BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Zero-shot design of drug-binding proteins using neural networks - 
 Nicholas Polizzi
DTSTART:20251020T113000Z
DTEND:20251020T123000Z
UID:TALK238894@talks.cam.ac.uk
CONTACT:Simona Valeviciute
DESCRIPTION:The use of deep neural networks has improved almost every aspe
 ct of protein structure prediction and design. Yet\, the design of protein
 s that bind to small molecules has remained an outstanding challenge. Here
 \, I will discuss new models and algorithms that unlock the use of neural 
 networks for design of drug-binding proteins from scratch with unprecedent
 ed success rates. This work enables the design of binders in a single shot
 \, which we demonstrate with the design of an exatecan-binding protein for
  applications in targeted delivery. We further devised an approach to turn
  this binder into an exatecan sensor. The de novo design of biosensors is 
 an outstanding challenge in the field. I will finish my presentation by di
 scussing our latest results that could potentially generalize de novo bios
 ensor design.
LOCATION:CRUK CI Lecture Theatre
END:VEVENT
END:VCALENDAR