{"id":"https://openalex.org/W2889211717","doi":"https://doi.org/10.7287/peerj.preprints.27028v1","title":"Comparison of natural language processing tools for automatic gene ontology annotation of scientific literature","display_name":"Comparison of natural language processing tools for automatic gene ontology annotation of scientific literature","publication_year":2018,"publication_date":"2018-07-11","ids":{"openalex":"https://openalex.org/W2889211717","doi":"https://doi.org/10.7287/peerj.preprints.27028v1","mag":"2889211717"},"language":"en","primary_location":{"id":"doi:10.7287/peerj.preprints.27028v1","is_oa":true,"landing_page_url":"https://doi.org/10.7287/peerj.preprints.27028v1","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":null,"raw_type":"posted-content"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.7287/peerj.preprints.27028v1","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5049179847","display_name":"Lucas Beasley","orcid":null},"institutions":[{"id":"https://openalex.org/I169335092","display_name":"University of North Carolina at Greensboro","ror":"https://ror.org/04fnxsj42","country_code":"US","type":"education","lineage":["https://openalex.org/I169335092"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Lucas Beasley","raw_affiliation_strings":["Department of Computer Science, University of North Carolina at    Greensboro, Greensboro, North Carolina, United States","Department of Computer Science, University of North Carolina at Greensboro, Greensboro, North Carolina, United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of North Carolina at    Greensboro, Greensboro, North Carolina, United States","institution_ids":["https://openalex.org/I169335092"]},{"raw_affiliation_string":"Department of Computer Science, University of North Carolina at Greensboro, Greensboro, North Carolina, United States","institution_ids":["https://openalex.org/I169335092"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5054086551","display_name":"Prashanti Manda","orcid":"https://orcid.org/0000-0002-7162-7770"},"institutions":[{"id":"https://openalex.org/I169335092","display_name":"University of North Carolina at Greensboro","ror":"https://ror.org/04fnxsj42","country_code":"US","type":"education","lineage":["https://openalex.org/I169335092"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Prashanti Manda","raw_affiliation_strings":["Department of Computer Science, University of North Carolina at    Greensboro, Greensboro, North Carolina, United States","Department of Computer Science, University of North Carolina at Greensboro, Greensboro, North Carolina, United States"],"raw_orcid":"https://orcid.org/0000-0002-7162-7770","affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of North Carolina at    Greensboro, Greensboro, North Carolina, United States","institution_ids":["https://openalex.org/I169335092"]},{"raw_affiliation_string":"Department of Computer Science, University of North Carolina at Greensboro, Greensboro, North Carolina, United States","institution_ids":["https://openalex.org/I169335092"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5049179847"],"corresponding_institution_ids":["https://openalex.org/I169335092"],"apc_list":null,"apc_paid":null,"fwci":0.3723,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.60913444,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9907000064849854,"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"}},{"id":"https://openalex.org/T10887","display_name":"Bioinformatics and Genomic Networks","score":0.973800003528595,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.810425877571106},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.7289614677429199},{"id":"https://openalex.org/keywords/annotation","display_name":"Annotation","score":0.7260496616363525},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.6580874919891357},{"id":"https://openalex.org/keywords/ontology","display_name":"Ontology","score":0.620045006275177},{"id":"https://openalex.org/keywords/parsing","display_name":"Parsing","score":0.6004014015197754},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5678635835647583},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5559942126274109},{"id":"https://openalex.org/keywords/knowledge-representation-and-reasoning","display_name":"Knowledge representation and reasoning","score":0.4676995277404785},{"id":"https://openalex.org/keywords/semantic-similarity","display_name":"Semantic similarity","score":0.44248875975608826},{"id":"https://openalex.org/keywords/open-biomedical-ontologies","display_name":"Open Biomedical Ontologies","score":0.4336399435997009},{"id":"https://openalex.org/keywords/scientific-literature","display_name":"Scientific literature","score":0.4210372865200043},{"id":"https://openalex.org/keywords/upper-ontology","display_name":"Upper ontology","score":0.40339747071266174},{"id":"https://openalex.org/keywords/suggested-upper-merged-ontology","display_name":"Suggested Upper Merged