{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,27]],"date-time":"2026-08-27T06:42:11Z","timestamp":1787812931239,"version":"build-2784847793"},"reference-count":55,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2022,11,29]],"date-time":"2022-11-29T00:00:00Z","timestamp":1669680000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100010767","name":"Innovative Medicines Initiative","doi-asserted-by":"publisher","award":["115372"],"award-info":[{"award-number":["115372"]}],"id":[{"id":"10.13039\/501100010767","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004359","name":"Swedish Research Council","doi-asserted-by":"publisher","award":["#2018\u201302532"],"award-info":[{"award-number":["#2018\u201302532"]}],"id":[{"id":"10.13039\/501100004359","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100000781","name":"European Research Council","doi-asserted-by":"publisher","award":["#681712"],"award-info":[{"award-number":["#681712"]}],"id":[{"id":"10.13039\/501100000781","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100000781","name":"European Research Council","doi-asserted-by":"publisher","award":["#101053962"],"award-info":[{"award-number":["#101053962"]}],"id":[{"id":"10.13039\/501100000781","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Aging Neurosci."],"abstract":"<jats:sec><jats:title>Background and objective<\/jats:title><jats:p>Blood-based biomarkers represent a promising approach to help identify early Alzheimer\u2019s disease (AD). Previous research has applied traditional machine learning (ML) to analyze plasma omics data and search for potential biomarkers, but the most modern ML methods based on deep learning has however been scarcely explored. In the current study, we aim to harness the power of state-of-the-art deep learning neural networks (NNs) to identify plasma proteins that predict amyloid, tau, and neurodegeneration (AT[N]) pathologies in AD.<\/jats:p><\/jats:sec><jats:sec><jats:title>Methods<\/jats:title><jats:p>We measured 3,635 proteins using SOMAscan in 881 participants from the European Medical Information Framework for AD Multimodal Biomarker Discovery study (EMIF-AD MBD). Participants underwent measurements of brain amyloid \u03b2 (A\u03b2) burden, phosphorylated tau (p-tau) burden, and total tau (t-tau) burden to determine their AT(N) statuses. We ranked proteins by their association with A\u03b2, p-tau, t-tau, and AT(N), and fed the top 100 proteins along with age and apolipoprotein E (<jats:italic>APOE<\/jats:italic>) status into NN classifiers as input features to predict these four outcomes relevant to AD. We compared NN performance of using proteins, age, and <jats:italic>APOE<\/jats:italic> genotype with performance of using age and <jats:italic>APOE<\/jats:italic> status alone to identify protein panels that optimally improved the prediction over these main risk factors. Proteins that improved the prediction for each outcome were aggregated and nominated for pathway enrichment and protein\u2013protein interaction enrichment analysis.<\/jats:p><\/jats:sec><jats:sec><jats:title>Results<\/jats:title><jats:p>Age and <jats:italic>APOE<\/jats:italic> alone predicted A\u03b2, p-tau, t-tau, and AT(N) burden with area under the curve (AUC) scores of 0.748, 0.662, 0.710, and 0.795. The addition of proteins significantly improved AUCs to 0.782, 0.674, 0.734, and 0.831, respectively. The identified proteins were enriched in five clusters of AD-associated pathways including human immunodeficiency virus 1 infection, p53 signaling pathway, and phosphoinositide-3-kinase\u2013protein kinase B\/Akt signaling pathway.<\/jats:p><\/jats:sec><jats:sec><jats:title>Conclusion<\/jats:title><jats:p>Combined with age and <jats:italic>APOE<\/jats:italic> genotype, the proteins identified have the potential to serve as blood-based biomarkers for AD and await validation in future studies. While the NNs did not achieve better scores than the support vector machine model used in our previous study, their performances were likely limited by small sample size.