KMAN Publication Inc. Journal of Poultry Sciences and Avian Diseases 2981-135X 4 Serial Number 16 2026 06 22 Machine learning-driven identification of immune signatures from RNA-Seq data in H5N1-infected chickens: a computational Immunology approach Machine learning-driven identification of immune signatures from RNA-Seq data in H5N1-infected chickens: a computational Immunology approach EN Journal Article Highly Pathogenic Avian Influenza (H5N1) continues to pose a serious risk to public health and poultry. In order to differentiate H5N1-infected from healthy chicken samples and to guide the development of diagnostics and vaccines, we postulated that Machine Learning (ML) applied to RNA sequencing (RNA-Seq) data could biologically detect meaningful immune gene signatures. While previous transcriptomic studies have characterized host responses to H5N1 infection in chickens, the application of interpretable machine-learning approaches to prioritize immune-associated transcriptional signatures from chicken RNA-Seq datasets remains relatively unexplored. RNA-Seq data from H5N1-infected chicken lung and ileum tissues (ArrayExpress E-MTAB-2908) that were publicly available, were chosen. Fivefold stratified cross-validation (~80/20 train/test per fold) was used to train two supervised ML models, such as Random Forest (RF) and linear-kernel Support Vector Machine (SVM). Performance was evaluated using Area Under Curve (AUC) and Receiver Operating Characteristic (ROC) curves. RF reached a mean AUC=0.85, while SVM-Linear achieved AUC=0.75. Top-ranking interferon-stimulated genes (ISGs), including IFIT5, MX1, and OASL, were consistently upregulated in infected samples, indicating activation of type I interferon pathways. Concordant findings across models support the stability and biological relevance of the identified signatures despite the modest sample size. These findings demonstrate that interpretable ML approaches can successfully prioritize biologically relevant antiviral signatures from chicken RNA-Seq datasets. However, the identified signatures should be considered candidate computational immune signatures that require independent experimental validation before potential application in biomarker development, disease surveillance, or vaccine-related research.

https://www.journals.kmanpub.com/index.php/jpsad/article/download/6092/11626