Techniques for Theoretical Prediction of Immunogenic Peptides

Abstract

Small peptides are an important component of the vertebrate immune system. They are important molecules for distinguishing proteins that originate in the host from proteins derived from a pathogenic organism, such as a virus or bacterium. Consequently, these peptides are central for the vertebrate host response to intracellular and extracellular pathogens. Computational models for prediction of these peptides have been based on a narrow sample of data with an emphasis on the position and chemical properties of the amino acids. In past literature, this approach has resulted in higher predictability than models that rely on the geometrical arrangement of atoms. However, protein structure data from experiment and theory are a source for building models at scale, and, therefore, knowledge on the role of small peptides and their immunogenicity in the vertebrate immune system. The following sections introduce procedures that contribute to theoretical prediction of peptides and their role in immunogenicity. Lastly, deep learning is discussed as it applies to immunogenetics and the acceleration of knowledge by a capability for modeling the complexity of natural phenomena.