PXPermute reveals staining importance in multichannel imaging flow cytometry

Imaging flow cytometry (IFC) allows rapid acquisition of numerous single-cell images per second, capturing information from multiple fluorescent channels. However, the traditional process of staining cells with fluorescently labeled conjugated antibodies for IFC analysis is time consuming, expensive, and potentially harmful to cell viability. To streamline experimental workflows and reduce costs, it is crucial to identify the most relevant channels for downstream analysis. In this study, we introduce PXPermute, a user-friendly and powerful method for assessing the significance of IFC channels, particularly for cell profiling. Our approach evaluates channel importance by permuting pixel values within each channel and analyzing the resulting impact on machine learning or deep learning models. Through rigorous evaluation of three multichannel IFC image datasets, we demonstrate PXPermute’s potential in accurately identifying the most informative channels, aligning with established biological knowledge. PXPermute can assist biologists with systematic channel analysis, experimental design optimization, and biomarker identification. [Display omitted] •PXPermute identifies the most informative channels in imaging flow cytometry•The channels identified by PXPermute align with biological understanding•PXPermute facilitates biomarker discovery processes Imaging flow cytometry (IFC) is a high-throughput microscopic technique that gathers multiparametric fluorescent and morphological data from individual cells. However, fluorescent staining is time consuming, expensive, spectrally overlapping, and potentially harmful to cells. To reduce the number of fluorescent stainings to the most informative ones, we introduce PXPermute, a model-agnostic method that quantitatively guides IFC channel selection. Our approach streamlines workflows, reduces costs, and assists in optimizing experimental designs, addressing the need for more efficient and effective IFC analysis. Shetab Boushehri et al. introduce PXPermute, a model-agnostic tool for optimizing imaging flow cytometry by accurately determining the most informative fluorescent channels. This method simplifies workflows and aids in precise biomarker identification.