EUVIMEDEUVIMED entdecken
Open Access · CC BY-NC 3.0

Assessing the extrapolation capability of template-free retrosynthesis models

Jonghwi Choe, Shuan Chen, Yousung Jung

Digital Discovery · 2026 · 5 (6) · 2591-2599

DOI: 10.1039/d6dd00072j ↗

Kurz gefasst

Fachartikel in der Zeitschrift Digital Discovery, 2026. Verfasst von Jonghwi Choe und 2 weiteren Autor:innen. Die Arbeit nennt 36 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC 3.0). Gefördert von: National Research Foundation of Korea, Institute for Information and Communications Technology Promotion.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Out-of-distribution evaluation shows template-free retrosynthesis models achieve only around 1% accuracy on unseen reaction types, with novel predictions frequently showing invalid chemical transformations.

Förderung

  • National Research Foundation of Korea
  • Institute for Information and Communications Technology Promotion

Zitieren

APA

Choe, J., Chen, S., & Jung, Y. (2026). Assessing the extrapolation capability of template-free retrosynthesis models. Digital Discovery, 5(6), 2591-2599. https://doi.org/10.1039/d6dd00072j

Vancouver

Choe J, Chen S, Jung Y. Assessing the extrapolation capability of template-free retrosynthesis models. Digital Discovery. 2026;5(6):2591-2599. doi:10.1039/d6dd00072j

BibTeX
@article{Choe2026,
  author = {Choe, Jonghwi and Chen, Shuan and Jung, Yousung},
  title = {Assessing the extrapolation capability of template-free retrosynthesis models},
  journal = {Digital Discovery},
  year = {2026},
  volume = {5},
  number = {6},
  pages = {2591--2599},
  doi = {10.1039/d6dd00072j}
}
Kostenlos starten →