{"id":"https://openalex.org/W7222963145","doi":"https://doi.org/10.64898/2026.10.18.759502","title":"DCSMAP: A Hybrid Linear-Pangenome Framework for Accurate and Efficient Read Alignment","display_name":"DCSMAP: A Hybrid Linear-Pangenome Framework for Accurate and Efficient Read Alignment","publication_year":2026,"publication_date":"2026-10-19","ids":{"openalex":"https://openalex.org/W7222963145","doi":"https://doi.org/10.64898/2026.10.18.759502"},"language":"en","primary_location":{"id":"doi:10.64898/2026.10.18.759502","doi":"https://doi.org/10.64898/2026.10.18.759502","is_oa":true,"landing_page_url":"https://doi.org/10.64898/2026.10.18.759502","pdf_url":"https://www.biorxiv.org/content/biorxiv/early/2026/10/19/2026.10.18.759502.full.pdf","source":{"id":"https://openalex.org/S4306402567","display_name":"bioRxiv (Cold Spring Harbor Laboratory)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I2750212522","host_organization_name":"Cold Spring Harbor Laboratory","host_organization_lineage":["https://openalex.org/I2750212522"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"bioRxiv","raw_type":"posted-content"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://www.biorxiv.org/content/biorxiv/early/2026/10/19/2026.10.18.759502.full.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5115602230","display_name":"Qi Yang","orcid":"https://orcid.org/0000-0002-4930-9661","observed_orcids":["https://orcid.org/0000-0002-4930-9661","https://orcid.org/0009-0008-6216-9262","https://orcid.org/0000-0001-8373-6096","https://orcid.org/0000-0002-0708-4388"]},"institutions":[{"id":"https://openalex.org/I4405257986","display_name":"BGI Research, Wuhan","ror":"https://ror.org/05x3m4218","country_code":"CN","type":"nonprofit","lineage":["https://openalex.org/I100135526","https://openalex.org/I4387153646","https://openalex.org/I4405257986"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qi Yang","raw_affiliation_strings":["BGI Research, Wuhan 430074, China"],"raw_orcid":"https://orcid.org/0009-0008-6216-9262","affiliations":[{"raw_affiliation_string":"BGI Research, Wuhan 430074, China","institution_ids":["https://openalex.org/I4405257986"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5128170515","display_name":"Ruiwen Wan","orcid":"https://orcid.org/0009-0001-5604-6126","observed_orcids":["https://orcid.org/0009-0001-5604-6126"]},"institutions":[{"id":"https://openalex.org/I4405257986","display_name":"BGI Research, Wuhan","ror":"https://ror.org/05x3m4218","country_code":"CN","type":"nonprofit","lineage":["https://openalex.org/I100135526","https://openalex.org/I4387153646","https://openalex.org/I4405257986"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ruiwen Wan","raw_affiliation_strings":["BGI Research, Wuhan 430074, China"],"raw_orcid":"https://orcid.org/0009-0001-5604-6126","affiliations":[{"raw_affiliation_string":"BGI Research, Wuhan 430074, China","institution_ids":["https://openalex.org/I4405257986"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038037118","display_name":"Gong Chun","orcid":"https://orcid.org/0009-0004-0902-0654","observed_orcids":["https://orcid.org/0009-0004-0902-0654"]},"institutions":[{"id":"https://openalex.org/I4405257986","display_name":"BGI Research, Wuhan","ror":"https://ror.org/05x3m4218","country_code":"CN","type":"nonprofit","lineage":["https://openalex.org/I100135526","https://openalex.org/I4387153646","https://openalex.org/I4405257986"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chun Gong","raw_affiliation_strings":["BGI Research, Wuhan 430074, China"],"raw_orcid":"https://orcid.org/0009-0004-0902-0654","affiliations":[{"raw_affiliation_string":"BGI Research, Wuhan 430074, China","institution_ids":["https://openalex.org/I4405257986"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103145930","display_name":"Shengkang Li","orcid":"https://orcid.org/0000-0002-6864-5644","observed_orcids":["https://orcid.org/0000-0002-6864-5644","https://orcid.org/0000-0001-6784-1873"]},"institutions":[{"id":"https://openalex.org/I100135526","display_name":"BGI Group (China)","ror":"https://ror.org/045pn2j94","country_code":"CN","type":"company","lineage":["https://openalex.org/I100135526"]},{"id":"https://openalex.org/I4387153646","display_name":"BGI