Bioinformatic processes for determination of peptide binding

A process of identifying peptide and polypeptide ligands for a MHC-I or MHC-II binding partner and synthesizing a biomolecule encoding the identified peptide and polypeptide ligands comprising:

• a) obtaining an amino acid sequence for a target polypeptide;
• b) providing peptide binding prediction equations for a MHC-I or MHC-II binding partner polypeptide derived by:
• (i) assembling experimentally derived data from a plurality of experiments comprising a multiplicity of measurements of amino acid physicochemical properties;
• (ii) producing a correlation matrix of the experimentally derived data;
• (iii) deriving by Principal Component Analysis multiple uncorrelated dimensionless, weighted and ranked proxy descriptors to describe at least 80% of the variance in said physicochemical properties of individual amino acids,
• (iv) using said proxy descriptors to describe individual amino acids in peptides with known binding affinities thereby creating vectors which describe said peptides with known binding affinities, and
• (v) via neural network modeling, deriving said binding prediction equations for said MHC-I or MHC-II binding partner by comparing said vectors with said known binding affinities of said peptides, wherein said principal components of said amino acids are utilized as the input layer of a multilayer perceptron neural network;
• (c) in-putting said amino acid sequence from said target polypeptide into a computer;
• (d) applying said proxy descriptors from said Principal Component Analysis to describe individual amino acids in said target polypeptide sequence;
• (e) deriving vectors to describe a plurality of peptides of defined length in said target polypeptide;
• (f) via said neural network, applying said peptide binding prediction equations to said plurality of peptides of defined length from said target polypeptide to predict the ability of said plurality of peptides of defined length from said target polypeptide to bind to said binding partner, wherein said neural network determines the permuted average binding of a peptide to at least 20 MHC-I or MHC-II binding regions;
• (g) displaying the binding affinity of said peptides of defined length in said target polypeptide to said binding partner;
• and
• (h) selecting one or more peptides from the target polypeptide having a binding affinity of about greater than 106 M−1 to said binding partner;
• and
• (i) cloning the one or more peptides from the target molecule identified in step (h) with a into an expression vector and recombinantly synthesizing a biomolecule selected from the group consisting of a protein and nucleic acid encoding the one or more peptides.