{"id":"https://openalex.org/W2759261668","doi":"https://doi.org/10.1093/bioinformatics/bty292","title":"A space and time-efficient index for the compacted colored de Bruijn graph","display_name":"A space and time-efficient index for the compacted colored de Bruijn graph","publication_year":2018,"publication_date":"2018-04-16","ids":{"openalex":"https://openalex.org/W2759261668","doi":"https://doi.org/10.1093/bioinformatics/bty292","mag":"2759261668","pmid":"https://pubmed.ncbi.nlm.nih.gov/29949982"},"language":"en","primary_location":{"id":"doi:10.1093/bioinformatics/bty292","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/bty292","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/34/13/i169/25098250/bty292.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":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","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":"hybrid","oa_url":"https://academic.oup.com/bioinformatics/article-pdf/34/13/i169/25098250/bty292.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5023979383","display_name":"Fatemeh Almodaresi","orcid":"https://orcid.org/0000-0003-0993-3600"},"institutions":[{"id":"https://openalex.org/I59553526","display_name":"Stony Brook University","ror":"https://ror.org/05qghxh33","country_code":"US","type":"education","lineage":["https://openalex.org/I59553526"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Fatemeh Almodaresi","raw_affiliation_strings":["Department of Computer Science, Stony Brook University, Stonybrook, NY, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Stony Brook University, Stonybrook, NY, USA","institution_ids":["https://openalex.org/I59553526"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040245011","display_name":"Hirak Sarkar","orcid":"https://orcid.org/0000-0003-3636-7384"},"institutions":[{"id":"https://openalex.org/I59553526","display_name":"Stony Brook University","ror":"https://ror.org/05qghxh33","country_code":"US","type":"education","lineage":["https://openalex.org/I59553526"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hirak Sarkar","raw_affiliation_strings":["Department of Computer Science, Stony Brook University, Stonybrook, NY, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Stony Brook University, Stonybrook, NY, USA","institution_ids":["https://openalex.org/I59553526"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085346602","display_name":"Avi Srivastava","orcid":"https://orcid.org/0000-0001-9798-2079"},"institutions":[{"id":"https://openalex.org/I59553526","display_name":"Stony Brook University","ror":"https://ror.org/05qghxh33","country_code":"US","type":"education","lineage":["https://openalex.org/I59553526"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Avi Srivastava","raw_affiliation_strings":["Department of Computer Science, Stony Brook University, Stonybrook, NY, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Stony Brook University, Stonybrook, NY, USA","institution_ids":["https://openalex.org/I59553526"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5014584023","display_name":"Rob Patro","orcid":"https://orcid.org/0000-0001-8463-1675"},"institutions":[{"id":"https://openalex.org/I59553526","display_name":"Stony Brook University","ror":"https://ror.org/05qghxh33","country_code":"US","type":"education","lineage":["https://openalex.org/I59553526"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Rob Patro","raw_affiliation_strings":["Department of Computer Science, Stony Brook University, Stonybrook, NY, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Stony Brook University, Stonybrook, NY, USA","institution_ids":["https://openalex.org/I59553526"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5014584023"],"corresponding_institution_ids":["https://openalex.org/I59553526"],"apc_list":{"value":3618,"currency":"USD","value_usd":3618},"apc_paid":{"value":3618,"currency":"USD","value_usd":3618},"fwci":4.1501,"has_fulltext":false,"cited_by_count":103,"citation_normalized_percentile":{"value":0.95144888,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":100},"biblio":{"volume":"34","issue":"13","first_page":"i169","last_page":"i177"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.8162000179290771,"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":0.8162000179290771,"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/T11269","display_name":"Algorithms and Data