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.

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).…”