DSSGNN-PPI: A Protein-Protein Interactions prediction model based on Double Structure and Sequence graph neural networks.

The process of experimentally confirming complex interaction networks among proteins is time-consuming and laborious. This study aims to address Protein-Protein Interactions (PPIs) prediction based on graph neural networks (GNN). A novel multilevel prediction model for PPIs named DSSGNN-PPI (Double Structure and Sequence GNN for PPIs) is designed. Initially, a distance graph between amino acid residues is constructed. Subsequently, the distance graph is fed into an underlying graph attention network module. This enables us to efficiently learn vector representations that encode the three-dimensional structure of proteins and simultaneously aggregate key local patterns and overall topological information to obtain graph embedding that adequately represent local and global structural features. In addition, the embedding representations that reflect sequence properties are obtained. Two features are fused to construct high-level protein complex networks, which are fed into the designed gated graph attention network to extract complex topological patterns. By combining heterogeneous multi-source information from downstream structure graph and upstream sequence models, the understanding of PPIs is comprehensively enhanced. A series of evaluation results validate the remarkable effectiveness of DSSGNN-PPI framework in enhancing the prediction of multi-type interactions among proteins. The multilevel representation learning and information fusion strategies provide a new effective solution paradigm for structural biology problems. The source code for DSSGNN-PPI has been hosted on GitHub and is available at https://github.com/cstudy1/DSSGNN-PPI.

Effect Analysis of Nurse-Led Cognitive Behavioural Therapy on Patients with Urinary Incontinence after Radical Prostatectomy.

OBJECTIVE: To study the effects of nurse-led cognitive behavioural therapy on anxiety, depression and quality of life in patients with urinary incontinence after radical prostatectomy. METHODS: Patients with urinary incontinence after undergoing radical prostatectomy in our hospital from January 2019 to January 2023 were selected as the research objects. They were divided into the observation and control groups in accordance with whether they received nurse-led cognitive behavioural therapy. The general data of the patients were collected, and the baseline data of the two groups were balanced by propensity score matching. The disease-related knowledge; Urinary catheter indwelling time; Urinary incontinence duration; And scores on the Exercise of Self-Care Agency Scale (ESCA), Hamilton Anxiety Scale (HAMA), Hamilton Depression Scale (HAMD) and Nursing Effect and Health Questionnaire (SF-36) were compared between the two groups after matching. RESULTS: At discharge, the ESCA, SF-36 and disease cognition scores of the observation group were higher than those of the control group (p < 0.05). The HAMA and HAMD scores of the observation group were lower than those of the control group (p < 0.001), and the total effective rate of the observation group (89.83%) was higher than that of the control group (76.27%) (p < 0.05). CONCLUSIONS: In patients with urinary incontinence after radical prostatectomy, the implementation of nurse-led cognitive behavioural therapy can effectively improve self-care and disease cognition abilities, relieve anxiety and depression and improve quality of life.

Effects of alcohol on the composition and metabolism of the intestinal microbiota among people with HIV: a cross-sectional study.

OBJECTIVES: Alcohol consumption is not uncommon among people with HIV (PWH) and may exacerbate HIV-induced intestinal damage, and further lead to dysbiosis and increased intestinal permeability. This study aimed to determine the changes in the faecal microbiota and its association with alcohol consumption in HIV-infected patients. METHODS: A cross-sectional survey was conducted between November 2021 and May 2022, and 93 participants were recruited. To investigate the alterations of alcohol misuse on fecal microbiology in HIV-infected individuals, we performed 16s rDNA gene sequencing on fecal samples from the low to moderate drinking (n=21) and non-drinking (n=72) groups. RESULTS: Comparison between groups using alpha and beta diversity showed that the diversity of stool microbiota in the low to moderate drinkinge group did not differ from that of the non-drinking group (all P>0.05). The Linear discriminant Analysis effect size (LEfSe) algorithm was to determine the bacterial taxa associated with alcohol consumption, and the results showed altered fecal bacterial composition in HIV-infected patients who consumed alcohol, with Coprobacillus, Pseudobutyrivibrio and Peptostreptococcaceae enriched, and Pasteurellaceae and Xanthomonadaceae were depleted. In addition, by using the Kyoto Encyclopedia of Genes and Genomes (KEGG) functional microbiome features were also found to be altered in the low to moderate drinking group, showing a reduction in metabolic pathways (P=0.036) and cardiovascular disease pathway (P=0.006). CONCLUSION: Low to moderate drinking will change the composition, metabolism and cardiovascular disease pathway of the gut microbiota of HIV-infected patients.

