Identification of Early Genetic Markers in the Peripheral Blood of Newborns with Bronchopulmonary Dysplasia Using Bioinformatics Analysis and Machine Learning Algorithms

Arailym Abilbayeva 1 * , Anel Tarabayeva 1, Iskander Isgandarov 1, Dana Yerbolat 1, Nuray Shaktay 1, Dinara Yelyubayeva 2
More Detail
1 Asfendiyarov Kazakh National Medical University
2 Center for Perinatology and Pediatric Cardiac Surgery
* Corresponding Author
J CLIN MED KAZ, Volume 23, Issue 1, pp. 52-61. https://doi.org/10.23950/jcmk/17772
OPEN ACCESS 271 Views 112 Downloads
Download Full Text (PDF)
Author Contributions: Conceptualization, A.A., A.T. and D.Y.; methodology, A.A., A.T., I.I., Dana Ye.; formal analysis, I.I. and Dana Ye.; writing – original draft preparation, A.A., A.T., I.I.,  Dana Ye. and N.S; writing – review and editing, A.A. and A.T.; visualization, N.S. and D.Y. All authors have read and agreed to the published version of the manuscript.

Data availability statement: The corresponding author can provide the data supporting the study's conclusions upon request. Due to ethical and privacy constraints, the data are not publicly accessible.

Artificial Intelligence (AI) Disclosure Statement: AI-Unassisted Work.

ABSTRACT

Objective: To identify and characterize a unique set of biomarker genes in peripheral blood on day 5 of life in preterm infants with subsequent development of bronchopulmonary dysplasia.
Methods: The open dataset GSE32472 was used to analyze gene expression profiles. The sample included preterm infants with a gestational age of less than 32 weeks and a body weight of ≤1500g. Peripheral blood samples collected within a 5-day window were analyzed to identify early transcriptional changes. Differential gene expression analysis was performed using the limma package with thresholds of |log_2FC|>0.5 and p.adj<0.05. Coexpression network analysis and functional enrichment were used to narrow the pool of potential target genes. At the final stage, three independent machine learning algorithms, such as SVM-RFE, LASSO, and Random Forest, were used to select the most prognostically significant genes. The diagnostic model based on the selected genes was visualized as a nomogram, and its predictive ability was assessed using ROC analysis and decision curve analysis.
Results: Comparative analysis identified 451 differentially expressed genes in the BPD group on day 5 of life. WGCNA analysis identified the MEpink module as the one most significantly correlated with the BPD phenotype. The intersection of DEGs and genes within the MEpink module identified 106 common genes, functional analysis of which revealed significant enrichment for processes associated with T-cell activation and T-cell receptor signaling pathways. A combined machine learning approach reliably identified four key hub genes with high prognostic significance: BTN3A3, AK5, NOG, and GCSAM. A diagnostic model based on these four genes demonstrated high predictive ability (AUC = 0.888) and clinical utility. Regulatory analysis revealed that the AK5, BTN3A3, and GCSAM genes are central nodes in the miRNA–mRNA regulatory network.
Conclusion: The identified day 5 gene window reflects key pathophysiological processes: developmental impairment, cellular stress, and inflammatory immune dysregulation. These results shift the focus from BPD diagnosis to early risk prediction. Day 5 molecular signatures possess high prognostic value and can be used to develop targeted therapeutic interventions.
Keywords: bronchopulmonary dysplasia, bioinformatics analysis, machine learning, hub genes, preterm infants

CITATION

Abilbayeva A, Tarabayeva A, Isgandarov I, Yerbolat D, Shaktay N, Yelyubayeva D. Identification of Early Genetic Markers in the Peripheral Blood of Newborns with Bronchopulmonary Dysplasia Using Bioinformatics Analysis and Machine Learning Algorithms. J CLIN MED KAZ. 2026;23(1):52-61. https://doi.org/10.23950/jcmk/17772