Research","ror":"https://ror.org/05gsxrt27","country_code":"CN","type":"nonprofit","lineage":["https://openalex.org/I100135526","https://openalex.org/I4387153646"]},{"id":"https://openalex.org/I4405257986","display_name":"BGI Research, Wuhan","ror":"https://ror.org/05x3m4218","country_code":"CN","type":"nonprofit","lineage":["https://openalex.org/I100135526","https://openalex.org/I4387153646","https://openalex.org/I4405257986"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shengkang Li","raw_affiliation_strings":["BGI Research, Wuhan 430074, China","State Key Laboratory of Genome and Multi-omics Technologies, BGI Research, Shenzhen 518083, China"],"raw_orcid":"https://orcid.org/0000-0002-6864-5644","affiliations":[{"raw_affiliation_string":"BGI Research, Wuhan 430074, China","institution_ids":["https://openalex.org/I4405257986"]},{"raw_affiliation_string":"State Key Laboratory of Genome and Multi-omics Technologies, BGI Research, Shenzhen 518083, China","institution_ids":["https://openalex.org/I100135526","https://openalex.org/I4387153646"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100341650","display_name":"Yuxiang Li","orcid":"https://orcid.org/0000-0002-1575-3692","observed_orcids":["https://orcid.org/0000-0002-1575-3692","https://orcid.org/0009-0004-5386-8070"]},"institutions":[{"id":"https://openalex.org/I100135526","display_name":"BGI Group (China)","ror":"https://ror.org/045pn2j94","country_code":"CN","type":"company","lineage":["https://openalex.org/I100135526"]},{"id":"https://openalex.org/I4387153646","display_name":"BGI Research","ror":"https://ror.org/05gsxrt27","country_code":"CN","type":"nonprofit","lineage":["https://openalex.org/I100135526","https://openalex.org/I4387153646"]},{"id":"https://openalex.org/I4405257986","display_name":"BGI Research, Wuhan","ror":"https://ror.org/05x3m4218","country_code":"CN","type":"nonprofit","lineage":["https://openalex.org/I100135526","https://openalex.org/I4387153646","https://openalex.org/I4405257986"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yuxiang Li","raw_affiliation_strings":["BGI Research, Wuhan 430074, China","State Key Laboratory of Genome and Multi-omics Technologies, BGI Research, Shenzhen 518083, China"],"raw_orcid":"https://orcid.org/0000-0002-1575-3692","affiliations":[{"raw_affiliation_string":"BGI Research, Wuhan 430074, China","institution_ids":["https://openalex.org/I4405257986"]},{"raw_affiliation_string":"State Key Laboratory of Genome and Multi-omics Technologies, BGI Research, Shenzhen 518083, China","institution_ids":["https://openalex.org/I100135526","https://openalex.org/I4387153646"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100419755","display_name":"Yong Zhang","orcid":"https://orcid.org/0000-0001-9950-1793","observed_orcids":["https://orcid.org/0000-0001-9950-1793","https://orcid.org/0000-0001-6046-8420"]},"institutions":[{"id":"https://openalex.org/I100135526","display_name":"BGI Group (China)","ror":"https://ror.org/045pn2j94","country_code":"CN","type":"company","lineage":["https://openalex.org/I100135526"]},{"id":"https://openalex.org/I4387153646","display_name":"BGI Research","ror":"https://ror.org/05gsxrt27","country_code":"CN","type":"nonprofit","lineage":["https://openalex.org/I100135526","https://openalex.org/I4387153646"]},{"id":"https://openalex.org/I4405257986","display_name":"BGI Research, Wuhan","ror":"https://ror.org/05x3m4218","country_code":"CN","type":"nonprofit","lineage":["https://openalex.org/I100135526","https://openalex.org/I4387153646","https://openalex.org/I4405257986"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yong Zhang","raw_affiliation_strings":["BGI Research, Wuhan 430074, China","State Key Laboratory of Genome and Multi-omics Technologies, BGI Research, Shenzhen 518083, China"],"raw_orcid":"https://orcid.org/0000-0001-9950-1793","affiliations":[{"raw_affiliation_string":"BGI Research, Wuhan 430074, China","institution_ids":["https://openalex.org/I4405257986"]},{"raw_affiliation_string":"State Key Laboratory of Genome and Multi-omics Technologies, BGI Research, Shenzhen 