{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,8]],"date-time":"2026-08-08T00:35:15Z","timestamp":1786149315540,"version":"3.56.0"},"reference-count":131,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2025,6,20]],"date-time":"2025-06-20T00:00:00Z","timestamp":1750377600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0"},{"start":{"date-parts":[[2025,6,20]],"date-time":"2025-06-20T00:00:00Z","timestamp":1750377600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["npj Digit. Med."],"DOI":"10.1038\/s41746-025-01749-1","type":"journal-article","created":{"date-parts":[[2025,6,20]],"date-time":"2025-06-20T13:20:21Z","timestamp":1750425621000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":36,"title":["Few shot learning for phenotype-driven diagnosis of patients with rare genetic diseases"],"prefix":"10.1038","volume":"8","author":[{"given":"Emily","family":"Alsentzer","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Michelle M.","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shilpa N.","family":"Kobren","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ayush","family":"Noori","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"name":"Undiagnosed Diseases Network","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Isaac S.","family":"Kohane","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Marinka","family":"Zitnik","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2025,6,20]]},"reference":[{"key":"1749_CR1","doi-asserted-by":"publisher","first-page":"241","DOI":"10.1038\/s41591-021-01657-3","volume":"28","author":"HL Rehm","year":"2022","unstructured":"Rehm, H. L. Time to make rare disease diagnosis accessible to all. Nat. Med. 28, 241\u2013242 (2022).","journal-title":"Nat. Med."},{"key":"1749_CR2","doi-asserted-by":"crossref","unstructured":"Haendel, M. et al. How many rare diseases are there? Nat. Rev. Drug Discov. 19, 77\u201378 (2020).","DOI":"10.1038\/d41573-019-00180-y"},{"key":"1749_CR3","doi-asserted-by":"crossref","unstructured":"Nguengang Wakap, S. et al. Estimating cumulative point prevalence of rare diseases: analysis of the Orphanet database. Eur. J. Hum. Genet. 28, 165\u2013173 (2020).","DOI":"10.1038\/s41431-019-0508-0"},{"key":"1749_CR4","doi-asserted-by":"crossref","unstructured":"Whicher, D., Philbin, S. & Aronson, N. An overview of the impact of rare disease characteristics on research methodology. Orphanet J. Rare Dis. 13, 14 (2018).","DOI":"10.1186\/s13023-017-0755-5"},{"key":"1749_CR5","doi-asserted-by":"crossref","unstructured":"Gahl, W. A. et al. The NIH undiagnosed diseases program: insights into rare diseases. Genet. Med. 14, 51\u201359 (2012).","DOI":"10.1038\/gim.0b013e318232a005"},{"key":"1749_CR6","unstructured":"Chong, J. X. et al. The genetic basis of Mendelian phenotypes: discoveries, challenges, and opportunities. Am. J. Hum. Genet. 97, 199\u2013215 (2015)."},{"key":"1749_CR7","doi-asserted-by":"publisher","first-page":"W446","DOI":"10.1093\/nar\/gkab266","volume":"49","author":"R Steinhaus","year":"2021","unstructured":"Steinhaus, R. et al. MutationTaster2021. Nucleic Acids Res. 49, W446 (2021).","journal-title":"Nucleic Acids Res."},{"key":"1749_CR8","doi-asserted-by":"publisher","first-page":"D886","DOI":"10.1093\/nar\/gky1016","volume":"47","author":"P Rentzsch","year":"2019","unstructured":"Rentzsch, P., Witten, D., Cooper, G. M., Shendure, J. & Kircher, M. CADD: predicting the deleteriousness of variants throughout the human genome. Nucleic Acids Res. 47, D886\u2013D894 (2019).","journal-title":"Nucleic Acids Res."},{"key":"1749_CR9","doi-asserted-by":"publisher","first-page":"1581","DOI":"10.1038\/ng.3703","volume":"48","author":"KA Jagadeesh","year":"2016","unstructured":"Jagadeesh, K. A. et al. M-CAP eliminates a majority of variants of uncertain significance in clinical exomes at high sensitivity. Nat. Genet. 48, 1581\u20131586 (2016).","journal-title":"Nat. Genet."},{"key":"1749_CR10","doi-asserted-by":"publisher","first-page":"60","DOI":"10.1038\/s41591-018-0279-0","volume":"25","author":"Y Gurovich","year":"2019","unstructured":"Gurovich, Y. et al. Identifying facial phenotypes of genetic disorders using deep learning. Nat. Med. 25, 60\u201364 (2019).","journal-title":"Nat. Med."},{"key":"1749_CR11","doi-asserted-by":"publisher","first-page":"349","DOI":"10.1038\/s41588-021-01010-x","volume":"54","author":"T-C Hsieh","year":"2022","unstructured":"Hsieh, T.-C. et al. GestaltMatcher facilitates rare disease matching using facial phenotype descriptors. Nat. Genet. 54, 349\u2013357 (2022).","journal-title":"Nat. Genet."