English

Assessing the Extrapolation Capability of Template-Free Retrosynthesis Models

Chemical Physics 2024-03-08 v1 Machine Learning

Abstract

Despite the acknowledged capability of template-free models in exploring unseen reaction spaces compared to template-based models for retrosynthesis prediction, their ability to venture beyond established boundaries remains relatively uncharted. In this study, we empirically assess the extrapolation capability of state-of-the-art template-free models by meticulously assembling an extensive set of out-of-distribution (OOD) reactions. Our findings demonstrate that while template-free models exhibit potential in predicting precursors with novel synthesis rules, their top-10 exact-match accuracy in OOD reactions is strikingly modest (< 1%). Furthermore, despite the capability of generating novel reactions, our investigation highlights a recurring issue where more than half of the novel reactions predicted by template-free models are chemically implausible. Consequently, we advocate for the future development of template-free models that integrate considerations of chemical feasibility when navigating unexplored regions of reaction space.

Cite

@article{arxiv.2403.03960,
  title  = {Assessing the Extrapolation Capability of Template-Free Retrosynthesis Models},
  author = {Shuan Chen and Yousung Jung},
  journal= {arXiv preprint arXiv:2403.03960},
  year   = {2024}
}
R2 v1 2026-06-28T15:11:25.326Z