Research continues to highlight the biological importance of cellular heterogeneity, unveiling novel cell types and subtypes with physiological and pathological relevance. Modern flow cytometry analyzes dozens of parameters simultaneously, resulting in millions of possible outcome combinations in a given experiment.

Researchers typically cope with large data volumes by focusing their observations on specific parameters. To do this, they execute manual gating; however, this can miss key relationships and connections because it is imprecise and it does not parse the entire dataset. Machine learning can bridge this information gap.

Download this poster from Beckman Coulter to discover how machine learning—both automated gating and algorithmic data analysis—helps researchers take full advantage of modern flow cytometry.