{"id":"https://openalex.org/W2183388783","doi":"https://doi.org/10.2390/biecoll-jib-2011-184","title":"Automatic extraction of microorganisms and their habitats from free text using text mining workflows","display_name":"Automatic extraction of microorganisms and their habitats from free text using text mining workflows","publication_year":2011,"publication_date":"2011-01-01","ids":{"openalex":"https://openalex.org/W2183388783","doi":"https://doi.org/10.2390/biecoll-jib-2011-184","mag":"2183388783","pmid":"https://pubmed.ncbi.nlm.nih.gov/21987583"},"language":"en","primary_location":{"id":"pmid:21987583","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/21987583","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,"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":"Journal of integrative bioinformatics","raw_type":null},"type":"article","indexed_in":["datacite","pubmed"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.2390/biecoll-jib-2011-184","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5038473184","display_name":"BalaKrishna Kolluru","orcid":null},"institutions":[{"id":"https://openalex.org/I28407311","display_name":"University of Manchester","ror":"https://ror.org/027m9bs27","country_code":"GB","type":"education","lineage":["https://openalex.org/I28407311"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Kolluru, BalaKrishna","raw_affiliation_strings":["2School of Computer Science, University of Manchester, Kilburn Building, Oxford Road, Manchester, M13 9PL, United Kingdom of Great Britain and Northern Ireland"],"affiliations":[{"raw_affiliation_string":"2School of Computer Science, University of Manchester, Kilburn Building, Oxford Road, Manchester, M13 9PL, United Kingdom of Great Britain and Northern Ireland","institution_ids":["https://openalex.org/I28407311"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080394398","display_name":"Sirintra Nakjang","orcid":"https://orcid.org/0000-0003-2960-6842"},"institutions":[{"id":"https://openalex.org/I84884186","display_name":"Newcastle University","ror":"https://ror.org/01kj2bm70","country_code":"GB","type":"education","lineage":["https://openalex.org/I84884186"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Nakjang, Sirintra","raw_affiliation_strings":["4School of Computing Science, University of Newcastle, Newcastle upon Tyne, NE1 7RU, United Kingdom of Great Britain and Northern Ireland"],"affiliations":[{"raw_affiliation_string":"4School of Computing Science, University of Newcastle, Newcastle upon Tyne, NE1 7RU, United Kingdom of Great Britain and Northern Ireland","institution_ids":["https://openalex.org/I84884186"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086891018","display_name":"Robert P. Hirt","orcid":"https://orcid.org/0000-0002-3760-9958"},"institutions":[{"id":"https://openalex.org/I84884186","display_name":"Newcastle University","ror":"https://ror.org/01kj2bm70","country_code":"GB","type":"education","lineage":["https://openalex.org/I84884186"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Hirt, Robert P.","raw_affiliation_strings":["5Institute for Cell and Molecular Biosciences, University of Newcastle, Newcastle upon Tyne, NE2 4HH, United Kingdom of Great Britain and Northern Ireland"],"affiliations":[{"raw_affiliation_string":"5Institute for Cell and Molecular Biosciences, University of Newcastle, Newcastle upon Tyne, NE2 4HH, United Kingdom of Great Britain and Northern Ireland","institution_ids":["https://openalex.org/I84884186"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089978830","display_name":"Anil Wipat","orcid":"https://orcid.org/0000-0001-7310-4191"},"institutions":[{"id":"https://openalex.org/I84884186","display_name":"Newcastle University","ror":"https://ror.org/01kj2bm70","country_code":"GB","type":"education","lineage":["https://openalex.org/I84884186"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Wipat, Anil","raw_affiliation_strings":["4School of Computing Science, University of Newcastle, Newcastle upon Tyne, NE1 7RU, United Kingdom of Great Britain and Northern Ireland"],"affiliations":[{"raw_affiliation_string":"4School of Computing Science, University of Newcastle, Newcastle upon Tyne, NE1 7RU, United Kingdom of Great Britain and Northern Ireland","institution_ids":["https://openalex.org/I84884186"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5077976343","display_name":"Sophia