A Cancer Biologist's Primer on Machine Learning Applications in High-Dimensional Cytometry

Area of Science:

• Bioinformatics
• Computational Biology
• Cancer Research

Background:

• Machine learning (ML) and artificial intelligence (AI) are increasingly vital for analyzing complex, high-dimensional cytometry data.
• High-throughput, multiparameter single-cell data collection is rapidly advancing in cancer biology.

Purpose of the Study:

• To introduce cancer biologists and physician-scientists to fundamental ML concepts and tools for cytometry data analysis.
• To provide a conceptual framework for translating ML-driven insights from cytometry data into clinically relevant discoveries.

Main Methods:

• Overview of keystone machine learning-based analytic approaches for cytometry data.
• Emphasis on defining key terms and providing a conceptual framework.
• Focus on practical applications for researchers with limited bioinformatics training.

Main Results:

• Provides a foundational understanding of ML methodologies applicable to cytometry.
• Enables interpretation of complex single-cell data for cancer research.
• Facilitates the identification of translational and clinical insights.

Conclusions:

• ML and AI are indispensable tools for modern cancer biology research using cytometry.
• Understanding these methods empowers researchers to leverage high-dimensional data for discovery.
• This work bridges the gap between bioinformatics and cancer biology for clinical application.