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

peer-reviewed · Nature Methods · 2018

peer-reviewed · Nature Methods · 2018. Ngoc Hieu Tran et al. We present DeepNovo-DIA, a de novo peptide-sequencing method for data-independent acquisition (DIA) mass…
Date 2018-12-20
Type peer-reviewed
Venue Nature Methods
Publisher Springer Science and Business Media LLC
Contribution algorithm
DOI 10.1038/s41592-018-0260-3
Citations (OpenAlex) 381
Venue 2-year citedness 22.29

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.

Authors

  1. Ngoc Hieu Tran · Bioinformatics Solutions (Canada), Bioinformatics Solutions Inc., University of Waterloo
  2. Rui Qiao · Bioinformatics Solutions (Canada), Bioinformatics Solutions Inc., University of Waterloo
  3. Lei Xin · Bioinformatics Solutions (Canada), Bioinformatics Solutions Inc., Western University
  4. Xin Chen (Waterloo) · Bioinformatics Solutions (Canada), Bioinformatics Solutions Inc.
  5. Chuyi Liu · University of Waterloo
  6. Xianglilan Zhang · Beijing Institute of Microbiology and Epidemiology, University of Waterloo
  7. Baozhen Shan · Bioinformatics Solutions (Canada), Bioinformatics Solutions Inc., Western University
  8. Ali Ghodsi · University of Waterloo
  9. Ming Li · Bioinformatics Solutions Inc., Central China Institute of Artificial Intelligence, Peng Cheng Laboratory, University of Waterloo, University of Western Ontario

Methods and tools

Data used

  • De novo sequencing of DIA data (as deposited) · MSV000082368

Cites (2)

Cited by (64)

Seen in the charts

Back to the full map

Back to top