{"id":"https://openalex.org/W4311404396","doi":"https://doi.org/10.1093/bioinformatics/btac804","title":"Cloud-native distributed genomic pileup operations","display_name":"Cloud-native distributed genomic pileup operations","publication_year":2022,"publication_date":"2022-12-14","ids":{"openalex":"https://openalex.org/W4311404396","doi":"https://doi.org/10.1093/bioinformatics/btac804","pmid":"https://pubmed.ncbi.nlm.nih.gov/36515465"},"language":"en","primary_location":{"id":"doi:10.1093/bioinformatics/btac804","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btac804","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/39/1/btac804/48763654/btac804.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/39/1/btac804/48763654/btac804.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5018800555","display_name":"Marek Wiewi\u00f3rka","orcid":"https://orcid.org/0000-0002-8724-5646"},"institutions":[{"id":"https://openalex.org/I108403487","display_name":"Warsaw University of Technology","ror":"https://ror.org/00y0xnp53","country_code":"PL","type":"education","lineage":["https://openalex.org/I108403487"]},{"id":"https://openalex.org/I4210087266","display_name":"Institute of Computer Science","ror":"https://ror.org/003fvp964","country_code":"PL","type":"facility","lineage":["https://openalex.org/I4210087266","https://openalex.org/I99542240"]}],"countries":["PL"],"is_corresponding":false,"raw_author_name":"Marek Wiewi\u00f3rka","raw_affiliation_strings":["Institute of Computer Science, Warsaw University of Technology, Warsaw , Warsaw 00-661, Poland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Computer Science, Warsaw University of Technology, Warsaw , Warsaw 00-661, Poland","institution_ids":["https://openalex.org/I108403487","https://openalex.org/I4210087266"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5052597497","display_name":"Agnieszka Szmur\u0142o","orcid":"https://orcid.org/0000-0002-9192-7420"},"institutions":[{"id":"https://openalex.org/I108403487","display_name":"Warsaw University of Technology","ror":"https://ror.org/00y0xnp53","country_code":"PL","type":"education","lineage":["https://openalex.org/I108403487"]},{"id":"https://openalex.org/I4210087266","display_name":"Institute of Computer Science","ror":"https://ror.org/003fvp964","country_code":"PL","type":"facility","lineage":["https://openalex.org/I4210087266","https://openalex.org/I99542240"]}],"countries":["PL"],"is_corresponding":false,"raw_author_name":"Agnieszka Szmur\u0142o","raw_affiliation_strings":["Institute of Computer Science, Warsaw University of Technology, Warsaw , Warsaw 00-661, Poland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Computer Science, Warsaw University of Technology, Warsaw , Warsaw 00-661, Poland","institution_ids":["https://openalex.org/I108403487","https://openalex.org/I4210087266"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075195054","display_name":"Pawe\u0142 Stankiewicz","orcid":"https://orcid.org/0000-0002-6456-7490"},"institutions":[{"id":"https://openalex.org/I181547552","display_name":"Baylor College of Medicine","ror":"https://ror.org/02pttbw34","country_code":"US","type":"education","lineage":["https://openalex.org/I181547552","https://openalex.org/I2801539370"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Pawe\u0142 Stankiewicz","raw_affiliation_strings":["Department of Molecular and Human Genetics, Baylor College of Medicine , Houston, TX 77030, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Molecular and Human Genetics, Baylor College of Medicine , Houston, TX 77030, USA","institution_ids":["https://openalex.org/I181547552"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5079290300","display_name":"Tomasz Gambin","orcid":"https://orcid.org/0000-0002-0941-4571"},"institutions":[{"id":"https://openalex.org/I108403487","display_name":"Warsaw University of Technology","ror":"https://ror.org/00y0xnp53","country_code":"PL","type":"education","lineage":["https://openalex.org/I108403487"]},{"id":"https://openalex.org/I4210087266","display_name":"Institute of Computer Science","ror":"https://ror.org/003fvp964","country_code":"PL","type":"facility","lineage":["https://openalex.org/I4210087266","https://openalex.org/I99542240"]}],"countries":["PL"],"is_corresponding":true,"raw_author_name":"Tomasz Gambin","raw_affiliation_strings":["Institute of Computer Science, Warsaw University of Technology, Warsaw , Warsaw 00-661, Poland"],"raw_orcid":"https://orcid.org/0000-0002-0941-4571","affiliations":[{"raw_affiliation_string":"Institute of Computer Science, Warsaw University of Technology, Warsaw , Warsaw 