Search

In biomedicine, the critical task is to decode Drug–Drug Interactions (DDIs) from complex biomedical texts. The scientific community employs Knowledge Graph Embedding (KGE) methods, enhanced with advanced neural network technologies, including capsule networks. However, existing methodologies primarily focus on the structural details of individual entities or relations within Biomedical Knowledge Graphs (BioKGs), overlooking the overall structural context of BioKGs, molecular structures, positional features of drug pairs, and their critical Relational Mapping Properties. To tackle the challenges identified, this study presents HSTrHouse an innovative hierarchical self-attention BioKGs embedding framework. This architecture integrates self-attention mechanisms with advanced neural network technologies, including Convolutional Neural Network (CNN) and Graph Neural Network (GNN), for enhanced computational modeling in biomedical contexts. The model bifurcates the BioKGs into entity and relation layers for structural analysis. It employs self-attention across these layers, utilizing PubMedBERT and CNN for position feature extraction, and a GNN for drug pair molecular structure analysis. Then, we connect the position and molecular structure features to integrate them into the self-attention calculation of entity and relation. After that, the output of the self-attention layer is combined with the connected vectors of the position feature and molecular structure feature to obtain the final representation vector, and finally, to model the Relational Mapping Properties (RMPs), the representation vector is embedded into the complex vector space using Householder projections to obtain the BioKGs model. The paper validates HSTrHouse's efficacy by comparing it with advanced models on three standard BioKGs for DDIs research. [ABSTRACT FROM AUTHOR]

Background: Following China's strategy of developing applied and compound social talents, vocational undergraduates are surging rapidly, and it is essential to understand the causes of their depression to effectively prevent and intervene in schools. Objective: We aimed to investigate the relationship between negative life events (NLEs) and depression among vocational undergraduates in China, along with the mediating role of loneliness and the moderating role of socioeconomic status (SES). Methods: A convenience sample survey was conducted at a vocational education university (N = 1487), and analyzed using partial least squares structural equation modeling. Results: Findings showed that NLEs directly predicted depression (β = 0.399, 95% CI [0.339, 0.452], p < 0.001) among vocational undergraduates. Furthermore, this relationship was partially mediated by loneliness (β = 0.182, 95% CI [0.145, 221], p < 0.001); SES moderated the link between NLEs and depression (β = 0.051, 95% CI [0.004, 092], p < 0.05), but not between NLEs and loneliness (p > 0.05). Conclusions: The current study highlights the impact of NLEs on depression among vocational undergraduates, indicating the importance of addressing NLEs and consequent feelings of loneliness to promote mental health. In addition, the moderating role of SES underscores the necessity of targeted interventions to mitigate the impact of NLEs on depression. The present study contributes to our understanding of the unique characteristics of depression in vocational undergraduates and has practical implications for psychological support services. Moreover, it probably has broader implications for addressing mental health challenges in global education settings for vocational undergraduates. [ABSTRACT FROM AUTHOR]

The prevalence of depression among adolescents is increasing, which can hinder their healthy development and is intricately linked to the intolerance of uncertainty (IU). IU involves both prospective anxiety and inhibitory anxiety. However, the precise relationship between depressive symptoms and these two components of IU remains unclear, particularly when considering the specific context of rural adolescents in China. A total of 1488 adolescents (male, 848; Meanage = 20, SDage = 1.51, age range from 16 to 24) in China were recruited and divided into urban adolescents (N = 439) and rural adolescents (N = 1049) groups. The Patient Health Questionnaire-9 and Intolerance of Uncertainty Scale-12 were utilized to measure depression and IU. The symptom network approach and the flow network approach were employed. The prevalence of depression was significantly higher (χ2 = 4.09, p = 0.04) among rural adolescents (N = 419, 40.1%) than urban adolescents (N = 152, 34.8%). The node strength of "motor" demonstrated some discrepancy between rural and urban adolescents, while there was no notable disparity in the global strength and structure of the network between the two groups. However, rural adolescents exhibited a significantly higher global strength in the flow network (including depression and IU) than their urban counterparts. In the flow networks of rural adolescents, "guilt" was directly associated with prospective and inhibitory anxiety. These findings highlight the urgent need for interventions that enhance the ability of rural adolescents to cope with uncertainty and prevent their depressive symptoms more effectively. [ABSTRACT FROM AUTHOR]

