BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:SynFlowNet: Design of Synthesisable Molecules with GFlowNets - Mir
 una Cretu (University of Cambridge)
DTSTART:20250128T130000Z
DTEND:20250128T140000Z
UID:TALK223375@talks.cam.ac.uk
CONTACT:Mateja Jamnik
DESCRIPTION:Generative models see increasing use in computer-aided drug de
 sign. However\, while performing well at capturing distributions of molecu
 lar motifs\, they often produce synthetically inaccessible molecules. To a
 ddress this\, we introduce SynFlowNet\, a GFlowNet model whose action spac
 e uses chemical reactions and buyable reactants to sequentially build new 
 molecules. By incorporating forward synthesis as an explicit constraint of
  the generative mechanism\, we aim at bridging the gap between in silico m
 olecular generation and real world synthesis capabilities. We evaluate our
  approach using synthetic accessibility scores and an independent retrosyn
 thesis tool to assess the synthesizability of our compounds\, and motivate
  the choice of GFlowNets through considerable improvement in sample divers
 ity compared to baselines. Additionally\, we identify challenges with reac
 tion encodings that can complicate traversal of the MDP in the backward di
 rection. To address this\, we introduce various strategies for learning th
 e GFlowNet backward policy and thus demonstrate how additional constraints
  can be integrated into the GFlowNet MDP framework.\n\n"You can also join 
 us on Zoom":https://cam-ac-uk.zoom.us/j/83400335522?pwd=LkjYvMOvVpMbabOV1M
 VTm8QU6DrGN7.1
LOCATION:Lecture Theatre 2\, Computer Laboratory\, William Gates Building
END:VEVENT
END:VCALENDAR