Transfer learning between preclinical models and human tumors identifies conserved NK cell activation signature in anti-CTLA-4 responsive tumors

BackgroundTumor response to therapy is affected by both the cell types and the cell states present in the tumor microenvironment. This is true for many cancer treatments, including notably immune checkpoint inhibitors (ICIs). While it is well-established that ICIs promote T cell activation, their broader impact on other intratumoral immune cells is unclear; this information is needed to identify new mechanisms of action and improve ICI efficacy. Many preclinical studies have begun to use single cell analysis to delineate therapeutic responses in individual immune cell types within tumors. One major limitation to this approach is that therapeutic mechanisms identified in preclinical models have failed to fully translate to human disease, restraining efforts to improve ICI efficacy in bench to bedside research. MethodWe previously developed a computational transfer learning approach to identify shared biology between independent high-throughput single-cell RNA sequencing (scRNA-seq) datasets. In the present study, we test this frameworks ability to identify conserved and clinically relevant transcriptional changes in complex tumor scRNA-seq data and further expand its application beyond comparison of scRNA-seq datasets into comparison of scRNA-seq datasets with additional data types such as bulk RNA-seq and mass cytometry. ResultsWe found a conserved signature of NK cell activation in anti-CTLA-4 responsive mice and human tumors. In human melanoma, we found that the NK cell activation signature correlates with longer overall survival and is predictive of anti-CTLA-4 (ipilimumab) response. Additional molecular approaches to confirm the computational findings demonstrated that human NK cells express CTLA-4 and bind anti-CTLA-4 independent of the antibody binding receptor (FcR), and that similar to T cells, CTLA-4 expression by NK cells is modified by cytokine-mediated and target cell-mediated NK cell activation. ConclusionsThese data demonstrate the ability of our transfer learning approach to identify cell state transitions conserved in preclinical models and human tumors. This approach can be adapted to explore many immuno-oncology questions, enhancing bench to bedside research and enabling better understanding and treatment of disease. Graphical Abstract O_FIG O_LINKSMALLFIG WIDTH=200 HEIGHT=162 SRC="FIGDIR/small/125625v2_ufig1.gif" ALT="Figure 1"> View larger version (25K): org.highwire.dtl.DTLVardef@1ca0c13org.highwire.dtl.DTLVardef@1dedc51org.highwire.dtl.DTLVardef@5277eforg.highwire.dtl.DTLVardef@4007c5_HPS_FORMAT_FIGEXP M_FIG C_FIG