The prevalence and factors of willingness to accept circumcision among MSM in Maanshan City, China.

To investigate the prevalence of male circumcision and the willingness to undergo male circumcision and influencing factors among MSM in Maanshan City, we conducted a cross-sectional study from June 2016 to December 2019. Respondent-driven sampling (RDS) was used to recruit participants. Influential factors of willingness to accept circumcision were identified by a multivariable logistic regression model. The multivariable logistic regression model revealed that five variables were independent influential factors for willingness to participate. The factors include that used condoms during last anal intercourse (OR = 1.87, 95% CI:1.03-3.41, P = 0.04), sex with female sex partners (OR = 0.499, 95% CI:0.298-0.860, P = 0.012, level of education (junior college: OR = 0.413, 95% CI:0.200-0.854, P = 0.017; bachelor's degree or higher: OR = 0.442, 95% CI:0.208-0.938, P = 0.033), condom use during oral sex in the last six months (OR = 4.20, 95% CI:1.47-12.0, P = 0.007) and level of knowledge of PrEP (OR = 5.09, 95% CI:1.39-18.7, P = 0.014). Given the willingness of MSM to accept circumcision was low in China, establishing a proper understanding of circumcision is essential if it is to be used as a strategy to prevent HIV infection among MSM. Therefore, publicity and education on the operation should be strengthened to increase the willingness to undergo male circumcision.

Research on the estimation and spatial pattern of net tourism carbon emissions in the Yellow River Basin from 2009 to 2019.

Based on panel data and remote sensing data of cities in the Yellow River Basin in China from 2009 to 2019, and using the tourism carbon footprint and tourism carbon carrying capacity models, the tourism carbon emissions, tourism carbon carrying capacity, and net tourism carbon of 65 cities in the Yellow River Basin were calculated. The balance and dynamic changes in carbon emissions and carbon fixation of urban tourism in the past ten years were compared. The results show that (1) tourism carbon emissions in the Yellow River Basin are generally on the rise, along with a distribution characteristic of downstream > middle reaches > upstream with obvious characteristics of urban agglomeration centrality within the basin; (2) the carbon carrying capacity of tourism is higher than that of tourism. The growth of carbon emissions is relatively slow, showing a spatial distribution pattern of high in the west and low in the east, which is mainly related to the geographical environment and economic development of the city; (3) the tourism carbon emissions and tourism carbon carrying capacity in the upstream areas can basically maintain a balance, but in the middle and lower reaches of the region, they show a carbon surplus. There is a significant positive spatial correlation in urban net tourism carbon emissions, and the clusters are mainly H-H and L-L.

Improvement in organic solvent resistance of keratinase BLk by directed evolution.

Keratinase, a vital enzyme in hair degradation, requires enhanced stability for industrial applications in the harsh reaction environment used for keratin hydrolysis. Previous studies have focused on improving keratinase thermostability. In this study, directed evolution was applied to enhance the organic solvent stability of the keratinase BLk from Bacillus licheniformis. Three mutants were identified, exhibiting significant enhanced stability in various solvents, although no similar improvements were observed in terms of thermostability. The identified mutations were located on the enzyme surface. The half-lives of the D41A, A24E, and A24Q mutants increased by 47-, 63-, and 61-fold, respectively, in the presence of 50% (v/v) acetonitrile compared to that of the wild type (WT). Similarly, in the presence of 50% (v/v) acetone, the half-lives of these mutants increased by 22-, 27-, and 27-fold compared to that of the WT enzyme. Notably, the proteolytic activity of all the selected mutants was similar to that of the WT enzyme. Furthermore, molecular dynamics simulation was used to assess the possible reasons for enhanced solvent stability. These results suggest that heightened intramolecular interactions, such as hydrogen bonding and hydrophobic interactions, contribute to improved solvent tolerance. The mutants obtained in this study hold significant potential for industrial applications.

Stenosis Detection and Quantification of Coronary Artery Using Machine Learning and Deep Learning.

