PXD072999

PXD072999 is an original dataset announced via ProteomeXchange.

Title	DDA-BERT: end-to-end training for data-dependent acquisition mass spectrometry-based proteomics
Description	This project provides a large-scale training dataset for DDA-BERT, an end-to-end transformer-based deep learning model developed for PSM rescoring in data-dependent acquisition (DDA) proteomics. The dataset comprises curated PSMs generated using established database search engines, including FragPipe, Sage, and AlphaPept, and is intended to support the training of the DDA-BERT model.
HostingRepository	PRIDE
AnnounceDate	2026-08-24
AnnouncementXML	Submission_2026-08-23_19:09:25.208.xml
DigitalObjectIdentifier
ReviewLevel	Peer-reviewed dataset
DatasetOrigin	Original dataset
RepositorySupport	Unsupported dataset by repository
PrimarySubmitter	Jun A
SpeciesList	scientific name: Bacillus subtilis; NCBI TaxID: NEWT:1423; scientific name: Homo sapiens (Human); NCBI TaxID: NEWT:9606; scientific name: Chlamydomonas reinhardtii; NCBI TaxID: NEWT:3055; scientific name: Mus musculus (Mouse); NCBI TaxID: NEWT:10090; scientific name: Rattus norvegicus (Rat); NCBI TaxID: NEWT:10116; scientific name: Saccharomyces cerevisiae (Baker's yeast); NCBI TaxID: NEWT:4932; scientific name: Escherichia coli; NCBI TaxID: NEWT:562; scientific name: Arabidopsis thaliana (Mouse-ear cress); NCBI TaxID: NEWT:3702; scientific name: Caenorhabditis elegans; NCBI TaxID: NEWT:6239; scientific name: Bacillus cereus; NCBI TaxID: NEWT:1396; scientific name: Glycine max; NCBI TaxID: NEWT:3847;
ModificationList	S-carboxamidoethyl-L-cysteine; acetylated residue; monohydroxylated residue; iodoacetamide derivatized residue
Instrument	Orbitrap Eclipse; Q Exactive HF; Orbitrap Fusion Lumos; Orbitrap Exploris 480; Orbitrap Fusion ETD; PinPoint; Q Exactive HF-X; Q Exactive; Orbitrap Fusion; LTQ Orbitrap

Revision	Datetime	Status	ChangeLog Entry
0	2026-01-13 01:38:07	ID requested
⏵ 1	2026-08-23 19:09:26	announced

A J, Liu P, Sun Y, Lin J, Zhang X, Nie Z, Liu J, Yu Z, Zhang Y, Xing Z, Chen Y, Guo T, DDA-BERT: end-to-end training for data-dependent acquisition mass spectrometry-based proteomics. Nat Commun, 17(1):(2026) [pubmed]

10.1038/s41467-026-72246-6;

submitter keyword: Deep learning, DDA proteomics, Peptide-spectrum matches (PSMs) rescoring, DDA-BERT, peptide identification

Tiannan Guo
contact affiliation	Westlake University
contact email	guotiannan@westlake.edu.cn
lab head
Jun A
contact affiliation	Westlake University
contact email	ajun@westlake.edu.cn
dataset submitter

Dataset FTP location NOTE: Most web browsers have now discontinued native support for FTP access within the browser window. But you can usually install another FTP app (we recommend FileZilla) and configure your browser to launch the external application when you click on this FTP link. Or otherwise, launch an app that supports FTP (like FileZilla) and use this address: ftp://ftp.pride.ebi.ac.uk/pride/data/archive/2026/08/PXD072999

PRIDE project URI

• PRIDE
  1. PXD072999
     1. Label: PRIDE project
     2. Name: DDA-BERT: end-to-end training for data-dependent acquisition mass spectrometry-based proteomics