{"id":"https://openalex.org/W1961588674","doi":null,"title":"Towards Structuring Unstructured GenBank Metadata for Enhancing Comparative Biological Studies.","display_name":"Towards Structuring Unstructured GenBank Metadata for Enhancing Comparative Biological Studies.","publication_year":2011,"publication_date":"2011-01-01","ids":{"openalex":"https://openalex.org/W1961588674","mag":"1961588674","pmid":"https://pubmed.ncbi.nlm.nih.gov/22211174","pmcid":"https://www.ncbi.nlm.nih.gov/pmc/articles/3248757"},"language":"en","primary_location":{"id":"pmh:oai:europepmc.org:2252516","doi":null,"is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/3248757","pdf_url":null,"source":{"id":"https://openalex.org/S4306400806","display_name":"Europe PMC (PubMed Central)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I1303153112","host_organization_name":"European Bioinformatics Institute","host_organization_lineage":["https://openalex.org/I1303153112"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":null,"raw_type":"Text"},"volume":null,"type":"article","indexed_in":["pubmed"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/3248757","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Elizabeth S Chen","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Elizabeth S Chen","raw_affiliation_strings":["Center for Clinical and Translational Science"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Clinical and Translational Science","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5086602697","display_name":"Indra Neil Sarkar","orcid":"https://orcid.org/0000-0003-2054-7356","observed_orcids":["https://orcid.org/0000-0003-2054-7356"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Indra Neil Sarkar","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.1297,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.48612698,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":88,"max":96},"biblio":{"volume":"2011","issue":null,"first_page":"6","last_page":"10"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.9955999851226807,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},"topics":[{"id":"https://openalex.org/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.9955999851226807,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.0024999999441206455,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T10215","display_name":"Semantic Web and Ontologies","score":0.0006000000284984708,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/isolation-source","display_name":"isolation source","score":0.8949999809265137},{"id":"https://openalex.org/keywords/biomedical-ontologies","display_name":"biomedical ontologies","score":0.9710000157356262},{"id":"https://openalex.org/keywords/semantic-types","display_name":"semantic types","score":0.9639999866485596},{"id":"https://openalex.org/keywords/comparative-biology","display_name":"comparative biology","score":0.6869999766349792},{"id":"https://openalex.org/keywords/metadata-enrichment","display_name":"metadata enrichment","score":0.3149999976158142}],"concepts":[{"id":"https://openalex.org/C93518851","wikidata":"https://www.wikidata.org/wiki/Q180160","display_name":"Metadata","level":2,"score":0.9030531644821167},{"id":"https://openalex.org/C79029880","wikidata":"https://www.wikidata.org/wiki/Q901755","display_name":"GenBank","level":3,"score":0.7651863098144531},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7029927968978882},{"id":"https://openalex.org/C2775941552","wikidata":"https://www.wikidata.org/wiki/Q25212305","display_name":"Isolation (microbiology)","level":2,"score":0.569955050945282},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5423790216445923},{"id":"https://openalex.org/C2775945657","wikidata":"https://www.wikidata.org/wiki/Q381442","display_name":"Structuring","level":2,"score":0.5093573331832886},{"id":"https://openalex.org/C193150823","wikidata":"https://www.wikidata.org/wiki/Q1477538","display_name":"Geospatial metadata","level":5,"score":0.4737620949745178},{"id":"https://openalex.org/C126831891","wikidata":"https://www.wikidata.org/wiki/Q221673","display_name":"Host (biology)","level":2,"score":0.44817814230918884},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.424116849899292},{"id":"https://openalex.org/C25810664","wikidata":"https://www.wikidata.org/wiki/Q44325","display_name":"Ontology","level":2,"score":0.4213462769985199},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.380391389131546},{"id":"https://openalex.org/C153048206","wikidata":"https://www.wikidata.org/wiki/Q3454922","display_name":"Metadata repository","level":3,"score":0.36893200874328613},{"id":"https://openalex.org/C60644358","wikidata":"https://www.wikidata.org/wiki/Q128570","display_name":"Bioinformatics","level":1,"score":0.18142956495285034},{"id":"https://openalex.org/C136976847","wikidata":"https://www.wikidata.org/wiki/Q6822297","display_name":"Meta Data