{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,7]],"date-time":"2026-10-07T08:44:46Z","timestamp":1791362686622,"version":"4.3.1"},"reference-count":56,"publisher":"Public Library of Science (PLoS)","issue":"1","license":[{"start":{"date-parts":[[2026,1,6]],"date-time":"2026-01-06T00:00:00Z","timestamp":1767657600000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["www.plosone.org"],"crossmark-restriction":false},"short-container-title":["PLoS One"],"abstract":"<jats:sec id=\"sec001\">\n                    <jats:title>Background<\/jats:title>\n                    <jats:p>Accurate diagnosis of Parkinson\u2019s Disease (PD) remains challenging due to its biological complexity. Integrating machine learning with multi-omics and network topological analyses may enhance diagnostic precision.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec id=\"sec002\">\n                    <jats:title>Objective<\/jats:title>\n                    <jats:p>To classify early-stage PD patients and healthy controls (HCs) by integrating multi-omics data and network-based machine learning.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec id=\"sec003\">\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>We analyzed 305 participants from the PPMI cohort (213 PD, 92 HCs) using DNA methylation, gene expression, and proteomic data. Feature selection was conducted through sPLS-DA, followed by integration via DIABLO. Regulatory gene networks were constructed using STRING-based topology analysis. An XGBoost classifiers were trained and optimized on 244 samples and validated on 61 independent samples. Furthermore, we conducted external validation using data from 26 participants (12 PD, 14 HCs) in the GEO dataset, incorporating DNA methylation and gene expression profiles.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec id=\"sec004\">\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>DIABLO-based integration identified 56 CpG sites, 61 genes, and 70 proteins. Network topology analysis revealed 59 key regulators. Among three XGBoost models\u2014based on multi-omics signatures, topological regulators, and their combination\u2014the multi-omics model achieved the best test-set performance (AUC 0.72, 95%CI 0.51-0.85, accuracy 0.74, 95%CI 0.61-0.82). Within the validation set, the topological regulators model achieved the superior performance (AUC 0.57, 95%CI 0.37-0.73, accuracy 0.62, 95%CI 0.38-0.73).<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec id=\"sec005\">\n                    <jats:title>Conclusion<\/jats:title>\n                    <jats:p>Combining machine learning with integrative multi-omics and network topology analysis enables effective biomarker identification and PD classification, with strong potential for clinical diagnostic applications.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1371\/journal.pone.0329980","type":"journal-article","created":{"date-parts":[[2026,1,6]],"date-time":"2026-01-06T18:53:42Z","timestamp":1767725622000},"page":"e0329980","update-policy":"https:\/\/doi.org\/10.1371\/journal.pone.corrections_policy","source":"Crossref","is-referenced-by-count":6,"title":["Integrative multi-omics and network-based machine learning for early diagnosis of Parkinson\u2019s disease"],"prefix":"10.1371","volume":"21","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-1246-4032","authenticated-orcid":true,"given":"Wei","family":"Liu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lina","family":"Xu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2908-7763","authenticated-orcid":true,"given":"Xuejing","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-4774-1782","authenticated-orcid":true,"given":"Jiuqi","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"340","published-online":{"date-parts":[[2026,1,6]]},"reference":[{"issue":"13","key":"pone.0329980.ref001","doi-asserted-by":"crossref","first-page":"1583","DOI":"10.1002\/mds.25945","article-title":"The prevalence of Parkinson\u2019s disease: A systematic review and meta\u2010analysis","volume":"29","author":"T Pringsheim","year":"2014","journal-title":"Mov Disord"},{"issue":"5","key":"pone.0329980.ref002","article-title":"Parkinson Disease","volume":"169","author":"H Homayoun","year":"2018","journal-title":"Ann Intern