摘要
为预测埃坡霉素类衍生物的抗癌活性,定义了一套表征分子形状的描述符,即K阶形状参数,并计算了67个表征分子的电子、拓扑和几何结构的分子描述符.描述符经遗传算法筛选,用于建立基于支持向量学习机(SVM)的抗癌活性分类模型;用留一法和5重交叉验证法对SVM模型参数进行了优化.结果表明模型具有较高的预测性且两种方法得到相近结果,交叉验证的预测正确率达80.6%;经筛选后的描述符有30个,其中含有5个K阶形状参数,这些描述符对埃坡霉素类衍生物的抗癌活性的模型建立具有比较重要的作用.
In order to predict the antitumor activities of various epothilone analogues, a set of molecular descriptors, including electronic, topological and geometric descriptors, and molecular shape indices （K-order moment shape indices）, were calculated to characterize the structural and physicochemical properties for 150 compounds. The 30 descriptors selected with genetic algorithm were employed to establish the classification and prediction model of epothilone analogues by using support vector machine（SVM）. This SVM system gives a total prediction accuracy of 83.3% by the leave-one-out method and that of 80.6% by the 5-fold cross-validation method. The present study indicates that K-order moment shape indices are useful for description of configuration isomers, and SVM is a facilitating tool in prediction of antitumor activity of epothilone analogues.
出处
《物理化学学报》
SCIE
CAS
CSCD
北大核心
2006年第4期397-402,共6页
Acta Physico-Chimica Sinica
基金
国家自然科学基金(20572073)资助项目
关键词
支持向量学习机
埃坡霉素
分子描述符
K阶形状参数
Support vector machine, Epothilone, Molecular descriptors, K-order moment shape index
