SIOC English
化学学报
高级检索

化学学报 ›› 2006, Vol. 64 ›› Issue (5): 415-422. 上一篇    下一篇

研究论文

基于启发式方法和支持向量机方法预测药物与人血浆蛋白结合率

司宏宗1,2，姚小军1，刘焕香1，王杰1
李加忠1，胡之德*,1，刘满仓1   

  1. (1兰州大学化学化工学院 兰州 730000)
    (2甘肃省疾病预防控制中心 兰州 730020)
  • 投稿日期:2005-07-19 修回日期:2005-11-04 发布日期:2006-03-15
  • 通讯作者: 胡之德

Prediction of Binding Rate of Drug to Human Plasma Protein Based on Heuristic Method and Support Vector Machine

SI Hong-Zong1,2, YAO Xiao-Jun1, LIU Huan-Xiang1, WANG Jie1, LI Jia-Zhong1, HU Zhi-De*,1, LIU Man-Cang1   

  1. (1 Department of Chemistry, Lanzhou University, Lanzhou 730000)
    (2 Center for Disease Control of Gansu Province, Lanzhou 730020)
  • Received:2005-07-19 Revised:2005-11-04 Published:2006-03-15
  • Contact: HU Zhi-De

PDF

1178

被引次数

40

应用启发式方法和支持向量机方法建立了70种药物与血浆蛋白结合率的定量构效关系模型, 研究了分子结构对药物与血浆蛋白结合率的影响. 两种方法均得到了较好的结果, 交互检验的相关系数平方分别为0.80和0.82; 通过对模型的稳定性和预测能力比较, 支持向量机建立的QSAR模型能够更好地预测药物与血浆蛋白结合率.

关键词: 定量构效关系, 血浆蛋白结合率, 支持向量机, 启发式回归方法

The binding rate to human plasma protein for 70 diverse drugs was modeled using the descriptors calculated from the molecular structure along with a quantitative structure-activity relationship (QSAR) technique. The heuristic method (HM) and support vector machine (SVM) were utilized to construct the linear and nonlinear prediction models, leading to a good cross-validation correlation coefficient Rcv2 of 0.80 and 0.82, respectively. By comparison the stability with prediction ability of the models, it was found that support vector machine was a good method for predicting the binding rate of drug to human plasma protein.

Key words: quantitative structure-activity relationship, binding rate to human plasma protein, support vector machine, heuristic method