Work

An automated and scalable pipeline for high-dimensional immune cell phenotyping in mass cytometry datasets 2931

Year: 2025

Type: article

Abstract: Description Efficient single-cell phenotyping has become essential for the identification of complex cell populations. Traditionally, these populations are identified through manual gating, a time-consuming process that is also subject to variability and a lack of reproducibility. Here, we adapted a deep learning model [1] to devise an automated gating pipeline with the goal of enhancing the accuracy, speed, and reproducibility of immune cell gating. Our pipeline was tested on 12 million cells obtained from two mass-cytometry datasets [1], [2]. Results The automated gating pipeline achieved classification scores comparable to expert manual gating with overall accuracy of 0.917 and 0.921 for dataset 1 and 2, respectively. Processing time was significantly reduced: <12min for both datasets (8CPUs, 8GB of RAM). More granular analysis revealed that high-level populations were identified with excellent accuracy (e.g., Granulocytes, Tcells, Bcells with f1-score of 0.991, 0.993 and 0.937 on the first dataset and 0.997, 0.996 and 0.934 on the second dataset, respectively). However, rare and heterogeneous populations showed higher discrepancies (e.g., intermediate monocytes, DC with f1-scores of 0.864, 0.816 on the first dataset and 0.678, 0.552 on the second dataset, respectively). By eliminating operator-dependent biases and enabling the simultaneous handling of multiple markers, this automated approach is paving the way for more reliable and efficient analyses in research and clinical settings. Funding Sources 1. Blampey, Q. et al, A biology-driven deep generative model for cell-type annotation in cytometry. Brief Bioinform. 2023 Sep 20;. doi: 10.1093/bib/bbad260. 2. Development and Validation of a Predictive Score for Surgical Site Infections (SPRED) https://clinicaltrials.gov/study/NCT05523713 3. Ina A. Stelzer et al, Sci.Transl.Med.13,eabd9898(2021). DOI:10.1126/scitranslmed.abd9898 Topic Categories Technological Innovations in Immunology (TECH)

Source: The Journal of Immunology

DOI: 10.1093/jimmun/vkaf283.788