Potential cerebrospinal fluid metabolomic biomarkers and early prediction model for Parkinson's disease

Abstract

Objective: To identify key cerebrospinal fluid (CSF) metabolomic biomarkers associated with Parkinson's disease (PD) and prodromal PD, providing insights for intervention strategy development.

Methods: Six hundred and thirty-nine participants from the Parkinson's Progression Markers Initiative (PPMI) cohort were included: 300 PD patients, 112 healthy controls (HC), and 227 prodromal PD patients. Regression analysis and OPLS-DA identified metabolic biomarkers, while pathway analysis examined their relationship to clinical features. An XGBoost-based early prediction model was developed to assess the distinction between PD, prodromal PD, and HC. A two-sample bidirectional Mendelian randomization analysis was performed to examine the association between differential metabolites and Parkinson's disease.

Results: Sixty-four metabolites were significantly altered in PD patients compared to HC, with 58 elevated and 6 reduced. In prodromal PD, 19 metabolites were increased, and 34 were decreased. Key metabolic pathways involved glutathione and amino acid metabolism. Dopamine 3-O-sulfate correlated with PD progression, levodopa-equivalent dose, and non-motor symptoms. The XGBoost model demonstrated high specificity in predicting the onset of PD. The MR analysis results showed a positive correlation between higher genetic predictions of dopamine 3-O-sulfate levels and the risk of Parkinson's disease. In contrast, the reverse MR analysis found that Parkinson's disease susceptibility significantly increased dopamine 3-O-sulfate levels.

Conclusion: The differential expression of CSF metabolites reveals early cellular metabolic changes, providing insights for early diagnosis and monitoring PD progression. A bidirectional causal relationship exists between genetically determined PD susceptibility and metabolites.

Keywords: PD susceptibility; Parkinson diseases; bidirectional Mendelian randomization; early prediction model; metabolomic biomarkers.

Figure 1

Univariate and multivariate metabolomic analysis. Metabolomic profiling. (A) Volcano plots showing differential metabolites between PD and HC, highlighting dopamine 3-O-sulfate and timethylamine. (B) Violin plots depicting key metabolites [dopamine 3-O-sulfate, caffeine, CE (20:5)] in HC, PD, and prodromal groups. (C) OPLS-DA score plots illustrating group separation based on metabolic profiles. (D) VIP score plots for top differential metabolites between groups.

Figure 2

Metabolic pathway enrichment analysis. (A) KEGG pathway enrichment showing key pathways, such as glutathione and amino acid metabolism, across PD, prodromal PD, and HC groups. (B) SMDB pathway analysis highlighting metabolic disruptions in amino acid and steroid metabolism. (C) RaMP-DB network illustrating the connection between altered pathways and neurodegenerative diseases.

Figure 3

Metabolite-clinical correlation analysis. (A) Spearman’s correlation analysis of dopamine 3-O-sulfate with clinical measures, showing significant positive correlations with various PD progression indicators. (B) Scatter plots illustrating the correlation between dopamine 3-O-sulfate levels and clinical scores, including disease duration, SCOPA, LEED, and MDS-UPDRS.

Figure 4

Clinical prediction model analysis. (A) Beeswarm plot of SHAP values showing the contribution of key metabolites in distinguishing between PD, prodromal PD, and HC groups. (B,C) Feature importance plots for prediction accuracy in PD, prodromal, and HC groups, highlighting the significant metabolites influencing model predictions. (D) Receiver operating characteristic (ROC) curves and AUC values assessing the predictive performance of the model in the training and test datasets.