VaxinPAD: Computer-Aided Prediction of Antigen Presenting Cell Modulators for Designing Peptide-Based Vaccine Adjuvants

VaxinPAD: Computer-Aided Prediction of Antigen Presenting Cell Modulators for Designing Peptide-Based Vaccine Adjuvants VaxinPAD is a computational web server developed for the prediction and design of immunomodulatory peptides that can activate antigen presenting cells. These immunomodulatory peptides are referred to as A-cell epitopes because they can activate antigen presenting cells such as dendritic cells and macrophages, leading to downstream activation of adaptive immune responses. VaxinPAD helps researchers identify and design peptide-based vaccine adjuvants using machine learning-based prediction models. Web Server: http://webs.iiitd.edu.in/raghava/vaxinpad/ Citation Nagpal, G., Chaudhary, K., Agrawal, P., and Raghava, G. P. S. Computer-aided prediction of antigen presenting cell modulators for designing peptide-based vaccine adjuvants. Journal of Translational Medicine, 16, 181, 2018. https://doi.org/10.1186/s12967-018-1560-1 About the Research Peptide-based subunit vaccines are safer than live or inactivated whole-organism vaccines, but they are often weakly immunogenic on their own. To improve immune response, vaccine formulations require adjuvants that can activate innate immunity. Antigen presenting cells, especially dendritic cells and macrophages, play a central role in vaccine adjuvant activity. Immunomodulatory peptides can activate these antigen presenting cells through innate immune receptors such as pattern recognition receptors. VaxinPAD was developed to predict and design such immunomodulatory peptides, called A-cell epitopes, that may serve as peptide-based vaccine adjuvants. Data Compilation: Experimentally validated immunomodulatory peptides were collected from patents and literature. After filtering, the final positive dataset contained 304 A-cell epitopes of length 3 to 30 residues. The negative dataset contained 385 endogenous human serum peptides considered as non-epitopes. Methodology: VaxinPAD uses support vector machine-based models trained on sequence-derived peptide features such as amino acid composition, dipeptide composition, binary profiles, terminal residue features, and MERCI motif information.