Med"},{"issue":"10291","key":"pone.0329980.ref003","doi-asserted-by":"crossref","first-page":"2284","DOI":"10.1016\/S0140-6736(21)00218-X","article-title":"Parkinson\u2019s disease","volume":"397","author":"BR Bloem","year":"2021","journal-title":"Lancet"},{"issue":"12","key":"pone.0329980.ref004","doi-asserted-by":"crossref","first-page":"695","DOI":"10.1038\/s41582-024-01034-x","article-title":"Parkinson disease therapy: current strategies and future research priorities","volume":"20","author":"F Stocchi","year":"2024","journal-title":"Nat Rev Neurol"},{"issue":"7","key":"pone.0329980.ref005","doi-asserted-by":"crossref","first-page":"435","DOI":"10.1038\/nrn.2017.62","article-title":"Non-motor features of Parkinson disease","volume":"18","author":"AHV Schapira","year":"2017","journal-title":"Nat Rev Neurosci"},{"issue":"1","key":"pone.0329980.ref006","doi-asserted-by":"crossref","first-page":"111","DOI":"10.1186\/s10020-021-00327-x","article-title":"Circuit imaging biomarkers in preclinical and prodromal Parkinson\u2019s disease","volume":"27","author":"SK Meles","year":"2021","journal-title":"Mol Med"},{"issue":"454","key":"pone.0329980.ref007","article-title":"Finding useful biomarkers for Parkinson\u2019s disease","volume":"10","author":"AS Chen-Plotkin","year":"2018","journal-title":"Sci Transl Med"},{"issue":"10","key":"pone.0329980.ref008","doi-asserted-by":"crossref","first-page":"1452","DOI":"10.1002\/mds.27794","article-title":"Value of in vivo \u03b1-synuclein deposits in Parkinson\u2019s disease: A systematic review and meta-analysis","volume":"34","author":"K Tsukita","year":"2019","journal-title":"Mov Disord"},{"issue":"8","key":"pone.0329980.ref009","doi-asserted-by":"crossref","first-page":"620","DOI":"10.1016\/S1474-4422(17)30122-9","article-title":"Prediction of cognition in Parkinson\u2019s disease with a clinical\u2013genetic score: a longitudinal analysis of nine cohorts","volume":"16","author":"G Liu","year":"2017","journal-title":"Lancet Neurol"},{"issue":"1","key":"pone.0329980.ref010","doi-asserted-by":"crossref","first-page":"35","DOI":"10.1038\/s41531-022-00288-w","article-title":"Multi-modality machine learning predicting Parkinson\u2019s disease","volume":"8","author":"MB Makarious","year":"2022","journal-title":"NPJ Parkinsons Dis"},{"issue":"6","key":"pone.0329980.ref011","doi-asserted-by":"crossref","first-page":"746","DOI":"10.1001\/jamaneurol.2020.0428","article-title":"Identification of Risk Loci for Parkinson Disease in Asians and Comparison of Risk Between Asians and Europeans: A Genome-Wide Association Study","volume":"77","author":"JN Foo","year":"2020","journal-title":"JAMA Neurol"},{"issue":"2","key":"pone.0329980.ref012","doi-asserted-by":"crossref","first-page":"170","DOI":"10.1016\/S1474-4422(19)30287-X","article-title":"The genetic architecture of Parkinson\u2019s disease","volume":"19","author":"C Blauwendraat","year":"2020","journal-title":"Lancet Neurol"},{"issue":"1","key":"pone.0329980.ref013","doi-asserted-by":"crossref","first-page":"4558","DOI":"10.1038\/s41467-019-12576-w","article-title":"International meta-analysis of PTSD genome-wide association studies identifies sex- and ancestry-specific genetic risk loci","volume":"10","author":"CM Nievergelt","year":"2019","journal-title":"Nat Commun"},{"issue":"5","key":"pone.0329980.ref014","doi-asserted-by":"crossref","first-page":"668","DOI":"10.1038\/s41588-018-0090-3","article-title":"Genome-wide association analyses identify 44 risk variants and refine the genetic architecture of major depression","volume":"50","author":"NR Wray","year":"2018","journal-title":"Nat Genet"},{"issue":"8","key":"pone.0329980.ref015","doi-asserted-by":"crossref","first-page":"440","DOI":"10.1038\/s41582-020-0377-8","article-title":"Applications of machine learning to diagnosis and treatment of neurodegenerative diseases","volume":"16","author":"MA Myszczynska","year":"2020","journal-title":"Nat Rev Neurol"},{"issue":"1","key":"pone.0329980.ref016","doi-asserted-by":"crossref","first-page":"25","DOI":"10.1016\/j.neuron.2015.03.031","article-title":"The mutual inspirations of machine learning and neuroscience","volume":"86","author":"M Helmstaedter","year":"2015","journal-title":"Neuron"},{"issue":"1","key":"pone.0329980.ref017","article-title":"Mining genetic and transcriptomic data using machine learning approaches in Parkinson\u2019s