Abstract: Finding synthesis routes for molecules of interest is essential in the discovery of new drugs and materials. To find such routes, computer-assisted synthesis planning (CASP) methods are employed, which rely on a single-step model of chemical reactivity. In this study, we introduce a template-based single-step retrosynthesis model based on Modern Hopfield Networks, which learn an encoding of both molecules and reaction templates in order to predict the relevance of templates for a given molecule. The template representation allows generalization across different reactions and significantly improves the performance of template relevance prediction, especially for templates with few or zero training examples. With inference speed up to orders of magnitude faster than baseline methods, we improve or match the state-of-the-art performance for top-k exact match accuracy for k ≥ 3 in the retrosynthesis benchmark USPTO-50k.

Bio: Philipp Seidl is a PhD candidate at the Institute for Machine Learning - JKU Linz. He has a double Bachelor degree in Information Systems and Medical Engineering and a Msc degree in Bioinformatics. His current research focus on how to leverage machine learning methods especially Transformers, Modern Hopfield Networks and Few-Shot Learning algorithms for drug discovery applications

Useful links: Paper MHNreact