<\/jats:p><\/jats:sec>","DOI":"10.3389\/fnagi.2022.1040001","type":"journal-article","created":{"date-parts":[[2022,11,29]],"date-time":"2022-11-29T15:29:50Z","timestamp":1669735790000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":16,"title":["Predicting AT(N) pathologies in Alzheimer\u2019s disease from blood-based proteomic data using neural networks"],"prefix":"10.3389","volume":"14","author":[{"given":"Yuting","family":"Zhang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Upamanyu","family":"Ghose","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Noel J.","family":"Buckley","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sebastiaan","family":"Engelborghs","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kristel","family":"Sleegers","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Giovanni B.","family":"Frisoni","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Anders","family":"Wallin","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Alberto","family":"Lle\u00f3","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Julius","family":"Popp","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Pablo","family":"Martinez-Lage","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Cristina","family":"Legido-Quigley","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Frederik","family":"Barkhof","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Henrik","family":"Zetterberg","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Pieter Jelle","family":"Visser","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lars","family":"Bertram","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Simon","family":"Lovestone","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Alejo J.","family":"Nevado-Holgado","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Liu","family":"Shi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2022,11,29]]},"reference":[{"key":"ref1","doi-asserted-by":"publisher","first-page":"5628","DOI":"10.4049\/jimmunol.0903678","article-title":"Molecular intercommunication between the complement and coagulation systems","volume":"185","author":"Amara","year":"2010","journal-title":"J. Immunol."},{"key":"ref2","doi-asserted-by":"publisher","first-page":"419","DOI":"10.1212\/CON.0000000000000307","article-title":"Alzheimer disease","volume":"22","author":"Apostolova","year":"2016","journal-title":"Continuum"},{"key":"ref3","author":"Ar\u0131k","year":"2021"},{"key":"ref4","doi-asserted-by":"publisher","first-page":"eaau7220","DOI":"10.1126\/sciadv.aau7220","article-title":"A plasma protein classifier for predicting amyloid burden for preclinical Alzheimer\u2019s disease. Science","volume":"5","author":"Ashton","year":"2019","journal-title":"Advances"},{"key":"ref5","doi-asserted-by":"publisher","first-page":"709","DOI":"10.1007\/s00401-021-02275-6","article-title":"Plasma p-tau231: a new biomarker for incipient Alzheimer\u2019s disease pathology","volume":"141","author":"Ashton","year":"2021","journal-title":"Acta Neuropathol."},{"key":"ref6","doi-asserted-by":"publisher","first-page":"e0235663","DOI":"10.1371\/journal.pone.0235663","article-title":"Inexpensive, non-invasive biomarkers predict Alzheimer transition using machine learning analysis of the Alzheimer\u2019s disease neuroimaging (ADNI) database","volume":"15","author":"Beltr\u00e1n","year":"2020","journal-title":"PLoS One"},{"key":"ref7","doi-asserted-by":"publisher","first-page":"64","DOI":"10.1186\/s13195-018-0396-5","article-title":"The EMIF-AD multimodal biomarker discovery study: design, methods and cohort characteristics","volume":"10","author":"Bos","year":"2018","journal-title":"Alzheimers Res. Ther."},{"key":"ref8","doi-asserted-by":"publisher","first-page":"1877","DOI":"10.48550\/arXiv.2005.14165","article-title":"Language models are few-shot learners","volume":"33","author":"Brown","year":"2020","journal-title":"Adv. Neural Inf. Proces. Syst."},{"key":"ref9","doi-asserted-by":"publisher","first-page":"518","DOI":"10.1016\/j.nbd.2008.12.014","article-title":"JNK regulates APP cleavage and degradation in a model of Alzheimer\u2019s disease","volume":"33","author":"Colombo","year":"2009","journal-title":"Neurobiol. Dis."},{"key":"ref10","doi-asserted-by":"publisher","first-page":"287","DOI":"10.1001\/jamaneurol.2014.4144","article-title":"Phase 3 trial of flutemetamol labeled with radioactive fluorine 18 imaging and neuritic plaque density","volume":"72","author":"Curtis","year":"2015","journal-title":"JAMA Neurol."