Physics guided deep learning for generative design of crystal materials with symmetry constraints

Zhao, Yong; Siriwardane, Edirisuriya M. Dilanga; Wu, Zhenyao; Fu, Nihang; Al-Fahdi, Mohammed; Hu, Ming; Hu, Jianjun

doi:10.1038/s41524-023-00987-9

Cited by 34 publications

(25 citation statements)

References 40 publications

(62 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…26,29 Instead, VAE models always generate crystal structures with very low symmetry. 28 On the other hand, we only use materials falling in the three space groups Fm 3̄ m , F 4̄3 m , and Pm 3̄ m because these three space groups are with the greatest number of materials in the OQMD 30 using selection criteria in CubicGAN.…”

Section: Methodsmentioning

confidence: 99%

See 1 more Smart Citation

Data-driven deep generative design of stable spintronic materials

Siriwardane,

Zhao,

2023

CrystEngComm

View full text Add to dashboard Cite

show abstract

Section: Methodsmentioning

confidence: 99%

“…The generator takes random noise as input to generate fake samples and the discriminator tells the fake samples from the real ones. CubicGAN 24 and PGCGM 28 are two typical crystal generative models using GANs. Both are provided with the space group in the training and physical losses are added in PGCGM to improve the performance.…”

Section: Introductionmentioning

confidence: 99%

Data-driven deep generative design of stable spintronic materials

Siriwardane,

Zhao,

2023

CrystEngComm

View full text Add to dashboard Cite

show abstract

“…A more efficient approach would combine these extremes to avoid the need to evaluate candidates that are ultimately discarded by the subsequent process. This might range from including physics-based symmetry contraints, 161 directly incorporating a learned formation energy constraint into the generative process, 162 or by restricting the generating samples to obey compositional "grammatical" rules. 163 The combination of empirical synthetic accessibility metrics, fragment-and synthesis-based constraints, and forward and reverse synthesis prediction to constrain generative models for drug design 160 can serve as a model for materials chemists.…”

Section: Vc Sample What Can Be Made and How To Make It � Defer Optimi...mentioning

confidence: 99%

In Pursuit of the Exceptional: Research Directions for Machine Learning in Chemical and Materials Science

Schrier,

Norquist,

Buonassisi

et al. 2023

J. Am. Chem. Soc.

View full text Add to dashboard Cite

Exceptional molecules and materials with one or more extraordinary properties are both technologically valuable and fundamentally interesting, because they often involve new physical phenomena or new compositions that defy expectations. Historically, exceptionality has been achieved through serendipity, but recently, machine learning (ML) and automated experimentation have been widely proposed to accelerate target identification and synthesis planning. In this Perspective, we argue that the data-driven methods commonly used today are well-suited for optimization but not for the realization of new exceptional materials or molecules. Finding such outliers should be possible using ML, but only by shifting away from using traditional ML approaches that tweak the composition, crystal structure, or reaction pathway. We highlight case studies of high-T c oxide superconductors and superhard materials to demonstrate the challenges of ML-guided discovery and discuss the limitations of automation for this task. We then provide six recommendations for the development of ML methods capable of exceptional materials discovery: (i) Avoid the tyranny of the middle and focus on extrema; (ii) When data are limited, qualitative predictions that provide direction are more valuable than interpolative accuracy; (iii) Sample what can be made and how to make it and defer optimization; (iv) Create room (and look) for the unexpected while pursuing your goal; (v) Try to fill-in-the-blanks of input and output space; (vi) Do not confuse human understanding with model interpretability. We conclude with a description of how these recommendations can be integrated into automated discovery workflows, which should enable the discovery of exceptional molecules and materials.

show abstract

“…In that respect, this model is the most similar to ours. The second one is the Physics Guided Crystal Generative Model (PGCGM), 49 which uses a Generative Adversarial Network to sample crystal structures within a given set of 20 space groups. For a fair comparison, all models should be trained on the same data set.…”

Section: Comparison With Other Modelsmentioning

confidence: 99%

Data-Driven Score-Based Models for Generating Stable Structures with Adaptive Crystal Cells

Sultanov,

Crivello,

Rebafka

et al. 2023

J. Chem. Inf. Model.

View full text Add to dashboard Cite

The discovery of new functional and stable materials is a big challenge due to its complexity. This work aims at the generation of new crystal structures with desired properties, such as chemical stability and specified chemical composition, by using machine learning generative models. Compared with the generation of molecules, crystal structures pose new difficulties arising from the periodic nature of the crystal and from the specific symmetry constraints related to the space group. In this work, score-based probabilistic models based on annealed Langevin dynamics, which have shown excellent performance in various applications, are adapted to the task of crystal generation. The novelty of the presented approach resides in the fact that the lattice of the crystal cell is not fixed. During the training of the model, the lattice is learned from the available data, whereas during the sampling of a new chemical structure, two denoising processes are used in parallel to generate the lattice along with the generation of the atomic positions. A multigraph crystal representation is introduced that respects symmetry constraints, yielding computational advantages and a better quality of the sampled structures. We show that our model is capable of generating new candidate structures in any chosen chemical system and crystal group without any additional training. To illustrate the functionality of the proposed method, a comparison of our model to other recent generative models based on descriptor-based metrics is provided.

show abstract

Physics guided deep learning for generative design of crystal materials with symmetry constraints

Cited by 34 publications

References 40 publications

Data-driven deep generative design of stable spintronic materials

Data-driven deep generative design of stable spintronic materials

In Pursuit of the Exceptional: Research Directions for Machine Learning in Chemical and Materials Science

Data-Driven Score-Based Models for Generating Stable Structures with Adaptive Crystal Cells

Contact Info

Product

Resources

About