A machine learning approach to explore the spectra intensity pattern of peptides using tandem mass spectrometry data

In this work, a Bayesian neural network approach is employed to analyze ion intensity information present in 13878 different MS/MS spectra. The influence of a library of 35 features on peptide fragmentation is examined under different proton mobility conditions. Useful rules involved in peptide fragmentation are found and subsets of features which have significant influence on fragmentation pathway of peptides are characterised. An intensity model is built based on the selected features and the model can make an accurate prediction of the intensity patterns for given MS/MS spectra. The predictions include not only the mean values of spectra intensity but also the variances that can be used to tolerate noises and system biases within experimental MS/MS spectra.The intensity patterns of fragmentation spectra are informative and can be used to analyze the influence of various characteristics of fragmented peptides on their fragmentation pathway. The features with significant influence can be used in turn to predict spectra intensities. Such information can help develop more reliable algorithms for peptide and protein identification.Mass spectrometry (MS) has emerged in recent years as one of the most powerful tools for protein analysis available to proteomics research. MS-based protein identification strategies typically involve the digestion of protein samples prior to introduction into the mass spectrometer by a site-specific protease such as trypsin. The derived peptides are subsequently ionized at entry into the mass spectrometer and measured as intact fragment (parent) ions. Subsets of these ions can then be selected on the basis of their mass-to-charge ratio (m/z) and subject to further fragmentation, most commonly using collision induced dissociation (CID), in a process known as tandem mass spectrometry (MS/MS). Under the conditions utilized in CID, peptides fragment in predictable patterns resulting in a series of signature spectra. Identification of the protei