期刊文献+

基于特征选择的HIV-1蛋白酶剪切位点预测

HIV-1 protease cleavage site prediction based on feature selection
下载PDF
导出
摘要 研究HIV-1蛋白酶的剪切特异性是研制蛋白酶抑制剂类药物的基础。针对HIV-1蛋白酶剪切位点预测改进一种新型的过滤器方法,去除特征集中的冗余特征,简化分类器结构。通过融合三种特征获得完备的特征表达并对支持向量机(SVM)进行参数优化从而提高预测性能。结果表明该方法的预测性能优于当前基于特征提取的研究成果,这表明特征选择结合特征融合并且进行SVM参数优化可以有效提高HIV-1蛋白酶剪切位点预测效果,能够为未来开发HIV-1蛋白酶抑制剂提供有用的帮助。 Understanding the specificity of HIV-1 protease is crucial for designing HIV-1 protease inhibitors. A filter feature selection method was improved specially for HIV-1 protease cleavage site prediction, thus the redundant features were eliminated and the classifier was simplified. Three kinds of features were fused to make sure comprehensive feature representation and parameter optimization for Support Vector Machine (SVM) was conducted in order to improve prediction capability. The experiment results show that the method used in this paper gains better performance than the state-of-the-art researches based on feature extraction. This means feature selection combining feature fusion with classifier parameter optimization can effectively improve HIV-1 cleavage site prediction performance. Moreover the work in this paper can provide useful help for HIV-1 protease inhibitor developing in the future.
出处 《计算机应用》 CSCD 北大核心 2014年第A01期133-136,195,共5页 journal of Computer Applications
基金 国家自然科学基金资助项目(61003175)
关键词 降维 模式识别 HIV-1 蛋白酶 特征融合 特征选择 dimensionality reduction pattern recognition HIV-1 protease feature fusion feature selection
  • 相关文献

参考文献19

  • 1BRIK A, WONG C-H. HIV-1 protease: mechanism and drug discovery [J]. Organic & Biomolecular Chemistry, 2003, 1(1): 5-14.
  • 2NANNI L. Comparison among feature extraction methods for HIV-1 protease cleavage site prediction[ J]. Pattern Recognition, 2006, 39 (4): 711-713.
  • 3KAWASHIMA S, POKAROWSKI P, POKAROWSKA M, et al. AAindex: amino acid index database, progress report 2008[ J]. Nu- cleic Acids Research, 2008, 36(S1): 202-205.
  • 4NIU B, LU L, LIU L, et al. HIV - 1 protease cleavage site pre- diction based on amino acid property[ J]. Journal of Computational Chemistry, 2009, 30(1) : 33 -39.
  • 5DU P, LI Y. Prediction of protein submitochondria locations by hybridi- zing pseudo-amino acid composition with various physicochemical fea- tures of segmented sequence[J]. BMC Bioinformatics, 2006, 7: 518.
  • 6NANNI L, LUMINIA. MppS: An ensemble of support vector ma- chine based on multiple physicochemical properties of amino acids [ J]. Neurocomputing, 2006, 69(13/14/15) : 1688 - 1690.
  • 7SARDA D, CHUA G H, LI HUO-BIN, et al. pSLIP: SVM based protein subeellular localization prediction using multiple physieo- chemical properties[J]. BMC Bioinformatics, 2005, 6: 152.
  • 8NANNI L LUMINIA. A new encoding technique for peptide classifica- tion[J]. Expert Systems with Applications, 2011, 38(4): 3185-3191.
  • 9JAIN A K, DUIN R P W, MAO J. Statistical pattern recognition: a review[ J]. IEEE Transactions on Pattern Analysis and Machine In- telligence, 2000, 22(1) : 4 - 37.
  • 10GUYON I, ELISSEEFF A. An introduction to variable and feature selection[ J]. The Journal of Machine Learning Research, 2003, 3: 1157-1182.

相关作者

内容加载中请稍等...

相关机构

内容加载中请稍等...

相关主题

内容加载中请稍等...

浏览历史

内容加载中请稍等...
;
使用帮助 返回顶部