The aim of this review is to introduce some applications of artificial intelligence (AI) algorithms for the detection and quantification of coronary stenosis using computed tomography angiography (CTA). The realization of automatic/semi-automatic stenosis detection and quantification includes the following steps: vessel central axis extraction, vessel segmentation, stenosis detection, and quantification. Many new AI techniques, such as machine learning and deep learning, have been widely used in medical image segmentation and stenosis detection. This review also summarizes the recent progress regarding coronary stenosis detection and quantification, and discusses the development trends in this field. Through evaluation and comparison, researchers can better understand the research frontier in related fields, compare the advantages and disadvantages of various methods, and better optimize the new technologies. Machine learning and deep learning will promote the process of automatic detection and quantification of coronary artery stenosis. However, the machine learning and the deep learning methods need a large amount of data, so they also face some challenges because of the lack of professional image annotations (manually add labels by experts).

Towards sustainable transport: quantifying and mitigating pollutant emissions from heavy-duty diesel trucks in Northeast China.

Heavy-duty diesel trucks (HDDTs) have caused serious environmental pollution in China. Accurate estimation of their pollutant emission characteristics is essential to reduce emissions and associated environmental and public health impacts. To achieve sustainable development for transport emissions in Northeast China, we developed localized emission factors and a high-resolution emission inventory of HDDTs, based on on-board test, Guidebook and international vehicle emission (IVE) model. The results show that the total emissions of CO, NO, NO2, and PM from HDDTs in Northeast China in 2020 were 172.2 kt, 531.5 kt, 11.2 kt, and 921.4 t, respectively. In terms of spatial distribution, emissions decreased from the city center to the city fringe. Temporally, the NOx emission variation curves of different types of roads presented a "single-peak" emission characteristic, which was different from the peak of traffic flow. Three emission reduction scenarios are further developed in the paper. Scenario analysis shows that elimination of HDDTs that follow the old China III emission standard and installing tailpipe treatment devices are the most effective pollutant reduction measure. The reduction percentages for CO, NO, NO2, and PM ranged from 62.9 to 83.89%. The results of our study could inform policymakers to devise feasible strategies to reduce vehicle pollution in Northeast China.

Rotating Stomata Measurement Based on Anchor-Free Object Detection and Stomata Conductance Calculation.

Stomata play an essential role in regulating water and carbon dioxide levels in plant leaves, which is important for photosynthesis. Previous deep learning-based plant stomata detection methods are based on horizontal detection. The detection anchor boxes of deep learning model are horizontal, while the angle of stomata is randomized, so it is not possible to calculate stomata traits directly from the detection anchor boxes. Additional processing of image (e.g., rotating image) is required before detecting stomata and calculating stomata traits. This paper proposes a novel approach, named DeepRSD (deep learning-based rotating stomata detection), for detecting rotating stomata and calculating stomata basic traits at the same time. Simultaneously, the stomata conductance loss function is introduced in the DeepRSD model training, which improves the efficiency of stomata detection and conductance calculation. The experimental results demonstrate that the DeepRSD model reaches 94.3% recognition accuracy for stomata of maize leaf. The proposed method can help researchers conduct large-scale studies on stomata morphology, structure, and stomata conductance models.

Survival times of HIV/AIDS in different AIDS Diagnostic and Treatment Guidelines from 2006 to 2020 in Liuzhou, China.

BACKGROUND: To compare the survival rates of four timing of treatment initiation for people living with HIV/AIDS provided in China in 2006, 2011, 2015, and 2018, and to investigate the factors impacting survival time. METHODS: A people living with HIV/AIDS retrospective cohort study was in Liuzhou City from April 2006 to December 2020. The information was obtained from the National Comprehensive AIDS Prevention and Control Information System. Life tables and the Kaplan-Meier method were used to calculate participant survival rates and time. The univariate and multivariate Cox regression models were used to investigate the factors related to survival. RESULTS: 18,543 participants were included in this study. In four periods, the 1-year survival rates were 81%, 87%, 95%, and 95%. The 2-year survival rates were 76%, 85%, 93%, and 94%. The 3-year survival rates were 73%, 84%, 92%, and 94%. Results of multivariate Cox regression showed that sex, age of HIV diagnosis, ethnicity, household registration, occupation, marital status, the timing of treatment, education level, route of HIV transmission, whether receiving antiretroviral therapy (ART), and the count of CD4+T cells at baseline (count of CD4+T cells at HIV diagnosis) were factors that are significantly correlated with mortality caused by HIV infection. CONCLUSIONS: With the Guidelines updated from 2006 to 2020, the 1-, 2-, and 3-year survival rates of people living with HIV/AIDS in four periods tended to increase. The timing of treatment initiation of the updated edition of the AIDS Diagnostic and Treatment Guidelines (Guidelines) significantly prolonged the survival time of people living with HIV/AIDS.

