Protein-ligand binding affinity prediction with edge awareness and supervised attention.

Accurate prediction of protein-ligand binding affinity is crucial in structure-based drug design but remains some challenges even with recent advances in deep learning: (1) Existing methods neglect the edge information in protein and ligand structure data; (2) current attention mechanisms struggle to capture true binding interactions in the small dataset. Herein, we proposed SEGSA_DTA, a SuperEdge Graph convolution-based and Supervised Attention-based Drug-Target Affinity prediction method, where the super edge graph convolution can comprehensively utilize node and edge information and the multi-supervised attention module can efficiently learn the attention distribution consistent with real protein-ligand interactions. Results on the multiple datasets show that SEGSA_DTA outperforms current state-of-the-art methods. We also applied SEGSA_DTA in repurposing FDA-approved drugs to identify potential coronavirus disease 2019 (COVID-19) treatments. Besides, by using SHapley Additive exPlanations (SHAP), we found that SEGSA_DTA is interpretable and further provides a new quantitative analytical solution for structure-based lead optimization.

The prevalence of adverse reactions among individuals with three-dose COVID-19 vaccination.

BACKGROUND: Considering the adverse reactions to vaccination against coronavirus disease 2019 (COVID-19), some people, particularly the elderly and those with underlying medical conditions, are hesitant to be vaccinated. This study aimed to explore the prevalence of adverse reactions and provide direct evidence of vaccine safety, mainly for the elderly and people with underlying medical conditions, to receive COVID-19 vaccination. METHODS: From 1st March to 30th April 2022, we conducted an online survey of people who had completed three doses of COVID-19 vaccination by convenience sampling. Adverse reaction rates and 95% confidence intervals were calculated. In addition, conditional logistic regression was used to compare the differences in adverse reactions among the elderly and those with underlying medical conditions with the general population. RESULTS: A total of 3339 individuals were included in this study, of which 2335 (69.9%) were female, with an average age of 32.1 ± 11.4 years. The prevalence of adverse reactions after the first dose of inactivated vaccine was 24.6% (23.1-26.2%), 19.2% (17.8-20.7%) for the second dose, and 19.1% (17.7-20.6%) for the booster dose; among individuals using messenger RNA vaccines, the prevalence was 42.7% (32.3-53.6%) for the first dose, 47.2% (36.5-58.1%) for the second dose, and 46.1% (35.4-57.0%) for the booster dose. Compared with the general population, the prevalence of adverse events did not differ in individuals with underlying medical conditions and those aged 60 and above. CONCLUSIONS: For individuals with underlying medical conditions and those aged 60 and above, the prevalence of adverse reactions is similar to that of the general population, which provides a scientific basis regarding vaccination safety for these populations.

A CRISPR-based ultrasensitive assay detects attomolar concentrations of SARS-CoV-2 antibodies in clinical samples.

CRISPR diagnostics are powerful tools for detecting nucleic acids but are generally not deployable for the detection of clinically important proteins. Here, we report an ultrasensitive CRISPR-based antibody detection (UCAD) assay that translates the detection of anti-SARS-CoV-2 antibodies into CRISPR-based nucleic acid detection in a homogeneous solution and is 10,000 times more sensitive than the classic immunoassays. Clinical validation using serum samples collected from the general population (n = 197), demonstrates that UCAD has 100% sensitivity and 98.5% specificity. With ultrahigh sensitivity, UCAD enables the quantitative analysis of serum anti-SARS-CoV-2 levels in vaccinated kidney transplant recipients who are shown to produce "undetectable" anti-SARS-CoV-2 using standard immunoassay. Because of the high sensitivity and simplicity, we anticipate that, upon further clinical validation against large cohorts of clinical samples, UCAD will find wide applications for clinical uses in both centralized laboratories and point-of-care settings.

Acute stress disorder in patients with accidental traumatic fractures: What can we do.

AIM: To evaluate the potential influencing factors of acute stress disorder (ASD) in patients with accidental traumatic fractures to provide evidence for clinical nursing care. DESIGN: A retrospective study. METHODS: Patients with traumatic fractures treated in our hospital from 1 January 2020 to 30 November 2021 were included. The characteristics of ASD and no ASD patients were assessed. RESULTS: A total of 468 patients with traumatic fractures were included, the incidence of ASD was 28.20%. Logistic regression analysis showed that age ≤50 years (OR2.918, 95% CI1.994 ~ 3.421), female (OR2.074, 95% CI1.489 ~ 3.375), AIS-ISS at admission ≥20 (OR3.981, 95% CI2.188 ~ 5.091), VAS at admission≥7 (OR2.804, 95% CI2.027 ~ 3.467), introverted personality (OR1.722, 95%CI1.314 ~ 2.432) and CD-RISC at admission≤60 (OR3.026, 95% CI2.338 ~ 4.769) were the risk factors of ASD in patients with traumatic fractures (all p < .05). CONCLUSIONS: The development of ASD in patients with traumatic fractures is affected by multiple factors. Medical workers should take early and timely management and nursing measures for related risk factors to reduce the occurrence of ASD.

