为许多元素找到文献中的 Tm 参考值却非常罕见。在此,我们应用在密度泛函理论(DFT)生成的数据集上训练的深度神经网络原子势(DNP),通过大规模分子动力学模拟来描述元素周期表中 20 种单元素材料的熔化温度。我们的结果表明与实验观测结果和计算参考熔化温度高度吻合,平均偏差小于 18%。我们为这些计算参考值提出了 Tm 与内聚能之间简单明了的元素组特定关系,以提供可靠的 DFT 特定参考点,我们相信这可以很容易地应用于许多材料。此外,我们还在分子动力学模拟中比较了三种代表性元素在高达 30 GPa 的外部压力下的 DNP 预测值,结果表明,尽管在这些高压下缺乏明确的训练,但 DNP 与实验和 DFT 文献参考具有合理的一致性。这项工作进一步扩展了我们开发和修改 DNP 的灵活方法,以创建独特的原子势能,用于描述极端环境条件下的原子复杂材料。
{"title":"Predicting melting temperatures across the periodic table with machine learning atomistic potentials†","authors":"Christopher M. Andolina and Wissam A. Saidi","doi":"10.1039/D4DD00069B","DOIUrl":"10.1039/D4DD00069B","url":null,"abstract":"<p >Understanding how materials melt is crucial for their practical applications and development, thereby enabling us to predict their behavior in real-world environmental conditions. Accurate computation of melting temperatures (<em>T</em><small><sub>m</sub></small>) has been a long-standing pursuit involving various methods for classical potentials and first-principles calculations. However, finding literature <em>T</em><small><sub>m</sub></small> references for many elements using a clearly defined set of calculation parameters is rare. Herein we apply deep neural network atomistic potentials (DNPs), trained on density functional theory (DFT) generated datasets, to describe the melting temperature of 20 single-element materials across the Periodic Table using large-scale molecular dynamics simulations. Our results demonstrate high-fidelity with experimental observations and also with calculated reference melting temperatures, yielding an average deviation of less than 18%. We propose a straightforward elemental-group-specific relationship between <em>T</em><small><sub>m</sub></small> and cohesive energy for these calculated references to provide reliable DFT specific reference points, which we believe can be readily applied to many materials. Additionally, we compare DNP predictions for three representative elements at external pressures up to 30 GPa in molecular dynamics simulations, revealing reasonable consistency with experimental and DFT literature references despite the lack of explicit training at these high pressures. This work further extends our flexible approach to developing and modifying DNPs to create unique atomistic potentials tailored to describe atomically complex materials under extreme environmental conditions.</p>","PeriodicalId":72816,"journal":{"name":"Digital discovery","volume":" 7","pages":" 1421-1429"},"PeriodicalIF":6.2,"publicationDate":"2024-06-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://pubs.rsc.org/en/content/articlepdf/2024/dd/d4dd00069b?page=search","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141501242","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
DrugPose: benchmarking 3D generative methods for early stage drug discovery DrugPose:为早期药物发现的三维生成方法设定基准
IF 6.2 Q1 CHEMISTRY, MULTIDISCIPLINARY Pub Date : 2024-06-14 DOI: 10.1039/D4DD00076E
Zygimantas Jocys, Joanna Grundy and Katayoun Farrahi

Molecule generation in 3D space has gained attention in the past few years. These models typically have a hypothesis that they need to satisfy (i.e. shape) or they are designed to fit into a protein pocket. However, there's been limited evaluation of the 3D poses they produce. In the previous work, the generated molecules are redocked and the generated poses are disregarded. Moreover, many of the generated molecules are not synthesisable and druglike. To tackle these challenges we propose DrugPose, a novel benchmark framework, that utilises Simbind to evaluate the generated molecules based on their coherence with the initial hypothesis formed from available data (e.g., active compounds and protein structures) and their adherence to the laws of physics. Moreover, it offers enhanced insights into synthesizability by directly cross-referencing with a commercial database and utilising the Ghose filter for assessing drug-likeness. Considering current generative methods, the percentage of generated molecules with the intended binding mode ranges from 4.7% to 15.9%, with commercial accessibility spanning 23.6% to 38.8% and fully satisfying the Ghose filter between 10% and 40%. These results highlight the need for further research to develop more reliable and transparent methodologies for 3D molecule generation.

