Deep variational graph autoencoders for novel host-directed therapy options against COVID-19
作者：
Highlights：
• Integrate SARS-CoV-2 interaction data with drug–protein and proteinprotein interaction.
• Proposed deep learning model suggests drugs using links in the integrated network.
• The model utilized variational graph autoencoder and node2vec to learn integrated network.
• Results shows excellent levels of accuracy in predicting molecular interfaces.
• The model establishes novel host-directed therapy (HDT) options.
摘要
•Integrate SARS-CoV-2 interaction data with drug–protein and proteinprotein interaction.•Proposed deep learning model suggests drugs using links in the integrated network.•The model utilized variational graph autoencoder and node2vec to learn integrated network.•Results shows excellent levels of accuracy in predicting molecular interfaces.•The model establishes novel host-directed therapy (HDT) options.
论文关键词：COVID-19,Variational graph autoEncoder,Node2Vec,Molecular interaction network,Host directed therapy
论文评审过程：Received 21 August 2021, Revised 22 March 2022, Accepted 2 October 2022, Available online 13 October 2022, Version of Record 20 October 2022.
论文官网地址：https://doi.org/10.1016/j.artmed.2022.102418
