EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

A Robust Drug–Target Interaction Prediction Framework with Capsule Network and Transfer Learning

Yixian Huang iD, Hsi-Yuan Huang iD, Yigang Chen iD, Yang-Chi-Dung Lin, Lantian Yao, Tianxiu Lin, Junlin Leng, Yuan Chang, Yuntian Zhang, Zihao Zhu, Kun Ma, Yeong-Nan Cheng und 2 weitere

International Journal of Molecular Sciences · 14.09.2023 · 24 (18) · 14061

DOI: 10.3390/ijms241814061 ↗

Kurz gefasst

Fachartikel in der Zeitschrift International Journal of Molecular Sciences, online erschienen am 14.09.2023. Verfasst von Yixian Huang und 13 weiteren Autor:innen. Beteiligte Einrichtung: School of Medicine, The Chinese University of Hong Kong, Shenzhen, Longgang District, Shenzhen 518172, China. Hauptthemen laut MEDLINE: Drug Discovery, Computational Biology. Die Arbeit wurde bisher 24-mal zitiert (Crossref) und nennt 61 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: the National Natural Science Foundation of China, Shenzhen Science and Technology Program, the Warshel Institute for Computational Biology funding from Shenzhen City and Longgang District.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Drug–target interactions (DTIs) are considered a crucial component of drug design and drug discovery. To date, many computational methods were developed for drug–target interactions, but they are insufficiently informative for accurately predicting DTIs due to the lack of experimentally verified negative datasets, inaccurate molecular feature representation, and ineffective DTI classifiers. Therefore, we address the limitations of randomly selecting negative DTI data from unknown drug–target pairs by establishing two experimentally validated datasets and propose a capsule network-based framework called CapBM-DTI to capture hierarchical relationships of drugs and targets, which adopts pre-trained bidirectional encoder representations from transformers (BERT) for contextual sequence feature extraction from target proteins through transfer learning and the message-passing neural network (MPNN) for the 2-D graph feature extraction of compounds to accurately and robustly identify drug–target interactions. We compared the performance of CapBM-DTI with state-of-the-art methods using four experimentally validated DTI datasets of different sizes, including human (Homo sapiens) and worm (Caenorhabditis elegans) species datasets, as well as three subsets (new compounds, new proteins, and new pairs). Our results demonstrate that the proposed model achieved robust performance and powerful generalization ability in all experiments. The case study on treating COVID-19 demonstrates the applicability of the model in virtual screening.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Drug DiscoveryComputational BiologyHumansNeural Networks, ComputerAnimalsCaenorhabditis elegansSARS-CoV-2COVID-19 Drug TreatmentCOVID-19Machine LearningAlgorithms

Stichwörter der Autor:innen

bidirectional encoder representations from transformerscapsule networkdrug–target interactionsmessage-passing neural networkstransfer learning

Autor:innen und Institutionen

  • School of Medicine, The Chinese University of Hong Kong, Shenzhen, Longgang District, Shenzhen 518172, China.
  • Warshel Institute for Computational Biology, The Chinese University of Hong Kong, Shenzhen, Longgang District, Shenzhen 518172, China.
  • Institute of Bioinformatics and Systems Biology, Department of Biological Science and Technology, National Yang Ming Chiao Tung University, Hsinchu 300, Taiwan.

ORCID-Profile: Yixian Huang, Hsi-Yuan Huang, Yigang Chen

Förderung

  • the National Natural Science Foundation of China
  • Shenzhen Science and Technology Program
  • the Warshel Institute for Computational Biology funding from Shenzhen City and Longgang District
  • Shenzhen-Hong Kong Cooperation Zone for Technology and Innovation
  • Guangdong Young Scholar Development Fund of Shenzhen Ganghong Group Co., Ltd.
  • Key Program of Guangdong Basic and Applied Basic Research Fund (Guangdong-Shenzhen Joint Fund)
  • National Natural Science Foundation of China
  • Warshel Institute for Computational Biology funding from Shenzhen City and Longgang District; Shenzhen-Hong Kong Cooperation Zone for Technology and Innovation

Zitieren

APA

Huang, Y., Huang, H. Y., Chen, Y., Lin, Y. C., Yao, L., Lin, T., Leng, J., Chang, Y., Zhang, Y., Zhu, Z., Ma, K., Cheng, Y. N., Lee, T. Y., & Huang, H. D. (2023). A Robust Drug–Target Interaction Prediction Framework with Capsule Network and Transfer Learning. International Journal of Molecular Sciences, 24(18), 14061. https://doi.org/10.3390/ijms241814061

Vancouver

Huang Y, Huang HY, Chen Y, Lin YC, Yao L, Lin T, et al. A Robust Drug–Target Interaction Prediction Framework with Capsule Network and Transfer Learning. International Journal of Molecular Sciences. 2023;24(18):14061. doi:10.3390/ijms241814061

BibTeX
@article{Huang2023,
  author = {Huang, Yixian and Huang, Hsi-Yuan and Chen, Yigang and Lin, Yang-Chi-Dung and Yao, Lantian and Lin, Tianxiu and Leng, Junlin and Chang, Yuan and Zhang, Yuntian and Zhu, Zihao and Ma, Kun and Cheng, Yeong-Nan and Lee, Tzong-Yi and Huang, Hsien-Da},
  title = {A Robust Drug–Target Interaction Prediction Framework with Capsule Network and Transfer Learning},
  journal = {International Journal of Molecular Sciences},
  year = {2023},
  volume = {24},
  number = {18},
  pages = {14061},
  doi = {10.3390/ijms241814061}
}
Kostenlos starten →