Data-Driven Chemical Domain for Polypharmacology Agents: Focus on Alzheimer’s Disease

Exploratory data domains for Alzheimer's Disease (AD) analysis are inherently complex due to the disease's polyetiological and polypathogenic nature. Addressing this complexity requires a multidisciplinary approach to data exploration. Effective drug discovery and repositioning strategies must account for the diversity of ligand–receptor interactions, aiming to expand the scope of the exploratory domain and identify therapeutic solutions targeting the most prevalent pathological features of AD. Considering the multifactorial characteristics of the disease, we propose a data retrieval and extraction strategy that integrates heterogeneous and relevant information from multiple bioinformatic databases, focusing on the key targets Acetylcholinesterase (AChE), Butyrylcholinesterase (BChE), and Beta-secretase 1 (BACE1). This strategy generates datasets that capture diverse facets of the disease's complexity, enabling comprehensive domain representations. To address the inherent challenges in the investigative process, we leveraged ChEMBL, ZINC, and the Protein Data Bank (PDB), producing an extensive and well-curated dataset that facilitates the analysis of causal relationships and reduces the complexity of AD-related research.

针对阿尔茨海默病（Alzheimer's Disease, AD）分析的探索性数据域，因该疾病兼具多病因与多致病机制的特性而具有固有复杂性。应对这一复杂性需采用多学科方法开展数据探索工作。行之有效的药物发现与重定位策略必须考量配体-受体相互作用的多样性，以期拓展探索性数据域的范围，并识别出针对AD最普遍病理特征的治疗方案。鉴于该疾病具有多因素特征，本研究提出一种数据检索与提取策略，该策略整合了来自多个生物信息学数据库的异质性相关信息，并聚焦于关键靶点：乙酰胆碱酯酶（Acetylcholinesterase, AChE）、丁酰胆碱酯酶（Butyrylcholinesterase, BChE）以及β-分泌酶1（Beta-secretase 1, BACE1）。该策略生成的数据集能够涵盖该疾病复杂性的多个维度，从而实现探索性数据域的全面表征。为应对研究过程中的固有挑战，本研究依托ChEMBL、ZINC以及蛋白质数据银行（Protein Data Bank, PDB），构建了大规模且经过精心审核整理的数据集，该数据集可助力因果关系分析，并降低AD相关研究的复杂性。