{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,28]],"date-time":"2026-01-28T20:25:11Z","timestamp":1769631911230,"version":"3.49.0"},"publisher-location":"Cham","reference-count":34,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783030676698","type":"print"},{"value":"9783030676704","type":"electronic"}],"license":[{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2021]]},"DOI":"10.1007\/978-3-030-67670-4_12","type":"book-chapter","created":{"date-parts":[[2021,2,24]],"date-time":"2021-02-24T17:04:13Z","timestamp":1614186253000},"page":"187-203","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":10,"title":["Automated Integration of Genomic Metadata with Sequence-to-Sequence Models"],"prefix":"10.1007","author":[{"given":"Giuseppe","family":"Cannizzaro","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Michele","family":"Leone","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Anna","family":"Bernasconi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Arif","family":"Canakoglu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mark J.","family":"Carman","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2021,2,25]]},"reference":[{"key":"12_CR1","unstructured":"Abadi, M., Agarwal, A., Barham, P., et al.: Tensorflow: Large-scale machine learning on heterogeneous distributed systems. arXiv preprint arXiv:1603.04467 (2016)"},{"issue":"D1","key":"12_CR2","doi-asserted-by":"publisher","first-page":"D991","DOI":"10.1093\/nar\/gks1193","volume":"41","author":"T Barrett","year":"2012","unstructured":"Barrett, T., Wilhite, S.E., Ledoux, P., et al.: NCBI GEO: archive for functional genomics data sets-update. Nucleic Acids Res. 41(D1), D991\u2013D995 (2012)","journal-title":"Nucleic Acids Res."},{"key":"12_CR3","doi-asserted-by":"publisher","unstructured":"Bernasconi, A., Canakoglu, A., Masseroli, M., et al.: META-BASE: a novel architecture for large-scale genomic metadata integration. IEEE\/ACM Trans. Comput. Biol. Bioinform. https:\/\/doi.org\/10.1109\/TCBB.2020.2998954","DOI":"10.1109\/TCBB.2020.2998954"},{"issue":"1","key":"12_CR4","doi-asserted-by":"publisher","first-page":"30","DOI":"10.1093\/bib\/bbaa080","volume":"22","author":"A Bernasconi","year":"2021","unstructured":"Bernasconi, A., Canakoglu, A., Masseroli, M., et al.: The road towards data integration in human genomics: players, steps and interactions. Briefings in Bioinform. 22(1), 30\u201344 (2021). https:\/\/doi.org\/10.1093\/bib\/bbaa080","journal-title":"Briefings in Bioinform."},{"key":"12_CR5","doi-asserted-by":"publisher","unstructured":"Bernasconi, A., Ceri, S., Campi, A., Masseroli, M.: Conceptual modeling for genomics: building an integrated repository of open data. In: Mayr, H.C., Guizzardi, G., Ma, H., Pastor, O. (eds.) ER 2017. LNCS, vol. 10650, pp. 325\u2013339. Springer, Cham (2017). https:\/\/doi.org\/10.1007\/978-3-319-69904-2_26","DOI":"10.1007\/978-3-319-69904-2_26"},{"key":"12_CR6","doi-asserted-by":"crossref","unstructured":"Bodenreider, O.: Biomedical ontologies in action: role in knowledge management, data integration and decision support. Yearbook of Medical Informatics, p. 67 (2008)","DOI":"10.1055\/s-0038-1638585"},{"key":"12_CR7","doi-asserted-by":"crossref","unstructured":"Canakoglu, A., Bernasconi, A., Colombo, A., et\u00a0al.: GenoSurf: metadata drivensemantic search system for integrated genomic datasets. Database 2019 (2019)","DOI":"10.1093\/database\/baz132"},{"issue":"D1","key":"12_CR8","doi-asserted-by":"publisher","first-page":"D794","DOI":"10.1093\/nar\/gkx1081","volume":"46","author":"CA Davis","year":"2017","unstructured":"Davis, C.A., Hitz, B.C., Sloan, C.A., et al.: The encyclopedia of DNA elements (ENCODE): data portal update. Nucleic Acids Res. 46(D1), D794\u2013D801 (2017)","journal-title":"Nucleic Acids Res."},{"key":"12_CR9","unstructured":"Devlin, J., Chang, M.W., Lee, K., et al.: BERT: Pre-training of deep bidirectional transformers for language understanding. In: Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, vol. 1 (Long and Short Papers), pp. 4171\u20134186 (2019)"},{"issue":"9","key":"12_CR10","doi-asserted-by":"publisher","first-page":"e54","DOI":"10.1093\/nar\/gky102","volume":"46","author":"SE Ellis","year":"2018","unstructured":"Ellis, S.E., Collado-Torres, L., Jaffe, A., et al.: Improving the value of public RNA-seq expression data by phenotype prediction. Nucleic Acids Res. 46(9), e54\u2013e54 (2018)","journal-title":"Nucleic Acids Res."},{"issue":"1","key":"12_CR11","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1038\/s41598-020-57716-1","volume":"10","author":"E Galeota","year":"2020","unstructured":"Galeota, E., Kishore, K., Pelizzola, M.: Ontology-driven integrative analysis of omics data through onassis. Sci. Rep. 10(1), 1\u20139 (2020)","journal-title":"Sci. Rep."