Artificial Intelligence-Powered H and E Analyzer Reveals Distinct Immunologic and Mutational Profiles Among Immune Phenotypes in Non-Small Cell Lung Cancer
Menée à partir de données du projet "The Cancer Genome Atlas" portant sur 965 échantillons de carcinomes du poumon non à petites cellules et menée à l'aide d'un logiciel utilisant l'intelligence artificielle, cette étude identifie les profils mutationnels et immunologiques des phénotypes immunitaires du microenvironnement tumoral
The tumor microenvironment can be classified into three immune phenotypes: inflamed, immune-excluded, and immune-desert. Immunotherapy efficacy has been shown to vary by phenotype; yet, the mechanisms are poorly understood and demands further investigation. In this study, we unveil the mechanisms using an artificial intelligence-powered software called Lunit SCOPE. We utilized the artificial intelligence to classify 965 samples of non-small cell lung carcinoma from The Cancer Genome Atlas into the three immune phenotypes. We then described the immune and mutational profiles that shape each phenotype using xCell, Gene Set Enrichment Analysis with RNA sequencing data, and cBioportal. In the inflamed, which showed higher cytolytic score, the enriched pathways were generally associated with immune response and immune-related cell types were highly expressed. In the immune-excluded, excluded subtype enriched glycolysis, fatty acid and cholesterol metabolism pathways. The KRAS mutation, BRAF mutation, and MET splicing variant were mostly observed in the inflamed. The two prominent mutations found in the immune-excluded were EGFR and PIK3CA mutations. This is the first to report the distinct immunologic and mutational landscapes of immune phenotypes which demonstrates the biological relevance of the classification. In light of these findings, we conclude by offering some insight into potential treatment options tailored to each immune phenotype.
The American Journal of Pathology , résumé, 2021