Deep learning reveals a damage signalling hierarchy that coordinates different cell behaviours driving wound...

Area of Science:

• Cell Biology
• Developmental Biology
• Biophysics

Background:

• Re-epithelialisation is a crucial process in wound healing, involving dynamic cell behaviors like division, shape change, and migration.
• Understanding the regulatory signals controlling these behaviors is essential for advancing wound repair therapies.

Purpose of the Study:

• To quantify the contributions of individual cell behaviors to wound re-epithelialisation using deep learning.
• To investigate the roles of conserved signaling pathways (Calcium (Ca2+), JNK) and macrophage-derived factors in regulating these behaviors.

Main Methods:

• Utilized deep learning tools to analyze movies of wound repair in Drosophila pupal wing epithelium.
• Performed genetic perturbations, including knockdown of Ca2+ and JNK signaling, and ablation of macrophages.
• Quantified the impact of these perturbations on cell division, shape changes, and migration.

Main Results:

• Calcium (Ca2+) signaling acts as a master regulator, essential for all studied cell behaviors during wound repair.
• JNK signaling primarily influences cell shape changes and divisions.
• Macrophage-derived signals significantly regulate cell migration and proliferation.

Conclusions:

• Deep learning provides a powerful approach to dissect complex signaling networks in tissue repair.
• Identified distinct roles for Ca2+, JNK, and macrophage signals in orchestrating cellular behaviors during re-epithelialisation.
• This study offers quantifiable insights into the signaling hierarchy governing wound healing.