Predicting incidence density of COVID-19 rebound using tree-based machine learning algorithms (preprint)

Introduction: A series of strategies adopted by the Chinese government can indeed control the COVID-19 epidemic, but they can also cause negative impact on people's mental health and economic incomes. How to balance the relationship between epidemic prevention and social development is an urgent topic for current research. Methods: We included 122 rebound events involved 96 cities caused by Delta variant from May 21, 2021 to February 23, 2022 and corresponding 32 social environmental factors. Principal Component Analysis and K-Means were used for dimensionality reduction. Conventional logistic regression model, Random Forest model, and extreme Gradient Boosting model were used to model the factors for incidence density. Results: A total of 96 cities were clustered into six categories. Cities with the number of cases or incidence density above the median are concentrated in cluster 1 and cluster 6. We selected “older”, “urbanratio”, “unemploy”, “serve”, and “air” as the optimal features, and constructed three concise models. The three models showed good discriminatory powers with AUCs of 0.666, 0.795, and 0.747. Conclusion: Based on available public data, high prediction accuracy of the incidence density of COVID‐19 rebound can be achieved by machine learning methods. Developed level of cities may confer the rebound of COVID-19.

CAT, AGTR2, L-SIGN and DC-SIGN are potential receptors for the entry of SARS-CoV-2 into human cells (preprint)

Since December 2019, the COVID-19 caused by SARS-CoV-2 has been widely spread all over the world. It is reported that SARS-CoV-2 infection affects a series of human tissues, including lung, gastrointestinal tract, kidney, etc. ACE2 has been identified as the primary receptor of the SARS-CoV-2 Spike (S) protein. The relatively low expression level of this known receptor in the lungs, which is the predominantly infected organ in COVID-19, indicates that there may be some other co-receptors or alternative receptors of SARS-CoV-2 to work in coordination with ACE2. Here, we identified twenty-one candidate receptors of SARS-CoV-2, including ACE2-interactor proteins and SARS-CoV receptors. Then we investigated the protein expression levels of these twenty-one candidate receptors in different human tissues and found that five of which CAT, MME, L-SIGN, DC-SIGN, and AGTR2 were specifically expressed in SARS-CoV-2 affected tissues. Next, we performed molecular simulations of the above five candidate receptors with SARS-CoV-2 S protein, and found that the binding affinities of CAT, AGTR2, L-SIGN and DC-SIGN to S protein were even higher than ACE2. Interestingly, we also observed that CAT and AGTR2 bound to S protein in different regions with ACE2 conformationally, suggesting that these two proteins are likely capable of the co-receptors of ACE2. Conclusively, we considered that CAT, AGTR2, L-SIGN and DC-SIGN were the potential receptors of SARS-CoV-2. Moreover, AGTR2 and DC-SIGN tend to be highly expressed in the lungs of smokers, which is consistent with clinical phenomena of COVID-19, and further confirmed our conclusion. Besides, we also predicted the binding hot spots for these putative protein-protein interactions, which would help develop drugs against SARS-CoV-2.