SeqNovo: De Novo Peptide Sequencing Prediction in IoMT via Seq2Seq

peer-reviewed · IEEE Journal of Biomedical and Health Informatics · 2023

peer-reviewed · IEEE Journal of Biomedical and Health Informatics · 2023. Ke Wang et al. In the Internet of Medical Things (IoMT), de novo peptide sequencing prediction is one of the most important…
Date 2023-10-04
Type peer-reviewed
Venue IEEE Journal of Biomedical and Health Informatics
Publisher IEEE Journal of Biomedical and Health Informatics
Contribution algorithm
DOI 10.1109/JBHI.2023.3321780
Citations (OpenAlex) 7
Venue 2-year citedness 4.78

Abstract

In the Internet of Medical Things (IoMT), de novo peptide sequencing prediction is one of the most important techniques for the fields of disease prediction, diagnosis, and treatment. Recently, deep-learning-based peptide sequencing prediction has been a new trend. However, most popular deep learning models for peptide sequencing prediction suffer from poor interpretability and poor ability to capture long-range dependencies. To solve these issues, we propose a model named SeqNovo, which has the encoding-decoding structure of sequence to sequence (Seq2Seq), the highly nonlinear properties of multilayer perceptron (MLP), and the ability of the attention mechanism to capture long-range dependencies. SeqNovo use MLP to improve the feature extraction and utilize the attention mechanism to discover key information. A series of experiments have been conducted to show that the SeqNovo is superior to the Seq2Seq benchmark model, DeepNovo. SeqNovo improves both the accuracy and interpretability of the predictions, which will be expected to support more related research.

Authors

  1. Ke Wang · Guizhou University, Jinan University
  2. Mingjia Zhu · Jinan University
  3. Wadii Boulila · Prince Sultan University, University of Manouba
  4. Maha Driss · Prince Sultan University, University of Manouba
  5. Thippa Reddy Gadekallu · Jiaxing University, Lebanese American University, Lovely Professional University, Zhongda Group
  6. Chien-Ming Chen · Nanjing University of Information Science and Technology
  7. Lei Wang · Jinan University
  8. Saru Kumari · Chaudhary Charan Singh University
  9. Siu-Ming Yiu · The University of Hong Kong

Methods and tools

Cites (10)

Cited by (3)

Seen in the charts

Back to the full map

Back to top