},{"key":"1749_CR12","doi-asserted-by":"publisher","first-page":"2807","DOI":"10.1038\/s41436-019-0566-2","volume":"21","author":"T-C Hsieh","year":"2019","unstructured":"Hsieh, T.-C. et al. PEDIA: prioritization of exome data by image analysis. Genet. Med. 21, 2807\u20132814 (2019).","journal-title":"Genet. Med."},{"key":"1749_CR13","doi-asserted-by":"publisher","first-page":"864092","DOI":"10.3389\/fgene.2022.864092","volume":"13","author":"D Duong","year":"2022","unstructured":"Duong, D. et al. Neural networks for classification and image generation of aging in genetic syndromes. Front. Genet. 13, 864092 (2022).","journal-title":"Front. Genet."},{"key":"1749_CR14","doi-asserted-by":"publisher","DOI":"10.1186\/s13023-021-01979-y","volume":"16","author":"D Hong","year":"2021","unstructured":"Hong, D. et al. Genetic syndromes screening by facial recognition technology: VGG-16 screening model construction and evaluation. Orphanet J. Rare Dis. 16, 344 (2021).","journal-title":"Orphanet J. Rare Dis."},{"key":"1749_CR15","doi-asserted-by":"crossref","unstructured":"Shukla, P., Gupta, T., Saini, A., Singh, P. & Balasubramanian, R. A deep learning framework for recognizing developmental disorders. In 2017 IEEE Winter Conference on Applications of Computer Vision (WACV) 705\u2013714 (IEEE, 2017).","DOI":"10.1109\/WACV.2017.84"},{"key":"1749_CR16","doi-asserted-by":"crossref","unstructured":"Jagadeesh, K. A. et al. Phrank measures phenotype sets similarity to greatly improve Mendelian diagnostic disease prioritization. Genet. Med. 21, 464\u2013470 (2019).","DOI":"10.1038\/s41436-018-0072-y"},{"key":"1749_CR17","doi-asserted-by":"publisher","first-page":"841","DOI":"10.1038\/nmeth.3484","volume":"12","author":"H Yang","year":"2015","unstructured":"Yang, H., Robinson, P. N. & Wang, K. Phenolyzer: phenotype-based prioritization of candidate genes for human diseases. Nat. Methods 12, 841\u2013843 (2015).","journal-title":"Nat. Methods"},{"key":"1749_CR18","doi-asserted-by":"publisher","first-page":"457","DOI":"10.1016\/j.ajhg.2009.09.003","volume":"85","author":"S K\u00f6hler","year":"2009","unstructured":"K\u00f6hler, S. et al. Clinical diagnostics in human genetics with semantic similarity searches in ontologies. Am. J. Hum. Genet. 85, 457\u2013464 (2009).","journal-title":"Am. J. Hum. Genet."},{"key":"1749_CR19","doi-asserted-by":"crossref","unstructured":"Peng, C. et al. CADA: phenotype-driven gene prioritization based on a case-enriched knowledge graph. NAR Genom. Bioinform. 3, lqab078 (2021).","DOI":"10.1093\/nargab\/lqab078"},{"key":"1749_CR20","doi-asserted-by":"publisher","DOI":"10.1186\/s12920-018-0372-8","volume":"11","author":"A Rao","year":"2018","unstructured":"Rao, A. et al. Phenotype-driven gene prioritization for rare diseases using graph convolution on heterogeneous networks. BMC Med. Genom. 11, 57 (2018).","journal-title":"BMC Med. Genom."},{"key":"1749_CR21","doi-asserted-by":"publisher","first-page":"403","DOI":"10.1016\/j.ajhg.2020.06.021","volume":"107","author":"PN Robinson","year":"2020","unstructured":"Robinson, P. N. et al. Interpretable clinical genomics with a likelihood ratio paradigm. Am. J. Hum. Genet. 107, 403\u2013417 (2020).","journal-title":"Am. J. Hum. Genet."},{"key":"1749_CR22","doi-asserted-by":"publisher","first-page":"935","DOI":"10.1038\/nmeth.3046","volume":"11","author":"A Javed","year":"2014","unstructured":"Javed, A., Agrawal, S. & Ng, P. C. Phen-Gen: combining phenotype and genotype to analyze rare disorders. Nat. Methods 11, 935\u2013937 (2014).","journal-title":"Nat. Methods"},{"key":"1749_CR23","doi-asserted-by":"publisher","first-page":"AIoa2300009","DOI":"10.1056\/AIoa2300009","volume":"1","author":"D Mao","year":"2024","unstructured":"Mao, D. et al. AI-MARRVEL - a knowledge-driven AI system for diagnosing Mendelian disorders. NEJM AI 1, AIoa2300009 (2024).","journal-title":"NEJM AI"},{"key":"1749_CR24","doi-asserted-by":"crossref","unstructured":"Smedley, D. et al. Next-generation diagnostics and disease-gene discovery with the exomiser. Nat. Protoc. 10, 2004\u20132015 (2015).","DOI":"10.1038\/nprot.2015.124"},{"key":"1749_CR25","doi-asserted-by":"publisher","first-page":"2126","DOI":"10.1038\/s41436-019-0439-8","volume":"21","author":"Q Li","year":"2019","unstructured":"Li, Q., Zhao, K., Bustamante, C. D., Ma, X. & Wong, W. H. Xrare: a machine learning method jointly modeling phenotypes and genetic evidence for rare disease diagnosis. Genet. Med. 21, 2126\u20132134 (2019).","journal-title":"Genet. Med."