Machine learning analysis of metabolomics and neuro-imaging data for Parkinson’s disease

Presentation (2019, January)

Impaired serine metabolism complements LRRK2-G2019S pathogenicity in PD patients

in Parkinsonism and Related Disorders (2019)

BSA4Yeast: Web-based quantitative trait locus linkage analysis and bulk segregant analysis of yeast sequencing data

in GigaScience (2019), 8(6), 060

Quantitative Trait Loci (QTL) mapping using bulk segregants is an effective approach for identifying genetic variants associated with phenotypes of interest in model organisms. By exploiting next ... [more ▼]

Quantitative Trait Loci (QTL) mapping using bulk segregants is an effective approach for identifying genetic variants associated with phenotypes of interest in model organisms. By exploiting next-generation sequencing technology, the QTL mapping accuracy can be improved significantly, providing a valuable means to annotate new genetic variants. However, setting up a comprehensive analysis framework for this purpose is a time-consuming and error prone task, posing many challenges for scientists with limited experience in this domain. Findings: Here, we present BSA4Yeast, a comprehensive web-application for QTL mapping via bulk segregant analysis of yeast sequencing data. The software provides an automated and efficiency-optimized data processing, up-to-date functional annotations, and an interactive web-interface to explore identified QTLs. Conclusion: BSA4Yeast enables researchers to identify plausible candidate genes in QTL regions efficiently in order to validate their genetic variations experimentally as causative for a phenotype of interest. BSA4Yeast is freely available at https://bsa4yeast.lcsb.uni.lu. [less ▲]

Integrative analysis of blood metabolomics and PET brain neuroimaging data for Parkinson's disease

in Neurobiology of Disease (2019), 124(1), 555-562

The diagnosis of Parkinson's disease (PD) often remains a clinical challenge. Molecular neuroimaging can facilitate the diagnostic process. The diagnostic potential of metabolomic signatures has recently ... [more ▼]

The diagnosis of Parkinson's disease (PD) often remains a clinical challenge. Molecular neuroimaging can facilitate the diagnostic process. The diagnostic potential of metabolomic signatures has recently been recognized. Methods: We investigated whether the joint data analysis of blood metabolomics and PET imaging by machine learning provides enhanced diagnostic discrimination and gives further pathophysiological insights. Blood plasma samples were collected from 60 PD patients and 15 age- and gender-matched healthy controls. We determined metabolomic profiles by gas chromatography coupled to mass spectrometry (GC-MS). In the same cohort and at the same time we performed FDOPA PET in 44 patients and 14 controls and FDG PET in 51 patients and 16 controls. 18 PD patients were available for a follow-up exam after one year. Both data sets were analysed by two machine learning approaches, applying either linear support vector machines or random forests within a leave-one-out cross-validation and computing receiver operating characteristic (ROC) curves. Results: In the metabolomics data, the baseline comparison between cases and controls as well as the followup assessment of patients pointed to metabolite changes associated with oxidative stress and inflammation. For the FDOPA and FDG PET data, the diagnostic predictive performance (DPP) in the ROC analyses was highest when combining imaging features with metabolomics data (ROC AUC for best FDOPA + metabolomics model: 0.98; AUC for best FDG + metabolomics model: 0.91). DPP was lower when using only PET attributes or only metabolomics signatures. Conclusion: Integrating blood metabolomics data combined with PET data considerably enhances the diagnostic discrimination power. Metabolomic signatures also indicate interesting disease-inherent changes in cellular processes, including oxidative stress response and inflammation. [less ▲]

Combining PET imaging and blood metabolomics data to improve machine learning models for Parkinson’s disease diagnosis

Poster (2018, October 08)

Objective: To investigate whether the integration of PET imaging and metabolomics data can provide improved machine learning models for PD diagnosis. Background: The reliable diagnosis of PD can remain ... [more ▼]

