Interpretable machine learning leverages proteomics to improve cardiovascular disease risk prediction and biomarker identification
In conclusion, we present a more accurate and explanatory framework for proteomics data analysis, supporting future approaches that prioritize individualized disease risk prediction, and identification of target genes for drug development.
Authors
- Matthew Traylor (ORCID: https://orcid.org/0000-0001-6624-8621)
- Nils Koelling (ORCID: https://orcid.org/0000-0001-5292-4510)
- Héctor Climente-González (ORCID: https://orcid.org/0000-0002-3030-7471)
- Sudipto Mukherjee (ORCID: https://orcid.org/0000-0003-2998-5272)
- Robin Abraham (ORCID: https://orcid.org/0000-0003-1915-8118)
- Urszula Chajewska (ORCID: https://orcid.org/0009-0005-0077-4190)
- Sile Hu (ORCID: https://orcid.org/0000-0002-8437-7387)
- Ghazaleh Fatemifar (ORCID: https://orcid.org/0000-0002-2321-4963)
- Jonas Ghouse (ORCID: https://orcid.org/0000-0002-9634-5964)
- Erik Vernet (ORCID: https://orcid.org/0000-0002-4175-1244)
- Wei Gan
- Chuan Li (ORCID: https://orcid.org/0000-0002-4381-3891)
- Liang Du (ORCID: https://orcid.org/0000-0003-1855-9139)
- Roya Hosseini (ORCID: https://orcid.org/0000-0003-0531-5530)
- Min Oh (ORCID: https://orcid.org/0000-0002-0938-9046)
- Joanna M. M. Howson (ORCID: https://orcid.org/0000-0001-7618-0050)
- Paul Pangilinan Del Villar
Institutions
- Microsoft (United States) (US)
- Novo Nordisk (Denmark) (DK)
- Novo Nordisk (Finland) (FI)
Publication Details
- Journal
- Communications Medicine
- Published
- 2025-05-19
- DOI
- https://doi.org/10.1038/s43856-025-00872-0
- Citations
- 8
- Primary Topic
- GDF15 and Related Biomarkers
- Type
- article
- Field-Weighted Citation Impact
- 13.34