Identification of new antigens using hot spots

摘要

A method for identifying new antigens that are likely to be presented on the surface of a subject''s tumor cells. The peptide sequence of the tumor neoantigen is obtained by sequencing the tumor cells of the subject. The peptide sequence of each neoantigen is associated with one or more k-mer blocks of a plurality of k-mer blocks of the subject''s nucleotide sequencing data; Peptide sequences and associated k-mer blocks are entered into a machine-learned presentation model to generate presentation possibilities for tumor-neoplastic antigens, each presentation probability being the MHC allele on the surface of a tumor cell of a subject. Indicates the possibility to be presented by. The subset of new antigens is selected based on the likelihood of presentation.