},{"key":"1749_CR26","doi-asserted-by":"publisher","first-page":"eaau9113","DOI":"10.1126\/scitranslmed.aau9113","volume":"12","author":"J Birgmeier","year":"2020","unstructured":"Birgmeier, J. et al. AMELIE speeds Mendelian diagnosis by matching patient phenotype and genotype to primary literature. Sci. Transl. Med. 12, eaau9113 (2020).","journal-title":"Sci. Transl. Med."},{"key":"1749_CR27","doi-asserted-by":"publisher","first-page":"1984","DOI":"10.1038\/s41436-021-01238-2","volume":"23","author":"B Yoo","year":"2021","unstructured":"Yoo, B., Birgmeier, J., Bernstein, J. A. & Bejerano, G. InpherNet accelerates monogenic disease diagnosis using patients\u2019 candidate genes\u2019 neighbors. Genet. Med. 23, 1984\u20131992 (2021).","journal-title":"Genet. Med."},{"key":"1749_CR28","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-019-13345-5","volume":"10","author":"D Anderson","year":"2019","unstructured":"Anderson, D., Baynam, G., Blackwell, J. M. & Lassmann, T. Personalised analytics for rare disease diagnostics. Nat. Commun. 10, 5274 (2019).","journal-title":"Nat. Commun."},{"key":"1749_CR29","doi-asserted-by":"crossref","unstructured":"Splinter, K. et al. Effect of genetic diagnosis on patients with previously undiagnosed disease. N. Engl. J. Med. 379, 2131\u20132139 (2018).","DOI":"10.1056\/NEJMoa1714458"},{"key":"1749_CR30","doi-asserted-by":"crossref","unstructured":"The 100,000 Genomes Project Pilot Investigators et al. 100,000 genomes pilot on rare-disease diagnosis in health care - preliminary report. N. Engl. J. Med. 385, 1868\u20131880 (2021).","DOI":"10.1056\/NEJMoa2035790"},{"key":"1749_CR31","doi-asserted-by":"crossref","unstructured":"Topol, E. J. High-performance medicine: the convergence of human and artificial intelligence. Nat. Med. 25, 44\u201356. (2019).","DOI":"10.1038\/s41591-018-0300-7"},{"key":"1749_CR32","doi-asserted-by":"crossref","unstructured":"Yu, K.-H., Beam, A. L. & Kohane, I. S. Artificial intelligence in healthcare. Nat. Biomed. Eng. 2, 719\u2013731. (2018).","DOI":"10.1038\/s41551-018-0305-z"},{"key":"1749_CR33","doi-asserted-by":"crossref","unstructured":"Liu, Y. et al. A deep learning system for differential diagnosis of skin diseases. Nat. Med. 26, 900\u2013908 (2020).","DOI":"10.1038\/s41591-020-0842-3"},{"key":"1749_CR34","doi-asserted-by":"crossref","unstructured":"Saldanha, O. L. et al. Swarm learning for decentralized artificial intelligence in cancer histopathology. Nat. Med. 28, 1232\u20131239 (2022).","DOI":"10.1038\/s41591-022-01768-5"},{"key":"1749_CR35","unstructured":"Bulten, W. et al. Artificial intelligence for diagnosis and Gleason grading of prostate cancer: the PANDA challenge. Nat. Med. 28, 154\u2013163 (2022)."},{"key":"1749_CR36","doi-asserted-by":"crossref","unstructured":"Ribeiro, A. H. et al. Automatic diagnosis of the 12-lead ECG using a deep neural network. Nat. Commun. 11, 1760 (2020).","DOI":"10.1038\/s41467-020-15432-4"},{"key":"1749_CR37","doi-asserted-by":"crossref","unstructured":"Tang, A. S. et al. Deep phenotyping of Alzheimer\u2019s disease leveraging electronic medical records identifies sex-specific clinical associations. Nat. Commun. 13, 675 (2022).","DOI":"10.1038\/s41467-022-28273-0"},{"key":"1749_CR38","unstructured":"Qiu, S. et al. Multimodal deep learning for Alzheimer\u2019s disease dementia assessment. Nat. Commun. 13, 3404 (2022)."},{"key":"1749_CR39","doi-asserted-by":"crossref","unstructured":"Tschandl, P. et al. Human-computer collaboration for skin cancer recognition. Nat. Med. 26, 1229\u20131234 (2020).","DOI":"10.1038\/s41591-020-0942-0"},{"key":"1749_CR40","doi-asserted-by":"crossref","unstructured":"De Fauw, J. et al. Clinically applicable deep learning for diagnosis and referral in retinal disease. Nat. Med. 24, 1342\u20131350 (2018).","DOI":"10.1038\/s41591-018-0107-6"},{"key":"1749_CR41","doi-asserted-by":"crossref","unstructured":"Gulshan, V. et al. Development and validation of a deep learning algorithm for detection of diabetic retinopathy in retinal fundus photographs. JAMA 316, 2402\u20132410 (2016).","DOI":"10.1001\/jama.2016.17216"},{"key":"1749_CR42","doi-asserted-by":"crossref","unstructured":"Esteva, A. et al. Dermatologist-level classification of skin cancer with deep neural networks. Nature 542, 115\u2013118 (2017).","DOI":"10.1038\/nature21056"},{"key":"1749_CR43","doi-asserted-by":"crossref","unstructured":"Liang, H. et al. Evaluation and accurate diagnoses of pediatric diseases using artificial intelligence. Nat. Med. 25, 433\u2013438 (2019).","DOI":"10.1038\/s41591-018-0335-9"},{"key":"1749_CR44","doi-asserted-by":"publisher","DOI":"10.1186\/s12859-019-2633-8","volume":"20","author":"I Boudellioua","year":"2019","unstructured":"Boudellioua, I., Kulmanov, M., Schofield, P. N., Gkoutos, G. V. & Hoehndorf, R. DeepPVP: phenotype-based prioritization of causative variants using deep learning. BMC Bioinformatics 20, 65 (2019).","journal-title":"BMC Bioinformatics"},{"key":"1749_CR45","doi-asserted-by":"publisher","first-page":"1134","DOI":"10.1038\/s41591-024-02855-5","volume":"30","author":"D Van Veen","year":"2024","unstructured":"Van Veen, D. et al. Adapted large language models can outperform medical experts in clinical text summarization. Nat. Med. 30, 1134\u20131142 (2024).","journal-title":"Nat. Med."