{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,11,16]],"date-time":"2026-11-16T19:07:18Z","timestamp":1794856038606,"version":"4.9.1"},"reference-count":41,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2022,10,21]],"date-time":"2022-10-21T00:00:00Z","timestamp":1666310400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2022,10,21]],"date-time":"2022-10-21T00:00:00Z","timestamp":1666310400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"name":"Complutense University of Madrid and Banco Santander","award":["CT63\/19-CT64\/19"],"award-info":[{"award-number":["CT63\/19-CT64\/19"]}]},{"name":"Technical University Munich \u2013 Institute for Advanced Study, funded by the German Excellence Initiative"},{"DOI":"10.13039\/501100004587","name":"Instituto de Salud Carlos III","doi-asserted-by":"publisher","award":["INT20\/00079"],"award-info":[{"award-number":["INT20\/00079"]}],"id":[{"id":"10.13039\/501100004587","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004837","name":"Ministerio de Ciencia e Innovaci\u00f3n","doi-asserted-by":"publisher","award":["PID2019-110866RB-I00"],"award-info":[{"award-number":["PID2019-110866RB-I00"]}],"id":[{"id":"10.13039\/501100004837","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Sci Rep"],"abstract":"<jats:title>Abstract<\/jats:title><jats:p>Alzheimer's disease (AD) is a neurodegenerative disease whose molecular mechanisms are activated several years before cognitive symptoms appear. Genotype-based prediction of the phenotype is thus a key challenge for the early diagnosis of AD. Machine learning techniques that have been proposed to address this challenge do not consider known biological interactions between the genes used as input features, thus neglecting important information about the disease mechanisms at play. To mitigate this, we first extracted AD subnetworks from several protein\u2013protein interaction (PPI) databases and labeled these with genotype information (number of missense variants) to make them patient-specific. Next, we trained Graph Neural Networks (GNNs) on the patient-specific networks for phenotype prediction. We tested different PPI databases and compared the performance of the GNN models to baseline models using classical machine learning techniques, as well as randomized networks and input datasets. The overall results showed that GNNs could not outperform a baseline predictor only using the APOE gene, suggesting that missense variants are not sufficient to explain disease risk beyond the APOE status. Nevertheless, our results show that GNNs outperformed other machine learning techniques and that protein\u2013protein interactions lead to superior results compared to randomized networks. These findings highlight that gene interactions are a valuable source of information in predicting disease status.<\/jats:p>","DOI":"10.1038\/s41598-022-21491-y","type":"journal-article","created":{"date-parts":[[2022,10,21]],"date-time":"2022-10-21T10:03:36Z","timestamp":1666346616000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":35,"title":["On the limits of graph neural networks for the early diagnosis of Alzheimer\u2019s disease"],"prefix":"10.1038","volume":"12","author":[{"given":"Laura","family":"Hern\u00e1ndez-Lorenzo","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Markus","family":"Hoffmann","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Evelyn","family":"Scheibling","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Markus","family":"List","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jordi A.","family":"Mat\u00edas-Guiu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jose L.","family":"Ayala","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2022,10,21]]},"reference":[{"key":"21491_CR1","doi-asserted-by":"crossref","first-page":"327","DOI":"10.1002\/alz.12328","volume":"17","author":"J Wiley","year":"2021","unstructured":"Wiley, J. Alzheimer\u2019s disease facts and figures. Alzheimers Dement. 