disease","volume":"6","author":"C Su","year":"2020","journal-title":"NPJ Parkinsons Dis"},{"key":"pone.0329980.ref018","doi-asserted-by":"crossref","first-page":"12","DOI":"10.1016\/j.media.2018.05.004","article-title":"Complex networks reveal early MRI markers of Parkinson\u2019s disease","volume":"48","author":"N Amoroso","year":"2018","journal-title":"Med Image Anal"},{"issue":"10","key":"pone.0329980.ref019","doi-asserted-by":"crossref","first-page":"1002","DOI":"10.1016\/S1474-4422(15)00178-7","article-title":"Diagnosis of Parkinson\u2019s disease on the basis of clinical and genetic classification: a population-based modelling study","volume":"14","author":"MA Nalls","year":"2015","journal-title":"Lancet Neurol"},{"issue":"5","key":"pone.0329980.ref020","doi-asserted-by":"crossref","first-page":"727","DOI":"10.3390\/genes13050727","article-title":"A Machine Learning Approach to Parkinson\u2019s Disease Blood Transcriptomics","volume":"13","author":"E Pantaleo","year":"2022","journal-title":"Genes (Basel)"},{"key":"pone.0329980.ref021","doi-asserted-by":"crossref","first-page":"36","DOI":"10.1186\/1752-0509-3-36","article-title":"Identifying disease-specific genes based on their topological significance in protein networks","volume":"3","author":"Z Dezso","year":"2009","journal-title":"BMC Syst Biol"},{"issue":"1","key":"pone.0329980.ref022","doi-asserted-by":"crossref","DOI":"10.1371\/journal.pcbi.1000641","article-title":"Associating genes and protein complexes with disease via network propagation","volume":"6","author":"O Vanunu","year":"2010","journal-title":"PLoS Comput Biol"},{"issue":"4","key":"pone.0329980.ref023","doi-asserted-by":"crossref","first-page":"629","DOI":"10.1016\/j.pneurobio.2011.09.005","article-title":"The Parkinson Progression Marker Initiative (PPMI)","volume":"95","author":"K Marek","year":"2011","journal-title":"Prog Neurobiol"},{"issue":"14","key":"pone.0329980.ref024","doi-asserted-by":"crossref","DOI":"10.1212\/WNL.0000000000207725","article-title":"High-Throughput CSF Proteomics and Machine Learning to Identify Proteomic Signatures for Parkinson Disease Development and Progression","volume":"101","author":"K Tsukita","year":"2023","journal-title":"Neurology"},{"key":"pone.0329980.ref025","doi-asserted-by":"crossref","DOI":"10.3389\/fgene.2021.640266","article-title":"DNA Methylation and Expression Profiles of Whole Blood in Parkinson\u2019s Disease","volume":"12","author":"AR Henderson","year":"2021","journal-title":"Front Genet"},{"issue":"12","key":"pone.0329980.ref026","doi-asserted-by":"crossref","first-page":"503","DOI":"10.1186\/s13059-014-0503-2","article-title":"Functional normalization of 450k methylation array data improves replication in large cancer studies","volume":"15","author":"J-P Fortin","year":"2014","journal-title":"Genome Biol"},{"key":"pone.0329980.ref027","doi-asserted-by":"crossref","first-page":"587","DOI":"10.1186\/1471-2105-11-587","article-title":"Comparison of Beta-value and M-value methods for quantifying methylation levels by microarray analysis","volume":"11","author":"P Du","year":"2010","journal-title":"BMC Bioinformatics"},{"issue":"12","key":"pone.0329980.ref028","doi-asserted-by":"crossref","first-page":"550","DOI":"10.1186\/s13059-014-0550-8","article-title":"Moderated estimation of fold change and dispersion for RNA-seq data with DESeq2","volume":"15","author":"MI Love","year":"2014","journal-title":"Genome Biol"},{"issue":"1","key":"pone.0329980.ref029","doi-asserted-by":"crossref","DOI":"10.2202\/1544-6115.1492","article-title":"Sparse partial least squares classification for high dimensional data","volume":"9","author":"D Chung","year":"2010","journal-title":"Stat Appl Genet Mol Biol"},{"key":"pone.0329980.ref030","doi-asserted-by":"crossref","first-page":"253","DOI":"10.1186\/1471-2105-12-253","article-title":"Sparse PLS discriminant analysis: biologically relevant feature selection and graphical displays for multiclass problems","volume":"12","author":"K-A L\u00ea Cao","year":"2011","journal-title":"BMC Bioinformatics"},{"issue":"17","key":"pone.0329980.ref031","doi-asserted-by":"crossref","first-page":"3055","DOI":"10.1093\/bioinformatics\/bty1054","article-title":"DIABLO: an integrative approach for identifying key molecular drivers from multi-omics assays","volume":"35","author":"A