Compression","score":0.09709999710321426,"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/T13664","display_name":"Genome Rearrangement Algorithms","score":0.03790000081062317,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/search-engine-indexing","display_name":"Search engine indexing","score":0.7802871465682983},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7303402423858643},{"id":"https://openalex.org/keywords/de-bruijn-graph","display_name":"De Bruijn graph","score":0.6785581111907959},{"id":"https://openalex.org/keywords/de-bruijn-sequence","display_name":"De Bruijn sequence","score":0.6497513651847839},{"id":"https://openalex.org/keywords/data-structure","display_name":"Data structure","score":0.585578441619873},{"id":"https://openalex.org/keywords/hash-function","display_name":"Hash function","score":0.5802324414253235},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.4986152648925781},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.49698856472969055},{"id":"https://openalex.org/keywords/auxiliary-memory","display_name":"Auxiliary memory","score":0.4500737488269806},{"id":"https://openalex.org/keywords/suffix-array","display_name":"Suffix array","score":0.4145599603652954},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.2397235631942749},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.18887022137641907},{"id":"https://openalex.org/keywords/combinatorics","display_name":"Combinatorics","score":0.1569470763206482}],"concepts":[{"id":"https://openalex.org/C75165309","wikidata":"https://www.wikidata.org/wiki/Q2258979","display_name":"Search engine indexing","level":2,"score":0.7802871465682983},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7303402423858643},{"id":"https://openalex.org/C20218877","wikidata":"https://www.wikidata.org/wiki/Q3066095","display_name":"De Bruijn graph","level":3,"score":0.6785581111907959},{"id":"https://openalex.org/C170320093","wikidata":"https://www.wikidata.org/wiki/Q1953457","display_name":"De Bruijn sequence","level":2,"score":0.6497513651847839},{"id":"https://openalex.org/C162319229","wikidata":"https://www.wikidata.org/wiki/Q175263","display_name":"Data structure","level":2,"score":0.585578441619873},{"id":"https://openalex.org/C99138194","wikidata":"https://www.wikidata.org/wiki/Q183427","display_name":"Hash function","level":2,"score":0.5802324414253235},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.4986152648925781},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.49698856472969055},{"id":"https://openalex.org/C82687282","wikidata":"https://www.wikidata.org/wiki/Q66221","display_name":"Auxiliary memory","level":2,"score":0.4500737488269806},{"id":"https://openalex.org/C2779259728","wikidata":"https://www.wikidata.org/wiki/Q281472","display_name":"Suffix array","level":3,"score":0.4145599603652954},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.2397235631942749},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.18887022137641907},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.1569470763206482},{"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/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[{"descriptor_ui":"D000078326","descriptor_name":"Data Visualization","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000078326","descriptor_name":"Data Visualization","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000078326","descriptor_name":"Data Visualization","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":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":"D001419","descriptor_name":"Bacteria","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D001419","descriptor_name":"Bacteria","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D001419","descriptor_name":"Bacteria","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","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":"D015894","descriptor_name":"Genome, Human","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D015894","descriptor_name":"Genome, Human","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D015894","descriptor_name":"Genome, Human","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016680","descriptor_name":"Genome, Bacterial","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016680","descriptor_name":"Genome, Bacterial","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016680","descriptor_name":"Genome, Bacterial","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D017422","descriptor_name":"Sequence