PXD049351-1

PXD049351 is an original dataset announced via ProteomeXchange.

Title	Combined clinical and proteomic data accurately discriminate atherosclerotic versus dyslipidemic patients by application of machine learning tools
Description	BACKGROUND. Atherosclerosis disease results from sustained lipid accumulation within the arterial walls and subsequent chronic inflammatory response, being the major responsible of adverse cardiovascular events with high mortality rates worldwide. An early identification of patients at risk of atherosclerotic occlusive events is crucial, in order to prevent further complications with appropriate therapies. Currently, the use of machine learning classification algorithms (MLCA) constitutes a promising alternative in biomedical research, allowing patients classification based on the integration of clinical, genomic and other individual information, which could enhance the application of precision medicine. METHODS. In order to identify discriminating markers of atherosclerosis, a high-throughput approach with six different MLCA was applied to evaluate the clinical information as well as the proteomic changes detected in the serum from hospitalized patients with carotid atherosclerotic stenosis (n:60), compared to diagnosed dyslipidemic patients (with subclinical atheromatous status, n:55) or healthy controls (n:66). RESULTS. The combined approach, considering clinical and individual proteomic data, provided a more accurate classification of patients than the clinical or proteomic analyses alone. Furthermore, a panel of 14 proteins were identified as highly discriminating markers between the groups: ACTB, APOB, B2MG, C4BPA, CO1A1, A1AG1, FIBA, FIBB, FIBG, GPV, MMP9, PCOC1, PLF4, TSP1. Turbidimetric assays validated the changes seen by proteomic analysis. CONCLUSIONS. Our results corroborate the potential of using MLCA in combination with clinical and proteomic data to provide optimal patients classification and enhance precision medicine approaches for atherosclerosis management. Furthermore, a panel of 14 proteins has been highlighted as a potential signature of atherosclerotic progression. Overall, our data addressed the need to orchestrate a multipathway therapy to prevent unwanted thrombotic events, which special emphasis on platelet activation, uncontrolled angiogenesis and intraplaque hemorrhage.
HostingRepository	PRIDE
AnnounceDate	2026-04-13
AnnouncementXML	Submission_2026-04-13_02:28:10.389.xml
DigitalObjectIdentifier
ReviewLevel	Peer-reviewed dataset
DatasetOrigin	Original dataset
RepositorySupport	Unsupported dataset by repository
PrimarySubmitter	Ana Martinez-Val
SpeciesList	scientific name: Homo sapiens (Human); NCBI TaxID: NEWT:9606;
ModificationList	No PTMs are included in the dataset
Instrument	Orbitrap Exploris 480

Revision	Datetime	Status	ChangeLog Entry
0	2024-02-13 05:31:41	ID requested
⏵ 1	2026-04-13 02:28:11	announced

10.1186/s43556-026-00438-z;

Extremera-Garc, í, a MJ, Rojas-Torres M, Priego-Torres B, Beltr, á, n-Camacho L, Eslava-Alc, ó, n S, Rodr, í, guez-Mart, í, n F, Ben, í, tez-Camacho J, Ballesteros-Ribelles A, Del Val AM, Olsen J, Lozano-Loaiza E, Gonz, á, lez-Garc, í, a M Á, Sanchez-Morillo D, Fern, á, ndez-Vega A, Montaner J, Doiz E, Rodriguez-Pi, ñ, ero M, Dur, á, n-Ruiz MC, Machine learning integrated clinical-proteomics data identifies a 6-protein panel signature for atherosclerotic severity and enhanced patient stratification. Mol Biomed, 7(1):(2026) [pubmed]

submitter keyword: HUman Plasma, Machine Learning, Atherosclerosis

Jesper V. Olsen
contact affiliation	Vice Director, Professor Novo Nordisk Foundation Center for Protein Research Proteomics Program University of Copenhagen Faculty of Health and Medical Sciences Blegdamsvej 3b DK-2200 Copenhagen Denmark
contact email	jesper.olsen@cpr.ku.dk
lab head
Ana Martinez-Val
contact affiliation	Novo Nordisk Foundation Center for Protein Research
contact email	ana.mdval@cpr.ku.dk
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/2026/04/PXD049351

PRIDE project URI

• PRIDE
  1. PXD049351
     1. Label: PRIDE project
     2. Name: Combined clinical and proteomic data accurately discriminate atherosclerotic versus dyslipidemic patients by application of machine learning tools