School of Software, XinJiang University, Urumqi 830091, China.
School of Computer Science and Engineering, Central South University, Changsha 410083, China.
J Chem Inf Model. 2024 Apr 22;64(8):3105-3113. doi: 10.1021/acs.jcim.3c02058. Epub 2024 Mar 22.
Molecular property prediction is a fundamental task of drug discovery. With the rapid development of deep learning, computational approaches for predicting molecular properties are experiencing increasing popularity. However, these existing methods often ignore the 3D information on molecules, which is critical in molecular representation learning. In the past few years, several self-supervised learning (SSL) approaches have been proposed to exploit the geometric information by using pre-training on 3D molecular graphs and fine-tuning on 2D molecular graphs. Most of these approaches are based on the global geometry of molecules, and there is still a challenge in capturing the local structure and local interpretability. To this end, we propose local geometry-guided graph attention (LGGA), which integrates local geometry into the attention mechanism and message-passing of graph neural networks (GNNs). LGGA introduces a novel method to model molecules, enhancing the model's ability to capture intricate local structural details. Experiments on various data sets demonstrate that the integration of local geometry has a significant impact on the improved results, and our model outperforms the state-of-the-art methods for molecular property prediction, establishing its potential as a promising tool in drug discovery and related fields.
分子性质预测是药物发现的一项基本任务。随着深度学习的快速发展，预测分子性质的计算方法越来越受到欢迎。然而，这些现有的方法往往忽略了分子的 3D 信息，而这对于分子表示学习至关重要。在过去的几年中，已经提出了几种自监督学习（SSL）方法来利用 3D 分子图的预训练和 2D 分子图的微调来挖掘几何信息。这些方法大多基于分子的全局几何形状，在捕捉局部结构和局部可解释性方面仍然存在挑战。为此，我们提出了局部几何引导图注意力（LGGA），它将局部几何形状集成到图神经网络（GNN）的注意力机制和消息传递中。LGGA 引入了一种新的分子建模方法，增强了模型捕捉复杂局部结构细节的能力。在各种数据集上的实验表明，局部几何形状的集成对改进结果有显著影响，我们的模型在分子性质预测方面优于最新方法，为药物发现和相关领域提供了一种有前途的工具。
