Data for Machine Learning-aided Computational Fragment-based Design of Small Molecules for Hypertension Treatment

The study sought to develop a machine learning-aided computational drug discovery system to generate new lead drug molecules for hypertension treatment by targeting the renin-angiotensin-aldosterone system (RAAS). The main agents that act on the RAAS are commonly classified as Angiotensin-Converting Enzyme Inhibitors (ACEIs) or Angiotensin II Receptor Blockers (ARBs), therefore, the objective was to generate new lead ACEIs and ARBs to treat hypertension through the RAAS. As a result, we developed a seven (7) phase computational fragment-based drug design system aided by machine learning, which guides the process of using existing hypertension molecules as the basis for discovering new hypertension lead (candidate) molecules. The output of this study was a dataset of newly generated lead Angiotensin-Converting Enzyme Inhibitor (ACEI) and Angiotensin II Receptor Blocker (ARB) molecules. The Input Data folder below contains all the files that were used to generate this dataset, which can be found in the Output Data folder below.本研究旨在开发一种机器学习辅助的计算药物发现系统，以通过靶向肾素-血管紧张素-醛固酮系统（renin-angiotensin-aldosterone system, RAAS），生成用于高血压治疗的新型先导药物分子。 作用于该系统的主要药物通常可归类为血管紧张素转换酶抑制剂（Angiotensin-Converting Enzyme Inhibitors, ACEIs）或血管紧张素II受体拮抗剂（Angiotensin II Receptor Blockers, ARBs），因此本研究的目标为通过靶向RAAS，生成用于治疗高血压的新型先导ACEIs与ARBs。 最终，本研究开发了一套七阶段机器学习辅助的基于片段的计算药物设计系统，该系统以现有高血压治疗分子为依托，指导新型高血压先导（候选）药物分子的发现流程。 本研究的最终产出为一套全新生成的血管紧张素转换酶抑制剂（ACEI, Angiotensin-Converting Enzyme Inhibitor）与血管紧张素II受体拮抗剂（ARB, Angiotensin II Receptor Blocker）先导分子数据集。 下述输入数据文件夹包含了用于生成本数据集的全部文件，而本数据集可于下述输出数据文件夹中获取。