Prediction of Potential miRNA-Disease Associations Based on a Masked Graph Autoencoder.

Biomedical evidence has demonstrated the relevance of microRNA (miRNA) dysregulation in complex human diseases, and determining the relationship between miRNAs and diseases can aid in the early detection and prevention of diseases. Traditional biological experimental methods have the disadvantages of high cost and low efficiency, which are well compensated by computational methods. However, many computational methods have the challenge of excessively focusing on the neighbor relationship, ignoring the structural information of the graph, and belittling the redundant information of the graph structure. This study proposed a computational model based on a graph-masking autoencoder named MGAEMDA. MGAEMDA is an asymmetric framework in which the encoder maps partially observed graphs into latent representations. The decoder reconstructs the masked structural information based on the edge and node levels and combines it with linear matrices to obtain the result. The empirical results on the two datasets reveal that the MGAEMDA model performs better than its counterparts. We also demonstrated the predictive performance of MGAEMDA using a case study of four diseases, and all the top 30 predicted miRNAs were validated in the database, providing further evidence of the excellent performance of the model.

Effects of a temporal self-regulation theory-based intervention on self-management in hemodialysis patients: A randomized controlled trial.

OBJECTIVE: To investigate the effects of a temporal self-regulation theory-based intervention on self-management in hemodialysis patients. METHODS: A randomized controlled trial was carried out in Lanzhou, China. Participants were randomly allocated to either the intervention group (n = 42) or control group (n = 42). The outcomes of self-management level, interdialytic weight gain, serum potassium and serum phosphorus were collected at baseline (T0), 1 month after intervention (T1), and 2 months after follow-up (T2). RESULTS: After intervention and follow-up, the self-management score of the intervention group was significantly higher than that of the control group, while the interdialytic weight gain, serum potassium, and serum phosphorus were significantly lower. The group and time interaction effects revealed that participants in the intervention group exhibited significantly greater improvement in self-management at T1 and T2. Interdialytic weight gain decreased significantly at T2. Serum potassium levels did not differ significantly at T1 or T2. The changes in serum phosphorus were both significant at T1 and T2. CONCLUSION: This study demonstrated that the temporal self-regulation theory-based intervention was effective in improving hemodialysis patients' self-management. PRACTICE IMPLICATIONS: The findings suggest popularizing and applying this intervention in the clinic to maintain the long-term effectiveness of the intervention effect.

DapBCH: a disease association prediction model Based on Cross-species and Heterogeneous graph embedding.

The study of comorbidity can provide new insights into the pathogenesis of the disease and has important economic significance in the clinical evaluation of treatment difficulty, medical expenses, length of stay, and prognosis of the disease. In this paper, we propose a disease association prediction model DapBCH, which constructs a cross-species biological network and applies heterogeneous graph embedding to predict disease association. First, we combine the human disease-gene network, mouse gene-phenotype network, human-mouse homologous gene network, and human protein-protein interaction network to reconstruct a heterogeneous biological network. Second, we apply heterogeneous graph embedding based on meta-path aggregation to generate the feature vector of disease nodes. Finally, we employ link prediction to obtain the similarity of disease pairs. The experimental results indicate that our model is highly competitive in predicting the disease association and is promising for finding potential disease associations.

Spatiotemporal-aware machine learning approaches for dissolved oxygen prediction in coastal waters.

Coastal waters face increasing threats from hypoxia, which can have severe consequences for marine life and fisheries. This study aims to develop a machine learning approach for hypoxia monitoring by investigating the effectiveness of four tree-based models, considering spatiotemporal effects in model prediction, and adopting the SHapley Additive exPlanations (SHAP) approach for model interpretability, using the long-term climate and marine monitoring dataset in Tolo Harbour (Zone 1) and Mirs Bay (Zone 2), Hong Kong. The LightBoost model was found to be the most effective for predicting dissolved oxygen (DO) concentrations using spatiotemporal datasets. Considering spatiotemporal effects improved the model's bottom DO prediction performance (R2 increase 0.30 in Zone1 and 0.68 in Zone 2), although the contributions from temporal and spatial factors varied depending on the complexity of physical and chemical processes. This study focused not only on error estimates but also on model interpretation. Using SHAP, we propose that hypoxia is largely influenced by hydrodynamics, but anthropogenic activities can increase the bias of systems, exacerbating chemical reactions and impacting DO levels. Additionally, the high relative importance of silicate (Zone 1:0.11 and Zone 2: 0.19) in the model suggests that terrestrial sources, particularly submarine groundwater discharge, are important factors influencing coastal hypoxia. This is the first machine learning effort to consider spatiotemporal effects in four dimensions to predict DO concentrations, and we believe it contributes to the development of a forecasting tool for alarming hypoxia, combining real-time data and machine learning models in the near future.

