BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Deep learning analysis of wound healing in flies - Jake Turley (Un
 iversity of Bristol)
DTSTART:20231205T150000Z
DTEND:20231205T160000Z
UID:TALK208951@talks.cam.ac.uk
DESCRIPTION:Wound healing is a highly conserved process required for survi
 val after tissue damage. In mammals\, the three cell-behaviours that contr
 ibute to wound re-epithelialisation are cell shape deformation\, cell divi
 sion\, and cell migration. This study aims to quantify the contributions o
 f each of these cell behaviours using wounded Drosophila pupae. Live confo
 cal time-lapse microscopy allows us to follow cell behaviours in the pupal
  wing before and after wounding. We have developed deep learning algorithm
 s to identify dividing cells with 97% accuracy and determine the orientati
 on of these divisions relative to the wound margin\, alongside additional 
 machine learning tools that measure other cell behaviours. We want to know
  whether these properties are synchronized/aligned by the chemical and mec
 hanical signals of wounding. We are also investigating how far back from t
 he wound edge these changes in cell behaviour occur\, and whether this dep
 ends on wound size. We have characterised the spatial-temporal distributio
 n of divisions and found a reduction in their density close to the wound e
 dge\, but 2hr after wounding there is a synchronised burst of divisions fu
 rther back. Next\, we will genetically modify wound signals to observe how
  they impact wound healing. We can not only quantify changes to the rate o
 f wound closure but also the difference in cell behaviours. Having a great
 er understanding of the mechanics of wound healing will hopefully be a fir
 st step in developing future treatments for the clinic.
LOCATION:Seminar Room 2\, Newton Institute
END:VEVENT
END:VCALENDAR