Potential miRNA–disease associations (MDA) play an important role in the discovery of complex human disease etiology. Therefore, MDA prediction is an attractive research topic in the field of biomedical machine learning. Recently, several models have been proposed for this task, but their performance limited by over-reliance on relevant network information with noisy graph structure connections. However, the application of self-supervised graph structure learning to MDA tasks remains unexplored. Our study is the first to use multi-view self-supervised contrastive learning (MSGCL) for MDA prediction. Specifically, we generated a learner view without association labels of miRNAs and diseases as input, and utilized the known association network to generate an anchor view that provides guiding signals for the learner view. The graph structure was optimized by designing a contrastive loss to maximize the consistency between the anchor and learner views. Our model is similar to a pre-trained model that continuously optimizes upstream tasks for high-quality association graph topology, thereby enhancing the latent representation of association predictions. The experimental results show that our proposed method outperforms state-of-the-art methods by 2.79$\%$ and 3.20$\%$ in area under the receiver operating characteristic curve (AUC) and area under the precision/recall curve (AUPR), respectively.

BackgroundThe aim of our study is to describe the status of induced abortion and contraceptive use in reproductive women and make clear the correlated factors in Guangdong province.MethodA self-administered questionnaire survey was conducted separately in 1839 individuals aged 18–49 and 900 health care providers from Guangdong province. The content of questionnaire was based on status of induced abortion and contraceptive use for the former and problems concerning contraceptive services for the latter. Systematic random sampling was used and data were analyzed using SPSS 19.0. Descriptive statistics and binary logistic regression were used in this study.Results30.61% of participants experienced the induced abortion. The rate of repeated abortion was 19.96% and it was 20.45% in persons under 20 years old. 18.23% of 1839 individuals chose LARC as the main contraceptive method. The females with college degree(Odds ratio, OR = 1.867; 95% confidence intervals 95%CI: 1.175–2.969), technologists(OR = 2.291; 95%CI: 1.063–4.936) and the persons whose monthly income were of between 3000–5000¥(OR = 1.920; 95%CI: 1.204–3.065) were more likely to use LARC. The younger females less than 30 years old and never using PAC services had lower odds of using LARC. The rate of post abortion care performance was merely 12.23%. Age, monthly income, occupation, living conditions and obtaining free contraceptives in time were all strongerly influence factors for the use of post-abortion care(P < 0.01). The satisfaction rate of free contraceptive services was about 57.44%. Variety uniformity, obtaining inconveniently and worrying about the quality were the main reasons. 66.22% of hospitals set up the department of family planning in our study. Highly work intensity(54.67%) and less leadership (40.22%) influenced health care providers to provide family planning services.ConclusionThe abortion rate was high especially in young women. There were many problems affecting contraceptive services which damaged women’reproductive health. Increasing government investment for family planning services, strengthening the construction of the family planning department and performing post abortion care and long-acting reversible contraception by taking relevant steps would be useful measures for improving current contraceptive status.

No abstract

No abstract

No abstract