Skip to yearly menu bar Skip to main content


Path-Aware and Structure-Preserving Generation of Synthetically Accessible Molecules

Juhwan Noh · Dae-Woong Jeong · Kiyoung Kim · Sehui Han · Moontae Lee · Honglak Lee · Yousung Jung

Hall E #107

Keywords: [ DL: Generative Models and Autoencoders ] [ MISC: Unsupervised and Semi-supervised Learning ] [ APP: Chemistry and Drug Discovery ]


Computational chemistry aims to autonomously design specific molecules with target functionality. Generative frameworks provide useful tools to learn continuous representations of molecules in a latent space. While modelers could optimize chemical properties, many generated molecules are not synthesizable. To design synthetically accessible molecules that preserve main structural motifs of target molecules, we propose a reaction-embedded and structure-conditioned variational autoencoder. As the latent space jointly encodes molecular structures and their reaction routes, our new sampling method that measures the path-informed structural similarity allows us to effectively generate structurally analogous synthesizable molecules. When targeting out-of-domain as well as in-domain seed structures, our model generates structurally and property-wisely similar molecules equipped with well-defined reaction paths. By focusing on the important region in chemical space, we also demonstrate that our model can design new molecules with even higher activity than the seed molecules.

Chat is not available.