[Meta analysis on the treatment of coronavirus disease 2019 by traditional Chinese and Western medicine].

OBJECTIVE: To evaluate the clinical efficacy and safety of combination of traditional Chinese and Western medicine in the treatment of coronavirus disease 2019 (COVID-19) by Meta analysis. METHODS: The clinical randomized controlled trials (RCT) and cohort studies on the treatment of COVID-19 with combination of Chinese traditional and Western medicine published on CNKI, Wanfang database, VIP database and PubMed were searched by computer from January 2020 to June 2020. Patients in the simple Western medicine treatment group were treated with routine treatment of Western medicine, and the patients in integrated traditional Chinese and Western medicine treatment group were treated with traditional Chinese medicine on the basis of routine treatment of Western medicine. The main outcome was the total effective rate of treatment. The secondary outcome were the antipyretic rate, chest CT recovery rate, lymphocyte count (LYM), C-reactive protein (CRP) level and safety. The Cochrane manual and the Newcastle Ottawa Scale (NOS) were used to evaluate the quality of the literature; the RevMan5.3 software was used to analyze the articles that meets the quality standards, and a funnel chart was drawn to evaluate the total effective publication bias. RESULTS: Thirteen articles were analyzed, including 1 039 COVID-19 patients, 559 in integrated traditional Chinese and Western medicine treatment group and 480 in simple Western medicine treatment group. The results of Meta- analysis showed that compared with the simple Western medicine treatment group, the combination of routine treatment of Western medicine and traditional Chinese medicine Qingfei Paidu decoction, Lianhua Qingwen granule, Shufeng jiedu capsule, Xuebijing injection or Reyanning mixture could significantly improve the total effective rate, antipyretic rate and chest CT recovery rate [total effective rate: odds ratio (OR) = 2.95, 95% confidence interval (95%CI) was 2.10-4.14, P < 0.000 01; antipyretic rate: OR =3.01, 95%CI was 1.64-5.53, P = 0.000 4; chest CT recovery rate: OR = 2.53, 95%CI was 1.83-3.51, P = 0.000 1], increase LYM levels [mean difference (MD) = 0.26, 95%CI was 0.02-0.50, P = 0.03], and reduce of CRP content (MD = -17.68, 95%CI was -33.14 to -2.22, P = 0.02). Based on the funnel chart analysis of 12 articles with total efficiency, the result showed that the funnel chart distribution was not completely symmetrical, indicating that there might be publication bias. CONCLUSIONS: On the basis of routine treatment with Western medicine, combined with traditional Chinese medicine can significantly improve the total effective rate of COVID-19 and improve the laboratory results and clinical symptoms of patients. Compared with the routine treatment of Western medicine alone, the combination of traditional Chinese and Western medicine has better clinical efficacy and safety.

Multicenter analysis and a rapid screening model to predict early novel coronavirus pneumonia using a random forest algorithm.

ABSTRACT: Early determination of coronavirus disease 2019 (COVID-19) pneumonia from numerous suspected cases is critical for the early isolation and treatment of patients.The purpose of the study was to develop and validate a rapid screening model to predict early COVID-19 pneumonia from suspected cases using a random forest algorithm in China.A total of 914 initially suspected COVID-19 pneumonia in multiple centers were prospectively included. The computer-assisted embedding method was used to screen the variables. The random forest algorithm was adopted to build a rapid screening model based on the training set. The screening model was evaluated by the confusion matrix and receiver operating characteristic (ROC) analysis in the validation.The rapid screening model was set up based on 4 epidemiological features, 3 clinical manifestations, decreased white blood cell count and lymphocytes, and imaging changes on chest X-ray or computed tomography. The area under the ROC curve was 0.956, and the model had a sensitivity of 83.82% and a specificity of 89.57%. The confusion matrix revealed that the prospective screening model had an accuracy of 87.0% for predicting early COVID-19 pneumonia.Here, we developed and validated a rapid screening model that could predict early COVID-19 pneumonia with high sensitivity and specificity. The use of this model to screen for COVID-19 pneumonia have epidemiological and clinical significance.

A rapid screening model for early predicting novel coronavirus pneumonia in Zhejiang Province of China: a multicenter study.

Novel coronavirus pneumonia (NCP) has been widely spread in China and several other countries. Early finding of this pneumonia from huge numbers of suspects gives clinicians a big challenge. The aim of the study was to develop a rapid screening model for early predicting NCP in a Zhejiang population, as well as its utility in other areas. A total of 880 participants who were initially suspected of NCP from January 17 to February 19 were included. Potential predictors were selected via stepwise logistic regression analysis. The model was established based on epidemiological features, clinical manifestations, white blood cell count, and pulmonary imaging changes, with the area under receiver operating characteristic (AUROC) curve of 0.920. At a cut-off value of 1.0, the model could determine NCP with a sensitivity of 85% and a specificity of 82.3%. We further developed a simplified model by combining the geographical regions and rounding the coefficients, with the AUROC of 0.909, as well as a model without epidemiological factors with the AUROC of 0.859. The study demonstrated that the screening model was a helpful and cost-effective tool for early predicting NCP and had great clinical significance given the high activity of NCP.