Machine learning screening for Parkinson's disease-related cuproptosis-related typing development and validation and exploration of personalized drugs for cuproptosis genes.

Background: Parkinson's disease (PD) is a common, degenerative disease of the nervous system that is characterized by the death of dopaminergic neurons in the substantia nigra densa (SNpc). There is growing evidence that copper (Cu) is involved in myelin formation and is involved in cell death through modulation of synaptic activity as well as neurotrophic factor-induced excitotoxicity. Methods: This study aimed to explore potential cuproptosis-related genes (CRGs) and immune infiltration patterns in PD and the development of Cu chelators relevant for PD treatment. The PD datasets GSE7621, GSE20141, and GSE49036 were downloaded from the Gene Expression Omnibus (GEO) database. The consensus clustering method was used to classify the specimens of PD. Using weighted gene co-expression network analysis (WGCNA) and random forest (RF) tree model, support vector machine (SVM) learning model, extreme gradient boosting (XGBoost) model, and general linear model (GLM) algorithms to screen disease progression-related models, the column charts were created to verify the accuracy of these CRGs in predicting PD progression. Single sample genomic enrichment analysis (ssGSEA) was used to estimate the correlation between genes associated with copper poisoning and genes associated with immune cells and immune function. Molecular docking was used to verify interactions with copper chelating agents associated with cuproptosis for PD treatment. Results: Through ssGSEA, we identified three copper poisoning related genes Conclusions: CRGs such as