Perceived stress, social support, and insomnia in hemodialysis patients and their family caregivers: an actor-partner interdependence mediation model analysis.

Objectives: Patients' and caregivers' physical and mental health may interact. The theory of dyadic illness management holds that patients and caregivers should be regarded as a whole in health management. Previous studies have found that hemodialysis patients and their family caregivers experience poor sleep quality. Perceived stress and social support have effects on insomnia. However, the dyadic interaction between perceived stress, social support, and insomnia among hemodialysis patients and caregivers is unclear. This study aimed to explore the mediating role of social support in the association between perceived stress and insomnia in hemodialysis patient-caregiver dyads. Methods: A total of 259 hemodialysis patient-caregiver dyads completed the Chinese Perceived Stress Scales (CPSS), the Perceived Social Support Scale (PSSS), and the Athens Insomnia Scale (AIS) in Lanzhou, China, from May 2022 to July 2022. The actor-partner interdependence mediation model analysis was used for data analysis. Results: In the actor effect, there was a significant positive correlation between perceived stress and insomnia in hemodialysis patients (ß = 0.091, p = 0.001) and their family caregivers (ß = 0.588, p < 0.001). Patient's and caregiver's social support played partial mediating roles in the relationship between caregiver's perceived stress and insomnia (ß = 0.135, p < 0.001 and ß = 0.111, p < 0.001). In the partner effect, caregiver's perceived stress was positively connected with patient's insomnia (ß = 0.915, p < 0.001), and the mediating effect of patient's social support on the relationship between caregiver's perceived stress and patient's insomnia was statistically significant (ß = -0.040, p = 0.046). Conclusion: The perceived stress, social support and insomnia of hemodialysis patients and their family caregivers had interactive effects. Effective dyadic-based interventions should be developed to improve hemodialysis patients' and caregivers' sleep quality.

Effects of perceived stress, self-acceptance and social support on insomnia in hemodialysis patients: A cross-sectional study.

OBJECTIVE: The aim of this study was to explore the influence of perceived stress, self-acceptance and social support on insomnia among hemodialysis patients in China. METHODS: A cross-sectional study was conducted in Gansu, China, from May 2022 to July 2022. The Chinese Perceived Stress Scales (CPSS), Athens Insomnia Scale (AIS), Self-acceptance Questionnaire (SAQ), and Perceived Social Support Scale (PSSS) were evaluated in 610 hemodialysis patients. RESULTS: The prevalence of insomnia among hemodialysis patients was 40.7% in this study. Insomnia was positively correlated with perceived stress (r = 0.742, P < 0.01), and negatively correlated with self-acceptance (r = -0.531, P < 0.01) and social support (r = -0.574, P < 0.01). Self-acceptance played a mediating role in perceived stress and insomnia, with the mediating effect accounting for 13.8% of the total effect. Social support played a moderating role in perceived stress and insomnia (ß = -0.008, t = -5.112, P < 0.001). CONCLUSIONS: The results of this study enrich the research on the influencing factors of insomnia in hemodialysis patients and provide theoretical basis and practical guidance for improving the sleep quality of hemodialysis patients.

Unraveling the Linkages between Molecular Abundance and Stable Carbon Isotope Ratio in Dissolved Organic Matter Using Machine Learning.

Dissolved organic matter (DOM) is a complex mixture of molecules that constitutes one of the largest reservoirs of organic matter on Earth. While stable carbon isotope values (δ13C) provide valuable insights into DOM transformations from land to ocean, it remains unclear how individual molecules respond to changes in DOM properties such as δ13C. To address this, we employed Fourier transform ion cyclotron resonance mass spectrometry (FT-ICR MS) to characterize the molecular composition of DOM in 510 samples from the China Coastal Environments, with 320 samples having δ13C measurements. Utilizing a machine learning model based on 5199 molecular formulas, we predicted δ13C values with a mean absolute error (MAE) of 0.30‰ on the training data set, surpassing traditional linear regression methods (MAE 0.85‰). Our findings suggest that degradation processes, microbial activities, and primary production regulate DOM from rivers to the ocean continuum. Additionally, the machine learning model accurately predicted δ13C values in samples without known δ13C values and in other published data sets, reflecting the δ13C trend along the land to ocean continuum. This study demonstrates the potential of machine learning to capture the complex relationships between DOM composition and bulk parameters, particularly with larger learning data sets and increasing molecular research in the future.

