{"id":"https://openalex.org/W2740048509","doi":"https://doi.org/10.18653/v1/w17-2311","title":"Creation and evaluation of a dictionary-based tagger for virus species and proteins","display_name":"Creation and evaluation of a dictionary-based tagger for virus species and proteins","publication_year":2017,"publication_date":"2017-01-01","ids":{"openalex":"https://openalex.org/W2740048509","doi":"https://doi.org/10.18653/v1/w17-2311","mag":"2740048509"},"language":"en","primary_location":{"id":"doi:10.18653/v1/w17-2311","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/w17-2311","pdf_url":"https://www.aclweb.org/anthology/W17-2311.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"BioNLP 2017","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.aclweb.org/anthology/W17-2311.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5047967178","display_name":"Helen Cook","orcid":"https://orcid.org/0000-0002-2659-3727"},"institutions":[{"id":"https://openalex.org/I2801134892","display_name":"Novo Nordisk Foundation","ror":"https://ror.org/04txyc737","country_code":"DK","type":"facility","lineage":["https://openalex.org/I2801134892"]},{"id":"https://openalex.org/I2802640032","display_name":"Foundation Center","ror":"https://ror.org/0377f6951","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I2802640032"]},{"id":"https://openalex.org/I124055696","display_name":"University of Copenhagen","ror":"https://ror.org/035b05819","country_code":"DK","type":"education","lineage":["https://openalex.org/I124055696"]},{"id":"https://openalex.org/I62916508","display_name":"Technical University of Munich","ror":"https://ror.org/02kkvpp62","country_code":"DE","type":"education","lineage":["https://openalex.org/I62916508"]}],"countries":["DE","DK","US"],"is_corresponding":true,"raw_author_name":"Helen Cook","raw_affiliation_strings":["Novo Nordisk Foundation Center for Protein Research,","TUM, Department of Informatics, Bioinformatics & Computational Biology, i12, Boltzmannstr. 3, 85748 Garching/Munich, Germany","Faculty of Health and Medical Sciences, University of Copenhagen, Denmark"],"affiliations":[{"raw_affiliation_string":"Novo Nordisk Foundation Center for Protein Research,","institution_ids":["https://openalex.org/I2801134892","https://openalex.org/I2802640032"]},{"raw_affiliation_string":"TUM, Department of Informatics, Bioinformatics & Computational Biology, i12, Boltzmannstr. 3, 85748 Garching/Munich, Germany","institution_ids":["https://openalex.org/I62916508"]},{"raw_affiliation_string":"Faculty of Health and Medical Sciences, University of Copenhagen, Denmark","institution_ids":["https://openalex.org/I124055696"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011118370","display_name":"R\u016bdolfs B\u0113rzi\u0146\u0161","orcid":null},"institutions":[{"id":"https://openalex.org/I62916508","display_name":"Technical University of Munich","ror":"https://ror.org/02kkvpp62","country_code":"DE","type":"education","lineage":["https://openalex.org/I62916508"]},{"id":"https://openalex.org/I2801134892","display_name":"Novo Nordisk Foundation","ror":"https://ror.org/04txyc737","country_code":"DK","type":"facility","lineage":["https://openalex.org/I2801134892"]},{"id":"https://openalex.org/I2802640032","display_name":"Foundation Center","ror":"https://ror.org/0377f6951","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I2802640032"]},{"id":"https://openalex.org/I124055696","display_name":"University of Copenhagen","ror":"https://ror.org/035b05819","country_code":"DK","type":"education","lineage":["https://openalex.org/I124055696"]}],"countries":["DE","DK","US"],"is_corresponding":false,"raw_author_name":"Rudolfs Berzins","raw_affiliation_strings":["Faculty of Health and Medical Sciences, University of Copenhagen, Denmark","Novo Nordisk Foundation Center for Protein Research,","TUM, Department of Informatics, Bioinformatics & Computational Biology, i12, Boltzmannstr. 3, 85748 Garching/Munich, Germany"],"affiliations":[{"raw_affiliation_string":"Faculty of Health and Medical Sciences, University of Copenhagen, Denmark","institution_ids":["https://openalex.org/I124055696"]},{"raw_affiliation_string":"Novo Nordisk Foundation Center for Protein Research,","institution_ids":["https://openalex.org/I2801134892","https://openalex.org/I2802640032"]},{"raw_affiliation_string":"TUM, Department of Informatics, Bioinformatics & Computational Biology, i12, Boltzmannstr. 