A hybrid gene selection method based on gene scoring strategy and improved particle swarm optimization

Fei Han,Yu-Wen-Tian Sun,Qiu-Wei Li,Di Tang,Zhun Cheng,Jing Jiang

doi:10.1186/s12859-019-2773-x

Fei Han, Yu-Wen-Tian Sun + Show 4 more

Open Access

https://doi.org/10.1186/s12859-019-2773-x

Copy DOI

Abstract

BackgroundGene selection is one of the critical steps in the course of the classification of microarray data. Since particle swarm optimization has no complicated evolutionary operators and fewer parameters need to be adjusted, it has been used increasingly as an effective technique for gene selection. Since particle swarm optimization is apt to converge to local minima which lead to premature convergence, some particle swarm optimization based gene selection methods may select non-optimal genes with high probability. To select predictive genes with low redundancy as well as not filtering out key genes is still a challenge.ResultsTo obtain predictive genes with lower redundancy as well as overcome the deficiencies of traditional particle swarm optimization based gene selection methods, a hybrid gene selection method based on gene scoring strategy and improved particle swarm optimization is proposed in this paper. To select the genes highly related to out samples’ classes, a gene scoring strategy based on randomization and extreme learning machine is proposed to filter much irrelevant genes. With the third-level gene pool established by multiple filter strategy, an improved particle swarm optimization is proposed to perform gene selection. In the improved particle swarm optimization, to decrease the likelihood of the premature of the swarm the Metropolis criterion of simulated annealing algorithm is introduced to update the particles, and the half of the swarm are reinitialized when the swarm is trapped into local minima.ConclusionsCombining the gene scoring strategy with the improved particle swarm optimization, the new method could select functional gene subsets which are significantly sensitive to the samples’ classes. With the few discriminative genes selected by the proposed method, extreme learning machine and support vector machine classifiers achieve much high prediction accuracy on several public microarray data, which in turn verifies the efficiency and effectiveness of the proposed gene selection method.

Highlights

Gene selection is one of the critical steps in the course of the classification of microarray data
To obtain predictive genes with lower redundancy as well as overcome the deficiencies of the above mentioned gene selection methods, a hybrid gene selection method based on gene scoring strategy and improved particle swarm optimization (PSO) is proposed in this paper
In the improved PSO, to decrease the probability of converging into local minima, the Metropolis criterion of simulated annealing (SA) algorithm is introduced to update the particles, and the half of the swarm are reinitialized when the swarm is trapped into local minima

Summary

Introduction

Gene selection is one of the critical steps in the course of the classification of microarray data [2]. The methods for gene selection are broadly divided into three categories: filter, wrapper and embedded methods [3]. A filter method relies on general characteristics of the training data to select genes without involving any classifier for evaluation. Most filter methods consider each feature separately with ignoring feature dependencies, which may lead to worse classification performance when compared to other types of feature selection methods [4]. In addition to considering feature dependencies, wrapper methods take into account the interaction between feature subset search and model selection. Embedded methods have the advantage that they include the interaction with the classification model, while being far less computationally intensive than wrapper methods [6]

Methods

Results

Discussion

Conclusion