},{"key":"1749_CR46","doi-asserted-by":"crossref","unstructured":"Wan, P. et al. Outpatient reception via collaboration between nurses and a large language model: a randomized controlled trial. Nat. Med. 30, 1\u20138 (2024).","DOI":"10.1038\/s41591-024-03148-7"},{"key":"1749_CR47","doi-asserted-by":"publisher","unstructured":"Reese, J. T. et al. Systematic benchmarking demonstrates large language models have not reached the diagnostic accuracy of traditional rare-disease decision support tools. Preprint at medRxiv https:\/\/doi.org\/10.1101\/2024.07.22.24310816 (2024).","DOI":"10.1101\/2024.07.22.24310816"},{"key":"1749_CR48","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-023-41980-6","volume":"14","author":"E Alsentzer","year":"2023","unstructured":"Alsentzer, E. et al. Simulation of undiagnosed patients with novel genetic conditions. Nat. Commun. 14, 6403 (2023).","journal-title":"Nat. Commun."},{"key":"1749_CR49","unstructured":"Ramoni, R. B. et al. The undiagnosed diseases network: accelerating discovery about health and disease. Am. J. Hum. Genet. 100, 185\u2013192 (2017)."},{"key":"1749_CR50","doi-asserted-by":"publisher","first-page":"1075","DOI":"10.1038\/s41436-020-01084-8","volume":"23","author":"SN Kobren","year":"2021","unstructured":"Kobren, S. N. et al. Commonalities across computational workflows for uncovering explanatory variants in undiagnosed cases. Genet. Med. 23, 1075\u20131085 (2021).","journal-title":"Genet. Med."},{"key":"1749_CR51","doi-asserted-by":"crossref","unstructured":"Zemojtel, T. et al. Effective diagnosis of genetic disease by computational phenotype analysis of the disease-associated genome. Sci. Transl. Med. 6, 252ra123 (2014).","DOI":"10.1126\/scitranslmed.3009262"},{"key":"1749_CR52","doi-asserted-by":"crossref","unstructured":"Chen, R. J., Lu, M. Y., Chen, T. Y., Williamson, D. F. K. & Mahmood, F. Synthetic data in machine learning for medicine and healthcare. Nat. Biomed. Eng. 5, 493\u2013497 (2021).","DOI":"10.1038\/s41551-021-00751-8"},{"key":"1749_CR53","unstructured":"Genomics, U. o. W. C. f. M. MyGene2. https:\/\/mygene2.org\/MyGene2\/."},{"key":"1749_CR54","doi-asserted-by":"publisher","first-page":"702","DOI":"10.1111\/j.1469-8749.2011.04032.x","volume":"53","author":"HV Firth","year":"2011","unstructured":"Firth, H. V. & Wright, C. F. The deciphering developmental disorders (DDD) study. Dev. Med. Child Neurol. 53, 702\u2013703 (2011).","journal-title":"Dev. Med. Child Neurol."},{"key":"1749_CR55","unstructured":"Dubey, A. et al. The llama 3 herd of models. Preprint at arXiv:2407.21783 (2024)."},{"key":"1749_CR56","doi-asserted-by":"crossref","unstructured":"Wicks, P. et al. Sharing health data for better outcomes on patientslikeme. J. Med. Internet Res. 12, e19. (2010).","DOI":"10.2196\/jmir.1549"},{"key":"1749_CR57","doi-asserted-by":"crossref","unstructured":"Gerarduzzi, C. et al. Silencing SMOC2 ameliorates kidney fibrosis by inhibiting fibroblast to myofibroblast transformation. JCI Insight 2, e90299 (2017).","DOI":"10.1172\/jci.insight.90299"},{"key":"1749_CR58","doi-asserted-by":"crossref","unstructured":"Morkmued, S. et al. Deficiency of the SMOC2 matricellular protein impairs bone healing and produces age-dependent bone loss. Sci. Rep.10, 14817 (2020).","DOI":"10.1038\/s41598-020-71749-6"},{"key":"1749_CR59","doi-asserted-by":"crossref","unstructured":"Romio, L. et al. OFD1, the gene mutated in oral-facial-digital syndrome type 1, is expressed in the metanephros and in human embryonic renal mesenchymal cells. J. Am. Soc. Nephrol. 14, 680\u2013689. (2003).","DOI":"10.1097\/01.ASN.0000054497.48394.D2"},{"key":"1749_CR60","doi-asserted-by":"crossref","unstructured":"Saal, S. et al. Renal insufficiency, a frequent complication with age in oral-facial-digital syndrome type I. Clin. Genet. 