Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2024 Mar 27;25(3):bbae080.
doi: 10.1093/bib/bbae080.

IBPGNET: lung adenocarcinoma recurrence prediction based on neural network interpretability

Affiliations

IBPGNET: lung adenocarcinoma recurrence prediction based on neural network interpretability

Zhanyu Xu et al. Brief Bioinform. .

Abstract

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.

Keywords: PSMC1 and PSMD11; lung adenocarcinoma; multi-omics data; neural network interpretability; recurrence prediction.

PubMed Disclaimer

Figures

Figure 1
Figure 1
The performance comparison of SGD, RF, LR, DT, LinearSVM, RBF-SVM, DeepOmix, P-NET, PathCNN and IBPGNET.
Figure 2
Figure 2
Performance of IBPGNET on different omics data types.
Figure 3
Figure 3
The effect of latent pathway hierarchy relationship on IBPGNET.
Figure 4
Figure 4
Visualization of biological hierarchies in IBPGNET.
Figure 5
Figure 5
Expression of PSMC1 and PSMD11 and siRNA study. (A) Expression of PSMC1 and PSMD11 in the bronchial epithelial cell line 16HBE and the LUAD cell lines. (B) H1975 cells transfected with control siRNA or PSMC1/PSMD11 siRNA. (C) CALU-3 cells transfected with control siRNA or PSMC1/PSMD11 siRNA.
Figure 6
Figure 6
Functional validation of PSMC1 and PSMD11 in LUAD. (A) The migratory and invasive capabilities of the H1975 and CALU-3 cells were evaluated by using Transwell migration and invasion assays. (B) Quantification of migration and invasion cells showed that the cell migration and invasion capacities in si-PSMC1 and si-PSMD11 group were remarkably inhibited. (C) si-PSMC1 and si-PSMD11 reduced H1975 and CALU-3 cells proliferation by CCK-8 assay. (D) Clonogenic assays were carried out for H1975 and CALU-3 cells transfected with either si-PSMC1 or si-PSMD11. E.si-PSMC1 and si-PSMD11 reduced H1975 and CALU-3 cells proliferation by clonogenic assays. (F) The IC50 of si-PSMC1 and si-PSMD11 were analyzed by the CCK8 assay. (G) WB analysis of the expression of EGFR protein in H1975 and CALU-3 cells.

Similar articles

Cited by

References

    1. Sung H, Ferlay J, Siegel RL, et al. Global cancer statistics 2020: GLOBOCAN estimates of incidence and mortality worldwide for 36 cancers in 185 countries. CA Cancer J Clin 2021;71:209–49. - PubMed
    1. Ettinger DS, Wood DE, Aisner DL, et al. NCCN guidelines® insights: non-small cell lung cancer, version 2.2023. J Natl Compr Canc Netw 2023;21:340–50. - PubMed
    1. Siegel RL, Miller KD, Fuchs HE, et al. Cancer statistics, 2022. CA Cancer J Clin 2022;72:7–33. - PubMed
    1. Yoo S, Sinha A, Yang D, et al. Integrative network analysis of early-stage lung adenocarcinoma identifies aurora kinase inhibition as interceptor of invasion and progression. Nat Commun 2022;13:1592. - PMC - PubMed
    1. Li J, Akbani R, Zhao W, et al. Explore, visualize, and analyze functional cancer proteomic data using the cancer proteome atlas. Cancer Res 2017;77:e51–51e54. - PMC - PubMed

MeSH terms