Login / Signup

VirVACPRED: A Web Server for Prediction of Protective Viral Antigens.

Jesús Herrera-BravoJorge G FaríasFernanda Parraguez ContrerasLisandra Herrera-BelénJuan-Alejandro NorambuenaJorge F Beltrán
Published in: International journal of peptide research and therapeutics (2021)
Viral antigens are key in the development of vaccines that prevent or eradicate infections caused by these pathogens. Bioinformatics tools are modern alternatives that facilitate the discovery of viral antigens, reducing the costs of experimental assays. We developed a bioinformatics tool called VirVACPRED, which is highly efficient in predicting viral antigens. In this study, we obtained a model based on the gradient boosting classifier, which showed high performance during the training, leave-one-out cross-validation (accuracy = 0.7402, sensitivity = 0.7319, precision = 0.7503, F1 = 0.7251, kappa = 0.4774, Matthews correlation coefficient = 0.4981) and testing (accuracy = 0.8889, sensitivity = 1.0, precision = 0.8276, F1 = 0.9057, kappa = 0.7734, Matthews correlation coefficient = 0.7941). VirVACPRED is a robust tool that can be of great help in the search and proposal of new viral antigens, which can be considered in the development of future vaccines against infections caused by viruses.
Keyphrases
  • sars cov
  • highly efficient
  • dendritic cells
  • nuclear factor
  • high throughput
  • immune response
  • diffusion weighted imaging
  • gram negative
  • current status
  • single cell
  • inflammatory response