高等学校化学学报

高等学校化学学报 ›› 2005, Vol. 26 ›› Issue (8): 1522.

• 研究论文 • 上一篇    下一篇

基于支持向量学习机方法的抗真菌药物活性预测

李泽荣1, 陈仕伟2, 谈宁馨2, 陈宇综3, 李象远2   

  1. 1. 四川大学化学学院,
    2. 四川大学化工学院, 成都610065;
    3. 新加坡国立大学计算科学系, 新加坡117543
  • 收稿日期:2004-07-07 出版日期:2005-08-10 发布日期:2005-08-10
  • 通讯作者: 李象远(1958年出生),男,博士,教授,博士生导师,从事理论和计算化学研究.E-mail:xyli@scu.edu.cn E-mail:xyli@scu.edu.cn
  • 基金资助:

    国家自然科学基金(批准号:20473054)资助.

Prediction of Antifungal Activity with Support Vector Machine

LI Ze-Rong1, CHEN Shi-Wei2, TAN Ning-Xin2, CHEN Yu-Zong3, LI Xiang-Yuan2   

  1. 1. College of Chemistry,
    2. College of Chemical Engineering, Sichuan University, Chengdu 610065, China;
    3. Department of Computational Science, National University of Singapore, Singapore 117543
  • Received:2004-07-07 Online:2005-08-10 Published:2005-08-10

PDF (PC)

被引次数

8

摘要： 为了预测分子的抗真菌活性,计算了表征分子的电子、拓扑、几何结构和分子形状等特征的67个分子描述符,并用于支持向量学习机对分子抗真菌活性分类模型的建立和活性预测.分别用留一法和五重交叉法对模型进行了验证.在五重交叉验证中,根据分子三维结构的相似性,首先把所研究的94个分子分成若干类,再分别从每一类中随机选择若干个分子组成若干个训练集,剩余的分子构成相应的测试集.结果表明,用上述两种验证方法得到的结果相近,且所建立的模型具有较高的预测性,交叉验证的预测正确率达到84.0%.

关键词: 支持向量学习机, 抗真菌活性, 分子描述符

Abstract: A set of 67 molecular descriptors, including electronic, topological, geometric descriptors and molecular shape indices, were calculated and used to predict the antifungal activity for 94 organic compounds by means of support vector machine method. The model was validated in two ways: leave-one-out and 5-fold cross-validation. In the 5-fold cross-validation, the compounds were divided into several clusters based on their similarities. The training sets were sorted by selecting molecules randomly from each cluster, the rest of the molecules being the test set. It was shown that two validation methods give similar results and our model has a good prediction ability, and about 84% of the compounds can be correctly classified.

Key words: Support vector machine(SVM), Antifungal activity, Molecular descriptors

中图分类号: 

TrendMD: