BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Structure-aware generation of molecules in protein pockets - Pavol
  Drotar
DTSTART:20210608T121500Z
DTEND:20210608T131500Z
UID:TALK160882@talks.cam.ac.uk
CONTACT:Mateja Jamnik
DESCRIPTION:"Join us on Zoom":https://zoom.us/j/99166955895?pwd=SzI0M3pMVE
 kvNmw3Q0dqNDVRalZvdz09\n\nSearching the vast chemical space for potential 
 drugs is intractable even for computational screening approaches\, though 
 deep generative methods have shown promise in proposing novel molecules fr
 om scratch (de-novo design). However\, most models fail to incorporate 3D 
 protein structures that are salient in designing drugs that bind to protei
 n targets. I present a novel supervised approach that combines insights fr
 om graph-generative and 3D models and constructs drugs inside protein pock
 ets\, atom-by-atom\, guided by structural information from crystallographi
 c drug datasets. I find that the model improves binding affinities on aver
 age by 8% and druglikeness scores by 10% over the non-guided baseline\, an
 d proposes some molecules that exceed the binding scores of known ligands.
LOCATION:Zoom
END:VEVENT
END:VCALENDAR