{"id":"https://openalex.org/W4417023074","doi":"https://doi.org/10.1177/15578666251400784","title":"Col-BWT: Pangenomic Seed Chaining with Maximal Matches Improves Read Classification","display_name":"Col-BWT: Pangenomic Seed Chaining with Maximal Matches Improves Read Classification","publication_year":2025,"publication_date":"2025-12-05","ids":{"openalex":"https://openalex.org/W4417023074","doi":"https://doi.org/10.1177/15578666251400784","pmid":"https://pubmed.ncbi.nlm.nih.gov/41346014"},"language":"en","primary_location":{"id":"doi:10.1177/15578666251400784","is_oa":false,"landing_page_url":"https://doi.org/10.1177/15578666251400784","pdf_url":null,"source":{"id":"https://openalex.org/S78571599","display_name":"Journal of Computational Biology","issn_l":"1066-5277","issn":["1066-5277","1557-8666"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320443","host_organization_name":"Mary Ann Liebert, Inc.","host_organization_lineage":["https://openalex.org/P4310320443"],"host_organization_lineage_names":["Mary Ann Liebert, Inc."],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Computational Biology","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC13049588/pdf/nihms-2156945.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5025703951","display_name":"Nathaniel K. Brown","orcid":"https://orcid.org/0000-0002-6201-2301"},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Nathaniel K. Brown","raw_affiliation_strings":["Department of Computer Science, Johns Hopkins University, Baltimore, Maryland, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Johns Hopkins University, Baltimore, Maryland, USA","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048838408","display_name":"Vikram S. Shivakumar","orcid":"https://orcid.org/0000-0002-1424-3711"},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Vikram S. Shivakumar","raw_affiliation_strings":["Department of Computer Science, Johns Hopkins University, Baltimore, Maryland, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Johns Hopkins University, Baltimore, Maryland, USA","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5009556658","display_name":"Ben Langmead","orcid":"https://orcid.org/0000-0003-2437-1976"},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ben Langmead","raw_affiliation_strings":["Department of Computer Science, Johns Hopkins University, Baltimore, Maryland, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Johns Hopkins University, Baltimore, Maryland, USA","institution_ids":["https://openalex.org/I145311948"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5025703951"],"corresponding_institution_ids":["https://openalex.org/I145311948"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.18866409,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"33","issue":"1","first_page":"168","last_page":"183"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11269","display_name":"Algorithms and Data Compression","score":0.39010000228881836,"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":0.39010000228881836,"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/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.10459999740123749,"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/T11719","display_name":"Data Quality and Management","score":0.08179999887943268,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/chaining","display_name":"Chaining","score":0.8751000165939331},{"id":"https://openalex.org/keywords/multiplicity","display_name":"Multiplicity (mathematics)","score":0.5842999815940857},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.519599974155426},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.436599999666214},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3873000144958496}],"concepts":[{"id":"https://openalex.org/C49020025","wikidata":"https://www.wikidata.org/wiki/Q1059099","display_name":"Chaining","level":2,"score":0.8751000165939331},{"id":"https://openalex.org/C156004811","wikidata":"https://www.wikidata.org/wiki/Q2228257","display_name":"Multiplicity (mathematics)","level":2,"score":0.5842999815940857},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.5257999897003174},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.519599974155426},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.46639999747276306},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.45579999685287476},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.436599999666214},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3873000144958496},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3865000009536743},{"id":"https://openalex.org/C142614401","wikidata":"https://www.wikidata.org/wiki/Q777433","display_name":"Forward chaining","level":3,"score":0.31610000133514404},{"id":"https://openalex.org/C2777382242","wikidata":"https://www.wikidata.org/wiki/Q6017816","display_name":"Index (typography)","level":2,"score":0.2935999929904938},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.29260000586509705},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2815999984741211},{"id":"https://openalex.org/C118615104","wikidata":"https://www.wikidata.org/wiki/Q121416","display_name":"Discrete mathematics","level":1,"score":0.26579999923706055}],"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":"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":"D019295","descriptor_name":"Computational Biology","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D023281","descriptor_name":"Genomics","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D023281","descriptor_name":"Genomics","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D023281","descriptor_name":"Genomics","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true}],"locations_count":3,"locations":[{"id":"doi:10.1177/15578666251400784","is_oa":false,"landing_page_url":"https://doi.org/10.1177/15578666251400784","pdf_url":null,"source":{"id":"https://openalex.org/S78571599","display_name":"Journal