{"id":"https://openalex.org/W2474973645","doi":"https://doi.org/10.1093/bioinformatics/btw371","title":"deBGA: read alignment with de Bruijn graph-based seed and extension","display_name":"deBGA: read alignment with de Bruijn graph-based seed and extension","publication_year":2016,"publication_date":"2016-07-04","ids":{"openalex":"https://openalex.org/W2474973645","doi":"https://doi.org/10.1093/bioinformatics/btw371","mag":"2474973645","pmid":"https://pubmed.ncbi.nlm.nih.gov/27378303"},"language":"en","primary_location":{"id":"doi:10.1093/bioinformatics/btw371","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btw371","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/32/21/3224/7889593/btw371.pdf","source":{"id":"https://openalex.org/S52395412","display_name":"Bioinformatics","issn_l":"1367-4803","issn":["1367-4803","1367-4811"],"is_oa":false,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310311648","host_organization_name":"Oxford University Press","host_organization_lineage":["https://openalex.org/P4310311648","https://openalex.org/P4310311647"],"host_organization_lineage_names":["Oxford University Press","University of Oxford"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Bioinformatics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://academic.oup.com/bioinformatics/article-pdf/32/21/3224/7889593/btw371.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100461657","display_name":"Bo Liu","orcid":"https://orcid.org/0000-0002-4414-4001"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bo Liu","raw_affiliation_strings":["1 Center for Bioinformatics, Harbin Institute of Technology, Harbin, Heilongjiang 150001, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"1 Center for Bioinformatics, Harbin Institute of Technology, Harbin, Heilongjiang 150001, China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102735907","display_name":"Hongzhe Guo","orcid":"https://orcid.org/0000-0002-5625-5438"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hongzhe Guo","raw_affiliation_strings":["1 Center for Bioinformatics, Harbin Institute of Technology, Harbin, Heilongjiang 150001, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"1 Center for Bioinformatics, Harbin Institute of Technology, Harbin, Heilongjiang 150001, China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5012113499","display_name":"Michael Brudno","orcid":"https://orcid.org/0000-0001-7947-2243"},"institutions":[{"id":"https://openalex.org/I185261750","display_name":"University of Toronto","ror":"https://ror.org/03dbr7087","country_code":"CA","type":"education","lineage":["https://openalex.org/I185261750"]},{"id":"https://openalex.org/I2801317318","display_name":"Hospital for Sick Children","ror":"https://ror.org/057q4rt57","country_code":"CA","type":"healthcare","lineage":["https://openalex.org/I2801317318"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Michael Brudno","raw_affiliation_strings":["2 Department of Computer Science, University of Toronto, ON M5S 3G4, Canada","3 Genetics and Genome Biology Program, The Hospital for Sick Children, Toronto, ON M5G 1L7, Canada","4 Centre for Computational Medicine, The Hospital for Sick Children, Toronto, ON M5G 1L7, Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"2 Department of Computer Science, University of Toronto, ON M5S 3G4, Canada","institution_ids":["https://openalex.org/I185261750"]},{"raw_affiliation_string":"3 Genetics and Genome Biology Program, The Hospital for Sick Children, Toronto, ON M5G 1L7, Canada","institution_ids":["https://openalex.org/I2801317318"]},{"raw_affiliation_string":"4 Centre for Computational Medicine, The Hospital for Sick Children, Toronto, ON M5G 1L7, Canada","institution_ids":["https://openalex.org/I2801317318"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100392447","display_name":"Yadong Wang","orcid":"https://orcid.org/0000-0001-6500-6217"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yadong Wang","raw_affiliation_strings":["1 Center for Bioinformatics, Harbin Institute of Technology, Harbin, Heilongjiang 150001, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"1 Center for Bioinformatics, Harbin Institute of Technology, Harbin, Heilongjiang 150001, China","institution_ids":["https://openalex.org/I204983213"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5100392447"],"corresponding_institution_ids":["https://openalex.org/I204983213"],"apc_list":{"value":3618,"currency":"USD","value_usd":3618},"apc_paid":null,"fwci":5.2967,"has_fulltext":false,"cited_by_count":105,"citation_normalized_percentile":{"value":0.96072896,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":100},"biblio":{"volume":"32","issue":"21","first_page":"3224","last_page":"3232"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.9908999800682068,"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":0.9908999800682068,"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/T13664","display_name":"Genome