77, 258\u2013265 (2010).","DOI":"10.1111\/j.1399-0004.2009.01290.x"},{"key":"1749_CR61","doi-asserted-by":"crossref","unstructured":"Ganapathi, M. et al. A homozygous splice variant in atp5po, disrupts mitochondrial complex v function and causes leigh syndrome in two unrelated families. J. Inherit. Metab. Dis. 45, 996\u20131012 (2022).","DOI":"10.1002\/jimd.12526"},{"key":"1749_CR62","doi-asserted-by":"crossref","unstructured":"Chen, H., Morris, M. A., Rossier, C., Blouin, J.-L. & Antonarakis, S. E. Cloning of the cDNA for the human ATP synthase OSCP subunit (ATP50) by exon trapping and mapping to chromosome 21q22. 1-q22. 2. Genomics 28, 470\u2013476 (1995).","DOI":"10.1006\/geno.1995.1176"},{"key":"1749_CR63","doi-asserted-by":"crossref","unstructured":"Aggeler, R. et al. A functionally active human F1F0 ATPase can be purified by immunocapture from heart tissue and fibroblast cell lines: subunit structure and activity studies. J. Biol. Chem. 277, 33906\u201333912 (2002).","DOI":"10.1074\/jbc.M204538200"},{"key":"1749_CR64","doi-asserted-by":"crossref","unstructured":"Brautigam, C. A., Wynn, R. M., Chuang, J. L. & Chuang, D. T. Subunit and catalytic component stoichiometries of an in vitro reconstituted human pyruvate dehydrogenase complex. J. Biol. Chem. 284, 13086\u201313098 (2009).","DOI":"10.1074\/jbc.M806563200"},{"key":"1749_CR65","doi-asserted-by":"crossref","unstructured":"Jiang, Y. et al. Component co-expression and purification of recombinant human pyruvate dehydrogenase complex from baculovirus infected SF9 cells. Protein Expr. Purif. 97, 9\u201316 (2014).","DOI":"10.1016\/j.pep.2014.02.002"},{"key":"1749_CR66","doi-asserted-by":"crossref","unstructured":"Glasgow, R. I. et al. Novel GFM2 variants associated with early-onset neurological presentations of mitochondrial disease and impaired expression of oxphos subunits. Neurogenetics 18, 227\u2013235 (2017).","DOI":"10.1007\/s10048-017-0526-4"},{"key":"1749_CR67","doi-asserted-by":"crossref","unstructured":"Warde-Farley, D. et al. The genemania prediction server: biological network integration for gene prioritization and predicting gene function. Nucleic Acids Res. 38, W214\u2013W220 (2010).","DOI":"10.1093\/nar\/gkq537"},{"key":"1749_CR68","doi-asserted-by":"crossref","unstructured":"Franz, M. et al. GeneMANIA update 2018. Nucleic Acids Res. 46, W60\u2013W64 (2018).","DOI":"10.1093\/nar\/gky311"},{"key":"1749_CR69","doi-asserted-by":"publisher","first-page":"3629","DOI":"10.1093\/nar\/gki678","volume":"33","author":"I Ispolatov","year":"2005","unstructured":"Ispolatov, I., Yuryev, A., Mazo, I. & Maslov, S. Binding properties and evolution of homodimers in protein\u2013protein interaction networks. Nucleic Acids Res. 33, 3629\u20133635 (2005).","journal-title":"Nucleic Acids Res."},{"key":"1749_CR70","doi-asserted-by":"publisher","first-page":"4884","DOI":"10.1021\/acs.chemrev.5b00683","volume":"116","author":"O Keskin","year":"2016","unstructured":"Keskin, O., Tuncbag, N. & Gursoy, A. Predicting protein\u2013protein interactions from the molecular to the proteome level. Chem. Rev. 116, 4884\u20134909 (2016).","journal-title":"Chem. Rev."},{"key":"1749_CR71","doi-asserted-by":"publisher","first-page":"4426","DOI":"10.1073\/pnas.1818013116","volume":"116","author":"M Zitnik","year":"2019","unstructured":"Zitnik, M., Sosi\u010d, R., Feldman, M. W. & Leskovec, J. Evolution of resilience in protein interactomes across the tree of life. Proc. Natl Acad. Sci. USA 116, 4426\u20134433 (2019).","journal-title":"Proc. Natl Acad. Sci. USA"},{"key":"1749_CR72","doi-asserted-by":"crossref","unstructured":"Westermarck, J., Ivaska, J. & Corthals, G. L. Identification of protein interactions involved in cellular signaling. Mol. Cell. Proteomics 12, 1752\u20131763 (2013).","DOI":"10.1074\/mcp.R113.027771"},{"key":"1749_CR73","doi-asserted-by":"crossref","unstructured":"Luck, K. et al. A reference map of the human binary protein interactome. Nature 580, 402\u2013408 (2020).","DOI":"10.1038\/s41586-020-2188-x"},{"key":"1749_CR74","doi-asserted-by":"crossref","unstructured":"Tyler, A. L., Asselbergs, F. W., Williams, S. M. & Moore, J. H. Shadows of complexity: what biological networks reveal about epistasis and pleiotropy. Bioessays 31, 220\u2013227 (2009).","DOI":"10.1002\/bies.200800022"},{"key":"1749_CR75","doi-asserted-by":"crossref","unstructured":"Hu, J. X., Thomas, C. E. & Brunak, S. Network biology concepts in complex disease comorbidities. Nat. Rev. Genet. 17, 615\u2013629 (2016).","DOI":"10.1038\/nrg.2016.87"},{"key":"1749_CR76","doi-asserted-by":"crossref","unstructured":"Ried, J. S. et al. PSEA: phenotype set enrichment analysis\u2013a new method for analysis of multiple phenotypes. Genet. Epidemiol. 