![]() |
COOKIES: By using this website you agree that we can place Google Analytics Cookies on your device for performance monitoring. | ![]() |
University of Cambridge > Talks.cam > Artificial Intelligence Research Group Talks (Computer Laboratory) > SynFlowNet: Design of Synthesisable Molecules with GFlowNets
SynFlowNet: Design of Synthesisable Molecules with GFlowNetsAdd to your list(s) Download to your calendar using vCal
If you have a question about this talk, please contact Mateja Jamnik. Generative models see increasing use in computer-aided drug design. However, while performing well at capturing distributions of molecular motifs, they often produce synthetically inaccessible molecules. To address this, we introduce SynFlowNet, a GFlowNet model whose action space 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 molecular generation and real world synthesis capabilities. We evaluate our approach using synthetic accessibility scores and an independent retrosynthesis tool to assess the synthesizability of our compounds, and motivate the choice of GFlowNets through considerable improvement in sample diversity compared to baselines. Additionally, we identify challenges with reaction encodings that can complicate traversal of the MDP in the backward direction. To address this, we introduce various strategies for learning the GFlowNet backward policy and thus demonstrate how additional constraints can be integrated into the GFlowNet MDP framework. This talk is part of the Artificial Intelligence Research Group Talks (Computer Laboratory) series. This talk is included in these lists:
Note that ex-directory lists are not shown. |
Other listsCUCRS Caius Medsoc Talks: "A Timeline of Medicine" OkayVBNGOther talksPolynomial time guarantees for sampling based posterior inference Ghost Rats: Afterlives of Eradication on Lord Howe Island KK-duality and quantum hyperbolicity Mini Course - Random interlacements and the Gaussian free field A Systems Approach to Sustainability Transformation: science-based and stakeholders co-designed solution pathways Locke's Political Legacy |