{"id":"https://openalex.org/W3182208245","doi":"https://doi.org/10.1093/bioinformatics/btab281","title":"Constructing small genome graphs via string compression","display_name":"Constructing small genome graphs via string compression","publication_year":2021,"publication_date":"2021-04-28","ids":{"openalex":"https://openalex.org/W3182208245","doi":"https://doi.org/10.1093/bioinformatics/btab281","mag":"3182208245","pmid":"https://pubmed.ncbi.nlm.nih.gov/34252955"},"language":"en","primary_location":{"id":"doi:10.1093/bioinformatics/btab281","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btab281","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/37/Supplement_1/i205/39620253/btab281.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","license_id":"https://openalex.org/licenses/cc-by","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/37/Supplement_1/i205/39620253/btab281.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5063377635","display_name":"Yutong Qiu","orcid":"https://orcid.org/0000-0001-6058-1212"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yutong Qiu","raw_affiliation_strings":["Computational Biology Department, School of Computer Science, Carnegie Mellon University , Pittsburgh, PA 15213, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computational Biology Department, School of Computer Science, Carnegie Mellon University , Pittsburgh, PA 15213, USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5113653378","display_name":"Carl Kingsford","orcid":null},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Carl Kingsford","raw_affiliation_strings":["Computational Biology Department, School of Computer Science, Carnegie Mellon University , Pittsburgh, PA 15213, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computational Biology Department, School of Computer Science, Carnegie Mellon University , Pittsburgh, PA 15213, USA","institution_ids":["https://openalex.org/I74973139"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5113653378"],"corresponding_institution_ids":["https://openalex.org/I74973139"],"apc_list":{"value":3618,"currency":"USD","value_usd":3618},"apc_paid":{"value":3618,"currency":"USD","value_usd":3618},"fwci":3.4121,"has_fulltext":true,"cited_by_count":21,"citation_normalized_percentile":{"value":0.9348175,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":100},"biblio":{"volume":"37","issue":"Supplement_1","first_page":"i205","last_page":"i213"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11269","display_name":"Algorithms and Data Compression","score":0.5873000025749207,"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":0.5873000025749207,"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":0.3935999870300293,"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/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.00419999985024333,"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/string","display_name":"String (physics)","score":0.7404057383537292},{"id":"https://openalex.org/keywords/genome","display_name":"Genome","score":0.5800145268440247},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5457507967948914},{"id":"https://openalex.org/keywords/computational-biology","display_name":"Computational biology","score":0.4097203016281128},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.40471237897872925},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.3850948214530945},{"id":"https://openalex.org/keywords/genetics","display_name":"Genetics","score":0.3095014691352844},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.254947304725647},{"id":"https://openalex.org/keywords/gene","display_name":"Gene","score":0.14182209968566895}],"concepts":[{"id":"https://openalex.org/C157486923","wikidata":"https://www.wikidata.org/wiki/Q1376436","display_name":"String (physics)","level":2,"score":0.7404057383537292},{"id":"https://openalex.org/C141231307","wikidata":"https://www.wikidata.org/wiki/Q7020","display_name":"Genome","level":3,"score":0.5800145268440247},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5457507967948914},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.4097203016281128},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.40471237897872925},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.3850948214530945},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.3095014691352844},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.254947304725647},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.14182209968566895},{"id":"https://openalex.org/C37914503","wikidata":"https://www.wikidata.org/wiki/Q156495","display_name":"Mathematical physics","level":1,"score":0.0}],"mesh":[{"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":"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":"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":"D044962","descriptor_name":"Data Compression","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D044962","descriptor_name":"Data Compression","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D044962","descriptor_name":"Data Compression","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true}],"locations_count":3,"locations":[{"id":"doi:10.1093/bioinformatics/btab281","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btab281","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/37/Supplement_1/i205/39620253/btab281.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","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Bioinformatics","raw_type":"journal-article"},{"id":"pmid:34252955","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/34252955","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:pubmedcentral.nih.gov:8275343","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/8275343","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":"Bioinformatics","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.1093/bioinformatics/btab281","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btab281","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/37/Supplement_1/i205/39620253/btab281.