{"id":"https://openalex.org/W2078420731","doi":"https://doi.org/10.1186/1471-2105-9-321","title":"GBParsy: A GenBank flatfile parser library with high speed","display_name":"GBParsy: A GenBank flatfile parser library with high speed","publication_year":2008,"publication_date":"2008-07-25","ids":{"openalex":"https://openalex.org/W2078420731","doi":"https://doi.org/10.1186/1471-2105-9-321","mag":"2078420731","pmid":"https://pubmed.ncbi.nlm.nih.gov/18652706"},"language":"en","primary_location":{"id":"doi:10.1186/1471-2105-9-321","is_oa":true,"landing_page_url":"https://doi.org/10.1186/1471-2105-9-321","pdf_url":"https://bmcbioinformatics.biomedcentral.com/counter/pdf/10.1186/1471-2105-9-321","source":{"id":"https://openalex.org/S19032547","display_name":"BMC Bioinformatics","issn_l":"1471-2105","issn":["1471-2105"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320256","host_organization_name":"BioMed Central","host_organization_lineage":["https://openalex.org/P4310320256","https://openalex.org/P4310319965"],"host_organization_lineage_names":["BioMed Central","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"BMC Bioinformatics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://bmcbioinformatics.biomedcentral.com/counter/pdf/10.1186/1471-2105-9-321","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100759354","display_name":"Tae\u2010Ho Lee","orcid":"https://orcid.org/0000-0001-6458-0620"},"institutions":[{"id":"https://openalex.org/I89440247","display_name":"Myongji University","ror":"https://ror.org/00s9dpb54","country_code":"KR","type":"education","lineage":["https://openalex.org/I89440247"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Tae-Ho Lee","raw_affiliation_strings":["Division of Bioscience and Bioinformatics, MyongJi University, Yongin, Kyonggido, Republic of Korea. thlee@bio.mju.ac.kr","Division of Bioscience and Bioinformatics, MyongJi University, Yongin, Kyonggido, Republic of Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Division of Bioscience and Bioinformatics, MyongJi University, Yongin, Kyonggido, Republic of Korea. thlee@bio.mju.ac.kr","institution_ids":["https://openalex.org/I89440247"]},{"raw_affiliation_string":"Division of Bioscience and Bioinformatics, MyongJi University, Yongin, Kyonggido, Republic of Korea","institution_ids":["https://openalex.org/I89440247"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024673732","display_name":"Yeon-Ki Kim","orcid":"https://orcid.org/0000-0002-4507-341X"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Yeon-Ki Kim","raw_affiliation_strings":["Genomics Genetics Institute, GreenGene BioTech Inc., Yongin, Kyonggido, Republic of Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Genomics Genetics Institute, GreenGene BioTech Inc., Yongin, Kyonggido, Republic of Korea","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5035270274","display_name":"Baek Hie Nahm","orcid":"https://orcid.org/0000-0003-0951-7420"},"institutions":[{"id":"https://openalex.org/I89440247","display_name":"Myongji University","ror":"https://ror.org/00s9dpb54","country_code":"KR","type":"education","lineage":["https://openalex.org/I89440247"]}],"countries":["KR"],"is_corresponding":true,"raw_author_name":"Baek Hie Nahm","raw_affiliation_strings":["Division of Bioscience and Bioinformatics, MyongJi University, Yongin, Kyonggido, Republic of Korea","Genomics Genetics Institute, GreenGene BioTech Inc., Yongin, Kyonggido, Republic of Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Division of Bioscience and Bioinformatics, MyongJi University, Yongin, Kyonggido, Republic of Korea","institution_ids":["https://openalex.org/I89440247"]},{"raw_affiliation_string":"Genomics Genetics Institute, GreenGene BioTech Inc., Yongin, Kyonggido, Republic of Korea","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5024673732","https://openalex.org/A5035270274"],"corresponding_institution_ids":["https://openalex.org/I89440247"],"apc_list":{"value":1690,"currency":"GBP","value_usd":2072},"apc_paid":{"value":1690,"currency":"GBP","value_usd":2072},"fwci":0.2778,"has_fulltext":true,"cited_by_count":11,"citation_normalized_percentile":{"value":0.60621142,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":"9","issue":"1","first_page":"321","last_page":"321"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.2750999927520752,"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":0.2750999927520752,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.24549999833106995,"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/T11269","display_name":"Algorithms and Data