Identification of platelet-related subtypes and diagnostic markers in pediatric Crohn's disease based on WGCNA and machine learning.

Background: The incidence of pediatric Crohn's disease (PCD) is increasing worldwide every year. The challenges in early diagnosis and treatment of PCD persist due to its inherent heterogeneity. This study's objective was to discover novel diagnostic markers and molecular subtypes aimed at enhancing the prognosis for patients suffering from PCD. Methods: Candidate genes were obtained from the GSE117993 dataset and the GSE93624 dataset by weighted gene co-expression network analysis (WGCNA) and differential analysis, followed by intersection with platelet-related genes. Based on this, diagnostic markers were screened by five machine learning algorithms. We constructed predictive models and molecular subtypes based on key markers. The models were evaluated using the GSE101794 dataset as the validation set, combined with receiver operating characteristic curves, decision curve analysis, clinical impact curves, and calibration curves. In addition, we performed pathway enrichment analysis and immune infiltration analysis for different molecular subtypes to assess their differences. Results: Through WGCNA and differential analysis, we successfully identified 44 candidate genes. Following this, employing five machine learning algorithms, we ultimately narrowed it down to five pivotal markers: GNA15, PIK3R3, PLEK, SERPINE1, and STAT1. Using these five key markers as a foundation, we developed a nomogram exhibiting exceptional performance. Furthermore, we distinguished two platelet-related subtypes of PCD through consensus clustering analysis. Subsequent analyses involving pathway enrichment and immune infiltration unveiled notable disparities in gene expression patterns, enrichment pathways, and immune infiltration landscapes between these subtypes. Conclusion: In this study, we have successfully identified five promising diagnostic markers and developed a robust nomogram with high predictive efficacy. Furthermore, the recognition of distinct PCD subtypes enhances our comprehension of potential pathogenic mechanisms and paves the way for future prospects in early diagnosis and personalized treatment.

Identification of cuproptosis-associated subtypes and signature genes for diagnosis and risk prediction of Ulcerative colitis based on machine learning.

Background: Ulcerative colitis (UC) is a chronic and debilitating inflammatory bowel disease that impairs quality of life. Cuproptosis, a recently discovered form of cell death, has been linked to many inflammatory diseases, including UC. This study aimed to examine the biological and clinical significance of cuproptosis-related genes in UC. Methods: Three gene expression profiles of UC were obtained from the Gene Expression Omnibus (GEO) database to form the combined dataset. Differential analysis was performed based on the combined dataset to identify differentially expressed genes, which were intersected with cuproptosis-related genes to obtain differentially expressed cuproptosis-related genes (DECRGs). Machine learning was conducted based on DECRGs to identify signature genes. The prediction model of UC was established using signature genes, and the molecular subtypes related to cuproptosis of UC were identified. Functional enrichment analysis and immune infiltration analysis were used to evaluate the biological characteristics and immune infiltration landscape of signature genes and molecular subtypes. Results: Seven signature genes (ABCB1, AQP1, BACE1, CA3, COX5A, DAPK2, and LDHD) were identified through the machine learning algorithms, and the nomogram built from these genes had excellent predictive performance. The 298 UC samples were divided into two subtypes through consensus cluster analysis. The results of the functional enrichment analysis and immune infiltration analysis revealed significant differences in gene expression patterns, biological functions, and enrichment pathways between the cuproptosis-related molecular subtypes of UC. The immune infiltration analysis also showed that the immune cell infiltration in cluster A was significantly higher than that of cluster B, and six of the characteristic genes (excluding BACE1) had higher expression levels in subtype B than in subtype A. Conclusions: This study identified several promising signature genes and developed a nomogram with strong predictive capabilities. The identification of distinct subtypes of UC enhances our current understanding of UC's underlying pathogenesis and provides a foundation for personalized diagnosis and treatment in the future.