Artificial Intelligence Analysis of Celiac Disease Using an Autoimmune Discovery Transcriptomic Panel Highlighted...

Area of Science:

• Immunology
• Computational Biology
• Genetics

Background:

• Celiac disease is an immune-mediated enteropathy triggered by gluten in genetically susceptible individuals.
• Understanding the genetic and molecular underpinnings of celiac disease is crucial for developing effective diagnostic and therapeutic strategies.

Purpose of the Study:

• To demonstrate the proof-of-concept for utilizing Artificial Intelligence (AI) and an autoimmune discovery gene panel to predict and model celiac disease.
• To identify novel pathogenic genes and pathways associated with celiac disease.

Main Methods:

• Applied conventional bioinformatics, gene set enrichment analysis (GSEA), and various machine learning/deep learning algorithms (e.g., C5, logistic regression, SVM, XGBoost, neural networks) to a public dataset (GSE164883).
• Utilized an autoimmune discovery gene panel for predictive modeling.
• Validated key findings, specifically BTLA protein expression, using immunohistochemistry on an independent case series.

Main Results:

• The AI model, leveraging the autoimmune gene panel, achieved high accuracy (95-100%) in predicting celiac disease.
• Identified several pathogenic genes involved in immune checkpoint and immuno-oncology pathways, including CASP3, CD86, CTLA4, FASLG, GZMB, IFNG, IL15RA, ITGAX, LAG3, MMP3, MUC1, MYD88, PRDM1, and RGS1.
• Demonstrated elevated BTLA expression in inflammatory cells within the lamina propria of celiac disease patients, validated at the protein level.

Conclusions:

• Artificial intelligence, combined with an autoimmune gene panel, effectively predicts celiac disease.
• The study highlights the role of specific genes and pathways, particularly BTLA, in the pathogenesis of celiac disease.
• This AI-driven approach offers a promising avenue for advancing celiac disease research and diagnostics.