Self-management experiences of haemodialysis patients with self-regulatory fatigue: A phenomenological study.

AIM: To understand the real experiences of self-management in haemodialysis patients with self-regulatory fatigue, and to explore the influencing factors and coping strategies for patients with decreased self-management. DESIGN: A qualitative study was carried out using the phenomenological analysis method. METHODS: From 5 January to 25 February, 2022, semi-structured interviews were conducted with 18 haemodialysis patients in Lanzhou, China. Thematic analysis of the data was performed using the NVivo 12 software based on the 7 steps of Colaizzi's method. The study reporting followed the SRQR checklist. RESULTS: Five themes and 13 sub-themes were identified. The main themes were difficulties in fluid restrictions and emotional management, hard to adhere to long-term self-management, uncertainty about self-management, influencing factors are complex and diverse and coping strategies should be further improved. CONCLUSION: This study revealed the difficulties, uncertainty, influencing facts and coping strategies of self-management among haemodialysis patients with self-regulatory fatigue. A targeted program should be developed and implemented according to the characteristics of patients to reduce the level of self-regulatory fatigue and improve self-management. IMPACT: Self-regulatory fatigue has a significant impact on the self-management behaviour of haemodialysis patients. Understanding the real experiences of self-management in haemodialysis patients with self-regulatory fatigue enables medical staff to correctly identify the occurrence of self-regulatory fatigue in time and help patients adopt positive coping strategies to keep effective self-management behaviour. PATIENT OR PUBLIC CONTRIBUTION: Haemodialysis patients who met the inclusion criteria were recruited to participate in the study from a blood purification centre in Lanzhou, China.

Matrix reconstruction with reliable neighbors for predicting potential MiRNA-disease associations.

Numerous experimental studies have indicated that alteration and dysregulation in mircroRNAs (miRNAs) are associated with serious diseases. Identifying disease-related miRNAs is therefore an essential and challenging task in bioinformatics research. Computational methods are an efficient and economical alternative to conventional biomedical studies and can reveal underlying miRNA-disease associations for subsequent experimental confirmation with reasonable confidence. Despite the success of existing computational approaches, most of them only rely on the known miRNA-disease associations to predict associations without adding other data to increase the prediction accuracy, and they are affected by issues of data sparsity. In this paper, we present MRRN, a model that combines matrix reconstruction with node reliability to predict probable miRNA-disease associations. In MRRN, the most reliable neighbors of miRNA and disease are used to update the original miRNA-disease association matrix, which significantly reduces data sparsity. Unknown miRNA-disease associations are reconstructed by aggregating the most reliable first-order neighbors to increase prediction accuracy by representing the local and global structure of the heterogeneous network. Five-fold cross-validation of MRRN produced an area under the curve (AUC) of 0.9355 and area under the precision-recall curve (AUPR) of 0.2646, values that were greater than those produced by comparable models. Two different types of case studies using three diseases were conducted to demonstrate the accuracy of MRRN, and all top 30 predicted miRNAs were verified.

Dynamic and Static Representation Learning Network for Recommendation.

Existing review-based recommendation methods learn a latent representation of user and item from user-generated reviews by a static strategy, which are unable to capture the dynamic evolution of users' interests and the dynamic attraction of items. Here, we propose a dynamic and static representation learning network (DSRLN) to improve the rating prediction accuracy by exploring fine-grained representations of users and items. Specifically, we built DSRLN with a dynamic representation extractor to model the dynamic evolution of users' interests by exploring the inner relations of an interaction sequence, and with a static representation extractor to model the users' intrinsic preferences by learning the semantic coherence and feature strength information from reviews. To identify the different influences of dynamic and static features for different users, a personalized adaptive fusion module was designed using a weighted attention mechanism. Extensive experiments on five real-world datasets from Amazon demonstrated the superiority of the proposed model, and the additional ablation studies verified the effectiveness of the components designed in the DSRLN model.