在过去几年中,三维空间中的分子生成技术受到了广泛关注。这些模型通常有一个需要满足的假设(即形状),或者被设计成适合蛋白质口袋。然而,对它们生成的三维姿态的评估却很有限。在以前的工作中,生成的分子会被重新锁定,而生成的姿势会被忽略。此外,许多生成的分子无法合成,也不像药物。为了应对这些挑战,我们提出了一种新的基准框架 DrugPose,它利用 Simbind 评估生成的分子,评估的依据是这些分子是否与根据现有数据(如活性化合物和蛋白质结构)形成的初始假设一致,是否符合物理定律。此外,它还通过直接与商业数据库进行交叉对比,并利用 Ghose 过滤器评估药物相似性,从而提高了对可合成性的洞察力。考虑到当前的生成方法,所生成的分子中具有预期结合模式的比例在 4.7% 到 15.9% 之间,商业可得性在 23.6% 到 38.8% 之间,完全符合 Ghose 过滤器的比例在 10% 到 40% 之间。这些结果凸显了进一步研究的必要性,以开发更可靠、更透明的三维分子生成方法。
{"title":"DrugPose: benchmarking 3D generative methods for early stage drug discovery","authors":"Zygimantas Jocys, Joanna Grundy and Katayoun Farrahi","doi":"10.1039/D4DD00076E","DOIUrl":"10.1039/D4DD00076E","url":null,"abstract":"<p >Molecule generation in 3D space has gained attention in the past few years. These models typically have a hypothesis that they need to satisfy (<em>i.e.</em> shape) or they are designed to fit into a protein pocket. However, there's been limited evaluation of the 3D poses they produce. In the previous work, the generated molecules are redocked and the generated poses are disregarded. Moreover, many of the generated molecules are not synthesisable and druglike. To tackle these challenges we propose DrugPose, a novel benchmark framework, that utilises Simbind to evaluate the generated molecules based on their coherence with the initial hypothesis formed from available data (<em>e.g.</em>, active compounds and protein structures) and their adherence to the laws of physics. Moreover, it offers enhanced insights into synthesizability by directly cross-referencing with a commercial database and utilising the Ghose filter for assessing drug-likeness. Considering current generative methods, the percentage of generated molecules with the intended binding mode ranges from 4.7% to 15.9%, with commercial accessibility spanning 23.6% to 38.8% and fully satisfying the Ghose filter between 10% and 40%. These results highlight the need for further research to develop more reliable and transparent methodologies for 3D molecule generation.</p>","PeriodicalId":72816,"journal":{"name":"Digital discovery","volume":" 7","pages":" 1308-1318"},"PeriodicalIF":6.2,"publicationDate":"2024-06-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://pubs.rsc.org/en/content/articlepdf/2024/dd/d4dd00076e?page=search","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141501272","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
期刊
Digital discovery
全部 Acc. Chem. Res. ACS Applied Bio Materials ACS Appl. Electron. Mater. ACS Appl. Energy Mater. ACS Appl. Mater. Interfaces ACS Appl. Nano Mater. ACS Appl. Polym. Mater. ACS BIOMATER-SCI ENG ACS Catal. ACS Cent. Sci. ACS Chem. Biol. ACS Chemical Health & Safety ACS Chem. Neurosci. ACS Comb. Sci. ACS Earth Space Chem. ACS Energy Lett. ACS Infect. Dis. ACS Macro Lett. ACS Mater. Lett. ACS Med. Chem. Lett. ACS Nano ACS Omega ACS Photonics ACS Sens. ACS Sustainable Chem. Eng. ACS Synth. Biol. Anal. Chem. BIOCHEMISTRY-US Bioconjugate Chem. BIOMACROMOLECULES Chem. Res. Toxicol. Chem. Rev. Chem. Mater. CRYST GROWTH DES ENERG FUEL Environ. Sci. Technol. Environ. Sci. Technol. Lett. Eur. J. Inorg. Chem. IND ENG CHEM RES Inorg. Chem. J. Agric. Food. Chem. J. Chem. Eng. Data J. Chem. Educ. J. Chem. Inf. Model. J. Chem. Theory Comput. J. Med. Chem. J. Nat. Prod. J PROTEOME RES J. Am. Chem. Soc. LANGMUIR MACROMOLECULES Mol. Pharmaceutics Nano Lett. Org. Lett. ORG PROCESS RES DEV ORGANOMETALLICS J. Org. Chem. J. Phys. Chem. J. Phys. Chem. A J. Phys. Chem. B J. Phys. Chem. C J. Phys. Chem. Lett. Analyst Anal. Methods Biomater. Sci. Catal. Sci. Technol. Chem. Commun. Chem. Soc. Rev. CHEM EDUC RES PRACT CRYSTENGCOMM Dalton Trans. Energy Environ. Sci. ENVIRON SCI-NANO ENVIRON SCI-PROC IMP ENVIRON SCI-WAT RES Faraday Discuss. Food Funct. Green Chem. Inorg. Chem. Front. Integr. Biol. J. Anal. At. Spectrom. J. Mater. Chem. A J. Mater. Chem. B J. Mater. Chem. C Lab Chip Mater. Chem. Front. Mater. Horiz. MEDCHEMCOMM Metallomics Mol. Biosyst. Mol. Syst. Des. Eng. Nanoscale Nanoscale Horiz. Nat. Prod. Rep. New J. Chem. Org. Biomol. Chem. Org. Chem. Front. PHOTOCH PHOTOBIO SCI PCCP Polym. Chem.
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
0
微信
客服QQ
Book学术公众号 扫码关注我们
反馈
×
意见反馈
请填写您的意见或建议
请填写您的手机或邮箱
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
现在去查看 取消
×
提示
确定
Book学术官方微信
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术
文献互助 智能选刊 最新文献 互助须知 联系我们:info@booksci.cn
Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。
Copyright © 2023 Book学术 All rights reserved.
ghs 京公网安备 11010802042870号 京ICP备2023020795号-1