Identification and Validation of Anoikis-Related Signatures for Predicting Prognosis in Lung Adenocarcinoma with Machine Learning

Qilong Wang; Nannan Sun; Mingzhi Zhang

doi:10.2147/IJGM.S409006

Identification and Validation of Anoikis-Related Signatures for Predicting Prognosis in Lung Adenocarcinoma with Machine Learning

Int J Gen Med. 2023 May 16:16:1833-1844. doi: 10.2147/IJGM.S409006. eCollection 2023.

Authors

Qilong Wang^{1

2}, Nannan Sun³, Mingzhi Zhang¹

Affiliations

¹ Department of Oncology, The First Affiliated Hospital of Zhengzhou University, Zhengzhou, Henan, People's Republic of China.
² The Academy of Medical Science of Zhengzhou University, Zhengzhou University, Zhengzhou, Henan, People's Republic of China.
³ Department of Hematology, The First Affiliated Hospital of Zhengzhou University, Zhengzhou, Henan, People's Republic of China.

Abstract

Background: Lung adenocarcinoma (LUAD) is an aggressive cancer that has an extremely poor prognosis. As well as facilitating the detachment of cancer cells from the primary tumor site, anoikis plays an important role in cancer metastasis. Few studies to date, however, have examined the role of anoikis in LUAD, in patient prognosis.

Methods: A total of 316 anoikis-related genes (ANRGs) integrated from Genecards and Harmonizome portals. LUAD transcriptome data were retrieved from the Genotype-Tissue Expression Project (GEO) and The Cancer Genome Atlas (TCGA). Anoikis-related prognostic genes (ANRGs) were primarily screened by univariate Cox regression. All ANRGs were included in the Least Absolute Shrinkage and Selection Operator (LASSO) Cox regression model to construct the powerful prognostic signature. This signature was validated and assessed using the Kaplan-Meier method as well as univariate and multivariate Cox regression analyses. Anoikis-related regulators of risk score were identified using a XG-boost machine learning model. The expression of ITGB4 protein was examined in a ZhengZhou University (ZZU) tissue cohort by immunohistochemistry, and the potential mechanisms of action of ITGB4 in LUAD were explored by GO, KEGG, and ingenuity pathway analyses and by GSEA.

Results: A risk score signature was constructed based on eight ANRGs, with high risk scores found to closely correlate with unfavorable clinical features. ITGB4 expression may be associated with 5-year over survival, with immunohistochemistry showed that the expression of ITGB4 was higher in LUAD than in nontumor tissues. Enrichment analysis suggested that ITGB4 may promote LUAD development by targeting E2F, MYC, and oxidative phosphorylation signaling pathways.

Conclusion: Our anoikis-related signature from RNA-seq data may be a novel prognostic biomarker in patients with LUAD. It may help physicians develop personalized LUAD treatments in clinical practice. Moreover, ITGB4 may affect the development of LUAD through the oxidative phosphorylation pathway.

Keywords: ITGB4; anoikis; lung adenocarcinoma; machine learning; prognosis.

Grants and funding

This study was supported by funds from the National Natural Science Foundation of China (81970184, 81570203).