Exploring potential contributors to endocrine disrupting activities in Taiwan's surface waters using yeast assays and chemical analysis.

Surface waters serve as sinks for anthropogenic contaminants, including naturally occurring hormones and a variety of synthetic endocrine active substances. To investigate the presence of endocrine active contaminants in the aquatic environment in Taiwan, river water and suspended solids were analyzed by yeast assays to examine the distribution of estrogenic, androgenic, and aryl hydrocarbon receptor agonist activities. The results showed that dry-season river samples exhibited strong estrogenic and aryl hydrocarbon receptor agonist activities, but no androgenic activity was detected. Owing to the ubiquitous detection of estrogenic activities in Taiwan's surface waters, samples were further subjected to liquid chromatography-tandem mass spectrometry (LC-MS/MS) analysis for quantification of selected estrogenic compounds. LC-MS/MS results indicated that natural estrogens, such as estrone and 17ß-estradiol were often the most contributing compounds for the bioassay-derived estrogenic activities due to their strong estrogenic potencies and high detection frequencies, whereas high concentrations of bisphenol A and nonylphenol also posed a threat to the aquatic ecosystems in Taiwan. Water samples eliciting strong estrogenic activities were further fractionated using high performance liquid chromatography, and significant estrogenic activities were detected in fractions containing estrone, 17ß-estradiol, 17α-ethynylestradiol, and bisphenol A. Also, the presence of unidentified estrogenic compounds was found in few river water samples. Further identification of unknown endocrine active substances is necessary to better protect the aquatic environment in Taiwan.

Monitoring of xenobiotic ligands for human estrogen receptor and aryl hydrocarbon receptor in industrial wastewater effluents.

Industrial wastewater contains a variety of toxic substances, which may severely contaminate the aquatic environment if discharged without adequate treatment. In this study, effluents from a thin film transistor liquid crystal display wastewater treatment plant and the receiving water were analyzed by bioassays and liquid chromatography-tandem mass spectrometry to investigate the presence of estrogenic compounds, aryl hydrocarbon receptor (AhR) agonists, and genotoxicants. Xenobiotic AhR agonists were frequently detected and, in particular, strong AhR agonist activity and genotoxicity were found in the suspended solids of the aeration tank outflow. The high AhR agonist activity in the final effluent (FE) and the downstream river water suggested that the treatment plant failed to remove the wastewater-related AhR agonists. In contrast, although significant estrogenic potency could be detected in raw wastewater or effluents from different treatment processes, the FE and the receiving river water exhibited no or weak estrogenicity. Instrumental analysis showed that bisphenol A was often detected in water samples. However, the investigated estrogenic compounds could only account for a small portion of the estrogenicity in the collected samples. Therefore, further investigation is necessary to identify the major estrogenic compounds and AhR agonist contaminants in the wastewater effluents.

Occurrence of aryl hydrocarbon receptor agonists and genotoxic compounds in the river systems in Southern Taiwan.

Water and sediment samples from river systems located in Southern Taiwan were investigated for the presence of aryl hydrocarbon receptor (AhR) agonists and genotoxicants by a combination of recombinant cell assays and gas chromatography-mass spectrometry analysis. AhR agonist activity and genotoxic response were frequently detected in samples collected during different seasons. In particular, dry-season water and sediment samples from Erren River showed strong AhR agonist activity (201-1423 ng L(-1) and 1374-5631 ng g(-1) ß-naphthoflavone equivalents) and high genotoxic potential. Although no significant correlation was found between AhR agonist activity and genotoxicity, potential genotoxicants in sample extracts were suggested to be causative agents for yeast growth inhibition in the AhR-responsive reporter gene assay. After high performance liquid chromatography fractionation, AhR agonist candidates were detected in several fractions of Erren River water and sediment extracts, while possible genotoxicants were only found in water extracts. In addition, polycyclic aromatic hydrocarbons, the typical contaminants showing high AhR binding affinity, were only minor contributors to the AhR agonist activity detected in Erren River sediment extracts. Our findings displayed the usefulness of bioassays in evaluating the extent of environmental contamination, which may be helpful in reducing the chances of false-negative results obtained from chemical analysis of conventional contaminants. Further research will be undertaken to identify major candidates for xenobiotic AhR agonists and genotoxicants to better protect the aquatic environments in Taiwan.