{"id":"https://openalex.org/W4399027736","doi":"https://doi.org/10.1186/s13015-024-00254-6","title":"Compression algorithm for colored de Bruijn graphs","display_name":"Compression algorithm for colored de Bruijn graphs","publication_year":2024,"publication_date":"2024-05-26","ids":{"openalex":"https://openalex.org/W4399027736","doi":"https://doi.org/10.1186/s13015-024-00254-6","pmid":"https://pubmed.ncbi.nlm.nih.gov/38797858"},"language":"en","primary_location":{"id":"doi:10.1186/s13015-024-00254-6","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13015-024-00254-6","pdf_url":"https://almob.biomedcentral.com/counter/pdf/10.1186/s13015-024-00254-6","source":{"id":"https://openalex.org/S205663195","display_name":"Algorithms for Molecular Biology","issn_l":"1748-7188","issn":["1748-7188"],"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":"Algorithms for Molecular Biology","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://almob.biomedcentral.com/counter/pdf/10.1186/s13015-024-00254-6","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5055479093","display_name":"Amatur Rahman","orcid":"https://orcid.org/0000-0002-9166-1220"},"institutions":[{"id":"https://openalex.org/I130769515","display_name":"Pennsylvania State University","ror":"https://ror.org/04p491231","country_code":"US","type":"education","lineage":["https://openalex.org/I130769515"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Amatur Rahman","raw_affiliation_strings":["Department of Computer Science and Engineering, The Pennsylvania State University, University Park, PA, 16802, USA. amatur003@gmail.com","Department of Computer Science and Engineering, The Pennsylvania State University, University Park, PA, 16802, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, The Pennsylvania State University, University Park, PA, 16802, USA. amatur003@gmail.com","institution_ids":["https://openalex.org/I130769515"]},{"raw_affiliation_string":"Department of Computer Science and Engineering, The Pennsylvania State University, University Park, PA, 16802, USA","institution_ids":["https://openalex.org/I130769515"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018499801","display_name":"Yoann Dufresne","orcid":"https://orcid.org/0000-0002-0930-8920"},"institutions":[{"id":"https://openalex.org/I157536573","display_name":"Institut Pasteur","ror":"https://ror.org/0495fxg12","country_code":"FR","type":"nonprofit","lineage":["https://openalex.org/I157536573"]},{"id":"https://openalex.org/I204730241","display_name":"Universit\u00e9 Paris Cit\u00e9","ror":"https://ror.org/05f82e368","country_code":"FR","type":"education","lineage":["https://openalex.org/I204730241"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Yoann Dufresne","raw_affiliation_strings":["Institut Pasteur, Universit\u00e9 Paris Cit\u00e9, Bioinformatics and Biostatistics Hub, Paris, 75015, France","Institut Pasteur, Universit\u00e9 Paris Cit\u00e9, G5 Sequence Bioinformatics, Paris, France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institut Pasteur, Universit\u00e9 Paris Cit\u00e9, Bioinformatics and Biostatistics Hub, Paris, 75015, France","institution_ids":["https://openalex.org/I157536573","https://openalex.org/I204730241"]},{"raw_affiliation_string":"Institut Pasteur, Universit\u00e9 Paris Cit\u00e9, G5 Sequence Bioinformatics, Paris, France","institution_ids":["https://openalex.org/I157536573","https://openalex.org/I204730241"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5066909672","display_name":"Paul Medvedev","orcid":"https://orcid.org/0000-0003-3143-594X"},"institutions":[{"id":"https://openalex.org/I130769515","display_name":"Pennsylvania State University","ror":"https://ror.org/04p491231","country_code":"US","type":"education","lineage":["https://openalex.org/I130769515"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Paul Medvedev","raw_affiliation_strings":["Department of Biochemistry and Molecular Biology, The Pennsylvania State University, University Park, PA, 16802, USA","Department of Computer Science and Engineering, The Pennsylvania State University, University Park, PA, 16802, USA","Huck Institutes of the Life Sciences, The Pennsylvania State University, University Park, PA, 16802, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Biochemistry and Molecular Biology, The Pennsylvania State University, University Park, PA, 16802, USA","institution_ids":["https://openalex.org/I130769515"]},{"raw_affiliation_string":"Department of Computer Science and Engineering, The Pennsylvania State University, University Park, PA, 16802, USA","institution_ids":["https://openalex.org/I130769515"]},{"raw_affiliation_string":"Huck Institutes of the Life Sciences, The Pennsylvania State University, University Park, PA, 16802, USA","institution_ids":["https://openalex.org/I130769515"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5055479093"],"corresponding_institution_ids":["https://openalex.org/I130769515"],"apc_list":{"value":2290,"currency":"USD","value_usd":2290},"apc_paid":{"value":2290,"currency":"USD","value_usd":2290},"fwci":0.9517,"has_fulltext":true,"cited_by_count":4,"citation_normalized_percentile":{"value":0.78412486,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":98},"biblio":{"volume":"19","issue":"1","first_page":"20","last_page":"20"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11269","display_name":"Algorithms