DeepLPI: A Novel Drug Repurposing Model based on Ligand-Protein Interaction Using Deep Learning

Background. Drug repurposing has gained increased attention because it proposes to find effective cures for new diseases from approved drugs to lower development costs and time, and computational prediction of protein-ligand interactions (PLI) can provide accurate and fast drug screening. The shortcomings of existing machine learning-based methods for PLI prediction include 1) using human-selected features leads to loss of information and therefore lower accuracy and 2) using limited 3D structure data for input leads to lower generalizability. Methods. To address the shortcomings, I proposed DeepLPI, a novel deep learning-based model that takes as input the raw sequences of drug molecules and proteins. DeepLPI applied pre-trained embedding models to encode the raw sequences into dense vector representations, which were then fed into 1D-CNN and biLSTM to obtain predictions. BindingDB dataset was used for model training and performance evaluation that is compared with a start-of-the-art method DeepCDA. Conclusion. The high performance of DeepLPI suggests that our model has the potential to identify new COVID-19 drugs when applied to approved drugs. The generalizability of the model also promises applications to diseases in a wider scope.

[Assessment of quality of systematic reviews and Meta-analyses on efficacy and safety of COVID-19 vaccines].

Objective: To evaluate the methodology of the published systematic reviews and Meta-analyses (SR/MA) on efficacy and safety of coronavirus disease 2019 (COVID-19) vaccines. Methods: We conducted a retrieval for literatures published as of December 10, 2021 in English databases (Medline, Embase, Cochrane Library, Web of science) and Chinese databases (CNKI, Wanfang data, VIP, Sinomed). Two reviewers independently screened literatures and extracted data. The methodology of included SR/MA papers was assessed by A MeaSurement Tool to Assess systematic Review-2 (AMSTAR-2) tool in 16 items. Results: A total 22 SR/MA papers were included, in which 3 (13.6%) had low quality and 19 (86.4%) had very low quality. The main problems of these SR/MA included having no definite PICO (Participants, intervention, control and outcome), providing no preliminary research protocol, no list of excluded studies and justify the exclusions, making no evaluation and explanation or discussion of the risk of bias of original studies, no adequate evaluation of publication bias and discuss its likely impact on the results, etc. Conclusion: SR/MA for the efficacy and safety of COVID-19 vaccines had varied methodological deficiencies, further improvements are needed.

Emergency response report of a positive COVID-19 nucleic test case

Background: Eight pm on April 13, 2022,a10:1 mixed test tube was found to be positive in the COVID-19 nucleic acid test site set up outside the hospital. In order to identify the infected case and control the spread of COVID-19 rapidly, we conducted this emergency investigation. Methods: According to the National COVID-19 Control and Prevention Protocol (8th edition), Guideline on Emergency Response to COVID-19 Case Found in Hospital in Shandong Province, and the Emergency Response Plan for COVID-19 in our hospital, information reporting, hospitalblockading, potential COVID- 19 cases tracing, close contact screening, environmental sampling and disinfecting, COVID-19 nucleic acid testing and risk assessment were carried out by our team. Results: A female COVID-19 case aged 50 years was identified. She is aodd-jobber who works in the labour market near the hospital. The virus strain was sequenced as Omicron BA.2. A total of 65 close contacts was controlled in a hotel. The COVID-19 nucleic acid test results for all the staff of hospital, environmental samples were negative. The risk of COVID-19 spread was controlled and the hospital restarted of clinical activities as normal at 8 am on April 14 after blockaded for 12 hours. Inthe following 7 days, the staff of the hospital were tested for COVID-19 nucleic acid twice a day, and the results were negative. Then the testing frequency changed to once a day. Conclusion: Formulating detailed and feasible COVID-19 emergency response plans based on the requirements of the public documents and the actual conditions of the hospital, is useful to improve the efficiency of emergency response to COVID-19 cases and save time for control of COVID-19 spread and restart the clinical activities of hospital. © 2022 Shandong Yinbao Technology Co. Ltd. All Rights Reserved.

A narrative review of tissue-resident memory T cells and their role in immune surveillance and COVID-19.

Most effector T cells will undergo programmed apoptosis after an immune response and some of them may become memory T cells. According to the distribution and functional status, the memory T cells can be divided into effector central memory T cells (TCM), effector memory T cells (TEM) and tissue-resident memory T cells (TRM) cells. TRM cells, including CD4+ TRM and CD8+ TRM cells, colonize various barrier surfaces and are no longer involved in lymphocyte recycling, closely monitored for local perturbations in homeostasis throughout the body as a critical component of the first defense line. When pathogenic microorganisms invade the body, TRM cells can quickly produce a defense response to initiate innate immunity and adaptive immunity by producing cytokines or killer molecules to resist viral and bacterial infections. In addition, TRM cells are also involved in cancer surveillance and play an essential role in maintaining cancer-immune equilibrium. The high frequency of TRM cells in tumor tissues often means favorable survival for patients. The latest research proves that TRM cells also play an important role in vaccine development and pathological features of COVID-19. This article will summarize the biological functions of TRM cells and aims at providing references for further research on their mechanism and for targeting the best treatment of clinical disease.

