{"id":"https://openalex.org/W7214345101","doi":"https://doi.org/10.64898/2026.09.20.753062","title":"RosaSeed: Faster and Accurate Short Read Alignment Using a Configurable Seeding Strategy","display_name":"RosaSeed: Faster and Accurate Short Read Alignment Using a Configurable Seeding Strategy","publication_year":2026,"publication_date":"2026-09-25","ids":{"openalex":"https://openalex.org/W7214345101","doi":"https://doi.org/10.64898/2026.09.20.753062"},"language":"en","primary_location":{"id":"doi:10.64898/2026.09.20.753062","doi":"https://doi.org/10.64898/2026.09.20.753062","is_oa":true,"landing_page_url":"https://doi.org/10.64898/2026.09.20.753062","pdf_url":"https://www.biorxiv.org/content/biorxiv/early/2026/09/25/2026.09.20.753062.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","license_id":"https://openalex.org/licenses/cc-by","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/2026/09/25/2026.09.20.753062.full.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5050580238","display_name":"S. Girish Gandhi","orcid":"https://orcid.org/0000-0002-0974-1302","observed_orcids":["https://orcid.org/0000-0002-0974-1302"]},"institutions":[{"id":"https://openalex.org/I154425047","display_name":"University of Alberta","ror":"https://ror.org/0160cpw27","country_code":"CA","type":"education","lineage":["https://openalex.org/I154425047"]}],"countries":["CA"],"is_corresponding":true,"raw_author_name":"Shyama M. Gandhi","raw_affiliation_strings":["Department of Electrical and Computer Engineering, University of Alberta, 9211\u2013116 St. NW, Suite #11-203, Edmonton, AB, T6G 1H9, Canada"],"raw_orcid":"https://orcid.org/0000-0002-0974-1302","affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, University of Alberta, 9211\u2013116 St. NW, Suite #11-203, Edmonton, AB, T6G 1H9, Canada","institution_ids":["https://openalex.org/I154425047"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5013568704","display_name":"B.F. Cockburn","orcid":"https://orcid.org/0000-0002-4340-8394","observed_orcids":["https://orcid.org/0000-0002-4340-8394"]},"institutions":[{"id":"https://openalex.org/I154425047","display_name":"University of Alberta","ror":"https://ror.org/0160cpw27","country_code":"CA","type":"education","lineage":["https://openalex.org/I154425047"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Bruce F. Cockburn","raw_affiliation_strings":["Department of Electrical and Computer Engineering, University of Alberta, 9211\u2013116 St. NW, Suite #11-203, Edmonton, AB, T6G 1H9, Canada"],"raw_orcid":"https://orcid.org/0000-0002-4340-8394","affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, University of Alberta, 9211\u2013116 St. NW, Suite #11-203, Edmonton, AB, T6G 1H9, Canada","institution_ids":["https://openalex.org/I154425047"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5050580238"],"corresponding_institution_ids":["https://openalex.org/I154425047"],"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":0.8295999765396118,"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":0.8295999765396118,"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":0.16699999570846558,"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/T12946","display_name":"Fractal and DNA sequence analysis","score":0.0008999999845400453,"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/short-read-alignment","display_name":"short-read alignment","score":0.7839999794960022},{"id":"https://openalex.org/keywords/seed-production","display_name":"seed production","score":0.7739999890327454},{"id":"https://openalex.org/keywords/ert","display_name":"ERT","score":0.335999995470047},{"id":"https://openalex.org/keywords/memory-usage","display_name":"memory usage","score":0.7429999709129333},{"id":"https://openalex.org/keywords/variant-calling","display_name":"variant calling","score":0.4880000054836273},{"id":"https://openalex.org/keywords/genomic-sequence-alignment","display_name":"genomic sequence