摘要
提出了一种新的基于改进的伪氨基酸组成特征模型与随机森林的蛋白质相互作用预测方法。首先利用基于Geary自相关函数的伪氨基酸组成特征模型,对与蛋白质相互作用相关的氨基酸属性进行评价,然后根据评价结果选择相关的属性整合到基于Minkowski距离的伪氨基酸特征模型中,并使用随机森林作为分类器进行学习和预测,实验结果表明该方法相对于传统方法提高了正确率。
A new prediction method for protein-protein interaction (PPI) was proposed based on an improved pseudo amino acid composition (PseAA) feature model and random forest. A new PseAA feature model based on the Geray autocorrelation function is used to evaluate amino acid properties related to PPI. Then according to the results of evaluation, relevant properties are selected to integrate together by another new PseAA feature model based on the Minkowski function. The random forest is adopted as classifier for learning and prediction. The results obtained in the experiment indicate that this method can improve accuracy.
出处
《山东大学学报(理学版)》
CAS
CSCD
北大核心
2009年第9期17-21,共5页
Journal of Shandong University(Natural Science)
基金
国家自然科学基金资助项目(60573065)
山东省自然科学基金资助项目(Y2007G33)
关键词
蛋白质相互作用
伪氨基酸组成
随机森林
protein-protein interaction
pseudo amino acid composition
random forest