*Result*: Machine learning-guided deconvolution of plasma protein levels.
Title:
Machine learning-guided deconvolution of plasma protein levels.
Authors:
Pietzner M; Computational Medicine, Berlin Institute of Health at Charité - Universitätsmedizin Berlin, Berlin, Germany. maik.pietzner@bih-charite.de.; Precision Healthcare University Research Institute, Queen Mary University of London, London, UK. maik.pietzner@bih-charite.de.; DZHK (German Centre for Cardiovascular Research), partner site Berlin, Berlin, Germany. maik.pietzner@bih-charite.de., Beuchel C; Computational Medicine, Berlin Institute of Health at Charité - Universitätsmedizin Berlin, Berlin, Germany.; DZHK (German Centre for Cardiovascular Research), partner site Berlin, Berlin, Germany., Demircan K; Computational Medicine, Berlin Institute of Health at Charité - Universitätsmedizin Berlin, Berlin, Germany.; Precision Healthcare University Research Institute, Queen Mary University of London, London, UK., Hoffmann Anton J; Precision Healthcare University Research Institute, Queen Mary University of London, London, UK., Zeng W; Computational Medicine, Berlin Institute of Health at Charité - Universitätsmedizin Berlin, Berlin, Germany., Römisch-Margl W; Institute of Computational Biology, Helmholtz Zentrum München - German Research Center for Environmental Health, Neuherberg, Germany., Yasmeen S; Computational Medicine, Berlin Institute of Health at Charité - Universitätsmedizin Berlin, Berlin, Germany., Uluvar B; Computational Medicine, Berlin Institute of Health at Charité - Universitätsmedizin Berlin, Berlin, Germany., Zoodsma M; Computational Medicine, Berlin Institute of Health at Charité - Universitätsmedizin Berlin, Berlin, Germany.; DZHK (German Centre for Cardiovascular Research), partner site Berlin, Berlin, Germany., Koprulu M; Precision Healthcare University Research Institute, Queen Mary University of London, London, UK., Kastenmüller G; Institute of Computational Biology, Helmholtz Zentrum München - German Research Center for Environmental Health, Neuherberg, Germany., Carrasco-Zanini J; Precision Healthcare University Research Institute, Queen Mary University of London, London, UK., Langenberg C; Computational Medicine, Berlin Institute of Health at Charité - Universitätsmedizin Berlin, Berlin, Germany. claudia.langenberg@qmul.ac.uk.; Precision Healthcare University Research Institute, Queen Mary University of London, London, UK. claudia.langenberg@qmul.ac.uk.; DZHK (German Centre for Cardiovascular Research), partner site Berlin, Berlin, Germany. claudia.langenberg@qmul.ac.uk.
Source:
Molecular systems biology [Mol Syst Biol] 2025 Dec; Vol. 21 (12), pp. 1822-1844. Date of Electronic Publication: 2025 Oct 09.
Publication Type:
Journal Article
Language:
English
Journal Info:
Publisher: EMBO Press Country of Publication: Germany NLM ID: 101235389 Publication Model: Print-Electronic Cited Medium: Internet ISSN: 1744-4292 (Electronic) Linking ISSN: 17444292 NLM ISO Abbreviation: Mol Syst Biol Subsets: MEDLINE
Imprint Name(s):
Publication: 2024- : Heidelberg : EMBO Press
Original Publication: London : Nature Pub. Group, c2005-
Original Publication: London : Nature Pub. Group, c2005-
MeSH Terms:
References:
Nature. 2023 Dec;624(7990):164-172. (PMID: 38057571)
Nat Genet. 2021 Feb;53(2):185-194. (PMID: 33462484)
Nature. 2018 Jun;558(7708):73-79. (PMID: 29875488)
Nat Rev Genet. 2021 Jan;22(1):19-37. (PMID: 32860016)
Nat Aging. 2024 Jun;4(6):871-885. (PMID: 38724736)
Bioinformatics. 2012 Jan 1;28(1):112-8. (PMID: 22039212)
Nature. 2023 Oct;622(7982):339-347. (PMID: 37794183)
Science. 2024 Sep 27;385(6716):eads5749. (PMID: 39325883)
Science. 2018 Aug 24;361(6404):769-773. (PMID: 30072576)
