Modern Hopfield Networks for Few- and Zero-Shot Reaction Template Prediction

Abstract

Finding synthesis routes for molecules of interest is an essential step in the discovery of new drugs and materials. To find such routes, computer-assisted synthesis planning (CASP) methods are employed which rely on a model of chemical reactivity. In this study, we model single-step retrosynthesis in a template-based approach using modern Hopfield networks (MHNs). We adapt MHNs to associate different modalities, reaction templates and molecules, which allows the model to leverage structural information about reaction templates. This approach significantly improves the performance of template relevance prediction, especially for templates with few or zero training examples. With inference speed several times faster than that of baseline methods, we improve predictive performance for top-k exact match accuracy for $\mathrm{k}\ge 5$ in the retrosynthesis benchmark USPTO-50k.

14 pages + 12 pages appendix

References in corpus (9)

• PyTorch: An Imperative Style, High-Performance Deep Learning Library
• Sequence to Sequence Learning with Neural Networks
• Learning Transferable Visual Models From Natural Language Supervision
• Linking the Neural Machine Translation and the Prediction of Organic Chemistry Reactions
• Learning To Navigate The Synthetically Accessible Chemical Space Using Reinforcement Learning
• Learning to Make Generalizable and Diverse Predictions for Retrosynthesis
• Knowledge-aware Contrastive Molecular Graph Learning
• RetCL: A Selection-based Approach for Retrosynthesis via Contrastive Learning
• Data Transfer Approaches to Improve Seq-to-Seq Retrosynthesis