scholarly journals Excess of singleton loss-of-function variants in Parkinson’s disease contributes to genetic risk

2020 ◽  
Vol 57 (9) ◽  
pp. 617-623 ◽  
Author(s):  
Dheeraj Reddy Bobbili ◽  
Peter Banda ◽  
Rejko Krüger ◽  
Patrick May
Keyword(s):  
Parkinson’S Disease ◽  
Parkinson's Disease ◽  
Rare Variant ◽  
Prediction Models ◽  
Area Under The Curve ◽  
Classification Model ◽  
Polygenic Risk Score ◽  
Disease Prediction ◽  
Common Variants ◽  
Loss Of Function

BackgroundParkinson’s disease (PD) is a neurodegenerative disorder with complex genetic architecture. Besides rare mutations in high-risk genes related to monogenic familial forms of PD, multiple variants associated with sporadic PD were discovered via association studies.MethodsWe studied the whole-exome sequencing data of 340 PD cases and 146 ethnically matched controls from the Parkinson’s Progression Markers Initiative (PPMI) and performed burden analysis for different rare variant classes. Disease prediction models were built based on clinical, non-clinical and genetic features, including both common and rare variants, and two machine learning methods.ResultsWe observed a significant exome-wide burden of singleton loss-of-function variants (corrected p=0.037). Overall, no exome-wide burden of rare amino acid changing variants was detected. Finally, we built a disease prediction model combining singleton loss-of-function variants, a polygenic risk score based on common variants, and family history of PD as features and reached an area under the curve of 0.703 (95% CI 0.698 to 0.708). By incorporating a rare variant feature, our model increased the performance of the state-of-the-art classification model for the PPMI dataset, which reached an area under the curve of 0.639 based on common variants alone.ConclusionThe main finding of this study is to highlight the contribution of singleton loss-of-function variants to the complex genetics of PD and that disease risk prediction models combining singleton and common variants can improve models built solely on common variants.

Comparative analysis of four disease prediction models of Parkinson’s disease

2015 ◽  
Vol 411 (1-2) ◽  
pp. 127-134
Author(s):  
Nadella Kumudini ◽  
Shaik Mohammad Naushad ◽  
Balraj Alex Stanley ◽  
Manoharan Niveditha ◽  
Gunasekaran Sharmila ◽  
...  
Keyword(s):  
Parkinson’S Disease ◽  
Parkinson's Disease ◽  
Comparative Analysis ◽  
Prediction Models ◽  
Disease Prediction

scholarly journals Combined accelerometer and genetic analysis to differentiate essential tremor from Parkinson’s disease

PeerJ ◽  
2018 ◽  
Vol 6 ◽  
pp. e5308 ◽  
Author(s):  
Bhuvan Molparia ◽  
Brian N. Schrader ◽  
Eli Cohen ◽  
Jennifer L. Wagner ◽  
Sandeep R. Gupta ◽  
...  
Keyword(s):  
Parkinson’S Disease ◽  
Parkinson's Disease ◽  
Essential Tremor ◽  
Simple Procedure ◽  
Home Monitoring ◽  
Area Under The Curve ◽  
Community Setting ◽  
Diagnostic Procedures ◽  
Polygenic Risk Score ◽  
At Home

Essential tremor (ET) and Parkinson’s disease (PD) are among the most common adult-onset tremor disorders. Clinical and pathological studies suggest that misdiagnosis of PD for ET, and vice versa, occur in anywhere from 15% to 35% of cases. Complex diagnostic procedures, such as dopamine transporter imaging, can be powerful diagnostic aids but are lengthy and expensive procedures that are not widely available. Preliminary studies suggest that monitoring of tremor characteristics with consumer grade accelerometer devices could be a more accessible approach to the discrimination of PD from ET, but these studies have been performed in well-controlled clinical settings requiring multiple maneuvers and oversight from clinical or research staff, and thus may not be representative of at-home monitoring in the community setting. Therefore, we set out to determine whether discrimination of PD vs. ET diagnosis could be achieved by monitoring research subject movements at home using consumer grade devices, and whether discrimination could be improved with the addition of genetic profiling of the type that is readily available through direct-to-consumer genetic testing services. Forty subjects with PD and 27 patients with ET were genetically profiled and had their movements characterized three-times a day for two weeks through a simple procedure meant to induce rest tremors. We found that tremor characteristics could be used to predict diagnosis status (sensitivity = 76%, specificity = 65%, area under the curve (AUC) = 0.75), but that the addition of genetic risk information, via a PD polygenic risk score, did not improve discriminatory power (sensitivity = 80%, specificity = 65%, AUC = 0.73).

