arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2208.06360q-bio.BMcs.LG
收藏

三维图对比学习在分子性质预测中的应用

3D Graph Contrastive Learning for Molecular Property Prediction

Kisung Moon, Sunyoung Kwon

摘要:

自监督学习(SSL)是一种通过利用数据中固有的监督来学习数据表示的方法。这种学习方法在药物领域备受关注,由于耗时和昂贵的实验而缺乏注释数据。使用大量未标记数据的SSL在分子性质预测方面表现出优异的性能,但存在一些问题。(1)现有的SSL模型是大规模的;在计算资源不足的情况下,实现SSL存在限制。(2)在大多数情况下,他们不利用3D结构信息进行分子表征学习。药物的活性与药物分子的结构密切相关。然而,目前大多数模型不使用3D信息或部分使用它。(3)以前将对比学习应用于分子的模型使用置换原子和键的增强。因此,具有不同特征的分子可以在相同的阳性样品中。本文提出了一种新的用于分子性质预测的对比学习框架--小规模3D图对比学习(3DGCL)。3DGCL通过预训练过程反映分子的结构来学习分子表示,该过程不会改变药物的语义。仅使用1,128个样本进行预训练数据和100万个模型参数,我们在四个回归基准数据集中实现了最先进或相当的性能。大量的实验表明,基于化学知识的3D结构信息对于性质预测的分子表示学习是必不可少的。

英文摘要:

Self-supervised learning (SSL) is a method that learns the data representation by utilizing supervision inherent in the data. This learning method is in the spotlight in the drug field, lacking annotated data due to time-consuming and expensive experiments. SSL using enormous unlabeled data has shown excellent performance for molecular property prediction, but a few issues exist. (1) Existing SSL models are large-scale; there is a limitation to implementing SSL where the computing resource is insufficient. (2) In most cases, they do not utilize 3D structural information for molecular representation learning. The activity of a drug is closely related to the structure of the drug molecule. Nevertheless, most current models do not use 3D information or use it partially. (3) Previous models that apply contrastive learning to molecules use the augmentation of permuting atoms and bonds. Therefore, molecules having different characteristics can be in the same positive samples. We propose a novel contrastive learning framework, small-scale 3D Graph Contrastive Learning (3DGCL) for molecular property prediction, to solve the above problems. 3DGCL learns the molecular representation by reflecting the molecule's structure through the pre-training process that does not change the semantics of the drug. Using only 1,128 samples for pre-train data and 1 million model parameters, we achieved the state-of-the-art or comparable performance in four regression benchmark datasets. Extensive experiments demonstrate that 3D structural information based on chemical knowledge is essential to molecular representation learning for property prediction.

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。

↑