Graph Representation Learning Based on Specific Subgraphs for Biomedical Interaction Prediction.

Discovering the novel associations of biomedical entities is of great significance and can facilitate not only the identification of network biomarkers of disease but also the search for putative drug targets.Graph representation learning (GRL) has incredible potential to efficiently predict the interactions from biomedical networks by modeling the robust representation for each node.> However, the current GRL-based methods learn the representation of nodes by aggregating the features of their neighbors with equal weights.

Risk assessment and analysis of Traditional Chinese Medicine intervention in coronavirus disease.

Objective: To explore the advantages of Traditional Chinese Medicine (TCM) in "prevention" and "control" of coronavirus disease 2019 (COVID-19) pandemic.

Methods: In this paper, we wish to estimate the effect on the virus transmission of scenarios assuming TCM were used to build the first defense line at the very early stage of the spread in Wuhan. We therefore first developed a classic susceptible infected removed (susceptible infected removed, SIR) transmission model based on the national data in China and then updated it to a TCM-SIR model to assess the potential impact of such assumptions, i.