},{"key":"ref11","doi-asserted-by":"publisher","first-page":"1503","DOI":"10.1111\/j.1526-4610.2011.01959.x","article-title":"Incidence of post-dural puncture headache in research volunteers","volume":"51","author":"de Almeida","year":"2011","journal-title":"Headache"},{"key":"ref12","doi-asserted-by":"publisher","first-page":"16","DOI":"10.1186\/s12014-019-9237-1","article-title":"Deep undepleted human serum proteome profiling toward biomarker discovery for Alzheimer\u2019s disease","volume":"16","author":"Dey","year":"2019","journal-title":"Clin. Proteomics"},{"key":"ref13","doi-asserted-by":"publisher","first-page":"1583","DOI":"10.1038\/s41380-019-0365-9","article-title":"Deep neural networks in psychiatry","volume":"24","author":"Durstewitz","year":"2019","journal-title":"Mol. Psychiatry"},{"key":"ref14","doi-asserted-by":"publisher","first-page":"1013","DOI":"10.1109\/ICASSP.1999.759875","article-title":"Size matters: an empirical study of neural network training for large vocabulary continuous speech recognition","author":"Ellis","year":"1999","journal-title":"IEEE"},{"key":"ref15","doi-asserted-by":"publisher","first-page":"14487","DOI":"10.1007\/s00521-022-07263-9","article-title":"Two-stage deep learning model for Alzheimer\u2019s disease detection and prediction of the mild cognitive impairment time","volume":"34","author":"El-Sappagh","year":"2022","journal-title":"Neural Comput. Applic."},{"key":"ref16","doi-asserted-by":"publisher","first-page":"57","DOI":"10.1016\/S0014-5793(97)00483-3","article-title":"Phosphorylation of microtubule-associated protein tau by stress-activated protein kinases","volume":"409","author":"Goedert","year":"1997","journal-title":"FEBS Lett."},{"key":"ref17","doi-asserted-by":"publisher","first-page":"e15004","DOI":"10.1038\/npre.2010.4538.1","article-title":"Aptamer-based multiplexed proteomic technology for biomarker discovery","volume":"5","author":"Gold","year":"2010","journal-title":"Nat. Prec."},{"key":"ref18","doi-asserted-by":"publisher","first-page":"4163","DOI":"10.1038\/s41598-018-37149-7","article-title":"A blood-based signature of cerebrospinal fluid A\u03b21\u201342 status","volume":"9","author":"Goudey","year":"2019","journal-title":"Sci. Rep."},{"key":"ref19","doi-asserted-by":"publisher","first-page":"388","DOI":"10.1016\/S1474-4422(15)70016-5","article-title":"Neuroinflammation in Alzheimer\u2019s disease","volume":"14","author":"Heneka","year":"2015","journal-title":"Lancet Neurol."},{"key":"ref20","doi-asserted-by":"publisher","first-page":"3042","DOI":"10.1093\/brain\/awl279","article-title":"Proteome-based plasma biomarkers for Alzheimer\u2019s disease","volume":"129","author":"Hye","year":"2006","journal-title":"Brain"},{"key":"ref21","doi-asserted-by":"publisher","first-page":"207","DOI":"10.1016\/S1474-4422(12)70291-0","article-title":"Tracking pathophysiological processes in Alzheimer\u2019s disease: an updated hypothetical model of dynamic biomarkers","volume":"12","author":"Jack","year":"2013","journal-title":"Lancet Neurol."},{"key":"ref22","doi-asserted-by":"publisher","first-page":"88","DOI":"10.1002\/alz.12369","article-title":"Large-scale plasma proteomic profiling identifies a high-performance biomarker panel for Alzheimer\u2019s disease screening and staging","volume":"18","author":"Jiang","year":"2022","journal-title":"Alzheimers Dement."},{"key":"ref23","doi-asserted-by":"publisher","first-page":"1036","DOI":"10.3390\/jcm9093016","article-title":"Accurate blood-based diagnostic biosignatures for Alzheimer\u2019s disease via automated machine learning","volume":"9","author":"Karaglani","year":"2020","journal-title":"J. Clin. Med."},{"key":"ref24","doi-asserted-by":"publisher","first-page":"515","DOI":"10.3233\/JAD-130380","article-title":"Candidate blood proteome markers of Alzheimer\u2019s disease onset and pogression: a systematic review and replication study","volume":"38","author":"Kiddle","year":"2014","journal-title":"J. Alzheimers Dis."},{"key":"ref25","doi-asserted-by":"publisher","first-page":"436","DOI":"10.1038\/nature14539","article-title":"Deep learning","volume":"521","author":"LeCun","year":"2015","journal-title":"Nature"},{"key":"ref26","doi-asserted-by":"publisher","first-page":"765","DOI":"10.1042\/ETLS20210249","article-title":"Applied machine learning in Alzheimer\u2019s disease research: omics, imaging, and clinical data","volume":"5","author":"Li","year":"2021","journal-title":"Emerg. Topics Life Sci."},{"key":"ref27","doi-asserted-by":"publisher","first-page":"6914","DOI":"10.3390\/ijms21186914","article-title":"Classifications of neurodegenerative disorders using a multiplex blood biomarkers-based machine learning model","volume":"21","author":"Lin","year":"2020","journal-title":"Int. J. Mol. Sci."