De novo peptide sequencing by deep learning

peer-reviewed · Proceedings of the National Academy of Sciences · 2017

peer-reviewed · Proceedings of the National Academy of Sciences · 2017. Ngoc Hieu Tran et al. De novo peptide sequencing from tandem MS data is the key technology in proteomics for the characterization…
Date 2017-07-18
Type peer-reviewed
Venue Proceedings of the National Academy of Sciences
Publisher National Academy of Sciences
Contribution algorithm
DOI 10.1073/pnas.1705691114
Citations (OpenAlex) 448
Venue 2-year citedness 8.56

Abstract

De novo peptide sequencing from tandem MS data is the key technology in proteomics for the characterization of proteins, especially for new sequences, such as mAbs. In this study, we propose a deep neural network model, DeepNovo, for de novo peptide sequencing. DeepNovo architecture combines recent advances in convolutional neural networks and recurrent neural networks to learn features of tandem mass spectra, fragment ions, and sequence patterns of peptides. The networks are further integrated with local dynamic programming to solve the complex optimization task of de novo sequencing. We evaluated the method on a wide variety of species and found that DeepNovo considerably outperformed state of the art methods, achieving 7.7-22.9% higher accuracy at the amino acid level and 38.1-64.0% higher accuracy at the peptide level. We further used DeepNovo to automatically reconstruct the complete sequences of antibody light and heavy chains of mouse, achieving 97.5-100% coverage and 97.2-99.5% accuracy, without assisting databases. Moreover, DeepNovo is retrainable to adapt to any sources of data and provides a complete end-to-end training and prediction solution to the de novo sequencing problem. Not only does our study extend the deep learning revolution to a new field, but it also shows an innovative approach in solving optimization problems by using deep learning and dynamic programming.

Authors

  1. Ngoc Hieu Tran · Bioinformatics Solutions Inc., University of Waterloo
  2. Xianglilan Zhang · Beijing Institute of Microbiology and Epidemiology, University of Waterloo
  3. Lei Xin · Bioinformatics Solutions Inc., Western University
  4. Baozhen Shan · Bioinformatics Solutions Inc., Western University
  5. Ming Li · Bioinformatics Solutions Inc., Central China Institute of Artificial Intelligence, Peng Cheng Laboratory, University of Waterloo, University of Western Ontario

Methods and tools

  • DeepNovo: The model that started the deep-learning wave (CNN+LSTM)

Data deposited

Trained on

Evaluated on

Cites (20)

Cited by (155)

Cited in patents (5)

  • US11573239B2 Methods and systems for de novo peptide sequencing using deep learning ↗ (Bioinformatics Solutions Inc., priority 2017-07-17, active)
  • US11694769B2 Systems and methods for de novo peptide sequencing from data-independent acquisition using deep learning ↗ (Bioinformatics Solutions Inc., priority 2017-07-17, active)
  • US12340874B1 Artificial neural network models for prediction of de novo sequencing of chains of amino acids ↗ (Verily Life Sciences, priority 2017-11-03, active)
  • US20200243164A1 Systems and methods for patient-specific identification of neoantigens by de novo peptide sequencing for personalized immunotherapy ↗ (Bioinformatics Solutions Inc., priority 2019-01-30, abandoned)
  • US11644470B2 Systems and methods for de novo peptide sequencing using deep learning and spectrum pairs ↗ (Bioinformatics Solutions Inc., priority 2019-04-15, active)

Patents that list this paper among the literature they cite, whether the applicant or the examiner added it.

Seen in the charts

Back to the full map

Back to top