DeepFLR facilitates false localization rate control in phosphoproteomics

Abstract Protein phosphorylation is a post-translational modification crucial for many cellular processes and protein functions. Accurate identification and quantification of protein phosphosites at the proteome-wide level are challenging, not least because efficient tools for protein phosphosite fa...

Full description

Bibliographic Details
Main Authors: Yu Zong, Yuxin Wang, Yi Yang, Dan Zhao, Xiaoqing Wang, Chengpin Shen, Liang Qiao
Format: Article
Language:English
Published: Nature Portfolio 2023-04-01
Series:Nature Communications
Online Access:https://doi.org/10.1038/s41467-023-38035-1
_version_ 1797840917700280320
author Yu Zong
Yuxin Wang
Yi Yang
Dan Zhao
Xiaoqing Wang
Chengpin Shen
Liang Qiao
author_facet Yu Zong
Yuxin Wang
Yi Yang
Dan Zhao
Xiaoqing Wang
Chengpin Shen
Liang Qiao
author_sort Yu Zong
collection DOAJ
description Abstract Protein phosphorylation is a post-translational modification crucial for many cellular processes and protein functions. Accurate identification and quantification of protein phosphosites at the proteome-wide level are challenging, not least because efficient tools for protein phosphosite false localization rate (FLR) control are lacking. Here, we propose DeepFLR, a deep learning-based framework for controlling the FLR in phosphoproteomics. DeepFLR includes a phosphopeptide tandem mass spectrum (MS/MS) prediction module based on deep learning and an FLR assessment module based on a target-decoy approach. DeepFLR improves the accuracy of phosphopeptide MS/MS prediction compared to existing tools. Furthermore, DeepFLR estimates FLR accurately for both synthetic and biological datasets, and localizes more phosphosites than probability-based methods. DeepFLR is compatible with data from different organisms, instruments types, and both data-dependent and data-independent acquisition approaches, thus enabling FLR estimation for a broad range of phosphoproteomics experiments.
first_indexed 2024-04-09T16:22:40Z
format Article
id doaj.art-4700cd83d821403aa913ca6656447e0f
institution Directory Open Access Journal
issn 2041-1723
language English
last_indexed 2024-04-09T16:22:40Z
publishDate 2023-04-01
publisher Nature Portfolio
record_format Article
series Nature Communications
spelling doaj.art-4700cd83d821403aa913ca6656447e0f2023-04-23T11:22:00ZengNature PortfolioNature Communications2041-17232023-04-0114111610.1038/s41467-023-38035-1DeepFLR facilitates false localization rate control in phosphoproteomicsYu Zong0Yuxin Wang1Yi Yang2Dan Zhao3Xiaoqing Wang4Chengpin Shen5Liang Qiao6Department of Chemistry, and Shanghai Stomatological Hospital, Fudan UniversityDepartment of Chemistry, and Shanghai Stomatological Hospital, Fudan UniversityDepartment of Chemistry, and Shanghai Stomatological Hospital, Fudan UniversityDepartment of Chemistry, and Shanghai Stomatological Hospital, Fudan UniversityShanghai Omicsolution Co., LtdShanghai Omicsolution Co., LtdDepartment of Chemistry, and Shanghai Stomatological Hospital, Fudan UniversityAbstract Protein phosphorylation is a post-translational modification crucial for many cellular processes and protein functions. Accurate identification and quantification of protein phosphosites at the proteome-wide level are challenging, not least because efficient tools for protein phosphosite false localization rate (FLR) control are lacking. Here, we propose DeepFLR, a deep learning-based framework for controlling the FLR in phosphoproteomics. DeepFLR includes a phosphopeptide tandem mass spectrum (MS/MS) prediction module based on deep learning and an FLR assessment module based on a target-decoy approach. DeepFLR improves the accuracy of phosphopeptide MS/MS prediction compared to existing tools. Furthermore, DeepFLR estimates FLR accurately for both synthetic and biological datasets, and localizes more phosphosites than probability-based methods. DeepFLR is compatible with data from different organisms, instruments types, and both data-dependent and data-independent acquisition approaches, thus enabling FLR estimation for a broad range of phosphoproteomics experiments.https://doi.org/10.1038/s41467-023-38035-1
spellingShingle Yu Zong
Yuxin Wang
Yi Yang
Dan Zhao
Xiaoqing Wang
Chengpin Shen
Liang Qiao
DeepFLR facilitates false localization rate control in phosphoproteomics
Nature Communications
title DeepFLR facilitates false localization rate control in phosphoproteomics
title_full DeepFLR facilitates false localization rate control in phosphoproteomics
title_fullStr DeepFLR facilitates false localization rate control in phosphoproteomics
title_full_unstemmed DeepFLR facilitates false localization rate control in phosphoproteomics
title_short DeepFLR facilitates false localization rate control in phosphoproteomics
title_sort deepflr facilitates false localization rate control in phosphoproteomics
url https://doi.org/10.1038/s41467-023-38035-1
work_keys_str_mv AT yuzong deepflrfacilitatesfalselocalizationratecontrolinphosphoproteomics
AT yuxinwang deepflrfacilitatesfalselocalizationratecontrolinphosphoproteomics
AT yiyang deepflrfacilitatesfalselocalizationratecontrolinphosphoproteomics
AT danzhao deepflrfacilitatesfalselocalizationratecontrolinphosphoproteomics
AT xiaoqingwang deepflrfacilitatesfalselocalizationratecontrolinphosphoproteomics
AT chengpinshen deepflrfacilitatesfalselocalizationratecontrolinphosphoproteomics
AT liangqiao deepflrfacilitatesfalselocalizationratecontrolinphosphoproteomics