Aligned Diffusion Models for Retrosynthesis

Najwa Laabid, Severi Rissanen, Markus Heinonen, Arno Solin, Vikas Garg

Keywords: diffusion models, retrosynthesis, equivariance, graph generative models

TL;DR: We figure out the proper way to apply graph diffusion models to retrosynthesis, which includes relaxing permutation equivariance.

Abstract: Retrosynthesis, the task of identifying precursors for a given molecule, can be naturally framed as a conditional graph generation task, with diffusion models being a particularly promising approach. We show mathematically that permutation equivariant denoisers severely limit the expressiveness of graph diffusion models and thus their adaptation to retrosynthesis. To address this limitation, we relax the equivariance requirement such that it only applies to aligned permutations of the conditioning and the generated graphs obtained through atom mapping, resulting in a diffusion model with state-of-the-art results in template-free retrosynthesis.

Submission Number: 77