Genes Expression Classification Through Histone Modification Using Temporal Neural Network

Abstract

\n\nGenes expression is high dimensional data, so it is very difficult to classify\nhigh dimensional data through traditional machine learning approaches. In this work we have proposed\na model based on combined approach of Convolutional Neural Network and Recurrent Neural\nNetwork, both belong to deep learning model. The prediction has shown improved result than other\nmachine learning algorithms. Expressions are generated through histone modification.\n\n\n\nTo improve the accuracy deep learning model is proposed i.e. based on Convolutional and\nRecurrent neural network. This proposed model uses filter, causal convolutional layers and Residual\nBlock for predictions.\n\n\n\n In this work we have implemented the machine learning algorithms and deep learning algorithms\nlike Logistic Regression, SVM, CNN, Deep Chrome and the proposed Temporal Neural\nNetwork. The performance is measured on the basis of parameters like accuracy, precision and AUC\non the training and testing set.\n\n\n\nThe proposed Temporal Neural Network model has shown better performance than\nother machine learning and deep learning algorithms. Due to this proposed deep learning algorithm\ncan be successfully applied on the genes expression dataset.\n