A Methylation Diagnostic Model Based on Random Forests and Neural Networks for Asthma Identification

Li, Dong-Dong; Chen, Ting; Ling, You-Liang; Jiang, Yongan; Li, Qiugen

doi:10.1155/2022/2679050

Cited by 2 publications

(1 citation statement)

References 38 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Additionally, learning rates and momentum can be customized. For smaller datasets, the neuralnet package provides fast and efficient performance 24 . The random seed size was set at 12,345,678.…”

Section: Methodsmentioning

confidence: 99%

Development and verification of a combined diagnostic model for primary Sjögren's syndrome by integrated bioinformatics analysis and machine learning

Yang

Wang

et al. 2023

Sci Rep

View full text Add to dashboard Cite

Primary Sjögren’s syndrome (pSS) is a chronic, systemic autoimmune disease mostly affecting the exocrine glands. This debilitating condition is complex and specific treatments remain unavailable. There is a need for the development of novel diagnostic models for early screening. Four gene profiling datasets were downloaded from the Gene Expression Omnibus database. The ‘limma’ software package was used to identify differentially expressed genes (DEGs). A random forest-supervised classification algorithm was used to screen disease-specific genes, and three machine learning algorithms, including artificial neural networks (ANN), random forest (RF), and support vector machines (SVM), were used to build a pSS diagnostic model. The performance of the model was measured using its area under the receiver operating characteristic curve. Immune cell infiltration was investigated using the CIBERSORT algorithm. A total of 96 DEGs were identified. By utilizing a RF classifier, a set of 14 signature genes that are pivotal in transcription regulation and disease progression in pSS were identified. Through the utilization of training and testing datasets, diagnostic models for pSS were successfully designed using ANN, RF, and SVM, resulting in AUCs of 0.972, 1.00, and 0.9742, respectively. The validation set yielded AUCs of 0.766, 0.8321, and 0.8223. It was the RF model that produced the best prediction performance out of the three models tested. As a result, an early predictive model for pSS was successfully developed with high diagnostic performance, providing a valuable resource for the screening and early diagnosis of pSS.

show abstract

Section: Methodsmentioning

confidence: 99%

Development and verification of a combined diagnostic model for primary Sjögren's syndrome by integrated bioinformatics analysis and machine learning

Yang

Wang

et al. 2023

Sci Rep

View full text Add to dashboard Cite

show abstract

Bioinformatics analyses of NET-related hub genes in chronic obstructive pulmonary disease and their association with immune infiltration

Xu,

Qiang,

et al. 2023

Preprint

View full text Add to dashboard Cite

The early diagnosis of chronic obstructive pulmonary disease (COPD), a chronic inflammatory disease, remains challenging. Immune metabolism plays a crucial role in COPD pathogenesis, with neutrophils playing a key role. Although neutrophil extracellular traps (NETs) play a crucial function in preventing infection, irregular and excessive NETs creation can cause COPD to appear and progress. There is still confusion over the precise mechanism, thus more research is required. Herein, we aimed to determine the correlation and diagnostic markers of neutrophil extracellular trap (NET) genes that contribute to immunoinfiltration in COPD. The comprehensive gene expression dataset GSE76925 in the Gene Expression Omnibus database was subjected to differential gene expression analysis. In total, 558 differentially expressed genes were identified, which were then subjected to gene set enrichment analysis. Additionally, the correlation between their expression and immune infiltration was analyzed, and then validated by cluster analysis. Furthermore, 30 differentially expressed NET-related genes were identified and used to construct diagnostic and risk prediction models by random forest and Least absolute shrinkage and selection operator regression analysis. Seven key genes, namely CLEC6A, CTSG, ENTPD4, IRAK4, MAPK1, PIK3CA, and SELPLG, were identified The diagnostic model was validated by generating a receiver operating characteristic curve (ROC) using the GSE38974 dataset. The results revealed that the model exhibited high discrimination ability. Additionally, the models exhibited high diagnostic and risk prediction abilities for COPD. Analysis of single-cell sequencing data from the GSE128033 and GSE163295 datasets revealed that the seven key genes are highly expressed in COPD. Notably, SELPLG and MAPK1 are primarily expressed in monocytes and T cells. Additionally, the genes TLR4, CTSG, IRAK4, SELP, ELPLG, and MAPK1 were revealed to be involved in the pathogenesis of COPD through immune infiltration that leads to NETs. The purpose of this study is to determine the hub genes related to NETs and their association with immune cell infiltration in COPD lung tissue, and provides potential targets for the treatment of COPD.

show abstract

A Methylation Diagnostic Model Based on Random Forests and Neural Networks for Asthma Identification

Cited by 2 publications

References 38 publications

Development and verification of a combined diagnostic model for primary Sjögren's syndrome by integrated bioinformatics analysis and machine learning

Development and verification of a combined diagnostic model for primary Sjögren's syndrome by integrated bioinformatics analysis and machine learning

Bioinformatics analyses of NET-related hub genes in chronic obstructive pulmonary disease and their association with immune infiltration

Contact Info

Product

Resources

About