Format

Send to

Choose Destination
Nat Methods. 2019 Jan;16(1):63-66. doi: 10.1038/s41592-018-0260-3. Epub 2018 Dec 20.

Deep learning enables de novo peptide sequencing from data-independent-acquisition mass spectrometry.

Author information

1
David R. Cheriton School of Computer Science, University of Waterloo, Waterloo, ON, Canada.
2
Department of Statistics and Actuarial Science, University of Waterloo, Waterloo, ON, Canada.
3
Bioinformatics Solutions Inc., Waterloo, ON, Canada.
4
Department of Electrical & Computer Engineering, University of Waterloo, Waterloo, ON, Canada.
5
State Key Laboratory of Pathogen and Biosecurity, Beijing Institute of Microbiology and Epidemiology, Beijing, China.
6
David R. Cheriton School of Computer Science, University of Waterloo, Waterloo, ON, Canada. mli@uwaterloo.ca.

Abstract

We present DeepNovo-DIA, a de novo peptide-sequencing method for data-independent acquisition (DIA) mass spectrometry data. We use neural networks to capture precursor and fragment ions across m/z, retention-time, and intensity dimensions. They are then further integrated with peptide sequence patterns to address the problem of highly multiplexed spectra. DIA coupled with de novo sequencing allowed us to identify novel peptides in human antibodies and antigens.

PMID:
30573815
DOI:
10.1038/s41592-018-0260-3

Supplemental Content

Full text links

Icon for Nature Publishing Group
Loading ...
Support Center