17, 327\u2013406 (2021).","journal-title":"Alzheimers Dement."},{"key":"21491_CR2","doi-asserted-by":"publisher","first-page":"613","DOI":"10.4088\/JCP.v68n0419","volume":"68","author":"KD Coon","year":"2007","unstructured":"Coon, K. D. et al. A high-density whole-genome association study reveals that APOE is the major susceptibility gene for sporadic late-onset Alzheimer\u2019s disease. J. Clin. Psychiatry 68, 613\u2013618 (2007).","journal-title":"J. Clin. Psychiatry"},{"key":"21491_CR3","doi-asserted-by":"publisher","first-page":"1347","DOI":"10.1016\/j.neuron.2013.12.003","volume":"80","author":"CR Jack Jr","year":"2013","unstructured":"Jack, C. R. Jr. & Holtzman, D. M. Biomarker modeling of Alzheimer\u2019s disease. Neuron 80, 1347\u20131358 (2013).","journal-title":"Neuron"},{"key":"21491_CR4","doi-asserted-by":"publisher","first-page":"177","DOI":"10.1016\/j.copbio.2020.02.005","volume":"63","author":"A Yadav","year":"2020","unstructured":"Yadav, A., Vidal, M. & Luck, K. Precision medicine: Networks to the rescue. Curr. Opin. Biotechnol. 63, 177\u2013189 (2020).","journal-title":"Curr. Opin. Biotechnol."},{"key":"21491_CR5","doi-asserted-by":"publisher","first-page":"e1002820","DOI":"10.1371\/journal.pcbi.1002820","volume":"8","author":"D-Y Cho","year":"2012","unstructured":"Cho, D.-Y., Kim, Y.-A. & Przytycka, T. M. Network biology approach to complex diseases. PLoS Comput. Biol. 8, e1002820 (2012).","journal-title":"PLoS Comput. Biol."},{"key":"21491_CR6","doi-asserted-by":"publisher","DOI":"10.1002\/wsbm.1443","volume":"11","author":"E Capriotti","year":"2019","unstructured":"Capriotti, E., Ozturk, K. & Carter, H. Integrating molecular networks with genetic variant interpretation for precision medicine. Wiley Interdiscip. Rev. Syst. Biol. Med. 11, e1443 (2019).","journal-title":"Wiley Interdiscip. Rev. Syst. Biol. Med."},{"key":"21491_CR7","doi-asserted-by":"publisher","first-page":"73","DOI":"10.1159\/000073735","volume":"56","author":"JH Moore","year":"2003","unstructured":"Moore, J. H. The ubiquitous nature of epistasis in determining susceptibility to common human diseases. Hum. Hered. 56, 73\u201382 (2003).","journal-title":"Hum. Hered."},{"key":"21491_CR8","doi-asserted-by":"publisher","first-page":"1217","DOI":"10.1002\/humu.23272","volume":"38","author":"S Laksshman","year":"2017","unstructured":"Laksshman, S., Bhat, R. R., Viswanath, V. & Li, X. DeepBipolar: Identifying genomic mutations for bipolar disorder via deep learning. Hum. Mutat. 38, 1217\u20131224 (2017).","journal-title":"Hum. Mutat."},{"key":"21491_CR9","first-page":"011","volume":"2","author":"D Raimondi","year":"2020","unstructured":"Raimondi, D. et al. An interpretable low-complexity machine learning framework for robust exome-based in-silico diagnosis of Crohn\u2019s disease patients. NAR Genom. Bioinform. 2, 011 (2020).","journal-title":"NAR Genom. Bioinform."},{"key":"21491_CR10","doi-asserted-by":"publisher","first-page":"3173","DOI":"10.1093\/bioinformatics\/btx408","volume":"33","author":"M Hess","year":"2017","unstructured":"Hess, M., Lenz, S., Bl\u00e4tte, T. J., Bullinger, L. & Binder, H. Partitioned learning of deep Boltzmann machines for SNP data. Bioinformatics 33, 3173\u20133180 (2017).","journal-title":"Bioinformatics"},{"key":"21491_CR11","doi-asserted-by":"publisher","first-page":"1515","DOI":"10.1093\/bib\/bbaa257","volume":"22","author":"G Muzio","year":"2021","unstructured":"Muzio, G., O\u2019Bray, L. & Borgwardt, K. Biological network analysis with deep learning. Brief. Bioinform. 22, 1515\u20131530 (2021).","journal-title":"Brief. Bioinform."