BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//132.216.98.100//NONSGML kigkonsult.se iCalcreator 2.20.4//
BEGIN:VEVENT
UID:20250510T051237EDT-8426LZzx8V@132.216.98.100
DTSTAMP:20250510T091237Z
DESCRIPTION:Dissecting gene regulation syntax using glass-box machine learn
 ing\n\nSelin Jessa\, Stanford University\n	Tuesday April 29\, 12-1pm\n	Zoom 
 Link: https://mcgill.zoom.us/j/89914150820\n	In Person: 550 Sherbrooke\, Ro
 om 189\n	\n	Abstract: Most cells in the body share an identical genome\, but
  gene regulation during development ensures that distinct cell types activ
 ate appropriate gene programs in the right place and time. This process is
  directed by transcription factors (TFs)\, which recognize and bind short 
 DNA sequences in non-coding genomic elements\, and drive cell type-specifi
 c gene expression programs. Yet\, the map of TFs that bind the genome in e
 ach cell type remains incomplete. Furthermore\, the syntax of binding site
 s—their composition\, orientation\, and spacing—contributes to cell type-s
 pecific regulation\, just as word organization in a sentence impacts its m
 eaning. However\, we lack a systematic understanding of how this syntax me
 diates combinatorial activity of TFs.\n\nI will introduce a 'glass-box' de
 ep learning strategy to study TF activities during human development. TFs 
 typically bind physically accessible or uncompacted DNA\, and in turn\, th
 ey often promote local DNA accessibility. We thus train convolutional neur
 al networks to predict DNA accessibility using local sequence alone. We us
 e a model interpretation algorithm to extract the sequence features which 
 are predictive of DNA accessibility\, which generally reflect TF binding s
 ite motifs. We apply this strategy to nearly 200 human fetal cell types to
  define the TF motifs relevant in human development. Finally\, we use thes
 e trained models to perform in silico experiments to identify synergistic 
 TF motif pairs and systematically dissect the role of binding site syntax.
  Altogether\, our approach reveals novel motif rules which are encoded in 
 DNA and mediate the combinatorial\, context-specific regulation that gover
 ns development.\n
DTSTART:20250429T160000Z
DTEND:20250429T170000Z
SUMMARY:QLS Seminar Series -  Selin Jessa
URL:/qls/channels/event/qls-seminar-series-selin-jessa
 -365034
END:VEVENT
END:VCALENDAR