Machine learning-based proteomics analysis identified 23 protein biomarkers for enhanced risk prediction of myocardial infarction in Chinese and Europeans
GigaScience · 17.11.2026
DOI: 10.1093/gigascience/giag102 ↗Kurz gefasst
Fachartikel in der Zeitschrift GigaScience, online erschienen am 17.11.2026. Verfasst von Neil Wright und 28 weiteren Autor:innen. Beteiligte Einrichtung: Clinical Trial Service Unit, Nuffield Department of Population Health, University of Oxford, Old Road Campus, Headington, Oxford, UK. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
Background
Advances in proteomics assays enable measurement of thousands of plasma proteins, which could facilitate machine learning-based approaches to enhance risk prediction of disease.
Methods
We measured plasma levels of >9500 proteins among 4000 Chinese adults (1937 myocardial infarction [MI] cases and 2026 subcohort), using both Olink Explore (2923 proteins) and SomaScan (6597 proteins) platforms. Protein-based risk prediction models were constructed, using conventional and machine learning approaches, with model performance assessed via discrimination (C-statistic), classification (net reclassification index; NRI) and calibration. Protein scores were compared and combined with conventional risk factors and polygenic scores (PGS), and externally validated in 37,187 Europeans (630 MI cases) in UK Biobank.
Findings
Overall, 451 Olink and 530 SomaScan proteins were significantly associated (5% false discovery rate) with MI risk after adjustment for conventional risk factors. The protein prediction models based on Olink, SomaScan, or both platforms combined, outperformed conventional risk factors and PGS using discrimination, classification and calibration. The protein score using 23 Boruta-selected (Olink/SomaScan: 11/12) proteins yielded a 3.3-fold difference in 10-year cumulative incidence of MI between the top and bottom 20% risk groups (3.6 [95%CI: 3.1–4.1] vs 1.1 [0.9–1.2] per 100), compared with 2.5-fold (2.5 [2.2–2.9] vs 1.0 [0.9–1.2]) and 1.5-fold (1.9 [1.6–2.1] vs 1.3 [1.1–1.4]) differences for conventional and PGS, respectively. Adding this protein score to conventional risk factors increased C-statistics from 0.846 (0.829–0.862) to 0.864 (0.849–0.879), yielding an NRI of 72%. External validation in 37,187 participants in UK Biobank by adding 23 Boruta-selected proteins to conventional risk factors yielded comparable improvement in C-statistics for MI (from 0.710 [0.688–0.731] to 0.733 [0.710–0.756]) and 45% improvement in NRI (NRI 45%).
Conclusions
Machine learning identified subsets of proteins for improved MI risk prediction beyond conventional risk factors and PGS, showing the potential for developing small panel proteomics assays to improve disease risk prediction.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Clinical Trial Service Unit, Nuffield Department of Population Health, University of Oxford, Old Road Campus, Headington, Oxford, UK.
- Department of Epidemiology and Biostatistics, School of Public Health, Peking University Health Science Center, Beijing, China.
- NCDs Prevention and Control Department, Henan CDC, Henan, China.
- Peking University Center for Public Health and Epidemic Preparedness and Response, Beijing, China.
- Key Laboratory of Epidemiology of Major Diseases, Peking University, Beijing, China.
- China National Center for Food Risk Assessment, Beijing, China.
ORCID-Profile: Neil Wright, Pang Yao, Christiana Kartsonaki, Iona Y Millwood, Andri Iona, Hannah Fry, Pei Pei, Yiping Chen, Baihan Wang, Daniel Avery, Dan Valle Schmidt, Huaidong Du, Ling Yang, Yali Yan, Canqing Yu, DianJianYi Sun, Richard Peto, Rory Collins, Robin G Walters, Derrick A Bennett, Zhengming Chen
Zitieren
APA
Wright, N., Mazidi, M., Pozarickij, A., Yao, P., Kartsonaki, C., Millwood, I. Y., Iona, A., Fry, H., Pei, P., Chen, Y., Wang, B., Avery, D., Schmidt, D. V., Du, H., Yang, L., Yan, Y., Lv, J., Yu, C., Sun, D., …, & China Kadoorie Biobank Collaborative Group (2026). Machine learning-based proteomics analysis identified 23 protein biomarkers for enhanced risk prediction of myocardial infarction in Chinese and Europeans. GigaScience. https://doi.org/10.1093/gigascience/giag102
Vancouver
Wright N, Mazidi M, Pozarickij A, Yao P, Kartsonaki C, Millwood IY, et al. Machine learning-based proteomics analysis identified 23 protein biomarkers for enhanced risk prediction of myocardial infarction in Chinese and Europeans. GigaScience. 2026. doi:10.1093/gigascience/giag102
BibTeX
@article{Wright2026,
author = {Wright, Neil and Mazidi, Mohsen and Pozarickij, Alfred and Yao, Pang and Kartsonaki, Christiana and Millwood, Iona Y and Iona, Andri and Fry, Hannah and Pei, Pei and Chen, Yiping and Wang, Baihan and Avery, Daniel and Schmidt, Dan Valle and Du, Huaidong and Yang, Ling and Yan, Yali and Lv, Jun and Yu, Canqing and Sun, DianJianYi and Chen, Junshi and Hill, Michael and Peto, Richard and Collins, Rory and Walters, Robin G and Bennett, Derrick A and Li, Liming and Clarke, Robert and Chen, Zhengming and China Kadoorie Biobank Collaborative Group, China Kadoorie Biobank Collaborative Group},
title = {Machine learning-based proteomics analysis identified 23 protein biomarkers for enhanced risk prediction of myocardial infarction in Chinese and Europeans},
journal = {GigaScience},
year = {2026},
doi = {10.1093/gigascience/giag102}
}
EUVIMED