Novel hybrid DCNN–SVM model for classifying RNA-sequencing gene expression data

Abstract

In recent years, cancer is one of the leading causes of death worldwide. Therefore, there are more and more studies that have been conducted to find effective solutions to diagnose and treat cancer. However, there are still many challenges in cancer treatment because possible causes of cancer are genetic disorders or epigenetic alterations in the cells. RNA sequencing is a powerful technique for gene expression profiling in model organisms and it is able to produce information for diagnosing cancer at the biomolecular level. Gene expression data are used to build a classification model which supports treatment of cancer. Nevertheless, its characteristic is very-high-dimensional data which lead to over-fitting issue of classifying model. In this paper, we propose a new gene expression classification model of support vector machines (SVM) using features extracted by deep convolutional neural network (DCNN). In our approach, the DCNN extracts latent features from gene expression data, then they are used in conjunction with SVM that efficiently classify RNA-Seq gene expression data. Numerical test results on RNA-Seq gene expression datasets from The Cancer Genome Atlas (TCGA) illustrate that our proposed algorithm is more accurate than state-of-the-art classifying models including DCNN, SVM and random forests.

Analysis of the pattern recognition algorithm of broadband satellite modulation signal under deformable convolutional neural networks

“…[ 21 , 22 ]. Gradient descent in the network can adjust network back propagation parameters, while the commonly used gradient descent algorithms are stochastic gradient descent (SGD), batch gradient descent (BGD) and MBGD [ 23 ]. Classifiers for image classification during output include Softmax, Logistic, Boosting, Adaboost, SVM [ 24 ].…”

A Hybrid Heuristic Dimensionality Reduction Methods for Classifying Malaria Vector Gene Expression Data

“…They evaluated the applications which showed that PCA procedures grounded on Krylov subspace and random singular value breakdown are fast, retention adequate and precise. Huynh, Nguyen, and Do [21] proposed an innovative hybrid Deep Convolutional NN (DCNN)-SVM approach, classifying gene expression RNA-Seq data. They used DCNN to abstract hidden features from a cancer RNA-Seq gene expression data, SVM used as a classifier which the results were efficiently accurate compared to hi-tech.…”

“…It realizes numerous facets of transcriptomes-a leading present-day DNA-microarray technology, used in carrying out a high-throughput investigation of gene expressions. Providing improved understanding into cell transcriptomes, giving unconventional treatments and better resolutions [26][27], it distinguishes early hidden variations happening in disease conditions by answering to therapeutics of diverse environments and other training, creating ample amount of sequencing data [21]. Gene expression RNA-Seq data classification has given beneficial evidence for identifying and determining germane drugs for ailments.…”

“…A significant challenge of RNA-Seq is the problem of diagnostic challenges, and it gives unfitting outcome due to high dimensions of gene expression data. Numerous machine learning approaches proposed to enhance gene expression data classification such as; dimensional reduction, clustering, classification, among others [21].…”

“…Dimensionality reduction approaches are used in selecting select [7] and extract [8] relevant and specific information in a massive amount of dataset, which are known as the feature selection and the feature extraction [9]. Classification of diverse types of predominant gene expression RNA-Seq data in enumerating genes for biological questions has given beneficial information for identifying and discovering drugs [10], [11]. A hybrid dimensionality reduction technique is proposed, to classify malaria vector gene expression RNA-Seq data and identify significant features using genetic algorithm as a feature selection technique to fetch pertinent subset features from given dataset.…”