EUVIMEDEUVIMED entdecken
Open Access · CC BY 3.0

SurGBSA: learning representations from molecular dynamics simulations

Derek Jones, Yue Yang, Felice C. Lightstone, Niema Moshiri, Jonathan E. Allen, Tajana S. Rosing

Digital Discovery · 2026 · 5 (11) · 5214-5231

DOI: 10.1039/d6dd00174b ↗

Kurz gefasst

Fachartikel in der Zeitschrift Digital Discovery, 2026. Verfasst von Derek Jones und 5 weiteren Autor:innen. Die Arbeit nennt 64 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 3.0). Gefördert von: Office of the President, University of California, University of California, Lawrence Livermore National Laboratory.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

SurGBSA combines molecular dynamics pretraining with fine-tuning on snapshot-level MMGBSA energies, enabled by a dataset of short MD simulations of docking poses. The MMGBSA fine-tuned models adapt to binding affinity and decoy pose ranking tasks.

Förderung

  • Office of the President, University of California
  • University of California
  • Lawrence Livermore National Laboratory
  • Defense Threat Reduction Agency
  • American Heart Association
  • Semiconductor Research Corporation

Zitieren

APA

Jones, D., Yang, Y., Lightstone, F. C., Moshiri, N., Allen, J. E., & Rosing, T. S. (2026). SurGBSA: learning representations from molecular dynamics simulations. Digital Discovery, 5(11), 5214-5231. https://doi.org/10.1039/d6dd00174b

Vancouver

Jones D, Yang Y, Lightstone FC, Moshiri N, Allen JE, Rosing TS. SurGBSA: learning representations from molecular dynamics simulations. Digital Discovery. 2026;5(11):5214-5231. doi:10.1039/d6dd00174b

BibTeX
@article{Jones2026,
  author = {Jones, Derek and Yang, Yue and Lightstone, Felice C. and Moshiri, Niema and Allen, Jonathan E. and Rosing, Tajana S.},
  title = {SurGBSA: learning representations from molecular dynamics simulations},
  journal = {Digital Discovery},
  year = {2026},
  volume = {5},
  number = {11},
  pages = {5214--5231},
  doi = {10.1039/d6dd00174b}
}
Kostenlos starten →