Receive a weekly summary and discussion of the top papers of the week by leading researchers in the field.

In PeerJ

Machine learning and weighted gene co-expression network analysis (WGCNA) have been widely used due to its well-known accuracy in the biological field. However, due to the nature of a gene's multiple functions, it is challenging to locate the exact genes involved in complex diseases such as asthma. In this study, we combined machine learning and WGCNA in order to analyze the gene expression data of asthma for better understanding of associated pathogenesis. Specifically, the role of machine learning is assigned to screen out the key genes in the asthma development, while the role of WGCNA is to set up gene co-expression network. Our results indicated that hormone secretion regulation, airway remodeling, and negative immune regulation, were all regulated by critical gene modules associated with pathogenesis of asthma progression. Overall, the method employed in this study helped identify key genes in asthma and their roles in the asthma pathogenesis.

Huang Yuyi, Liu Hui, Zuo Li, Tao Ailin


Asthma, Endocyte, Machine learning, Pathology, WGCNA