The goal of a hypothesis-driven analysis (or guided analysis) is to identify known cellular subsets to then assess the frequency of a known population or marker expression levels on the cell type of interest. Predominantly, this is achieved by creating a manual gating strategy tailored to the user’s panel and incorporating the user’s expertise and knowledge of the biological system, mechanism or process being studied. Manual gating is often cited as a major source of variability in cytometry assays (Maecker et al., 2005) in addition to being a time-consuming method. Machine learning-assisted analysis of cytometry data has proven advantageous, however, there is a lack of methods that allow the user to automate their own user-defined gating strategy for their specific marker panel in a hypothesis-driven setting (Hu et al., 2022).
Cytobank Automatic gating video tutorial
The Cytobank Automatic gating algorithm allows you to train a model on your manual gating strategy on a small number of samples, replicating faithfully the manual analysis a user would perform. You can apply a trained model to new datasets to infer the populations or subsets present in your cytometry data. With automatic gating on the Cytobank platform we are adding the power of machine learning assisted analysis to hypothesis-driven workflows reducing the variability of the analysis and the time to results.
(Workflow of Cytobank Automatic Gating)
Read more about:
How to set up a new automatic gating analysis by training a new model
How to set up a new automatic gating analysis by running inference using trained model
How to interpret the automatic gating results
REFERENCES:
Maecker HT, Rinfret A, D’Souza P et al. Standardization of cytokine flow cytometry assays. BMC Immunol. 2005;6:13
Hu Z, Bhattacharya S, Butte AJ. Application of Machine Learning for Cytometry Data. Front Immunol. 2022:12:787574