Analysis, DNA","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D017422","descriptor_name":"Sequence Analysis, DNA","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D017422","descriptor_name":"Sequence Analysis, DNA","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D017423","descriptor_name":"Sequence Analysis, RNA","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D017423","descriptor_name":"Sequence Analysis, RNA","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D017423","descriptor_name":"Sequence Analysis, RNA","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D020869","descriptor_name":"Gene Expression Profiling","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D020869","descriptor_name":"Gene Expression Profiling","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D020869","descriptor_name":"Gene Expression Profiling","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D023281","descriptor_name":"Genomics","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D023281","descriptor_name":"Genomics","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D023281","descriptor_name":"Genomics","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},{"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/bty292","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/bty292","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/34/13/i169/25098250/bty292.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":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Bioinformatics","raw_type":"journal-article"},{"id":"pmid:29949982","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/29949982","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:europepmc.org:4991145","is_oa":false,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/6022659","pdf_url":null,"source":{"id":"https://openalex.org/S4306400806","display_name":"Europe PMC (PubMed Central)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1303153112","host_organization_name":"European Bioinformatics Institute","host_organization_lineage":["https://openalex.org/I1303153112"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Text"}],"best_oa_location":{"id":"doi:10.1093/bioinformatics/bty292","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/bty292","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/34/13/i169/25098250/bty292.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":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Bioinformatics","raw_type":"journal-article"},"sustainable_development_goals":[{"display_name":"Partnerships for the goals","id":"https://metadata.un.org/sdg/17","score":0.4399999976158142}],"awards":[{"id":"https://openalex.org/G7536231128","display_name":null,"funder_award_id":"BBSRC-NSF/BIO-1564917","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W1813440684","https://openalex.org/W1868469711","https://openalex.org/W2000586119","https://openalex.org/W2003347102","https://openalex.org/W2010361633","https://openalex.org/W2011657487","https://openalex.org/W2102278945","https://openalex.org/W2103441770","https://openalex.org/W2110905563","https://openalex.org/W2112113834","https://openalex.org/W2124985265","https://openalex.org/W2126419817","https://openalex.org/W2129264270","https://openalex.org/W2136651963","https://openalex.org/W2159954944","https://openalex.org/W2169456326","https://openalex.org/W2170551349","https://openalex.org/W2272733715","https://openalex.org/W2278452282","https://openalex.org/W2320964193","https://openalex.org/W2323326409","https://openalex.org/W2438121987","https://openalex.org/W2474973645","https://openalex.org/W2500932352","https://openalex.org/W2603734366","https://openalex.org/W2952152744","https://openalex.org/W2952379095","https://openalex.org/W2952379406","https://openalex.org/W2963158913","https://openalex.org/W6695144035"],"related_works":["https://openalex.org/W2562683361","https://openalex.org/W3087469195","https://openalex.org/W2354744388","https://openalex.org/W3125399386","https://openalex.org/W2949121831","https://openalex.org/W3215786367","https://openalex.org/W1908987670","https://openalex.org/W2756186577","https://openalex.org/W2735897904","https://openalex.org/W4391943936"],"abstract_inverted_index":{"Motivation:":[0],"Indexing":[1],"reference":[2,120,153,307],"sequences":[3,121],"for":[4,16,30,54,133,145,268,280,302],"search-both