Identification of novel variants, genes and pathways potentially linked to Parkinson's disease using machine learning

There are 78 loci associated with Parkinson's disease (PD) in the most recent genome-wide association study (GWAS), yet the specific genes driving these associations are mostly unknown. Herein, we aimed to nominate the top candidate gene from each PD locus, and identify variants and pathways potentially involved in PD. We trained a machine learning model to predict PD-associated genes from GWAS loci using genomic, transcriptomic, and epigenomic data from brain tissues and dopaminergic neurons. We nominated candidate genes in each locus, identified novel pathways potentially involved in PD, such as the inositol phosphate biosynthetic pathway (INPP5F, IP6K2, ITPKB, PPIP5K2). Specific common coding variants in SPNS1 and MLX may be involved in PD, and burden tests of rare variants further support that CNIP3, LSM7, NUCKS1 and the polyol/inositol phosphate biosynthetic pathway are associated with PD. Functional studies are needed to further analyze the involvements of these genes and pathways in PD.

[1]  T. Takeuchi,et al.  Phosphatidylinositol-3,4,5-trisphosphate interacts with alpha-synuclein and initiates its aggregation and formation of Parkinson’s disease-related fibril polymorphism , 2023, Acta Neuropathologica.

[2]  E. Martin,et al.  Identification of novel genes for age‐at‐onset of Alzheimer's disease by combining quantitative and survival trait analyses , 2023, Alzheimer's & dementia : the journal of the Alzheimer's Association.

[3]  C. Hoggart,et al.  PRSet: Pathway-based polygenic risk score analyses and software , 2023, PLoS genetics.

[4]  D. Hernandez,et al.  The Foundational Data Initiative for Parkinson Disease: Enabling efficient translation from genetic maps to mechanism , 2023, Cell genomics.

[5]  V. Baekelandt,et al.  Increased Levels of the Parkinson’s Disease-Associated Gene ITPKB Correlate with Higher Expression Levels of α-Synuclein, Independent of Mutation Status , 2023, International journal of molecular sciences.

[6]  M. Wenk,et al.  Spns1 is a lysophospholipid transporter mediating lysosomal phospholipid salvage , 2022, Proceedings of the National Academy of Sciences of the United States of America.

[7]  Thomas M. Durcan,et al.  GALC variants affect galactosylceramidase enzymatic activity and risk of Parkinson’s disease , 2022, medRxiv.

[8]  Evan Z. Macosko,et al.  Single-cell genomic profiling of human dopamine neurons identifies a population that selectively degenerates in Parkinson’s disease , 2022, Nature Neuroscience.

[9]  S. Snyder,et al.  Inositol hexakisphosphate kinase-2 non-catalytically regulates mitophagy by attenuating PINK1 signaling , 2022, Proceedings of the National Academy of Sciences of the United States of America.

[10]  Jie Zhou,et al.  PPIP5K2 promotes colorectal carcinoma pathogenesis through facilitating DNA homologous recombination repair , 2021, Oncogene.

[11]  D. Hassabis,et al.  Protein complex prediction with AlphaFold-Multimer , 2021, bioRxiv.

[12]  S. Ovchinnikov,et al.  ColabFold: making protein folding accessible to all , 2022, Nature Methods.

[13]  K. Kavukcuoglu,et al.  Highly accurate protein structure prediction for the human proteome , 2021, Nature.

[14]  J. Hardy,et al.  Identification of Candidate Parkinson Disease Genes by Integrating Genome-Wide Association Study, Expression, and Epigenetic Data Sets , 2021, JAMA neurology.

[15]  H. Runz,et al.  The Parkinson’s disease-associated gene ITPKB protects against α-synuclein aggregation by regulating ER-to-mitochondria calcium release , 2020, Proceedings of the National Academy of Sciences.

[16]  Sonja W. Scholz,et al.  Accelerating Medicines Partnership: Parkinson's Disease. Genetic Resource , 2020, medRxiv.

[17]  C. Blauwendraat,et al.  Fine mapping of the HLA locus in Parkinson’s disease in Europeans , 2020, medRxiv.

[18]  I. Vucenik,et al.  Role of Inositols and Inositol Phosphates in Energy Metabolism , 2020, Molecules.

[19]  T. Raj,et al.  Fine-mapping of Parkinson’s disease susceptibility loci identifies putative causal variants , 2020, bioRxiv.

[20]  Ellen M. Schmidt,et al.  Open Targets Genetics: An open approach to systematically prioritize causal variants and genes at all published human GWAS trait-associated loci , 2020, bioRxiv.

[21]  Sonja W. Scholz,et al.  Large-scale pathway specific polygenic risk and transcriptomic community network analysis identifies novel functional pathways in Parkinson disease , 2020, Acta Neuropathologica.

[22]  Hugh Chen,et al.  From local explanations to global understanding with explainable AI for trees , 2020, Nature Machine Intelligence.

[23]  Sonja W. Scholz,et al.  Identification of novel risk loci, causal insights, and heritable risk for Parkinson's disease: a meta-analysis of genome-wide association studies , 2019, The Lancet Neurology.

