结直肠癌 T 细胞巢中细胞毒性 T 淋巴细胞上 CD112R（PVRIG）和 PD-1 的非冗余上调

Focal T lymphocyte aggregates commonly occur in colorectal cancer; however, their biological significance is unknown. To study focal aggregates of T lymphocytes, a deep learning-based framework for automated identification of T cell accumulations (T cell nests) was developed using CD8, PD-1, CD112R, and Ki67 multiplex fluorescence immunohistochemistry. To evaluate the clinical significance of these parameters, a cohort of 523 colorectal cancers with clinical follow-up data was analyzed. Spatial analysis of locally enriched CD8 + T cell density and cell-to-cell contacts identified T cell nests in the tumor microenvironment of colorectal cancer. CD112R and PD-1 expressions on CD8 + T cells located in T cell nests were found to be elevated compared with those on CD8 + T cells in all other tumor compartments (P < . 001 each). Although the highest mean CD112R expression on CD8 + T cells was observed at the invasive margin, the PD-1 expression on CD8 + T cells was elevated in the center of the tumor (P < .

001 each). Across all tissue compartments, proliferating CD8 + T cells showed higher relative CD112R and PD-1 expressions than those shown by non-proliferating CD8 + T cells (P < . 001 each). Integration of all available spatial and immune checkpoint expression parameters revealed a superior predictive performance for overall survival (area under the curve, 0. 65; 95% CI, 0. 60-0.

70) compared with the commonly used CD8 + tumor-infiltrating lymphocyte density (area under the curve, 0. 57; 95% CI, 0. 53-0. 61; P < . 001). Cytotoxic T cells with elevated CD112R and PD-1 expression levels are orchestrated in T cell nests of colorectal cancer and predict favorable patient outcomes, and the spatial nonredundancy underlies fundamental differences between both inhibitory immune checkpoints that provide a rationale for dual anti-CD112R/PD-1 immune checkpoint therapy.