Abstract
BackgroundThe immune system must detect a wide variety of microbial pathogens, such as viruses, bacteria, fungi and parasitic worms, to protect the host against disease. Antigenic peptides displayed by MHC II (class II Major Histocompatibility Complex) molecules is a pivotal process to activate CD4+ TH cells (Helper T cells). The activated TH cells can differentiate into effector cells which assist various cells in activating against pathogen invasion. Each MHC locus encodes a great number of allele variants. Yet this limited number of MHC molecules are required to display enormous number of antigenic peptides. Since the peptide binding measurements of MHC molecules by biochemical experiments are expensive, only a few of the MHC molecules have suffecient measured peptides. To perform accurate binding prediction for those MHC alleles without suffecient measured peptides, a number of computational algorithms were proposed in the last decades.ResultsHere, we propose a new MHC II binding prediction approach, OWA-PSSM, which is a significantly extended version of a well known method called TEPITOPE. The TEPITOPE method is able to perform prediction for only 50 MHC alleles, while OWA-PSSM is able to perform prediction for much more, up to 879 HLA-DR molecules. We evaluate the method on five benchmark datasets. The method is demonstrated to be the best one in identifying binding cores compared with several other popular state-of-the-art approaches. Meanwhile, the method performs comparably to the TEPITOPE and NetMHCIIpan2.0 approaches in identifying HLA-DR epitopes and ligands, and it performs significantly better than TEPITOPEpan in the identification of HLA-DR ligands and MultiRTA in identifying HLA-DR T cell epitopes.ConclusionsThe proposed approach OWA-PSSM is fast and robust in identifying ligands, epitopes and binding cores for up to 879 MHC II molecules.
Highlights
The immune system must detect a wide variety of microbial pathogens, such as viruses, bacteria, fungi and parasitic worms, to protect the host against disease
Through introducing the ordered weighted averaging (OWA) weights [19,20], we develop a novel weighting scheme for those pocket profiles generated by TEPITOPE
Five independent benchmark datasets are employed to evaluate the performance of OWA-PSSM through comparing with the TEPITOPE, MultiRTA, NetMHCIIpan2.0 and TEPITOPEpan methods
Summary
The immune system must detect a wide variety of microbial pathogens, such as viruses, bacteria, fungi and parasitic worms, to protect the host against disease. Antigenic peptides displayed by MHC II (class II Major Histocompatibility Complex) molecules is a pivotal recognize those foreign peptides that are displayed by MHC II from endocytosed proteins to the surface of APCs and produce a large number of cytokineses to activate various cells to defend invasion [2,3]. MHC I molecules have conserved residues which bind to the terminal residues of antigenic peptides, so they form close grooves. Each MHC locus encodes a great number of allele variants This limited number of MHC molecules are required to display enormous number of antigenic peptides. To perform accurate binding prediction for those MHC alleles without suffecient measured peptides, a number of computational algorithms were proposed in the last decades
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
