Updated project metadata. For celiac disease (CeD) the diagnosis and response to treatment is determined by histological evaluation of gut biopsies which depend on proper biopsy orientation and has poor inter-observer reproducibility. Biopsy proteome measurement that reports on the tissue state can be obtained by mass spectrometry (MS) analysis of formalin-fixed paraffin embedded (FFPE) tissue. Here we aimed to transform biopsy proteome data into numerical scores that would give observer-independent measures of mucosal remodeling in CeD. A pipeline was established that employs glass-mounted FFPE sections for MS-based proteome analysis. Proteome data was converted to a numerical score using two different approaches, by calculating a rank-based enrichment score and by training a machine-learning algorithm to calculate a disease-state prediction value. The scoring approaches were compared to each other and to histology using a validation cohort of 18 CeD patients comparing biopsies collected before and after treatment with gluten-free diet (GFD). Biopsies from non-CeD individuals (n = 18) served as controls.