BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Memento EPFL//
BEGIN:VEVENT
SUMMARY:Epitope-specific antibody design by a deep learning generative mod
 el
DTSTART:20220516T100000
DTEND:20220516T110000
DTSTAMP:20260413T224213Z
UID:9f5a86189db30831add20b6c919ee78b8a9414144c6929087cbb1e12
CATEGORIES:Conferences - Seminars
DESCRIPTION:Prof. Possu Huang    Standford University\nhttp://www.protei
 ndesign.org\nBIOENGINEERING SEMINAR\n \n\n\n\n\n\n\n\n\nAbstract\n\n\n\n\
 n\nThe growing need for antibodies with customized specificity provides a 
 rich environment for engineering efforts. In recent years\, despite having
  streamlined experimental pipelines\, the fundamental math requiring exten
 sive libraries and screen campaigns to get an initial binding signal remai
 ns unchanged. A major advancement would be to directly design in silico 
 an epitope-specific binder from scratch\, providing a signal for potential
  optimization by artificial evolution. We have observed several key advant
 ages in neural network approaches over existing methods. By leveraging th
 e unique properties of neural networks\, we developed a generative model f
 or immunoglobulin 3D structures\, with which diverse structures can be mod
 eled with unprecedented speed. We extended it to a purely deep learning-ba
 sed protein-protein interface design pipeline that optimize not only spati
 al orientations but fully-flexible protein structures on the fly to desire
 d epitopes. This novel strategy explores neural network’s capabilities i
 n modeling dynamic structures\, and preliminary experimental results on 
 multiple targets support the plausibility of in silico design of epitope-
 specific antibodies.\n\n\n\n\n\n\n\n\n\n\n \n\n 
LOCATION:BM 5202 https://plan.epfl.ch/?room==BM%205202 https://epfl.zoom.u
 s/j/64283015868
STATUS:CONFIRMED
END:VEVENT
END:VCALENDAR