36, 244\u2013252 (2012).","DOI":"10.1002\/gepi.21617"},{"key":"1749_CR77","doi-asserted-by":"crossref","unstructured":"Li, J., Cairns, B. J., Li, J. & Zhu, T. Generating synthetic mixed-type longitudinal electronic health records for artificial intelligent applications. npj Digit. Med. 6, 98 (2021).","DOI":"10.21203\/rs.3.rs-1258744\/v1"},{"key":"1749_CR78","doi-asserted-by":"crossref","unstructured":"Mahmood, F. et al. Deep adversarial training for multi-organ nuclei segmentation in histopathology images. IEEE Trans. Med. Imag. 39, 3257\u20133267 (2020).","DOI":"10.1109\/TMI.2019.2927182"},{"key":"1749_CR79","doi-asserted-by":"crossref","unstructured":"Waheed, A. et al. CovidGAN: data augmentation using auxiliary classifier GAN for improved Covid-19 detection. IEEE Access 8, 91916\u201391923 (2020).","DOI":"10.1109\/ACCESS.2020.2994762"},{"key":"1749_CR80","doi-asserted-by":"crossref","unstructured":"Jaipuria, N. et al. Deflating dataset bias using synthetic data augmentation. In 2020 IEEE\/CVF Conference on Computer Vision and Pattern Recognition Workshops CVPRW (IEEE, 2020).","DOI":"10.1109\/CVPRW50498.2020.00394"},{"key":"1749_CR81","doi-asserted-by":"crossref","unstructured":"Frid-Adar, M., Klang, E., Amitai, M., Goldberger, J. & Greenspan, H. Synthetic data augmentation using GAN for improved liver lesion classification. In 2018 IEEE 15th International Symposium on Biomedical Imaging (ISBI) (IEEE, 2018).","DOI":"10.1109\/ISBI.2018.8363576"},{"key":"1749_CR82","doi-asserted-by":"crossref","unstructured":"Oprisanu, B., Ganev, G. & De Cristofaro, E. On utility and privacy in synthetic genomic data. In Proceedings of the 29th Network and Distributed System Security Symposium (NDSS, 2022).","DOI":"10.14722\/ndss.2022.24092"},{"key":"1749_CR83","doi-asserted-by":"crossref","unstructured":"Wang, Z., Myles, P. & Tucker, A. Generating and evaluating cross-sectional synthetic electronic healthcare data: preserving data utility and patient privacy. Comput. Intell. 37, 819\u2013851 (2021).","DOI":"10.1111\/coin.12427"},{"key":"1749_CR84","unstructured":"Wang, J. et al. MARRVEL: integration of human and model organism genetic resources to facilitate functional annotation of the human genome. Am. Jo. Hum. Genet. 100, 843\u2013853 (2017)."},{"key":"1749_CR85","doi-asserted-by":"publisher","first-page":"2190","DOI":"10.1016\/j.ajhg.2024.08.010","volume":"111","author":"J Kim","year":"2024","unstructured":"Kim, J., Wang, K., Weng, C. & Liu, C. Assessing the utility of large language models for phenotype-driven gene prioritization in the diagnosis of rare genetic disease. Am. J. Hum. Genet. 111, 2190\u20132202 (2024). Publisher: Elsevier.","journal-title":"Am. J. Hum. Genet."},{"key":"1749_CR86","unstructured":"Soman, K. et al. Zebra-Llama: a context-aware large language model for democratizing rare disease knowledge. Preprint at http:\/\/arxiv.org\/abs\/2411.02657 (2024)."},{"key":"1749_CR87","doi-asserted-by":"publisher","first-page":"1819","DOI":"10.1016\/j.ajhg.2024.07.011","volume":"111","author":"KA Flaharty","year":"2024","unstructured":"Flaharty, K. A. et al. Evaluating large language models on medical, lay-language, and self-reported descriptions of genetic conditions. Am. J. Hum. Genet. 111, 1819\u20131833 (2024).","journal-title":"Am. J. Hum. Genet."},{"key":"1749_CR88","doi-asserted-by":"publisher","DOI":"10.1038\/s41597-023-01960-3","volume":"10","author":"P Chandak","year":"2023","unstructured":"Chandak, P., Huang, K. & Zitnik, M. Building a knowledge graph to enable precision medicine. Sci. Data 10, 67 (2023).","journal-title":"Sci. Data"},{"key":"1749_CR89","doi-asserted-by":"crossref","unstructured":"Marwaha, S., Knowles, J. W. & Ashley, E. A. A guide for the diagnosis of rare and undiagnosed disease: beyond the exome. Genome Med. 14, 23 (2022).","DOI":"10.1186\/s13073-022-01026-w"},{"key":"1749_CR90","doi-asserted-by":"crossref","unstructured":"Consortium, G. O. The gene ontology resource: 20 years and still going strong. Nucleic Acids Res. 47, D330\u2013D338 (2019).","DOI":"10.1093\/nar\/gky1055"},{"key":"1749_CR91","unstructured":"Jassal, B. et al. The reactome pathway knowledgebase. Nucleic Acids Res. 48, D498\u2013D503 (2020)."},{"key":"1749_CR92","doi-asserted-by":"crossref","unstructured":"Pi\u00f1ero, J. et al. The DisGeNET knowledge platform for disease genomics: 2019 update. Nucleic Acids Research (2020).","DOI":"10.1093\/nar\/gkz1021"},{"key":"1749_CR93","unstructured":"Maglott, D., Ostell, J., Pruitt, K. D. & Tatusova, T. Entrez gene: gene-centered information at ncbi. Nucleic Acids Res. 48, D845\u2013D855 (2005)."