Predicting the risk of primary Sjögren's syndrome with key N7-methylguanosine-related genes: A novel XGBoost model

Abstract

Objectives: N7-methylguanosine (m7G) plays a crucial role in mRNA metabolism and other biological processes. However, its regulators' function in Primary Sjögren's Syndrome (PSS) remains enigmatic. Methods: We screened five key m7G-related genes across multiple datasets, leveraging statistical and machine learning computations. Based on these genes, we developed a prediction model employing the extreme gradient boosting decision tree (XGBoost) method to assess PSS risk. Immune infiltration in PSS samples was analyzed using the ssGSEA method, revealing the immune landscape of PSS patients. Results: The XGBoost model exhibited high accuracy, AUC, sensitivity, and specificity in both training, test sets and extra-test set. The decision curve confirmed its clinical utility. Our findings suggest that m7G methylation might contribute to PSS pathogenesis through immune modulation. Conclusions: m7G regulators play an important role in the development of PSS. Our study of m7G-realted genes may inform future immunotherapy strategies for PSS.

Keywords

• N7-methylguanosine
• Machine learning
• Primary Sjögren's syndrome
• Gene expression omnibus database