[Chronic Disease Prevention: Present and Future].

Non-communicable diseases (NCDs) have risen to become a major threat to health worldwide. According to the World Health Organization, NCDs accounted for 68% of all global mortality in 2014, with over 40% of NCD-related mortality incidents defined as premature deaths under the age of 70 years. Among the top-10 causes of death named by the Taiwan Ministry of Health and Welfare in 2017, 28% were cancers, 22.3% were cardiovascular diseases, 5.7% were diabetes, and 3.6% were chronic obstructive pulmonary diseases. These four major NCDs currently account for nearly 60% of all mortalities in Taiwan and reflect the threat of NCDs to global health. Taiwan's increasingly ageing society faces an increasing risk of NCDs, which threatens the health and wellbeing of Taiwan's population. A survey by the Health Promotion Administration in 2013 found that over 80% of senior citizens in Taiwan are afflicted with one or more NCD and that the presence of a comorbidity further exacerbates the problem of living and coping with NCDs. This article introduces the primary, secondary, and tertiary public health prevention measures related to NCDs in order to help caregivers better understand the importance of reducing the risk factors of NCDs and of screening to promote early detection and treatment. This article further proposes a systemic framework for the future care of NCDs.

Machine learning guided aptamer refinement and discovery.

Aptamers are single-stranded nucleic acid ligands that bind to target molecules with high affinity and specificity. They are typically discovered by searching large libraries for sequences with desirable binding properties. These libraries, however, are practically constrained to a fraction of the theoretical sequence space. Machine learning provides an opportunity to intelligently navigate this space to identify high-performing aptamers. Here, we propose an approach that employs particle display (PD) to partition a library of aptamers by affinity, and uses such data to train machine learning models to predict affinity in silico. Our model predicted high-affinity DNA aptamers from experimental candidates at a rate 11-fold higher than random perturbation and generated novel, high-affinity aptamers at a greater rate than observed by PD alone. Our approach also facilitated the design of truncated aptamers 70% shorter and with higher binding affinity (1.5 nM) than the best experimental candidate. This work demonstrates how combining machine learning and physical approaches can be used to expedite the discovery of better diagnostic and therapeutic agents.