Multiparameter quantitative analyses of diagnostic cells in brain tissues from tuberous sclerosis complex

Area of Science:

• Biomedical imaging
• Computational pathology
• Molecular diagnostics

Background:

• Tuberous sclerosis complex (TSC) is a genetic disorder characterized by benign tumor growth.
• Balloon cells (BCs) are diagnostic markers in TSC brain tissue, but their molecular identity is not fully understood.
• Accurate BC identification is crucial for research models and understanding TSC pathogenesis.

Purpose of the Study:

• To develop a computational pipeline for automated BC identification in TSC.
• To characterize BCs molecularly using high-dimensional imaging mass cytometry (IMC).
• To establish a workflow for analyzing cellular features in human tissues.

Main Methods:

• Development of a machine learning pipeline (BAlloon IDENtifier; BAIDEN) for BC detection.
• Application of a 36-antibody panel with IMC for high-dimensional single-cell analysis.
• Integration of BAIDEN with IMC data and analysis pipelines for comprehensive BC profiling.

Main Results:

• Successful prospective identification of BCs in TSC brain tissue sections using a novel computational approach.
• Exploration of multiple protein markers to define conserved BC features across patient samples.
• Characterization of BC abundance, structure, and signaling activity within the TSC context.

Conclusions:

• High-dimensional imaging combined with machine learning offers powerful tools for characterizing rare cell types in human diseases.
• The developed workflow provides a framework for molecularly defining diagnostic cells in complex disorders like TSC.
• This approach facilitates the study of BCs in both clinical samples and experimental models, advancing TSC research.