and Data Compression","score":0.9990000128746033,"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"}},"topics":[{"id":"https://openalex.org/T11269","display_name":"Algorithms and Data Compression","score":0.9990000128746033,"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/T12029","display_name":"DNA and Biological Computing","score":0.9847000241279602,"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/T12162","display_name":"Cellular Automata and Applications","score":0.9775999784469604,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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/computer-science","display_name":"Computer science","score":0.788029670715332},{"id":"https://openalex.org/keywords/de-bruijn-sequence","display_name":"De Bruijn sequence","score":0.5481194257736206},{"id":"https://openalex.org/keywords/compression","display_name":"Compression (physics)","score":0.5271921753883362},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.47990095615386963},{"id":"https://openalex.org/keywords/colored","display_name":"Colored","score":0.4639859199523926},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.3446088433265686},{"id":"https://openalex.org/keywords/combinatorics","display_name":"Combinatorics","score":0.2336723506450653},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.16511452198028564},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.07826569676399231}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.788029670715332},{"id":"https://openalex.org/C170320093","wikidata":"https://www.wikidata.org/wiki/Q1953457","display_name":"De Bruijn sequence","level":2,"score":0.5481194257736206},{"id":"https://openalex.org/C180016635","wikidata":"https://www.wikidata.org/wiki/Q2712821","display_name":"Compression (physics)","level":2,"score":0.5271921753883362},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.47990095615386963},{"id":"https://openalex.org/C2778307483","wikidata":"https://www.wikidata.org/wiki/Q5149038","display_name":"Colored","level":2,"score":0.4639859199523926},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3446088433265686},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.2336723506450653},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.16511452198028564},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.07826569676399231},{"id":"https://openalex.org/C97355855","wikidata":"https://www.wikidata.org/wiki/Q11473","display_name":"Thermodynamics","level":1,"score":0.0},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.0},{"id":"https://openalex.org/C159985019","wikidata":"https://www.wikidata.org/wiki/Q181790","display_name":"Composite material","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1186/s13015-024-00254-6","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13015-024-00254-6","pdf_url":"https://almob.biomedcentral.com/counter/pdf/10.1186/s13015-024-00254-6","source":{"id":"https://openalex.org/S205663195","display_name":"Algorithms for Molecular Biology","issn_l":"1748-7188","issn":["1748-7188"],"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":"Algorithms for Molecular Biology","raw_type":"journal-article"},{"id":"pmid:38797858","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/38797858","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":"Algorithms for molecular biology : AMB","raw_type":null},{"id":"pmh:oai:pubmedcentral.nih.gov:11129398","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/11129398","pdf_url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC11129398/pdf/13015_2024_Article_254.pdf","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":"Algorithms Mol Biol","raw_type":"Text"},{"id":"pmh:oai:doaj.org/article:752476abc619485db84d6a7a6b54552b","is_oa":true,"landing_page_url":"https://doaj.org/article/752476abc619485db84d6a7a6b54552b","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":"Algorithms for Molecular Biology, Vol 19, Iss 1, Pp 1-11 (2024)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1186/s13015-024-00254-6","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13015-024-00254-6","pdf_url":"https://almob.biomedcentral.com/counter/pdf/10.1186/s13015-024-00254-6","source":{"id":"https://openalex.org/S205663195","display_name":"Algorithms for Molecular Biology","issn_l":"1748-7188","issn":["1748-7188"],"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":"Algorithms for Molecular Biology","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G174627229","display_name":"Frameworks: Re-Engineering Galaxy for Performance, Scalability and Energy Efficiency","funder_award_id":"1931531","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G318861138","display_name":"Leveraging k-mer sketching statistics to enhance metagenomic methods and alignment algorithms","funder_award_id":"5r01gm146462-02","funder_id":"https://openalex.org/F4320332161","funder_display_name":"National Institutes of Health"},{"id":"https://openalex.org/G347575844","display_name":null,"funder_award_id":"R01 