Multiplex immunofluorescence (mIF) is a powerful technology that enables visualization of the spatial relationships between cells in the tumor microenvironment (TME). Using tumor tissue from 93 patients with metastatic melanoma, Giraldo et al. developed and validated a mIF data-analysis pipeline and spatial uniform manifold approximation and projection (UMAP) algorithm to cluster and visualize the data. This approach revealed that PD-L1 and PD-1 expression intensity was spatially encoded in the TME. For example, PD-L1 expression intensity was highest on CD163⁺ cells in neighborhoods with a high density of CD8⁺ cells. The differences in spatial clustering correlated with distinct clinical outcomes, highlighting the potential for using this approach to identify prognostic and predictive immuno-oncology biomarkers. Read more in this issue on page 1262. Original image from Fig. 1B. Artwork by Lewis Long.