Dataset Information

Combined clinical and proteomic data accurately discriminate atherosclerotic versus dyslipidemic patients by application of machine learning tools

ABSTRACT: 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.

INSTRUMENT(S):

ORGANISM(S): Homo Sapiens (human)

TISSUE(S): Blood Plasma

SUBMITTER: Ana Martinez-Val

LAB HEAD: Jesper V. Olsen

PROVIDER: PXD049351 | Pride | 2026-04-13

REPOSITORIES: Pride

ACCESS DATA

Dataset's files

Source:

			Action	DRS
	20220520_EXPL1_EVO0_AMV_Collab_UCA_30SPD_DIA_Plasma_ATER_01.raw	Raw
	20220520_EXPL1_EVO0_AMV_Collab_UCA_30SPD_DIA_Plasma_ATER_010.raw	Raw
	20220520_EXPL1_EVO0_AMV_Collab_UCA_30SPD_DIA_Plasma_ATER_011.raw	Raw
	20220520_EXPL1_EVO0_AMV_Collab_UCA_30SPD_DIA_Plasma_ATER_012.raw	Raw
	20220520_EXPL1_EVO0_AMV_Collab_UCA_30SPD_DIA_Plasma_ATER_013.raw	Raw

Items per page:

1 - 5 of 128

Publications

Machine learning integrated clinical-proteomics data identifies a 6-protein panel signature for atherosclerotic severity and enhanced patient stratification.

Extremera-García Mª Jesús MJ Rojas-Torres Marta M Priego-Torres Blanca B Beltrán-Camacho Lucía L Eslava-Alcón Sara S Rodríguez-Martín Francisco F Benítez-Camacho Josefa J Ballesteros-Ribelles Antonio A Del Val Ana Martínez AM Olsen Jesper J Lozano-Loaiza Eva E González-García Mª Ángela MÁ Sanchez-Morillo Daniel D Fernández-Vega Alejandro A Montaner Joan J Doiz Esther E Rodriguez-Piñero Manuel M Durán-Ruiz Mª Carmen MC

Molecular biomedicine 20260410 1

Atherosclerosis, a major cause of adverse cardiovascular events and mortality rates worldwide, stems from sustained lipid accumulation and subsequent chronic inflammation within the arterial walls. An early identification of patients at risk is crucial to prevent life-threatening thrombotic events and provide effective and personalized treatments. Leveraging the power of machine learning (ML) to enhance diagnostics and biomarker discovery, we applied a high-throughput approach using five ML clas ...[more]

PMID: 41961364

Similar Datasets

Project description:Monocytes and T-cells play an important role in the development of atherosclerotic coronary artery disease (CAD). Differences in transcriptional activity of these cells might reflect the individual's atherosclerotic burden. Transcriptome analysis of circulating mononuclear cells from carefully matched atherosclerotic and control patients will potentially provide insights into the pathophysiology of atherosclerosis and supply biomarkers for diagnostic purposes. From patients undergoing coronary angiography because of anginal symptoms, we carefully matched 18 patients with severe triple-vessel CAD to 13 control patients without signs of CAD on angiography. All patients were on statin and aspirin treatment. RNA from circulating CD4+ T-cells, CD14+ monocytes, lipopolysaccharide-stimulated monocytes, macrophages and CD34+ progenitor cells was subjected to genome-wide expression analysis. Only CD14+ monocytes demonstrated that a small number of genes involved in activation was overexpressed in control patients, which was verified by real-time polymerase-chain reaction. In this pilot study, cautious matching of patients with severe atherosclerotic CAD with control patients without angiographic signs of coronary atherosclerosis did not reveal differences in transcriptional activity in four out of five different mononuclear cell types. In resting monocytes from patients without overt CAD some inflammatory genes were overexpressed as compared to patients with severe CAD. Large inter-individual variability prevented the use of single differentially expressed genes as biomarkers. Keywords: disease-state analysis In total 153 arrays were analyzed with 6 technical replicates (147 biological samples). CD34+ stem cells, CD4+ T-cells, resting CD14+ monocytes, stimulated monocytes and macrophages were analyzed, all from patient with severe coronary atherosclerosis or controls that had no coronary atherosclerosis as determined angiographically, and which were carefully matched for age and gender.