COVID-19 Genome Sequence Analysis for New Variant Prediction and Generation

The new COVID-19 variants of concern are causing more infections and spreading much faster than their predecessors. Recent cases show that even vaccinated people highly affected by these variants. proactive nucleotide sequence prediction possible developing better healthcare plans to address spread require a unified framework for variant classification early prediction. This paper attempts answer the following research questions: can convolutional neural network with self-attention extracting discriminative features from sequences be used classify variants? Second, is it employ uncertainty calculation in predicted probability distribution predict Finally, synthetic approaches such as variational autoencoder-decoder networks employed generate random noise? Experimental results generated significantly similar original coronavirus its variants, proving our learn mutation patterns old Moreover, knowledge, we first collect data all computational analysis. proposed extensively evaluated classification, prediction, generation tasks achieves performance tasks. Our code, data, trained models available on GitHub (https://github.com/Aminullah6264/COVID19, accessed 16 September 2022).