Impact Statement:This study introduces a novel computational model for identifying antigenic fragments also known as T-cell epitopes (TCEs) of the SARS-CoV-2 virus, offering a promising a...Show More
Abstract:
The development of Epitope-based vaccines (EBVs) necessitates the identification of antigenic fragments (AFs) of the target pathogen known as T-cell epitopes (TCEs). TCEs...Show MoreMetadata
Impact Statement:
This study introduces a novel computational model for identifying antigenic fragments also known as T-cell epitopes (TCEs) of the SARS-CoV-2 virus, offering a promising avenue for epitope-based vaccine development. Unlike existing methods, the proposed model provides deterministic predictions and accommodates peptides of varying lengths, addressing limitations of current techniques like NetMHC and CTLpred. With its potential to identify effective vaccine candidates quickly and cost-effectively, this model represents a significant step towards combating COVID-19 like diseases and preventing future outbreaks. While further in vivo and in vitro experimental validation is necessary, the results underscore the transformative impact of computational approaches in vaccine research and public health.
Abstract:
The development of Epitope-based vaccines (EBVs) necessitates the identification of antigenic fragments (AFs) of the target pathogen known as T-cell epitopes (TCEs). TCEs are recognized by immune system, specifically by T cells, B cells or antibodies. Traditional wet lab methods for identifying TCEs are often costly, challenging, and time-consuming compared to computational approaches. In the present study, we propose a neural network-based ensemble machine learning (ML) model trained on physicochemical properties of SARS-CoV-2 peptides sequences to predict TCE sequences. The performance of the model assessed using test dataset demonstrated an accuracy of > 95%, surpassing the results of other ML classifiers that were employed for comparative analysis. Through five-fold cross-validation technique, a mean accuracy of approximately 95% was reported. Additionally, when compared to other existing TCE prediction methods using a blind dataset, the proposed model was found to be more accurate...
Published in: IEEE Transactions on Artificial Intelligence ( Early Access )