arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2302.08680cs.LG
收藏

在多峰图上使用深度生成模型对多药作用建模并预测药物-药物相互作用

Modeling Polypharmacy and Predicting Drug-Drug Interactions using Deep Generative Models on Multimodal Graphs

FPT Software AI Center(FPT软件人工智能中心);Halıcıoğlu Data Science Institute(哈利哲奥卢数据科学研究所);University of California San Diego(加州大学圣地亚哥分校);University of Chicago(芝加哥大学)

Nhat Khang Ngo, Truong Son Hy, Risi Kondor

摘要:

由当代图形自动编码器模型产生的药物及其靶标的潜在表示已被证明在预测大型网络上的许多类型的节点对相互作用方面是有用的,包括药物-药物,药物-靶标和靶标-靶标相互作用。然而,大多数现有的方法模型要么节点的潜在空间,其中节点分布是刚性的,或者不能有效地捕捉药物之间的相互关系,这些限制阻碍了准确预测药物对相互作用的方法。在本文中,我们提出了变分图自编码器(VGAE)在建模多模态网络上的潜在节点表示的有效性。我们的方法可以为多模态图的每个节点类型产生灵活的潜在空间;嵌入稍后用于预测不同边缘类型下的节点对之间的链接。为了进一步提高模型的性能,我们提出了一种新的方法,连接摩根指纹,捕捉每种药物的分子结构,与他们的潜在嵌入之前,他们的解码阶段的链接预测。我们提出的模型在三个多模态网络上显示了竞争结果:(1)由药物和蛋白质节点组成的多模态图,(2)从DrugBank数据库的一个子集构建的多模态图,涉及不同相互作用类型下的药物节点,以及(3)由药物和细胞系节点组成的多模态图。我们的源代码可在https://github.com/HySonLab/drug-interactions上公开获取。

英文摘要:

Latent representations of drugs and their targets produced by contemporary graph autoencoder models have proved useful in predicting many types of node-pair interactions on large networks, including drug-drug, drug-target, and target-target interactions. However, most existing approaches model either the node's latent spaces in which node distributions are rigid or do not effectively capture the interrelations between drugs; these limitations hinder the methods from accurately predicting drug-pair interactions. In this paper, we present the effectiveness of variational graph autoencoders (VGAE) in modeling latent node representations on multimodal networks. Our approach can produce flexible latent spaces for each node type of the multimodal graph; the embeddings are used later for predicting links among node pairs under different edge types. To further enhance the models' performance, we suggest a new method that concatenates Morgan fingerprints, which capture the molecular structures of each drug, with their latent embeddings before preceding them to the decoding stage for link prediction. Our proposed model shows competitive results on three multimodal networks: (1) a multimodal graph consisting of drug and protein nodes, (2) a multimodal graph constructed from a subset of the DrugBank database involving drug nodes under different interaction types, and (3) a multimodal graph consisting of drug and cell line nodes. Our source code is publicly available at https://github.com/HySonLab/drug-interactions.

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。

↑