arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2409.04737cond-mat.mtrl-scics.LG
收藏

CrysAtom:用于晶体性质预测的原子分布式表示

CrysAtom: Distributed Representation of Atoms for Crystal Property Prediction

Indian Association for the Cultivation of Science(印度科学促进协会)

Shrimon Mukherjee, Madhusudan Ghosh, Partha Basuchowdhuri

AI总结:

提出无监督框架 CrysAtom,利用未标注晶体数据学习原子稠密向量表示,并将其融入现有 GNN 模型以提升晶体性质预测性能。

摘要:

人工智能(AI)的应用在基础科学领域的研究发展中已无处不在。过去十年间,研究人员频繁使用基于机器学习(ML)和深度学习(DL)的方法,带来了重大进展。这些技术在蛋白质结构预测、药物-靶点结合亲和力预测以及分子性质预测等不同任务中实现了显著的性能提升。在材料科学文献中,众所周知晶体材料具有拓扑结构。这类拓扑结构可以表示为图,而利用基于图神经网络(GNN)的方法,有助于将其编码到增强的表示空间中。此类框架主要采用监督学习技术,旨在根据电子性质(形成能、带隙、总能量等)和晶体结构完成下游性质预测任务。通常,这类框架高度依赖手工制作的原子特征表示以及结构表示。本文提出了一个名为 CrysAtom 的无监督框架,利用未标注的晶体数据生成原子的稠密向量表示,该表示可用于现有基于 GNN 的性质预测模型,以准确预测晶体的重要性质。实证结果表明,我们的稠密表示嵌入了原子的化学性质,并显著提升了基线性质预测模型的性能。

英文摘要:

Application of artificial intelligence (AI) has been ubiquitous in the growth of research in the areas of basic sciences. Frequent use of machine learning (ML) and deep learning (DL) based methodologies by researchers has resulted in significant advancements in the last decade. These techniques led to notable performance enhancements in different tasks such as protein structure prediction, drug-target binding affinity prediction, and molecular property prediction. In material science literature, it is well-known that crystalline materials exhibit topological structures. Such topological structures may be represented as graphs and utilization of graph neural network (GNN) based approaches could help encoding them into an augmented representation space. Primarily, such frameworks adopt supervised learning techniques targeted towards downstream property prediction tasks on the basis of electronic properties (formation energy, bandgap, total energy, etc.) and crystalline structures. Generally, such type of frameworks rely highly on the handcrafted atom feature representations along with the structural representations. In this paper, we propose an unsupervised framework namely, CrysAtom, using untagged crystal data to generate dense vector representation of atoms, which can be utilized in existing GNN-based property predictor models to accurately predict important properties of crystals. Empirical results show that our dense representation embeds chemical properties of atoms and enhance the performance of the baseline property predictor models significantly.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