1 Since December 2019, a newly identified coronavirus (2019 novel coronavirus, 2 2019-nCov) is causing outbreak of pneumonia in one of largest cities, Wuhan, in 3 Hubei province of China and has draw significant public health attention. The same as 4 severe acute respiratory syndrome coronavirus (SARS-CoV), 2019-nCov enters into 5 host cells via cell receptor angiotensin converting enzyme II (ACE2). In order to 6 dissect the ACE2-expressing cell composition and proportion and explore a potential 7 route of the 2019-nCov infection in digestive system infection, 4 datasets with 8 single-cell transcriptomes of lung, esophagus, gastric, ileum and colon were analyzed.9

ObjectiveSince December 2019, a newly identified coronavirus (severe acute respiratory syndrome coronavirus (SARS-CoV-2)) has caused outbreaks of pneumonia in Wuhan, China. SARS-CoV-2 enters host cells via cell receptor ACE II (ACE2) and the transmembrane serine protease 2 (TMPRSS2). In order to identify possible prime target cells of SARS-CoV-2 by comprehensive dissection of ACE2 and TMPRSS2 coexpression pattern in different cell types, five datasets with single-cell transcriptomes of lung, oesophagus, gastric mucosa, ileum and colon were analysed.DesignFive datasets were searched, separately integrated and analysed. Violin plot was used to show the distribution of differentially expressed genes for different clusters. The ACE2-expressing and TMPRRSS2-expressing cells were highlighted and dissected to characterise the composition and proportion.ResultsCell types in each dataset were identified by known markers. ACE2 and TMPRSS2 were not only coexpressed in lung AT2 cells and oesophageal upper epithelial and gland cells but also highly expressed in absorptive enterocytes from the ileum and colon. Additionally, among all the coexpressing cells in the normal digestive system and lung, the expression of ACE2 was relatively highly expressed in the ileum and colon.ConclusionThis study provides the evidence of the potential route of SARS-CoV-2 in the digestive system along with the respiratory tract based on single-cell transcriptomic analysis. This finding may have a significant impact on health policy setting regarding the prevention of SARS-CoV-2 infection. Our study also demonstrates a novel method to identify the prime cell types of a virus by the coexpression pattern analysis of single-cell sequencing data.

The coronavirus disease 2019 (COVID-19) breaking out in late December 2019 is gradually being controlled in China, but it is still spreading rapidly in many other countries and regions worldwide. It is urgent to conduct prediction research on the development and spread of the epidemic. In this article, a hybrid artificial-intelligence (AI) model is proposed for COVID-19 prediction. First, as traditional epidemic models treat all individuals with coronavirus as having the same infection rate, an improved susceptible-infected (ISI) model is proposed to estimate the variety of the infection rates for analyzing the transmission laws and development trend. Second, considering the effects of prevention and control measures and the increase of the public's prevention awareness, the natural language processing (NLP) module and the long short-term memory (LSTM) network are embedded into the ISI model to build the hybrid AI model for COVID-19 prediction. The experimental results on the epidemic data of several typical provinces and cities in China show that individuals with coronavirus have a higher infection rate within the third to eighth days after they were infected, which is more in line with the actual transmission laws of the epidemic. Moreover, compared with the traditional epidemic models, the proposed hybrid AI model can significantly reduce the errors of the prediction results and obtain the mean absolute percentage errors (MAPEs) with 0.52%, 0.38%, 0.05%, and 0.86% for the next six days in Wuhan, Beijing, Shanghai, and countrywide, respectively. Index Terms-Coronavirus disease 2019 (COVID-19) prediction, epidemic model, hybrid artificial-intelligence (AI) model, natural language processing (NLP).