Integrated proteomics and machine learning reveal AHNAK as a discriminative biomarker of atrial fibrillation in heart failure.
8 affiliations
- 1Department of Cardiology, the First Affiliated Hospital of Sun Yat-Sen University, Guangzhou, 510080, PR China. [email protected].
- 2Department of Cardiology, the First Affiliated Hospital of Sun Yat-Sen University, Guangzhou, 510080, PR China.
- 3Department of Medical Ultrasonics, Institute for Diagnostic and Interventional Ultrasound, The First Affiliated Hospital, Sun Yat-sen University, Guangzhou, P. R. China.
- 4NHC Key Laboratory of Assisted Circulation and Vascular Diseases, Sun Yat-sen University), Guangzhou, 510080, China.
- 5Department of Cardiology, the First Affiliated Hospital of Sun Yat-Sen University, Guangzhou, 510080, PR China. [email protected].
- 6Department of Cardiology, the First Affiliated Hospital of Sun Yat-Sen University, Guangzhou, 510080, PR China. [email protected].
- 7NHC Key Laboratory of Assisted Circulation and Vascular Diseases, Sun Yat-sen University), Guangzhou, 510080, China. [email protected].
- 8National-Guangdong Joint Engineering Laboratory for Diagnosis and Treatment of Vascular Diseases, Guangzhou, 510080, China. [email protected].
Abstract
Background
Atrial fibrillation (AF) is a frequent complication of heart failure (HF), markedly increasing morbidity and mortality. Although atrial fibrosis is increasingly recognized as a central mechanistic substrate linking HF to AF, the molecular determinants driving fibrotic remodeling and enabling early AF discrimination in HF remain poorly defined.Methods
We integrated label-free quantitative plasma proteomics with machine learning-based feature selection to analyze samples from 59 age- and sex-matched patients hospitalized with acute decompensated HF. Differentially expressed proteins were subjected to functional and pathway enrichment analyses, and candidate biomarkers were prioritized using an incremental feature selection framework. AHNAK, the top-ranked candidate, was functionally interrogated in vitro using TGF-β1-stimulated primary mouse atrial fibroblasts with siRNA-mediated knockdown and in vivo using a pressure overload-induced HF model in AHNAK heterozygous mice. A two-sample Mendelian randomization analysis was performed to evaluate the association between genetically proxied AHNAK expression and AF risk.Results
Plasma proteomic profiling identified 126 proteins that were significantly dysregulated in HF patients with AF compared with those in sinus rhythm, among which AHNAK was the most upregulated. Machine learning-based feature selection consistently ranked AHNAK as the most discriminative protein, with robust performance for AF discrimination in HF patients (AUC = 0.897, 95% confidence interval: 0.82-0.97). Functionally, AHNAK heterozygous deficiency promoted a profibrotic phenotype, characterized by increased expression of α-smooth muscle actin, fibronectin, and collagen Iα in atrial fibroblasts and exacerbated atrial fibrosis and cardiac dysfunction in pressure-overloaded mice. Mendelian randomization analysis demonstrated a significant protective effect of higher AHNAK expression against AF, with no evidence of horizontal pleiotropy.Conclusions
This study identifies AHNAK as a discriminative plasma biomarker for AF in HF patients and implicates AHNAK deficiency as a contributor to atrial fibrotic remodeling and AF pathogenesis. External validation in larger and prospective HF cohorts will be required to confirm the clinical utility of AHNAK for AF risk stratification and early detection.
Related
- Differentiating benign from malignant adnexal masses by biomarker-agnostic plasma proteomics using adaptive machine learning
- High-Throughput Proteomics in Lymphangioleiomyomatosis: Premelanosome Protein as a Diagnostic Biomarker, Construction of a Diagnosis Score, and Evidence of Neutrophil Involvement
- Fine-grained Chinese dish recognition on CNFOOD-241: A discriminative learning approach for improving category-level discrimination
- Identification of hepatitis B virus-associated membrane proteins as prognostic biomarkers for hepatocellular carcinoma based on retrospective analysis of integrated membrane proteomics
- 2026 Asia Pacific Heart Rhythm Society (APHRS) Guidelines (Part I) on Epidemiology, Detection/Screening and Integrated Patient Care in Atrial Fibrillation.
BibTeX
@article{zhu2026integrated,
title = {{Integrated proteomics and machine learning reveal AHNAK as a discriminative biomarker of atrial fibrillation in heart failure.}},
author = {Wengen Zhu and Zhenbang Gu and Yuwen Huang and Min Ye and Ruicong Xue and Yugang Dong and Yuzhong Wu and Chen Liu},
journal = {BMC medicine},
year = {2026},
month = jul,
doi = {10.1186/s12916-026-05079-1},
url = {https://europepmc.org/article/MED/42902265},
note = {CC BY-NC-ND},
}
RIS
TY - JOUR
TI - Integrated proteomics and machine learning reveal AHNAK as a discriminative biomarker of atrial fibrillation in heart failure.
AU - Wengen Zhu
AU - Zhenbang Gu
AU - Yuwen Huang
AU - Min Ye
AU - Ruicong Xue
AU - Yugang Dong
AU - Yuzhong Wu
AU - Chen Liu
PY - 2026
DA - 2026/07/01
JO - BMC medicine
DO - 10.1186/s12916-026-05079-1
UR - https://europepmc.org/article/MED/42902265
AB - Background Atrial fibrillation (AF) is a frequent complication of heart failure (HF), markedly increasing morbidity and mortality. Although atrial fibrosis is increasingly recognized as a central mechanistic substrate linking HF to AF, the molecular determinants driving fibrotic remodeling and enabling early AF discrimination in HF remain poorly defined.Methods We integrated label-free quantitative plasma proteomics with machine learning-based feature selection to analyze samples from 59 age- and sex-matched patients hospitalized with acute decompensated HF. Differentially expressed proteins were subjected to functional and pathway enrichment analyses, and candidate biomarkers were prioritized using an incremental feature selection framework. AHNAK, the top-ranked candidate, was functionally interrogated in vitro using TGF-β1-stimulated primary mouse atrial fibroblasts with siRNA-mediated knockdown and in vivo using a pressure overload-induced HF model in AHNAK heterozygous mice. A two-sample Mendelian randomization analysis was performed to evaluate the association between genetically proxied AHNAK expression and AF risk.Results Plasma proteomic profiling identified 126 proteins that were significantly dysregulated in HF patients with AF compared with those in sinus rhythm, among which AHNAK was the most upregulated. Machine learning-based feature selection consistently ranked AHNAK as the most discriminative protein, with robust performance for AF discrimination in HF patients (AUC = 0.897, 95% confidence interval: 0.82-0.97). Functionally, AHNAK heterozygous deficiency promoted a profibrotic phenotype, characterized by increased expression of α-smooth muscle actin, fibronectin, and collagen Iα in atrial fibroblasts and exacerbated atrial fibrosis and cardiac dysfunction in pressure-overloaded mice. Mendelian randomization analysis demonstrated a significant protective effect of higher AHNAK expression against AF, with no evidence of horizontal pleiotropy.Conclusions This study identifies AHNAK as a discriminative plasma biomarker for AF in HF patients and implicates AHNAK deficiency as a contributor to atrial fibrotic remodeling and AF pathogenesis. External validation in larger and prospective HF cohorts will be required to confirm the clinical utility of AHNAK for AF risk stratification and early detection.
SN - 1741-7015
ER -