AUTHOR=Tao Ziyu , Mao Yan , Hu Yifang , Tang Xinfang , Wang Jimei , Zeng Ni , Bao Yunlei , Luo Fei , Wu Chuyan , Jiang Feng 

TITLE=Identification and immunological characterization of endoplasmic reticulum stress-related molecular subtypes in bronchopulmonary dysplasia based on machine learning

JOURNAL=Frontiers in Physiology

VOLUME=Volume 13 - 2022

YEAR=2023

URL=https://www.frontiersin.org/journals/physiology/articles/10.3389/fphys.2022.1084650

DOI=10.3389/fphys.2022.1084650

ISSN=1664-042X

ABSTRACT=Introduction: Bronchopulmonary dysplasia (BPD) is a life-threatening lung illness that affects premature infants and has a high incidence and mortality. Using interpretable machine learning, we aimed to investigate the involvement of endoplasmic reticulum (ER) stress-related genes (ERSGs) in BPD patients.
Methods: We evaluated the expression profiles of ERSGs and immune features in BPD using the GSE32472 dataset. The ERSG-based molecular clusters and associated immune cell infiltration were studied using 62 BPD samples. Cluster-specific differentially expressed genes (DEGs) were identified utilizing the WGCNA technique. The optimum machine model was applied after comparing its performance with that of the generalized linear model, the eXtreme Gradient Boosting, the support vector machine (SVM) model, and the random forest model.  Validation of the prediction efficiency was done by the use of a calibration curve, nomogram, decision curve analysis, and an external data set.
Results: The BPD samples were compared to the control samples, and the dysregulated ERSGs and activated immunological responses were analyzed. In BPD, two distinct molecular clusters associated with ER stress were identified. The analysis of immune cell infiltration indicated a considerable difference in levels of immunity between the various clusters. As measured by residual and root mean square error, as well as the area under the curve, the SVM machine model showed the greatest discriminative capacity. In the end, an SVM model integrating five genes was developed, and its performance was shown to be excellent on an external validation dataset. The effectiveness in predicting BPD subtypes was further established by decision curves, calibration curves, and nomogram analyses. 
Conclusions: We developed a potential prediction model to assess the risk of ER stress subtypes and the clinical outcomes of BPD patients, and our work comprehensively revealed the complex association between ER stress and BPD.