518083, China","institution_ids":["https://openalex.org/I100135526","https://openalex.org/I4387153646"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5100341650","https://openalex.org/A5100419755"],"corresponding_institution_ids":["https://openalex.org/I100135526","https://openalex.org/I4387153646","https://openalex.org/I4405257986"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.9990000128746033,"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":0.9990000128746033,"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":0.00039999998989515007,"subfield":{"id":"https://openalex.org/subfields/2614","display_name":"Theoretical Computer Science"},"field":{"id":"https://openalex.org/fields/26","display_name":"Mathematics"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11213","display_name":"Genomic variations and chromosomal abnormalities","score":9.999999747378752e-05,"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/reference-bias","display_name":"reference bias","score":0.765999972820282},{"id":"https://openalex.org/keywords/indel-realignment","display_name":"indel realignment","score":0.8420000076293945},{"id":"https://openalex.org/keywords/variant-calling-accuracy","display_name":"variant calling accuracy","score":0.8809999823570251},{"id":"https://openalex.org/keywords/genome-in-a-bottle","display_name":"Genome in a Bottle","score":0.7350000143051147},{"id":"https://openalex.org/keywords/short-read-mapping","display_name":"short read mapping","score":0.4259999990463257}],"concepts":[{"id":"https://openalex.org/C119054055","wikidata":"https://www.wikidata.org/wiki/Q1576681","display_name":"Indel","level":5,"score":0.7042999863624573},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6413000226020813},{"id":"https://openalex.org/C177212765","wikidata":"https://www.wikidata.org/wiki/Q627335","display_name":"Workflow","level":2,"score":0.6126000285148621},{"id":"https://openalex.org/C192953774","wikidata":"https://www.wikidata.org/wiki/Q7307127","display_name":"Reference genome","level":4,"score":0.5577999949455261},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.5055999755859375},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.36809998750686646},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.36329999566078186},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.3522999882698059},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.3449999988079071},{"id":"https://openalex.org/C311688","wikidata":"https://www.wikidata.org/wiki/Q2393193","display_name":"Time complexity","level":2,"score":0.2797999978065491},{"id":"https://openalex.org/C2910714999","wikidata":"https://www.wikidata.org/wiki/Q1576681","display_name":"INDEL Mutation","level":5,"score":0.2782000005245209},{"id":"https://openalex.org/C3017489831","wikidata":"https://www.wikidata.org/wiki/Q2393193","display_name":"Running time","level":2,"score":0.2727999985218048},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2538999915122986}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.64898/2026.10.18.759502","doi":"https://doi.org/10.64898/2026.10.18.759502","is_oa":true,"landing_page_url":"https://doi.org/10.64898/2026.10.18.759502","pdf_url":"https://www.biorxiv.org/content/biorxiv/early/2026/10/19/2026.10.18.759502.full.pdf","source":{"id":"https://openalex.org/S4306402567","display_name":"bioRxiv (Cold Spring Harbor Laboratory)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I2750212522","host_organization_name":"Cold Spring Harbor Laboratory","host_organization_lineage":["https://openalex.org/I2750212522"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"bioRxiv","raw_type":"posted-content"}],"best_oa_location":{"id":"doi:10.64898/2026.10.18.759502","doi":"https://doi.org/10.64898/2026.10.18.759502","is_oa":true,"landing_page_url":"https://doi.org/10.64898/2026.10.18.759502","pdf_url":"https://www.biorxiv.org/content/biorxiv/early/2026/10/19/2026.10.18.759502.full.pdf","source":{"id":"https://openalex.org/S4306402567","display_name":"bioRxiv (Cold Spring Harbor Laboratory)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I2750212522","host_organization_name":"Cold Spring Harbor