":[5],"individual":[6],"genomes":[7],"and":[8,44,80,109,117,135,149,198,208,213,237,297,300,352,359,369],"collections":[9],"of":[10,119,151,162,181,184,240,314,331,341,354],"genomes-is":[11],"an":[12,63,168,312],"important":[13],"building":[14,232],"block":[15],"many":[17],"sequence":[18,55,84],"analysis":[19],"tasks.":[20],"Much":[21],"work":[22],"has":[23,57,90,170],"been":[24,59,91],"dedicated":[25],"to":[26,68,72,81,94,96,203,258,275,317],"developing":[27],"full-text":[28],"indices":[29],"genomic":[31],"sequences,":[32],"based":[33],"on":[34,305],"data":[35,65,131,246,377],"structures":[36,188],"such":[37,99,102],"as":[38,62,93,114,167],"the":[39,42,45,48,115,137,152,160,163,173,179,204,255,273,284,318,329,349],"suffix":[40],"array,":[41],"BWT":[43],"FM-index.":[46],"However,":[47],"de":[49,140,164],"Bruijn":[50,141,165],"graph,":[51,142],"commonly":[52],"used":[53],"assembly,":[56],"recently":[58],"gaining":[60],"attention":[61,89],"indexing":[64,136],"structure,":[66,79,101],"due":[67],"its":[69],"natural":[70],"ability":[71,274],"represent":[73],"multiple":[74],"references":[75],"using":[76],"a":[77,100,129,225,265,281,292],"graphical":[78],"collapse":[82],"highly-repetitive":[83],"regions.":[85],"Yet,":[86],"much":[87],"less":[88],"given":[92],"how":[95],"best":[97],"index":[98,169,285,316],"that":[103,195,210,325],"queries":[104],"can":[105,347],"be":[106],"performed":[107],"efficiently":[108],"memory":[110],"usage":[111],"remains":[112],"practical":[113],"size":[116],"number":[118,180],"being":[122],"indexed":[123],"grows":[124],"large.":[125],"Results:":[126],"We":[127,287,323],"present":[128],"novel":[130],"structure":[132,247],"representing":[134],"compacted":[138],"colored":[139],"which":[143,271],"allows":[144,301],"efficient":[146,216],"pattern":[147,220],"matching":[148],"retrieval":[150],"information":[154],"associated":[155],"with":[156,337],"each":[157],"k-mer.":[158],"As":[159],"popularity":[161],"graph":[166],"increased":[171],"over":[172],"past":[174],"few":[175],"years,":[176],"so":[177],"have":[178],"proposed":[182],"representations":[183,242],"this":[185,269,289,315],"structure.":[186],"Existing":[187],"typically":[189],"fall":[190],"into":[191],"two":[192,229],"categories;":[193],"those":[194,209],"are":[196,211,378],"hashing-based":[197,260],"provide":[199,214],"very":[200],"fast":[201,250,303],"access":[202],"underlying":[205],"k-mer":[206,335],"information,":[207],"space-frugal":[212],"asymptotically":[215],"but":[217,333],"practically":[218,249],"slower":[219],"search.":[221],"Our":[222],"representation":[223,290],"achieves":[224],"compromise":[226],"between":[227,295],"these":[228],"extremes.":[230],"By":[231],"upon":[233],"minimum":[234],"perfect":[235],"hashing":[236],"making":[238],"use":[239],"succinct":[241],"where":[243],"applicable,":[244],"our":[245],"provides":[248,272],"lookup":[251],"while":[252],"greatly":[253],"reducing":[254],"space":[256,298],"compared":[257],"traditional":[259],"implementations.":[261],"Further,":[262],"we":[263,310,346],"describe":[264,311],"sampling":[266],"scheme":[267],"index,":[270],"trade":[276],"off":[277],"query":[278],"speed":[279,296,351],"reduction":[282],"in":[283,364],"size.":[286],"believe":[288],"strikes":[291],"desirable":[293],"balance":[294],"usage,":[299],"search":[304],"large":[306],"sequences.":[308],"Finally,":[309],"application":[313],"taxonomic":[319,355],"read":[320,356],"assignment":[321],"problem.":[322],"show":[324],"by":[326,339],"adopting,":[327],"essentially,":[328],"approach":[330],"Kraken,":[332],"replacing":[334],"presence":[336],"coverage":[338],"chains":[340],"consistent":[342],"unique":[343],"maximal":[344],"matches,":[345],"improve":[348],"space,":[350],"accuracy":[353],"assignment.":[357],"Availability":[358],"implementation:":[360],"pufferfish":[361],"is":[362,366,370],"written":[363],"C++11,":[365],"open":[367],"source,":[368],"available":[371,379],"at":[372,380],"https://github.com/COMBINE-lab/pufferfish.":[373],"Supplementary":[374,376],"information:":[375],"Bioinformatics":[381],"online.":[382]},"counts_by_year":[{"year":2026,"cited_by_count":5},{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":13},{"year":2023,"cited_by_count":14},{"year":2022,"cited_by_count":19},{"year":2021,"cited_by_count":16},{"year":2020,"cited_by_count":18},{"year":2019,"cited_by_count":9},{"year":2018,"cited_by_count":3}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}