Medical applications of generative adversarial network: a visualization analysis.

BACKGROUND: Deep learning (DL) is one of the latest approaches to artificial intelligence. As an unsupervised DL method, a generative adversarial network (GAN) can be used to synthesize new data. PURPOSE: To explore GAN applications in medicine and point out the significance of its existence for clinical medical research, as well as to provide a visual bibliometric analysis of GAN applications in the medical field in combination with the scientometric software Citespace and statistical analysis methods. MATERIAL AND METHODS: PubMed, MEDLINE, Web of Science, and Google Scholar were searched to identify studies of GAN in medical applications between 2017 and 2022. This study was performed and reported according to the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guidelines. Citespace was used to analyze the number of publications, authors, institutions, and keywords of articles related to GAN in medical applications. RESULTS: The applications of GAN in medicine are not limited to medical image processing, but will also penetrate wider and more complex fields, or may be applied to clinical medicine. Eligibility criteria were the full texts of peer-reviewed journals reporting the application of GANs in medicine. Research selections included material published in English between 1 January 2017 and 1 December 2022. CONCLUSION: GAN has been fully applied to the medical field and will be more deeply and widely used in clinical medicine, especially in the field of privacy protection and medical diagnosis. However, clinical applications of GAN require consideration of ethical and legal issues. GAN-based applications should be well validated by expert radiologists.

Metabolic Signature of Healthy Lifestyle and Risk of Rheumatoid Arthritis: Observational and Mendelian Randomization Study.

BACKGROUND: Although substantial evidence reveals that healthy lifestyle behaviors are associated with a lower risk of rheumatoid arthritis (RA), the underlying metabolic mechanisms remain unclear. OBJECTIVES: This study aimed to identify the metabolic signature reflecting a healthy lifestyle and investigate its observational and genetic linkage with RA risk. METHODS: This study included 87,258 UK Biobank participants (557 cases with incident RA) aged 37-73 y with complete lifestyle, genotyping, and nuclear magnetic resonance (NMR) metabolomics data. A healthy lifestyle was assessed based on 5 factors: healthy diet, regular exercise, not smoking, moderate alcohol consumption, and normal body mass index. The metabolic signature was developed by summing the selected metabolites' concentrations weighted by the coefficients using elastic net regression. We used the multivariate Cox model to assess the associations between metabolic signatures and RA risk, and examined the mediating role of the metabolic signature in the impact of a healthy lifestyle on RA. We performed genome-wide association analysis (GWAS) to obtain genetic variants associated with the metabolic signature and then conducted Mendelian randomization (MR) analyses to detect causality. RESULTS: The metabolic signature comprised 81 metabolites, robustly correlated with a healthy lifestyle (r = 0.45, P = 4.2 × 10-15). The metabolic signature was inversely associated with RA risk (HR per standard deviation (SD) increment: 0.76; 95% CI: 0.70-0.83), and largely explained the protective effects of healthy lifestyle on RA with 64% (95% CI: 50.4-83.3) mediation proportion. 1- and 2-sample MR analyses also consistently showed the associations of genetically inferred per SD increment in metabolic signature with a reduction in RA risk (HR: 0.84; 95% CI: 0.75-0.94; and P = 0.002 and OR: 0.84; 95% CI: 0.73-0.97; and P = 0.02, respectively). CONCLUSIONS: Our findings implicate that the metabolic signature reflecting healthy lifestyle is a potential causal mediator in the development of RA, highlighting the importance of early lifestyle intervention and metabolic status tracking for precise prevention of RA.

Association analysis of hepatocellular carcinoma-related hub proteins and hub genes.