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","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Bioinformatics","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1310392732","display_name":null,"funder_award_id":"DBI-1937540","funder_id":"https://openalex.org/F4320332161","funder_display_name":"National Institutes of Health"},{"id":"https://openalex.org/G3023850491","display_name":null,"funder_award_id":"R01GM122935","funder_id":"https://openalex.org/F4320332161","funder_display_name":"National Institutes of Health"},{"id":"https://openalex.org/G3355402586","display_name":"Carl Kingsford Investigator Award","funder_award_id":"GBMF4554","funder_id":"https://openalex.org/F4320306202","funder_display_name":"Gordon and Betty Moore Foundation"},{"id":"https://openalex.org/G5836720286","display_name":null,"funder_award_id":"R01 GM122935","funder_id":"https://openalex.org/F4320337354","funder_display_name":"National Institute of General Medical Sciences"},{"id":"https://openalex.org/G6667550415","display_name":"IIBR:Informatics:Toward an Automated RNA-seq Bioinformatician","funder_award_id":"1937540","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G7686337660","display_name":null,"funder_award_id":"DBI-1937540","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"},{"id":"https://openalex.org/F4320306202","display_name":"Gordon and Betty Moore Foundation","ror":"https://ror.org/006wxqw41"},{"id":"https://openalex.org/F4320310207","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33"},{"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":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3182208245.pdf","grobid_xml":"https://content.openalex.org/works/W3182208245.grobid-xml"},"referenced_works_count":35,"referenced_works":["https://openalex.org/W1575413654","https://openalex.org/W1962019683","https://openalex.org/W1978981589","https://openalex.org/W2010361633","https://openalex.org/W2011210839","https://openalex.org/W2022126655","https://openalex.org/W2033005962","https://openalex.org/W2037219729","https://openalex.org/W2053393747","https://openalex.org/W2080721852","https://openalex.org/W2104549677","https://openalex.org/W2107745473","https://openalex.org/W2134761228","https://openalex.org/W2137661542","https://openalex.org/W2137892587","https://openalex.org/W2150131459","https://openalex.org/W2194172909","https://openalex.org/W2547528004","https://openalex.org/W2603734366","https://openalex.org/W2888300707","https://openalex.org/W2950122868","https://openalex.org/W2952366981","https://openalex.org/W2957382730","https://openalex.org/W2963158913","https://openalex.org/W2966459122","https://openalex.org/W2966929769","https://openalex.org/W2999349690","https://openalex.org/W3005228641","https://openalex.org/W3011785159","https://openalex.org/W3085875665","https://openalex.org/W3092652421","https://openalex.org/W3105559940","https://openalex.org/W3130788486","https://openalex.org/W4206067192","https://openalex.org/W4255659575"],"related_works":["https://openalex.org/W2086525401","https://openalex.org/W2006735166","https://openalex.org/W2079327011","https://openalex.org/W2053325634","https://openalex.org/W3178279768","https://openalex.org/W193851735","https://openalex.org/W2773861473","https://openalex.org/W1971903861","https://openalex.org/W3047903919","https://openalex.org/W40194678"],"abstract_inverted_index":{"MOTIVATION:":[0],"The":[1,106,214,244],"size":[2,115,132],"of":[3,19,45,54,80,95,116,123,133,220,230],"a":[4,31,34,37,93,162,167,193],"genome":[5,68,81,101,118,135,168,194,232],"graph-the":[6],"space":[7,190],"required":[8],"to":[9,29,33,65,186,191,201,235],"store":[10,192],"the":[11,17,26,42,48,52,57,61,76,84,114,117,131,134,139,146,173,188,211],"nodes,":[12],"node":[13,49],"labels":[14,50],"and":[15,51,83,103,151,223,237],"edges-affects":[16],"efficiency":[18],"operations":[20],"performed":[21],"on":[22,41,113,172,196],"it.":[23],"For":[24],"example,":[25],"time":[27,222],"complexity":[28],"align":[30],"sequence":[32],"graph":[35,38,119,169,195,224],"without":[36],"index":[39],"depends":[40],"total":[43],"number":[44,53,229],"characters":[46],"in":[47,56,75,109,121,218],"edges":[55],"graph.":[58],"This":[59],"raises":[60],"need":[62],"for":[63],"approaches":[64],"construct":[66],"space-efficient":[67],"graphs.":[69],"RESULTS:":[70],"We":[71,91],"point":[72],"out":[73],"similarities":[74],"string":[77],"encoding":[78],"mechanisms":[79],"graphs":[82,102,206,239],"external":[85],"pointer":[86],"macro":[87],"(EPM)":[88],"compression":[89,150],"model.":[90],"present":[92],"pair":[94],"linear-time":[96],"algorithms":[97,107],"that":[98,143,156,158],"transform":[99],"between":[100],"EPM-compressed":[104],"forms.":[105],"result":[108],"an":[110,124,153,227],"upper":[111],"bound":[112],"constructed":[120,170,207],"terms":[122,219],"optimal":[125],"EPM":[126],"compression.":[127],"To":[128],"further":[129],"reduce":[130,187],"graph,":[136],"we":[137,164,183],"propose":[138],"source":[140],"assignment":[141],"problem":[142,159],"optimizes":[144],"over":[145],"equivalent":[147],"choices":[148],"during":[149],"introduce":[152,165],"ILP":[154],"formulation":[155],"solves":[157],"optimally.":[160],"As":[161],"proof-of-concept,":[163],"RLZ-Graph,":[166,178],"based":[171],"relative":[174],"Lempel-Ziv":[175],"algorithm.":[176],"Using":[177],"across":[179],"all":[180],"human":[181,231],"chromosomes,":[182],"are":[184,255],"able":[185],"disk":[189],"average":[197],"by":[198,208,241],"40.7%":[199],"compared":[200,234],"colored":[202],"compacted":[203],"de":[204],"Bruijn":[205],"Bifrost":[209,236],"under":[210],"default":[212],"settings.":[213],"RLZ-Graph":[215,245],"scales":[216],"well":[217],"running":[221],"sizes":[225],"with":[226],"increasing":[228],"sequences":[233],"variation":[238],"produced":[240],"VGtoolkit.":[242],"AVAILABILITY:":[243],"software":[246],"is":[247],"available":[248,256],"at:":[249],"https://github.com/Kingsford-Group/rlzgraph.":[250],"SUPPLEMENTARY":[251],"INFORMATION:":[252],"Supplementary":[253],"data":[254],"at":[257],"Bioinformatics":[258],"online.":[259]},"counts_by_year":[{"year":2024,"cited_by_count":17},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":2}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}
