Suppr超能文献

PGPointNovo:一种用于并行肽段测序的高效神经网络工具。

PGPointNovo: an efficient neural network-based tool for parallel peptide sequencing.

作者信息

Xu Xiaofang, Yang Chunde, He Qiang, Shu Kunxian, Xinpu Yuan, Chen Zhiguang, Zhu Yunping, Chen Tao

机构信息

The School of Computer Science and Technology, Chongqing University of Posts and Telecommunications, Chongqing 400065, China.

School of Software and Electrical Engineering, Swinburne University of Technology, Melbourne, Victoria 3122, Australia.

出版信息

Bioinform Adv. 2023 Apr 25;3(1):vbad057. doi: 10.1093/bioadv/vbad057. eCollection 2023.

Abstract

SUMMARY

peptide sequencing for tandem mass spectrometry data is not only a key technology for novel peptide identification, but also a precedent task for many downstream tasks, such as vaccine and antibody studies. In recent years, neural network models for peptide sequencing have manifested a remarkable ability to accommodate various data sources and outperformed conventional peptide identification tools. However, the excellent model is computationally expensive, taking up to 1 week to process about 400 000 spectrums. This article presents PGPointNovo, a novel neural network-based tool for parallel peptide sequencing. PGPointNovo uses data parallelization technology to accelerate training and inference and optimizes the training obstacles caused by large batch sizes. The results of extensive experiments conducted on multiple datasets of different sizes demonstrate that compared with PointNovo the excellent neural network-based peptide sequencing tool, PGPointNovo, accelerates peptide sequencing by up to 7.35× without precision or recall compromises.

AVAILABILITY AND IMPLEMENTATION

The source code and the parameter settings are available at https://github.com/shallFun4Learning/PGPointNovo.

SUPPLEMENTARY INFORMATION

Supplementary data are available at online.

摘要

摘要

串联质谱数据的肽段测序不仅是鉴定新型肽段的关键技术,也是许多下游任务(如疫苗和抗体研究)的前置任务。近年来,用于肽段测序的神经网络模型已展现出整合各种数据源的卓越能力,且性能优于传统的肽段鉴定工具。然而,性能优异的模型计算成本高昂,处理约400000个谱图耗时长达1周。本文介绍了PGPointNovo,一种基于神经网络的新型并行肽段测序工具。PGPointNovo采用数据并行化技术加速训练和推理,并优化了由大批量数据导致的训练障碍。在多个不同规模数据集上进行的大量实验结果表明,与基于神经网络的优秀肽段测序工具PointNovo相比,PGPointNovo在不损失精度或召回率的情况下,将肽段测序速度提高了7.35倍。

可用性与实现方式

源代码和参数设置可在https://github.com/shallFun4Learning/PGPointNovo获取。

补充信息

补充数据可在线获取。

相似文献

1
PGPointNovo: an efficient neural network-based tool for parallel peptide sequencing.
Bioinform Adv. 2023 Apr 25;3(1):vbad057. doi: 10.1093/bioadv/vbad057. eCollection 2023.
2
MRUniNovo: an efficient tool for de novo peptide sequencing utilizing the hadoop distributed computing framework.
Bioinformatics. 2017 Mar 15;33(6):944-946. doi: 10.1093/bioinformatics/btw721.
4
SWPepNovo: An Efficient De Novo Peptide Sequencing Tool for Large-scale MS/MS Spectra Analysis.
Int J Biol Sci. 2019 Jul 3;15(9):1787-1801. doi: 10.7150/ijbs.32142. eCollection 2019.
5
DNMSO; an ontology for representing de novo sequencing results from Tandem-MS data.
PeerJ. 2020 Oct 21;8:e10216. doi: 10.7717/peerj.10216. eCollection 2020.
6
De novo peptide sequencing by deep learning.
Proc Natl Acad Sci U S A. 2017 Aug 1;114(31):8247-8252. doi: 10.1073/pnas.1705691114. Epub 2017 Jul 18.
8
PDV: an integrative proteomics data viewer.
Bioinformatics. 2019 Apr 1;35(7):1249-1251. doi: 10.1093/bioinformatics/bty770.
9
pNovo 3: precise de novo peptide sequencing using a learning-to-rank framework.
Bioinformatics. 2019 Jul 15;35(14):i183-i190. doi: 10.1093/bioinformatics/btz366.
10
MCtandem: an efficient tool for large-scale peptide identification on many integrated core (MIC) architecture.
BMC Bioinformatics. 2019 Jul 17;20(1):397. doi: 10.1186/s12859-019-2980-5.

引用本文的文献

1
A learned score function improves the power of mass spectrometry database search.
Bioinformatics. 2024 Jun 28;40(Suppl 1):i410-i417. doi: 10.1093/bioinformatics/btae218.
2
Emerging potential of immunopeptidomics by mass spectrometry in cancer immunotherapy.
Cancer Sci. 2024 Apr;115(4):1048-1059. doi: 10.1111/cas.16118. Epub 2024 Feb 21.

本文引用的文献

1
iProX in 2021: connecting proteomics data sharing with big data.
Nucleic Acids Res. 2022 Jan 7;50(D1):D1522-D1527. doi: 10.1093/nar/gkab1081.
2
sequencing of proteins by mass spectrometry.
Expert Rev Proteomics. 2020 Jul-Aug;17(7-8):595-607. doi: 10.1080/14789450.2020.1831387. Epub 2020 Oct 21.
3
De novo peptide sequencing by deep learning.
Proc Natl Acad Sci U S A. 2017 Aug 1;114(31):8247-8252. doi: 10.1073/pnas.1705691114. Epub 2017 Jul 18.
4
MRUniNovo: an efficient tool for de novo peptide sequencing utilizing the hadoop distributed computing framework.
Bioinformatics. 2017 Mar 15;33(6):944-946. doi: 10.1093/bioinformatics/btw721.

文献AI研究员

20分钟写一篇综述,助力文献阅读效率提升50倍。

立即体验

用中文搜PubMed

大模型驱动的PubMed中文搜索引擎

马上搜索

文档翻译

学术文献翻译模型,支持多种主流文档格式。

立即体验