Computational multiplex panel reduction to maximize information retention in breast cancer tissue microarrays

Recent state-of-the-art multiplex imaging techniques have expanded the depth of information that can be captured within a single tissue sample by allowing for panels with dozens of markers. Despite this increase in capacity, space on the panel is still limited due to technical artifacts, tissue loss, and long imaging acquisition time. As such, selecting which markers to include on a panel is important, since removing important markers will result in a loss of biologically relevant information, but identifying redundant markers will provide a room for other markers. To address this, we propose computational approaches to determine the amount of shared information between markers and select an optimally reduced panel that captures maximum amount of information with the fewest markers. Here we examine several panel selection approaches and evaluate them based on their ability to reconstruct the full panel images and information within breast cancer tissue microarray datasets using cyclic immunofluorescence as a proof of concept. We show that all methods perform adequately and can re-capture cell types using only 18 of 25 markers (72% of the original panel size). The correlation-based selection methods achieved the best single-cell marker mean intensity predictions with a Spearman correlation of 0.90 with the reduced panel. Using the proposed methods shown here, it is possible for researchers to design more efficient multiplex imaging panels that maximize the amount of information retained with the limited number of markers with respect to certain evaluation metrics and architecture biases.Author summary: Multiplex tissue imaging techniques utilize large panels of markers that attempt to gather as much information as possible, but increasing the number of stains does come with the downsides of increased autofluorescence and tissue degradation. There exists a theoretical subsampling of markers that is able to recreate the same information as a full panel; therefore, removing the self-correlating information with such a subset would increase the efficiency of the imaging process and maximize the information collected. By selecting an idealized subsample of markers, a deep learning model can be trained to predict the same information as a full dataset with fewer rounds of staining. Here we evaluate several methods of subsample marker selection and demonstrate their ability to reconstruct the full panel’s information.