ABSTRACT
Introduction: Coronaviruses (CoVs) are naturally found in bats and can occasionally cause infection and transmission in humans and other mammals. Our study aimed to build a deep learning (DL) method to predict the adaptation of bat CoVs to other mammals. Methods: The CoV genome was represented with a method of dinucleotide composition representation (DCR) for the two main viral genes, ORF1ab and Spike. DCR features were first analyzed for their distribution among adaptive hosts and then trained with a DL classifier of convolutional neural networks (CNN) to predict the adaptation of bat CoVs. Results and discussion: The results demonstrated inter-host separation and intra-host clustering of DCR-represented CoVs for six host types: Artiodactyla, Carnivora, Chiroptera, Primates, Rodentia/Lagomorpha, and Suiformes. The DCR-based CNN with five host labels (without Chiroptera) predicted a dominant adaptation of bat CoVs to Artiodactyla hosts, then to Carnivora and Rodentia/Lagomorpha mammals, and later to primates. Moreover, a linear asymptotic adaptation of all CoVs (except Suiformes) from Artiodactyla to Carnivora and Rodentia/Lagomorpha and then to Primates indicates an asymptotic bats-other mammals-human adaptation. Conclusion: Genomic dinucleotides represented as DCR indicate a host-specific separation, and clustering predicts a linear asymptotic adaptation shift of bat CoVs from other mammals to humans via deep learning.
ABSTRACT
Background: The outbreak of the novel coronavirus disease COVID-19 caused panic and psychological stress throughout the World. We investigated the extent of adverse psychological reactions in two medical staff groups in China, and explored the importance of online psychological assistance for them. Methods: A cross-sectional online survey including Hospital Anxiety and Depression Scale (HADS) and Insomnia Severity Index (ISI) was utilized to assess anxiety, depression, and insomnia. Propensity score matching (PSM) was applied to match sex and age between the two groups. Differences in the prevalence of adverse psychological reactions between the two groups were compared by a Chi-square test. A multivariate logistic regression analysis was utilized to search for associated adverse psychological reaction factors of two groups. Results: A total of 2,920 medical staff took part in the survey, including 470 frontline and 2,450 non-frontline medical staff. The risk of the frontline group experiencing anxiety, depression, insomnia-early, insomnia-middle, and insomnia-late were 1.16, 1.28, 1.26, 1.22, 1.28 times those of the non-frontline group after PSM. For frontline medical staff, the spinsterhood state (OR = 1.23, 95% CI: 1.00-1.51; P = 0.05) was a risk factor for anxiety. Bachelor or college degree (OR = 2.23, 95% CI: 1.24-4.02, P = 0.01) and a contact history with COVID-19 patients (OR = 1.62, 95% CI: 1.10-2.40; P = 0.02) were risk factors for insomnia. For non-frontline medical staff, being a woman (OR = 1.49, 95% CI: 1.08-2.06, P = 0.01) was a risk factor for anxiety, whilst being in a middle age group was a protective factor for anxiety (OR = 0.70, 95% CI: 0.50-0.99, P = 0.04) and depression (OR = 0.65, 95% CI: 0.45-0.93, P = 0.02). Being a woman (OR = 1.47, 95% CI: 1.14-1.89, P = 0.003) and working in a COVID-19 unit (OR = 1.31, 95% CI: 1.11-1.54, P = 0.001) were risk factors for insomnia, whilst the spinsterhood state (OR = 0.80, 95% CI: 0.67-0.95; P = 0.01) was a protective factor for insomnia. Online forms of psychological aid were all popular with medical staff. Conclusions: The prevalence of anxiety, depression, and insomnia in frontline medical staff was significantly higher than in the non-frontline group. Appropriate intervention methods should be adopted according to the different influencing factors of the two groups. Online psychological aid was the preferred mechanism for relieving psychological problems.