},{"issue":"14","key":"12_CR12","doi-asserted-by":"publisher","first-page":"509","DOI":"10.1186\/s12859-017-1888-1","volume":"18","author":"CB Giles","year":"2017","unstructured":"Giles, C.B., Brown, C.A., Ripperger, M., et al.: ALE: automated label extraction from GEO metadata. BMC Bioinform. 18(14), 509 (2017)","journal-title":"BMC Bioinform."},{"issue":"24","key":"12_CR13","doi-asserted-by":"crossref","first-page":"4038","DOI":"10.1093\/bioinformatics\/btv503","volume":"31","author":"Z Guo","year":"2015","unstructured":"Guo, Z., Tzvetkova, B., Bassik, J.M., et al.: RNASeqMetaDB: a database and web server for navigating metadata of publicly available mouse RNA-Seq datasets. Bioinformatics 31(24), 4038\u20134040 (2015)","journal-title":"Bioinformatics"},{"key":"12_CR14","doi-asserted-by":"publisher","first-page":"170125","DOI":"10.1038\/sdata.2017.125","volume":"4","author":"D Hadley","year":"2017","unstructured":"Hadley, D., Pan, J., El-Sayed, O., et al.: Precision annotation of digital samples in NCBI\u2019s Gene Expression Omnibus. Sci. Data 4, 170125 (2017)","journal-title":"Sci. Data"},{"key":"12_CR15","doi-asserted-by":"crossref","unstructured":"Hong, E.L., Sloan, C.A., Chan, E.T., et\u00a0al.: Principles of metadata organization at the ENCODE data coordination center. Database 2016 (2016)","DOI":"10.1093\/database\/baw001"},{"issue":"1","key":"12_CR16","doi-asserted-by":"publisher","first-page":"132","DOI":"10.1093\/bib\/bbv024","volume":"17","author":"CC Huang","year":"2016","unstructured":"Huang, C.C., Lu, Z.: Community challenges in biomedical text mining over 10 years: success, failure and the future. Briefings Bioinform. 17(1), 132\u2013144 (2016)","journal-title":"Briefings Bioinform."},{"key":"12_CR17","unstructured":"Kans, J.: Entrez direct: E-utilities on the unix command line. In: Entrez Programming Utilities Help [Internet]. National Center for Biotechnology Information (US) (2020)"},{"issue":"7539","key":"12_CR18","doi-asserted-by":"publisher","first-page":"317","DOI":"10.1038\/nature14248","volume":"518","author":"A Kundaje","year":"2015","unstructured":"Kundaje, A., Meuleman, W., Ernst, J., et al.: Integrative analysis of 111 reference human epigenomes. Nature 518(7539), 317 (2015)","journal-title":"Nature"},{"key":"12_CR19","doi-asserted-by":"crossref","unstructured":"Li, J., Tseng, C.S., Federico, A., et\u00a0al.: SFMetaDB: a comprehensive annotation of mouse RNA splicing factor RNA-Seq datasets. Database 2017 (2017)","DOI":"10.1093\/database\/bax071"},{"key":"12_CR20","doi-asserted-by":"crossref","unstructured":"Li, Z., Li, J., Yu, P.: GEOMetaCuration: a web-based application for accurate manual curation of Gene Expression Omnibus metadata. Database J. Biol. Databases Curation 2018 (2018)","DOI":"10.1093\/database\/bay019"},{"key":"12_CR21","unstructured":"Liu, Y., Ott, M., Goyal, N., et al.: RoBERTa: a robustly optimized bert pretraining approach. arXiv preprint arXiv:1907.11692 (2019)"},{"issue":"6","key":"12_CR22","doi-asserted-by":"publisher","first-page":"580","DOI":"10.1038\/ng.2653","volume":"45","author":"J Lonsdale","year":"2013","unstructured":"Lonsdale, J., Thomas, J., Salvatore, M., et al.: The genotype-tissue expression (GTEx) project. Nat. Genet. 45(6), 580 (2013)","journal-title":"Nat. Genet."},{"key":"12_CR23","doi-asserted-by":"crossref","unstructured":"Luong, T., Pham, H., Manning, C.D.: Effective approaches to attention-based neural machine translation. In: Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing, pp. 1412\u20131421 (2015)","DOI":"10.18653\/v1\/D15-1166"},{"key":"12_CR24","doi-asserted-by":"crossref","unstructured":"Musen, M.A., Sansone, S.A., Cheung, K.H., et al.: CEDAR: semantic web technology to support open science. In: Companion Proceedings of the The Web Conference 2018, pp. 427\u2013428. International World Wide Web Conferences Steering Committee (2018)","DOI":"10.1145\/3184558.3186200"},{"key":"12_CR25","doi-asserted-by":"crossref","unstructured":"Posch, L., Panahiazar, M., Dumontier, M., et\u00a0al.: Predicting structured metadata from unstructured metadata. Database 2016 (2016)","DOI":"10.1093\/database\/baw097"},{"issue":"8","key":"12_CR26","first-page":"9","volume":"1","author":"A Radford","year":"2019","unstructured":"Radford, A., Wu, J., Child, R., et al.: Language models are unsupervised multitask learners. OpenAI Blog. 1(8), 9 (2019)","journal-title":"OpenAI Blog."},{"issue":"7571","key":"12_CR27","doi-asserted-by":"publisher","first-page":"68","DOI":"10.1038\/nature15393","volume":"526","author":"Genomes Project Consortium","year":"2015","unstructured":"Genomes Project Consortium: A global reference for human genetic variation. Nature 526(7571), 68 (2015)","journal-title":"Nature"},{"key":"12_CR28","unstructured":"Vaswani, A., Shazeer, N., Parmar, N., et al.: Attention is all you need. In: Advances in Neural Information Processing Systems, pp. 5998\u20136008 (2017)"},{"issue":"1","key":"12_CR29","doi-asserted-by":"publisher","first-page":"103","DOI":"10.1007\/s12551-018-0490-8","volume":"11","author":"Z Wang","year":"2019","unstructured":"Wang, Z., Lachmann, A., Ma\u2019ayan, A.: Mining data and metadata from the Gene Expression Omnibus. Biophys. Rev. 11(1), 103\u2013110 (2019)","journal-title":"Biophys. Rev."