},{"key":"21491_CR12","first-page":"1","volume":"33","author":"J You","year":"2020","unstructured":"You, J., Ying, R. & Leskovec, J. Design space for graph neural networks. Adv. Neural Inf. Process. Syst. 33, 1\u201310 (2020).","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"21491_CR13","first-page":"D845","volume":"48","author":"J Pi\u00f1ero","year":"2019","unstructured":"Pi\u00f1ero, J. et al. The DisGeNET knowledge platform for disease genomics: 2019 update. Nucleic Acids Res. 48, D845\u2013D855 (2019).","journal-title":"Nucleic Acids Res."},{"key":"21491_CR14","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1186\/s13059-016-0974-4","volume":"17","author":"W McLaren","year":"2016","unstructured":"McLaren, W. et al. The ensembl variant effect predictor. Genome Biol. 17, 1\u201314 (2016).","journal-title":"Genome Biol."},{"key":"21491_CR15","doi-asserted-by":"publisher","first-page":"008","DOI":"10.1093\/gigascience\/giab008","volume":"10","author":"P Danecek","year":"2021","unstructured":"Danecek, P. et al. Twelve years of SAMtools and BCFtools. GigaScience 10, 008 (2021).","journal-title":"GigaScience"},{"key":"21491_CR16","doi-asserted-by":"publisher","first-page":"1398","DOI":"10.1007\/s00259-014-2753-3","volume":"41","author":"S Landau","year":"2014","unstructured":"Landau, S. et al. Amyloid PET imaging in Alzheimer\u2019s disease: A comparison of three radiotracers. Eur. J. Nucl. Med. Mol. Imaging 41, 1398\u20131407 (2014).","journal-title":"Eur. J. Nucl. Med. Mol. Imaging"},{"key":"21491_CR17","doi-asserted-by":"publisher","first-page":"1377","DOI":"10.1212\/WNL.0000000000002576","volume":"86","author":"SM Landau","year":"2016","unstructured":"Landau, S. M. et al. Amyloid negativity in patients with clinically diagnosed Alzheimer disease and MCI. Neurology 86, 1377\u20131385 (2016).","journal-title":"Neurology"},{"key":"21491_CR18","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1186\/s13195-021-00785-9","volume":"13","author":"F Levin","year":"2021","unstructured":"Levin, F. et al. Data-driven FDG-PET subtypes of Alzheimer\u2019s disease-related neurodegeneration. Alzheimers Res. Ther. 13, 1\u201314 (2021).","journal-title":"Alzheimers Res. Ther."},{"key":"21491_CR19","doi-asserted-by":"publisher","DOI":"10.1016\/j.nbd.2020.104976","volume":"143","author":"SM Neuner","year":"2020","unstructured":"Neuner, S. M., Tcw, J. & Goate, A. M. Genetic architecture of Alzheimer\u2019s disease. Neurobiol. Dis. 143, 104976 (2020).","journal-title":"Neurobiol. Dis."},{"key":"21491_CR20","doi-asserted-by":"publisher","first-page":"D607","DOI":"10.1093\/nar\/gky1131","volume":"47","author":"D Szklarczyk","year":"2019","unstructured":"Szklarczyk, D. et al. STRING v11: Protein\u2013protein association networks with increased coverage, supporting functional discovery in genome-wide experimental datasets. Nucleic Acids Res. 47, D607\u2013D613 (2019).","journal-title":"Nucleic Acids Res."},{"key":"21491_CR21","doi-asserted-by":"publisher","first-page":"D529","DOI":"10.1093\/nar\/gky1079","volume":"47","author":"R Oughtred","year":"2018","unstructured":"Oughtred, R. et al. The BioGRID interaction database: 2019 update. Nucleic Acids Res. 47, D529\u2013D541 (2018).","journal-title":"Nucleic Acids Res."},{"key":"21491_CR22","doi-asserted-by":"publisher","first-page":"402","DOI":"10.1038\/s41586-020-2188-x","volume":"580","author":"K Luck","year":"2020","unstructured":"Luck, K. et al. A reference map of the human binary protein interactome. Nature 580, 402\u2013408 (2020).","journal-title":"Nature"},{"key":"21491_CR23","unstructured":"Zitnik, M., Sosi\u010d, R., Maheshwari, S. & Leskovec, J. BioSNAP Datasets: Stanford Biomedical Network Dataset Collection. http:\/\/snap.stanford.edu\/biodata (2018)."