Deep learning boosts sensitivity of mass spectrometry-based immunopeptidomics

Mathias Wilhelm (), Daniel P. Zolg, Michael Graber, Siegfried Gessulat, Tobias Schmidt, Karsten Schnatbaum, Celina Schwencke-Westphal, Philipp Seifert, Niklas Andrade Krätzig, Johannes Zerweck, Tobias Knaute, Eva Bräunlein, Patroklos Samaras, Ludwig Lautenbacher, Susan Klaeger, Holger Wenschuh, Roland Rad, Bernard Delanghe, Andreas Huhmer, Steven A. Carr, Karl R. Clauser, Angela M. Krackhardt, Ulf Reimer and Bernhard Kuster ()
Additional contact information
Mathias Wilhelm: Technical University of Munich (TUM)
Daniel P. Zolg: Technical University of Munich (TUM)
Michael Graber: Technical University of Munich (TUM)
Siegfried Gessulat: Technical University of Munich (TUM)
Tobias Schmidt: Technical University of Munich (TUM)
Karsten Schnatbaum: JPT Peptide Technologies GmbH
Celina Schwencke-Westphal: Technical University of Munich (TUM)
Philipp Seifert: Technical University of Munich (TUM)
Niklas Andrade Krätzig: Technical University of Munich (TUM)
Johannes Zerweck: JPT Peptide Technologies GmbH
Tobias Knaute: JPT Peptide Technologies GmbH
Eva Bräunlein: Technical University of Munich (TUM)
Patroklos Samaras: Technical University of Munich (TUM)
Ludwig Lautenbacher: Technical University of Munich (TUM)
Susan Klaeger: Broad Institute of MIT and Harvard
Holger Wenschuh: JPT Peptide Technologies GmbH
Roland Rad: Technical University of Munich (TUM)
Bernard Delanghe: Thermo Fisher Scientific
Andreas Huhmer: Thermo Fisher Scientific
Steven A. Carr: Broad Institute of MIT and Harvard
Karl R. Clauser: Broad Institute of MIT and Harvard
Angela M. Krackhardt: Technical University of Munich (TUM)
Ulf Reimer: JPT Peptide Technologies GmbH
Bernhard Kuster: Technical University of Munich (TUM)

Nature Communications, 2021, vol. 12, issue 1, 1-12

Abstract: 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.

Date: 2021
References: Add references at CitEc
Citations: View citations in EconPapers (13)

Downloads: (external link)
https://www.nature.com/articles/s41467-021-23713-9 Abstract (text/html)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:nat:natcom:v:12:y:2021:i:1:d:10.1038_s41467-021-23713-9

Ordering information: This journal article can be ordered from
https://www.nature.com/ncomms/

DOI: 10.1038/s41467-021-23713-9

Access Statistics for this article

Nature Communications is currently edited by Nathalie Le Bot, Enda Bergin and Fiona Gillespie

More articles in Nature Communications from Nature
Bibliographic data for series maintained by Sonal Shukla () and Springer Nature Abstracting and Indexing ().