Compression","score":0.1776999980211258,"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/parsing","display_name":"Parsing","score":0.8001760244369507},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7986030578613281},{"id":"https://openalex.org/keywords/genbank","display_name":"GenBank","score":0.7915189266204834},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.5569509863853455},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.4163428246974945},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.41322970390319824},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.39735203981399536},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.14739775657653809},{"id":"https://openalex.org/keywords/genetics","display_name":"Genetics","score":0.13288971781730652},{"id":"https://openalex.org/keywords/gene","display_name":"Gene","score":0.08962109684944153}],"concepts":[{"id":"https://openalex.org/C186644900","wikidata":"https://www.wikidata.org/wiki/Q194152","display_name":"Parsing","level":2,"score":0.8001760244369507},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7986030578613281},{"id":"https://openalex.org/C79029880","wikidata":"https://www.wikidata.org/wiki/Q901755","display_name":"GenBank","level":3,"score":0.7915189266204834},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.5569509863853455},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.4163428246974945},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.41322970390319824},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.39735203981399536},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.14739775657653809},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.13288971781730652},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.08962109684944153}],"mesh":[{"descriptor_ui":"D001483","descriptor_name":"Base Sequence","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D001483","descriptor_name":"Base Sequence","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D001483","descriptor_name":"Base Sequence","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D002875","descriptor_name":"Chromosomes","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D002875","descriptor_name":"Chromosomes","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D002875","descriptor_name":"Chromosomes","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D012984","descriptor_name":"Software","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D012984","descriptor_name":"Software","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D012984","descriptor_name":"Software","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D013997","descriptor_name":"Time Factors","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D013997","descriptor_name":"Time Factors","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D013997","descriptor_name":"Time Factors","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D014584","descriptor_name":"User-Computer Interface","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D014584","descriptor_name":"User-Computer Interface","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D014584","descriptor_name":"User-Computer Interface","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D015723","descriptor_name":"Gene Library","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D015723","descriptor_name":"Gene Library","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D015723","descriptor_name":"Gene Library","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D016678","descriptor_name":"Genome","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016678","descriptor_name":"Genome","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016678","descriptor_name":"Genome","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D030561","descriptor_name":"Databases, Nucleic Acid","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D030561","descriptor_name":"Databases, Nucleic Acid","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D030561","descriptor_name":"Databases, Nucleic Acid","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true}],"locations_count":4,"locations":[{"id":"doi:10.1186/1471-2105-9-321","is_oa":true,"landing_page_url":"https://doi.org/10.1186/1471-2105-9-321","pdf_url":"https://bmcbioinformatics.biomedcentral.com/counter/pdf/10.1186/1471-2105-9-321","source":{"id":"https://openalex.org/S19032547","display_name":"BMC Bioinformatics","issn_l":"1471-2105","issn":["1471-2105"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320256","host_organization_name":"BioMed Central","host_organization_lineage":["https://openalex.org/P4310320256","https://openalex.org/P4310319965"],"host_organization_lineage_names":["BioMed Central","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"BMC Bioinformatics","raw_type":"journal-article"},{"id":"pmid:18652706","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/18652706","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":"BMC bioinformatics","raw_type":null},{"id":"pmh:oai:doaj.org/article:91bbc97861a54d128ec36dfd230b7fa1","is_oa":true,"landing_page_url":"https://doaj.org/article/91bbc97861a54d128ec36dfd230b7fa1","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"BMC