Effective of Various Vaccines on Antibody Response and Genetic Immune Using Deep Learning Method

Authors

  • Nuha Hisham Mohammed Department of Information Technology, University of Babylon, Babylon, Iraq, Iraq
  • Sura Zaki Al-Rashid Department of Information Technology, University of Babylon, Babylon, Iraq, Iraq

Keywords:

COVID-19, Convolutional Neural Network (CNN), mRNA, Analysis of Variance (ANOVA), Chi-square, Mutual Information (MI).

Abstract

The COVID-19 epidemic has affected daily life on a global scale. Many research teams from major pharmaceutical companies and university institutions around the world have been developing vaccines since the beginning of the pandemic. The effectiveness, acceptability, and results of vaccinations are influenced by gender. The SARS-CoV-2 mRNA vaccines were released on the market in reaction to the Covid-19 public health emergencies. There is no history of using mRNA vaccines to treat infectious diseases. The numerous modifications of the vaccine’s mRNA work to protect it from cellular defenses, lengthen its biological half-life and increase the creation of spike protein. In this paper, we propose a novel model to predict the antibody response based on deep learning by proposing a Convolutional Neural Network (CNN) model. The proposed system consists of several stages, where the GSE201533 dataset which used, containing 26,370 features is first split into two sets, then the missing value and normalization were applied as a preprocessing stage, then the best features were selected using three techniques (Mutual information, Chi-square, and Analysis of Variance (ANOVA)). Then the selected features were classified using the proposed CNN model. The proposed CNN contributed to raising the accuracy of the model and reducing the time required for prediction. The experimental results indicate an accuracy rate of 100% in all cases.

Downloads

Published

2023-06-15

How to Cite

Nuha Hisham Mohammed, & Sura Zaki Al-Rashid. (2023). Effective of Various Vaccines on Antibody Response and Genetic Immune Using Deep Learning Method. Utilitas Mathematica, 120, 330–344. Retrieved from https://utilitasmathematica.com/index.php/Index/article/view/1660

Citation Check