scholarly journals Real-Time Detection of Freezing Motions in Parkinson's Patients for Adaptive Gait Phase Synchronous Cueing

2021 ◽  
Vol 12 ◽  
Author(s):  
Ardit Dvorani ◽  
Vivian Waldheim ◽  
Magdalena C. E. Jochner ◽  
Christina Salchow-Hömmen ◽  
Jonas Meyer-Ohle ◽  
...  
Keyword(s):  
Parkinson’S Disease ◽  
Parkinson's Disease ◽  
Prediction Models ◽  
Inertial Sensor ◽  
Freezing Of Gait ◽  
Area Under The Curve ◽  
Support Vector ◽  
Average Performance ◽  
Gait Phase ◽  
Fog Detection

Parkinson's disease is the second most common neurodegenerative disease worldwide reducing cognitive and motoric abilities of affected persons. Freezing of Gait (FoG) is one of the severe symptoms that is observed in the late stages of the disease and considerably impairs the mobility of the person and raises the risk of falls. Due to the pathology and heterogeneity of the Parkinsonian gait cycle, especially in the case of freezing episodes, the detection of the gait phases with wearables is challenging in Parkinson's disease. This is addressed by introducing a state-automaton-based algorithm for the detection of the foot's motion phases using a shoe-placed inertial sensor. Machine-learning-based methods are investigated to classify the actual motion phase as normal or FoG-affected and to predict the outcome for the next motion phase. For this purpose, spatio-temporal gait and signal parameters are determined from the segmented movement phases. In this context, inertial sensor fusion is applied to the foot's 3D acceleration and rate of turn. Support Vector Machine (SVM) and AdaBoost classifiers have been trained on the data of 16 Parkinson's patients who had shown FoG episodes during a clinical freezing-provoking assessment course. Two clinical experts rated the video-recorded trials and marked episodes with festination, shank trembling, shuffling, or akinesia. Motion phases inside such episodes were labeled as FoG-affected. The classifiers were evaluated using leave-one-patient-out cross-validation. No statistically significant differences could be observed between the different classifiers for FoG detection (p>0.05). An SVM model with 10 features of the actual and two preceding motion phases achieved the highest average performance with 88.5 ± 5.8% sensitivity, 83.3 ± 17.1% specificity, and 92.8 ± 5.9% Area Under the Curve (AUC). The performance of predicting the behavior of the next motion phase was significantly lower compared to the detection classifiers. No statistically significant differences were found between all prediction models. An SVM-predictor with features from the two preceding motion phases had with 81.6 ± 7.7% sensitivity, 70.3 ± 18.4% specificity, and 82.8 ± 7.1% AUC the best average performance. The developed methods enable motion-phase-based FoG detection and prediction and can be utilized for closed-loop systems that provide on-demand gait-phase-synchronous cueing to mitigate FoG symptoms and to prevent complete motoric blockades.

