A programmed cell death-related model based on machine learning for predicting prognosis and immunotherapy responses in patients with lung adenocarcinoma

Yi Zhang; Yuzhi Wang; Jianlin Chen; Yu Xia; Yi Huang

doi:10.3389/fimmu.2023.1183230

A programmed cell death-related model based on machine learning for predicting prognosis and immunotherapy responses in patients with lung adenocarcinoma

Front Immunol. 2023 Aug 21:14:1183230. doi: 10.3389/fimmu.2023.1183230. eCollection 2023.

Authors

Yi Zhang^{1

2}, Yuzhi Wang³, Jianlin Chen^{1

2}, Yu Xia⁴, Yi Huang^{1

2

5

6}

Affiliations

¹ Shengli Clinical Medical College of Fujian Medical University, Fujian Medical University, Fuzhou, Fujian, China.
² Department of Clinical Laboratory, Fujian Provincial Hospital, Fuzhou, China.
³ Department of Laboratory Medicine, Deyang People's Hospital, Deyang, Sichuan, China.
⁴ Integrated Chinese and Western Medicine College, Fujian University of Traditional Chinese Medicine, Fuzhou, Fujian, China.
⁵ Central Laboratory, Center for Experimental Research in Clinical Medicine, Fujian Provincial Hospital, Fuzhou, China.
⁶ Fujian Provincial Key Laboratory of Critical Care Medicine, Fujian Provincial Key Laboratory of Cardiovascular Disease, Fuzhou, China.

Abstract

Background: lung adenocarcinoma (LUAD) remains one of the most common and lethal malignancies with poor prognosis. Programmed cell death (PCD) is an evolutionarily conserved cell suicide process that regulates tumorigenesis, progression, and metastasis of cancer cells. However, a comprehensive analysis of the role of PCD in LUAD is still unavailable.

Methods: We analyzed multi-omic variations in PCD-related genes (PCDRGs) for LUAD. We used cross-validation of 10 machine learning algorithms (101 combinations) to synthetically develop and validate an optimal prognostic cell death score (CDS) model based on the PCDRGs expression profile. Patients were classified based on their median CDS values into the high and low-CDS groups. Next, we compared the differences in the genomics, biological functions, and tumor microenvironment of patients between both groups. In addition, we assessed the ability of CDS for predicting the response of patients from the immunotherapy cohort to immunotherapy. Finally, functional validation of key genes in CDS was performed.

Results: We constructed CDS based on four PCDRGs, which could effectively and consistently stratify patients with LUAD (patients with high CDS had poor prognoses). The performance of our CDS was superior compared to 77 LUAD signatures that have been previously published. The results revealed significant genetic alterations like mutation count, TMB, and CNV were observed in patients with high CDS. Furthermore, we observed an association of CDS with immune cell infiltration, microsatellite instability, SNV neoantigens. The immune status of patients with low CDS was more active. In addition, CDS could be reliable to predict therapeutic response in multiple immunotherapy cohorts. In vitro experiments revealed that high DNA damage inducible transcript 4 (DDIT4) expression in LUAD cells mediated protumor effects.

Conclusion: CDS was constructed based on PCDRGs using machine learning. This model could accurately predict patients' prognoses and their responses to therapy. These results provide new promising tools for clinical management and aid in designing personalized treatment strategies for patients with LUAD.

Keywords: lung adenocarcinoma; machine learning; prognosis; programmed cell death; tumor microenvironment.

Publication types

Research Support, Non-U.S. Gov't

MeSH terms

Adenocarcinoma of Lung*
Apoptosis
Humans
Immunotherapy
Lung Neoplasms*
Machine Learning
Prognosis
Tumor Microenvironment

Grants and funding

This study was supported in part by Medical Vertical Project of Fujian Province (Grant No. 2020CXB001) to YH, Joint fund of science and technology innovation of Fujian province (Grant No. 2021Y9024) to YH, Key Project of Natural Science Foundation of Fujian province (Grant No. 2022J02048) to YH.