},{"issue":"1","key":"12_CR30","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1038\/s41467-024-52768-7","volume":"7","author":"Z Wang","year":"2016","unstructured":"Wang, Z., Monteiro, C.D., Jagodnik, K.M., et al.: Extraction and analysis of signatures from the Gene Expression Omnibus by the crowd. Nature Commun. 7(1), 1\u201311 (2016)","journal-title":"Nature Commun."},{"issue":"10","key":"12_CR31","doi-asserted-by":"publisher","first-page":"1113","DOI":"10.1038\/ng.2764","volume":"45","author":"JN Weinstein","year":"2013","unstructured":"Weinstein, J.N., Collisson, E.A., Mills, G.B., et al.: The cancer genome atlas pan-cancer analysis project. Nat. Genet. 45(10), 1113 (2013)","journal-title":"Nat. Genet."},{"issue":"1","key":"12_CR32","doi-asserted-by":"publisher","first-page":"98","DOI":"10.15346\/hc.v6i1.6","volume":"6","author":"A Zaveri","year":"2019","unstructured":"Zaveri, A., Hu, W., Dumontier, M.: MetaCrowd: crowdsourcing biomedical metadata quality assessment. Hum. Comput. 6(1), 98\u2013112 (2019)","journal-title":"Hum. Comput."},{"issue":"D1","key":"12_CR33","doi-asserted-by":"publisher","first-page":"D729","DOI":"10.1093\/nar\/gky1094","volume":"47","author":"R Zheng","year":"2018","unstructured":"Zheng, R., Wan, C., Mei, S., et al.: Cistrome Data Browser: expanded datasets and new tools for gene regulatory analysis. Nucleic Acids Res. 47(D1), D729\u2013D735 (2018)","journal-title":"Nucleic Acids Res."},{"issue":"23","key":"12_CR34","doi-asserted-by":"publisher","first-page":"2798","DOI":"10.1093\/bioinformatics\/btn520","volume":"24","author":"Y Zhu","year":"2008","unstructured":"Zhu, Y., Davis, S., Stephens, R., et al.: GEOmetadb: powerful alternative search engine for the Gene Expression Omnibus. Bioinformatics 24(23), 2798\u20132800 (2008)","journal-title":"Bioinformatics"}],"container-title":["Lecture Notes in Computer Science","Machine Learning and Knowledge Discovery in Databases. Applied Data Science and Demo Track"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-67670-4_12","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,2,23]],"date-time":"2025-02-23T23:07:36Z","timestamp":1740352056000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-67670-4_12"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"ISBN":["9783030676698","9783030676704"],"references-count":34,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-67670-4_12","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021]]},"assertion":[{"value":"25 February 2021","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ECML PKDD","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Joint European Conference on Machine Learning and Knowledge Discovery in Databases","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Ghent","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Belgium","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2020","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"14 September 2020","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"18 September 2020","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"ecml2020","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/ecmlpkdd2020.net\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Double-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"EasyChair","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"945","order":3,"name":"number_of_submissions_sent_for_review","label":"Number of Submissions Sent for Review","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"195","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"0","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"21% - The value is computed by the equation \"Number of Full Papers Accepted \/ Number of Submissions Sent for Review * 100\" and then rounded to a whole number.","order":6,"name":"acceptance_rate_of_full_papers","label":"Acceptance Rate of Full Papers","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"4,5","order":7,"name":"average_number_of_reviews_per_paper","label":"Average Number of Reviews per Paper","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"4,4","order":8,"name":"average_number_of_papers_per_reviewer","label":"Average Number of Papers per Reviewer","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"No","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"The conference took place virtually due to the COVID-19 pandemic","order":10,"name":"additional_info_on_review_process","label":"Additional Info on Review Process","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}