HIV-1整合酶-LEDGF/p75相互作用抑制剂活性分类模型的构建
首发时间:2024-06-03
摘要:人类免疫缺陷病毒(HIV)对全球公共卫生有着深远的影响。获得性免疫缺陷综合症(AIDS)已在全球导致数百万人死亡,且仍有成千上万的人受到感染。本研究通过建立LEDGF/p75与HIV整合酶相互作用的小分子抑制剂活性分类模型,以促进新型LEDGF/p75-IN抑制剂的预测和药物设计。首先对四种分子描述符进行筛选,确定使用拓扑指纹描述符作为模型输入变量。通过四种模型评价指标对基于六种机器学习方法建立得到的分类模型进行对比评估,最终得到随机森林模型是最优模型的结论。
关键词: HIV整合酶 晶状体上皮源性生长因子 定量构效关系 机器学习
For information in English, please click here
Construction of Activity Classification Model for HIV-1 Integrase-LEDGF/p75 Interaction Inhibitors#
Abstract:Human Immunodeficiency Virus (HIV) has far-reaching impacts on global public health. Acquired Immune Deficiency Syndrome (AIDS) has caused millions of deaths globally, with thousands still getting infected. This study aims to facilitate the prediction and design of novel LEDGF/p75-IN inhibitors by establishing an activity classification model for small-molecule inhibitors of the LEDGF/p75 and HIV integrase interaction. Four molecular descriptors were initially screened, and the topological fingerprint descriptor was selected as the input variable for the model. The classification models, developed using six machine learning methods, were evaluated based on four model evaluation metrics. Ultimately, the Random Forest model was concluded to be the optimal model.
Keywords: HIV Integrase LEDGF/p75 Quantitative Structure-Activity Relationship (QSAR) Machine Learning
引用
No.****
同行评议
勘误表
HIV-1整合酶-LEDGF/p75相互作用抑制剂活性分类模型的构建
评论
全部评论0/1000