Identification and validation of biomarkers related to mitochondria during ex vivo lung perfusion for lung transplants based on machine learning algorithm

Zhi-Chang Yang; Wen-Yuan Lu; Zhen-Yang Geng; Yang Zhao; Xiao-Ming Chen; Tong Zheng; Ji-Ze Wu; Kai-Jun Huang; Hao-Xiang Yuan; Yang Yang

doi:10.1016/j.gene.2024.149097

Identification and validation of biomarkers related to mitochondria during ex vivo lung perfusion for lung transplants based on machine learning algorithm

Gene. 2024 Nov 14:149097. doi: 10.1016/j.gene.2024.149097. Online ahead of print.

Authors

Affiliations

¹ Department of Thoracic Surgery, The First Affiliated Hospital of Zhengzhou University, Zhengzhou University, Zhengzhou 450000, China.
² Department of Thoracic Surgery, Anyang Tumor Hospital, The Fourth Affiliated Hospital of Henan University of Science and Technology, Anyang 455000, China.
³ Department of General Surgery, Guangdong Provincial People's Hospital (Guangdong Academy of Medical Sciences), Southern Medical University, Guangzhou, Guangdong 510080, China.
⁴ Department of Thoracic Surgery, The First Affiliated Hospital of Zhengzhou University, Zhengzhou University, Zhengzhou 450000, China. Electronic address: [email protected].
⁵ Department of Thoracic Surgery, The First Affiliated Hospital of Zhengzhou University, Zhengzhou University, Zhengzhou 450000, China. Electronic address: [email protected].

PMID: 39549776
DOI: 10.1016/j.gene.2024.149097

Abstract

Background: Ex vivo lung perfusion (EVLP) is a critical strategy to rehabilitate marginal donor lungs, thereby increasing lung transplantation (LTx) rates. Ischemia-reperfusion (I/R) injury inevitably occurs during LTx. Exploring the common mechanisms between EVLP and I/R may unveil new treatment targets to enhance LTx outcomes.

Methods: We obtained datasets from the public Gene Expression Omnibus (GEO) for EVLP (GSE127055 and GSE127057) and I/R (GSE145989) processes. We performed analysis of differential gene expression (DEGs) and Gene Set Enrichment Analysis (GSEA). Mitochondrial genes were sourced from the MitoCarta 3.0 database. Hub mitochondrial-related DEGs (MitoDEGs) were identified using a combination of protein-protein interaction networks and machine learning methods, which were further validated in cell and mice models of EVLP.

Results: GSEA analysis of DEGs following EVLP and I/R revealed significant inhibition of mitochondrial function pathways, encompassing mitochondrial central dogma, mtRNA metabolism, OXPHOS assembly factors, metals and cofactors, and heme synthesis and processing processes. Machine learning algorithms including random forest, LASSO, and XGBoost identified five downregulated genes (MTERF1, ACACA, COX15, OSGEPL1, and COQ9) as hub MitoDEGs for both EVLP and I/R processes. We confirmed the reduced expression of these hub MitoDEGs in endothelial cells during EVLP and observed mitochondrial damage in endothelial cells characterized by swollen morphology and cristae disappearance.

Conclusions: Imbalance in mitochondrial homeostasis is a shared pathological process during EVLP and I/R-induced lung injury. The identified hub mitochondrial-related genes (MTERF1, ACACA, COX15, OSGEPL1, and COQ9) suggest promising therapeutic targets for lung injury during LTx. The downregulation of these genes indicates a significant disruption in mitochondrial function. This study provides potential mitochondrial-related therapeutic targets for I/R-induced lung injury and for donor lung repair during EVLP procedure in LTx.

Keywords: Ex vivo lung perfusion; Ischemia–reperfusion; Lung transplantation; Machine learning algorithms; Mitochondrial function.