Friedrich, V. D. | Search bioRxiv

bioRxiv2024

ConvexGating infers gating strategies from clusters in single cell cytometry data

Manual expert gating remains common practice for the definition of specific cell populations in the analysis of flow cytometry data. The increasing number of measured parameters per individual cell and high inter-rater variability makes manual gating inconsistent in many scenarios such as multi-center studies. Here, we propose ConvexGating, an AI tool that automatically learns gating strategies in an unbiased, fully data-driven, yet interpretable manner. ConvexGating scales efficiently with increasing parameter space, creating proficient strategies with low-contamination in the extracted population for previously known and so far unknown or ill-defined cell populations. The inferred strategies are independent of parent populations, for instance, plasmacytoid dendritic cells (pDCs) can be fully identified as CD45RA- CD123+. In addition to flow cytometry data, ConvexGating derives gating strategies for cyTOF (Cytometry by Time of Flight) and CITEseq (Cellular Indexing of Transcriptomes and Epitopes by Sequencing) data and supports optimal design of marker panels for cell sorting.

immunology↗

bioRxiv2024

Neural Network-Assisted Humanization of COVID-19 Hamster scRNAseq Data Reveals Matching Severity States in Human Disease

Translating findings from animal models to human disease is essential for dissecting disease mechanisms, developing and testing precise therapeutic strategies. The coronavirus disease 2019 (COVID-19) pandemic has highlighted this need, particularly for models showing disease severity-dependent immune responses. Single-cell transcriptomics (scRNAseq) is well poised to reveal similarities and differences between species at the molecular and cellular level with unprecedented resolution. However, computational methods enabling detailed matching are still scarce. Here, we provide a structured scRNAseq-based approach that we applied to scRNAseq from blood leukocytes originating from humans and hamsters affected with moderate or severe COVID-19. Integration of COVID-19 patient data with two hamster models that develop moderate (Syrian hamster, Mesocricetus auratus) or severe (Roborovski hamster, Phodopus roborovskii) disease revealed that most cellular states are shared across species. A neural network-based analysis using variational autoencoders quantified the overall transcriptomic similarity across species and severity levels, showing highest similarity between neutrophils of Roborovski hamsters and severe COVID-19 patients, while Syrian hamsters better matched patients with moderate disease, particularly in classical monocytes. We further used transcriptome-wide differential expression analysis to identify which disease stages and cell types display strongest transcriptional changes. Consistently, hamsters response to COVID-19 was most similar to humans in monocytes and neutrophils. Disease-linked pathways found in all species specifically related to interferon response or inhibition of viral replication. Analysis of candidate genes and signatures supported the results. Our structured neural network-supported workflow could be applied to other diseases, allowing better identification of suitable animal models with similar pathomechanisms across species. Key PointsO_LINeural networks can successfully match disease states between animal models and humans using single-cell data as shown for COVID-19 C_LIO_LIModerately diseased patients best matched Syrian hamster cells; severely diseased patients best matched Roborovski hamster neutrophils C_LI

immunology↗