Ananiadou","orcid":"https://orcid.org/0000-0002-4097-9191"},"institutions":[{"id":"https://openalex.org/I28407311","display_name":"University of Manchester","ror":"https://ror.org/027m9bs27","country_code":"GB","type":"education","lineage":["https://openalex.org/I28407311"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Ananiadou, Sophia","raw_affiliation_strings":["2School of Computer Science, University of Manchester, Kilburn Building, Oxford Road, Manchester, M13 9PL, United Kingdom of Great Britain and Northern Ireland"],"affiliations":[{"raw_affiliation_string":"2School of Computer Science, University of Manchester, Kilburn Building, Oxford Road, Manchester, M13 9PL, United Kingdom of Great Britain and Northern Ireland","institution_ids":["https://openalex.org/I28407311"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5038473184"],"corresponding_institution_ids":["https://openalex.org/I28407311"],"apc_list":null,"apc_paid":null,"fwci":0.667,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.69793079,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":"8","issue":"2","first_page":"184","last_page":"184"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.9988999962806702,"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":0.9988999962806702,"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":0.9936000108718872,"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/T13083","display_name":"Advanced Text Analysis Techniques","score":0.988099992275238,"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/computer-science","display_name":"Computer science","score":0.7840768098831177},{"id":"https://openalex.org/keywords/workflow","display_name":"Workflow","score":0.7492418885231018},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.6684568524360657},{"id":"https://openalex.org/keywords/relationship-extraction","display_name":"Relationship extraction","score":0.6305205225944519},{"id":"https://openalex.org/keywords/information-extraction","display_name":"Information extraction","score":0.5492380857467651},{"id":"https://openalex.org/keywords/relation","display_name":"Relation (database)","score":0.5351871252059937},{"id":"https://openalex.org/keywords/extraction","display_name":"Extraction (chemistry)","score":0.4994041919708252},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.4749845862388611},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.45364806056022644},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.38846874237060547},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.37067514657974243},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.17441195249557495},{"id":"https://openalex.org/keywords/chemistry","display_name":"Chemistry","score":0.09351301193237305}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7840768098831177},{"id":"https://openalex.org/C177212765","wikidata":"https://www.wikidata.org/wiki/Q627335","display_name":"Workflow","level":2,"score":0.7492418885231018},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.6684568524360657},{"id":"https://openalex.org/C153604712","wikidata":"https://www.wikidata.org/wiki/Q7310755","display_name":"Relationship extraction","level":3,"score":0.6305205225944519},{"id":"https://openalex.org/C195807954","wikidata":"https://www.wikidata.org/wiki/Q1662562","display_name":"Information extraction","level":2,"score":0.5492380857467651},{"id":"https://openalex.org/C25343380","wikidata":"https://www.wikidata.org/wiki/Q277521","display_name":"Relation (database)","level":2,"score":0.5351871252059937},{"id":"https://openalex.org/C4725764","wikidata":"https://www.wikidata.org/wiki/Q844704","display_name":"Extraction (chemistry)","level":2,"score":0.4994041919708252},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.4749845862388611},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.45364806056022644},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.38846874237060547},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.37067514657974243},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.17441195249557495},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.09351301193237305},{"id":"https://openalex.org/C43617362","wikidata":"https://www.wikidata.org/wiki/Q170050","display_name":"Chromatography","level":1,"score":0.0}],"mesh":[{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D001331","descriptor_name":"Automation","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D001331","descriptor_name":"Automation","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