REFERENCES

  • Cui X, Fu J. Early prediction of bronchopulmonary dysplasia: can noninvasive monitoring methods be essential?. ERJ Open Res. 2023;9(2):00621-2022. https://doi.org/10.1183/23120541.00621-2022
  • Verder H, Li Z, Ramanathan R, Clark H, Sweet DG, Schousboe P, Scoutaris N, Verder P, Heiring C. Bronchopulmonary dysplasia with focus on early prediction and treatment: a narrative review. Pediatric Medicine. 2023;6:13. https://doi.org/10.21037/pm-21-98
  • Tenero L, Piazza M, Sandri M, Ferrante G, Giacomello E, Ficial B, Zaffanello M, Biban P, Piacentini G. Early Diagnosis of Bronchopulmonary Dysplasia with E-Nose: A Pilot Study in Preterm Infants. Sensors. 2024;24(19):6282. https://doi.org/10.3390/s24196282
  • Luo L, Luo F, Wu C, Zhang H, Jiang Q, He S, Li W, Zhang W, Cheng Y, Yang P, Li Z, Li M, Bao Y, & Jiang F. Identification of potential biomarkers in the peripheral blood of neonates with bronchopulmonary dysplasia using WGCNA and machine learning algorithms. Medicine (Baltimore). 2024;103(4):e37083. https://doi.org/10.1097/MD.0000000000037083
  • Dankhara N, Holla I, Ramarao S, Kalikkot Thekkeveedu R. Bronchopulmonary Dysplasia: Pathogenesis and Pathophysiology. J Clin Med. 2023;12(13):4207. https://doi.org/10.3390/jcm12134207
  • Ambalavanan N, Deutsch G, Pryhuber G, Travers CP, Willis KA. The evolving pathophysiology of bronchopulmonary dysplasia. Physiol Rev. 2026;106(1):197-237. https://doi.org/10.1152/physrev.00042.2024
  • Nuthakki S, Ahmad K, Johnson G, Cuevas Guaman M. Bronchopulmonary Dysplasia: Ongoing Challenges from Definitions to Clinical Care. J Clin Med. 2023;12(11):3864. https://doi.org/10.3390/jcm12113864
  • Kimble A, Robbins ME, Perez M. Pathogenesis of Bronchopulmonary Dysplasia: Role of Oxidative Stress from ‘Omics’ Studies. Antioxidants. 2022;11(12):2380. https://doi.org/10.3390/antiox11122380
  • Sikdar O, Harris C, Greenough A. Improving early diagnosis of bronchopulmonary dysplasia. Expert Rev Respir Med. 2024;18(5):283-294. https://doi.org/10.1080/17476348.2024.2367584
  • Cao L, Liu X, Sun T, Zhang Y, Bao T, Cheng H, Tian Z. Predictive and Diagnostic Values of Systemic Inflammatory Indices in Bronchopulmonary Dysplasia. Children (Basel). 2023;11(1):24. https://doi.org/10.3390/children11010024
  • An N, Li J, Li M. Role of systemic inflammation response index and prognostic nutritional index in the prediction of moderate-to-severe bronchopulmonary dysplasia in very preterm infants. Transl Pediatr. 2025;14(1):52-60. https://doi.org/10.21037/tp-24-381
  • Lowery JW, de Caestecker MP. BMP signaling in vascular development and disease. Cytokine Growth Factor Rev. 2010;21(4):287-298. https://doi.org/10.1016/j.cytogfr.2010.06.001
  • Katagiri T, Watabe T. Bone Morphogenetic Proteins. Cold Spring Harb Perspect Biol. 2016;8(6):a021899. https://doi.org/10.1101/cshperspect.a021899
