Related Experiment Video
Updated: Jun 15, 2026
05:22
Author Spotlight: Enhanced Multiplex Immunofluorescent Microscopy Protocol for Neuroscience Research
Published on: June 21, 2024
307
Automated cytometric gating with human-level performance using bivariate segmentation
Jiong Chen1,2, Matei Ionita3,4, Yanbo Feng2
1Department of Bioengineering, University of Pennsylvania School of Engineering and Applied Science, Philadelphia, PA, USA.
Nature Communications
|February 12, 2025
Summary
UNITO automates cytometry analysis by transforming cell data into images, accurately identifying cell populations and overcoming challenges in high-throughput single-cell protein measurements.
Area of Science:
- Immunology
- Computational Biology
- Biotechnology
Background:
- High-throughput cytometry enables extensive single-cell protein expression analysis.
- Biological and technical variability complicates manual gating, particularly for initial pre-gates dealing with debris and artifacts.
Purpose of the Study:
- To develop an automated framework, UNITO, for rigorous identification of hierarchical cytometric subpopulations.
- To reduce the labor-intensive nature of manual gating in cytometry data analysis.
Main Methods:
- UNITO reframes cell-level classification as an image-based segmentation problem.
- The framework was validated on three independent cohorts: two mass cytometry and one flow cytometry datasets.
Main Results:
- UNITO demonstrated superior performance compared to existing automated methods.
- Its results closely align with the consensus of experienced immunologists, with deviations comparable to individual human performance.
Conclusions:
- UNITO offers a robust and efficient solution for automated cytometry data analysis.
- The framework provides reproducible gating contours for inspection and enables parallel processing for increased speed.
