EUVIMEDEUVIMED entdecken
Crossref

FunQG: Molecular Representation Learning via Quotient Graphs

Hossein Hajiabolhassan iD, Zahra Taheri iD, Ali Hojatnia, Yavar Taheri Yeganeh iD

Journal of Chemical Information and Modeling · 12.06.2023 · 63 (11) · 3275-3287

DOI: 10.1021/acs.jcim.3c00445 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of Chemical Information and Modeling, online erschienen am 15.05.2023. Verfasst von Hossein Hajiabolhassan und 3 weiteren Autor:innen. Beteiligte Einrichtung: Department of Mathematics and Information Technology, Chair of Information Technology, Montanuniversität Leoben, Franz-Josef-Strasse 18, A-8700 Leobe…. Hauptthemen laut MEDLINE: Learning. Die Arbeit wurde bisher 15-mal zitiert (Crossref) und nennt 69 Literaturangaben. Gefördert von: Ministry of Science Research and Technology, National Natural Science Foundation of China.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

To accurately predict molecular properties, it is important to learn expressive molecular representations. Graph neural networks (GNNs) have made significant advances in this area, but they often face limitations like neighbors-explosion, under-reaching, oversmoothing, and oversquashing. Additionally, GNNs tend to have high computational costs due to their large number of parameters. These limitations emerge or increase when dealing with larger graphs or deeper GNN models. One potential solution is to simplify the molecular graph into a smaller, richer, and more informative one that is easier to train GNNs. Our proposed molecular graph coarsening framework called FunQG, uses Functional groups as building blocks to determine a molecule's properties, based on a graph-theoretic concept called Quotient Graph. We show through experiments that the resulting informative graphs are much smaller than the original molecular graphs and are thus more suitable for training GNNs. We apply FunQG to popular molecular property prediction benchmarks and compare the performance of popular baseline GNNs on the resulting data sets to that of state-of-the-art baselines on the original data sets. Our experiments demonstrate that FunQG yields notable results on various data sets while dramatically reducing the number of parameters and computational costs. By utilizing functional groups, we can achieve an interpretable framework that indicates their significant role in determining the properties of molecular quotient graphs. Consequently, FunQG is a straightforward, computationally efficient, and generalizable solution for addressing the molecular representation learning problem.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

LearningNeural Networks, Computer

Autor:innen und Institutionen

  • Department of Mathematics and Information Technology, Chair of Information Technology, Montanuniversität Leoben, Franz-Josef-Strasse 18, A-8700 Leoben, Austria.
  • Machine Learning and Graph Mining Lab, Department of Applied Mathematics, Faculty of Mathematical Sciences, Shahid Beheshti University, 19839-69411 Tehran, Iran.

ORCID-Profile: Hossein Hajiabolhassan, Zahra Taheri, Yavar Taheri Yeganeh

Förderung

  • Ministry of Science Research and Technology
  • National Natural Science Foundation of China

Zitieren

APA

Hajiabolhassan, H., Taheri, Z., Hojatnia, A., & Yeganeh, Y. T. (2023). FunQG: Molecular Representation Learning via Quotient Graphs. Journal of Chemical Information and Modeling, 63(11), 3275-3287. https://doi.org/10.1021/acs.jcim.3c00445

Vancouver

Hajiabolhassan H, Taheri Z, Hojatnia A, Yeganeh YT. FunQG: Molecular Representation Learning via Quotient Graphs. Journal of Chemical Information and Modeling. 2023;63(11):3275-3287. doi:10.1021/acs.jcim.3c00445

BibTeX
@article{Hajiabolhassan2023,
  author = {Hajiabolhassan, Hossein and Taheri, Zahra and Hojatnia, Ali and Yeganeh, Yavar Taheri},
  title = {FunQG: Molecular Representation Learning via Quotient Graphs},
  journal = {Journal of Chemical Information and Modeling},
  year = {2023},
  volume = {63},
  number = {11},
  pages = {3275--3287},
  doi = {10.1021/acs.jcim.3c00445}
}
Kostenlos starten →