Ontology","score":0.2231164276599884},{"id":"https://openalex.org/keywords/domain-knowledge","display_name":"Domain knowledge","score":0.1653854250907898}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.810425877571106},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.7289614677429199},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.7260496616363525},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.6580874919891357},{"id":"https://openalex.org/C25810664","wikidata":"https://www.wikidata.org/wiki/Q44325","display_name":"Ontology","level":2,"score":0.620045006275177},{"id":"https://openalex.org/C186644900","wikidata":"https://www.wikidata.org/wiki/Q194152","display_name":"Parsing","level":2,"score":0.6004014015197754},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5678635835647583},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5559942126274109},{"id":"https://openalex.org/C161301231","wikidata":"https://www.wikidata.org/wiki/Q3478658","display_name":"Knowledge representation and reasoning","level":2,"score":0.4676995277404785},{"id":"https://openalex.org/C130318100","wikidata":"https://www.wikidata.org/wiki/Q2268914","display_name":"Semantic similarity","level":2,"score":0.44248875975608826},{"id":"https://openalex.org/C137982476","wikidata":"https://www.wikidata.org/wiki/Q7072326","display_name":"Open Biomedical Ontologies","level":5,"score":0.4336399435997009},{"id":"https://openalex.org/C2781083858","wikidata":"https://www.wikidata.org/wiki/Q17327049","display_name":"Scientific literature","level":2,"score":0.4210372865200043},{"id":"https://openalex.org/C78726541","wikidata":"https://www.wikidata.org/wiki/Q3882785","display_name":"Upper ontology","level":3,"score":0.40339747071266174},{"id":"https://openalex.org/C50971890","wikidata":"https://www.wikidata.org/wiki/Q7635093","display_name":"Suggested Upper Merged Ontology","level":4,"score":0.2231164276599884},{"id":"https://openalex.org/C207685749","wikidata":"https://www.wikidata.org/wiki/Q2088941","display_name":"Domain knowledge","level":2,"score":0.1653854250907898},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","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},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.7287/peerj.preprints.27028v1","is_oa":true,"landing_page_url":"https://doi.org/10.7287/peerj.preprints.27028v1","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":null,"raw_type":"posted-content"}],"best_oa_location":{"id":"doi:10.7287/peerj.preprints.27028v1","is_oa":true,"landing_page_url":"https://doi.org/10.7287/peerj.preprints.27028v1","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":null,"raw_type":"posted-content"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.8600000143051147,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":9,"referenced_works":["https://openalex.org/W161474860","https://openalex.org/W1550258693","https://openalex.org/W2040298461","https://openalex.org/W2053673723","https://openalex.org/W2144949988","https://openalex.org/W2168905447","https://openalex.org/W2189198211","https://openalex.org/W2346673125","https://openalex.org/W2503655816"],"related_works":["https://openalex.org/W2373434917","https://openalex.org/W2360108448","https://openalex.org/W2393185060","https://openalex.org/W337103899","https://openalex.org/W4246765187","https://openalex.org/W1969816234","https://openalex.org/W2184133400","https://openalex.org/W1140107","https://openalex.org/W2293073117","https://openalex.org/W2889211717"],"abstract_inverted_index":{"Manual":[0],"curation":[1],"of":[2,20,42,54,61,71,74,82,107],"scientific":[3,21],"literature":[4,43,89],"for":[5],"ontology-based":[6],"knowledge":[7],"representation":[8],"has":[9],"proven":[10],"infeasible":[11],"and":[12,17,30,51,58],"unscalable":[13],"to":[14,38,56,111,116],"the":[15,40,75,80,91,105,117],"large":[16],"growing":[18],"volume":[19],"literature.":[22],"Automated":[23],"annotation":[24],"solutions":[25],"that":[26],"leverage":[27],"text":[28,55,62],"mining":[29],"Natural":[31],"Language":[32],"Processing":[33],"(NLP)":[34],"have":[35],"been":[36],"developed":[37],"ameliorate":[39],"problem":[41],"curation.":[44],"These":[45],"NLP":[46,77,113],"approaches":[47],"use":[48,106],"parsing,":[49],"syntactical,":[50],"lexical":[52],"analysis":[53],"recognize":[57],"annotate":[59],"pieces":[60],"with":[63],"ontology":[64],"concepts.":[65],"Here,":[66],"we":[67],"conduct":[68],"a":[69,99],"comparison":[70],"four":[72],"state":[73],"art":[76],"tools":[78],"at":[79],"task":[81],"recognizing":[83],"Gene":[84],"Ontology":[85],"concepts":[86],"from":[87],"biomedical":[88],"using":[90],"Colorado":[92],"Richly":[93],"Annotated":[94],"Full-Text":[95],"(CRAFT)":[96],"corpus":[97],"as":[98],"gold":[100,118],"standard":[101],"reference.":[102],"We":[103],"demonstrate":[104],"semantic":[108],"similarity":[109],"metrics":[110],"compare":[112],"tool":[114],"annotations":[115],"standard.":[119]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
