KLRF1, a novel marker of CD56bright NK cells, predicts improved survival for patients with locally advanced bladder cancer

Background: Bladder tumor-infiltrating CD56(bright) NK cells are more tumor cytotoxic than their CD56(dim) counterparts. Identification of NK cell subsets is labor-intensive and has limited utility in the clinical setting. Here, we sought to identify a surrogate marker of bladder CD56(bright) NK cells and to test its prognostic significance. Methods: CD56(bright) and CD56(dim) NK cells were characterized with the multiparametric flow (n = 20) and mass cytometry (n = 21) in human bladder tumors. Transcriptome data from bladder tumors (n = 351) profiled by The Cancer Genome Atlas (TCGA) were analyzed. The expression levels of individual markers in intratumoral CD56(bright) and CD56(dim) NK cells were visualized in tSNE plots. Expressions of activation markers were also compared between Killer Cell Lectin-Like Receptor Subfamily F Member 1 (KLRF1)(+) and KLRF1(-) NK cells. Results: Intratumoral CD56(bright) NK cells displayed a more activated phenotype compared to the CD56(dim) subset. Multiple intratumoral cell types expressed CD56, including bladder tumor cells and nonspecific intratumoral CD56 expression was associated with worse patient survival. Thus, an alternative to CD56 as a marker of CD56(bright) NK cells was sought. The activation receptor KLRF1 was significantly increased on CD56(bright) but not on CD56(dim) NK cells. Intratumoral KLRF1(+) NK cells were more activated and expressed higher levels of activation molecules compared with KLRF1(-) NK cells, analogous to the distinct effector function of NK cells across CD56 expression. High intratumoral KLRF1 was associated with improved recurrence-free survival (hazard ratio [HR] 0.53, p = 0.01), cancer-specific survival (HR 0.47, p = 0.02), and overall survival (HR 0.54, p = 0.02) on multivariable analyses that adjusted for clinical and pathologic variables. Conclusions: KLRF1 is a promising prognostic marker in bladder cancer and may guide treatment decisions upon validation.