DASH Live Video Streaming Control Using Actor-Critic Reinforcement Learning Method

With the COVID19 pandemic, video streaming traffic is increasing rapidly. Especially, the live streaming traffic accounts for large amount due to the fact that many events have been switched to the online forms. Therefore, the demand to ensure a high-quality streaming experience is increasing urgently. Since the network condition is expected to fluctuate dynamically, the video streaming needs to be controlled adaptively according to the network condition to provide high quality of experience (QoE) for users. In this paper, a method was proposed to control the live video streaming using the actor-critic reinforcement learning (RL) technique. In this method, the historical video streaming logs such as throughput, buffer size, rebuffering time, latency are taken consideration as the states of RL, then the model is established to map the states to an action such as bitrate decision. In this study, the live streaming simulation is utilized to evaluate the method since the model needs training and the simulation can generate data much faster than real experiment. Experiments were conducted to evaluate the proposed method. Results demonstrate that the total QoE in Bus and Car scenarios show the best performance. The QoE of Tram case shows the lowest due to the low bandwidth. © 2022, ICST Institute for Computer Sciences, Social Informatics and Telecommunications Engineering.

Semi-Supervised Screening of COVID-19 from Positive and Unlabeled Data with Constraint Non-Negative Risk Estimator

With the COVID-19 pandemic bringing about a severe global crisis, our health systems are under tremendous pressure. Automated screening plays a critical role in the fight against this pandemic, and much of the previous work has been very successful in designing effective screening models. However, they would lose effectiveness under the semi-supervised learning environment with only positive and unlabeled (PU) data, which is easy to collect clinically. In this paper, we report our attempt towards achieving semi-supervised screening of COVID-19 from PU data. We propose a new PU learning method called Constraint Non-Negative Positive Unlabeled Learning (cnPU). It suggests the constraint non-negative risk estimator, which is more robust against overfitting than previous PU learning methods when giving limited positive data. It also embodies a new and efficient optimization algorithm that can make the model learn well on positive data and avoid overfitting on unlabeled data. To the best of our knowledge, this is the first work that realizes PU learning of COVID-19. A series of empirical studies show that our algorithm remarkably outperforms state of the art in real datasets of two medical imaging modalities, including X-ray and computed tomography. These advantages endow our algorithm as a robust and useful computer-assisted tool in the semi-supervised screening of COVID-19. © 2021, Springer Nature Switzerland AG.

Infection control in coronavirus disease 2019 wards of Wuhan Huoshenshan Hospital

This paper summarizes the infection control practice in coronavirus disease 2019 (COVID-19) wards of Wuhan Huoshenshan Hospital. By closely focusing on the three key elements of infectious diseases and strictly following the general prevention principles, we implement systematic management, including ward design, personnel management, disinfection measures, protection management, diagnosis and treatment path, clinical specimens, redisinfection of medical equipment and clearance of garbage. Severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) nucleic acid was detected in samples from critical patients and their surrounding environments, so as to indentify the possible contamination path to guide the prevention and control. During the mission, the systematic and meticulous infection control management in the wards effectively controlled cross infections, ensured the effective and safe treatment of COVID-19 patients, with no medical staff infections occurred, providing references for infection control of wards in similar epidemics in the future.

Defining heart disease risk for death in COVID-19 infection.

BACKGROUND: Cardiovascular disease (CVD) was in common in coronavirus disease 2019 (COVID-19) patients and associated with unfavorable outcomes. We aimed to compare the clinical observations and outcomes of severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2)-infected patients with or without CVD. METHODS: Patients with laboratory-confirmed SARS-CoV-2 infection were clinically evaluated at Wuhan Seventh People's Hospital, Wuhan, China, from 23 January to 14 March 2020. Demographic data, laboratory findings, comorbidities, treatments and outcomes were collected and analyzed in COVID-19 patients with and without CVD. RESULTS: Among 596 patients with COVID-19, 215 (36.1%) of them with CVD. Compared with patients without CVD, these patients were significantly older (66 vs. 52 years) and had higher proportion of men (52.5% vs. 43.8%). Complications in the course of disease were more common in patients with CVD, included acute respiratory distress syndrome (22.8% vs. 8.1%), malignant arrhythmias (3.7% vs. 1.0%) including ventricular tachycardia/ventricular fibrillation, acute coagulopathy(7.9% vs. 1.8%) and acute kidney injury (11.6% vs. 3.4%). The rate of glucocorticoid therapy (36.7% vs. 25.5%), Vitamin C (23.3% vs. 11.8%), mechanical ventilation (21.9% vs. 7.6%), intensive care unit admission (12.6% vs. 3.7%) and mortality (16.7% vs. 4.7%) were higher in patients with CVD (both P < 0.05). The multivariable Cox regression models showed that older age (≥65 years old) (HR 3.165, 95% CI 1.722-5.817) and patients with CVD (HR 2.166, 95% CI 1.189-3.948) were independent risk factors for death. CONCLUSIONS: CVD are independent risk factors for COVID-19 patients. COVID-19 patients with CVD were more severe and had higher mortality rate, early intervention and vigilance should be taken.