Department of Electronic Engineering, Tsinghua University, Beijing 100084, China.
Department of Electronic Engineering, Tsinghua University, Beijing 100084, China; Institute for Precision Medicine, Tsinghua University, Beijing 100084, China.
Methods. 2020 Jul 1;179:47-54. doi: 10.1016/j.ymeth.2020.05.014. Epub 2020 Jul 3.
One drug's pharmacological activity may be changed unexpectedly, owing to the concurrent administration of another drug. It is likely to cause unexpected drug-drug interactions (DDIs). Several machine learning approaches have been proposed to predict the occurrence of DDIs. However, existing approaches are almost dependent heavily on various drug-related features, which may incur noisy inductive bias. To alleviate this problem, we investigate the utilization of the end-to-end graph representation learning for the DDI prediction task. We establish a novel DDI prediction method named GCN-BMP (Graph Convolutional Network with Bond-aware Message Propagation) to conduct an accurate prediction for DDIs. Our experiments on two real-world datasets demonstrate that GCN-BMP can achieve higher performance compared to various baseline approaches. Moreover, in the light of the self-contained attention mechanism in our GCN-BMP, we could find the most vital local atoms that conform to domain knowledge with certain interpretability.
一种药物的药理活性可能会因同时使用另一种药物而意外改变。这很可能会导致意想不到的药物相互作用（DDI）。已经提出了几种机器学习方法来预测 DDI 的发生。然而，现有的方法几乎严重依赖于各种药物相关的特征，这可能会产生嘈杂的归纳偏差。为了解决这个问题，我们研究了端到端图表示学习在 DDI 预测任务中的应用。我们建立了一种名为 GCN-BMP（具有键感知消息传播的图卷积网络）的新型 DDI 预测方法，用于进行准确的 DDI 预测。我们在两个真实数据集上的实验表明，GCN-BMP 可以比各种基线方法实现更高的性能。此外，根据我们的 GCN-BMP 中的自包含注意力机制，我们可以找到最符合特定可解释性领域知识的关键局部原子。
