Graph Transformer for Drug Response Prediction.

BACKGROUND: Previous models have shown that learning drug features from their graph representation is more efficient than learning from their strings or numeric representations. Furthermore, integrating multi-omics data of cell lines increases the performance of drug response prediction. However, these models have shown drawbacks in extracting drug features from graph representation and incorporating redundancy information from multi-omics data. This paper proposes a deep learning model, GraTransDRP, to better drug representation and reduce information redundancy. First, the Graph transformer was utilized to extract the drug representation more efficiently. Next, Convolutional neural networks were used to learn the mutation, meth, and transcriptomics features. However, the dimension of transcriptomics features was up to 17737. Therefore, KernelPCA was applied to transcriptomics features to reduce the dimension and transform them into a dense presentation before putting them through the CNN model. Finally, drug and omics features were combined to predict a response value by a fully connected network. Experimental results show that our model outperforms some state-of-the-art methods, including GraphDRP and GraOmicDRP.

Prevalence, Awareness, Treatment, and Control of High Blood Pressure: A Population-Based Survey in Thai Nguyen, Vietnam.

BACKGROUND: Cardiovascular disease (CVD) is one of the leading causes of morbidity and mortality in Vietnam and hypertension (HTN) is an important and prevalent risk factor for CVD in the adult Vietnamese population. Despite an increasing prevalence of HTN in this country, information about the awareness, treatment, and control of HTN is limited. The objectives of this study were to describe the prevalence, awareness, treatment, and control of HTN, and factors associated with these endpoints, in residents of a mountainous province in Vietnam. METHODS: Data from 2,368 adults (age≥25 years) participating in a population-based survey conducted in 2011 in Thai Nguyen province were analyzed. All eligible participants completed a structured questionnaire and were examined by community health workers using a standardized protocol. RESULTS: The overall prevalence of HTN in this population was 23%. Older age, male sex, and being overweight were associated with a higher odds of having HTN, while higher educational level was associated with a lower odds of having HTN. Among those with HTN, only 34% were aware of their condition, 43% of those who were aware they had HTN received treatment and, of these, 39% had their HTN controlled. CONCLUSIONS: Nearly one in four adults in Thai Nguyen is hypertensive, but far fewer are aware of this condition and even fewer have their blood pressure adequately controlled. Public health strategies increasing awareness of HTN in the community, as well as improvements in the treatment and control of HTN, remain needed to reduce the prevalence of HTN and related morbidity and mortality.