Rearrangement Algorithms","score":0.002400000113993883,"subfield":{"id":"https://openalex.org/subfields/1311","display_name":"Genetics"},"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/T11269","display_name":"Algorithms and Data Compression","score":0.0015999999595806003,"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/de-bruijn-graph","display_name":"De Bruijn graph","score":0.9374446868896484},{"id":"https://openalex.org/keywords/de-bruijn-sequence","display_name":"De Bruijn sequence","score":0.8192017078399658},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7954103946685791},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.5287083387374878},{"id":"https://openalex.org/keywords/limiting","display_name":"Limiting","score":0.4251047670841217},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.3722103238105774},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.08393460512161255}],"concepts":[{"id":"https://openalex.org/C20218877","wikidata":"https://www.wikidata.org/wiki/Q3066095","display_name":"De Bruijn graph","level":3,"score":0.9374446868896484},{"id":"https://openalex.org/C170320093","wikidata":"https://www.wikidata.org/wiki/Q1953457","display_name":"De Bruijn sequence","level":2,"score":0.8192017078399658},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7954103946685791},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.5287083387374878},{"id":"https://openalex.org/C188198153","wikidata":"https://www.wikidata.org/wiki/Q1613840","display_name":"Limiting","level":2,"score":0.4251047670841217},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3722103238105774},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.08393460512161255},{"id":"https://openalex.org/C78519656","wikidata":"https://www.wikidata.org/wiki/Q101333","display_name":"Mechanical engineering","level":1,"score":0.0},{"id":"https://openalex.org/C118615104","wikidata":"https://www.wikidata.org/wiki/Q121416","display_name":"Discrete mathematics","level":1,"score":0.0},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0}],"mesh":[{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000818","descriptor_name":"Animals","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000818","descriptor_name":"Animals","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000818","descriptor_name":"Animals","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":true},{"descriptor_ui":"D016678","descriptor_name":"Genome","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":true},{"descriptor_ui":"D017422","descriptor_name":"Sequence Analysis, DNA","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D017422","descriptor_name":"Sequence Analysis, DNA","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D017422","descriptor_name":"Sequence Analysis, DNA","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D059014","descriptor_name":"High-Throughput Nucleotide Sequencing","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D059014","descriptor_name":"High-Throughput Nucleotide Sequencing","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D059014","descriptor_name":"High-Throughput Nucleotide Sequencing","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false}],"locations_count":3,"locations":[{"id":"doi:10.1093/bioinformatics/btw371","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btw371","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/32/21/3224/7889593/btw371.pdf","source":{"id":"https://openalex.org/S52395412","display_name":"Bioinformatics","issn_l":"1367-4803","issn":["1367-4803","1367-4811"],"is_oa":false,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310311648","host_organization_name":"Oxford University Press","host_organization_lineage":["https://openalex.org/P4310311648","https://openalex.org/P4310311647"],"host_organization_lineage_names":["Oxford University Press","University of Oxford"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Bioinformatics","raw_type":"journal-article"},{"id":"pmid:27378303","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/27378303","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":"Bioinformatics (Oxford, England)","raw_type":null},{"id":"pmh:oai:open-archive.highwire.org:bioinfo:32/21/3224","is_oa":false,"landing_page_url":"http://bioinformatics.oxfordjournals.org/cgi/content/short/32/21/3224","pdf_url":null,"source":{"id":"https://openalex.org/S4406923041","display_name":"HighWire Press Open Archive","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"TEXT"}],"best_oa_location":{"id":"doi:10.1093/bioinformatics/btw371","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btw371","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/32/21/3224/7889593/btw371.pdf","source":{"id":"https://openalex.org/S52395412","display_name":"Bioinformatics","issn_l":"1367-4803","issn":["1367-4803","1367-4811"],"is_oa":false,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310311648","host_organization_name":"Oxford