Novel genes associated with folic acid-mediated metabolism in mouse: A bioinformatics study

Abstract

Folic acid plays an essential role in the central nervous system and cancer. This study aimed to screen genes related to folic acid metabolism. Datasets (GSE80587, GSE65267 and GSE116299) correlated to folic acid were screened in the Gene Expression Omnibus. Weighed gene co-expression network analysis was performed to identify modules associated with sample traits of folic acid and organs (brain, prostate and kidney). Functional enrichment analysis was performed for the eigengenes in modules that were significantly correlated with sample traits. Accordingly, the hub genes and key nodes in the modules were identified using the protein interaction network. A total of 17,252 genes in three datasets were identified. One module, which included 97 genes that were highly correlated with sample traits (including folic acid treatment [cor = -0.57, P = 3e-04] and kidney [cor = -0.68, p = 4e-06]), was screened out. Hub genes, including tetratricopeptide repeat protein 38 (Ttc38) and miR-185, as well as those (including Sema3A, Insl3, Dll1, Msh4 and Snai1) associated with "neuropilin binding", "regulation of reproductive process" and "vitamin D metabolic process", were identified. Genes, including Ttc38, Sema3A, Insl3, Dll1, Msh4 and Snai1, were the novel factors that may be associated with the development of the kidneys and related to folic acid treatment.

Fig 1. Sample correlation and batch effect correction.

(A) The Pearson’s correlation analysis for the samples included in the GSE80587, GSE65267 and GSE116299 datasets. (B) The batch effect correction of samples in the GSE80587, GSE65267 and GSE116299 datasets.

Fig 2. The network topology analysis for the soft threshold power of the adjacency matrix.

(A) The soft-thresholding power corresponding to the correlation coefficient square value (r², y-axis). The higher the r² value, the closer this was to the scale-free topology. (B) The connectivity corresponding to the different soft-thresholding power. The higher the soft-thresholding power, the lower the mean connectivity. The mean connectivity was equal to 1 when soft-thresholding power = 11. (C) The WGCNA modules tree. (D) The WGCNA modules and number of nodes in the modules.

Fig 3. The correlation of modules with the sample trait.

ME, module of eigengenes. Red and blue colors in the heatmap note the positive and negative correlations with the corresponding traits, respectively. *Indicates the significant correlation (absolute cor > 0.5 and P<0.05).

Fig 4. Functional enrichment analysis and the protein-protein interaction (PPI) network of eigengenes in the brown4 module.

(A) The GO biological processes that involve the eigengenes in the brown4 module. (B) The PPI network of eigengenes in the brown4 module. The node size indicates the interaction degree.