Sequence determination of peptides from CID spectra using artificial neural networks

A new technique using artificial neural networks to aid in the automated interpretation of peptide sequence from high-energy collision-induced dissociation (CID) tandem mass spectra of peptides is presented. Two backpropagation networks classify fragment ions before the commencement of an iterative sequencing algorithm. The first neural network attempts to determine whether or not peaks belong to one of eleven fragment ion classes while the second network assigns classification scores. The results enable the program to generate an idealized spectrum consisting of a single ion type, from which the sequencing module builds and ranks candidate sequences in a high-speed iterative process