University Press","host_organization_lineage":["https://openalex.org/P4310311648","https://openalex.org/P4310311647"],"host_organization_lineage_names":["Oxford University Press","University of Oxford"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Bioinformatics","raw_type":"journal-article"},"sustainable_development_goals":[{"display_name":"Industry, innovation and infrastructure","id":"https://metadata.un.org/sdg/9","score":0.47999998927116394}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":36,"referenced_works":["https://openalex.org/W1544273448","https://openalex.org/W1912672559","https://openalex.org/W1978981589","https://openalex.org/W2001725958","https://openalex.org/W2011210839","https://openalex.org/W2022986961","https://openalex.org/W2025648894","https://openalex.org/W2032866129","https://openalex.org/W2046137036","https://openalex.org/W2055615325","https://openalex.org/W2066047071","https://openalex.org/W2075996757","https://openalex.org/W2078889228","https://openalex.org/W2089310071","https://openalex.org/W2093931624","https://openalex.org/W2095680943","https://openalex.org/W2096791516","https://openalex.org/W2098291606","https://openalex.org/W2103441770","https://openalex.org/W2122732537","https://openalex.org/W2129264270","https://openalex.org/W2132580017","https://openalex.org/W2136101247","https://openalex.org/W2137351413","https://openalex.org/W2146005104","https://openalex.org/W2147733682","https://openalex.org/W2159075303","https://openalex.org/W2166469005","https://openalex.org/W2167673155","https://openalex.org/W2168133698","https://openalex.org/W2169456326","https://openalex.org/W2170551349","https://openalex.org/W2180594373","https://openalex.org/W3098304617","https://openalex.org/W4237091274","https://openalex.org/W4247053599"],"related_works":["https://openalex.org/W2562683361","https://openalex.org/W3087469195","https://openalex.org/W3125399386","https://openalex.org/W2354744388","https://openalex.org/W2949121831","https://openalex.org/W3215786367","https://openalex.org/W4301429973","https://openalex.org/W2951695076","https://openalex.org/W1964377951","https://openalex.org/W2122316710"],"abstract_inverted_index":{"MOTIVATION:":[0],"As":[1],"high-throughput":[2],"sequencing":[3,133],"(HTS)":[4],"technology":[5,39],"becomes":[6],"ubiquitous":[7],"and":[8,94,119,147],"the":[9,26,58,128],"volume":[10],"of":[11,28,37,47,65,104,132],"data":[12,165],"continues":[13],"to":[14,43,61,67,83,87,126,144],"rise,":[15],"HTS":[16,38,85,151],"read":[17,30],"alignment":[18,31],"is":[19,53,92,107,157],"becoming":[20],"increasingly":[21],"rate-limiting,":[22],"which":[23],"keeps":[24],"pressing":[25],"development":[27],"novel":[29,35],"approaches.":[32],"Moreover,":[33],"promising":[34,139],"applications":[36],"require":[40],"aligning":[41,142],"reads":[42,66,86,143],"multiple":[44,68,145],"genomes":[45,146],"instead":[46],"a":[48,88,97,138],"single":[49],"reference;":[50],"however,":[51],"it":[52,123,136],"still":[54],"not":[55],"viable":[56],"for":[57,141],"state-of-the-art":[59,111],"aligners":[60],"align":[62,84],"large":[63],"numbers":[64],"genomes.":[69],"RESULTS:":[70],"We":[71],"propose":[72],"de":[73,98],"Bruijn":[74,99],"Graph-based":[75],"Aligner":[76],"(deBGA),":[77],"an":[78],"innovative":[79],"graph-based":[80,148],"seed-and-extension":[81],"algorithm":[82],"reference":[89],"genome":[90],"that":[91],"organized":[93],"indexed":[95],"using":[96],"graph.":[100],"With":[101],"its":[102],"well-handling":[103],"repeats,":[105],"deBGA":[106,156],"substantially":[108],"faster":[109],"than":[110],"approaches":[112],"while":[113],"maintaining":[114],"similar":[115],"or":[116],"higher":[117],"sensitivity":[118],"accuracy.":[120],"This":[121],"makes":[122],"particularly":[124],"well-suited":[125],"handle":[127],"rapidly":[129],"growing":[130],"volumes":[131],"data.":[134],"Furthermore,":[135],"provides":[137],"solution":[140],"references":[149],"in":[150],"applications.":[152],"AVAILABILITY":[153],"AND":[154],"IMPLEMENTATION:":[155],"available":[158,167],"at:":[159],"https://github.com/hitbc/deBGA":[160],"CONTACT:":[161],"ydwang@hit.edu.cnSupplementary":[162],"information:":[163],"Supplementary":[164],"are":[166],"at":[168],"Bioinformatics":[169],"online.":[170]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":12},{"year":2023,"cited_by_count":6},{"year":2022,"cited_by_count":19},{"year":2021,"cited_by_count":14},{"year":2020,"cited_by_count":18},{"year":2019,"cited_by_count":16},{"year":2018,"cited_by_count":8},{"year":2017,"cited_by_count":7}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}