},{"key":"21491_CR24","doi-asserted-by":"publisher","first-page":"569","DOI":"10.1038\/ng.3259","volume":"47","author":"CS Greene","year":"2015","unstructured":"Greene, C. S. et al. Understanding multicellular function and disease with human tissue-specific networks. Nat. Genet. 47, 569\u2013576 (2015).","journal-title":"Nat. Genet."},{"key":"21491_CR25","doi-asserted-by":"publisher","first-page":"066","DOI":"10.1093\/bib\/bbab066","volume":"22","author":"O Lazareva","year":"2021","unstructured":"Lazareva, O., Baumbach, J., List, M. & Blumenthal, D. B. On the limits of active module identification. Brief. Bioinform. 22, 066 (2021).","journal-title":"Brief. Bioinform."},{"key":"21491_CR26","first-page":"1","volume":"14","author":"WL Hamilton","year":"2020","unstructured":"Hamilton, W. L. Graph representation learning. Synth. Lect. Artif. Intell. Mach. Learn. 14, 1\u2013159 (2020).","journal-title":"Synth. Lect. Artif. Intell. Mach. Learn."},{"key":"21491_CR27","doi-asserted-by":"publisher","first-page":"1184","DOI":"10.1038\/nprot.2009.97","volume":"4","author":"S Durinck","year":"2009","unstructured":"Durinck, S., Spellman, P. T., Birney, E. & Huber, W. Mapping identifiers for the integration of genomic datasets with the R\/Bioconductor package biomaRt. Nat. Protoc. 4, 1184\u20131191 (2009).","journal-title":"Nat. Protoc."},{"key":"21491_CR28","doi-asserted-by":"publisher","first-page":"2156","DOI":"10.1093\/bioinformatics\/btr330","volume":"27","author":"P Danecek","year":"2011","unstructured":"Danecek, P. et al. The variant call format and VCFtools. Bioinformatics 27, 2156\u20132158 (2011).","journal-title":"Bioinformatics"},{"key":"21491_CR29","doi-asserted-by":"crossref","unstructured":"Hagberg, A. A., Schult, D. A. & Swart, P. J. Exploring Network Structure, Dynamics, and Function using NetworkX. in Proceedings of the 7th Python in Science Conference (eds. Varoquaux, G., Vaught, T. & Millman, J.) 11\u201315 (2008).","DOI":"10.25080\/TCWV9851"},{"key":"21491_CR30","first-page":"2825","volume":"12","author":"F Pedregosa","year":"2011","unstructured":"Pedregosa, F. et al. Scikit-learn: Machine learning in Python. J. Mach. Learn. Res. 12, 2825\u20132830 (2011).","journal-title":"J. Mach. Learn. Res."},{"key":"21491_CR31","doi-asserted-by":"publisher","first-page":"261","DOI":"10.1038\/s41592-019-0686-2","volume":"17","author":"P Virtanen","year":"2020","unstructured":"Virtanen, P. et al. SciPy 1.0: Fundamental algorithms for scientific computing in Python. Nat. Methods 17, 261\u2013272 (2020).","journal-title":"Nat. Methods"},{"key":"21491_CR32","doi-asserted-by":"crossref","first-page":"289","DOI":"10.1111\/j.2517-6161.1995.tb02031.x","volume":"57","author":"Y Benjamini","year":"1995","unstructured":"Benjamini, Y. & Hochberg, Y. Controlling the false discovery rate: A practical and powerful approach to multiple testing. J. R. Stat. Soc. Ser. B 57, 289\u2013300 (1995).","journal-title":"J. R. Stat. Soc. Ser. B"},{"key":"21491_CR33","doi-asserted-by":"publisher","first-page":"221","DOI":"10.1007\/s00401-019-02004-0","volume":"138","author":"P Dourlen","year":"2019","unstructured":"Dourlen, P., Kilinc, D., Malmanche, N., Chapuis, J. & Lambert, J.-C. The new genetic landscape of Alzheimer\u2019s disease: From amyloid cascade to genetically driven synaptic failure hypothesis?. Acta Neuropathol. 138, 221\u2013236 (2019).","journal-title":"Acta Neuropathol."},{"key":"21491_CR34","doi-asserted-by":"publisher","DOI":"10.1002\/alz.055086","volume":"17","author":"JL Whitwell","year":"2021","unstructured":"Whitwell, J. L. et al. Relationship of APOE, age, amyloid and clinical phenotype in Alzheimer disease. Alzheimers Dement. 17, e055086 (2021).","journal-title":"Alzheimers Dement."