[24]  Z. Gan-Or,et al.  Autophagy lysosomal pathway dysfunction in Parkinson's disease; evidence from human genetics. , 2019, Parkinsonism & related disorders.

[25]  Jing Wang,et al.  WebGestalt 2019: gene set analysis toolkit with revamped UIs and APIs , 2019, Nucleic Acids Res..

[26]  Y. Bossé,et al.  Benefits and limitations of genome-wide association studies , 2019, Nature Reviews Genetics.

[27]  C. Legido-Quigley,et al.  Palmitate and Stearate are Increased in the Plasma in a 6-OHDA Model of Parkinson’s Disease , 2019, Metabolites.

[28]  Rick B. Vega,et al.  Single-Nucleotide Polymorphism of the MLX Gene Is Associated With Takayasu Arteritis , 2018, Circulation. Genomic and precision medicine.

[29]  A. Chakraborty.  The inositol pyrophosphate pathway in health and diseases , 2018, Biological reviews of the Cambridge Philosophical Society.

[30]  C. Gu,et al.  Mutations in Diphosphoinositol-Pentakisphosphate Kinase PPIP5K2 are associated with hearing loss in human and mouse , 2018, PLoS genetics.

[31]  T. Raj,et al.  Prioritizing Parkinson’s disease genes using population-scale transcriptomic data , 2017, bioRxiv.

[32]  D. Posthuma,et al.  Functional mapping and annotation of genetic associations with FUMA , 2017, Nature Communications.

[33]  Scott Lundberg,et al.  A Unified Approach to Interpreting Model Predictions , 2017, NIPS.

[34]  F. Cunningham,et al.  The Ensembl Variant Effect Predictor , 2016, bioRxiv.

[35]  Chuanxia Ju,et al.  Neuroprotection of inositol hexaphosphate and changes of mitochondrion mediated apoptotic pathway and α-synuclein aggregation in 6-OHDA induced parkinson׳s disease cell model , 2016, Brain Research.

[36]  J. McLaurin,et al.  α-Synuclein aggregation, seeding and inhibition by scyllo-inositol. , 2016, Biochemical and biophysical research communications.

[37]  P. Linsley,et al.  MAST: a flexible statistical framework for assessing transcriptional changes and characterizing heterogeneity in single-cell RNA sequencing data , 2015, Genome Biology.

[38]  P. De Camilli,et al.  Sac2/INPP5F is an inositol 4-phosphatase that functions in the endocytic pathway , 2015, The Journal of cell biology.

[39]  W. Huber,et al.  Moderated estimation of fold change and dispersion for RNA-seq data with DESeq2 , 2014, Genome Biology.

[40]  Uwe Klose,et al.  Dopamine Reduction in the Substantia Nigra of Parkinson's Disease Patients Confirmed by In Vivo Magnetic Resonance Spectroscopic Imaging , 2014, PloS one.

[41]  S. Pappatà,et al.  Mutation in the SYNJ1 Gene Associated with Autosomal Recessive, Early‐Onset Parkinsonism , 2013, Human mutation.

[42]  Seunggeun Lee,et al.  General framework for meta-analysis of rare variants in sequencing association studies. , 2013, American journal of human genetics.

[43]  Shane J. Neph,et al.  Systematic Localization of Common Disease-Associated Variation in Regulatory DNA , 2012, Science.

[44]  S. Snyder,et al.  Inositol Pyrophosphates as Mammalian Cell Signals , 2011, Science Signaling.

[45]  Ayellet V. Segrè,et al.  Hundreds of variants clustered in genomic loci and biological pathways affect human height , 2010, Nature.

[46]  P. Bork,et al.  A method and server for predicting damaging missense mutations , 2010, Nature Methods.

[47]  Stephen K. Burley,et al.  X-Ray Structures of Myc-Max and Mad-Max Recognizing DNA Molecular Bases of Regulation by Proto-Oncogenic Transcription Factors , 2003, Cell.

[48]  D. Ayer,et al.  MondoA, a Novel Basic Helix-Loop-Helix–Leucine Zipper Transcriptional Activator That Constitutes a Positive Branch of a Max-Like Network , 2000, Molecular and Cellular Biology.

[49]  D. Ayer,et al.  Mlx, a Novel Max-like BHLHZip Protein That Interacts with the Max Network of Transcription Factors* , 1999, The Journal of Biological Chemistry.

[50]  R. Belmaker,et al.  Inositol is not therapeutic in Parkinson's Disease , 1999 .

[51]  D. K. Chowdhuri,et al.  Metabolomic Analysis Provides Insights on Paraquat-Induced Parkinson-Like Symptoms in Drosophila melanogaster , 2014, Molecular Neurobiology.

[52]  C. Tanaka,et al.  Inositol 1,4,5-trisphosphate binding sites in the brain: Regional distribution, characterization, and alterations in brains of patients with Parkinson's disease , 2008, Journal of Molecular Neuroscience.

[53]  D. Ayer,et al.  The Mlx network: evidence for a parallel Max-like transcriptional network that regulates energy metabolism. , 2006, Current topics in microbiology and immunology.