Feature Selection for Alzheimer’s Gene Expression Data Using Modified Binary Particle Swarm Optimization

Abstract

Alzheimer’s Disease (AD) is a neurological disorder that destroys memory and other significant mental functions. One of the most accurate methods to identify the disease-causing genes is to monitor gene expression values in various samples. Selecting significant genes for classification is important in gene expression studies. In this study, the experimental data are taken from the gene expression data of human brain in persons with AD and older control subjects GEO GSE5281 data set. In this work, a new two-step gene selection is applied to filter the noisy and redundant genes, based on the statistical method and heuristic optimization approach. T-statistic (T-test), Signal to Noise Ratio (SNR) and F-test, are used in the first step of the gene selection process. The top ten significant genes selected from the statistical methods are applied to Particle Swarm Optimization (PSO) to obtain the optimal number of features of Alzheimer’s disease. To avoid the stagnation issue in PSO, a modified PSO approach is proposed which finds a new particle position by utilizing the Genetic Algorithm (GA) crossover and mutation operators. The classifiers, Decision tree, Support Vector Machine (SVM), Linear Model, Random Forest and Neural network, are employed in training and testing data to analyse the performance of GA & PSOs. Modified PSO with t-Test in Random forest and Linear model provides 100% accuracy for the test dataset of GSE5281 with optimum number of genes. The significant genes identified through this research are EGR1, CKMT1B, RPL15, PSMB3, GRK4, COX6A1 and PHIP from the GSE5281 dataset.

KEYWORDS:

• Alzheimer’s disease
• Boruta algorithm
• Feature selection
• Gene selection
• Genetic algorithm
• Modified particle swarm optimization
• Random forest
• Linear model

Additional information

Notes on contributors

Ramya Ramaswamy

Ramya Ramaswamy is currently working as assistant professor in the Department of Computer Science Engineering at Bannari Amman Institute of Technology, Erode, Tamil Nadu, India. She completed her Master of Engineering in computer science engineering (CSE) at Sri Krishna College of Engineering and Technology, Coimbatore, Tamil Nadu, India and Bachelor of Technology in IT at VLBJECT, Coimbatore, Tamil Nadu, India. Her primary research interests include data mining, machine learning, optimization and genetic algorithms.

Premalatha Kandhasamy

Premalatha Kandhasamy is currently working as professor and head in the Department of Computer Science Engineering at Bannari Amman Institute of Technology, Erode, Tamil Nadu, India. She completed her PhD in CSE at Anna University, Chennai, India. She did her Master of Engineering in CSE and Bachelor of Engineering in CSE at Bharathiar University, Coimbatore, Tamil Nadu, India. Her research interests include data mining, networking, information retrieval and soft computing. Email: [email protected]

Swathypriyadharsini Palaniswamy

Swathypriyadharsini Palaniswamy is currently working as assistant professor in the Department of Computer Science Engineering at Bannari Amman Institute of Technology, Erode, Tamil Nadu, India. She completed her PhD in CSE at Anna University, Chennai, India. She completed her Master of Engineering in computer science engineering (CSE) at Bannari Amman Institute of Technology, Erode, Tamil Nadu, India and Bachelor of Engineering in CSE at Avinashilingam University, Coimbatore, Tamil Nadu, India. Her research interests include data mining, soft computing and artificial intelligence. Email: [email protected]