of Computational Biology","issn_l":"1066-5277","issn":["1066-5277","1557-8666"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320443","host_organization_name":"Mary Ann Liebert, Inc.","host_organization_lineage":["https://openalex.org/P4310320443"],"host_organization_lineage_names":["Mary Ann Liebert, Inc."],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Computational Biology","raw_type":"journal-article"},{"id":"pmid:41346014","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/41346014","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":"Journal of computational biology : a journal of computational molecular cell biology","raw_type":null},{"id":"pmh:oai:pubmedcentral.nih.gov:13049588","is_oa":true,"landing_page_url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC13049588/","pdf_url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC13049588/pdf/nihms-2156945.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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"J Comput Biol","raw_type":"Text"}],"best_oa_location":{"id":"pmh:oai:pubmedcentral.nih.gov:13049588","is_oa":true,"landing_page_url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC13049588/","pdf_url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC13049588/pdf/nihms-2156945.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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"J Comput Biol","raw_type":"Text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4417023074.pdf","grobid_xml":"https://content.openalex.org/works/W4417023074.grobid-xml"},"referenced_works_count":23,"referenced_works":["https://openalex.org/W2090021115","https://openalex.org/W2158874082","https://openalex.org/W2789843538","https://openalex.org/W2901237963","https://openalex.org/W2945228634","https://openalex.org/W2963653132","https://openalex.org/W2967058481","https://openalex.org/W3005528502","https://openalex.org/W3090465494","https://openalex.org/W3171564659","https://openalex.org/W4205330988","https://openalex.org/W4220999759","https://openalex.org/W4230945265","https://openalex.org/W4310786235","https://openalex.org/W4317698849","https://openalex.org/W4376133202","https://openalex.org/W4377013047","https://openalex.org/W4388652965","https://openalex.org/W4392452275","https://openalex.org/W4392616406","https://openalex.org/W4400140655","https://openalex.org/W4404770452","https://openalex.org/W4408512727"],"related_works":[],"abstract_inverted_index":{"Given":[0],"a":[1,40,58,100,120,164,206,212],"set":[2],"of":[3,8,27,47,73,122,163,208,217,267],"exact":[4,74],"matches,":[5],"chaining":[6,247],"consists":[7],"finding":[9],"those":[10,152],"which":[11,87],"are":[12],"colinear":[13,106],"with":[14,119,172,190,238,258],"respect":[15,191,239],"to":[16,43,78,145,184,187,192,240],"the":[17,25,44,85,125,161,181,193,264],"reference.":[18,194],"However,":[19],"this":[20,179,252],"requires":[21],"superlinear":[22,246],"time":[23,237],"in":[24,84,157,166,235],"number":[26],"matches":[28,137],"and":[29,139,169,231,262],"is":[30],"not":[31],"suitable":[32],"for":[33,205],"approaches":[34,261],"such":[35],"as":[36,90,93,269],"read":[37,55],"classification":[38,56,68,255],"using":[39],"pangenome":[41,59],"due":[42,183],"increased":[45],"multiplicity":[46],"matches.":[48,75],"While":[49],"compressed":[50,66],"full-text":[51],"indexes":[52],"enable":[53],"efficient":[54,271],"against":[57],"or":[60],"tree-of-life":[61],"index,":[62],"past":[63,259],"work":[64],"on":[65],"index":[67,204],"captures":[69],"only":[70],"fine-grained":[71,229],"colinearity":[72,114,189],"This":[76,195],"fails":[77],"capture":[79],"whether":[80],"seeds":[81],"appear":[82],"colinearly":[83],"reference,":[86],"we":[88,150,225],"denote":[89],"\u201ccoarse-grained":[91],"colinearity,\u201d":[92],"traditionally":[94],"described":[95],"by":[96,129],"chaining.":[97],"We":[98,117,132,177,249],"present":[99],"novel":[101],"data":[102],"structure,":[103],"col-BWT":[104,182,223],"(for":[105],"Burrows\u2013Wheeler":[107],"Transform":[108],"[BWT]),":[109],"that":[110,143,153,158,251],"additionally":[111],"obtains":[112],"coarse-grained":[113,232],"(\u201cchain\u201d)":[115],"statistics.":[116],"start":[118],"collection":[121,207],"strings,":[123],"avoiding":[124],"multiple-alignment":[126],"step":[127],"required":[128],"graph":[130],"approaches.":[131,248],"rapidly":[133],"compute":[134,227],"multi-maximal":[135],"unique":[136],"(multi-MUMs)":[138],"identify":[140],"BWT":[141,167,215],"sub-runs":[142],"correspond":[144],"these":[146],"multi-MUMs.":[147],"From":[148],"these,":[149],"select":[151],"can":[154],"be":[155],"\u201ctunneled,\u201d":[156],"they":[159],"satisfy":[160],"concept":[162],"tunnel":[165],"compression,":[168],"mark":[170],"them":[171],"their":[173],"corresponding":[174],"multi-MUM":[175],"identifier.":[176],"call":[178],"approach":[180],"its":[185],"ability":[186],"recognize":[188],"yields":[196],"an":[197],"O":[198],"(":[199],"r":[200,218],"+":[201],"n/d":[202],")-space":[203],"d":[209],"sequences":[210],"having":[211],"length-":[213],"n":[214],"consisting":[216],"maximal":[219],"equal-character":[220],"runs.":[221],"Using":[222],",":[224],"simultaneously":[226],"both":[228],"statistics":[230,234],"chain":[233],"linear":[236],"query":[241],"length,":[242],"faster":[243],"than":[244],"traditional":[245],"found":[250],"substantially":[253],"improves":[254],"accuracy":[256,268],"compared":[257],"compressed-indexing":[260],"reaches":[263],"same":[265],"level":[266],"less":[270],"alignment-based":[272],"methods.":[273]},"counts_by_year":[],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-12-05T00:00:00"}