Zhang Lianwei, Niu Dongjiang, Zhang Beiyi, Zhang Qiang, Li Zhen
IEEE J Biomed Health Inform. 2025 Mar;29(3):1747-1758. doi: 10.1109/JBHI.2024.3381896. Epub 2025 Mar 6.
Molecular property prediction is an important task in drug discovery. However, experimental data for many drug molecules are limited, especially for novel molecular structures or rare diseases which affect the accuracy of many deep learning methods that rely on large training datasets. To this end, we propose PG-DERN, a novel few-shot learning model for molecular property prediction. A dual-view encoder is introduced to learn a meaningful molecular representation by integrating information from node and subgraph. Next, a relation graph learning module is proposed to construct a relation graph based on the similarity between molecules, which improves the efficiency of information propagation and the accuracy of property prediction. In addition, we use a MAML-based meta-learning strategy to learn well-initialized meta-parameters. In order to guide the tuning of meta-parameters, a property-guided feature augmentation module is designed to transfer information from similar properties to the novel property to improve the comprehensiveness of the feature representation of molecules with novel property. A series of comparative experiments on four benchmark datasets demonstrate that the proposed PG-DERN outperforms state-of-the-art methods.
分子性质预测是药物发现中的一项重要任务。然而，许多药物分子的实验数据有限，特别是对于新型分子结构或罕见疾病，这会影响许多依赖大型训练数据集的深度学习方法的准确性。为此，我们提出了PG-DERN，一种用于分子性质预测的新型少样本学习模型。引入了双视图编码器，通过整合来自节点和子图的信息来学习有意义的分子表示。接下来，提出了一种关系图学习模块，基于分子之间的相似性构建关系图，提高了信息传播效率和性质预测的准确性。此外，我们使用基于MAML的元学习策略来学习初始化良好的元参数。为了指导元参数的调整，设计了一个性质引导的特征增强模块，将相似性质的信息转移到新性质上，以提高具有新性质分子的特征表示的全面性。在四个基准数据集上进行的一系列对比实验表明，所提出的PG-DERN优于现有方法。
