Related Experiment Video
Updated: Jan 8, 2026
Standardized SDS-PAGE Workflow for Personalized Protein Corona Profiling in Early Cancer Detection
Published on: December 19, 2025
Plasma proteomic profiles identify biomarkers predicting Crohn's disease up to 16 years before onset
Jing Feng1, Shuo Chen1,2, Qinming Li1
1Department of Gastroenterology, Guangdong Provincial People's Hospital (Guangdong Academy of Medical Sciences), Southern Medical University, Guangzhou, China.
Insights
Early Crohn's disease (CD) detection is challenging. A new proteomics model using 9 plasma proteins can predict CD risk up to 16 years before diagnosis, improving early screening and intervention opportunities.
Area of Science:
- Gastroenterology
- Proteomics
- Biomarker Discovery
Background:
- Early identification of Crohn's disease (CD) is crucial but lacks reliable tools.
- Current diagnostic methods often identify CD after significant disease progression.
Purpose of the Study:
- To develop and validate a predictive model for early Crohn's disease identification using plasma proteomics.
- To assess the performance of the model compared to existing clinical risk assessments.
Main Methods:
- Analysis of 2736 plasma proteins in 39,634 UK Biobank participants to identify CD-associated proteins.
- Development of a machine learning model using the top 9 identified proteins (CD274, CHI3L1, REG1B, ITGAV, PRSS8, ITGA11, GDF15, DEFA1_DEFA1B, IL6).
- Validation in independent UK Biobank, EPIC-Norfolk, and Southern China cohorts.
Main Results:
- Identified 44 plasma proteins associated with incident CD, with 9 proteins showing highest importance.
- The 9-protein machine learning model achieved high prediction accuracy (AUC 0.76 in UKB testing, 0.73 in EPIC-Norfolk, 0.79 in Southern China).
- The model predicted CD risk up to 16 years pre-diagnosis, outperforming clinical models and identifying high-risk individuals (4.23x more likely to develop CD).
Conclusions:
- Proteomics-based models show significant promise for predicting Crohn's disease risk.
- This approach enables early screening and intervention up to 16 years before clinical diagnosis.
- The identified protein signatures offer a novel avenue for understanding CD pathogenesis and developing targeted therapies.
Abstract:
Reliable tools for early identification of Crohn's disease (CD) remain lacking. We analyzed 2736 plasma proteins in 39,634 UK Biobank (UKB) participants and identified 44 associated with incident CD. CD274, CHI3L1, REG1B, ITGAV, PRSS8, ITGA11, GDF15, DEFA1_DEFA1B, and IL6 ranked highest in protein importance ordering. A machine learning model based on these 9 proteins achieved high prediction for CD in a geographically distinct UKB testing cohort (n = 13,262, AUC 0.76), outperforming clinical risk models. It was externally validated in EPIC-Norfolk (n = 2944, AUC 0.73) and exhibited high discriminatory capacity for CD in the cross-sectional Southern China cohort (n = 74, AUC 0.79). In the UKB testing cohort, combining proteins with clinical data improved predictive performance (AUC 0.78) up to 16 years pre-diagnosis. In the same cohort, individuals at high risk stratified by the protein model were 4.23 times more likely to develop CD. Our findings highlight proteomics-based models as a promising approach to predict CD up to 16 years before diagnosis, offering opportunities for early screening and intervention.
