物理化学学报 >> 2007, Vol. 23 >> Issue (02): 198-205.doi: 10.1016/S1872-1508(07)60016-3

研究论文 上一篇    下一篇

抗原肽与MHC分子相互作用的QSAR模型研究

宋哲;刘涛;刘伟;朱鸣华;王晓钢   

  1. 大连理工大学物理系,辽宁 大连 116023;大连理工大学高科技研究院, 辽宁 大连 116023
  • 收稿日期:2006-07-12 修回日期:2006-09-14 发布日期:2007-02-01
  • 通讯作者: 刘涛;王晓钢 E-mail:jchjys@dlut.edu.cn

The QSAR Model Study of Interaction Between Peptides and MHC molecules

SONG Zhe;LIU Tao;LIU Wei;ZHU Ming-Hua;WANG Xiao-Gang   

  1. Department of Physics, College of Advanced Science and Technology, Dalian University of Technology, Dalian 116023, Liaoning Province, P. R. China
  • Received:2006-07-12 Revised:2006-09-14 Published:2007-02-01
  • Contact: LIU Wei; WANG Xiao-Gang E-mail:jchjys@dlut.edu.cn

摘要: 分别采用氨基酸序列及氨基酸结构描述符方法定量研究了短肽-MHC(major histocompatibility complex)分子结合亲合力的定量构效关系(QSAR)模型, 用这两个模型对短肽与HLA-A*0201分子结合的805个预测样本进行了预测, 预测准确度分别达到66.8%和65.5%. 采用了去除“劣点”方法检验模型的鲁棒性, 结果证明两个模型都具有良好的鲁棒性. 通过改变两个模型的参数, 对氨基酸残基个数为8或10的CTL(cytotoxicy T lymphocyte)表位进行预测.

关键词: CTL表位, 氨基酸结构描述符, 定量构效关系, 偏最小二乘法

Abstract: The binding affinity model of a peptide-major histocompatibility complex (MHC) was studied using the methods of partial least squares (PLS) and amino acid structure descriptors. Using these models, the predictive sets of 805 peptides are predicted for the binding affinity of the HLA-A*0201 complex, and the predictive accuracies of the two models are 66.8% and 65.5%, respectively. To test the robustness of the models, the outliers are eliminated, and it is proved that the robustness of the models is good. This shows that the models using the PLS and amino acid structure descriptors are feasible on predicting of CTL (cytotoxicy T lymphocyte) epitopes.

Key words: CTL epitopes, Amino acid structure descriptors, QSAR, Partial least squares method