Velociraptor Machine Learning Quantifies Similarity to Known Cell Types and Matches Cells Across Flow and Imaging Cytometry Platforms.

Velociraptor machine learning accurately registers and identifies cell types across diverse flow and imaging cytometry platforms with median F1 of 0.81 and correlation of 0.99.

• Why it matters: Integrating data from flow and imaging cytometry enhances cellular analysis by combining spatial context with high-throughput profiling, addressing a key gap in multi-platform cellular characterization.
• What they did: Velociraptor employs graph-based Marker Enrichment Modeling to generate quantitative phenotype labels for each cell, enabling rapid similarity calculations and cell registration across platforms like IMC, CyTOF, and SFC, tested on cancer and immunology samples.
• The result: The workflow successfully identified and spatially characterized rare and abundant cell types, including a novel tumor cell subset, facilitating deeper insights into tissue architecture and cell heterogeneity, and is freely available for broader use.