CytoBERT: A Foundation Model for Cytometry Data

2026-08-14

AI Summary

This study addresses the challenge of cross-study model transfer in flow cytometry caused by data heterogeneity and the lack of standardized markers. To overcome this, we present the first open-source single-cell flow foundation model designed for variable marker panels. Leveraging self-supervised pretraining and marker standardization on a corpus of 50 million cells, the model learns transferable features across heterogeneous panels, effectively breaking data migration bottlenecks. Experimental results demonstrate robust cross-dataset generalization in sample-level classification tasks. By enabling reliable feature extraction despite panel variability, this work establishes a methodological foundation for scalable, universal flow cytometry analysis and facilitates broader application of foundation models in immunophenotyping research.

Abstract

Cytometry measures the complex characteristics of single cells (e.g., counts and protein expression of immune cells) and is widely used across immunological research and clinical settings. However, cytometry data is highly heterogeneous and unstandardized due to experimental protocols and the choice of measured features. While machine learning methods hold the potential to gain deeper insights into cell biology, these challenges make them difficult to apply and transfer across studies. Recent advances in foundation models can alleviate these issues, but corresponding approaches are still scarce in this field. To address this, we provide CytoBERT, a publicly available, open-source, open-weight foundation model for single-cell cytometry data with variable marker panels. CytoBERT is pretrained in a self-supervised manner on a large-scale cytometry corpus (15 human datasets with heterogeneous marker panels and more than 50 million cells) curated through marker standardization, enabling it to learn transferable inter-marker relationships within cells. Fine-tuning CytoBERT for sample-level classification demonstrates that transfer learning across heterogeneous cytometry datasets is feasible, providing a starting point for scalable, generalizable cytometry analysis. Code is available at GitHub.

Problem

• Cytometry data heterogeneity
• Cross-study transferability
• Data standardization
• Foundation models

Innovation

• Foundation Model
• Self-supervised Learning
• Cytometry
• Transfer Learning
• Marker Standardization