Association of Recent SARS-CoV-2 Infection With New-Onset Alcohol Use Disorder, January 2020 Through January 2022.

Importance: The COVID-19 pandemic affects many diseases, including alcohol use disorders (AUDs). As the pandemic evolves, understanding the association of a new diagnosis of AUD with COVID-19 over time is required to mitigate negative consequences. Objective: To examine the association of COVID-19 infection with new diagnosis of AUD over time from January 2020 through January 2022. Design, Setting, and Participants: In this retrospective cohort study of electronic health records of US patients 12 years of age or older, new diagnoses of AUD were compared between patients with COVID-19 and patients with other respiratory infections who had never had COVID-19 by 3-month intervals from January 20, 2020, through January 27, 2022. Exposures: SARS-CoV-2 infection or non-SARS-CoV-2 respiratory infection. Main Outcomes and Measures: New diagnoses of AUD were compared in COVID-19 and propensity score-matched control cohorts by hazard ratios (HRs) and 95% CIs from either 14 days to 3 months or 3 to 6 months after the index event. Results: This study comprised 1 201 082 patients with COVID-19 (56.9% female patients; 65.7% White; mean [SD] age at index, 46.2 [18.9] years) and 1 620 100 patients with other respiratory infections who had never had COVID-19 (60.4% female patients; 71.1% White; mean [SD] age at index, 44.5 [20.6] years). There was a significantly increased risk of a new diagnosis of AUD in the 3 months after COVID-19 was contracted during the first 3 months of the pandemic (block 1) compared with control cohorts (HR, 2.53 [95% CI, 1.82-3.51]), but the risk decreased to nonsignificance in the next 3 time blocks (April 2020 to January 2021). The risk for AUD diagnosis increased after infection in January to April 2021 (HR, 1.30 [95% CI, 1.08-1.56]) and April to July 2021 (HR, 1.80 [95% CI, 1.47-2.21]). The result became nonsignificant again in blocks 7 and 8 (COVID-19 diagnosis between July 2021 and January 2022). A similar temporal pattern was seen for new diagnosis of AUD 3 to 6 months after infection with COVID-19 vs control index events. Conclusions and Relevance: Elevated risk for AUD after COVID-19 infection compared with non-COVID-19 respiratory infections during some time frames may suggest an association of SARS-CoV-2 infection with the pandemic-associated increase in AUD. However, the lack of excess hazard in most time blocks makes it likely that the circumstances surrounding the pandemic and the fear and anxiety they created also were important factors associated with new diagnoses of AUD.

Deep Learning for Novel Antimicrobial Peptide Design.

Antimicrobial resistance is an increasing issue in healthcare as the overuse of antibacterial agents rises during the COVID-19 pandemic. The need for new antibiotics is high, while the arsenal of available agents is decreasing, especially for the treatment of infections by Gram-negative bacteria like Escherichia coli. Antimicrobial peptides (AMPs) are offering a promising route for novel antibiotic development and deep learning techniques can be utilised for successful AMP design. In this study, a long short-term memory (LSTM) generative model and a bidirectional LSTM classification model were constructed to design short novel AMP sequences with potential antibacterial activity against E. coli. Two versions of the generative model and six versions of the classification model were trained and optimised using Bayesian hyperparameter optimisation. These models were used to generate sets of short novel sequences that were classified as antimicrobial or non-antimicrobial. The validation accuracies of the classification models were 81.6-88.9% and the novel AMPs were classified as antimicrobial with accuracies of 70.6-91.7%. Predicted three-dimensional conformations of selected short AMPs exhibited the alpha-helical structure with amphipathic surfaces. This demonstrates that LSTMs are effective tools for generating novel AMPs against targeted bacteria and could be utilised in the search for new antibiotics leads.