The Immune Subtypes and Landscape of Gastric Cancer and to Predict Based on the Whole-Slide Images Using Deep Learning

Abstract

BackgroundGastric cancer (GC) is a highly heterogeneous tumor with different responses to immunotherapy. Identifying immune subtypes and landscape of GC could improve immunotherapeutic strategies.MethodsBased on the abundance of tumor-infiltrating immune cells in GC patients from The Cancer Genome Atlas, we used unsupervised consensus clustering algorithm to identify robust clusters of patients, and assessed their reproducibility in an independent cohort from Gene Expression Omnibus. We further confirmed the feasibility of our immune subtypes in five independent pan-cancer cohorts. Finally, functional enrichment analyses were provided, and a deep learning model studying the pathological images was constructed to identify the immune subtypes.ResultsWe identified and validated three reproducible immune subtypes presented with diverse components of tumor-infiltrating immune cells, molecular features, and clinical characteristics. An immune-inflamed subtype 3, with better prognosis and the highest immune score, had the highest abundance of CD8+ T cells, CD4+ T–activated cells, follicular helper T cells, M1 macrophages, and NK cells among three subtypes. By contrast, an immune-excluded subtype 1, with the worst prognosis and the highest stromal score, demonstrated the highest infiltration of CD4+ T resting cells, regulatory T cells, B cells, and dendritic cells, while an immune-desert subtype 2, with an intermediate prognosis and the lowest immune score, demonstrated the highest infiltration of M2 macrophages and mast cells, and the lowest infiltration of M1 macrophages. Besides, higher proportion of EVB and MSI of TCGA molecular subtyping, over expression of CTLA4, PD1, PDL1, and TP53, and low expression of JAK1 were observed in immune subtype 3, which consisted with the results from Gene Set Enrichment Analysis. These subtypes may suggest different immunotherapy strategies. Finally, deep learning can predict the immune subtypes well.ConclusionThis study offers a conceptual frame to better understand the tumor immune microenvironment of GC. Future work is required to estimate its reference value for the design of immune-related studies and immunotherapy selection.

The Roles of Immune Cells in Gastric Cancer: Anti-Cancer or Pro-Cancer?

“…Not surprisingly, patients with C2 tumors had better prognosis than that of patients with C1 tumors [ 106 ]. Chen et al [ 107 ] classified gastric tumors into three subtypes: i.e., immune subtype 1, 2 and 3, in order to determine the prognosis of gastric cancer patients based on the immune landscape of gastric tumors. They found that patients with immune subtype 3 with a high infiltration of CD8 + and CD4 + -activated T cells, NK cells, and M1 macrophages had the best prognosis, while the patients with immune subtype 1 with a high infiltration B cells, dendritic cells, and CD4 + resting T cells had the worst prognosis of gastric cancer.…”

Microbiota and the Immune System—Actors in the Gastric Cancer Story

“…Inflammation promotes cancer progression primarily by blocking antitumor immunity as well as shaping the tumor microenvironment towards a more favorable tumor cell and by exerting direct signals and tumor promoting functions [ 102 , 103 , 104 ]. Immune system disorders in the course of GC include changes in the microenvironment of the tumor itself as well as immune depletion of T lymphocytes and the involvement of immune checkpoints [ 20 ] ( Figure 7 ).…”

“…The likelihood of developing disease in those infected with these microorganisms is largely determined by the long-term inflammatory response that is associated with the virulence of the strains, genetic predisposition of the host, and environmental cofactors. The immune and inflammatory response to H. pylori infection is very important as gastritis may not only lead to further clinical consequences, an ineffective immune response, and increasing inflammation to persistent infection with these bacteria in the body but may also be the cause of the development of oncogenic processes within the stomach [ 19 , 20 , 21 ].…”

Artificial intelligence in gastric cancer: applications and challenges

“…Meanwhile, other biological factors are also found to be related to the prognosis. Researchers classified the histopathological images based on Human epidermal growth factor receptor 2 (Her2) [ 74 , 75 ], microsatellite instability (MSI) [ 76 ], and immune biomarkers [ 77 , 78 ]. In addition, researchers explored the radiogenomics method to identify the chromosomal instability (CIN) state based on CT images [ 79 ].…”