alignment","score":0.36800000071525574},{"id":"https://openalex.org/keywords/fm-index","display_name":"FM-index","score":0.6589999794960022},{"id":"https://openalex.org/keywords/bowtie2","display_name":"Bowtie2","score":0.6039999723434448},{"id":"https://openalex.org/keywords/minimap2","display_name":"minimap2","score":0.9890000224113464},{"id":"https://openalex.org/keywords/stac3","display_name":"STAC3","score":0.460999995470047}],"concepts":[{"id":"https://openalex.org/C36248471","wikidata":"https://www.wikidata.org/wiki/Q7445669","display_name":"Seeding","level":2,"score":0.853600025177002},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7522000074386597},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.7231000065803528},{"id":"https://openalex.org/C49020025","wikidata":"https://www.wikidata.org/wiki/Q1059099","display_name":"Chaining","level":2,"score":0.6542999744415283},{"id":"https://openalex.org/C74912251","wikidata":"https://www.wikidata.org/wiki/Q6815727","display_name":"Memory footprint","level":2,"score":0.5493000149726868},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.5249999761581421},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.5013999938964844},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.4530999958515167},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.3824000060558319},{"id":"https://openalex.org/C113174947","wikidata":"https://www.wikidata.org/wiki/Q2859736","display_name":"Tree (set theory)","level":2,"score":0.3779999911785126},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.35839998722076416},{"id":"https://openalex.org/C132943942","wikidata":"https://www.wikidata.org/wiki/Q2562511","display_name":"Footprint","level":2,"score":0.34880000352859497},{"id":"https://openalex.org/C149629883","wikidata":"https://www.wikidata.org/wiki/Q660926","display_name":"Fraction (chemistry)","level":2,"score":0.3091000020503998},{"id":"https://openalex.org/C115537543","wikidata":"https://www.wikidata.org/wiki/Q165596","display_name":"Cache","level":2,"score":0.26660001277923584},{"id":"https://openalex.org/C111696304","wikidata":"https://www.wikidata.org/wiki/Q2303697","display_name":"Sorting","level":2,"score":0.2637999951839447},{"id":"https://openalex.org/C2776235265","wikidata":"https://www.wikidata.org/wiki/Q18392052","display_name":"Fragment (logic)","level":2,"score":0.25200000405311584}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.64898/2026.09.20.753062","doi":"https://doi.org/10.64898/2026.09.20.753062","is_oa":true,"landing_page_url":"https://doi.org/10.64898/2026.09.20.753062","pdf_url":"https://www.biorxiv.org/content/biorxiv/early/2026/09/25/2026.09.20.753062.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","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"bioRxiv","raw_type":"posted-content"}],"best_oa_location":{"id":"doi:10.64898/2026.09.20.753062","doi":"https://doi.org/10.64898/2026.09.20.753062","is_oa":true,"landing_page_url":"https://doi.org/10.64898/2026.09.20.753062","pdf_url":"https://www.biorxiv.org/content/biorxiv/early/2026/09/25/2026.09.20.753062.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","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"bioRxiv","raw_type":"posted-content"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320319946","display_name":"University of Alberta","ror":"https://ror.org/0160cpw27"},{"id":"https://openalex.org/F4320334593","display_name":"Natural Sciences and Engineering Research Council of Canada","ror":"https://ror.org/01h531d29"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7214345101.pdf","grobid_xml":"https://content.openalex.org/works/W7214345101.grobid-xml"},"referenced_works_count":27,"referenced_works":["https://openalex.org/W1919257374","https://openalex.org/W2066852475","https://openalex.org/W2076359272","https://openalex.org/W2103903744","https://openalex.org/W2108234281","https://openalex.org/W2154468535","https://openalex.org/W2158322625","https://openalex.org/W2189510244","https://openalex.org/W2889664156","https://openalex.org/W2892014603","https://openalex.org/W2951331911","https://openalex.org/W2953263404","https://openalex.org/W3008701988","https://openalex.org/W3089043377","https://openalex.org/W3128964673","https://openalex.org/W3189987728","https://openalex.org/W3206657624","https://openalex.org/W4205616172","https://openalex.org/W4220999759","https://openalex.org/W4309305890","https://openalex.org/W4311803917","https://openalex.org/W4391925485","https://openalex.org/W4394666350","https://openalex.org/W4404814486","https://openalex.org/W4413020599","https://openalex.org/W4414403753","https://openalex.org/W7164910087"],"related_works":["https://openalex.org/W7164910087","https://openalex.org/W2563989789","https://openalex.org/W3189987728","https://openalex.org/W4214950926","https://openalex.org/W3173768211","https://openalex.org/W3013878438","https://openalex.org/W4311803917","https://openalex.org/W7097099563","https://openalex.org/W2103441770","https://openalex.org/W6979734753"],"abstract_inverted_index":{"Abstract":[0],"Conventional":[1],"short":[2,27,86],"read":[3,28,87],"DNA":[4],"alignment":[5,29,40,66,95,130,136,197,309],"algorithms,":[6],"such":[7],"as":[8],"widely":[9],"used":[10],"BWA-MEM2,":[11,103],"devote":[12],"a":[13,26,33,118,126,210,235,254],"substantial":[14],"fraction":[15],"of":[16,47,122,129,185,202,208,314],"their":[17],"execution":[18,243],"time":[19],"to":[20,45,60,132,200,277,298,312],"seed":[21,152,161],"generation.":[22],"We":[23,113],"present":[24],"RosaSeed,":[25],"algorithm,":[30],"based":[31],"on":[32,81,221,281],"configurable":[34],"seeding":[35,53,91],"framework,":[36],"that":[37,46,124,201,313],"significantly":[38,133],"accelerates":[39],"while":[41,195,244,307],"maintaining":[42,196,308],"accuracy":[43,131,198],"comparable":[44,199,311],"BWA-MEM2.":[48,159,203,315],"RosaSeed":[49,78,144,180,218,286,317],"replaces":[50],"the":[51,61,107,135,205,282],"BWA-MEM2":[52,63],"kernel":[54],"and":[55,65,84,89,97,106,148,154,176,193,258,270,293],"directly":[56],"supplies":[57],"candidate":[58],"seeds":[59],"existing":[62],"chaining":[64],"extension":[67],"pipeline,":[68],"producing":[69,245],"standard":[70,248,261],"SAM":[71],"output":[72],"suitable":[73],"for":[74,241,275,303],"downstream":[75],"variant":[76,121],"analysis.":[77],"was":[79,267],"evaluated":[80],"both":[82,268],"simulated":[83],"real":[85],"datasets,":[88],"its":[90],"time,":[92,94,156],"fastqto-SAM":[93],"accuracy,":[96],"memory":[98],"footprint":[99],"were":[100],"compared":[101,115],"against":[102,116,219],"Minimap2,":[104,175],"Bowtie2,":[105],"Enumerated":[108],"Radix":[109],"Tree":[110],"(ERT)":[111],"algorithm.":[112],"also":[114],"ERT2,":[117,172,194],"proposed":[119],"simplified":[120],"ERT":[123,192],"sacrifices":[125],"small":[127],"amount":[128],"increase":[134],"throughput.":[137],"With":[138],"single-threaded":[139,242],"software":[140,279],"execution,":[141,265],"our":[142],"recommended":[143],"configuration":[145,233],"achieves":[146,234],"13.06\u00d7":[147],"3.85\u00d7":[149],"speedups":[150,165],"in":[151],"processing":[153,162],"fastq-to-SAM":[155,237,256],"respectively,":[157],"over":[158,168,171,174,178,239],"Corresponding":[160],"(and":[163],"fastq-to-SAM)":[164],"are":[166],"3.96\u00d7(2.48\u00d7)":[167],"ERT,":[169],"1.2\u00d7(1.44\u00d7)":[170],"4.82\u00d7(3.31\u00d7)":[173],"33.24\u00d7(10.83\u00d7)":[177],"Bowtie2.":[179],"requires":[181],"only":[182],"49.61":[183],"GB":[184],"peak":[186],"memory,":[187],"approximately":[188],"25%":[189],"less":[190],"than":[191,273],"Following":[204],"recent":[206],"release":[207],"minibwa,":[209],"prefetch-optimized":[211],"FM":[212],"index":[213],"aligner,":[214],"we":[215],"additionally":[216],"benchmarked":[217],"it":[220],"an":[222],"upgraded":[223],"24-core,":[224],"48-thread":[225],"AMD":[226],"Zen":[227,283],"3":[228,284],"workstation.":[229,285],"Our":[230],"speed-optimized":[231],"miniRosaSeed":[232,252,266],"2.12\u00d7":[236],"speedup":[238,257],"minibwa":[240,274],"2.58%":[246],"higher":[247,260],"accuracy.":[249,262],"Against":[250],"Strobealign,":[251],"reported":[253],"2.18\u00d7":[255],"3.1%":[259],"For":[263],"multi-threaded":[264],"faster":[269],"more":[271],"accurate":[272],"up":[276],"26":[278],"threads":[280],"provides":[287],"multiple":[288],"runtimememory":[289],"configurations,":[290],"spanning":[291],"memory-efficient":[292],"high-performance":[294],"strategies,":[295],"enabling":[296],"users":[297],"select":[299],"operating":[300],"points":[301],"appropriate":[302],"diverse":[304],"computational":[305],"environments":[306],"quality":[310],"The":[316],"source":[318],"code":[319],"is":[320],"publicly":[321],"available":[322],"at":[323],"https://github.com/smgandhi-18/RosaSeed":[324],".":[325]},"counts_by_year":[],"updated_date":"2026-11-09T13:22:03.289127","created_date":"2026-09-26T00:00:00"}