EUVIMEDEUVIMED entdecken
Crossref

HimGNN: a novel hierarchical molecular graph representation learning framework for property prediction

Shen Han iD, Haitao Fu iD, Yuyang Wu, Ganglan Zhao, Zhenyu Song, Feng Huang, Zhongfei Zhang, Shichao Liu iD, Wen Zhang iD

Briefings in Bioinformatics · 20.09.2023 · 24 (5)

DOI: 10.1093/bib/bbad305 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Briefings in Bioinformatics, online erschienen am 18.08.2023. Verfasst von Shen Han und 8 weiteren Autor:innen. Beteiligte Einrichtung: College of Informatics, Huazhong Agricultural University, People's Republic of China. Hauptthemen laut MEDLINE: Deep Learning. Die Arbeit wurde bisher 60-mal zitiert (Crossref) und nennt 46 Literaturangaben. Gefördert von: National Natural Science Foundation of China.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Accurate prediction of molecular properties is an important topic in drug discovery. Recent works have developed various representation schemes for molecular structures to capture different chemical information in molecules. The atom and motif can be viewed as hierarchical molecular structures that are widely used for learning molecular representations to predict chemical properties. Previous works have attempted to exploit both atom and motif to address the problem of information loss in single representation learning for various tasks. To further fuse such hierarchical information, the correspondence between learned chemical features from different molecular structures should be considered. Herein, we propose a novel framework for molecular property prediction, called hierarchical molecular graph neural networks (HimGNN). HimGNN learns hierarchical topology representations by applying graph neural networks on atom- and motif-based graphs. In order to boost the representational power of the motif feature, we design a Transformer-based local augmentation module to enrich motif features by introducing heterogeneous atom information in motif representation learning. Besides, we focus on the molecular hierarchical relationship and propose a simple yet effective rescaling module, called contextual self-rescaling, that adaptively recalibrates molecular representations by explicitly modelling interdependencies between atom and motif features. Extensive computational experiments demonstrate that HimGNN can achieve promising performances over state-of-the-art baselines on both classification and regression tasks in molecular property prediction.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Deep LearningNeural Networks, ComputerLearningDrug Discovery

Stichwörter der Autor:innen

deep learningdrug discoverygraph neural networksmolecular property prediction

Autor:innen und Institutionen

  • College of Informatics, Huazhong Agricultural University, People's Republic of China.
  • College of Plant Science and Technology, Huazhong Agricultural University, People's Republic of China.
  • Computer Science Department, Binghamton University, Binghamton, NY, USA.
  • College of Informatics, Huazhong Agricultural University, People's Republic of China and Agricultural Bioinformatics Key Laboratory of Hubei Province, Hubei Engineering Technology Research Center of Agricultural Big Dat…

ORCID-Profile: Shen Han, Haitao Fu, Shichao Liu, Wen Zhang

Förderung

  • National Natural Science Foundation of China

Zitieren

APA

Han, S., Fu, H., Wu, Y., Zhao, G., Song, Z., Huang, F., Zhang, Z., Liu, S., & Zhang, W. (2023). HimGNN: a novel hierarchical molecular graph representation learning framework for property prediction. Briefings in Bioinformatics, 24(5). https://doi.org/10.1093/bib/bbad305

Vancouver

Han S, Fu H, Wu Y, Zhao G, Song Z, Huang F, et al. HimGNN: a novel hierarchical molecular graph representation learning framework for property prediction. Briefings in Bioinformatics. 2023;24(5). doi:10.1093/bib/bbad305

BibTeX
@article{Han2023,
  author = {Han, Shen and Fu, Haitao and Wu, Yuyang and Zhao, Ganglan and Song, Zhenyu and Huang, Feng and Zhang, Zhongfei and Liu, Shichao and Zhang, Wen},
  title = {HimGNN: a novel hierarchical molecular graph representation learning framework for property prediction},
  journal = {Briefings in Bioinformatics},
  year = {2023},
  volume = {24},
  number = {5},
  doi = {10.1093/bib/bbad305}
}
Kostenlos starten →