{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,8]],"date-time":"2026-07-08T07:56:15Z","timestamp":1783497375533,"version":"3.55.0"},"reference-count":28,"publisher":"Oxford University Press (OUP)","issue":"W1","license":[{"start":{"date-parts":[[2019,5,20]],"date-time":"2019-05-20T00:00:00Z","timestamp":1558310400000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/100000051","name":"National Human Genome Research Institute","doi-asserted-by":"publisher","award":["R01LM012895-01"],"award-info":[{"award-number":["R01LM012895-01"]}],"id":[{"id":"10.13039\/100000051","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2019,7,2]]},"abstract":"<jats:title>Abstract<\/jats:title><jats:p>We present Doc2Hpo, an interactive web application that enables interactive and efficient phenotype concept curation from clinical text with automated concept normalization using the Human Phenotype Ontology (HPO). Users can edit the HPO concepts automatically extracted by Doc2Hpo in real time, and export the extracted HPO concepts into gene prioritization tools. Our evaluation showed that Doc2Hpo significantly reduced manual effort while achieving high accuracy in HPO concept curation. Doc2Hpo is freely available at https:\/\/impact2.dbmi.columbia.edu\/doc2hpo\/. The source code is available at https:\/\/github.com\/stormliucong\/doc2hpo for local installation for protected health data.<\/jats:p>","DOI":"10.1093\/nar\/gkz386","type":"journal-article","created":{"date-parts":[[2019,5,1]],"date-time":"2019-05-01T03:20:07Z","timestamp":1556680807000},"page":"W566-W570","source":"Crossref","is-referenced-by-count":74,"title":["Doc2Hpo: a web application for efficient and accurate HPO concept curation"],"prefix":"10.1093","volume":"47","author":[{"given":"Cong","family":"Liu","sequence":"first","affiliation":[{"name":"Department of Biomedical Informatics, Columbia University, New York, NY 10032, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Fabricio Sampaio","family":"Peres\u00a0Kury","sequence":"additional","affiliation":[{"name":"Department of Biomedical Informatics, Columbia University, New York, NY 10032, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ziran","family":"Li","sequence":"additional","affiliation":[{"name":"Department of Biomedical Informatics, Columbia University, New York, NY 10032, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Casey","family":"Ta","sequence":"additional","affiliation":[{"name":"Department of Biomedical Informatics, Columbia University, New York, NY 10032, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kai","family":"Wang","sequence":"additional","affiliation":[{"name":"Center for Cellular and Molecular Therapeutics, Children's Hospital of Philadelphia, Philadelphia, PA 19104, USA"},{"name":"Department of Pathology and Laboratory Medicine, University of Pennsylvania, Philadelphia, PA 19104, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9624-0214","authenticated-orcid":false,"given":"Chunhua","family":"Weng","sequence":"additional","affiliation":[{"name":"Department of Biomedical Informatics, Columbia University, New York, NY 10032, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"286","published-online":{"date-parts":[[2019,5,20]]},"reference":[{"key":"2019062808223894500_B1","doi-asserted-by":"crossref","first-page":"702","DOI":"10.1038\/nrg3932","article-title":"Human genotype-phenotype databases: aims, challenges and opportunities","volume":"16","author":"Brookes","year":"2015","journal-title":"Nat. Rev. Genet."},{"key":"2019062808223894500_B2","doi-asserted-by":"crossref","first-page":"841","DOI":"10.1038\/nmeth.3484","article-title":"Phenolyzer: phenotype-based prioritization of candidate genes for human diseases","volume":"12","author":"Yang","year":"2015","journal-title":"Nat. Methods"},{"key":"2019062808223894500_B3","doi-asserted-by":"crossref","first-page":"457","DOI":"10.1016\/j.ajhg.2009.09.003","article-title":"Clinical diagnostics in human genetics with semantic similarity searches in ontologies","volume":"85","author":"Kohler","year":"2009","journal-title":"Am. J. Hum. Genet."