Singh","year":"2019","journal-title":"Bioinformatics"},{"issue":"6","key":"pone.0329980.ref032","article-title":"Integrative multiomics analysis of human atherosclerosis reveals a serum response factor-driven network associated with intraplaque hemorrhage","volume":"11","author":"H Jin","year":"2021","journal-title":"Clin Transl Med"},{"key":"pone.0329980.ref033","doi-asserted-by":"crossref","DOI":"10.1093\/nar\/gky1131","article-title":"STRING v11: protein-protein association networks with increased coverage, supporting functional discovery in genome-wide experimental datasets","volume":"47","author":"D Szklarczyk","year":"2019","journal-title":"Nucleic Acids Res"},{"key":"pone.0329980.ref034","first-page":"785","article-title":"XGBoost: A Scalable Tree Boosting System","author":"T Chen","year":"2016","journal-title":"Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. New York (NY): Association for Computing Machinery"},{"key":"pone.0329980.ref035","doi-asserted-by":"crossref","first-page":"10","DOI":"10.3389\/fnmol.2013.00010","article-title":"Small RNA sequencing-microarray analyses in Parkinson leukocytes reveal deep brain stimulation-induced splicing changes that classify brain region transcriptomes","volume":"6","author":"L Soreq","year":"2013","journal-title":"Front Mol Neurosci"},{"issue":"3","key":"pone.0329980.ref036","doi-asserted-by":"crossref","first-page":"261","DOI":"10.1002\/ajmg.b.30272","article-title":"Evaluating the comparability of gene expression in blood and brain","author":"PF Sullivan","year":"2006","journal-title":"Am J Med Genet B Neuropsychiatr Genet"},{"issue":"4","key":"pone.0329980.ref037","doi-asserted-by":"crossref","first-page":"365","DOI":"10.1080\/15592294.2019.1588682","article-title":"DNA methylation changes associated with Parkinson\u2019s disease progression: outcomes from the first longitudinal genome-wide methylation analysis in blood","volume":"14","author":"A Henderson-Smith","year":"2019","journal-title":"Epigenetics"},{"issue":"23","key":"pone.0329980.ref038","doi-asserted-by":"crossref","first-page":"4240","DOI":"10.1021\/acschemneuro.3c00629","article-title":"Shared and Unique Disease Pathways in Amyotrophic Lateral Sclerosis and Parkinson\u2019s Disease Unveiled in Peripheral Blood Mononuclear Cells","volume":"14","author":"M Lualdi","year":"2023","journal-title":"ACS Chem Neurosci"},{"issue":"5","key":"pone.0329980.ref039","doi-asserted-by":"crossref","first-page":"2469","DOI":"10.3390\/ijms23052469","article-title":"Dysregulation of Human Somatic piRNA Expression in Parkinson\u2019s Disease Subtypes and Stages","volume":"23","author":"T Zhang","year":"2022","journal-title":"Int J Mol Sci"},{"issue":"11","key":"pone.0329980.ref040","doi-asserted-by":"crossref","first-page":"787","DOI":"10.1038\/nchembio.462","article-title":"The challenges of integrating multi-omic data sets","volume":"6","author":"B Palsson","year":"2010","journal-title":"Nat Chem Biol"},{"key":"pone.0329980.ref041","doi-asserted-by":"crossref","DOI":"10.1186\/1752-0509-8-S2-I1","article-title":"Data integration in the era of omics: current and future challenges","volume":"8","author":"D Gomez-Cabrero","year":"2014","journal-title":"BMC Syst Biol"},{"key":"pone.0329980.ref042","doi-asserted-by":"crossref","DOI":"10.1093\/database\/baab012","article-title":"Post-translational modifications in proteins: resources, tools and prediction methods","volume":"2021","author":"S Ramazi","year":"2021","journal-title":"Database"},{"issue":"3","key":"pone.0329980.ref043","doi-asserted-by":"crossref","first-page":"964","DOI":"10.1093\/brain\/awab446","article-title":"Single-cell sequencing of human midbrain reveals glial activation and a Parkinson-specific neuronal state","volume":"145","author":"S Smaji\u0107","year":"2022","journal-title":"Brain"},{"issue":"1","key":"pone.0329980.ref044","doi-asserted-by":"crossref","first-page":"212","DOI":"10.1186\/s12964-024-01590-1","article-title":"Single cell analysis reveals the roles and regulatory mechanisms of type-I interferons in Parkinson\u2019s disease","volume":"22","author":"P Quan","year":"2024","journal-title":"Cell Commun Signal"},{"issue":"3","key":"pone.0329980.ref045","doi-asserted-by":"crossref","first-page":"471","DOI":"10.3390\/genes13030471","article-title":"Monogenic Parkinson\u2019s Disease: Genotype, Phenotype, Pathophysiology, and