Deep learning boosts sensitivity of mass spectrometry-based immunopeptidomics

Wilhelm, Mathias; Zolg, Daniel P.; Graber, Michael; Gessulat, Siegfried; Schmidt, Tobias; Schnatbaum, Karsten; Schwencke-Westphal, Celina; Seifert, Philipp; de Andrade Krätzig, Niklas; Zerweck, Johannes; Knaute, Tobias; Bräunlein, Eva; Samaras, Patroklos; Lautenbacher, Ludwig; Klaeger, Susan; Wenschuh, Holger; Rad, Roland; Delanghe, Bernard; Huhmer, Andreas; Carr, Steven A.; Clauser, Karl R.; Krackhardt, Angela M.; Reimer, Ulf; Kuster, Bernhard

doi:10.1038/s41467-021-23713-9

10.1038/s41467-021-23713-9

Title:: Deep learning boosts sensitivity of mass spectrometry-based immunopeptidomics
Document type:: Zeitschriftenaufsatz
Author(s):: Wilhelm, Mathias; Zolg, Daniel P.; Graber, Michael; Gessulat, Siegfried; Schmidt, Tobias; Schnatbaum, Karsten; Schwencke-Westphal, Celina; Seifert, Philipp; de Andrade Krätzig, Niklas; Zerweck, Johannes; Knaute, Tobias; Bräunlein, Eva; Samaras, Patroklos; Lautenbacher, Ludwig; Klaeger, Susan; Wenschuh, Holger; Rad, Roland; Delanghe, Bernard; Huhmer, Andreas; Carr, Steven A.; Clauser, Karl R.; Krackhardt, Angela M.; Reimer, Ulf; Kuster, Bernhard
Abstract:: Characterizing the human leukocyte antigen (HLA) bound ligandome by mass spectrometry (MS) holds great promise for developing vaccines and drugs for immune-oncology. Still, the identification of non-tryptic peptides presents substantial computational challenges. To address these, we synthesized and analyzed >300,000 peptides by multi-modal LC-MS/MS within the ProteomeTools project representing HLA class I & II ligands and products of the proteases AspN and LysN. The resulting data enabled training of a single model using the deep learning framework Prosit, allowing the accurate prediction of fragment ion spectra for tryptic and non-tryptic peptides. Applying Prosit demonstrates that the identification of HLA peptides can be improved up to 7-fold, that 87% of the proposed proteasomally spliced HLA peptides may be incorrect and that dozens of additional immunogenic neo-epitopes can be identified from patient tumors in published data. Together, the provided peptides, spectra and computational tools substantially expand the analytical depth of immunopeptidomics workflows.
Journal title:: Nature Communications
Year:: 2021
Journal volume:: 12
Journal issue:: 1
Fulltext / DOI:: doi:10.1038/s41467-021-23713-9
Publisher:: Springer Science and Business Media LLC
E-ISSN:: 2041-1723
Date of publication:: 07.06.2021
BibTeX

Occurrences:

mediaTUM Gesamtbestand Einrichtungen Schools TUM School of Life Sciences Departments Molecular Life Sciences Professur für Computational Mass Spectrometry (Prof. Wilhelm)

mediaTUM Gesamtbestand Hochschulbibliographie 2021 Fakultäten Wissenschaftszentrum Weihenstephan Professur für Computational Mass Spectrometry (Prof. Wilhelm)