},{"key":"2019062808223894500_B4","doi-asserted-by":"crossref","first-page":"599","DOI":"10.1016\/j.ajhg.2014.03.010","article-title":"Phevor combines multiple biomedical ontologies for accurate identification of disease-causing alleles in single individuals and small nuclear families","volume":"94","author":"Singleton","year":"2014","journal-title":"Am. J. Hum. Genet."},{"key":"2019062808223894500_B5","doi-asserted-by":"crossref","first-page":"340","DOI":"10.1101\/gr.160325.113","article-title":"Improved exome prioritization of disease genes through cross-species phenotype comparison","volume":"24","author":"Robinson","year":"2014","journal-title":"Genome Res."},{"key":"2019062808223894500_B6","doi-asserted-by":"crossref","first-page":"58","DOI":"10.1016\/j.ajhg.2018.05.010","article-title":"Deep phenotyping on electronic health records facilitates genetic diagnosis by clinical exomes","volume":"103","author":"Son","year":"2018","journal-title":"Am. J. Hum. Genet."},{"key":"2019062808223894500_B7","doi-asserted-by":"crossref","first-page":"D1018","DOI":"10.1093\/nar\/gky1105","article-title":"Expansion of the Human Phenotype Ontology (HPO) knowledge base and resources","volume":"47","author":"Kohler","year":"2019","journal-title":"Nucleic Acids Res."},{"key":"2019062808223894500_B8","doi-asserted-by":"crossref","first-page":"287","DOI":"10.1111\/cge.13471","article-title":"Phenotero: Annotate as you write","volume":"95","author":"Hombach","year":"2019","journal-title":"Clin. Genet."},{"key":"2019062808223894500_B9","doi-asserted-by":"crossref","first-page":"bav005","DOI":"10.1093\/database\/bav005","article-title":"Automatic concept recognition using the human phenotype ontology reference and test suite corpora","volume":"2015","author":"Groza","year":"2015","journal-title":"Database"},{"key":"2019062808223894500_B10","doi-asserted-by":"crossref","first-page":"169","DOI":"10.1197\/jamia.M3092","article-title":"A \u201cfundamental theorem\u201d of biomedical informatics","volume":"16","author":"Friedman","year":"2009","journal-title":"J. Am. Med. Inform. Assoc."},{"key":"2019062808223894500_B11","doi-asserted-by":"crossref","first-page":"301","DOI":"10.1006\/jbin.2001.1029","article-title":"A simple algorithm for identifying negated findings and diseases in discharge summaries","volume":"34","author":"Chapman","year":"2001","journal-title":"J. Biomed. Inform."},{"key":"2019062808223894500_B12","doi-asserted-by":"crossref","first-page":"333","DOI":"10.1145\/360825.360855","article-title":"Efficient string matching: an aid to bibliographic search","volume":"18","author":"Aho","year":"1975","journal-title":"Commun. ACM"},{"key":"2019062808223894500_B13","first-page":"17","article-title":"Effective mapping of biomedical text to the UMLS Metathesaurus: the MetaMap program","volume":"2001","author":"Aronson","year":"2001","journal-title":"Proc. AMIA Symp."},{"key":"2019062808223894500_B14","doi-asserted-by":"crossref","first-page":"1962","DOI":"10.1093\/bioinformatics\/bty009","article-title":"Enhanced functionalities for annotating and indexing clinical text with the NCBO Annotator","volume":"34","author":"Tchechmedjiev","year":"2018","journal-title":"Bioinformatics"},{"key":"2019062808223894500_B15","doi-asserted-by":"crossref","first-page":"841","DOI":"10.1093\/jamia\/ocw177","article-title":"MetaMap Lite: an evaluation of a new Java implementation of MetaMap","volume":"24","author":"Demner-Fushman","year":"2017","journal-title":"J. Am. Med. Inform. Assoc."},{"key":"2019062808223894500_B16","doi-asserted-by":"crossref","first-page":"207","DOI":"10.1186\/1471-2105-13-207","article-title":"A corpus of full-text journal articles is a robust evaluation tool for revealing differences in performance of biomedical natural language processing tools","volume":"13","author":"Verspoor","year":"2012","journal-title":"BMC Bioinformatics"},{"key":"2019062808223894500_B17","doi-asserted-by":"crossref","first-page":"589","DOI":"10.1016\/j.molcel.2006.02.012","article-title":"Biomedical language processing: what's beyond PubMed","volume":"21","author":"Hunter","year":"2006","journal-title":"Mol. Cell"},{"key":"2019062808223894500_B18","doi-asserted-by":"crossref","first-page":"132","DOI":"10.1093\/bib\/bbv024","article-title":"Community challenges in biomedical text mining over 10 years: success, failure and the future","volume":"17","author":"Huang","year":"2016","journal-title":"Brief. Bioinform."