Objective: To investigate whether the integration of PET imaging and metabolomics data can provide improved machine learning models for PD diagnosis. Background: The reliable diagnosis of PD can remain challenging, even at the motor stage. PET imaging can be used to confirm the clinical diagnosis. However, limitations in the robustness of predictive features extracted from the data and the costs associated with PET imaging restrict its application. Using blood metabolomics data as an additional information source may provide improved combined diagnostic models and/or an initial filter to decide on whether to apply PET imaging. Methods: Metabolomics profiling of blood plasma samples using gas chromatography coupled to mass spectrometry (GC­MS) was conducted in 60 IPD patients and 15 healthy controls. After pre-processing, these data were compared to neuroimaging data for subsets of the same individuals using FDOPA PET (44 patients and 14 controls) and FDG PET (51 patients and 15 controls). Machine learning models using linear support vector machines were trained on 50% of the data and evaluated on a 50% hold­out test set using Receiver Operating Characteristic (ROC) curves. Next, standardized FDOPA and FDG PET intensity measurements were combined with those from the metabolomics data to build and evaluate sample classification models in the same manner as for the individual datasets. Results: Both for the FDOPA and FDG PET data, the predictive performance given by the area under the ROC curve (AUC) was highest when combining imaging features with those from the metabolomics data (AUC for FDOPA + metabolomics: 0.98; AUC for FDG + metabolomics: 0.91). The performance was generally lower when using only the respective PET attributes (FDOPA: 0.94, FDG: 0.8) or only the metabolomics data (AUC: 0.66). [less ▲]

Computational systems biology approaches for Parkinson's disease

in Cell and Tissue Research (2018), 373(1), 91109

Parkinson’s disease (PD) is a prime example of a complex and heterogeneous disorder, characterized by multifaceted and varied motor- and non-motor symptoms and different possible interplays of genetic and ... [more ▼]

Parkinson’s disease (PD) is a prime example of a complex and heterogeneous disorder, characterized by multifaceted and varied motor- and non-motor symptoms and different possible interplays of genetic and environmental risk factors. While investigations of individual PD-causing mutations and risk factors in isolation are providing important insights to improve our understanding of the molecular mechanisms behind PD, there is a growing consensus that a more complete understanding of these mechanisms will require an integrative modeling of multifactorial disease-associated perturbations in molecular networks. Identifying and interpreting the combinatorial effects of multiple PD-associated molecular changes may pave the way towards an earlier and reliable diagnosis and more effective therapeutic interventions. This review provides an overview of computational systems biology approaches developed in recent years to study multifactorial molecular alterations in complex disorders, with a focus on PD research applications. Strengths and weaknesses of different cellular pathway and network analyses, and multivariate machine learning techniques for investigating PD-related omics data are discussed, and strategies proposed to exploit the synergies of multiple biological knowledge and data sources. A final outlook provides an overview of specific challenges and possible next steps for translating systems biology findings in PD to new omics-based diagnostic tools and targeted, drug-based therapeutic approaches. [less ▲]

A structure-activity relationship linking non-planar PCBs to functional deficits of neural crest cells: new roles for connexins

in Archives of Toxicology (2018), 92(3), 12251247

Migration of neural crest cells (NCC) is a fundamental developmental process, and test methods to identify interfering toxicants have been developed. By examining cell function endpoints, as in the ... [more ▼]

Migration of neural crest cells (NCC) is a fundamental developmental process, and test methods to identify interfering toxicants have been developed. By examining cell function endpoints, as in the ‘migration-inhibition of NCC (cMINC)’ assay, a large number of toxicity mechanisms and protein targets can be covered. However, the key events that lead to the adverse effects of a given chemical or group of related compounds are hard to elucidate. To address this issue, we explored here, whether the establishment of two overlapping structure–activity relationships (SAR)—linking chemical structure on the one hand to a phenotypic test outcome, and on the other hand to a mechanistic endpoint—was useful as strategy to identify relevant toxicity mechanisms. For this purpose, we chose polychlorinated biphenyls (PCB) as a large group of related, but still toxicologically and physicochemically diverse structures. We obtained concentration-dependent data for 26 PCBs in the cMINC assay. Moreover, the test chemicals were evaluated by a new high-content imaging method for their effect on cellular re-distribution of connexin43 and for their capacity to inhibit gap junctions. Non-planar PCBs inhibited NCC migration. The potency (1–10 μM) correlated with the number of ortho-chlorine substituents; non-ortho-chloro (planar) PCBs were non-toxic. The toxicity to NCC partially correlated with gap junction inhibition, while it fully correlated (p < 0.0004) with connexin43 cellular re-distribution. Thus, our double-SAR strategy revealed a mechanistic step tightly linked to NCC toxicity of PCBs. Connexin43 patterns in NCC may be explored as a new endpoint relevant to developmental toxicity screening. [less ▲]