D001331","descriptor_name":"Automation","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D001331","descriptor_name":"Automation","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D001419","descriptor_name":"Bacteria","qualifier_ui":"Q000145","qualifier_name":"classification","is_major_topic":false},{"descriptor_ui":"D001419","descriptor_name":"Bacteria","qualifier_ui":"Q000145","qualifier_name":"classification","is_major_topic":false},{"descriptor_ui":"D001419","descriptor_name":"Bacteria","qualifier_ui":"Q000145","qualifier_name":"classification","is_major_topic":false},{"descriptor_ui":"D001419","descriptor_name":"Bacteria","qualifier_ui":"Q000145","qualifier_name":"classification","is_major_topic":false},{"descriptor_ui":"D017753","descriptor_name":"Ecosystem","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D017753","descriptor_name":"Ecosystem","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D017753","descriptor_name":"Ecosystem","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D017753","descriptor_name":"Ecosystem","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D057225","descriptor_name":"Data Mining","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D057225","descriptor_name":"Data Mining","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D057225","descriptor_name":"Data Mining","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D057225","descriptor_name":"Data Mining","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false}],"locations_count":5,"locations":[{"id":"pmid:21987583","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/21987583","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,"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":"Journal of integrative bioinformatics","raw_type":null},{"id":"pmh:oai:pure.atira.dk:openaire_cris_publications/26460ed3-d0c0-49e9-a851-a01c2df405d1","is_oa":false,"landing_page_url":"https://research.manchester.ac.uk/en/publications/26460ed3-d0c0-49e9-a851-a01c2df405d1","pdf_url":null,"source":{"id":"https://openalex.org/S4306400662","display_name":"Research Explorer (The University of Manchester)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I28407311","host_organization_name":"University of Manchester","host_organization_lineage":["https://openalex.org/I28407311"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Kolluru, B, Nakjang, S, Hirt, R P, Wipat, A & Ananiadou, S 2011, 'Automatic extraction of microorganisms and their habitats from free text using text mining workflows.', Journal of integrative bioinformatics, vol. 8, no. 2, pp. 184.","raw_type":"info:eu-repo/semantics/publishedVersion"},{"id":"pmh:oai:pure.atira.dk:openaire_cris_publications/a7ea0ac9-8837-4255-aef1-402f838dbfb2","is_oa":false,"landing_page_url":"https://research.manchester.ac.uk/en/publications/a7ea0ac9-8837-4255-aef1-402f838dbfb2","pdf_url":null,"source":{"id":"https://openalex.org/S4306400662","display_name":"Research Explorer (The University of Manchester)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I28407311","host_organization_name":"University of Manchester","host_organization_lineage":["https://openalex.org/I28407311"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Kolluru, B, Nakjang, S, Hirt, R P, Wipat, A & Ananiadou, S 2011, Automatic extraction of microorganisms and their habitats from free text using text mining workflows. in Journal of integrative bioinformatics|J Integr Bioinform. vol. 8, pp. 184, International Symposium on Integrative Bioinformatics, 1/01/24.","raw_type":"info:eu-repo/semantics/publishedVersion"},{"id":"pmh:oai:biecoll.ub.uni-bielefeld.de:5200","is_oa":false,"landing_page_url":"http://biecoll.ub.uni-bielefeld.de/volltexte/2011/5200/","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://journal.imbio.de/article.php?aid=184","raw_type":"Journal Article"},{"id":"doi:10.2390/biecoll-jib-2011-184","is_oa":true,"landing_page_url":"https://doi.org/10.2390/biecoll-jib-2011-184","pdf_url":null,"source":{"id":"https://openalex.org/S4306401670","display_name":"PUB \u2013 Publications at Bielefeld University (Bielefeld University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I20121455","host_organization_name":"Bielefeld University","host_organization_lineage":["https://openalex.org/I20121455"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article-journal"}],"best_oa_location":{"id":"doi:10.2390/biecoll-jib-2011-184","is_oa":true,"landing_page_url":"https://doi.org/10.2390/biecoll-jib-2011-184","pdf_url":null,"source":{"id":"https://openalex.org/S4306401670","display_name":"PUB \u2013 Publications at Bielefeld University (Bielefeld University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I20121455","host_organization_name":"Bielefeld University","host_organization_lineage":["https://openalex.org/I20121455"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article-journal"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.5600000023841858}],"awards":[{"id":"https://openalex.org/G2633328597","display_name":null,"funder_award_id":"BB/F006039/1","funder_id":"https://openalex.org/F4320334629","funder_display_name":"Biotechnology and Biological Sciences Research Council"},{"id":"https://openalex.org/G3752877916","display_name":null,"funder_award_id":"BB/F006012/1","funder_id":"https://openalex.org/F4320334629","funder_display_name":"Biotechnology and Biological Sciences Research Council"},{"id":"https://openalex.org/G4655000275","display_name":null,"funder_award_id":"BB/E004431/1","funder_id":"https://openalex.org/F4320334629","funder_display_name":"Biotechnology and Biological Sciences Research Council"}],"funders":[{"id":"https://openalex.org/F4320334629","display_name":"Biotechnology and Biological Sciences Research Council","ror":"https://ror.org/00cwqg982"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W121221959","https://openalex.org/W1525521077","https://openalex.org/W1966233364","https://openalex.org/W1973406306","https://openalex.org/W1991056282","https://openalex.org/W2006390877","https://openalex.org/W2034235575","https://openalex.org/W2044867337","https://openalex.org/W2047655644","https://openalex.org/W2075623226","https://openalex.org/W2085519949","https://openalex.org/W2092489937","https://openalex.org/W2096525273","https://openalex.org/W2096876337","https://openalex.org/W2103235794","https://openalex.org/W2110132014","https://openalex.org/W2115356798","https://openalex.org/W2118362821","https://openalex.org/W2125552472","https://openalex.org/W2130956021","https://openalex.org/W2147880316","https://openalex.org/W2151296343","https://openalex.org/W2165618941","https://openalex.org/W2172180590","https://openalex.org/W2595461065"],"related_works":["https://openalex.org/W2276606543","https://openalex.org/W2104896715","https://openalex.org/W48763201","https://openalex.org/W1968889737","https://openalex.org/W2898301985","https://openalex.org/W6578894","https://openalex.org/W60538693","https://openalex.org/W1544491176","https://openalex.org/W2352911637","https://openalex.org/W2129595335","https://openalex.org/W2797889308","https://openalex.org/W2109544485","https://openalex.org/W2804022826","https://openalex.org/W3144508074","https://openalex.org/W2542906550","https://openalex.org/W2189023141","https://openalex.org/W69749311","https://openalex.org/W2557512290","https://openalex.org/W2016048023","https://openalex.org/W2030836983"],"abstract_inverted_index":{"In":[0],"this":[1,35,111],"paper":[2],"we":[3,37],"illustrate":[4],"the":[5,49,53,59,76,81],"usage":[6],"of":[7,15,48,55,73,80,86,97],"text":[8],"mining":[9],"workflows":[10],"to":[11,31,51],"automatically":[12],"extract":[13,52],"instances":[14],"microorganisms":[16,74],"and":[17,29,58,63,75,110],"their":[18,64],"habitats":[19,57],"from":[20],"free":[21],"text;":[22],"these":[23],"entries":[24],"can":[25,106],"then":[26],"be":[27,107],"curated":[28],"added":[30],"different":[32],"databases.":[33],"To":[34],"end,":[36],"use":[38],"a":[39,68,84],"Conditional":[40],"Random":[41],"Field":[42],"(CRF)":[43],"based":[44],"classifier,":[45],"as":[46],"part":[47],"workflows,":[50],"mention":[54],"microorganisms,":[56],"inter-relation":[60],"between":[61],"organisms":[62],"habitats.":[65],"Results":[66],"indicate":[67],"good":[69],"performance":[70],"for":[71],"extraction":[72,78,117],"relation":[77,116],"aspects":[79],"task":[82],"(with":[83],"precision":[85,96],"over":[87],"80%),":[88],"while":[89],"habitat":[90],"recognition":[91],"is":[92],"only":[93],"moderate":[94],"(a":[95],"about":[98],"65%).":[99],"We":[100],"also":[101],"conjecture":[102],"that":[103],"pdf-to-text":[104],"conversion":[105],"quite":[108],"noisy":[109],"implicitly":[112],"affects":[113],"any":[114],"sentence-based":[115],"algorithms.":[118]},"counts_by_year":[{"year":2016,"cited_by_count":1},{"year":2013,"cited_by_count":1},{"year":2012,"cited_by_count":4}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}