},{"key":"2019062808223894500_B19","doi-asserted-by":"crossref","first-page":"h1885","DOI":"10.1136\/bmj.h1885","article-title":"Development of phenotype algorithms using electronic medical records and incorporating natural language processing","volume":"350","author":"Liao","year":"2015","journal-title":"BMJ"},{"key":"2019062808223894500_B20","doi-asserted-by":"crossref","first-page":"59","DOI":"10.1186\/1471-2105-15-59","article-title":"Large-scale biomedical concept recognition: an evaluation of current automatic annotators and their parameters","volume":"15","author":"Funk","year":"2014","journal-title":"BMC Bioinformatics"},{"key":"2019062808223894500_B21","doi-asserted-by":"crossref","first-page":"e0116040","DOI":"10.1371\/journal.pone.0116040","article-title":"Generation of silver standard concept annotations from biomedical texts with special relevance to phenotypes","volume":"10","author":"Oellrich","year":"2015","journal-title":"PLoS One"},{"key":"2019062808223894500_B22","doi-asserted-by":"crossref","first-page":"D712","DOI":"10.1093\/nar\/gkw1128","article-title":"The Monarch Initiative: an integrative data and analytic platform connecting phenotypes to genotypes across species","volume":"45","author":"Mungall","year":"2017","journal-title":"Nucleic Acids Res."},{"key":"2019062808223894500_B23","first-page":"102","volume-title":"Proceedings of the Demonstrations at the 13th Conference of the European Chapter of the Association for Computational Linguistics","author":"Stenetorp","year":"2012"},{"key":"2019062808223894500_B24","first-page":"14","volume-title":"Proceedings of the conference. Association for Computational Linguistics. North American Chapter. Meeting","author":"Chen","year":"2013"},{"key":"2019062808223894500_B25","doi-asserted-by":"crossref","first-page":"507","DOI":"10.1136\/jamia.2009.001560","article-title":"Mayo clinical Text Analysis and Knowledge Extraction System (cTAKES): architecture, component evaluation and applications","volume":"17","author":"Savova","year":"2010","journal-title":"J. Am. Med. Inform. Assoc."},{"key":"2019062808223894500_B26","doi-asserted-by":"crossref","DOI":"10.1038\/s41436-018-0381-1","article-title":"ClinPhen extracts and prioritizes patient phenotypes directly from medical records to expedite genetic disease diagnosis","author":"Deisseroth","year":"2018","journal-title":"Genet. Med."},{"key":"2019062808223894500_B27","doi-asserted-by":"crossref","first-page":"D514","DOI":"10.1093\/nar\/gki033","article-title":"Online Mendelian Inheritance in Man (OMIM), a knowledgebase of human genes and genetic disorders","volume":"33","author":"Hamosh","year":"2005","journal-title":"Nucleic Acids Res."},{"key":"2019062808223894500_B28","doi-asserted-by":"crossref","first-page":"803","DOI":"10.1002\/humu.22078","article-title":"Representation of rare diseases in health information systems: the Orphanet approach to serve a wide range of end users","volume":"33","author":"Rath","year":"2012","journal-title":"Hum. Mutat."}],"container-title":["Nucleic Acids Research"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/academic.oup.com\/nar\/advance-article-pdf\/doi\/10.1093\/nar\/gkz386\/28672435\/gkz386.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"http:\/\/academic.oup.com\/nar\/article-pdf\/47\/W1\/W566\/28879980\/gkz386.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2020,12,9]],"date-time":"2020-12-09T12:16:58Z","timestamp":1607516218000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/nar\/article\/47\/W1\/W566\/5491745"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,5,20]]},"references-count":28,"journal-issue":{"issue":"W1","published-online":{"date-parts":[[2019,5,20]]},"published-print":{"date-parts":[[2019,7,2]]}},"URL":"https:\/\/doi.org\/10.1093\/nar\/gkz386","relation":{},"ISSN":["0305-1048","1362-4962"],"issn-type":[{"value":"0305-1048","type":"print"},{"value":"1362-4962","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2019,7,2]]},"published":{"date-parts":[[2019,5,20]]}}}