A Multi-agent Feature Selection and Hybrid Classification Model for Parkinson's Disease Diagnosis

2021 ◽  
Vol 17 (2s) ◽  
pp. 1-22
Author(s):  
Mazin Abed Mohammed ◽  
Mohamed Elhoseny ◽  
Karrar Hameed Abdulkareem ◽  
Salama A. Mostafa ◽  
Mashael S. Maashi
Keyword(s):  
Machine Learning ◽  
Parkinson’S Disease ◽  
Parkinson's Disease ◽  
Feature Selection ◽  
Prediction Models ◽  
Disease Diagnosis ◽  
Classification Model ◽  
Test Results ◽  
Multi Agent ◽  
The Voice

Parkinson's disease (PD) diagnostics includes numerous analyses related to the neurological, physical, and psychical status of the patient. Medical teams analyze multiple symptoms and patient history considering verified genetic influences. The proposed method investigates the voice symptoms of this disease. The voice files are processed, and the feature extraction is conducted. Several machine learning techniques are used to recognize Parkinson's and healthy patients. This study focuses on examining PD diagnosis through voice data features. A new multi-agent feature filter (MAFT) algorithm is proposed to select the best features from the voice dataset. The MAFT algorithm is designed to select a set of features to improve the overall performance of prediction models and prevent over-fitting possibly due to extreme reduction to the features. Moreover, this algorithm aims to reduce the complexity of the prediction, accelerate the training phase, and build a robust training model. Ten different machine learning methods are then integrated with the MAFT algorithm to form a powerful voice-based PD diagnosis model. Recorded test results of the PD prediction model using the actual and filtered features yielded 86.38% and 86.67% accuracies on average, respectively. With the aid of the MAFT feature selection, the test results are improved by 3.2% considering the hybrid model (HM) and 3.1% considering the Naïve Bayesian and random forest. Subsequently, an HM, which comprises a binary convolutional neural network and three feature selection algorithms (namely, genetic algorithm, Adam optimizer, and mini-batch gradient descent), is proposed to improve the classification accuracy of the PD. The results reveal that PD achieves an overall accuracy of 93.7%. The HM is integrated with the MAFT, and the combination realizes an overall accuracy of 96.9%. These results demonstrate that the combination of the MAFT algorithm and the HM model significantly enhances the PD diagnosis outcomes.

scholarly journals Interaction-based feature selection algorithm outperforms polygenic risk score in predicting Parkinson's Disease status

2021 ◽  
Author(s):  
Joern E. Klinger ◽  
Charles N. J. Ravarani ◽  
Hannes A. Baukmann ◽  
Justin L. Cope ◽  
Erwin P. Boettinger ◽  
...  
Keyword(s):  
Machine Learning ◽  
Parkinson’S Disease ◽  
Parkinson's Disease ◽  
Prediction Models ◽  
Learning Algorithms ◽  
Machine Learning Algorithms ◽  
Gene Interactions ◽  
Polygenic Risk Score ◽  
Genome Wide Association Studies ◽  
Polygenic Risk

Polygenic risk scores (PRS) aggregating results from genome-wide association studies are state of the art to predict the susceptibility to complex traits or diseases. Novel machine learning algorithms that use large amounts of data promise to find gene-gene interactions in order to build models with better predictive performance than PRS. Here, we present a data preprocessing step by using data-mining of contextual information to reduce the number of features, enabling machine learning algorithms to identify gene-gene interactions. We applied our approach to the Parkinson's Progression Markers Initiative (PPMI) dataset, an observational clinical study of 471 genotyped subjects (368 cases and 152 controls). With an AUC of 0.85 (95% CI = [0.72; 0.96]), the interaction-based prediction model outperforms the PRS (AUC of 0.58 (95% CI = [0.42; 0.81])). Furthermore, feature importance analysis of the model provided insights into the mechanism of Parkinson's Disease. For instance, the model revealed an interaction of previously described drug target candidate genes TMEM175 and GAPDHP25. These results demonstrate that interaction-based machine learning models can improve genetic prediction models and might provide an answer to the missing heritability problem.

scholarly journals Multiple Pathways of LRRK2-G2019S/Rab10 Interaction in Dopaminergic Neurons

2021 ◽  
pp. 1-16
Author(s):  
Alison Fellgett ◽  
C. Adam Middleton ◽  
Jack Munns ◽  
Chris Ugbode ◽  
David Jaciuch ◽  
...  
Keyword(s):  
Parkinson’S Disease ◽  
Parkinson's Disease ◽  
Dopaminergic Neurons ◽  
Genetic Interaction ◽  
In Vitro Assays ◽  
Rab Proteins ◽  
Circadian Activity ◽  
Loss Of Function ◽  
Lrrk2 G2019s