},{"key":"21491_CR35","doi-asserted-by":"publisher","first-page":"i190","DOI":"10.1093\/bioinformatics\/btx252","volume":"33","author":"M Zitnik","year":"2017","unstructured":"Zitnik, M. & Leskovec, J. Predicting multicellular function through multi-layer tissue networks. Bioinform. Oxf. Engl. 33, i190\u2013i198 (2017).","journal-title":"Bioinform. Oxf. Engl."},{"key":"21491_CR36","doi-asserted-by":"publisher","first-page":"46","DOI":"10.1016\/j.neulet.2017.02.062","volume":"645","author":"MS Lillenes","year":"2017","unstructured":"Lillenes, M. S. et al. Mitochondrial transcription factor A (TFAM) rs1937 and AP endonuclease 1 (APE1) rs1130409 alleles are associated with reduced cognitive performance. Neurosci. Lett. 645, 46\u201352 (2017).","journal-title":"Neurosci. Lett."},{"key":"21491_CR37","doi-asserted-by":"publisher","first-page":"709","DOI":"10.1186\/s12859-019-3158-x","volume":"20","author":"J De Velasco Oriol","year":"2019","unstructured":"De Velasco Oriol, J., Vallejo, E. E., Estrada, K., Tam\u00e9z Pe\u00f1a, J. G., Alzheimer\u2019s Disease Neuroimaging Initiative. Benchmarking machine learning models for late-onset Alzheimer\u2019s disease prediction from genomic data. BMC Bioinform. 20, 709 (2019).","journal-title":"BMC Bioinform."},{"key":"21491_CR38","doi-asserted-by":"publisher","first-page":"2246","DOI":"10.1038\/s41467-019-10101-7","volume":"10","author":"P Li","year":"2019","unstructured":"Li, P. et al. Epigenetic dysregulation of enhancers in neurons is associated with Alzheimer\u2019s disease pathology and cognitive symptoms. Nat. Commun. 10, 2246 (2019).","journal-title":"Nat. Commun."},{"key":"21491_CR39","doi-asserted-by":"publisher","first-page":"D309","DOI":"10.1093\/nar\/gkaa768","volume":"49","author":"Z Louadi","year":"2021","unstructured":"Louadi, Z. et al. DIGGER: Exploring the functional role of alternative splicing in protein interactions. Nucleic Acids Res. 49, D309\u2013D318 (2021).","journal-title":"Nucleic Acids Res."},{"key":"21491_CR40","doi-asserted-by":"publisher","first-page":"124","DOI":"10.1186\/gm561","volume":"6","author":"TF Mackay","year":"2014","unstructured":"Mackay, T. F. & Moore, J. H. Why epistasis is important for tackling complex human disease genetics. Genome Med. 6, 124 (2014).","journal-title":"Genome Med."},{"key":"21491_CR41","doi-asserted-by":"crossref","first-page":"1708","DOI":"10.1093\/bioinformatics\/btaa990","volume":"37","author":"DB Blumenthal","year":"2021","unstructured":"Blumenthal, D. B., Baumbach, J., Hoffmann, M., Kacprowski, T. & List, M. A framework for modeling epistatic interaction. Bioinformatics 37, 1708\u20131716 (2021).","journal-title":"Bioinformatics"}],"container-title":["Scientific Reports"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.nature.com\/articles\/s41598-022-21491-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41598-022-21491-y","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41598-022-21491-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,6]],"date-time":"2024-10-06T08:46:48Z","timestamp":1728204408000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.nature.com\/articles\/s41598-022-21491-y"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,10,21]]},"references-count":41,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2022,12]]}},"alternative-id":["21491"],"URL":"https:\/\/doi.org\/10.1038\/s41598-022-21491-y","relation":{},"ISSN":["2045-2322"],"issn-type":[{"value":"2045-2322","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,10,21]]},"assertion":[{"value":"23 May 2022","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"28 September 2022","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"21 October 2022","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"The authors declare no competing interests.","order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"17632"}}