SCIENTIFIC HUB

Follow the evidence.

SCIENTIFIC LITERATURE · MED

Machine learning-based characterization of cuprotosis-related biomarkers and immune infiltration in Parkinson's disease.

Front Genet · 2022-10-17

DOI: 10.3389/fgene.2022.1010361PMID: 36338988

Open accessresearch-article; Journal ArticleOriginal source ↗

Research overview

The text below is the source article’s original abstract under a verified reuse license. cc by

Background: Parkinson's disease (PD) is a neurodegenerative disease commonly seen in the elderly. On the other hand, cuprotosis is a new copper-dependent type of cell death that can be observed in various diseases. Methods: This study aimed to identify potential novel biomarkers of Parkinson's disease by biomarker analysis and to explore immune cell infiltration during the onset of cuprotosis. Gene expression profiles were retrieved from the GEO database for the GSE8397, GSE7621, GSE20163, and GSE20186 datasets. Three machine learning algorithms: the least absolute shrinkage and selection operator (LASSO), random forest, and support vector machine-recursive feature elimination (SVM-RFE) were used to screen for signature genes for Parkinson's disease onset and cuprotosis-related genes (CRG). Immune cell infiltration was estimated by ssGSEA, and cuprotosis-related genes associated with immune cells and immune function were examined using spearman correlation analysis. Nomogram was created to validate the accuracy of these cuprotosis-related genes in predicting PD disease progression. Classification of Parkinson's specimens using consensus clustering methods. Result: Three PD datasets from the Gene Expression Omnibus (GEO) database were combined after eliminating batch effects. By ssGSEA, we identified three cuprotosis-related genes ATP7A, SLC31A1, and DBT associated with immune cells or immune function in PD and more accurate for the diagnosis of Parkinson's disease course. Patients could benefit clinically from a characteristic line graph based on these genes. Consistent clustering analysis identified two subtypes, with the C2 subtype exhibiting higher immune cell infiltration and immune function. Conclusion: In conclusion, our study reveals that several newly identified cuprotosis-related genes intervene in the progression of Parkinson's disease through immune cell infiltration.

Scientific assessment

01

Research question

Assess the question within the original study’s scope.

02

Methods & sample

Check the source article for study design and sample details.

03

Key findings

An editorially approved findings summary is not yet published for this record.

04

Limitations

Generalizability, bias and clinical meaning require separate assessment.

Methods, samples and clinical conclusions are not inferred from bibliographic metadata.