Computational discovery of PGD, MAPK14, and KRAS as diagnostic biomarkers for neonatal sepsis through integrated machine learning, immune infiltration analysis, and molecular docking - Takeaways - MDSpire

Computational discovery of PGD, MAPK14, and KRAS as diagnostic biomarkers for neonatal sepsis through integrated machine learning, immune infiltration analysis, and molecular docking

  • By

  • Li Luo

  • Jing Chen

  • Weiwei Du

  • Jianchuan Hu

  • May 29, 2026

  • 0 min

Share

  • 1

    This study identifies PGD, MAPK14, and KRAS as potential diagnostic biomarkers for neonatal sepsis using integrated bioinformatics and machine learning.

  • 2

    Machine learning algorithms LASSO, SVM-RFE, and XGBoost were employed to select biomarkers from transcriptomic data of neonatal sepsis patients.

  • 3

    Immune infiltration analysis revealed increased neutrophils and Tregs, along with decreased CD8+ T cells in neonatal sepsis cases.

  • 4

    Molecular docking identified dasatinib and gefitinib as high-affinity binders to the biomarkers MAPK14 and KRAS.

  • 5

    In vitro validation showed that LPS stimulation significantly upregulated the expression of PGD, MAPK14, and KRAS in macrophages.

Original Source(s)

Computational discovery of PGD, MAPK14, and KRAS as diagnostic biomarkers for neonatal sepsis through integrated machine learning, immune infiltration analysis, and molecular docking

  • by Li Luo, Jing Chen, Weiwei Du, Jianchuan Hu

  • May 29, 2026

Related Content

Diagnostic performance of interleukin-27 and C-reactive protein in neonatal sepsis: an updated systematic review and meta-analysis

Sepsis and septic shock case identification from electronic health records: an open-source workflow and comparison of cohorts by criteria

Research progress on risk factors and clinical management of Ureaplasma Species infection in preterm infants