Background: Inherited mutations in the LRRK2 protein are the common causes of Parkinson’s disease, but the mechanisms by which increased kinase activity of mutant LRRK2 leads to pathological events remain to be determined. In vitro assays (heterologous cell culture, phospho-protein mass spectrometry) suggest that several Rab proteins might be directly phosphorylated by LRRK2-G2019S. An in vivo screen of Rab expression in dopaminergic neurons in young adult Drosophila demonstrated a strong genetic interaction between LRRK2-G2019S and Rab10. Objective: To determine if Rab10 is necessary for LRRK2-induced pathophysiological responses in the neurons that control movement, vision, circadian activity, and memory. These four systems were chosen because they are modulated by dopaminergic neurons in both humans and flies. Methods: LRRK2-G2019S was expressed in Drosophila dopaminergic neurons and the effects of Rab10 depletion on Proboscis Extension, retinal neurophysiology, circadian activity pattern (‘sleep’), and courtship memory determined in aged flies. Results: Rab10 loss-of-function rescued LRRK2-G2019S induced bradykinesia and retinal signaling deficits. Rab10 knock-down, however, did not rescue the marked sleep phenotype which results from dopaminergic LRRK2-G2019S. Courtship memory is not affected by LRRK2, but is markedly improved by Rab10 depletion. Anatomically, both LRRK2-G2019S and Rab10 are seen in the cytoplasm and at the synaptic endings of dopaminergic neurons. Conclusion: We conclude that, in Drosophila dopaminergic neurons, Rab10 is involved in some, but not all, LRRK2-induced behavioral deficits. Therefore, variations in Rab expression may contribute to susceptibility of different dopaminergic nuclei to neurodegeneration seen in people with Parkinson’s disease.

scholarly journals α-Synuclein-induced dysregulation of neuronal activity contributes to murine dopamine neuron vulnerability

2021 ◽  
Vol 7 (1) ◽  
Author(s):  
Abeer Dagra ◽  
Douglas R. Miller ◽  
Min Lin ◽  
Adithya Gopinath ◽  
Fatemeh Shaerzadeh ◽  
...  
Keyword(s):  
Parkinson’S Disease ◽  
Parkinson's Disease ◽  
Neuronal Activity ◽  
Dopaminergic Neurons ◽  
Prolonged Exposure ◽  
D2 Receptor ◽  
Neuronal Firing ◽  
Dopamine Neurons ◽  
Loss Of Function ◽  
Therapeutic Implications

AbstractPathophysiological damages and loss of function of dopamine neurons precede their demise and contribute to the early phases of Parkinson’s disease. The presence of aberrant intracellular pathological inclusions of the protein α-synuclein within ventral midbrain dopaminergic neurons is one of the cardinal features of Parkinson’s disease. We employed molecular biology, electrophysiology, and live-cell imaging to investigate how excessive α-synuclein expression alters multiple characteristics of dopaminergic neuronal dynamics and dopamine transmission in cultured dopamine neurons conditionally expressing GCaMP6f. We found that overexpression of α-synuclein in mouse (male and female) dopaminergic neurons altered neuronal firing properties, calcium dynamics, dopamine release, protein expression, and morphology. Moreover, prolonged exposure to the D2 receptor agonist, quinpirole, rescues many of the alterations induced by α-synuclein overexpression. These studies demonstrate that α-synuclein dysregulation of neuronal activity contributes to the vulnerability of dopaminergic neurons and that modulation of D2 receptor activity can ameliorate the pathophysiology. These findings provide mechanistic insights into the insidious changes in dopaminergic neuronal activity and neuronal loss that characterize Parkinson’s disease progression with significant therapeutic implications.

scholarly journals The Parkinson’s Disease-Associated Protein DJ-1 Protects Dictyostelium Cells from AMPK-Dependent Outcomes of Oxidative Stress

