RGFN: Synthesizable Molecular Generation Using GFlowNets

Michał Koziarski, Andrei Rekesh, Dmytro Shevchuk, Almer M. van der Sloot, Piotr Gaiński, Yoshua Bengio, Cheng-Hao Liu, Mike Tyers, Robert A. Batey

Keywords: drug discovery, generative models, GFlowNets, synthesizability

TL;DR: Molecular generation with GFlowNets in the chemical reaction space, ensuring synthesizability out-of-the-box

Abstract: In this paper, we propose an extension of the GFlowNet framework that operates directly in the space of chemical reactions, offering out-of-the-box synthesizability, while maintaining comparable quality of generated candidates. We demonstrate that with the proposed set of reactions and fragments, it is possible to obtain a search space of molecules orders of magnitude larger than existing screening libraries while offering low costs of synthesis. We also show that the approach scales to very large fragment libraries, further increasing the number of potential molecules. Our experiments showcase the effectiveness of the proposed approach across a range of oracle models.

Submission Number: 104