},{"key":"1749_CR94","unstructured":"K\u00f6hler, S. et al. Expansion of the human phenotype ontology (HPO) knowledge base and resources. Nucleic Acids Res. 47, D1018\u2013D1027 (2019)."},{"key":"1749_CR95","unstructured":"Vasilevsky, N. et al. Mondo disease ontology: harmonizing disease concepts across the world. In CEUR-WS (2020)."},{"key":"1749_CR96","doi-asserted-by":"crossref","unstructured":"Pavan, S. et al. Clinical practice guidelines for rare diseases: the orphanet database. PLoS ONE 12, e0170365 (2017).","DOI":"10.1371\/journal.pone.0170365"},{"key":"1749_CR97","doi-asserted-by":"crossref","unstructured":"Asikainen, A., I\u00f1iguez, G., Ure\u00f1a-Carri\u00f3n, J., Kaski, K. & Kivel\u00e4, M. Cumulative effects of triadic closure and homophily in social networks. Sci. Adv. 6, eaax7310 (2020).","DOI":"10.1126\/sciadv.aax7310"},{"key":"1749_CR98","doi-asserted-by":"crossref","unstructured":"Kov\u00e1cs, I. A. et al. Network-based prediction of protein interactions. Nat. Commun. 10, 1240 (2019).","DOI":"10.1038\/s41467-019-09177-y"},{"key":"1749_CR99","doi-asserted-by":"crossref","unstructured":"Gahl, W. A., Wise, A. L. & Ashley, E. A. The undiagnosed diseases network of the national institutes of health: a national extension. JAMA 314, 1797\u20131798 (2015).","DOI":"10.1001\/jama.2015.12249"},{"key":"1749_CR100","doi-asserted-by":"crossref","unstructured":"Girdea, M. et al. Phenotips: patient phenotyping software for clinical and research use. Hum. Mutat. 34, 1057\u20131065 (2013).","DOI":"10.1002\/humu.22347"},{"key":"1749_CR101","doi-asserted-by":"crossref","unstructured":"Richards, S. et al. Standards and guidelines for the interpretation of sequence variants: a joint consensus recommendation of the American College of Medical Genetics and Genomics and the Association for Molecular Pathology. Genet. Med. 17, 405\u2013424 (2015).","DOI":"10.1038\/gim.2015.30"},{"key":"1749_CR102","unstructured":"UDN manual of operations. https:\/\/undiagnosed.hms.harvard.edu\/research\/udn-manual-of-operations\/ (2022)."},{"key":"1749_CR103","doi-asserted-by":"crossref","unstructured":"Robinson, P. N. et al. Improved exome prioritization of disease genes through cross-species phenotype comparison. Genome Res. 24, 340\u2013348 (2014).","DOI":"10.1101\/gr.160325.113"},{"key":"1749_CR104","doi-asserted-by":"crossref","unstructured":"Hamosh, A. et al. Online Mendelian inheritance in man (OMIM), a knowledgebase of human genes and genetic disorders. Nucleic Acids Res. 33, D514\u2013D517 (2002).","DOI":"10.1093\/nar\/gki033"},{"key":"1749_CR105","unstructured":"Philippakis, A. A. et al. The Matchmaker exchange: a platform for rare disease gene discovery. Hum. Mutat. 36, 915\u2013921 (2015)."},{"key":"1749_CR106","unstructured":"Brody, S., Alon, U. & Yahav, E. How attentive are graph attention networks? ICLR (2022)."},{"key":"1749_CR107","unstructured":"Yang, B., Yih, W.-t., He, X., Gao, J. & Deng, L. Embedding entities and relations for learning and inference in knowledge bases. ICLR (2015)."},{"key":"1749_CR108","unstructured":"Glorot, X. & Bengio, Y. Understanding the difficulty of training deep feedforward neural networks. J. Mach. Learn. Res. 9, 249\u2013256 (2010)."},{"key":"1749_CR109","doi-asserted-by":"crossref","unstructured":"Huang, K. et al. A foundation model for clinician-centered drug repurposing. Nat. Med. 30, 3601\u20133613 (2024).","DOI":"10.1038\/s41591-024-03233-x"},{"key":"1749_CR110","doi-asserted-by":"crossref","unstructured":"Zolotareva, O. & Kleine, M. A survey of gene prioritization tools for mendelian and complex human diseases. J. Integr. Bioinform. 16, 20180069 (2019).","DOI":"10.1515\/jib-2018-0069"},{"key":"1749_CR111","doi-asserted-by":"crossref","unstructured":"Wang, X., Han, X., Huang, W., Dong, D. & Scott, M. R. Multi-similarity loss with general pair weighting for deep metric learning. In 2019 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) 5017\u20135025 (2019).","DOI":"10.1109\/CVPR.2019.00516"},{"key":"1749_CR112","unstructured":"Goldberger, J., Hinton, G. E., Roweis, S. & Salakhutdinov, R. R. Neighbourhood components analysis. In Proc. 18th International Conference on Neural Information Processing Systems 513\u2013520 (MIT Press, 2004)."},{"key":"1749_CR113","doi-asserted-by":"crossref","unstructured":"Zhao, Z.-Q., Zheng, P., Xu, S.-t. & Wu, X. Object detection with deep learning: a review. IEEE Trans. Neural Netw. Learn. Syst. 3212\u20133232 (IEEE, 2019).","DOI":"10.1109\/TNNLS.2018.2876865"},{"key":"1749_CR114","unstructured":"Ba, J. L., Kiros, J. R. & Hinton, G. E. Layer normalization. NeurIPS (2016)."