Collaborative promotion of carbon emission reduction has become one of the most significant strategies for China to realize the dual-carbon goal. The purpose of this study is to utilize "relational data" to investigate overall and regional building carbon emission reduction networks based on the coordination of equity and efficiency. Specifically, the difference in importance between equity and efficiency principles is measured by an improved Markov chain. The spatial correlation network is constructed under the principle of coordinating equity and efficiency, and the network is analyzed using the modified gravity model and social network analysis. The results indicate that (1) the long-term "low-efficiency" problem of building carbon emissions is more serious than the long-term "low-equity" problem, and (2) the efficiency principle should be given greater weight in calculating carbon emission reduction potential. (3) The strength of network spatial association is increasing, and the spillover effect is significant, but the network form remains unstable. (4) The network is significantly impacted by geographic proximity, environmental regulations, energy consumption intensity, and the development level of the construction industry. The main achievement will assist developing countries in promoting sustainable development and collaborative carbon emission reduction in the construction sector. [ABSTRACT FROM AUTHOR]

As a major province of energy consumption and carbon emission, Jiangsu Province is also a major province of the construction industry, which is a key region and potential area for carbon emission reduction in China. The research and prediction of carbon emission in the construction industry is of great significance for the development of low-carbon policies in the construction industry of other cities. The purpose of this paper is to study the influencing factors of the whole life cycle carbon emissions of buildings in Jiangsu Province, and to predict the carbon emissions of buildings in Jiangsu Province based on the main influencing factors. This paper uses the energy balance sheet splitting method, STIRPAT model, gray correlation method and GA-BP neural network model to study and predict the carbon emissions of construction industry in Jiangsu Province. The research results show that the resident population, urbanization rate, steel production, average distance of road transportation, and labor productivity of construction enterprises have a catalytic effect on construction carbon emissions; GDP per capita and added value of tertiary industry have a suppressive effect; construction carbon emissions reached the historical peak in 2012; the prediction results show that the future construction carbon emissions in Jiangsu province generally show a decreasing trend. The research results of this paper provide a possibility to refine the study of construction carbon emission, and also provide a basis and guidance for subsequent research on construction carbon emission. [ABSTRACT FROM AUTHOR]

A variable-exponent taper equation was developed for Chinese fir (Cunninghamia lanceolate (Lamb.) Hook.) trees grown in southern China. Thirty taper equations from different groups of models (single, segmented, or variable-exponent taper equation) were compared to find the excellent basic model with S-plus software. The lowest Akaike information criteria (AIC), Bayesian information criteria (BIC), and -2loglikelihood (-2LL) was chosen to determine the best combination of random parameters. Single taper models were found having the lowest precision, and the variable-exponent taper equations had higher precision than the segmented taper equations. Four variable-exponent taper models that developed by Zeng and Liao, Bi, Kozak, Sharma, and Zhang respectively, were selected as basic model and had no difference in fit statistics between them. Compared with the model without seldom parameter, the nonlinear mixed-effects (NLME) model improves the fitting performance. The plot-level NLME model was found not to remove the residual autocorrelation. The tree-level and two-level NLME model had better simulation accuracy than the plot-level NLME model, and there were no significant differences between the tree-level and two-level NLME model. Variable-exponent taper model developed by Kozak showed the best performance while considering two-level or tree-level NLME model, and produced better predictions for medium stems compared to lower and upper stems. [ABSTRACT FROM AUTHOR]