Screening marker genes of type 2 diabetes mellitus in mouse lacrimal gland by LASSO regression

Abstract

Type 2 diabetes mellitus (T2DM) is characterized by insulin resistance and a relative deficiency of insulin. This study aims to screen T2DM-related maker genes in the mouse extraorbital lacrimal gland (ELG) by LASSO regression.C57BLKS/J strain with leptin db/db homozygous mice (T2DM, n = 20) and wild-type mice (WT, n = 20) were used to collect data. The ELGs were collected for RNA sequencing. LASSO regression was conducted to screen marker genes with the training set. Five genes were selected from 689 differentially expressed genes by LASSO regression, including Synm, Elovl6, Glcci1, Tnks and Ptprt. Expression of Synm was downregulated in ELGs of T2DM mice. Elovl6, Glcci1, Tnks, and Ptprt were upregulated in T2DM mice. Area under receiver operating curve of the LASSO model was 1.000(1.000–1.000) and 0.980(0.929–1.000) in the training set and the test set, respectively. The C-index and the robust C-index of the LASSO model were 1.000 and 0.999, respectively, in the training set, and 1.000 and 0.978, respectively, in the test set. In the lacrimal gland of db/db mice, Synm, Elovl6, Glcci1, Tnks and Ptprt can be used as marker genes of T2DM. Abnormal expression of marker genes is related to lacrimal gland atrophy and dry eye in mice.

Integrated bioinformatics analysis of SEMA3C in tongue squamous cell carcinoma using machine-learning strategies

“…Zhang et al identified key modules and hub genes involved in the pathogenesis of OSCC by applying WGCNA to construct a gene co-expression network for the first time, and their study is of great significance for exploring the mechanism of OSCC tumourigenesis and searching for new prognostic biomarkers and therapeutic targets [ 35 ]. Compared with previous studies, the integrated procedure used in this study has the distinct advantage of selecting common markers shared by the combination of the three algorithms [ 28 , 29 ], thus reducing the number of markers while significantly improving the specificity and sensitivity of the identification indicators. Notably, SEMA3C emerged as the most significant hub gene through this comprehensive approach, and the diagnostic efficacy of elevated SEMA3C in distinguishing individuals with TSCC from those without was evaluated using ROC analysis, which yielded high-accuracy results.…”

“…It can greatly narrow down the range of genes to be screened, thereby increasing the accuracy of pinpointing genes associated with key traits [ 28 ]. LASSO regression is based on the regression method, which reduces the complexity of the model, prevents overfitting, and utilizes a smaller sample size to effectively filter features, resulting in a more accurate prediction algorithm [ 29 ]. RF algorithms are more accurate and well-suited for analyzing complex data, such as omics data, which is often high-dimensional [ 30 ].…”

Screening mitochondria-related biomarkers in skin and plasma of atopic dermatitis patients by bioinformatics analysis and machine learning

“…(2) The merging genes found in the PPI network and these RF-screened significant genes intersected, and the resulting genes were chosen as candidate modeling genes. (3) Using the R “glmnet” packages, the least absolute shrinkage and selection operator (LASSO) logistic regression ( 27 ) was used to further reduce the range of potential modeling genes. Ultimately, the hub MitoDEGs in AD were chosen using ten-fold cross-validation to determine the optimum λ and the risk score for each sample was computed using the method that follows:…”

Improved Detection of Decreased Glucose Handling Capacities via Novel Continuous Glucose Monitoring-Derived Indices: AC_Mean and AC_Var

“…These regression models have been used for studies where the number of input variables are large relative to the sample size. 42,43 PLS regression has been used for datasets with mutually correlated input variables and output variable, and important predictors can be estimated by VIP. 31 Here, high VIP indicates high contribution of the variables in predicting DI.…”