arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2106.06130cs.LGphysics.chem-phq-bio.MN
收藏

ChemRL-GEM:用于性质预测的几何增强分子表示学习

ChemRL-GEM: Geometry Enhanced Molecular Representation Learning for Property Prediction

Baidu Inc.(百度公司);Shenzhen International Graduate School, Tsinghua University(清华大学深圳国际研究生院)

Xiaomin Fang, Lihang Liu, Jieqiong Lei, Donglong He, Shanzhuo Zhang, Jingbo Zhou, Fan Wang, Hua Wu, Haifeng Wang

摘要:

有效的分子表示学习对于促进分子性质预测是非常重要的,这是药物和材料工业的基本任务。图神经网络(GNNs)的最新进展在将GNNs应用于分子表示学习方面显示出巨大的前景。此外,最近的一些研究也证明了自监督学习方法在预训练GNN以克服标记分子不足的问题上的成功应用。然而,现有的GNN和预训练策略通常将分子视为拓扑图数据,而没有充分利用分子的几何信息。然而,分子的三维(3D)空间结构,也称为分子几何形状,是决定分子物理,化学和生物学性质的最关键因素之一。为此,我们提出了一种新的几何增强分子表示学习方法(GEM)的化学表示学习(ChemRL)。首先,我们设计了一个基于几何的GNN架构,同时模拟分子中的原子,键和键角。具体地说,我们设计了一个分子的双重图:第一个编码原子-键关系;第二个编码键角关系。此外,在设计的GNN架构之上,我们提出了几种新的几何级自监督学习策略,通过利用局部和全局分子3D结构来学习空间知识。我们比较了ChemRL-GEM与不同分子基准上的各种最先进(SOTA)基线,并显示ChemRL-GEM在回归和分类任务中均显着优于所有基线。例如,实验结果显示,与SOTA基线相比,回归任务的总体平均改善了8.8%,证明了所提出的方法的优越性。

英文摘要:

Effective molecular representation learning is of great importance to facilitate molecular property prediction, which is a fundamental task for the drug and material industry. Recent advances in graph neural networks (GNNs) have shown great promise in applying GNNs for molecular representation learning. Moreover, a few recent studies have also demonstrated successful applications of self-supervised learning methods to pre-train the GNNs to overcome the problem of insufficient labeled molecules. However, existing GNNs and pre-training strategies usually treat molecules as topological graph data without fully utilizing the molecular geometry information. Whereas, the three-dimensional (3D) spatial structure of a molecule, a.k.a molecular geometry, is one of the most critical factors for determining molecular physical, chemical, and biological properties. To this end, we propose a novel Geometry Enhanced Molecular representation learning method (GEM) for Chemical Representation Learning (ChemRL). At first, we design a geometry-based GNN architecture that simultaneously models atoms, bonds, and bond angles in a molecule. To be specific, we devised double graphs for a molecule: The first one encodes the atom-bond relations; The second one encodes bond-angle relations. Moreover, on top of the devised GNN architecture, we propose several novel geometry-level self-supervised learning strategies to learn spatial knowledge by utilizing the local and global molecular 3D structures. We compare ChemRL-GEM with various state-of-the-art (SOTA) baselines on different molecular benchmarks and exhibit that ChemRL-GEM can significantly outperform all baselines in both regression and classification tasks. For example, the experimental results show an overall improvement of 8.8% on average compared to SOTA baselines on the regression tasks, demonstrating the superiority of the proposed method.

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。

↑