Key Laboratory of Green Chemistry and Technology in Ministry of Education, College of Chemistry, Sichuan University, Chengdu 610064, PR China.
Eur J Med Chem. 2010 Mar;45(3):1167-72. doi: 10.1016/j.ejmech.2009.12.038. Epub 2009 Dec 28.
Acetylcholinesterase (AChE) has become an important drug target and its inhibitors have proved useful in the symptomatic treatment of Alzheimer's disease. This work explores several machine learning methods (support vector machine (SVM), k-nearest neighbor (k-NN), and C4.5 decision tree (C4.5 DT)) for predicting AChE inhibitors (AChEIs). A feature selection method is used for improving prediction accuracy and selecting molecular descriptors responsible for distinguishing AChEIs and non-AChEIs. The prediction accuracies are 76.3% approximately 88.0% for AChEIs and 74.3% approximately 79.6% for non-AChEIs based on the three kinds of machine learning methods. This work suggests that machine learning methods such as SVM are facilitating for predicting AChEIs potential of unknown sets of compounds and for exhibiting the molecular descriptors associated with AChEIs.
乙酰胆碱酯酶（AChE）已成为重要的药物靶点，其抑制剂已被证明可用于治疗阿尔茨海默病的症状。本工作探讨了几种机器学习方法（支持向量机（SVM）、k-最近邻（k-NN）和 C4.5 决策树（C4.5 DT））用于预测乙酰胆碱酯酶抑制剂（AChEIs）。使用特征选择方法来提高预测准确性，并选择负责区分 AChEIs 和非 AChEIs 的分子描述符。基于这三种机器学习方法，AChEIs 的预测准确率约为 76.3%至 88.0%，而非 AChEIs 的预测准确率约为 74.3%至 79.6%。本工作表明，机器学习方法（如 SVM）有助于预测未知化合物集的 AChEIs 潜力，并展示与 AChEIs 相关的分子描述符。