GM146462","funder_id":"https://openalex.org/F4320337354","funder_display_name":"National Institute of General Medical Sciences"},{"id":"https://openalex.org/G434337789","display_name":null,"funder_award_id":"HORIZON2020","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"},{"id":"https://openalex.org/G5229109214","display_name":"Computation, Bioinformatics, and Statistics (CBIOS) Training Program","funder_award_id":"5t32gm102057-07","funder_id":"https://openalex.org/F4320332161","funder_display_name":"National Institutes of Health"},{"id":"https://openalex.org/G6636646442","display_name":"A k-mer-based search engine for sequencing databases","funder_award_id":"2138585","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G7440903218","display_name":"ALgorithms for PAngenome Computational Analysis","funder_award_id":"956229","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320320300","display_name":"European Commission","ror":"https://ror.org/00k4n6c32"},{"id":"https://openalex.org/F4320320883","display_name":"Agence Nationale de la Recherche","ror":"https://ror.org/00rbzpz17"},{"id":"https://openalex.org/F4320332161","display_name":"National Institutes of Health","ror":"https://ror.org/01cwqze88"},{"id":"https://openalex.org/F4320337354","display_name":"National Institute of General Medical Sciences","ror":"https://ror.org/04q48ey07"}],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4399027736.pdf"},"referenced_works_count":28,"referenced_works":["https://openalex.org/W1848935688","https://openalex.org/W2010361633","https://openalex.org/W2146005787","https://openalex.org/W2266239166","https://openalex.org/W2583363792","https://openalex.org/W2592811885","https://openalex.org/W2802889540","https://openalex.org/W2913847081","https://openalex.org/W2954828876","https://openalex.org/W2969627863","https://openalex.org/W2979069693","https://openalex.org/W3011785159","https://openalex.org/W3012149649","https://openalex.org/W3018162653","https://openalex.org/W3043153155","https://openalex.org/W3085875665","https://openalex.org/W3113074526","https://openalex.org/W3150463527","https://openalex.org/W3175899557","https://openalex.org/W3178792299","https://openalex.org/W4225502295","https://openalex.org/W4282946044","https://openalex.org/W4288692468","https://openalex.org/W4295087956","https://openalex.org/W4307607783","https://openalex.org/W4322008640","https://openalex.org/W4378783302","https://openalex.org/W4382632370"],"related_works":["https://openalex.org/W3198016531","https://openalex.org/W127787461","https://openalex.org/W2039773446","https://openalex.org/W1998517951","https://openalex.org/W2397939707","https://openalex.org/W2126473010","https://openalex.org/W2122316710","https://openalex.org/W2951695076","https://openalex.org/W4301429973","https://openalex.org/W1964377951"],"abstract_inverted_index":{"A":[0],"colored":[1,130,147],"de":[2,26,131,148],"Bruijn":[3,27,132,149],"graph":[4,70],"(also":[5],"called":[6,155],"a":[7,13,21,32,49,110,125],"set":[8,14,22],"of":[9,15,23,34,104,142],"k-mer":[10,19,143],"sets),":[11],"is":[12,193],"k-mers":[16],"with":[17,178],"every":[18],"assigned":[20],"colors.":[24],"Colored":[25],"graphs":[28,133],"are":[29],"used":[30],"in":[31],"variety":[33],"applications,":[35],"including":[36,160],"variant":[37],"calling,":[38],"genome":[39],"assembly,":[40],"and":[41,55,92,117,145,164,175],"database":[42],"search.":[43],"However,":[44,77],"their":[45],"size":[46],"has":[47,108],"posed":[48],"scalability":[50],"challenge":[51],"to":[52,67,85,112,134,183],"algorithm":[53],"developers":[54],"users.":[56],"There":[57],"have":[58,98],"been":[59,109],"numerous":[60],"indexing":[61,146],"data":[62,91,163],"structures":[63],"proposed":[64],"that":[65,128],"allow":[66],"store":[68],"the":[69,89],"compactly":[71],"while":[72],"supporting":[73],"fast":[74],"query":[75],"operations.":[76],"disk":[78],"compression":[79,106,141,170],"algorithms,":[80],"which":[81],"do":[82],"not":[83],"need":[84],"support":[86],"queries":[87],"on":[88,137,157],"compressed":[90],"can":[93],"thus":[94],"be":[95],"more":[96],"space-efficient,":[97],"received":[99],"little":[100],"attention.":[101],"The":[102,191],"dearth":[103],"specialized":[105],"tools":[107,174],"detriment":[111],"tool":[113,115,127,181],"developers,":[114],"users,":[116],"reproducibility":[118],"efforts.":[119],"In":[120],"this":[121],"paper,":[122],"we":[123],"develop":[124],"new":[126],"compresses":[129],"disk,":[135],"building":[136],"previous":[138],"ideas":[139],"for":[140],"sets":[144],"graphs.":[150],"We":[151],"test":[152],"our":[153],"tool,":[154],"ESS-color,":[156],"various":[158],"datasets,":[159,177],"both":[161],"sequencing":[162],"whole":[165],"genomes.":[166],"ESS-color":[167],"achieves":[168],"better":[169],"than":[171,187],"all":[172,176],"evaluated":[173],"no":[179],"other":[180],"able":[182],"consistently":[184],"achieve":[185],"less":[186],"44%":[188],"space":[189],"overhead.":[190],"software":[192],"available":[194],"at":[195],"http://github.com/medvedevgroup/ESSColor":[196],".":[197]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":2}],"updated_date":"2026-08-06T08:24:18.245995","created_date":"2025-10-10T00:00:00"}
