High-Throughput CSF Proteomics and Machine Learning to Identify Proteomic Signatures for Parkinson Disease Development and Progression

Abstract

Background and Objectives:This study aimed to identify CSF proteomic signatures characteristic of Parkinson disease (PD) and evaluate their clinical utility.Methods:This observational study utilized data from the Parkinson’s Progression Markers Initiative (PPMI), which enrolled PD patients, healthy controls (HCs), and non-PD participants carryingGBA1,LRRK2, and/orSNCAmutations (genetic-prodromals) at international sites. Study participants were chosen from PPMI enrollees based on the availability of aptamer-based CSF proteomic data, quantifying 4,071 proteins, and classified as patients with PD withoutGBA1,LRRK2, and/orSNCAmutations (non-genetic-PD), HCs, patients with PD carrying the aforementioned mutations (genetic-PD), or genetic-prodromals. Differentially expressed protein (DEP) analysis and the least absolute shrinkage and selection operator (LASSO) was applied to the data form non-genetic-PD and HCs. Signatures characteristics of non-genetic-PD were quantified as a PD proteomic score (PD-ProS), validated internally and then externally using data of 1,556 CSF proteins from theLRRK2Cohort Consortium (LCC). We further tested the PD-ProS in genetic-PD and genetic-prodromals, and examined associations with clinical progression.Results:Data from 279 non-genetic-PD patients (mean ± standard deviation, age, 62.0 ± 9.6 years; male, 67.7%) and 141 HCs (age, 60.5 ± 11.9 years; male, 64.5%) were used for PD-ProS derivation. From 23 DEPs, LASSO determined weights of 14 DEPs for the PD-ProS (area under the curve [AUC] = 0.83 [95% confidence interval (CI), 0.78–0.87]), validated in an independent internal validation cohort of 71 non-genetic-PD patients and 35 HCs (AUC=0.81 [95% CI, 0.73–0.90]). In the LCC, only 5 of the 14 DEPs were also measured. Importantly, these 5 DEPs still distinguished 31 non-genetic-PD patients from 34 HCs with the same weights (AUC = 0.75 [95% CI, 0.63–0.87]). Furthermore, the PD-ProS distinguished 258 genetic-PD patients from 365 genetic-prodromals. Finally, regardless of genetic status, the PD-ProS independently predicted both cognitive and motor decline in PD (dementia, adjusted hazard ratio in the highest quintile (aHR-Q5) = 2.8 [95% CI, 1.6–5.0]; Hoehn and Yahr stage IV, aHR-Q5 = 2.1 [95% CI, 1.1–4.0]).Discussion:By integrating high-throughput proteomics with machine learning, we identified PD-associated CSF proteomic signatures crucial for PD development and progression.Trial Registration Information:Clinicaltrials.gov (NCT01176565). A link to the trial registry page ishttps://clinicaltrials.gov/ct2/show/NCT01141023.Classification of Evidence:This study provides Class II evidence that the CSF proteome contains clinically important information regarding the development and progression of Parkinson disease that can be deciphered by a combination of high-throughput proteomics and machine learning.

Exosomal Proteomics: Unveiling Novel Insights into Lung Cancer

“…Furthermore, the application of machine learning algorithms has significantly improved the handling of large proteomics datasets [99]. By employing both supervised and unsupervised learning techniques, researchers can predict qualitative and quantitative outcomes, such as disease states or therapeutic responses, and uncover natural patterns within unlabeled datasets, facilitating novel discoveries in protein function and interaction [100,101]. Enrichment analysis further refines the biological significance of the data by mapping identified proteins to known biological pathways, functions, or disease states, using public databases such as DAVID and STRING [102,103].…”

Advances in Diagnosis and Prognosis of Parkinson Disease

“…The work by Tsukita et al 5 published in this issue of Neurology ® represents a good example of this type of approach. The authors applied SOMAscan to measure 4,071 different proteins in the CSF of 279 drug-naïve patients with PD without pathologic variants on LRRK2 , GBA1 , and SNCA genes (non-genetic PD) and 141 healthy controls (HCs) enrolled in the Parkinson's Progression Markers Initiative (PPMI).…”