论文部分内容阅读
脑部淀粉样β多肽(β-amyloid peptide,Aβ)的纤维化沉积是阿尔兹海默症(Alzheimer’s disease,AD)主要病理特征之一。因此,开发Aβ聚集抑制剂对AD治疗具有重要意义。本文采用支持向量机(Support Vector Machine,SVM)方法分别构建Aβ和Aβ_(40)聚集抑制活性分类模型。采用五重交叉验证筛选模型参数,并通过留一法验证模型。结果表明,Aβ和Aβ_(40)聚集抑制剂分类模型对训练集的预测精度分别为98.4%和93.2%,对测试集的预测精度分别为73.3%和75.0%。我们利用预测效果较好的Aβ_(40)聚集抑制剂分类模型从中药化学数据库(Traditional Chinese Medicines Database,TCMD)中筛选出17种具有潜在Aβ抑制活性的中药化合物。经统计分析,含有以上命中化台物最多的中草药植物分别为雷公藤(Tripterygium wilfordii)和猴头菌(Hericium erinaceus)。这为从中药化合物中发现新的AD治疗药物提供了理论指导。
Fibrosis deposition of brain amyloid β polypeptide (Aβ) is one of the major pathological features of Alzheimer’s disease (AD). Therefore, the development of Aβ aggregation inhibitors is of great importance for the treatment of AD. In this paper, Support Vector Machine (SVM) was used to establish the taxonomy of Aβ and Aβ40 aggregation inhibitory activity. The parameters of the model were screened by five-fold cross-validation, and the model was validated by leaving a test. The results showed that the prediction accuracy of the training model was 98.4% and 93.2% respectively for the Aβ and Aβ40 aggregation inhibitor models, and 73.3% and 75.0% for the test set respectively. We selected 17 traditional Chinese medicinal compounds with potential Aβ inhibitory activity from Traditional Chinese Medicines Database (TCMD) using the better prediction model of Aβ40 aggregation inhibitor. According to the statistical analysis, the Chinese herbal plants containing the most of the above hit compounds are Tripterygium wilfordii and Hericium erinaceus. This provides theoretical guidance for discovering new AD therapeutics from traditional Chinese medicine compounds.