Laboratory","host_organization_lineage":["https://openalex.org/I2750212522"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"bioRxiv","raw_type":"posted-content"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7222963145.pdf","grobid_xml":"https://content.openalex.org/works/W7222963145.grobid-xml"},"referenced_works_count":25,"referenced_works":["https://openalex.org/W2108234281","https://openalex.org/W2113312463","https://openalex.org/W2119180969","https://openalex.org/W2583363792","https://openalex.org/W2789843538","https://openalex.org/W2888300707","https://openalex.org/W2889664156","https://openalex.org/W2909021353","https://openalex.org/W2929354011","https://openalex.org/W2950228679","https://openalex.org/W2951331911","https://openalex.org/W2953263404","https://openalex.org/W2966929769","https://openalex.org/W3014151936","https://openalex.org/W4200597270","https://openalex.org/W4210887696","https://openalex.org/W4226151130","https://openalex.org/W4376133202","https://openalex.org/W4394961089","https://openalex.org/W4402459535","https://openalex.org/W4414403753","https://openalex.org/W7117321952","https://openalex.org/W7133976005","https://openalex.org/W7136269604","https://openalex.org/W7170083314"],"related_works":["https://openalex.org/W7065183817","https://openalex.org/W7133976005","https://openalex.org/W1991468993","https://openalex.org/W4402459535","https://openalex.org/W7204481382","https://openalex.org/W4406727462","https://openalex.org/W3014151936","https://openalex.org/W2978714755","https://openalex.org/W4376224197","https://openalex.org/W4389262376"],"abstract_inverted_index":{"Abstract":[0],"Background":[1],"Linear-reference":[2],"read":[3,92,101],"alignment":[4,17,37,193,207],"is":[5,9],"computationally":[6],"efficient":[7],"but":[8],"susceptible":[10],"to":[11,45,116,121,138,146,161,208,233],"reference":[12,135,143],"bias,":[13],"whereas":[14],"pangenome":[15,48,150],"graph":[16,104,192,206],"better":[18],"represents":[19],"genetic":[20],"diversity":[21],"at":[22],"substantially":[23,133,223],"greater":[24],"computational":[25],"cost.":[26],"Findings":[27],"We":[28],"developed":[29],"DCSMAP,":[30],"a":[31,46,84,96,159,237],"hybrid":[32,108,131,180],"workflow":[33],"that":[34,129,147],"combines":[35],"linear":[36,140,213],"with":[38,210],"machine-learning-based":[39],"selection":[40],"of":[41,71,98,100,148,219],"reads":[42,209],"for":[43,103],"remapping":[44],"personalized":[47,220],"graph,":[49],"followed":[50],"by":[51,113,189,194,200],"local":[52],"indel":[53,198],"realignment.":[54],"An":[55],"XGBoost":[56],"classifier":[57],"trained":[58],"on":[59,73,236],"linear-alignment":[60],"features":[61],"achieved":[62,158],"an":[63,228],"area":[64],"under":[65],"the":[66,130,149,166,179,216],"receiver":[67],"operating":[68],"characteristic":[69],"curve":[70],"0.9831":[72],"held-out":[74],"test":[75],"data.":[76],"Across":[77],"17":[78],"runs":[79],"covering":[80],"seven":[81],"Genome":[82],"in":[83],"Bottle":[85],"samples,":[86],"two":[87,91],"sequencing":[88],"platforms,":[89],"and":[90,118,182,197,230],"lengths,":[93],"it":[94],"selected":[95],"mean":[97],"14.80%":[99],"pairs":[102],"remapping.":[105],"The":[106],"optimized":[107],"workflows":[109,132,170],"reduced":[110,134],"variant-calling":[111],"errors":[112],"46.66%":[114],"relative":[115,120,137],"BWA-MEM2":[117,139],"8.39%":[119],"vg":[122],"personalized-pangenome":[123,167],"alignment.":[124,151],"Heterozygous":[125],"allelic":[126],"balance":[127],"indicated":[128],"bias":[136,144],"alignment,":[141],"yielding":[142],"comparable":[145],"On":[152],"HG003":[153],"DNBSEQ":[154],"PE150":[155],"data,":[156],"DCSMAP":[157,226],"2":[160],"2.5":[162,190,201],"times":[163],"speedup":[164],"over":[165],"workflow;":[168],"both":[169,178],"used":[171],"32":[172],"threads.":[173],"Efficiency":[174],"gains":[175],"arose":[176],"from":[177],"architecture":[181],"tool-level":[183],"optimizations,":[184],"which":[185],"accelerated":[186],"personalized-graph":[187],"construction":[188],"times,":[191,196],"1.2":[195],"realignment":[199],"times.":[202],"Conclusions":[203],"Selectively":[204],"applying":[205],"potentially":[211],"unreliable":[212],"placements":[214],"retains":[215],"accuracy":[217],"benefits":[218],"pangenomes":[221],"while":[222],"reducing":[224],"computation.":[225],"provides":[227],"accurate":[229],"resource-efficient":[231],"approach":[232],"short-read":[234],"mapping":[235],"standard":[238],"CPU":[239],"server.":[240]},"counts_by_year":[],"updated_date":"2026-11-09T13:22:03.289127","created_date":"2026-10-20T00:00:00"}
