Back

Blood protein levels predict leading incident diseases and mortality in UK Biobank

Gadd, D. A.; Hillary, R. F.; Kuncheva, Z.; Mangelis, T.; Admanit, R.; Gagnon, J.; Lin, T.; Ferber, K.; Runz, H.; Biogen Biobank Team, ; Marioni, R. E.; Foley, C. N.; Sun, B. B.

2023-05-03 epidemiology
10.1101/2023.05.01.23288879 medRxiv
Show abstract

The circulating proteome offers insights into the biological pathways that underlie disease. Here, we test relationships between 1,468 Olink protein levels and the incidence of 23 age-related diseases and mortality, over 16 years of electronic health linkage in the UK Biobank (N=47,600). We report 3,201 associations between 961 protein levels and 21 incident outcomes, identifying proteomic indicators of multiple morbidities. Next, protein-based scores (ProteinScores) are developed using penalised Cox regression. When applied to test sets, six ProteinScores improve Area Under the Curve (AUC) estimates for the 10-year onset of incident outcomes beyond age, sex and a comprehensive set of 24 lifestyle factors, clinically-relevant biomarkers and physical measures. Furthermore, the ProteinScore for type 2 diabetes outperformed a polygenic risk score, a metabolomic score and HbA1c - a clinical marker used to monitor and diagnose type 2 diabetes. These data characterise early proteomic contributions to major age-related disease and demonstrate the value of the plasma proteome for risk stratification.

Matching journals

The top 4 journals account for 50% of the predicted probability mass.

50% of probability mass above

"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.