EUVIMEDTutustu EUVIMEDiin
Open access · CC BY 4.0

IBPGNET: lung adenocarcinoma recurrence prediction based on neural network interpretability

Zhanyu Xu, Haibo Liao, Liuliu Huang, Qingfeng Chen iD, Wei Lan iD, Shikang Li iD

Briefings in Bioinformatics · 2024-03-27 · 25 (3)

DOI: 10.1093/bib/bbae080 ↗

At a glance

Journal article in Briefings in Bioinformatics, published online on 2024-03-31. Written by Zhanyu Xu and 5 co-authors. Institution: Department of Thoracic and Cardiovascular Surgery, The First Affiliated Hospital of Guangxi Medical University, Nanning, Guangxi Zhuang Autonomous Re…. Major MEDLINE topics: Adenocarcinoma of Lung, Lung Neoplasms. Cited 19 times so far (Crossref); 42 references. The full text is freely available (open access, CC BY 4.0). Funded by: Guangxi Natural Science Foundation, National Key Clinical Specialty Construction Project, Guangxi Key Clinical Specialty Construction Project.

TiivistelmäSubjectsBibliografiset tiedotCiteRelated studies

Abstract (original language)

Lung adenocarcinoma (LUAD) is the most common histologic subtype of lung cancer. Early-stage patients have a 30–50% probability of metastatic recurrence after surgical treatment. Here, we propose a new computational framework, Interpretable Biological Pathway Graph Neural Networks (IBPGNET), based on pathway hierarchy relationships to predict LUAD recurrence and explore the internal regulatory mechanisms of LUAD. IBPGNET can integrate different omics data efficiently and provide global interpretability. In addition, our experimental results show that IBPGNET outperforms other classification methods in 5-fold cross-validation. IBPGNET identified PSMC1 and PSMD11 as genes associated with LUAD recurrence, and their expression levels were significantly higher in LUAD cells than in normal cells. The knockdown of PSMC1 and PSMD11 in LUAD cells increased their sensitivity to afatinib and decreased cell migration, invasion and proliferation. In addition, the cells showed significantly lower EGFR expression, indicating that PSMC1 and PSMD11 may mediate therapeutic sensitivity through EGFR expression.

Subjects

MeSH terms (MEDLINE)

Adenocarcinoma of LungLung NeoplasmsHumansCell Line, TumorBiomarkers, TumorGene Expression Regulation, NeoplasticErbB ReceptorsCell Proliferation

Author keywords

PSMC1 and PSMD11lung adenocarcinomamulti-omics dataneural network interpretabilityrecurrence prediction

Substances

Biomarkers, TumorErbB Receptors

Authors and institutions

  • Department of Thoracic and Cardiovascular Surgery, The First Affiliated Hospital of Guangxi Medical University, Nanning, Guangxi Zhuang Autonomous Region 530021, China.
  • School of computer, Electronic and Information, Guangxi University, Nanning, Guangxi Zhuang Autonomous Region 530021, China.

ORCID profiles: Qingfeng Chen, Wei Lan, Shikang Li

Funding

  • Guangxi Natural Science Foundation
  • National Key Clinical Specialty Construction Project
  • Guangxi Key Clinical Specialty Construction Project
  • National Natural Science Foundation of China
  • Natural Science Foundation of Guangxi
  • CAAI-Huawei MindSpore Open Fund
  • Natural Science and Technology Innovation Development Foundation of Guangxi University

Cite

APA

Xu, Z., Liao, H., Huang, L., Chen, Q., Lan, W., & Li, S. (2024). IBPGNET: lung adenocarcinoma recurrence prediction based on neural network interpretability. Briefings in Bioinformatics, 25(3). https://doi.org/10.1093/bib/bbae080

Vancouver

Xu Z, Liao H, Huang L, Chen Q, Lan W, Li S. IBPGNET: lung adenocarcinoma recurrence prediction based on neural network interpretability. Briefings in Bioinformatics. 2024;25(3). doi:10.1093/bib/bbae080

BibTeX
@article{Xu2024,
  author = {Xu, Zhanyu and Liao, Haibo and Huang, Liuliu and Chen, Qingfeng and Lan, Wei and Li, Shikang},
  title = {IBPGNET: lung adenocarcinoma recurrence prediction based on neural network interpretability},
  journal = {Briefings in Bioinformatics},
  year = {2024},
  volume = {25},
  number = {3},
  doi = {10.1093/bib/bbae080}
}
Start for free →