  • Sountoulidis A, Stavropoulos A, Giaglis S, Apostolou E, Monteiro R, Chuva de Sousa Lopes SM, Chen H, Stripp BR, Mummery C, Andreakos E, Sideras P. Activation of the canonical bone morphogenetic protein (BMP) pathway during lung morphogenesis and adult lung tissue repair. PLoS One. 2012;7(8):e41460. https://doi.org/10.1371/journal.pone.0041460
  • Berrebeh N, Mbouamboua Y, Thuillet R, Ottaviani M, Robert F, Kamel Chelgham M, Magnone V, Desroches-Castan A, Ricard N, Anegon I, Remy S, Schermuly RT, Lebrigand K, Kojonazarov B, Savale L, Humbert M, Bailly S, Barbry P, Tu L, Guignabert C. Bone morphogenetic protein-9 controls pulmonary vascular growth and remodeling. Proc Natl Acad Sci USA. 2025;122(26):e2410229122. https://doi.org/10.1073/pnas.2410229122
  • Herrmann T, Karunakaran MM. Butyrophilins: γδ T Cell Receptor Ligands, Immunomodulators and More. Front Immunol. 2022;13:876493. https://doi.org/10.3389/fimmu.2022.876493
  • Kone A-s, Ait Ssi S, Sahraoui S, Badou A. BTN3A: A Promising Immune Checkpoint for Cancer Prognosis and Treatment. International Journal of Molecular Sciences. 2022;23(21):13424. https://doi.org/10.3390/ijms232113424
  • Kone AS, Ghouzlani A, Qandouci A, Issam Salah NEI, Bakoukou Y, Lakhdar A, Karkouri M, Badou A. High expression of BTN3A1 is associated with clinical and immunological characteristics and predicts a poor prognosis in advanced human gliomas. Front Immunol. 2024;15:1397486. https://doi.org/10.3389/fimmu.2024.1397486
  • Elsaie A, Menon RT, Shrestha AK, Gowda SH, Varghese NP, Barrios RJ, Blanco CL, Konduri GG, Shivanna B. Endothelial Adenosine Monophosphate-Activated Protein Kinase-Alpha1 Deficiency Potentiates Hyperoxia-Induced Experimental Bronchopulmonary Dysplasia and Pulmonary Hypertension. Antioxidants (Basel). 2021;10(12):1913. https://doi.org/10.3390/antiox10121913
  • Zhang F, Wang L, Zhou Y. Mitochondria as the central regulator of cell death in bronchopulmonary dysplasia. Front Physiol. 2025;16:1685526. https://doi.org/10.3389/fphys.2025.1685526
  • Xuefei Y, Xinyi Z, Qing C, Dan Z, Ziyun L, Hejuan Z, Xindong X, Jianhua F. Effects of Hyperoxia on Mitochondrial Homeostasis: Are Mitochondria the Hub for Bronchopulmonary Dysplasia?. Front Cell Dev Biol. 2021;9:642717. https://doi.org/10.3389/fcell.2021.642717
  • Jiang X, Lu X, McNamara G, Liu X, Cubedo E, Sarosiek KA, Sánchez-García I, Helfman DM, Lossos IS. HGAL, a germinal center specific protein, decreases lymphoma cell motility by modulation of the RhoA signaling pathway. Blood. 2010;116(24):5217-5227. https://doi.org/10.1182/blood-2010-04-281568
  • Lossos IS, Alizadeh AA, Rajapaksa R, Tibshirani R, Levy R. HGAL is a novel interleukin-4-inducible gene that strongly predicts survival in diffuse large B-cell lymphoma. Blood. 2003;101(2):433-440. https://doi.org/10.1182/blood-2002-06-1931
  • Wen L, Gao M, He Z, Guo P, Liu Z, Zhang P, Zhang F, Chen D, Zhou G, Zhou Z. Noggin, an inhibitor of bone morphogenetic protein signaling, antagonizes TGF-β1 in a mouse model of osteoarthritis. Biochemical and Biophysical Research Communications. 2021;570:199-205. https://doi.org/10.1016/j.bbrc.2021.07.044