Identification of core genes in systemic juvenile idiopathic arthritis based on 113 machine learning algorithms

基于113种机器学习算法识别系统性幼年特发性关节炎的核心基因

阅读:3

Abstract

BACKGROUND: Systemic juvenile idiopathic arthritis (sJIA) represents the most severe subtype of juvenile idiopathic arthritis and is classified as a rare autoinflammatory disease. It significantly impacts patients' quality of life. Its pathogenesis involves complex immune dysregulation and inflammatory responses, which remain incompletely understood. This study aims to identify key core genes associated with sJIA using advanced machine learning algorithms and construct an efficient diagnostic model. METHODS: We integrated chip and high-throughput datasets related to sJIA from the Gene Expression Omnibus database. Through differential expressed gene analysis and weighted gene co-expression network analysis, we selected 52 candidate genes. Gene Ontology, Kyoto Encyclopedia of Genes and Genomes, and Gene Set Enrichment Analysis were utilized to identify differentially expressed pathways. We employed 113 machine learning algorithms to screen candidate genes and identify the most critical core genes, validated with external datasets to construct a robust diagnostic model. RESULTS: Gene Set Enrichment Analysis revealed significant activation of the complement and coagulation cascade pathway alongside notable suppression of antigen processing and presentation pathway. We identified 8 core genes: ADIPOR1, GLRX5, MXI1, SIAH2, SLC22A4, SLC25A37, SLC6A8, and YBX3. The diagnostic model constructed from these genes achieved impressive performance, with an area under the receiver operating characteristic curve exceeding 0.70 across training and validation sets. CONCLUSION: This study elucidated biomarkers associated with sJIA, highlighting the crucial influence of 8 core genes on disease progression. It also successfully developed an effective diagnostic model, potentially guiding future clinical practice in managing sJIA.

特别声明

1、本页面内容包含部分的内容是基于公开信息的合理引用;引用内容仅为补充信息,不代表本站立场。

2、若认为本页面引用内容涉及侵权,请及时与本站联系,我们将第一时间处理。

3、其他媒体/个人如需使用本页面原创内容,需注明“来源:[生知库]”并获得授权;使用引用内容的,需自行联系原作者获得许可。

4、投稿及合作请联系:info@biocloudy.com。