基于改进伪氨基酸组成的蛋白质相互作用预测

J4 ›› 2009, Vol. 44 ›› Issue (9): 17-21.

基于改进伪氨基酸组成的蛋白质相互作用预测

许传轲陈月辉赵亚欧

济南大学信息科学与工程学院, 山东济南 250022

收稿日期:2009-05-20 出版日期:2009-09-16 发布日期:2009-11-05
通讯作者: 陈月辉(1964〓),男,教授,博士,主要研究方向为智能计算与生物信息学.
作者简介:许传轲(1984-),男,硕士,主要研究方向为智能计算与生物信息学.Email:xuchuanke@163.com
基金资助:
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)

Prediction of proteinprotein interaction based on improved pseudo amino acid composition

HU Chuan-Ke, CHEN Ru-Hui, DIAO E-Ou

School of Information Science and Engineering, University of Jinan, Jinan 250022, Shandong, China

Received:2009-05-20 Online:2009-09-16 Published:2009-11-05

摘要/Abstract

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。

关键词: 蛋白质相互作用;伪氨基酸组成;随机森林

Abstract:

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 Geary autocorrelation function is used to evaluate amino acid properties related to PPI. Then accordingto the results of evaluation, relevant properties are selected to integrate together by another new PseAA feature model based on the Minkowski function. The randomforest is adopted as classifier for learning and prediction. The results obtained in the experiment indicate that this method can improve accuracy.

Key words: proteinprotein interaction; pseudo amino acid composition;random forest

中图分类号:

TP181

许传轲陈月辉赵亚欧. 基于改进伪氨基酸组成的蛋白质相互作用预测[J]. J4, 2009, 44(9): 17-21.

HU Chuan-Ke, CHEN Ru-Hui, DIAO E-Ou. Prediction of proteinprotein interaction based on improved pseudo amino acid composition[J]. J4, 2009, 44(9): 17-21.

参考文献

多维度评价

Viewed

Full text

Abstract

Cited

Shared

Discussed