3, 85748 Garching/Munich, Germany","institution_ids":["https://openalex.org/I62916508"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102800998","display_name":"Cristina Leal Rodr\u00edguez","orcid":"https://orcid.org/0000-0002-3133-0630"},"institutions":[{"id":"https://openalex.org/I62916508","display_name":"Technical University of Munich","ror":"https://ror.org/02kkvpp62","country_code":"DE","type":"education","lineage":["https://openalex.org/I62916508"]},{"id":"https://openalex.org/I124055696","display_name":"University of Copenhagen","ror":"https://ror.org/035b05819","country_code":"DK","type":"education","lineage":["https://openalex.org/I124055696"]},{"id":"https://openalex.org/I2801134892","display_name":"Novo Nordisk Foundation","ror":"https://ror.org/04txyc737","country_code":"DK","type":"facility","lineage":["https://openalex.org/I2801134892"]},{"id":"https://openalex.org/I2802640032","display_name":"Foundation Center","ror":"https://ror.org/0377f6951","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I2802640032"]}],"countries":["DE","DK","US"],"is_corresponding":false,"raw_author_name":"Cristina Leal Rodr\u0131guez","raw_affiliation_strings":["TUM, Department of Informatics, Bioinformatics & Computational Biology, i12, Boltzmannstr. 3, 85748 Garching/Munich, Germany","Novo Nordisk Foundation Center for Protein Research,","Faculty of Health and Medical Sciences, University of Copenhagen, Denmark"],"affiliations":[{"raw_affiliation_string":"TUM, Department of Informatics, Bioinformatics & Computational Biology, i12, Boltzmannstr. 3, 85748 Garching/Munich, Germany","institution_ids":["https://openalex.org/I62916508"]},{"raw_affiliation_string":"Novo Nordisk Foundation Center for Protein Research,","institution_ids":["https://openalex.org/I2801134892","https://openalex.org/I2802640032"]},{"raw_affiliation_string":"Faculty of Health and Medical Sciences, University of Copenhagen, Denmark","institution_ids":["https://openalex.org/I124055696"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5052162892","display_name":"Juan Miguel Cejuela","orcid":"https://orcid.org/0000-0001-9588-984X"},"institutions":[{"id":"https://openalex.org/I124055696","display_name":"University of Copenhagen","ror":"https://ror.org/035b05819","country_code":"DK","type":"education","lineage":["https://openalex.org/I124055696"]},{"id":"https://openalex.org/I62916508","display_name":"Technical University of Munich","ror":"https://ror.org/02kkvpp62","country_code":"DE","type":"education","lineage":["https://openalex.org/I62916508"]},{"id":"https://openalex.org/I2802640032","display_name":"Foundation Center","ror":"https://ror.org/0377f6951","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I2802640032"]},{"id":"https://openalex.org/I2801134892","display_name":"Novo Nordisk Foundation","ror":"https://ror.org/04txyc737","country_code":"DK","type":"facility","lineage":["https://openalex.org/I2801134892"]}],"countries":["DE","DK","US"],"is_corresponding":false,"raw_author_name":"Juan Miguel Cejuela","raw_affiliation_strings":["TUM, Department of Informatics, Bioinformatics & Computational Biology, i12, Boltzmannstr. 3, 85748 Garching/Munich, Germany","Faculty of Health and Medical Sciences, University of Copenhagen, Denmark","Novo Nordisk Foundation Center for Protein Research,"],"affiliations":[{"raw_affiliation_string":"TUM, Department of Informatics, Bioinformatics & Computational Biology, i12, Boltzmannstr. 3, 85748 Garching/Munich, Germany","institution_ids":["https://openalex.org/I62916508"]},{"raw_affiliation_string":"Faculty of Health and Medical Sciences, University of Copenhagen, Denmark","institution_ids":["https://openalex.org/I124055696"]},{"raw_affiliation_string":"Novo Nordisk Foundation Center for Protein Research,","institution_ids":["https://openalex.org/I2801134892","https://openalex.org/I2802640032"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5005772961","display_name":"Lars Juhl Jensen","orcid":"https://orcid.org/0000-0001-7885-715X"},"institutions":[{"id":"https://openalex.org/I2801134892","display_name":"Novo Nordisk Foundation","ror":"https://ror.org/04txyc737","country_code":"DK","type":"facility","lineage":["https://openalex.org/I2801134892"]},{"id":"https://openalex.org/I124055696","display_name":"University of Copenhagen","ror":"https://ror.org/035b05819","country_code":"DK","type":"education","lineage":["https://openalex.org/I124055696"]},{"id":"https://openalex.org/I2802640032","display_name":"Foundation Center","ror":"https://ror.org/0377f6951","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I2802640032"]},{"id":"https://openalex.org/I62916508","display_name":"Technical University of Munich","ror":"https://ror.org/02kkvpp62","country_code":"DE","type":"education","lineage":["https://openalex.org/I62916508"]}],"countries":["DE","DK","US"],"is_corresponding":false,"raw_author_name":"Lars Juhl Jensen","raw_affiliation_strings":["Faculty of Health and Medical Sciences, University of Copenhagen, Denmark","TUM, Department of Informatics, Bioinformatics & Computational Biology, i12, Boltzmannstr. 