PURPOSE: Hepatocellular carcinoma (HCC) is one of the most common cancers worldwide. The occurrence and development of HCC are closely related to epigenetic modifications. Epigenetic modifications can regulate gene expression and related functions through DNA methylation. This paper presents an association analysis method of HCC-related hub proteins and hub genes. EXPERIMENTAL DESIGN: Bioinformatics analysis of HCC-related DNA methylation data is carried out to clarify the molecular mechanism of HCC-related genes and to find hub genes (genes with more connections in the network) by constructing in the gene interaction network. This paper proposes an accurate prediction method of protein-protein interaction (PPI) based on deep learning model DeepSG2PPI. The trained DeepSG2PPI model predicts the interaction relationship between the synthetic proteins regulated by HCC-related genes. RESULTS: This paper finds that four genes are the intersection of hub genes and hub proteins. The four genes are: FBL, CCNB2, ALDH18A1, and RPLP0. The association of RPLP0 gene with HCC is a new finding of this study. RPLP0 is expected to become a new biomarker for the treatment, diagnosis, and prognosis of HCC. The four proteins corresponding to the four genes are: ENSP00000221801, ENSP00000288207, ENSP00000360268, and ENSP00000449328. CONCLUSIONS AND CLINICAL RELEVANCE: The association between the hub genes with the hub proteins is analyzed. The mutual verification of the hub genes and the hub proteins can obtain more credible HCC-related genes and proteins, which is helpful for the diagnosis, treatment, and drug development of HCC.

DeepSG2PPI: A Protein-Protein Interaction Prediction Method Based on Deep Learning.

Protein-protein interaction (PPI) plays an important role in almost all life activities. Many protein interaction sites have been confirmed by biological experiments, but these PPI site identification methods are time-consuming and expensive. In this study, a deep learning-based PPI prediction method, named DeepSG2PPI, is developed. First, the protein sequence information is retrieved and the local context information of each amino acid residue is calculated. A two-dimensional convolutional neural network (2D-CNN) model is employed to extract features from a two-channel coding structure, in which an attention mechanism is embedded to assign higher weights to key features. Second, the global statistical information of each amino acid residue and the relationship graph between the protein and GO (Gene Ontology) function annotation are built, and the graph embedding vector is constructed to represent the biological features of the protein. Finally, a 2D-CNN model and two 1D-CNN models are combined for PPI prediction. The comparison analysis with existing algorithms shows that the DeepSG2PPI method has better performance. It provides more accurate and effective PPI site prediction, which will be helpful in reducing the cost and failure rate of biological experiments.

Student-centered case-based teaching and online-offline case discussion in postgraduate courses of computer science.

This study explores a student-centered teaching method in postgraduate courses. Teacher-centered classroom teaching cannot fully stimulate learning initiative and enthusiasm of students. Student-centered means that students actively learn and construct knowledge by participating in teaching activities. This study presents a student-centered online-offline hybrid teaching method, which adopts student-centered case-based teaching and online-offline case discussion in the postgraduate courses of computer science. The latest engineering cases are integrated into teaching and a case library is constructed. Taking the digital image processing course as an example, student-centered teaching allows students to choose what to learn and how to learn. Case-based teaching makes students better understand the application of theory of knowledge. It can introduce multiple perspectives, promote understanding and reflection on problems, and help students develop higher-level thinking, analysis, and synthesis skills. This study explores online-offline case discussion method in the student-centered teaching and proposes the principles of case design of postgraduate courses. Revised Bloom's taxonomy is used for teaching assessment. The actual teaching effect shows that student-centered case-based teaching and online-offline case discussion have achieved better teaching effect.

RESEARCH PROGRESS OF DEEP LEARNING IN LOW-DOSE CT IMAGE DENOISING.

Low-dose computed tomography (CT) will increase noise and artefacts while reducing the radiation dose, which will adversely affect the diagnosis of radiologists. Low-dose CT image denoising is a challenging task. There are essential differences between the traditional methods and the deep learning-based methods. This paper discusses the denoising approaches of low-dose CT image via deep learning. Deep learning-based methods have achieved relatively ideal denoising effects in both subjective visual quality and quantitative objective metrics. This paper focuses on three state-of-the-art deep learning-based image denoising methods, in addition, four traditional methods are used as the control group to compare the denoising effect. Comprehensive experiments show that the deep learning-based methods are superior to the traditional methods in low-dose CT images denoising.

