Accurate de novo peptide sequencing using fully convolutional neural networks

peer-reviewed · Nature Communications · 2023

peer-reviewed · Nature Communications · 2023. Kaiyuan Liu et al. De novo peptide sequencing, which does not rely on a comprehensive target sequence database, provides us with…
Date 2023-12-02
Type peer-reviewed
Venue Nature Communications
Publisher Springer Science and Business Media LLC
Contribution algorithm
DOI 10.1038/s41467-023-43010-x
Citations (OpenAlex) 78
Venue 2-year citedness 17.60

Preprint version: PepNet: A Fully Convolutional Neural Network for De novo Peptide Sequencing (2022-02-09, Research Square)

Abstract

De novo peptide sequencing, which does not rely on a comprehensive target sequence database, provides us with a way to identify novel peptides from tandem mass spectra. However, current de novo sequencing algorithms suffer from low accuracy and coverage, which hinders their application in proteomics. In this paper, we present PepNet, a fully convolutional neural network for high accuracy de novo peptide sequencing. PepNet takes an MS/MS spectrum (represented as a high-dimensional vector) as input, and outputs the optimal peptide sequence along with its confidence score. The PepNet model is trained using a total of 3 million high-energy collisional dissociation MS/MS spectra from multiple human peptide spectral libraries. Evaluation results show that PepNet significantly outperforms current best-performing de novo sequencing algorithms (e.g. PointNovo and DeepNovo) in both peptide-level accuracy and positional-level accuracy. PepNet can sequence a large fraction of spectra that were not identified by database search engines, and thus could be used as a complementary tool to database search engines for peptide identification in proteomics. In addition, PepNet runs around 3x and 7x faster than PointNovo and DeepNovo on GPUs, respectively, thus being more suitable for the analysis of large-scale proteomics data.

Authors

  1. Kaiyuan Liu · Indiana University, Indiana University Bloomington
  2. Yuzhen Ye · Indiana University Bloomington
  3. Sujun Li · Indiana University, Indiana University Bloomington
  4. Haixu Tang · Indiana University, Indiana University Bloomington, University of California San Diego

Methods and tools

  • PepNet: Temporal convolutional network

Data used

Cites (13)

Cited by (40)

Seen in the charts

Back to the full map

Back to top