Yang Ziduo, Zhao Yi-Ming, Wang Xian, Liu Xiaoqing, Zhang Xiuying, Li Yifan, Lv Qiujie, Chen Calvin Yu-Chian, Shen Lei
Department of Mechanical Engineering, National University of Singapore, Singapore, Singapore.
Artificial Intelligence Medical Research Center, School of Intelligent Systems Engineering, Shenzhen Campus of Sun Yat-sen University, Shenzhen, China.
Nat Commun. 2024 Sep 17;15(1):8148. doi: 10.1038/s41467-024-52378-3.
In computational molecular and materials science, determining equilibrium structures is the crucial first step for accurate subsequent property calculations. However, the recent discovery of millions of new crystals and super large twisted structures has challenged traditional computational methods, both ab initio and machine-learning-based, due to their computationally intensive iterative processes. To address these scalability issues, here we introduce DeepRelax, a deep generative model capable of performing geometric crystal structure relaxation rapidly and without iterations. DeepRelax learns the equilibrium structural distribution, enabling it to predict relaxed structures directly from their unrelaxed ones. The ability to perform structural relaxation at the millisecond level per structure, combined with the scalability of parallel processing, makes DeepRelax particularly useful for large-scale virtual screening. We demonstrate DeepRelax's reliability and robustness by applying it to five diverse databases, including oxides, Materials Project, two-dimensional materials, van der Waals crystals, and crystals with point defects. DeepRelax consistently shows high accuracy and efficiency, validated by density functional theory calculations. Finally, we enhance its trustworthiness by integrating uncertainty quantification. This work significantly accelerates computational workflows, offering a robust and trustworthy machine-learning method for material discovery and advancing the application of AI for science.
在计算分子和材料科学中，确定平衡结构是后续准确进行性质计算的关键第一步。然而，最近数百万种新晶体和超大型扭曲结构的发现对传统计算方法提出了挑战，无论是从头算方法还是基于机器学习的方法，因为它们的计算密集型迭代过程。为了解决这些可扩展性问题，我们在此引入DeepRelax，这是一种深度生成模型，能够快速且无需迭代地执行几何晶体结构弛豫。DeepRelax学习平衡结构分布，使其能够直接从未弛豫结构预测弛豫结构。每个结构在毫秒级执行结构弛豫的能力，再加上并行处理的可扩展性，使得DeepRelax对于大规模虚拟筛选特别有用。我们通过将DeepRelax应用于五个不同的数据库来证明其可靠性和稳健性，这些数据库包括氧化物、材料项目、二维材料、范德华晶体以及具有点缺陷的晶体。通过密度泛函理论计算验证，DeepRelax始终显示出高精度和高效率。最后，我们通过整合不确定性量化来提高其可信度。这项工作显著加速了计算工作流程，为材料发现提供了一种强大且可靠的机器学习方法，并推动了人工智能在科学领域的应用。
