Machine learning extracts oncogenic-specific γ-H2AX foci formation pattern upon genotoxic stress

Area of Science:

• Molecular Biology
• Cancer Research
• Genomics

Background:

• Histone H2AX phosphorylation (γ-H2AX) is crucial for DNA damage response.
• γ-H2AX foci patterns vary in intensity and size, but oncogenic-specific patterns remain uncharacterized.
• Defects in TIP60 acetyltransferase activity are linked to cancer cell growth.

Purpose of the Study:

• To investigate if characteristic γ-H2AX foci patterns are associated with oncogenesis.
• To compare γ-H2AX foci patterns between TIP60 wild-type and TIP60 HAT mutant cells using machine learning.
• To identify oncogenic-specific γ-H2AX foci patterns.

Main Methods:

• Utilized machine learning to analyze γ-H2AX foci patterns.
• Focused on foci intensity and size for pattern extraction.
• Employed Uniform Manifold Approximation and Projection (UMAP) for dimensionality reduction.

Main Results:

• Successfully extracted a TIP60 HAT mutant-like oncogenic-specific γ-H2AX foci pattern.
• Observed these oncogenic-specific γ-H2AX foci patterns in TIP60 wild-type cells using UMAP.
• Demonstrated the variability of γ-H2AX foci patterns.

Conclusions:

• Propose the existence of an oncogenic-specific γ-H2AX foci pattern.
• Highlight the importance of machine learning in identifying oncogenic signaling within γ-H2AX variations.
• Suggest potential for γ-H2AX pattern analysis in cancer diagnostics.