Based on multiple machine learning to identify the ENO2 as diagnosis biomarkers of glaucoma

Abstract

Purpose Glaucoma is a generic term of a highly different disease group of optic neuropathies, which the leading cause of irreversible vision in the world. There are few biomarkers available for clinical prediction and diagnosis, and the diagnosis of patients is mostly delayed. Methods Differential gene expression of transcriptome sequencing data (GSE9944 and GSE2378) for normal samples and glaucoma samples from the GEO database were analyzed. Furthermore, based on different algorithms (Logistic Regression (LR), Random Forest (RF), lasso regression (LASSO)) two diagnostic models are constructed and diagnostic markers are screened. GO and KEGG analyses revealed the possible mechanism of differential genes in the pathogenesis of glaucoma. ROC curve confirmed the effectiveness. Results LR-RF model included 3 key genes (NAMPT, ADH1C, ENO2), and the LASSO model outputted 5 genes (IFI16, RFTN1, NAMPT, ADH1C, and ENO2), both algorithms have excellent diagnostic efficiency. ROC curve confirmed that the three biomarkers ADH1C, ENO2, and NAMPT were effective in the diagnosis of glaucoma. Next, the expression analysis of the three diagnostic biomarkers in glaucoma and control samples confirmed that NAMPT and ADH1C were up-regulated in glaucoma samples, and ENO2 was down-regulated. Correlation analysis showed that ENO2 was significantly negatively correlated with ADH1C (cor = -0.865714202) and NAMPT (cor = -0.730541227). Finally, three compounds for the treatment of glaucoma were obtained in the TCMs database: acetylsalicylic acid, 7-o-methylisomucitol and scutellarin which were applied to molecular docking with the diagnostic biomarker ENO2. Conclusions In conclusion, our research shows that ENO2, NAMPT, and ADH1C can be used as diagnostic markers for glaucoma, and ENO2 can be used as a therapeutic target.

A new gene-scoring method for uncovering novel glaucoma-related genes using non-negative matrix factorization based on RNA-seq data

“…Differential gene expression analysis is a commonly used computational approach for identifying marker genes corresponding to a specified phenotype. A typical differential gene expression analysis often identifies a hundred or more differentially expressed genes (DEGs), where a considerable number of them might be highly correlated with one or more other DEGs ( Dai et al, 2022 ).…”

“…With the advancement of artificial intelligence, machine learning has provided more accurate glaucoma diagnosis based on imaging, visual field testing, clinical and transcriptomic data using supervised learning; results also have provided biological insight by revealing expression patterns from data using unsupervised learning ( Zheng et al, 2019 ; Alipanahi et al, 2021 ). Dai et al (2022) used Logistic Regression (LR), Random Forest (RF), and lasso regression (LASSO) for glaucoma diagnosis based on the DEGs and found diagnosis marker ENO2 by evaluating the efficiency of the classification model and the included features/genes. However, in this study, the classification model was based on a dataset with a very small number of samples (32 samples in total), thus the generalizability of the result is questionable, and needs further validation.…”

Identification of Potential Biomarkers for Group I Pulmonary Hypertension Based on Machine Learning and Bioinformatics Analysis

“…The gene set selected by SVM showed a superior performance in cancer classification compared to that selected by other selection methods. Dai et al found glaucoma diagnostic markers based on a logistic regression-RF (LR-RF) model coupled with experimental validation [13]. However, no study has been carried out using ML for PAH diagnosis and potential biomarker discovery and further validated the results using a pathway analysis and experiments.…”

Expression profile analysis to identify potential gene changes induced by dexamethasone in the trabecular meshwork

“…Therefore, understanding the pathological changes in the TM microstructure induced by DEX treatment is essential for the development of effective therapies [7] . To date, many studies have employed a variety of experimental methods [such as RNA sequencing (RNA-seq)] to select differentially expressed genes (DEG) profiles of TM after exposure to steroid hormones at the whole genome level, resulting in complex and comprehensive datasets [8] . Systematically and comprehensively analysing the relationship between DEGs and differentially activated signalling pathways in DEX-treated and nontreated samples will help us gain new insights into the progression and treatment of SIG.…”