BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Date iCal//NONSGML kigkonsult.se iCalcreator 2.20.2//
METHOD:PUBLISH
X-WR-CALNAME;VALUE=TEXT:Eventi DIAG
BEGIN:VTIMEZONE
TZID:Europe/Paris
BEGIN:STANDARD
DTSTART:20231029T030000
TZOFFSETFROM:+0200
TZOFFSETTO:+0100
TZNAME:CET
END:STANDARD
BEGIN:DAYLIGHT
DTSTART:20240331T020000
TZOFFSETFROM:+0100
TZOFFSETTO:+0200
TZNAME:CEST
END:DAYLIGHT
END:VTIMEZONE
BEGIN:VEVENT
UID:calendar.27647.field_data.0@www.diag.uniroma1.it
DTSTAMP:20260415T063442Z
CREATED:20240212T134109Z
DESCRIPTION:Abstract: Structure-based drug design (SBDD) aims to design sma
 ll-molecule ligands that bind with high affinity and specificity to pre-de
 termined protein targets. Traditional SBDD pipelines start with large-scal
 e docking of compound libraries from public databases\, thus limiting the 
 exploration of chemical space to existent previously studied regions. Rece
 nt machine learning methods approached this problem using an atom-by-atom 
 generation approach\, which is computationally expensive. In this talk\, I
  will reframe SBDD as a 3D-conditional generation problem and present Diff
 SBDD\, an SE(3)-equivariant 3D-conditional diffusion model that generates 
 novel ligands conditioned on protein pockets. Comprehensive in silico expe
 riments demonstrate the efficiency of DiffSBDD in generating novel and div
 erse drug-like ligands that engage protein pockets with high binding energ
 ies as predicted by in silico docking. Furthermore\, we show that DiffSBDD
  is capable of molecular optimisation and redesign out-of-the-box using in
 painting.Short Bio: Charlie is a PhD Student at the University of Cambridg
 e where he is supervised by Prof Sir Tom Blundell and Prof Pietro Lio. He 
 has a background in Biochemsitry and a passion for AI technology to solve 
 problems in structural biology and drug discovery\, in particular with dif
 fusion modelling and Geomtric Deep Learning.
DTSTART;TZID=Europe/Paris:20240220T143000
DTEND;TZID=Europe/Paris:20240220T143000
LAST-MODIFIED:20240212T135555Z
LOCATION:Aula Magna\, DIAG
SUMMARY:Talk: Structure-based Drug Design and Molecular Optimisation with D
 iffusion Models - Charles Harris
URL;TYPE=URI:https://www.diag.uniroma1.it/node/27647
END:VEVENT
END:VCALENDAR