Journal of inflammation research · 2025
Identification of Key Biomarkers and Immune Microenvironment Features in Ulcerative Colitis: An Integrated Analysis Using WGCNA and Multiple Machine Learning Algorithms.
СтатьяНазвание и аннотация: Перевод пока не подготовлен
Обработка статьи · этапы, ошибки и управление
Загрузка состояния…
Ошибки и ограничения
История · было → стало
Состояние обновляется каждые 5 секунд, пока блок открыт. Процент показывается только там, где известен объём работы. Пауза останавливает продолжение этапа; текущий запрос к источнику может завершиться.
Qi Yingchao, Wang Yichen, Zhang Siyao, Pan Xinxin, Li Wenkai, Cheng Meijia, Ma Wenjing, Li Jiajia, Pei Yue, Liu Yunen, Yu Yongduo
Аннотация
BACKGROUND: Ulcerative colitis (UC) is an inflammatory bowel disease (IBD) characterized by a dysregulated mucosal immune response in the intestine. The disease poses significant challenges for both diagnosis and treatment. This study aims to identify reliable biomarkers for UC and investigate its immunological characteristics, with the goal of improving diagnostic accuracy and informing treatment strategies.
METHODS: This study integrated multiple GEO datasets and identified UC-associated hub genes through differential expression and Weighted Gene Co-expression Network Analysis (WGCNA), with subsequent refinement using least absolute shrinkage and selection operator (LASSO), randomForest (RF), and support vector machine-recursive feature elimination (SVM-RFE) algorithms. These genes were used to construct a feedforward neural network (FNN) diagnostic model, whose performance was assessed using receiver operating characteristic (ROC) curve analysis. Immune profiling based on CIBERSORT, ssGSEA, Gene set variation analysis (GSVA), and ESTIMATE revealed associations between hub gene expression, immune cell infiltration, and inflammatory activity. Immunohistochemistry was performed to validate the protein expression of hub genes.
RESULTS: Ten hub genes (ACOX2, MMP3, CPT2, CTSK, CHP2, VCAM1, SLC25A34, BASP1, NCF2, and GLB1L2) were identified, and the FNN model showed strong diagnostic accuracy. Notably, NCF2 expression correlated with immune cell infiltration and immune/inflammation scores, and was confirmed to be elevated in UC tissues, suggesting a key role in disease pathogenesis.
CONCLUSION: This study identified ten hub genes with potential as biomarkers for the diagnosis and treatment of UC. NCF2 may contribute to UC pathogenesis by modulating inflammatory and immune responses, serving as a potential immune-related biomarker for improved UC diagnosis and treatment.
METHODS: This study integrated multiple GEO datasets and identified UC-associated hub genes through differential expression and Weighted Gene Co-expression Network Analysis (WGCNA), with subsequent refinement using least absolute shrinkage and selection operator (LASSO), randomForest (RF), and support vector machine-recursive feature elimination (SVM-RFE) algorithms. These genes were used to construct a feedforward neural network (FNN) diagnostic model, whose performance was assessed using receiver operating characteristic (ROC) curve analysis. Immune profiling based on CIBERSORT, ssGSEA, Gene set variation analysis (GSVA), and ESTIMATE revealed associations between hub gene expression, immune cell infiltration, and inflammatory activity. Immunohistochemistry was performed to validate the protein expression of hub genes.
RESULTS: Ten hub genes (ACOX2, MMP3, CPT2, CTSK, CHP2, VCAM1, SLC25A34, BASP1, NCF2, and GLB1L2) were identified, and the FNN model showed strong diagnostic accuracy. Notably, NCF2 expression correlated with immune cell infiltration and immune/inflammation scores, and was confirmed to be elevated in UC tissues, suggesting a key role in disease pathogenesis.
CONCLUSION: This study identified ten hub genes with potential as biomarkers for the diagnosis and treatment of UC. NCF2 may contribute to UC pathogenesis by modulating inflammatory and immune responses, serving as a potential immune-related biomarker for improved UC diagnosis and treatment.