Search Results (2)

In the growing field of vaccine design for COVID and cancer research, it is essential to predict accurate peptide binding affinity and immunogenicity. We developed a comprehensive machine learning method, ‘IntegralVac,’ by integrating three existing deep learning tools: DeepVacPred, MHCSeqNet, and HemoPI. IntegralVac makes predictions for single and multivalent cancer and COVID-19 epitopes without manually selecting epitope prediction possibilities. We performed several rounds of optimization before integration, then re-trained IntegralVac for multiple datasets. We validated the IntegralVac with 4500 human cancer MHC I peptides obtained from the Immune Epitope Database (IEDB) and with cancer and COVID epitopes previously selected in our laboratory. The other data referenced from existing deep learning tools served as a positive control to ensure successful prediction was possible. As evidenced by increased accuracy and AUC, IntegralVac improved the prediction rate of top-ranked epitopes. We also examined the compatibility between other servers’ clinical checkpoint filters and IntegralVac. This was to ensure that the other servers had a means for predicting additional checkpoint filters that we wanted to implement in IntegralVac. The clinical checkpoint filters, including allergenicity, antigenicity, and toxicity, were used as additional predictors to improve IntegralVac’s prediction accuracy. We generated immunogenicity scores by cross-comparing sequence inputs with each other and determining the overlap between each individual peptide sequence. The IntegralVac increased the immunogenicity prediction accuracy to 90.1% AUC and the binding affinity accuracy to 95.4% compared to the control NetMHCPan server. The IntegralVac opens new avenues for future in silico methods, by building upon established models for continued prediction accuracy improvement. Full article

This paper presents an alternative vaccination platform that provides long-term cellular immune protection mediated by cytotoxic T-cells. The immune response via cellular immunity creates superior resistance to viral mutations, which are currently the greatest threat to the global vaccination campaign. Furthermore, we also propose a safer, more facile, and physiologically appropriate immunization method using either intranasal or oral administration. The underlying technology is an adaptation of synthetic long peptides (SLPs) previously used in cancer immunotherapy. The overall quality of the SLP constructs was validated using in silico methods. SLPs comprising HLA class I and class II epitopes were designed to stimulate antigen cross-presentation and canonical class II presentation by dendritic cells. The desired effect is a cytotoxic T cell-mediated prompt and specific immune response against the virus-infected epithelia and a rapid and robust virus clearance. Epitopes isolated from COVID-19 convalescent patients were screened for HLA class I and class II binding (NetMHCpan and NetMHCIIpan) and highest HLA population coverage (IEDB Population Coverage). 15 class I and 4 class II epitopes were identified and used for this SLP design. The constructs were characterized based on their toxicity (ToxinPred), allergenicity (AllerCatPro), immunogenicity (VaxiJen 2.0), and physico-chemical parameters (ProtParam). Based on in silico predictions, out of 60 possible SLPs, 36 candidate structures presented a high probability to be immunogenic, non-allergenic, non-toxic, and stable. 3D peptide folding followed by 3D structure validation (PROCHECK) and molecular docking studies (HADDOCK 2.4) with Toll-like receptors 2 and 4 provided positive results, suggestive for favorable antigen presentation and immune stimulation. Full article