Combining Metabolomics and Neuroimaging in mid-stage Parkinson’s Disease. A Proof of Concept for Cross-Fertilization.

in Neurology (2018), 90(15), 3066

Absence of regulator of G-protein signaling 4 does not protect against dopamine neuron dysfunction and injury in the mouse 6-hydroxydopamine lesion model of Parkinson's disease

in Neurobiology of Aging (2017), 58

Regulator of G-Protein Signaling 4 (RGS4), a member of the RGS family of proteins that inactivate G-proteins, has gained interest as a potential drug target for neurological disorders, such as epilepsy ... [more ▼]

Regulator of G-Protein Signaling 4 (RGS4), a member of the RGS family of proteins that inactivate G-proteins, has gained interest as a potential drug target for neurological disorders, such as epilepsy and Parkinson’s disease (PD). In the case of PD, the main current option for alleviating motor symptoms are dopamine replacement therapies, which have limitations because of side effects, and reduced effectiveness over the long term. Research on new non-dopaminergic PD drug targets has indicated that inhibition of RGS4 could be an effective adjuvant treatment option. The effectiveness of RGS4 inhibition for an array of PD-linked functional and structural neuroprotection endpoints has not yet been demonstrated. Here, we use the 6-Hydroxydopamine (6-OHDA) lesioning model of the nigrostriatal pathway in mice to address this question. We observe, using a battery of behavioral and pathological measures, that mice deficient for RGS4 are not protected from 6-OHDA induced injury, and show enhanced susceptibility in some measures of motor function. Our results suggest that inhibition of RGS4 as a non-dopaminergic target for PD should be approached with caution. [less ▲]

NeuroChip, an updated version of the NeuroX genotyping platform to rapidly screen for variants associated with neurological diseases

in Neurobiology of Aging (2017)

Genetics has proven to be a powerful approach in neurodegenerative diseases research, resulting in the identification of numerous causal and risk variants. Previously, we introduced the NeuroX Illumina ... [more ▼]

Genetics has proven to be a powerful approach in neurodegenerative diseases research, resulting in the identification of numerous causal and risk variants. Previously, we introduced the NeuroX Illumina genotyping array, a fast and efficient genotyping platform designed for the investigation of genetic variation in neurodegenerative diseases. Here, we present its updated version, named NeuroChip. The NeuroChip is a low cost, custom-designed array containing a tagging variant backbone of about 306,670 variants complemented with a manually curated custom content comprised of 179,467 variants implicated in diverse neurological diseases, including Alzheimer’s disease, Parkinson’s disease, Lewy body dementia, amyotrophic lateral sclerosis, frontotemporal dementia, progressive supranuclear palsy, corticobasal degeneration and multiple system atrophy. The tagging backbone was chosen because of the low cost and good genome-wide resolution; the custom content can be combined with other backbones, like population or drug development arrays. Using the NeuroChip, we can accurately identify rare variants and impute over 5.3 million common SNPs from the latest release of the Haplotype Reference Consortium. In summary, we describe the design and usage of the NeuroChip array, and show its capability for detecting rare pathogenic variants in numerous neurodegenerative diseases. The NeuroChip has a more comprehensive and improved content, which makes it a reliable, high-throughput, cost-effective screening tool for genetic research and molecular diagnostics in neurodegenerative diseases. [less ▲]