Bioinformatics, Vol 9, Iss 1, p 321 (2008)","raw_type":"article"},{"id":"pmh:oai:pubmedcentral.nih.gov:2516526","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/2516526","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,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"BMC Bioinformatics","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.1186/1471-2105-9-321","is_oa":true,"landing_page_url":"https://doi.org/10.1186/1471-2105-9-321","pdf_url":"https://bmcbioinformatics.biomedcentral.com/counter/pdf/10.1186/1471-2105-9-321","source":{"id":"https://openalex.org/S19032547","display_name":"BMC Bioinformatics","issn_l":"1471-2105","issn":["1471-2105"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320256","host_organization_name":"BioMed Central","host_organization_lineage":["https://openalex.org/P4310320256","https://openalex.org/P4310319965"],"host_organization_lineage_names":["BioMed Central","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"BMC Bioinformatics","raw_type":"journal-article"},"sustainable_development_goals":[{"score":0.44999998807907104,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320322035","display_name":"Rural Development Administration","ror":"https://ror.org/03xs9yg50"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2078420731.pdf","grobid_xml":"https://content.openalex.org/works/W2078420731.grobid-xml"},"referenced_works_count":10,"referenced_works":["https://openalex.org/W1996423252","https://openalex.org/W2138270253","https://openalex.org/W2141652419","https://openalex.org/W2144297312","https://openalex.org/W2150934173","https://openalex.org/W2151464048","https://openalex.org/W2465323533","https://openalex.org/W2904955605","https://openalex.org/W2915880292","https://openalex.org/W4245145908"],"related_works":["https://openalex.org/W1993070549","https://openalex.org/W1906885765","https://openalex.org/W4232951075","https://openalex.org/W4386946098","https://openalex.org/W4240231372","https://openalex.org/W4212865600","https://openalex.org/W4256072927","https://openalex.org/W4381248170","https://openalex.org/W2817971408","https://openalex.org/W3189621521"],"abstract_inverted_index":{"BACKGROUND:":[0],"GenBank":[1,207],"flatfile":[2,208],"(GBF)":[3],"format":[4],"is":[5,37,40,109,182,195],"one":[6],"of":[7,15,22,70,123,151,178,205,224,230],"the":[8,26,29,48,51,61,68,92],"most":[9],"popular":[10],"sequence":[11,18,49,72,81,102,211],"file":[12,30,95],"formats":[13],"because":[14],"its":[16,97],"detailed":[17],"features":[19],"and":[20,39,50,96,103,120,136,176],"ease":[21],"readability.":[23],"To":[24],"use":[25,122],"data":[27],"in":[28,53,149,190],"by":[31,145],"a":[32,34,44,54,78,87,114,129,206,214,222,231,234],"computer,":[33],"parsing":[35,77,115,141,174],"process":[36],"required":[38],"performed":[41],"according":[42],"to":[43,91,112,166,197],"given":[45],"grammar":[46],"for":[47,60,209,221],"description":[52],"GBF.":[55],"Currently,":[56],"several":[57],"parser":[58],"libraries":[59,84],"GBF":[62,94,138],"have":[63],"been":[64],"developed.":[65],"However,":[66],"with":[67,82,117],"accumulation":[69],"DNA":[71],"information":[73,200,212],"from":[74,201],"eukaryotic":[75,79],"chromosomes,":[76],"genome":[80,232],"these":[83],"inevitably":[85],"takes":[86],"long":[88],"time,":[89],"due":[90],"large":[93,99],"correspondingly":[98],"genomic":[100],"nucleotide":[101],"related":[104,165],"feature":[105],"information.":[106],"Thus,":[107,216],"there":[108],"significant":[110],"need":[111],"develop":[113],"program":[116],"high":[118],"speed":[119,142],"efficient":[121],"system":[124],"memory.":[125],"RESULTS:":[126],"We":[127],"developed":[128],"library,":[130],"GBParsy,":[131],"which":[132],"was":[133,143],"C":[134],"language-based":[135],"parses":[137],"files.":[139],"The":[140],"maximized":[144],"using":[146],"content-specified":[147],"functions":[148],"place":[150],"regular":[152],"expressions":[153],"that":[154,170],"are":[155],"flexible":[156],"but":[157],"slow.":[158],"In":[159],"addition,":[160],"we":[161],"optimized":[162],"an":[163],"algorithm":[164],"memory":[167,179],"usage":[168],"so":[169],"it":[171,217],"also":[172],"increased":[173],"performance":[175],"efficiency":[177],"usage.":[180],"GBParsy":[181,194],"at":[183,233],"least":[184],"5-100x":[185],"faster":[186],"than":[187],"current":[188],"parsers":[189],"benchmark":[191],"tests.":[192],"CONCLUSION:":[193],"estimated":[196],"extract":[198],"annotated":[199],"almost":[202],"100":[203],"Mb":[204],"chromosomal":[210],"within":[213],"second.":[215],"should":[218],"be":[219],"used":[220],"variety":[223],"applications":[225],"such":[226],"as":[227],"on-time":[228],"visualization":[229],"web":[235],"site.":[236]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2016,"cited_by_count":2},{"year":2012,"cited_by_count":3}],"updated_date":"2026-06-19T15:47:20.252518","created_date":"2025-10-10T00:00:00"}
