EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

GD ‐Net: An Integrated Multimodal Information Model Based on Deep Learning for Cancer Outcome Prediction and Informative Feature Selection

Junqi Lin, Weizhen Deng, Junyu Wei, Jinyong Zheng, Kenan Chen, Hua Chai, Tao Zeng, Hui Tang iD

Journal of Cellular and Molecular Medicine · 2024

DOI: 10.1111/jcmm.70221 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of Cellular and Molecular Medicine, 2024. Verfasst von Junqi Lin und 7 weiteren Autor:innen. Beteiligte Einrichtung: School of Mathematics, Foshan University, Foshan, China. Hauptthemen laut MEDLINE: Deep Learning, Neoplasms. Die Arbeit wurde bisher 7-mal zitiert (Crossref) und nennt 58 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: The Natural Science Foundation of Guangdong Province of China, the National Natural Science Foundation of China, the Jihua laboratory scientific project.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Multimodal information provides valuable resources for cancer prognosis and survival prediction. However, the computational integration of this heterogeneous data information poses significant challenges due to the complex interactions between molecules from different biological modalities and the limited sample size. Here, we introduce GD‐Net, a G raph D eep learning algorithm to enhance the accuracy of survival prediction with an average accuracy of 72% by early fusing of multimodal information, which includes an interpretable and lightweight XGBoost module to efficiently extract informative features. First, we applied GD‐Net to eight cancer datasets and achieved superior performance compared to benchmarking methods, with an average 7.9% higher C‐index value. The ablation experiments strongly supported that multi‐modal integration could significantly improve accuracy over the single‐modality model. In the deep case study of liver cancer, 319 differential genes, 15 differential miRNAs and 155 methylated differential genes based on the predicted risk subgroups are identified as the informative features, and then we have statistically and biologically validated the efficacy of these key molecules in internal and external test datasets. The comprehensive independent validations demonstrated that GD‐Net is accurate and competitive in predicting different cancer outcomes in real‐time, and it is an effective tool for identifying new multimodal prognosis biomarkers.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Deep LearningNeoplasmsHumansPrognosisAlgorithmsBiomarkers, TumorLiver NeoplasmsComputational BiologyMicroRNAsDNA MethylationGene Expression Regulation, Neoplastic

Stichwörter der Autor:innen

cancer prognosiscontrastive learningdeep learningfeature selectionmulti‐modal integration

Substanzen

Biomarkers, TumorMicroRNAs

Autor:innen und Institutionen

  • School of Mathematics, Foshan University, Foshan, China.
  • Guangzhou National Laboratory, Guangzhou, China.
  • GMU-GIBH Joint School of Life Sciences, The Guangdong-Hong Kong-Macau Joint Laboratory for Cell Fate Regulation and Diseases, Guangzhou Laboratory, Guangzhou Medical University, Guangzhou, China.

ORCID-Profile: Hui Tang

Förderung

  • The Natural Science Foundation of Guangdong Province of China
  • the National Natural Science Foundation of China
  • the Jihua laboratory scientific project

Zitieren

APA

Lin, J., Deng, W., Wei, J., Zheng, J., Chen, K., Chai, H., Zeng, T., & Tang, H. (2024). GD ‐Net: An Integrated Multimodal Information Model Based on Deep Learning for Cancer Outcome Prediction and Informative Feature Selection. Journal of Cellular and Molecular Medicine. https://doi.org/10.1111/jcmm.70221

Vancouver

Lin J, Deng W, Wei J, Zheng J, Chen K, Chai H, et al. GD ‐Net: An Integrated Multimodal Information Model Based on Deep Learning for Cancer Outcome Prediction and Informative Feature Selection. Journal of Cellular and Molecular Medicine. 2024. doi:10.1111/jcmm.70221

BibTeX
@article{Lin2024,
  author = {Lin, Junqi and Deng, Weizhen and Wei, Junyu and Zheng, Jinyong and Chen, Kenan and Chai, Hua and Zeng, Tao and Tang, Hui},
  title = {GD ‐Net: An Integrated Multimodal Information Model Based on Deep Learning for Cancer Outcome Prediction and Informative Feature Selection},
  journal = {Journal of Cellular and Molecular Medicine},
  year = {2024},
  doi = {10.1111/jcmm.70221}
}
Kostenlos starten →