Services","level":4,"score":0.1548309624195099},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.15044957399368286},{"id":"https://openalex.org/C18903297","wikidata":"https://www.wikidata.org/wiki/Q7150","display_name":"Ecology","level":1,"score":0.13611936569213867},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C10138342","wikidata":"https://www.wikidata.org/wiki/Q43015","display_name":"Finance","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"pmh:oai:europepmc.org:2252516","doi":null,"is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/3248757","pdf_url":null,"source":{"id":"https://openalex.org/S4306400806","display_name":"Europe PMC (PubMed Central)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I1303153112","host_organization_name":"European Bioinformatics Institute","host_organization_lineage":["https://openalex.org/I1303153112"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":null,"raw_type":"Text"},{"id":"pmh:oai:pubmedcentral.nih.gov:3248757","doi":null,"is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/3248757","pdf_url":null,"source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"AMIA Jt Summits Transl Sci Proc","raw_type":"Text"},{"id":"pmid:22211174","doi":null,"is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/22211174","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"AMIA Joint Summits on Translational Science proceedings. AMIA Joint Summits on Translational Science","raw_type":"Journal Article"},{"id":"mag:1961588674","doi":null,"is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/22211174","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":"PubMed","raw_type":null}],"best_oa_location":{"id":"pmh:oai:europepmc.org:2252516","doi":null,"is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/3248757","pdf_url":null,"source":{"id":"https://openalex.org/S4306400806","display_name":"Europe PMC (PubMed Central)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I1303153112","host_organization_name":"European Bioinformatics Institute","host_organization_lineage":["https://openalex.org/I1303153112"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":null,"raw_type":"Text"},"sustainable_development_goals":[],"study_designs":[],"awards":[{"id":"https://openalex.org/G3006757812","display_name":"Enhancing Organism Based Disease Knowledge Via Name Based Taxonomic Intelligence","funder_award_id":"R01LM009725","funder_id":"https://openalex.org/F4320337372","funder_display_name":"U.S. National Library of Medicine"}],"funders":[{"id":"https://openalex.org/F4320337372","display_name":"U.S. National Library of Medicine","ror":"https://ror.org/0060t0j89"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":6,"referenced_works":["https://openalex.org/W1525521077","https://openalex.org/W2046485931","https://openalex.org/W2096525273","https://openalex.org/W2131660156","https://openalex.org/W2140291614","https://openalex.org/W2167214840"],"related_works":["https://openalex.org/W7100042665","https://openalex.org/W2786076794","https://openalex.org/W4409405022","https://openalex.org/W7160239077","https://openalex.org/W4284962984","https://openalex.org/W4301038757","https://openalex.org/W4391128431","https://openalex.org/W2995122237","https://openalex.org/W4291017647","https://openalex.org/W2504077205"],"abstract_inverted_index":{"Within":[0],"large":[1],"sequence":[2],"repositories":[3],"such":[4],"as":[5],"GenBank":[6,74],"there":[7],"is":[8,33],"a":[9,26,66,95],"wealth":[10],"of":[11,22,28,36,55,64,68,97,121],"metadata":[12,40],"providing":[13],"contextual":[14],"information":[15,122],"that":[16,93],"may":[17],"enhance":[18],"search":[19],"and":[20,49,81,106,133,136],"retrieval":[21],"relevant":[23],"sequences":[24],"for":[25,71,89,129,141],"range":[27],"subsequent":[29],"analyses.":[30],"One":[31],"challenge":[32],"the":[34,56,62,79,118,131,138],"use":[35],"free-text":[37],"in":[38],"these":[39,125],"fields":[41],"where":[42],"approaches":[43],"are":[44],"needed":[45],"to":[46,60,103,117],"extract,":[47],"structure,":[48],"encode":[50],"essential":[51],"information.":[52],"The":[53,109],"goal":[54],"present":[57],"study":[58,114],"was":[59],"explore":[61],"feasibility":[63],"using":[65],"combination":[67],"existing":[69],"resources":[70],"annotating":[72],"unstructured":[73,126],"metadata,":[75,127],"initially":[76],"focusing":[77],"on":[78],"\"host\"":[80],"\"isolation_source\"":[82],"fields.":[83],"This":[84],"paper":[85],"summarizes":[86],"early":[87],"results":[88],"10":[90],"host":[91],"organisms":[92],"include":[94],"characterization":[96],"associated":[98],"isolation":[99],"sources":[100],"with":[101],"respect":[102],"biomedical":[104],"ontologies":[105],"semantic":[107],"types.":[108],"findings":[110],"from":[111],"this":[112],"preliminary":[113],"provide":[115],"insights":[116],"rich":[119],"amount":[120],"captured":[123],"within":[124],"guidance":[128],"addressing":[130],"challenges":[132],"issues":[134],"encountered,":[135],"highlight":[137],"potential":[139],"value":[140],"enriching":[142],"comparative":[143],"biological":[144],"studies":[145],"towards":[146],"improving":[147],"human":[148],"health.":[149]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":1},{"year":2013,"cited_by_count":1}],"updated_date":"2026-10-30T12:39:25.321706","created_date":"2016-06-24T00:00:00"}
