A Deep Learning Approach for Viral DNA Sequence Classification using Genetic Algorithm

Abstract

DNA sequence classification is one of the major challenges in biological data processing. The identification and classification of novel viral genome sequences drastically help in reducing the dangers of a viral outbreak like COVID-19. The more accurate the classification of these viruses, the faster a vaccine can be produced to counter them. Thus, more accurate methods should be utilized to classify the viral DNA. This research proposes a hybrid deep learning model for efficient viral DNA sequence classification. A genetic algorithm (GA) was utilized for weight optimization with Convolutional Neural Networks (CNN) architecture. Furthermore, Long Short-Term Memory (LSTM) as well as Bidirectional CNN-LSTM model architectures are employed. Encoding methods are needed to transform the DNA into numeric format for the proposed model. Three different encoding methods to represent DNA sequences as input to the proposed model were experimented: k-mer, label encoding, and one hot vector encoding. Furthermore, an efficient oversampling method was applied to overcome the imbalanced dataset issues. The performance of the proposed GA optimized CNN hybrid model using label encoding achieved the highest classification accuracy of 94.88% compared with other encoding methods.

Integration of Deep Learning Models for Enhanced Classification of Viral DNA Sequences Across Specific Viruses and Viral Families

“…Furthermore, in a previous study, the Genetic Algorithm (GA) optimized Convolutional Neural Network (GA-CNN) model was introduced [9]. This model represents a synergy of two powerful computational concepts: the robust feature extraction inherent in Convolutional Neural Networks (CNNs) and the efficiency of optimization provided by Genetic Algorithms (GAs).…”

“…This model represents a synergy of two powerful computational concepts: the robust feature extraction inherent in Convolutional Neural Networks (CNNs) and the efficiency of optimization provided by Genetic Algorithms (GAs). The GA-CNN model, as detailed in previous research, has successfully harnessed these capabilities to analyze and classify specific viral sequences with remarkable accuracy [9]. El-Tohamy et al [9] developed an optimized Convolutional Neural Network (GA-CNN) for classification of viral genomes.…”

“…The GA-CNN model, as detailed in previous research, has successfully harnessed these capabilities to analyze and classify specific viral sequences with remarkable accuracy [9]. El-Tohamy et al [9] developed an optimized Convolutional Neural Network (GA-CNN) for classification of viral genomes. It was also enhanced to outperform previous work of Gunasekaran, Hemalatha, et al [21] by introducing more virus labels.…”

“…The GA-CNN model was adeptly applied to a dataset of specific viral sequences using 3 encoding methods label , one-hot and k-mer encoding, achieving the highest classification accuracy of 94.88% using label encoding . El-Tohamy et al [11] also introduced Convolutional Neural Network with Extreme Learning Machines (CNN-ELM) model with the generic diverse virus family dataset collected. This model achieved a notable accuracy of 94.54% using k-mer encoding for classifying a broad spectrum of viral families.…”

“…It effectively captures the subtle genetic variations and patterns that are key to distinguishing between different viruses. The other model is the Convolutional Neural Network with Extreme Learning Machines (CNN-ELM) [11]. It harnesses the power of Convolutional Neural Networks (CNNs) for extracting key features from complex viral sequences.…”