Gene Expression Data Classification Using Support Vector Machine and Mutual Information-based Gene Selection

Abstract

DNA microarray technology can monitor the expression levels of thousands of genes simultaneously during important biological processes and across collections of related samples. Knowledge gained through microarray data analysis is increasingly important as they are useful for phenotype classification of diseases. This paper presents an effective method for gene classification using Support Vector Machine (SVM). SVM is a supervised learning algorithm capable of solving complex classification problems. Mutual information (MI) between the genes and the class label is used for identifying the informative genes. The selected genes are utilized for training the SVM classifier and the testing ability is evaluated using Leave-one-Out Cross Validation (LOOCV) method. The performance of the proposed approach is evaluated using two cancer microarray datasets. From the simulation study it is observed that the proposed approach reduces the dimension of the input features by identifying the most informative gene subset and improve classification accuracy when compared to other approaches.

Cancer Mediating Genes Recognition using Multilayer Perceptron Model- An Application on Human Leukemia

“…SVM is a one type of machine learning procedure which is differ two classes by maximizing the margin between them [33]. For cancer classification, support vector machines (SVMs) is used to identify important genes [34]. The Lasso (L1) SVM and standard SVM are often considered using quadratic and linear programming procedure.…”

Analisis Pengaruh Kernel Support Vector Machine (SVM) pada Klasifikasi Data Microarray untuk Deteksi Kanker

“…Kekurangan utama dalam DNA microarray yaitu masalah dimensi (curse of dimensionality) [2]. Data DNA microarray ini mengandung jumlah gen yang melebihi jumlah sampel, sehingga diperlukan metode seleksi fitur untuk menentukan gen informatif [4].…”

“…All menggunakan metode Random Forest dan menghasilkan akurasi sebesar 95% [6], serta Devi Arockia et. All menggunakan Mutual Information (MI) sebagai seleksi fitur dan SVM sebagai classifier dengan tingkat akurasi yang dihasilkan yaitu sebesar 97,77% [2]. Berdasarkan rujukan tersebut, dapat terlihat bahwa ANOVA dan SVM merupakan metode dengan tingkat akurasi tertinggi, sehingga diharapkan akurasi yang dihasilkan pada pengujian ini akan lebih baik dengan memainkan beberapa kernel dan nilai parameter pada SVM.…”

A Review of Various Methods Used in the Analysis of Functional Gene Expression Data

“…The SVM [39] or SVM combined with other techniques such as LDA [40] discriminate against non-linearly separable data and some of these approaches offer the possibility to define several classes. Other works have applied SVM with MI (Mutual Information) for the classification of colon cancer and Lymphoma [41]. Others authors have proposed SVM with GA (Genetic algorithm) for also the classification of cancer.…”