This study compares the relative utility of deep learning models as automated phenotypic classifiers, built with features of peripheral blood cell populations assayed with flow cytometry. We report surprisingly good sensitively for the task of distinguishing male from female mice solely from attributes of cells present in peripheral blood samples. This novel application of cytometry technology is easily validated and represents an example use that is not reliably possible with current visual analysis techniques. It serves as a useful test case with known ground truth labels of a subtle cellular phenotype and indicates the potential of this approach to more biologically meaningful phenotypes. We evaluate three different deep neural network architectures that vary in how the high-dimensional flow cytometry data is processed as input: 1) a convolutional neural network applied to the raw, per-cell marker intensity values, 2) a multi-layer perceptron taking per-channel histograms representing the range of intensities for a given marker, and 3) a multi-layer perceptron using a hypervoxel representation of the set of marker intensities for each cell in a given input sample. Our results show the histogram-based multi-layer perceptron achieves the highest classification accuracy of 91% on 2300 mouse blood samples for a mutant phenotype classification task. This indicates the value of deep learning models for detection of subtle signals that are not readily observed in high dimensions by visual analysis. These results demonstrate the effectiveness of deep learning for automated analysis of flow cytometry data on a challenging and biologically complex classification task.

SUMMARY: Missense mutations that change protein stability are strongly associated with human genetic disease. With the recent availability of predicted structures for all human proteins generated using the AlphaFold2 prediction model, genome-wide assessment of the stability effects of genetic variation can, for the first time, be easily performed. This facilitates the interrogation of personal genetic variation for potentially pathogenic effects through the application of stability metrics. Here, we present a novel tool to prioritize variants predicted to cause strong instability in essential proteins. We show that by filtering by ΔΔG values and then prioritizing by StabilitySort Z-scores, we are able to more accurately discriminate pathogenic, protein-destabilizing mutations from population variation, compared with other mutation effect predictors. AVAILABILITY AND IMPLEMENTATION: StabilitySort is available as a web service (https://www.stabilitysort.org), as a data download for integration with other tools (https://www.stabilitysort.org/download) or can be deployed as a standalone system from source code (https://gitlab.com/baaron/StabilitySort). SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.