Non-invasive diagnostic tool for Parkinson\u2019s disease by sebum RNA profile with machine learning

Yuya Uehara,Takayoshi Inoue,Takatoshi Murase,Motoki Fujimaki,Shinji Saiki,Nobutaka Hattori,Haruka Amano-Takeshige,Yoko Imamichi,Shin-Ichi Ueno,Noriyasu Ota,Shuji Suzuki

doi:10.1038/s41598-021-98423-9

Yuya Uehara, Takayoshi Inoue + Show 9 more

Open Access

https://doi.org/10.1038/s41598-021-98423-9

Copy DOI

Abstract

Parkinson's disease (PD) is a progressive neurodegenerative disease presenting with motor and non-motor symptoms, including skin disorders (seborrheic dermatitis, bullous pemphigoid, and rosacea), skin pathological changes (decreased nerve endings and alpha-synuclein deposition), and metabolic changes of sebum. Recently, a transcriptome method using RNA in skin surface lipids (SSL-RNAs) which can be obtained non-invasively with an oil-blotting film was reported as a novel analytic method of sebum. Here we report transcriptome analyses using SSL-RNAs and the potential of these expression profiles with machine learning as diagnostic biomarkers for PD in double cohorts (PD [n = 15, 50], controls [n = 15, 50]). Differential expression analysis between the patients with PD and healthy controls identified more than 100 differentially expressed genes in the two cohorts. In each cohort, several genes related to oxidative phosphorylation were upregulated, and gene ontology analysis using differentially expressed genes revealed functional processes associated with PD. Furthermore, machine learning using the expression information obtained from the SSL-RNAs was able to efficiently discriminate patients with PD from healthy controls, with an area under the receiver operating characteristic curve of 0.806. This non-invasive gene expression profile of SSL-RNAs may contribute to early PD diagnosis based on the neurodegeneration background.

Highlights

Parkinson’s disease (PD) is a progressive neurodegenerative disease that is characterized by both motor symptoms and non-motor symptoms, such as depression, dysosmia, and dysautonomia[1,2]
We were unable to distinguish the patients with PD from the healthy controls using principal component (PC)[1] and PC2; PC3 was able to distinguish between them (Fig. 1)
We examined the potential ability to discriminate between PD and healthy controls using machine learning with skin surface lipids (SSLs)-RNA profiles

Summary

Introduction

Parkinson’s disease (PD) is a progressive neurodegenerative disease that is characterized by both motor symptoms and non-motor symptoms, such as depression, dysosmia, and dysautonomia (e.g., constipation and orthostatic hypotension)[1,2]. Facial seborrhea dermatitis, caused by excessive sebum secretion, is highly prevalent in PD and occasionally responds to levodopa therapy[8,9]. Plasma/serum metabolic changes[12,13,14] lipid composition, and fatty acid β-oxidation in sebum as well as volatile components of the skin are all PD-specific changes[15,16]. A major component of skin surface lipids (SSLs), is released by a holocrine mode of secretion from sebaceous gland cells releasing their cellular c omponents[17]. SSL-RNA analysis of atopic dermatitis identified genes consistent with known pathophysiology and indicated mechanisms related to altered lipid metabolism[18]. We investigated whether the SSL-RNA transcriptome can non-invasively differentiate patients with PD from healthy controls using machine learning

Objectives

Results

Conclusion