The abdominal aortic aneurysm-related disease model based on machine learning predicts immunity and m1A/m5C/m6A/m7G epigenetic regulation

Introduction: Abdominal aortic aneurysms (AAA) are among the most lethal non-cancerous diseases. A comprehensive analysis of the AAA-related disease model has yet to be conducted. Methods: Weighted correlation network analysis (WGCNA) was performed for the AAA-related genes. Machine learning random...

Descripción completa

Detalles Bibliográficos
Autores principales: Tian, Yu, Fu, Shengjie, Zhang, Nan, Zhang, Hao, Li, Lei
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Frontiers Media S.A. 2023
Materias:
Genetics
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9995589/
https://www.ncbi.nlm.nih.gov/pubmed/36911406
http://dx.doi.org/10.3389/fgene.2023.1131957
Descripción
Sumario:Introduction: Abdominal aortic aneurysms (AAA) are among the most lethal non-cancerous diseases. A comprehensive analysis of the AAA-related disease model has yet to be conducted. Methods: Weighted correlation network analysis (WGCNA) was performed for the AAA-related genes. Machine learning random forest and LASSO regression analysis were performed to develop the AAA-related score. Immune characteristics and epigenetic characteristics of the AAA-related score were explored. Results: Our study developed a reliable AAA-related disease model for predicting immunity and m1A/m5C/m6A/m7G epigenetic regulation. Discussion: The pathogenic roles of four model genes, UBE2K, TMEM230, VAMP7, and PUM2, in AAA, need further validation by in vitro and in vivo experiments.

Ejemplares similares