AI-Based Digital Pathology-Enabled Spatial-Omics Data Analyses of the Human Kidney

Area of Science:

• Nephrology
• Glycomics
• Computational Pathology

Background:

• Understanding kidney disease pathogenesis requires region-specific glycosylation analysis, which is challenging.
• N-glycans play critical roles in kidney function and disease.

Purpose of the Study:

• To develop and validate an AI-driven workflow for profiling N-glycan distribution within kidney functional tissue units (FTUs).
• To elucidate differences in N-glycosylation associated with diabetic kidney disease (DKD) and acute kidney injury (AKI).

Main Methods:

• Combined matrix-assisted laser desorption/ionization mass spectrometry imaging (MALDI-MSI) with AI-based digital pathology.
• Segmented MALDI-MSI data based on kidney functional tissue units (FTUs).
• Analyzed N-glycan profiles in healthy, DKD, and AKI kidney tissues.

Main Results:

• Successfully differentiated N-glycosylation within FTUs of healthy kidney tissue.
• Identified enrichment of sialic acid N-glycans in glomeruli and tubules in DKD.
• Found enrichment of sialic acid N-glycans in tubules and arteries in AKI.
• Detected enrichment of polylactosamine N-glycans specifically in AKI samples, suggesting roles in tubular injury.

Conclusions:

• The AI-based MALDI-MSI workflow enables detailed, region-specific N-glycan profiling in kidney tissues.
• Distinct glycosylation patterns are associated with DKD and AKI, offering insights into disease mechanisms.
• This approach facilitates targeted molecular imaging for kidney diseases and potentially other organs.