Sensitive immunopeptidomics by leveraging available large-scale multi-HLA spectral libraries, data-independent acquisition and MS/MS prediction.

Abstract

Mass spectrometry is the state-of-the-art methodology for capturing the breadth and depth of the immunopeptidome across HLA allotypes and cell types. The majority of studies in the immunopeptidomics field are discovery-driven. Hence, data-dependent tandem mass spectrometry acquisition (DDA MS/MS) is widely used, as it generates high quality references of peptide fingerprints. However, DDA suffers from the stochastic selection of abundant ions that impairs sensitivity and reproducibility. In contrast, in data-independent acquisition (DIA), the systematic fragmentation and acquisition of all fragment ions within a given isolation m/z windows yield a comprehensive map for a given sample. However, many DIA approaches commonly require generating comprehensive DDA-based spectrum libraries, which can become impractical for studying non-canonical and personalized neoantigens. Since the amount of HLA peptides eluted from biological samples such small tissue biopsies is typically not sufficient for acquiring both meaningful DDA data necessary for generating comprehensive spectral libraries and DIA MS measurements, the implementation of DIA in the immunopeptidomics translational research domain has remained limited. We implemented a DIA immunopeptidomics workflow and assessed its sensitivity and accuracy by matching DIA data against libraries with growing complexity - from sample-specific libraries to libraries combining two to forty different immunopeptidomics samples. Analyzing DIA immunopeptidomics data against a complex multi-HLA spectral library resulted in a two-fold increase in peptide identification compared with sample-specific library and in a three-fold increase compared with DDA measurements, yet with no detrimental effect on the specificity. Furthermore, we demonstrated the implementation of DIA for sensitive personalized neoantigen discovery through the analysis of DIA data with predicted MS/MS spectra of clinically relevant HLA ligands. We conclude that a comprehensive multi-HLA library for DIA approach in combination with MS/MS prediction is highly advantageous for the clinical immunopeptidomics especially when low amounts of biological samples are available for immunopeptidomics.