},{"key":"ref28","doi-asserted-by":"publisher","first-page":"1946","DOI":"10.1373\/clinchem.2005.053090","article-title":"High-resolution serum proteomic profiling of Alzheimer disease samples reveals disease-specific, carrier-protein\u2013bound mass signatures","volume":"51","author":"Lopez","year":"2005","journal-title":"Clin. Chem."},{"key":"ref29","doi-asserted-by":"publisher","first-page":"519","DOI":"10.1016\/S1471-4914(02)02422-X","article-title":"The possible role of complement activation in Alzheimer disease","volume":"8","author":"McGeer","year":"2002","journal-title":"Trends Mol. Med."},{"key":"ref30","doi-asserted-by":"publisher","first-page":"1797","DOI":"10.1038\/s41591-022-01925-w","article-title":"Plasma p-tau231 and p-tau217 as state markers of amyloid-\u03b2 pathology in preclinical Alzheimer\u2019s disease","volume":"28","author":"Mil\u00e0-Alom\u00e0","year":"2022","journal-title":"Nat. Med."},{"key":"ref31","doi-asserted-by":"publisher","first-page":"52","DOI":"10.1186\/1752-0509-6-52","article-title":"AlzPathway: a comprehensive map of signaling pathways of Alzheimer\u2019s disease","volume":"6","author":"Mizuno","year":"2012","journal-title":"BMC Syst. Biol."},{"key":"ref32","doi-asserted-by":"publisher","first-page":"561","DOI":"10.1016\/j.neuropharm.2009.11.010","article-title":"Targeting p38 MAPK pathway for the treatment of Alzheimer\u2019s disease","volume":"58","author":"Munoz","year":"2010","journal-title":"Neuropharmacology"},{"key":"ref33","doi-asserted-by":"publisher","first-page":"3835","DOI":"10.1091\/mbc.e06-07-0625","article-title":"The amyloid-\u03b2 precursor protein is phosphorylated via distinct pathways during differentiation, mitosis, stress, and degeneration","volume":"18","author":"Muresan","year":"2007","journal-title":"Mol. Biol. Cell"},{"key":"ref34","doi-asserted-by":"publisher","first-page":"83","DOI":"10.1016\/j.dadm.2016.06.004","article-title":"A blood screening test for Alzheimer\u2019s disease","volume":"3","author":"O\u2019Bryant","year":"2016","journal-title":"Alzheimers Dement."},{"key":"ref35","doi-asserted-by":"publisher","first-page":"1240","DOI":"10.1212\/WNL.0000000000001991","article-title":"Detailed comparison of amyloid PET and CSF biomarkers for identifying early Alzheimer disease","volume":"85","author":"Palmqvist","year":"2015","journal-title":"Neurology"},{"key":"ref36","doi-asserted-by":"publisher","first-page":"101690","DOI":"10.1016\/j.pneurobio.2019.101690","article-title":"Prognostic plasma protein panel for A\u03b2 deposition in the brain in Alzheimer\u2019s disease","volume":"183","author":"Park","year":"2019","journal-title":"Prog. Neurobiol."},{"key":"ref37","doi-asserted-by":"publisher","first-page":"96","DOI":"10.1186\/s13195-019-0549-1","article-title":"Plasma A\u03b242\/40 ratio alone or combined with FDG-PET can accurately predict amyloid-PET positivity: a cross-sectional analysis from the AB255 study","volume":"11","author":"P\u00e9rez-Grijalba","year":"2019","journal-title":"Alzheimers Res. Ther."},{"key":"ref38","doi-asserted-by":"publisher","first-page":"1248","DOI":"10.1002\/acn3.50827","article-title":"Key inflammatory pathway activations in the MCI stage of Alzheimer\u2019s disease","volume":"6","author":"Pillai","year":"2019","journal-title":"Ann. Clin. Transl. Neurol."},{"key":"ref39","doi-asserted-by":"publisher","first-page":"1359","DOI":"10.1038\/nm1653","article-title":"Classification and prediction of clinical Alzheimer\u2019s diagnosis based on plasma signaling proteins","volume":"13","author":"Ray","year":"2007","journal-title":"Nat. Med."},{"key":"ref40","doi-asserted-by":"publisher","first-page":"1587","DOI":"10.1046\/j.1471-4159.2000.0741587.x","article-title":"Phosphorylation sites on tau identified by nanoelectrospray mass spectrometry: differences in vitro between the mitogen-activated protein kinases ERK2, c-Jun N-terminal kinase and P38, and glycogen synthase kinase-3\u03b2","volume":"74","author":"Reynolds","year":"2000","journal-title":"J. Neurochem."},{"key":"ref41","doi-asserted-by":"publisher","first-page":"134","DOI":"10.1016\/j.jsbmb.2016.03.012","article-title":"Age, APOE and sex: triad of risk of Alzheimer\u2019s disease","volume":"160","author":"Riedel","year":"2016","journal-title":"J. Steroid Biochem. Mol. Biol."},{"key":"ref42","doi-asserted-by":"publisher","first-page":"724","DOI":"10.1016\/j.jalz.2013.09.016","article-title":"Alzheimer\u2019s disease biomarker discovery using SOMAscan multiplexed protein technology","volume":"10","author":"Sattlecker","year":"2014","journal-title":"Alzheimers Dement."