3, 85748 Garching/Munich, Germany","Novo Nordisk Foundation Center for Protein Research,"],"affiliations":[{"raw_affiliation_string":"Faculty of Health and Medical Sciences, University of Copenhagen, Denmark","institution_ids":["https://openalex.org/I124055696"]},{"raw_affiliation_string":"TUM, Department of Informatics, Bioinformatics & Computational Biology, i12, Boltzmannstr. 3, 85748 Garching/Munich, Germany","institution_ids":["https://openalex.org/I62916508"]},{"raw_affiliation_string":"Novo Nordisk Foundation Center for Protein Research,","institution_ids":["https://openalex.org/I2801134892","https://openalex.org/I2802640032"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5047967178"],"corresponding_institution_ids":["https://openalex.org/I124055696","https://openalex.org/I2801134892","https://openalex.org/I2802640032","https://openalex.org/I62916508"],"apc_list":null,"apc_paid":null,"fwci":0.2127,"has_fulltext":true,"cited_by_count":4,"citation_normalized_percentile":{"value":0.53763463,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"91","last_page":"98"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.991100013256073,"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/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.991100013256073,"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/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.9868999719619751,"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/T11048","display_name":"Bacteriophages and microbial interactions","score":0.9769999980926514,"subfield":{"id":"https://openalex.org/subfields/2303","display_name":"Ecology"},"field":{"id":"https://openalex.org/fields/23","display_name":"Environmental Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.735426664352417},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6963441967964172},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6099414825439453},{"id":"https://openalex.org/keywords/precision-and-recall","display_name":"Precision and recall","score":0.5743833780288696},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5473527908325195},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.505812406539917},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.5040106177330017},{"id":"https://openalex.org/keywords/recall","display_name":"Recall","score":0.48606637120246887},{"id":"https://openalex.org/keywords/virus-classification","display_name":"Virus classification","score":0.48318949341773987},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.45791497826576233},{"id":"https://openalex.org/keywords/computational-biology","display_name":"Computational biology","score":0.44461989402770996},{"id":"https://openalex.org/keywords/genome","display_name":"Genome","score":0.41370338201522827},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.23080378770828247},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.1564139425754547},{"id":"https://openalex.org/keywords/gene","display_name":"Gene","score":0.11247685551643372},{"id":"https://openalex.org/keywords/biochemistry","display_name":"Biochemistry","score":0.10578963160514832},{"id":"https://openalex.org/keywords/geography","display_name":"Geography","score":0.10440933704376221},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.08955243229866028}],"concepts":[{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.735426664352417},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6963441967964172},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6099414825439453},{"id":"https://openalex.org/C81669768","wikidata":"https://www.wikidata.org/wiki/Q2359161","display_name":"Precision and recall","level":2,"score":0.5743833780288696},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5473527908325195},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.505812406539917},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.5040106177330017},{"id":"https://openalex.org/C100660578","wikidata":"https://www.wikidata.org/wiki/Q18733","display_name":"Recall","level":2,"score":0.48606637120246887},{"id":"https://openalex.org/C20850961","wikidata":"https://www.wikidata.org/wiki/Q478216","display_name":"Virus