Abstract
These days, the classification between normal and cancerous tissues and between different types of cancers represents a very important issue. Selecting the little informative number of genes is considered the main challenge in the cancer diagnosis issue. Therefore, Gene selection is usually the preliminary step for solving the cancer classification problems. Bio-inspired metaheuristic optimization algorithms, when used to solve gene selection and classification problems, they demonstrate their effectiveness. Barnacles Mating Optimizer (BMO) algorithm, which imitates the behavior of mating barnacles in nature for solving optimization problems, is considered one of these algorithms. In this paper, Barnacles Mating Optimizer (BMO) algorithm augmented with Support Vector Machines (SVM) called BMO-SVM is proposed for a microarray gene expression profiling in order to select the most predictive and informative genes for cancer classification. Conducting a comparative experimental study among a set of the most common bio-inspired optimization techniques to specify the most effective. A binary microarray dataset (i.e., leukemia1) and a multi-class microarray dataset (i.e., SRBCT, lymphoma, and leukemia2) are used for testing the performance of the proposed model. The experimental results revealed the superiority of the proposed BMO-SVM approach against several well-known meta-heuristic optimization algorithms, such as the Tunicate Swarm Algorithm (TSA), Genetic Algorithm (GA), Particle Swarm Optimization (PSO), and Artificial Bee Colony (ABC). It is worth mentioning that our proposed algorithm achieves a high informational superiority percentage compared to other algorithms.
Highlights
Nowadays, DNA microarray technology is widely used in bioinformatics and machine learning fields [1]
In [22], the Particle Swarm Optimization (PSO) and a Genetic Algorithm (GA) is presented for measuring the classification of high dimensional microarray datasets
EXPERIMENTAL RESULTS AND ANALYSIS The microarray data are divided into training and testing sets by applying 10-fold cross validation technique on these four benchmark datasets (Leukemia [17], small round blue cell tumor (SRBCT) [18], Lymphoma [19], and Leukemia [20]) for calculating the Algorithm 3 Pseudo Code of Our Proposed Approach
Summary
DNA microarray technology is widely used in bioinformatics and machine learning fields [1] This type of technology is collecting information from cells and tissues regarding gene expression differences [1]. Houssein et al.: Hybrid BMO Algorithm With SVM for Gene Selection selecting the optimal number of informative genes represents an NP-hard problem [3]. According to our evaluation results, the BMO algorithm augmented with the SVM classifier outperforms the other algorithms in terms of classification accuracy and the little number of informative and predictive genes. The significant merits of the BMO are the motivation for employing the algorithm to select the most predictive and informative genes from microarray gene expression.
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