Cells ◽  
2021 ◽  
Vol 10 (8) ◽  
pp. 1874
Author(s):  
Suwei Chen ◽  
Sarah J. Annesley ◽  
Rasha A. F. Jasim ◽  
Paul R. Fisher
Keyword(s):  
Oxidative Stress ◽  
Parkinson’S Disease ◽  
Parkinson's Disease ◽  
Mitochondrial Dysfunction ◽  
Mitochondrial Respiration ◽  
Cysteine Residue ◽  
Reduced Form ◽  
Dependent Manner ◽  
Loss Of Function ◽  
Cellular Pathology

Mitochondrial dysfunction has been implicated in the pathology of Parkinson’s disease (PD). In Dictyostelium discoideum, strains with mitochondrial dysfunction present consistent, AMPK-dependent phenotypes. This provides an opportunity to investigate if the loss of function of specific PD-associated genes produces cellular pathology by causing mitochondrial dysfunction with AMPK-mediated consequences. DJ-1 is a PD-associated, cytosolic protein with a conserved oxidizable cysteine residue that is important for the protein’s ability to protect cells from the pathological consequences of oxidative stress. Dictyostelium DJ-1 (encoded by the gene deeJ) is located in the cytosol from where it indirectly inhibits mitochondrial respiration and also exerts a positive, nonmitochondrial role in endocytosis (particularly phagocytosis). Its loss in unstressed cells impairs endocytosis and causes correspondingly slower growth, while also stimulating mitochondrial respiration. We report here that oxidative stress in Dictyostelium cells inhibits mitochondrial respiration and impairs phagocytosis in an AMPK-dependent manner. This adds to the separate impairment of phagocytosis caused by DJ-1 knockdown. Oxidative stress also combines with DJ-1 loss in an AMPK-dependent manner to impair or exacerbate defects in phototaxis, morphogenesis and growth. It thereby phenocopies mitochondrial dysfunction. These results support a model in which the oxidized but not the reduced form of DJ-1 inhibits AMPK in the cytosol, thereby protecting cells from the adverse consequences of oxidative stress, mitochondrial dysfunction and the resulting AMPK hyperactivity.

Development of standardized regression-based formulas to assess meaningful cognitive change in early Parkinson’s disease

2020 ◽  
Author(s):  
Hannah L Combs ◽  
Kate A Wyman-Chick ◽  
Lauren O Erickson ◽  
Michele K York
Keyword(s):  
Parkinson’S Disease ◽  
Parkinson's Disease ◽  
Test Scores ◽  
Prediction Models ◽  
Early Stage ◽  
Cognitive Change ◽  
Cognitive Test ◽  
Healthy Controls ◽  
Change Over Time ◽  
Over Time

Abstract Objective Longitudinal assessment of cognitive and emotional functioning in patients with Parkinson’s disease (PD) is helpful in tracking progression of the disease, developing treatment plans, evaluating outcomes, and educating patients and families. Determining whether change over time is meaningful in neurodegenerative conditions, such as PD, can be difficult as repeat assessment of neuropsychological functioning is impacted by factors outside of cognitive change. Regression-based prediction formulas are one method by which clinicians and researchers can determine whether an observed change is meaningful. The purpose of the current study was to develop and validate regression-based prediction models of cognitive and emotional test scores for participants with early-stage idiopathic PD and healthy controls (HC) enrolled in the Parkinson’s Progression Markers Initiative (PPMI). Methods Participants with de novo PD and HC were identified retrospectively from the PPMI archival database. Data from baseline testing and 12-month follow-up were utilized in this study. In total, 688 total participants were included in the present study (NPD = 508; NHC = 185). Subjects from both groups were randomly divided into development (70%) and validation (30%) subsets. Results Early-stage idiopathic PD patients and healthy controls were similar at baseline. Regression-based models were developed for all cognitive and self-report mood measures within both populations. Within the validation subset, the predicted and observed cognitive test scores did not significantly differ, except for semantic fluency. Conclusions The prediction models can serve as useful tools for researchers and clinicians to study clinically meaningful cognitive and mood change over time in PD.

Sign in / Sign up

Export Citation Format

Share Document