},{"key":"ref43","doi-asserted-by":"publisher","first-page":"3479","DOI":"10.1021\/acschemneuro.9b00095","article-title":"Potential value of plasma amyloid-\u03b2, total tau, and neurofilament light for identification of early Alzheimer\u2019s disease","volume":"10","author":"Shi","year":"2019","journal-title":"ACS Chem. Nerosci."},{"key":"ref44","doi-asserted-by":"publisher","first-page":"1478","DOI":"10.1016\/j.jalz.2019.06.4951","article-title":"Discovery and validation of plasma proteomic biomarkers relating to brain amyloid burden by SOMAscan assay","volume":"15","author":"Shi","year":"2019","journal-title":"Alzheimers Dement."},{"key":"ref45","doi-asserted-by":"publisher","first-page":"1452","DOI":"10.1002\/alz.12322","article-title":"Replication study of plasma proteins relating to Alzheimer\u2019s pathology","volume":"17","author":"Shi","year":"2021","journal-title":"Alzheimers Dement."},{"key":"ref46","doi-asserted-by":"publisher","first-page":"933","DOI":"10.1016\/j.trci.2019.11.001","article-title":"A metabolite-based machine learning approach to diagnose Alzheimer-type dementia in blood: results from the European medical\u2009information framework for Alzheimer disease biomarker discovery cohort","volume":"5","author":"Stamate","year":"2019","journal-title":"Alzheimers Dement."},{"key":"ref47","doi-asserted-by":"publisher","first-page":"652","DOI":"10.1212\/01.WNL.0000046581.81650.D0","article-title":"CSF A\u03b2 42 levels correlate with amyloid-neuropathology in a population-based autopsy study","volume":"60","author":"Strozyk","year":"2003","journal-title":"Neurology"},{"key":"ref48","doi-asserted-by":"publisher","first-page":"739","DOI":"10.1001\/archgenpsychiatry.2010.78","article-title":"Association of plasma clusterin concentration with severity, pathology, and progression in Alzheimer disease","volume":"67","author":"Thambisetty","year":"2010","journal-title":"Arch. Gen. Psychiatry"},{"key":"ref49","doi-asserted-by":"publisher","first-page":"3254","DOI":"10.1038\/s41598-020-74399-w","article-title":"Multimodal deep learning models for early detection of Alzheimer\u2019s disease stage","volume":"11","author":"Venugopalan","year":"2021","journal-title":"Sci. Rep."},{"key":"ref50","doi-asserted-by":"publisher","first-page":"947","DOI":"10.3233\/JAD-150020","article-title":"Blood protein markers of neocortical amyloid-\u03b2 burden: a candidate study using SOMAscan technology","volume":"46","author":"Voyle","year":"2015","journal-title":"J. Alzheimers Dis."},{"key":"ref51","author":"Wei","year":"2022"},{"key":"ref52","doi-asserted-by":"publisher","first-page":"213","DOI":"10.3233\/JAD-190434","article-title":"Validation of plasma proteomic biomarkers relating to brain amyloid burden in the EMIF-Alzheimer\u2019s disease multimodal biomarker discovery cohort","volume":"74","author":"Westwood","year":"2020","journal-title":"J. Alzheimers Dis."},{"key":"ref53","doi-asserted-by":"publisher","first-page":"169","DOI":"10.1186\/s40478-019-0795-2","article-title":"Multiplex proteomics identifies novel CSF and plasma biomarkers of early Alzheimer\u2019s disease","volume":"7","author":"Whelan","year":"2019","journal-title":"Acta Neuropathol. Commun."},{"key":"ref54","doi-asserted-by":"publisher","first-page":"15","DOI":"10.1373\/jalm.2019.029595","article-title":"A machine learning approach to identify a circulating microRNA signature for Alzheimer disease","volume":"5","author":"Zhao","year":"2020","journal-title":"J. Appl. Lab. Med."},{"key":"ref55","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1038\/s41467-019-09234-6","article-title":"Metascape provides a biologist-oriented resource for the analysis of systems-level datasets","volume":"10","author":"Zhou","year":"2019","journal-title":"Nat. Commun."}],"container-title":["Frontiers in Aging Neuroscience"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fnagi.2022.1040001\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,11,29]],"date-time":"2022-11-29T15:29:55Z","timestamp":1669735795000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fnagi.2022.1040001\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,11,29]]},"references-count":55,"alternative-id":["10.3389\/fnagi.2022.1040001"],"URL":"https:\/\/doi.org\/10.3389\/fnagi.2022.1040001","relation":{},"ISSN":["1663-4365"],"issn-type":[{"value":"1663-4365","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,11,29]]},"article-number":"1040001"}}