Benchmarking graph neural networks for materials chemistry

Graph neural networks(GNNs)have received intense interest as a rapidly expanding class of machine learning models remarkably well-suited for materials applications.To date,a number of successful GNNs have been proposed and demonstrated for systems ranging from crystal stability to electronic property prediction and to surface chemistry and heterogeneous catalysis.However,a consistent benchmark of these models remains lacking,hindering the development and consistent evaluation of new models in the materials field.Here,we present a workflow and testing platform,MatDeepLearn,for quickly and reproducibly assessing and comparing GNNs and other machine learning models.We use this platform to optimize and evaluate a selection of top performing GNNs on several representative datasets in computational materials chemistry.From our investigations we note the importance of hyperparameter selection and find roughly similar performances for the top models once optimized.We identify several strengths in GNNs over conventional models in cases with compositionally diverse datasets and in its overall flexibility with respect to inputs,due to learned rather than defined representations.Meanwhile several weaknesses of GNNs are also observed including high data requirements,and suggestions for further improvement for applications in materials chemistry are discussed.

美国和欧洲生物类似药的发展（英文）

生物类似药(biosimilars)是与已批准上市的生物制品高度相似的药物,与小分子仿制药物(generics)不同,生物类似药并不是他们参比制品的精确复制品。尽管高度相似,生物类似药在某些方面仍然可能与参比制品不同,生物类似药间也会互不相同。生物制品不仅由于其复杂的性质和生产过程,还由于存在独特的免疫原性和活性的安全隐患,给研发和监管带来了相当大的挑战。欧洲药品管理局和美国食品药品管理局的指导原则建议采用"证据链完备性"(totality-of-evidence)的方法全面覆盖生物类似药物开发的各个步骤,包括分析表征化、结构相似性和功能等效性等的证据。这种"证据链完备性"是生物类似药整个研发过程中其余工作的基石,包括必须的动物试验研究、人体药代动力学/药效学研究,以及至少1个临床研究,以证实生物类似药功效等效,并且免疫原性或安全性风险没有增加。临床研究应选择敏感人群来进行试验,以便发现任何有临床意义的差异。工艺稳定质量恒定的生物类似药的研发需要丰富的经验和专业技能,只有这样才能够确保患者得到良好治疗。

High-throughput predictions of metal-organic framework electronic properties:theoretical challenges,graph neural networks,and data exploration

With the goal of accelerating the design and discovery of metal–organic frameworks(MOFs)for electronic,optoelectronic,and energy storage applications,we present a dataset of predicted electronic structure properties for thousands of MOFs carried out using multiple density functional approximations.Compared to more accurate hybrid functionals,we find that the widely used PBE generalized gradient approximation(GGA)functional severely underpredicts MOF band gaps in a largely systematic manner for semi-conductors and insulators without magnetic character.However,an even larger and less predictable disparity in the band gap prediction is present for MOFs with open-shell 3d transition metal cations.With regards to partial atomic charges,we find that different density functional approximations predict similar charges overall,although hybrid functionals tend to shift electron density away from the metal centers and onto the ligand environments compared to the GGA point of reference.Much more significant differences in partial atomic charges are observed when comparing different charge partitioning schemes.We conclude by using the dataset of computed MOF properties to train machine-learning models that can rapidly predict MOF band gaps for all four density functional approximations considered in this work,paving the way for future high-throughput screening studies.To encourage exploration and reuse of the theoretical calculations presented in this work,the curated data is made publicly available via an interactive and user-friendly web application on the Materials Project.

Predicting synthesizable multi-functional edge reconstructions in two-dimensional transition metal dichalcogenides

Two-dimensional(2D)transition metal dichalcogenides(TMDCs)have attracted tremendous interest as functional materials due to their exceptionally diverse and tunable properties,especially in their edges.In addition to the conventional armchair and zigzag edges common to hexagonal 2D materials,more complex edge reconstructions can be realized through careful control over the synthesis conditions.However,the whole family of synthesizable,reconstructed edges remains poorly studied.Here,we develop a computational approach integrating ensemble-generation,force-relaxation,and electronic-structure calculations to systematically and efficiently discover additional reconstructed edges and screen their functional properties.

Author Correction:Inverse design of two-dimensional materials with invertible neural networks

The original version of this Article contained errors in Fig.4,in which Fig.4a and Fig.4b were swapped.

Inverse design of two-dimensional materials with invertible neural networks

The ability to readily design novel materials with chosen functional properties on-demand represents a next frontier in materials discovery.However,thoroughly and efficiently sampling the entire design space in a computationally tractable manner remains a highly challenging task.To tackle this problem,we propose an inverse design framework(MatDesINNe)utilizing invertible neural networks which can map both forward and reverse processes between the design space and target property.This approach can be used to generate materials candidates for a designated property,thereby satisfying the highly sought-after goal of inverse design.We then apply this framework to the task of band gap engineering in two-dimensional materials,starting with MoS_(2).Within the design space encompassing six degrees of freedom in applied tensile,compressive and shear strain plus an external electric field,we show the framework can generate novel,high fidelity,and diverse candidates with near-chemical accuracy.We extend this generative capability further to provide insights regarding metal-insulator transition in MoS_(2)which are important for memristive neuromorphic applications,among others.This approach is general and can be directly extended to other materials and their corresponding design spaces and target properties.