classification","level":4,"score":0.48318949341773987},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.45791497826576233},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.44461989402770996},{"id":"https://openalex.org/C141231307","wikidata":"https://www.wikidata.org/wiki/Q7020","display_name":"Genome","level":3,"score":0.41370338201522827},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.23080378770828247},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.1564139425754547},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.11247685551643372},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.10578963160514832},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.10440933704376221},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.08955243229866028},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","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":1,"locations":[{"id":"doi:10.18653/v1/w17-2311","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/w17-2311","pdf_url":"https://www.aclweb.org/anthology/W17-2311.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"BioNLP 2017","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/w17-2311","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/w17-2311","pdf_url":"https://www.aclweb.org/anthology/W17-2311.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"BioNLP 2017","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"Life in Land","score":0.4300000071525574,"id":"https://metadata.un.org/sdg/15"}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2740048509.pdf","grobid_xml":"https://content.openalex.org/works/W2740048509.grobid-xml"},"referenced_works_count":24,"referenced_works":["https://openalex.org/W1157864489","https://openalex.org/W1495890774","https://openalex.org/W1997627120","https://openalex.org/W1998148929","https://openalex.org/W2001187841","https://openalex.org/W2052932001","https://openalex.org/W2055666215","https://openalex.org/W2071879021","https://openalex.org/W2096173332","https://openalex.org/W2100627415","https://openalex.org/W2124045889","https://openalex.org/W2127546476","https://openalex.org/W2162965868","https://openalex.org/W2165475425","https://openalex.org/W2169382766","https://openalex.org/W2181908191","https://openalex.org/W2190548957","https://openalex.org/W2260741209","https://openalex.org/W2511570169","https://openalex.org/W2604190529","https://openalex.org/W2606932501","https://openalex.org/W2739999456","https://openalex.org/W2962776108","https://openalex.org/W4250297812"],"related_works":["https://openalex.org/W2378211422","https://openalex.org/W4321353415","https://openalex.org/W2745001401","https://openalex.org/W2130974462","https://openalex.org/W2028665553","https://openalex.org/W2086519370","https://openalex.org/W972276598","https://openalex.org/W2358294942","https://openalex.org/W4367460280","https://openalex.org/W4311414634"],"abstract_inverted_index":{"Text":[0],"mining":[1],"automatically":[2],"extracts":[3],"information":[4],"from":[5,168],"the":[6,9,38,52,78,91,117,139,144,169],"literature":[7],"with":[8,143],"goal":[10,32],"of":[11,104,119,146],"making":[12],"it":[13,22],"available":[14],"for":[15,18,87,94],"further":[16],"analysis,":[17],"example":[19],"by":[20],"incorporating":[21],"into":[23],"biomedical":[24],"databases.":[25],"A":[26],"key":[27],"first":[28,92],"step":[29],"towards":[30],"this":[31],"is":[33],"to":[34,161],"identify":[35],"and":[36,44,61,75,90,113,121,125,128],"normalize":[37],"named":[39],"entities,":[40],"such":[41],"as":[42],"proteins":[43,76],"species,":[45],"which":[46,97],"are":[47,136],"mentioned":[48],"in":[49,77],"text.":[50],"Despite":[51],"large":[53],"detrimental":[54],"impact":[55],"that":[56,157],"viruses":[57,167],"have":[58],"on":[59,71,100,131],"human":[60],"agricultural":[62],"health,":[63],"very":[64],"little":[65],"previous":[66],"textmining":[67],"work":[68,153],"has":[69],"focused":[70],"identifying":[72],"virus":[73],"species":[74,89,124,148],"literature.":[79,170],"Here,":[80],"we":[81,98],"present":[82],"an":[83],"improved":[84],"dictionarybased":[85],"system":[86],"viral":[88,95,123,132,147],"dictionary":[93],"proteins,":[96],"benchmark":[99],"a":[101,155],"new":[102],"corpus":[103],"300":[105],"manually":[106],"annotated":[107],"abstracts.":[108],"We":[109],"achieve":[110],"81.0%":[111],"precision":[112,127],"72.7%":[114],"recall":[115,130],"at":[116],"task":[118],"recognizing":[120],"normalizing":[122],"76.2%":[126],"34.9%":[129],"proteins.":[133,151],"These":[134],"results":[135],"achieved":[137],"despite":[138],"many":[140],"challenges":[141],"involved":[142],"names":[145],"and,":[149],"especially,":[150],"This":[152],"provides":[154],"foundation":[156],"can":[158],"be":[159],"used":[160],"extract":[162],"more":[163],"complicated":[164],"relations":[165],"about":[166]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2018,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