Nat Metab. 2024 Apr;6(4):764-777. (PMID: 38429390)
Circ Res. 2023 Feb 17;132(4):432-448. (PMID: 36691905)
Int J Mol Sci. 2024 May 27;25(11):. (PMID: 38891996)
Nat Rev Cardiol. 2009 Jul;6(7):464-74. (PMID: 19468292)
Respir Med. 2017 Oct;131:184-191. (PMID: 28947028)
JAMA. 1971 Sep 6;217(10):1349-53. (PMID: 5109641)
Pharmacol Rev. 2015;67(1):118-75. (PMID: 25428932)
Annu Rev Pharmacol. 1969;9:363-78. (PMID: 4892431)
Lancet. 1972 Dec 23;2(7791):1369. (PMID: 4118235)
Science. 2015 Jan 23;347(6220):1260419. (PMID: 25613900)
Nat Med. 2024 Sep;30(9):2489-2498. (PMID: 39039249)
Nat Genet. 2020 Oct;52(10):1122-1131. (PMID: 32895551)
Nature. 2023 Oct;622(7982):329-338. (PMID: 37794186)
Nat Metab. 2024 Oct;6(10):2010-2023. (PMID: 39327534)
Sci Signal. 2019 Nov 26;12(609):. (PMID: 31772123)
J Clin Invest. 1998 Dec 1;102(11):1900-10. (PMID: 9835614)
J Hypertens. 2008 Dec;26(12):2445-9. (PMID: 19008724)
Cell Death Dis. 2022 Oct 29;13(10):911. (PMID: 36309486)
Nat Genet. 2025 Oct;57(10):2408-2417. (PMID: 40968291)
Cell. 2025 Jan 09;188(1):253-271.e7. (PMID: 39579765)
J Thromb Haemost. 2022 Jun;20(6):1437-1450. (PMID: 35253976)
Nature. 2023 Apr;616(7955):123-131. (PMID: 36991119)
EMBO Mol Med. 2025 Nov;17(11):3174-3196. (PMID: 40940569)
Nucleic Acids Res. 2019 Jan 8;47(D1):D1005-D1012. (PMID: 30445434)
Nature. 2018 Oct;562(7726):203-209. (PMID: 30305743)
Nat Commun. 2019 Apr 23;10(1):1891. (PMID: 31015401)
JAMA. 2023 Aug 22;330(8):725-735. (PMID: 37606673)
Nucleic Acids Res. 2023 Jan 6;51(D1):D1353-D1359. (PMID: 36399499)
Clin Chem. 2017 May;63(5):963-972. (PMID: 28270433)
Annu Rev Biomed Data Sci. 2021 Jul 20;4:1-19. (PMID: 34465180)
Sci Adv. 2021 Jul 28;7(31):. (PMID: 34321199)
PLoS Med. 2015 Mar 31;12(3):e1001779. (PMID: 25826379)
Atherosclerosis. 2024 Nov;398:118613. (PMID: 39340936)
J Invest Dermatol. 2004 Apr;122(4):1050-3. (PMID: 15102097)
Nature. 2023 Oct;622(7982):348-358. (PMID: 37794188)
EMBO Mol Med. 2019 Nov 7;11(11):e10427. (PMID: 31566909)
Science. 2021 Nov 12;374(6569):eabj1541. (PMID: 34648354)
Nat Commun. 2024 Jul 31;15(1):6462. (PMID: 39085232)
Am J Hum Genet. 2022 May 5;109(5):767-782. (PMID: 35452592)
Nat Genet. 2021 Feb;53(2):185-194. (PMID: 33462484)
Nature. 2018 Jun;558(7708):73-79. (PMID: 29875488)
Nat Rev Genet. 2021 Jan;22(1):19-37. (PMID: 32860016)
Nat Aging. 2024 Jun;4(6):871-885. (PMID: 38724736)
Bioinformatics. 2012 Jan 1;28(1):112-8. (PMID: 22039212)
Nature. 2023 Oct;622(7982):339-347. (PMID: 37794183)
Science. 2024 Sep 27;385(6716):eads5749. (PMID: 39325883)
Science. 2018 Aug 24;361(6404):769-773. (PMID: 30072576)
Nat Metab. 2024 Apr;6(4):764-777. (PMID: 38429390)
Circ Res. 2023 Feb 17;132(4):432-448. (PMID: 36691905)
Int J Mol Sci. 2024 May 27;25(11):. (PMID: 38891996)
Nat Rev Cardiol. 2009 Jul;6(7):464-74. (PMID: 19468292)
Respir Med. 2017 Oct;131:184-191. (PMID: 28947028)
JAMA. 1971 Sep 6;217(10):1349-53. (PMID: 5109641)
Pharmacol Rev. 2015;67(1):118-75. (PMID: 25428932)
Annu Rev Pharmacol. 1969;9:363-78. (PMID: 4892431)
Lancet. 1972 Dec 23;2(7791):1369. (PMID: 4118235)
Science. 2015 Jan 23;347(6220):1260419. (PMID: 25613900)
Nat Med. 2024 Sep;30(9):2489-2498. (PMID: 39039249)
Nat Genet. 2020 Oct;52(10):1122-1131. (PMID: 32895551)
Nature. 2023 Oct;622(7982):329-338. (PMID: 37794186)
Nat Metab. 2024 Oct;6(10):2010-2023. (PMID: 39327534)
Sci Signal. 2019 Nov 26;12(609):. (PMID: 31772123)
J Clin Invest. 1998 Dec 1;102(11):1900-10. (PMID: 9835614)
J Hypertens. 2008 Dec;26(12):2445-9. (PMID: 19008724)
Cell Death Dis. 2022 Oct 29;13(10):911. (PMID: 36309486)
Nat Genet. 2025 Oct;57(10):2408-2417. (PMID: 40968291)
Cell. 2025 Jan 09;188(1):253-271.e7. (PMID: 39579765)
J Thromb Haemost. 2022 Jun;20(6):1437-1450. (PMID: 35253976)
