Multi-Stage Temporal Convolution Network for COVID-19 Variant Classification

Abstract

The outbreak of the novel coronavirus disease COVID-19 (SARS-CoV-2) has developed into a global epidemic. Due to the pathogenic virus’s high transmission rate, accurate identification and early prediction are required for subsequent therapy. Moreover, the virus’s polymorphic nature allows it to evolve and adapt to various environments, making prediction difficult. However, other diseases, such as dengue, MERS-CoV, Ebola, SARS-CoV-1, and influenza, necessitate the employment of a predictor based on their genomic information. To alleviate the situation, we propose a deep learning-based mechanism for the classification of various SARS-CoV-2 virus variants, including the most recent, Omicron. Our model uses a neural network with a temporal convolution neural network to accurately identify different variants of COVID-19. The proposed model first encodes the sequences in the numerical descriptor, and then the convolution operation is applied for discriminative feature extraction from the encoded sequences. The sequential relations between the features are collected using a temporal convolution network to classify COVID-19 variants accurately. We collected recent data from the NCBI, on which the proposed method outperforms various baselines with a high margin.

An Efficient Lightweight Hybrid Model with Attention Mechanism for Enhancer Sequence Recognition

“…RNNs are particularly suitable for time series questions because of the way their architecture works: they share weights at every single time step in a series. Various applications of RNNs have been made in various fields, including anomaly detection [23], continuous B-cell epitope prediction [30,31], sentiment analysis [32,33], action recognition [34], and time series data analysis [35,36]. Generally, RNNs are prone to causing gradient vanishing or exploding when they are applied to long sequences of data; this is one of their major shortcomings.…”