EUVIMEDEUVIMED entdecken
Crossref

Discovery of Small‐Molecule Cryoprotectants Using Pretrained Language Model Representations

Sicai Li iD, Lingyu Shi, Yuanyuan Zhang, Zirui Wang, Xiaohu Wang, Huilan Liu iD, Gang Zhao iD

Advanced Materials · 09.11.2026

DOI: 10.1002/adma.75629 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Advanced Materials, online erschienen am 09.11.2026. Verfasst von Sicai Li und 6 weiteren Autor:innen. Beteiligte Einrichtung: Department of Electronic Engineering and Information Science, University of Science and Technology of China, Hefei, Anhui, P. R. China. Die Arbeit nennt 54 Literaturangaben. Gefördert von: National Natural Science Foundation of China, Yangtze River Delta Science and Technology Innovation Community Joint Basic Research Project, Strategic Priority Research Program of the Chinese Academy of Sciences.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Cryopreservation supports cell therapy, transfusion medicine, and tissue banking, but cryoprotectant selection remains constrained by empirical screening, toxicity, and ice recrystallization. We used pretrained language models as SMILES sequence encoders to prioritize small‐molecule cryoprotectants for experimental testing. Hierarchical representations were coupled to descriptor reconstruction, gated fusion, and downstream prediction of normalized mean grain size and thresholded labels. Splat‐cooling measurements assessed candidate ice recrystallization inhibition, followed by compatibility and cryopreservation experiments in red blood cells, human umbilical cord‐derived mesenchymal stem cells and rat abdominal aortas. Selected additives improved recovery or preservation endpoints within the tested formulations. This representation‐based screening workflow connects molecular property prediction with experimental cryobiology across ice, cellular, and tissue endpoints.

Schlagwörter

Stichwörter der Autor:innen

SMILEScryopreservationcryoprotectantsice recrystallizationpretrained language models

Autor:innen und Institutionen

  • Department of Electronic Engineering and Information Science, University of Science and Technology of China, Hefei, Anhui, P. R. China.
  • Department of Blood Transfusion, The First Affiliated Hospital of University of Science and Technology of China, Hefei, Anhui, P. R. China.
  • Department of Hematology, The First Affiliated Hospital of University of Science and Technology of China, Hefei, Anhui, P. R. China.
  • Center for Reproduction and Genetics, Department of Obstetrics and Gynecology, The First Affiliated Hospital of USTC, Division of Life Sciences and Medicine, University of Science and Technology of China, Hefei, Anhui,…
  • Anhui Provincial Joint Construction Key Laboratory of Biomimetic Medicine, Institute of Advanced Technology, University of Science and Technology of China, Hefei, Anhui, P. R. China.
  • Engineering Research Center of Biopreservation and Artificial Organs, Ministry of Education, Hefei, P. R. China.

ORCID-Profile: Sicai Li, Huilan Liu, Gang Zhao

Förderung

  • National Natural Science Foundation of China
  • Yangtze River Delta Science and Technology Innovation Community Joint Basic Research Project
  • Strategic Priority Research Program of the Chinese Academy of Sciences

Zitieren

APA

Li, S., Shi, L., Zhang, Y., Wang, Z., Wang, X., Liu, H., & Zhao, G. (2026). Discovery of Small‐Molecule Cryoprotectants Using Pretrained Language Model Representations. Advanced Materials. https://doi.org/10.1002/adma.75629

Vancouver

Li S, Shi L, Zhang Y, Wang Z, Wang X, Liu H, et al. Discovery of Small‐Molecule Cryoprotectants Using Pretrained Language Model Representations. Advanced Materials. 2026. doi:10.1002/adma.75629

BibTeX
@article{Li2026,
  author = {Li, Sicai and Shi, Lingyu and Zhang, Yuanyuan and Wang, Zirui and Wang, Xiaohu and Liu, Huilan and Zhao, Gang},
  title = {Discovery of Small‐Molecule Cryoprotectants Using Pretrained Language Model Representations},
  journal = {Advanced Materials},
  year = {2026},
  doi = {10.1002/adma.75629}
}
Kostenlos starten →