BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Development of the first proteochemometric model to understand the
  selectivity of bromodomains for small molecule inhibitors - Kathryn Gibli
 n (University of Cambridge)
DTSTART:20161118T122000Z
DTEND:20161118T124000Z
UID:TALK68037@talks.cam.ac.uk
CONTACT:Lisa Masters
DESCRIPTION:The bromodomain family presents a druggable family of epigenet
 ic proteins\, for which multiple recent drug discovery efforts have yielde
 d selective small molecule probes\, enabling elucidation of therapeutic ro
 les in oncology\, inflammation and cardiovascular disease. Although progre
 ss has been made\, the design of selective bromodomain inhibitors is still
  a challenge\, particularly due to the lack of understanding of the driver
 s of selectivity. This study integrates bioactivity data from the public d
 omain\, as well as internal data from AstraZeneca to build the first in si
 lico proteochemometric models to predict compound selectivity profiles for
  the bromodomain target family. The random forest algorithm was employed t
 o build highly predictive classification models\, utilising well-validated
  Morgan fingerprints and physicochemical property descriptors to describe 
 the compounds and alignment dependent amino acid property descriptors to d
 escribe the targets. The models outperformed global quantitative structure
  activity relationship (QSAR) predictions and also quantitative sequence a
 ctivity models (QSAM). Interpretation of the models led to the identificat
 ion of key chemotypes and protein hotspots that contribute to the binding 
 interaction between small molecules and bromodomains.\n
LOCATION:Unilever Lecture Theatre\,  Department of Chemistry
END:VEVENT
END:VCALENDAR