Protein-Protein Interaction Extraction Based on Convex Combination Kernel Function

Jianyi Guo,Sichao Wei,Feng Zhou,Peng Chen,Zhengtao Yu,Xin Yan

doi:10.4236/jcc.2013.15002

Abstract

Owing to the effect of classified models was different in Protein-Protein Interaction(PPI) extraction, which was made by different single kernel functions, and only using single kernel function hardly trained the optimal classified model to extract PPI, this paper presents a strategy to find the optimal kernel function from a kernel function set. The strategy is that in the kernel function set which consists of different single kernel functions, endlessly finding the last two kernel functions on the performance in PPI extraction, using their optimal kernel function to replace them, until there is only one kernel function and it’s the final optimal kernel function. Finally, extracting PPI using the classified model made by this kernel function. This paper conducted the PPI extraction experiment on AIMed corpus, the experimental result shows that the optimal convex combination kernel function this paper presents can effectively improve the extraction performance than single kernel function, and it gets the best precision which reaches 65.0 among the similar PPI extraction systems.

Highlights

IntroductionStudies on Protein-Protein Interaction (PPI) extraction mostly employ the machine learning method, it includes the convolution kernel based method [1,2,3] and feature based method [4,5,6,7]
That the presented protein entities exist interaction relation of the article in biomedical field is called ProteinProtein Interaction
Owing to the effect of classified models was different in Protein-Protein Interaction (PPI) extraction, which was made by different single kernel functions, and only using single kernel function hardly trained the optimal classified model to extract PPI, this paper presents a strategy to find the optimal kernel function from a kernel function set

Summary

Introduction

Studies on PPI extraction mostly employ the machine learning method, it includes the convolution kernel based method [1,2,3] and feature based method [4,5,6,7]. The convolution kernel-based method expresses the sentence as string [2], tree [1], graph [3] or other structured ways, and determine the high dimension matrix by counting the number of same substructure in two sentences. What calls for special attention is that in the feature-based method, the high dimension matrix is the only information in getting the classified model by training, so the selection of the kernel function is crucial in PPI extraction. The effect of classified models was different in PPI extraction, which was made by different single different kernel functions, and only using single kernel function hardly trained the optimal classified model to extract PPI

Objectives

Methods

Results

Conclusion