An HIV stochastic model with cell-to-cell infection, B-cell immune response and distributed delay.

In this study, a delayed HIV stochastic model with virus-to-cell infection, cell-to-cell transmission and B-cell immune response is proposed. We first transform the stochastic differential equation with distributed delay into a high-dimensional degenerate stochastic differential equation, and then theoretically analyze the dynamic behaviour of the degenerate model. The unique global solution of the model is given by rigorous analysis. By formulating suitable Lyapunov functions, the existence of the stationary Markov process is obtained if the stochastic B-cell-activated reproduction number is greater than one. We also use the law of large numbers theorem and the spectral radius analysis method to deduce that the virus can be cleared if the stochastic B-cell-inactivated reproduction number is less than one. Through uncertainty and sensitivity analysis, we obtain key parameters that determine the value of the stochastic B-cell-activated reproduction number. Numerically, we examine that low level noise can maintain the number of the virus and B-cell populations at a certain range, while high level noise is helpful for the elimination of the virus. Furthermore, the effect of the cell-to-cell infection on model behaviour, and the influence of the key parameters on the size of the stochastic B-cell-activated reproduction number are also investigated.

Anlotinib reduces the suppressive capacity of monocytic myeloid-derived suppressor cells and potentiates the immune microenvironment normalization window in a mouse lung cancer model.

By exploring the effects of an antiangiogenic small molecule drug named anlotinib on the levels of myeloid-derived suppressor cells (MDSCs) in a mouse xenograft model of lung cancer, the role of anti-angiogenesis in remodeling the immune microenvironment was discussed. In addition, the impact of anlotinib on the normalization of the immune microenvironment and time window was examined, providing a theoretical basis for the optimization of clinical strategies applying anlotinib combined with PD-1 inhibitors. On the basis of the LLC mouse xenograft model, MDSCs and MDSCs + immune microenvironment were examined in tissues, respectively, according to different samples. The former observation included the control (group A) and anlotinib monotherapy (group B) groups; the latter also included the control (group C) and anlotinib monotherapy (group D) groups. The levels of MDSCs in peripheral blood at different time points were analyzed by flow cytometry, and the levels of MDSCs in tissue samples at different time points were evaluated by immunofluorescence and immunohistochemistry. The volumes of subcutaneous xenografts were significantly smaller in the anlotinib treatment group compared with the control group ( P < 0.005). Flow cytometry showed that compared with the control group, the intratumoral percentages of total MDSCs ( P < 0.01) and mononuclear-MDSCs ( P < 0.05) were significantly decreased on days 3 and 17 after anlotinib treatment in peripheral blood samples; however, there was no significant difference in granulocytic-MDSCs changes between the experimental and control groups. Immunofluorescence showed that the levels of MDSCs in both the experimental and control groups reached the lowest points 10 days after drug administration, and were significantly lower in the experimental group than in the control group ( P < 0.05). Anlotinib reduces the levels of MDSCs in the mouse xenograft model of lung cancer, with the characteristics of time window. This study provides a basis for further exploring strategies for anti-angiogenic treatment combined with immunotherapy in lung cancer based on time-window dosing.

Prevalence and factors associated with late diagnosis among older adults living with HIV in liuzhou, China: 2010-2020.

This paper aimed to quantify and characterize the prevalence and associated factors for late diagnosis in older adults living with human immunodeficiency virus (HIV) in Liuzhou, China, from 2010 to 2020. The characteristics of older adults living with HIV were described separately in time, space and population. Multivariate logistic regression analysis evaluates the factors influencing late diagnosis in HIV-positive adults ≥ 50 years of age. The majority of older adults living with HIV were over 60 years old, male, and with CD4 counts < 200 cells/µl at diagnosis, with most late diagnoses being more likely to report heterosexual transmission. These two factors may potentially provide a positive influence on late diagnosis: older and CD4 counts < 500 cells/µl. In contrast, females and those with homosexual or other transmission provide a negative. These results suggest that late diagnosis of HIV-positive adults ≥ 50 years of age remains a severe and growing epidemiological issue.