},{"key":"1749_CR115","unstructured":"Loffe, S. & Szegedy, C. Batch normalization: Accelerating deep network training by reducing internal covariate shift. In International conference on machine learning, 448\u2013456 (2015)."},{"key":"1749_CR116","unstructured":"Biewald, L. Experiment tracking with weights and biases (2020)."},{"key":"1749_CR117","unstructured":"Paszke, A. et al. Pytorch: an imperative style, high-performance deep learning library. In 33rd Conference on Neural Information Processing Systems (NeurIPS) (2019)."},{"key":"1749_CR118","unstructured":"Falcon, W. & The PyTorch Lightning team. PyTorch lightning https:\/\/github.com\/PyTorchLightning\/pytorch-lightning (2019)."},{"key":"1749_CR119","unstructured":"Fey, M. & Lenssen, J. E. Fast graph representation learning with PyTorch Geometric. In ICLR Workshop on Representation Learning on Graphs and Manifolds (2019)."},{"key":"1749_CR120","unstructured":"Abid, A. et al. Gradio: hassle-free sharing and testing of ML models in the wild. In 2019 ICML Workshop on Human in the Loop Learning (2019)."},{"key":"1749_CR121","doi-asserted-by":"publisher","first-page":"2010","DOI":"10.1002\/humu.24459","volume":"43","author":"E Tosco-Herrera","year":"2022","unstructured":"Tosco-Herrera, E. et al. Evaluation of a whole-exome sequencing pipeline and benchmarking of causal germline variant prioritizers. Hum. Mutat. 43, 2010\u20132020 (2022).","journal-title":"Hum. Mutat."},{"key":"1749_CR122","doi-asserted-by":"crossref","unstructured":"McInnes, L., Healy, J., Saul, N. & Gro\u00dfberger, L. Umap: Uniform manifold approximation and projection. J. Open Source Softw. 3, 861 (2018).","DOI":"10.21105\/joss.00861"},{"key":"1749_CR123","unstructured":"McInnes, L. Outlier detection using UMAP \u2013 umap 0.5 documentation https:\/\/umap-learn.readthedocs.io\/en\/latest\/outliers.html (2018)."},{"key":"1749_CR124","doi-asserted-by":"crossref","unstructured":"Bastian, M., Heymann, S. & Jacomy, M. Gephi: an open source software for exploring and manipulating networks. In Proc. International AAAI Conference on Web and Social Media 361\u2013362 (2009).","DOI":"10.1609\/icwsm.v3i1.13937"},{"key":"1749_CR125","doi-asserted-by":"crossref","unstructured":"Aken, B. L. et al. The Ensembl gene annotation system. Database 2016, baw093 (2016).","DOI":"10.1093\/database\/baw093"},{"key":"1749_CR126","doi-asserted-by":"crossref","unstructured":"Menche, J. et al. Uncovering disease-disease relationships through the incomplete interactome. Science 347, 1257601(2015).","DOI":"10.1126\/science.1257601"},{"key":"1749_CR127","doi-asserted-by":"crossref","unstructured":"Oughtred, R. et al. The biogrid database: a comprehensive biomedical resource of curated protein, genetic, and chemical interactions. Protein Sci. 30, 187\u2013200 (2021).","DOI":"10.1002\/pro.3978"},{"key":"1749_CR128","doi-asserted-by":"crossref","unstructured":"Szklarczyk, D. et al. The string database in 2021: customizable protein\u2013protein networks, and functional characterization of user-uploaded gene\/measurement sets. Nucleic Acids Res. 49, D605\u2013D612 (2021).","DOI":"10.1093\/nar\/gkaa1074"},{"key":"1749_CR129","unstructured":"Noori, A. Created in BioRender. https:\/\/BioRender.com\/zkbpoj9 (2025)."},{"key":"1749_CR130","unstructured":"Noori, A. Created in BioRender. https:\/\/BioRender.com\/26t5d3v (2025)."},{"key":"1749_CR131","unstructured":"Noori, A. Created in BioRender. https:\/\/BioRender.com\/z7vfgnl (2025)."}],"container-title":["npj Digital Medicine"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.nature.com\/articles\/s41746-025-01749-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41746-025-01749-1","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41746-025-01749-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,20]],"date-time":"2025-06-20T13:20:37Z","timestamp":1750425637000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.nature.com\/articles\/s41746-025-01749-1"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6,20]]},"references-count":131,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2025,12]]}},"alternative-id":["1749"],"URL":"https:\/\/doi.org\/10.1038\/s41746-025-01749-1","relation":{"has-preprint":[{"id-type":"doi","id":"10.1101\/2022.12.07.22283238","asserted-by":"object"}]},"ISSN":["2398-6352"],"issn-type":[{"value":"2398-6352","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,6,20]]},"assertion":[{"value":"12 December 2024","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"26 May 2025","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"20 June 2025","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":"380"}}