New interpretable machine-learning method for single-cell data reveals correlates of clinical response to cancer immunotherapy
November 1, 2021
November 1, 2021
This recent study introduces a new method for single-cell cytometry studies, FAUST, which allows researchers to identify and measure the physical and functional characteristics of a population of immune cells. This method was applied to a prior Merkel cell carcinoma study that focused on tumor-specific T cells, which are cells that play an important role in fighting cancer cells. This study focused on three important “activation markers” (PD-1, HLA-DR, and CD28) that can be detected on the surface of these T cells. The results suggest that the presence of all three of these markers on tumor-specific T cells could be used to predict a patient’s response to pembrolizumab therapy.
We introduce a new method for single-cell cytometry studies, FAUST, which performs unbiased cell population discovery and annotation. FAUST processes experimental data on a per-sample basis and returns biologically interpretable cell phenotypes, making it well suited for the analysis of complex datasets. We provide simulation studies that compare FAUST with existing methodology, exemplifying its strength. We apply FAUST to data from a Merkel cell carcinoma anti-PD-1 trial and discover pre-treatment effector memory T cell correlates of outcome co-expressing PD-1, HLA-DR, and CD28. Using FAUST, we then validate these correlates in cryopreserved peripheral blood mononuclear cell samples from the same study, as well as an independent CyTOF dataset from a published metastatic melanoma trial. Finally,we show how FAUST’s phenotypes can be used to perform cross-study data integration in the presence of diverse staining panels. Together, these results establish FAUST as a powerful new approach for unbiased discovery in single-cell cytometry.