IBDome: an integrated molecular, histopathological, and clinical atlas of inflammatory bowel diseases

BACKGROUND & AIMS: Multiomic and multimodal datasets with detailed clinical annotations offer significant potential to advance understanding of inflammatory bowel diseases (IBDs), refine diagnostics, and enable personalized therapeutic strategies. METHODS: In this multicohort study, an extensive multiomic and multimodal analysis of 1002 clinically annotated patients with IBD and non-IBD controls was performed, incorporating whole-exome and RNA sequencing of normal and inflamed gut tissues, serum proteomics, and histopathological assessments from images of H&E-stained tissue sections. RESULTS: Transcriptomic profiles of normal and inflamed tissues revealed distinct site-specific inflammatory signatures in Crohn’s disease and ulcerative colitis. Leveraging serum proteomics, an inflammatory protein severity signature that reflects underlying intestinal molecular inflammation was developed. Furthermore, foundation model-based deep learning accurately predicted histologic disease activity scores and enabled Crohn’s disease vs ulcerative colitis classification from images of H&E-stained intestinal tissue sections, offering a robust tool for clinical evaluation. CONCLUSIONS: This integrative, publicly available multiomics resource for IBD research highlights the potential of combining multiomics and advanced computational approaches to improve understanding and management of IBD.