SynFlowNet: Design of Diverse and Novel Molecules with Synthesis Constraints
This addresses the challenge of generating synthesizable molecules for drug discovery, though it is incremental in integrating synthesis constraints into existing generative frameworks.
The paper tackled the problem of generative models producing synthetically inaccessible molecules in drug design by introducing SynFlowNet, a GFlowNet model that uses chemical reactions and purchasable reactants to build molecules, resulting in considerable improvement in sample diversity and successful identification of synthesis pathways for unseen molecules.
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 purchasable 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 approach enables our model to successfully identify synthesis pathways for previously unseen molecules.