Nature. 2023 Apr;616(7955):123-131. (PMID: 36991119)
EMBO Mol Med. 2025 Nov;17(11):3174-3196. (PMID: 40940569)
Nucleic Acids Res. 2019 Jan 8;47(D1):D1005-D1012. (PMID: 30445434)
Nature. 2018 Oct;562(7726):203-209. (PMID: 30305743)
Nat Commun. 2019 Apr 23;10(1):1891. (PMID: 31015401)
JAMA. 2023 Aug 22;330(8):725-735. (PMID: 37606673)
Nucleic Acids Res. 2023 Jan 6;51(D1):D1353-D1359. (PMID: 36399499)
Clin Chem. 2017 May;63(5):963-972. (PMID: 28270433)
Annu Rev Biomed Data Sci. 2021 Jul 20;4:1-19. (PMID: 34465180)
Sci Adv. 2021 Jul 28;7(31):. (PMID: 34321199)
PLoS Med. 2015 Mar 31;12(3):e1001779. (PMID: 25826379)
Atherosclerosis. 2024 Nov;398:118613. (PMID: 39340936)
J Invest Dermatol. 2004 Apr;122(4):1050-3. (PMID: 15102097)
Nature. 2023 Oct;622(7982):348-358. (PMID: 37794188)
EMBO Mol Med. 2019 Nov 7;11(11):e10427. (PMID: 31566909)
Science. 2021 Nov 12;374(6569):eabj1541. (PMID: 34648354)
Nat Commun. 2024 Jul 31;15(1):6462. (PMID: 39085232)
Am J Hum Genet. 2022 May 5;109(5):767-782. (PMID: 35452592)
Grant Information:
101116072 EC | ERC | HORIZON EUROPE European Research Council (ERC); 547107463 Deutsche Forschungsgemeinschaft (DFG); 81X2100281 Bundesministerium für Bildung und Forschung (BMBF); 031A532B Bundesministerium für Bildung und Forschung (BMBF); 031A533A Bundesministerium für Bildung und Forschung (BMBF); 031A533B Bundesministerium für Bildung und Forschung (BMBF); 031A534A Bundesministerium für Bildung und Forschung (BMBF); 031A535A Bundesministerium für Bildung und Forschung (BMBF); 031A537A Bundesministerium für Bildung und Forschung (BMBF); 031A537B Bundesministerium für Bildung und Forschung (BMBF); 031A537C Bundesministerium für Bildung und Forschung (BMBF); 031A537D Bundesministerium für Bildung und Forschung (BMBF); 031A538A Bundesministerium für Bildung und Forschung (BMBF); DZHK Bundesministerium für Bildung und Forschung (BMBF)
Contributed Indexing:
Keywords: Biomarker; Drugs; Enrichment; Plasma Proteomics
Substance Nomenclature:
0 (Blood Proteins)
0 (Biomarkers)
0 (Biomarkers)
Entry Date(s):
Date Created: 20251009 Date Completed: 20251202 Latest Revision: 20251205
Update Code:
20260130
PubMed Central ID:
PMC12672695
DOI:
10.1038/s44320-025-00158-6
PMID:
41068475
Database:
MEDLINE
*Further Information*
*Proteomic techniques now measure thousands of proteins circulating in blood at population scale, but successful translation into clinically useful protein biomarkers is hampered by our limited understanding of their origins. Here, we use machine learning to systematically identify a median of 20 factors (range: 1-37) out of >1800 participant and sample charateristics that jointly explained an average of 19.4% (max. 100.0%) of the variance in plasma levels of ~3000 protein targets among 43,240 individuals. Proteins segregated into distinct clusters according to their explanatory factors, with modifiable characteristics explaining more variance compared to genetic variation (median: 10.0% vs 3.9%), and factors being largely consistent across the sexes and ancestral groups. We establish a knowledge graph that integrates our findings with genetic studies and drug characteristics to guide identification of potential drug target engagement markers. We demonstrate the value of our resource by identifying disease-specific biomarkers, like matrix metalloproteinase 12 for abdominal aortic aneurysm, and by developing a widely applicable framework for phenotype enrichment (R package: https://github.com/comp-med/r-prodente ). All results are explorable via an interactive web portal ( https://omicscience.org/apps/prot_foundation ).
(© 2025. The Author(s).)*
*Disclosure and competing interests statement. The authors declare no competing interests.*