Improving Few- and Zero-Shot Reaction Template Prediction Using Modern Hopfield Networks
By Philipp Seidl, Philipp Renz, Natalia Dyubankova, Paulo Neves, Jonas Verhoeven, Jörg Kurt Wegner, Marwin H. S. Segler, Sepp Hochreiter, Günter Klambauer. 2022
90 citations recorded by the source corpus.
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. Code to reproduce the results is available at github.com/ml-jku/mhn-react.
Subfields: Computational Theory and Mathematics, Materials Chemistry, Molecular Biology, Prompting & Reasoning
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Computational Theory and Mathematics
In Materials Chemistry
- Sepp Hochreiter
- Günter Klambauer
- Angela Bitto-Nemling
- Nathan Oken Hodas
- Thomas Unterthiner
- Boris Hanin
- Abhinav Vishnu
- Garrett B. Goh
In Molecular Biology
Citations in the corpus
- CLOOB: Modern Hopfield Networks with InfoLOOB Outperform CLIP (2021, background): “Modern Hopfield networks have already been successfully applied to immune repertoire classification (Widrich et al., 2020), chemical reaction prediction (Seidl et al., 2022) and reinforcement learning (Widrich et al., 2021; Paischer et al., 2022).”
- History Compression via Language Models in Reinforcement Learning (2022, methodology): “MHNs have already been successfully applied to immune repertoire classification (Widrich et al., 2020), and chemical reaction prediction (Seidl et al., 2022).”