BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//132.216.98.100//NONSGML kigkonsult.se iCalcreator 2.20.4//
BEGIN:VEVENT
UID:20251218T214243EST-0030CCkL9Z@132.216.98.100
DTSTAMP:20251219T024243Z
DESCRIPTION:Understanding and guiding evolution with protein language model
 s\n\nPeter S. Kim\, Stanford University\n	Tuesday January 20\, 12-1pm\n	Zoom
  Link: https://mcgill.zoom.us/j/87078928687\n	In Person: 550 Sherbrooke\, R
 oom 189\n	\n	Abstract: Nature is the most powerful protein engineer\, and ev
 olution is nature’s design process. We have been using protein language mo
 dels to better understand the rules of natural protein evolution. By recon
 structing a global landscape of protein evolution through local evolutiona
 ry predictions that we refer to as evolutionary velocity (evo-velocity)\, 
 we can predict evolution in diverse landscapes\, including the progression
  of viral outbreaks\, and the evolution of eukaryotic proteins over geolog
 ic eons. The same ideas can also be used to evolve natural proteins with i
 mproved fitness\, in a highly efficient manner. To improve predictive capa
 bilities\, we incorporate structural information with a structure-informed
  language model. Importantly\, the use of only protein backbone coordinate
 s is sufficient to learn principles of binding that generalize to protein 
 complexes and enable antibody engineering with unprecedented efficiency. T
 ogether\, these results lay the groundwork for more potent and resilient t
 herapeutic design in unsupervised settings and in the absence of task-spec
 ific training data.\n
DTSTART:20260120T170000Z
DTEND:20260120T180000Z
SUMMARY:QLS Seminar Series - Peter S. Kim
URL:/science/channels/event/qls-seminar-series-peter-s
 -kim-369825
END:VEVENT
END:VCALENDAR