BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:RetroBridge: Modeling Retrosynthesis with Markov Bridges - Arne Sc
 hneuing &amp\; Ilia Igashov (EPFL)
DTSTART:20231114T130000Z
DTEND:20231114T140000Z
UID:TALK207871@talks.cam.ac.uk
CONTACT:118732
DESCRIPTION:Retrosynthesis planning is a fundamental challenge in chemistr
 y which aims at designing reaction pathways from commercially available st
 arting materials to a target molecule. Each step in multi-step retrosynthe
 sis planning requires accurate prediction of possible precursor molecules 
 given the target molecule and confidence estimates to guide heuristic sear
 ch algorithms. In this talk\, we present a new probabilistic way to addres
 s this challenge. To this end\, we model single-step retrosynthesis planni
 ng as a distribution learning problem in a discrete state space. First\, w
 e introduce the Markov Bridge Model\, a generative framework aimed to appr
 oximate the dependency between two intractable discrete distributions acce
 ssible via a finite sample of coupled data points. Our framework is based 
 on the concept of a Markov bridge\, a Markov process pinned at its endpoin
 ts. Unlike diffusion-based methods\, our Markov Bridge Model does not need
  a tractable noise distribution as a sampling proxy and directly operates 
 on the input product molecules as samples from the intractable prior distr
 ibution.\n\n*Bios:*\n\nArne Schneuing is a PhD student in Bruno Correia’
 s group at École Polytechnique Fédérale de Lausanne (EPFL) and co-advis
 ed by Michael Bronstein. Previously\, he obtained a Master’s degree in e
 lectrical engineering and robotics from RWTH Aachen and KTH Stockholm. Arn
 e works on geometric deep learning and generative models for the design of
  molecular interactions between proteins and other biomolecules.\n\nIlia I
 gashov is a PhD student at Laboratory of Protein Design and Immunoengineer
 ing (EPFL)\, advised by Bruno Correia and Michael Bronstein\, and is a fel
 low of EPFLglobaLeaders program. His research interests lie in geometric d
 eep learning for biology and chemistry\, and especially in applications to
  protein-protein interactions and drug discovery. Prior to PhD\, Ilia did 
 research internships at Inria and Université Grenoble Alpes where he work
 ed on graph neural networks for protein model quality assessment.\n\n"Join
  us on Zoom":https://cam-ac-uk.zoom.us/j/92041617729\n
LOCATION:Zoom: https://cam-ac-uk.zoom.us/j/92041617729
END:VEVENT
END:VCALENDAR