Dataset for discovering new hypertension small molecules using machine learning-aided computational fragment-based design.

This dataset demonstrates the use of computational fragmentation-based and machine learning-aided drug discovery to generate new lead molecules for the treatment of hypertension. Specifically, the focus is on agents targeting the renin-angiotensin-aldosterone system (RAAS), commonly classified as Angiotensin-Converting Enzyme Inhibitors (ACEIs) and Angiotensin II Receptor Blockers (ARBs). The preliminary dataset was a target-specific, user-generated fragment library of 63 molecular fragments of the 26 approved ACEI and ARB molecules obtained from the ChEMBL and DrugBank molecular databases. This fragment library provided the primary input dataset to generate the new lead molecules presented in the dataset. The newly generated molecules were screened to check whether they met the criteria for oral drugs and comprised the ACEI or ARB core functional group criterion. Using unsupervised machine learning, the molecules that met the criterion were divided into clusters of drug classes based on their functional group allocation. This process led to three final output datasets, one containing the new ACEI molecules, another for the new ARB molecules, and the last for the new unassigned class molecules. This data can aid in the timely and efficient design of novel antihypertensive drugs. It can also be used in precision hypertension medicine for patients with treatment resistance, non-response or co-morbidities. Although this dataset is specific to antihypertensive agents, the model can be reused with minimal changes to produce new lead molecules for other health conditions.

Burden of depressive disorders in Vietnam from 1990 to 2019: A secondary analysis of the Global Burden of Disease Study 2019.

Depressive disorders are among the leading causes of disability globally. However, information on the burden of depressive disorders in Vietnam is limited. We aimed to analyse the burden of depressive disorders in Vietnam from 1990 to 2019. Using data from the Global Burden of Disease Study 2019, prevalence and disability-adjusted life-years (DALYs) were used as indicators to analyse the burden of depressive disorders by age and sex. In 2019 in Vietnam, depressive disorders comprised 2629.1 thousand (95% uncertainty interval (UI): 2233.3-3155.9) estimated cases and 380.6 thousand (95% UI: 258.9-533.8) estimated DALYs. The crude prevalence rate of depressive disorders was higher among females than among males. The DALYs of depressive disorder accounted for a higher percentage of the total all-cause DALYs in the 10-64-year age group than in other age groups. Major depressive disorder was the largest contributor to the burden of depressive disorders. From 1990 to 2019, the crude prevalence and DALY rates per 100 000 population due to depressive disorders increased significantly, whereas age-standardised rates of prevalence and DALYs decreased significantly; the respective average annual percent changes were 0.88% (95% confidence interval: 0.87 to 0.89), 0.68% (0.66 to 0.70), -0.20% (-0.21 to -0.19), and -0.27% (-0.28 to -0.25). Although the age-standardised prevalence rate was lower than that seen globally, depressive disorders were considerable mental health issues in Vietnam. This study will help governments and policymakers to establish appropriate strategies to reduce the burden of these disorders by identifying the priority areas and individuals.