Genetic Testing","volume":"13","author":"F Jia","year":"2022","journal-title":"Genes"},{"issue":"8","key":"pone.0329980.ref046","doi-asserted-by":"crossref","DOI":"10.1126\/sciadv.abb1540","article-title":"Neurodevelopmental defects and neurodegenerative phenotypes in human brain organoids carrying Parkinson\u2019s disease-linked DNAJC6 mutations","volume":"7","author":"N Wulansari","year":"2021","journal-title":"Sci Adv"},{"key":"pone.0329980.ref047","doi-asserted-by":"crossref","first-page":"136602","DOI":"10.1016\/j.neulet.2022.136602","article-title":"Evaluation of the relationship between SORL1 gene polymorphism and Parkinson\u2019s disease in the Chinese population","volume":"778","author":"Y Wang","year":"2022","journal-title":"Neurosci Lett"},{"issue":"10","key":"pone.0329980.ref048","doi-asserted-by":"crossref","first-page":"1961","DOI":"10.1002\/acn3.51433","article-title":"SORL1 mutation in a Greek family with Parkinson\u2019s disease and dementia","volume":"8","author":"G Xiromerisiou","year":"2021","journal-title":"Ann Clin Transl Neurol"},{"issue":"3","key":"pone.0329980.ref049","doi-asserted-by":"crossref","first-page":"513","DOI":"10.3390\/genes13030513","article-title":"The Role of NEDD4 E3 Ubiquitin-Protein Ligases in Parkinson\u2019s Disease","volume":"13","author":"JA Conway","year":"2022","journal-title":"Genes (Basel)"},{"issue":"5","key":"pone.0329980.ref050","doi-asserted-by":"crossref","DOI":"10.1371\/journal.pone.0036458","article-title":"A deleterious mutation in DNAJC6 encoding the neuronal-specific clathrin-uncoating co-chaperone auxilin, is associated with juvenile parkinsonism","volume":"7","author":"S Edvardson","year":"2012","journal-title":"PLoS One"},{"issue":"9","key":"pone.0329980.ref051","doi-asserted-by":"crossref","first-page":"4412","DOI":"10.1073\/pnas.1000738107","article-title":"Endocytosis and clathrin-uncoating defects at synapses of auxilin knockout mice","volume":"107","author":"Y-I Yim","year":"2010","journal-title":"Proc Natl Acad Sci U S A"},{"issue":"3","key":"pone.0329980.ref052","doi-asserted-by":"crossref","first-page":"199","DOI":"10.1038\/nsmb.2954","article-title":"Structural basis for amyloidogenic peptide recognition by sorLA","volume":"22","author":"Y Kitago","year":"2015","journal-title":"Nat Struct Mol Biol"},{"issue":"8","key":"pone.0329980.ref053","doi-asserted-by":"crossref","first-page":"973","DOI":"10.1038\/ejhg.2017.87","article-title":"Characterization of pathogenic SORL1 genetic variants for association with Alzheimer\u2019s disease: a clinical interpretation strategy","volume":"25","author":"H Holstege","year":"2017","journal-title":"Eur J Hum Genet"},{"issue":"23","key":"pone.0329980.ref054","doi-asserted-by":"crossref","first-page":"19177","DOI":"10.1074\/jbc.M112.355909","article-title":"Protein kinase C (PKC)-promoted endocytosis of glutamate transporter GLT-1 requires ubiquitin ligase Nedd4-2-dependent ubiquitination but not phosphorylation","volume":"287","author":"N Garc\u00eda-Tard\u00f3n","year":"2012","journal-title":"J Biol Chem"},{"issue":"1","key":"pone.0329980.ref055","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1016\/j.gene.2014.11.051","article-title":"NEDD4-2 (NEDD4L): the ubiquitin ligase for multiple membrane proteins","volume":"557","author":"P Goel","year":"2015","journal-title":"Gene"},{"issue":"2","key":"pone.0329980.ref056","article-title":"Regulation of glutamate transporter trafficking by Nedd4-2 in a Parkinson\u2019s disease model","volume":"8","author":"Y Zhang","year":"2017","journal-title":"Cell Death Dis"}],"container-title":["PLOS One"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0329980","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,6]],"date-time":"2026-01-06T18:53:53Z","timestamp":1767725633000},"score":1,"resource":{"primary":{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0329980"}},"subtitle":[],"editor":[{"given":"Vijay","family":"Kumar","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"editor"}]}],"short-title":[],"issued":{"date-parts":[[2026,1,6]]},"references-count":56,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2026,1,6]]}},"URL":"https:\/\/doi.org\/10.1371\/journal.pone.0329980","relation":{},"ISSN":["1932-6203"],"issn-type":[{"value":"1932-6203","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,1,6]]}}}