A transformer model for de novo sequencing of data independent acquisition mass spectrometry data

preprint · bioRxiv · 2024

preprint · bioRxiv · 2024. Justin Sanders et al. A core computational challenge in the analysis of mass spectrometry data is the de novo sequencing problem…
Date 2024-06-03
Type preprint
Venue bioRxiv
Publisher Cold Spring Harbor Laboratory
Contribution algorithm
DOI 10.1101/2024.06.03.597251
Citations (OpenAlex) 10

Peer-reviewed version: A transformer model for de novo sequencing of data independent acquisition mass spectrometry data (2025-07-01, Nature Methods)

Abstract

A core computational challenge in the analysis of mass spectrometry data is the de novo sequencing problem, in which the generating amino acid sequence is inferred directly from an observed fragmentation spectrum without the use of a sequence database. Recently, deep learning models have made significant advances in de novo sequencing by learning from massive datasets of high-confidence labeled mass spectra. However, these methods are primarily designed for data-dependent acquisition (DDA) experiments. Over the past decade, the field of mass spectrometry has been moving toward using data-independent acquisition (DIA) protocols for the analysis of complex proteomic samples due to their superior specificity and reproducibility. Hence, we present a new de novo sequencing model called Cascadia, which uses a transformer architecture to handle the more complex data generated by DIA protocols. In comparisons with existing approaches for de novo sequencing of DIA data, Cascadia achieves state-of-the-art performance across a range of instruments and experimental protocols. Additionally, we demonstrate Cascadias ability to accurately discover de novo coding variants and peptides from the variable region of antibodies.

Authors

  1. Justin Sanders · University of Washington
  2. Bo Wen · Baylor College of Medicine, University of Washington
  3. Paul Rudnick · Spectragen Informatics
  4. Rich Johnson · University of Washington
  5. Christine C. Wu · University of Washington
  6. Sewoong Oh · University of Washington
  7. Michael J. MacCoss · University of Washington
  8. William Stafford Noble · University of Washington

Methods and tools

Cites (15)

Cited by (4)

Seen in the charts

Back to the full map

Back to top