Dataset Information

Classification of Parkinson's Disease Genotypes in Drosophila Using Spatiotemporal Profiling of Vision.

ABSTRACT: Electrophysiological studies indicate altered contrast processing in some Parkinson's Disease (PD) patients. We recently demonstrated that vision is altered in Drosophila PD models and hypothesised that different types of genetic and idiopathic PD may affect dopaminergic visual signalling pathways differently. Here we asked whether visual responses in Drosophila could be used to identify PD mutations. To mimic a clinical setting a range of flies was used. Young flies from four control lines were compared to three early-onset PD mutations (PINK1, DJ-1α and DJ-1β), and to two other neurodegenerative mutations, one in the fly LRRK2 orthologue (dLRRK) the other in eggroll, a model of general neurodegeneration in Drosophila. Stimuli were contrast reversing gratings spanning 64 spatiotemporal frequency combinations. We recorded the steady-state visually-evoked response amplitude across all combinations. We found that the pattern of neuronal responses differed between genotypes. Wild-type and early-onset PD flies formed separate clusters; the late-onset mutation is an outlier. Neuronal responses in early-onset PD flies were stronger than in wild-types. Multivariate pattern analysis grouped flies by PD/non-PD genotype with an accuracy >85%. We propose that machine learning algorithms may be useful in increasing the diagnostic specificity of human electrophysiological measurements in both animal models and PD patients.

SUBMITTER: West RJ

PROVIDER: S-EPMC4657034 | biostudies-other | 2015 Nov

REPOSITORIES: biostudies-other

ACCESS DATA

Similar Datasets

Project description:As digital health technology becomes more pervasive, machine learning (ML) provides a robust way to analyze and interpret the myriad of collected features. The purpose of this preliminary work was to use ML classification to assess the benefits and relevance of neurocognitive features both tablet-based assessments and self-reported metrics, as they relate to Parkinson's Disease (PD) and its stages [Hoehn and Yahr (H&Y) Stages 1-5]. Further, this work aims to compare perceived versus sensor-based neurocognitive abilities. In this study, 75 participants ([Formula: see text] PD; [Formula: see text] control) completed 14 tablet-based neurocognitive functional tests (e.g., motor, memory, speech, executive, and multifunction), functional movement assessments (e.g., Berg Balance Scale), and standardized health questionnaires (e.g., PDQ-39). Decision tree classification of sensor-based features allowed for the discrimination of PD from healthy controls with an accuracy of [Formula: see text], and early and advanced stages of PD with an accuracy of [Formula: see text]; compared to the current gold standard tools [e.g., standardized health questionnaires ([Formula: see text] accuracy) and functional movement assessments ([Formula: see text] accuracy)]. Significant features were also identified using decision tree classification. Device magnitude of acceleration was significant in 12 of 14 tests ([Formula: see text]), regardless of test type. For classification between diagnosed and control populations, 17 motor (e.g., device magnitude of acceleration), 9 accuracy (e.g., number of correct/incorrect interactions), and 8 timing features (e.g., time to between interactions) were significant. For classification between early (H&Y Stages 1 and 2) and advanced (H&Y Stages 3, 4, and 5) stages of PD, 7 motor, 12 accuracy, and 14 timing features were significant. Finally, this work depicts that perceived functionality of individuals with PD differed from sensor-based functionalities. In early-stage PD was shown to be [Formula: see text] lower than sensor-based scores with notable perceived deficits in memory and executive function. However, individuals in advanced stages had elevated perceptions (1.57x) for executive and behavioral functions compared to early-stage populations. Machine learning in digital health systems allows for a more comprehensive understanding of neurodegenerative diseases and their stages and may also depict new features that influence the ways digital health technology should be configured.

Project description:Parkinson’s disease is second most prevalent neurodegenerative disorder. Parkinson’s disease is hypothesized to be caused by a multifaceted interplay between genetic and environmental factors. We profiled the DNA methylation using the frontal lobe from people who died from Parkinson’s disease and compared them with age-, and sex-matched controls. We hypothesized that the complex regulation of DNA methylation and metabolome leads to deficits that cause irregular motor function among Parkinson’s disease subjects and the metabolomic disparities may reflect the effect of these complex interactions. Herein, we aim to integrate quantitative metabolomics and DNA methylation of brain tissue from primary motor cortex (Brodmann area 4) from Parkinson’s disease sufferers to better understand the biochemistry associated with the onset of the disease. Parkinson’s disease (PD) is second most prevalent neurodegenerative disorder following Alzheimer’s disease. Parkinson’s disease is hypothesized to be caused by a multifaceted interplay between genetic and environmental factors. Herein, and for the first time, we describe the integration of metabolomics and epigenetics (genome-wide DNA methylation; epimetabolomics) to profile the frontal lobe from people who died from PD and compared them with age-, and sex-matched controls. We identified 48 metabolites to be at significantly different concentrations (FDR q<0.05), 4,313 differentially methylated sites [5'-C-phosphate-G-3' (CpGs)] (FDR q<0.05) and increased DNA methylation age in the primary motor cortex of people who died from PD. We identified Primary bile acid biosynthesis as the major biochemical pathway to be perturbed in the frontal lobe of PD sufferers, and the metabolite taurine (p-value = 5.91E-06) as being positively correlated with CpG cg14286187 (SLC25A27; CYP39A1) (FDR q = 0.002), highlighting previously unreported biochemical changes associated with PD pathogenesis. In this novel multi-omics study, we identify regulatory mechanisms which we believe warrant future translational investigation and central biomarkers of PD which require further validation in more accessible biomatrices.

Dataset Information

Classification of Parkinson's Disease Genotypes in Drosophila Using Spatiotemporal Profiling of Vision.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets