EUVIMEDEUVIMED entdecken
Open Access · CC BY-NC-ND 4.0

MulAFNet: Integrating Multiple Molecular Representations for Enhanced Property Prediction

Lei Ci, Beilei Li, Jiahao Xu, Sihua Peng, Linhua Jiang, Wei Long iD

ACS Omega · 01.04.2025 · 10 (12) · 12043-12053

DOI: 10.1021/acsomega.4c09884 ↗

Kurz gefasst

Fachartikel in der Zeitschrift ACS Omega, online erschienen am 19.03.2025. Verfasst von Lei Ci und 5 weiteren Autor:innen. Beteiligte Einrichtung: School of Information Engineering, Huzhou University, Huzhou 313000, China. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 48 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC-ND 4.0). Gefördert von: National Natural Science Foundation of China, Zhejiang-French Digital Monitoring Lab for Aquatic Resources and Environment, Department of Science and Technology of Zhejiang Province.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

In computer-aided drug design, molecular representation plays a crucial role. Most existing multimodal approaches primarily perform simple concatenation of various feature representations, without adequately emphasizing effective integration among these features. To address this issue, this study proposes a network framework that integrates multimodal representations using a multihead attention flow (MulAFNet). MulAFNet utilizes SMILES string representation and two levels of molecular graph representations: atom-level and functional group-level graph structure. Pretraining tasks are established for each of these three representations, which are then fused in downstream tasks to predict molecular properties. The experiments were conducted on six classification data sets and three regression data sets, demonstrating that the use of multiple molecular representations as input has a significant impact on the results. In particular, the excellent performance of our fusion method in molecular property prediction outperforms other state-of-the-art methods, proving its superiority. Additionally, comparative experiments on fusion methods and ablation studies, further validate the effectiveness of MulAFNet. The results demonstrate that multiple molecular feature representations provide a more comprehensive molecular understanding, and appropriate pretraining tasks enhance molecular property prediction.

Autor:innen und Institutionen

  • School of Information Engineering, Huzhou University, Huzhou 313000, China.
  • Huzhou Fengshengwan Aquatic Products Co., Ltd, Huzhou 313000, China.
  • College of Public Health, University of Georgia, Athens, Georgia 30602, United States.

ORCID-Profile: Wei Long

Förderung

  • National Natural Science Foundation of China
  • Zhejiang-French Digital Monitoring Lab for Aquatic Resources and Environment, Department of Science and Technology of Zhejiang Province

Zitieren

APA

Ci, L., Li, B., Xu, J., Peng, S., Jiang, L., & Long, W. (2025). MulAFNet: Integrating Multiple Molecular Representations for Enhanced Property Prediction. ACS Omega, 10(12), 12043-12053. https://doi.org/10.1021/acsomega.4c09884

Vancouver

Ci L, Li B, Xu J, Peng S, Jiang L, Long W. MulAFNet: Integrating Multiple Molecular Representations for Enhanced Property Prediction. ACS Omega. 2025;10(12):12043-12053. doi:10.1021/acsomega.4c09884

BibTeX
@article{Ci2025,
  author = {Ci, Lei and Li, Beilei and Xu, Jiahao and Peng, Sihua and Jiang, Linhua and Long, Wei},
  title = {MulAFNet: Integrating Multiple Molecular Representations for Enhanced Property Prediction},
  journal = {ACS Omega},
  year = {2025},
  volume = {10},
  number = {12},
  pages = {12043--12053},
  doi = {10.1021/acsomega.4c09884}
}
Kostenlos starten →