EUVIMEDEUVIMED entdecken
Crossref

G2GT: Retrosynthesis Prediction with Graph-to-Graph Attention Neural Network and Self-Training

Zaiyun Lin, Shiqiu Yin iD, Lei Shi, Wenbiao Zhou, Yingsheng John Zhang iD

Journal of Chemical Information and Modeling · 2023

DOI: 10.1021/acs.jcim.2c01302 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of Chemical Information and Modeling, 2023. Verfasst von Zaiyun Lin und 4 weiteren Autor:innen. Beteiligte Einrichtung: Stone Wise, Room 918, Eighth Floor, Building 1, No. 6 Danling Street, Haidian District, Beijing, China 100089. Hauptthemen laut MEDLINE: Neural Networks, Computer, Learning. Die Arbeit wurde bisher 27-mal zitiert (Crossref) und nennt 37 Literaturangaben.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Retrosynthesis prediction, the task of identifying reactant molecules that can be used to synthesize product molecules, is a fundamental challenge in organic chemistry and related fields. To address this challenge, we propose a novel graph-to-graph transformation model, G2GT. The model is built on the standard transformer structure and utilizes graph encoders and decoders. Additionally, we demonstrate the effectiveness of self-training, a data augmentation technique that utilizes unlabeled molecular data, in improving the performance of the model. To further enhance diversity, we propose a weak ensemble method, inspired by reaction-type labels and ensemble learning. This method incorporates beam search, nucleus sampling, and top-k sampling to improve inference diversity. A simple ranking algorithm is employed to retrieve the final top-10 results. We achieved new state-of-the-art results on both the USPTO-50K data set, with a top-1 accuracy of 54%, and the larger more challenging USPTO-Full data set, with a top-1 accuracy of 49.3% and competitive top-10 results. Our model can also be generalized to all other graph-to-graph transformation tasks. Data and code are available at https://github.com/Anonnoname/G2GT_2

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Neural Networks, ComputerLearningAlgorithmsElectric Power Supplies

Autor:innen und Institutionen

  • Stone Wise, Room 918, Eighth Floor, Building 1, No. 6 Danling Street, Haidian District, Beijing, China 100089.

ORCID-Profile: Shiqiu Yin, Yingsheng John Zhang

Zitieren

APA

Lin, Z., Yin, S., Shi, L., Zhou, W., & Zhang, Y. J. (2023). G2GT: Retrosynthesis Prediction with Graph-to-Graph Attention Neural Network and Self-Training. Journal of Chemical Information and Modeling. https://doi.org/10.1021/acs.jcim.2c01302

Vancouver

Lin Z, Yin S, Shi L, Zhou W, Zhang YJ. G2GT: Retrosynthesis Prediction with Graph-to-Graph Attention Neural Network and Self-Training. Journal of Chemical Information and Modeling. 2023. doi:10.1021/acs.jcim.2c01302

BibTeX
@article{Lin2023,
  author = {Lin, Zaiyun and Yin, Shiqiu and Shi, Lei and Zhou, Wenbiao and Zhang, Yingsheng John},
  title = {G2GT: Retrosynthesis Prediction with Graph-to-Graph Attention Neural Network and Self-Training},
  journal = {Journal of Chemical Information and Modeling},
  year = {2023},
  doi = {10.1021/acs.jcim.2c01302}
}
Kostenlos starten →