00-661, Poland","institution_ids":["https://openalex.org/I108403487","https://openalex.org/I4210087266"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5079290300"],"corresponding_institution_ids":["https://openalex.org/I108403487","https://openalex.org/I4210087266"],"apc_list":{"value":3618,"currency":"USD","value_usd":3618},"apc_paid":{"value":3618,"currency":"USD","value_usd":3618},"fwci":0.0783,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.39395028,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":"39","issue":"1","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":0.7001000046730042,"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":0.7001000046730042,"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/T10222","display_name":"Genomics and Chromatin Dynamics","score":0.07450000196695328,"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/T10887","display_name":"Bioinformatics and Genomic Networks","score":0.033399999141693115,"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/cloud-computing","display_name":"Cloud computing","score":0.7712010145187378},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6301965117454529},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.2012152075767517}],"concepts":[{"id":"https://openalex.org/C79974875","wikidata":"https://www.wikidata.org/wiki/Q483639","display_name":"Cloud computing","level":2,"score":0.7712010145187378},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6301965117454529},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.2012152075767517}],"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":"D016678","descriptor_name":"Genome","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016678","descriptor_name":"Genome","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016678","descriptor_name":"Genome","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"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":4,"locations":[{"id":"doi:10.1093/bioinformatics/btac804","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btac804","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/39/1/btac804/48763654/btac804.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":"pmh:oai:pubmedcentral.nih.gov:9848050","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/9848050","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":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Bioinformatics","raw_type":"Text"},{"id":"pmid:36515465","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/36515465","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:digitalcommons.library.tmc.edu:baylor_docs-3287","is_oa":false,"landing_page_url":"https://digitalcommons.library.tmc.edu/baylor_docs/2314","pdf_url":null,"source":{"id":"https://openalex.org/S4377196655","display_name":"Digital Commons-TMC (Texas Medical Center)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1337852284","host_organization_name":"Texas Medical Center","host_organization_lineage":["https://openalex.org/I1337852284"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Faculty and Staff Publications","raw_type":"text"}],"best_oa_location":{"id":"doi:10.1093/bioinformatics/btac804","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btac804","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/39/1/btac804/48763654/btac804.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":[{"id":"https://metadata.un.org/sdg/9","score":0.44999998807907104,"display_name":"Industry, innovation and infrastructure"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":33,"referenced_works":["https://openalex.org/W1574680346","https://openalex.org/W1970326092","https://openalex.org/W2108234281","https://openalex.org/W2119180969","https://openalex.org/W2128505445","https://openalex.org/W2150131459","https://openalex.org/W2155943701","https://openalex.org/W2160363604","https://openalex.org/W2786396740","https://openalex.org/W2801277819","https://openalex.org/W2886161096","https://openalex.org/W2900668849","https://openalex.org/W2944034856","https://openalex.org/W2950006249","https://openalex.org/W2950662571","https://openalex.org/W2965904427","https://openalex.org/W2972702295","https://openalex.org/W2974197905","https://openalex.org/W2996823610","https://openalex.org/W3014232442","https://openalex.org/W3022744125","https://openalex.org/W3036330109","https://openalex.org/W3045563287","https://openalex.org/W3082037286","https://openalex.org/W3096043732","https://openalex.org/W3131055609","https://openalex.org/W3135330087","https://openalex.org/W3184642093","https://openalex.org/W3189220322","https://openalex.org/W3196007724","https://openalex.org/W3197743743","https://openalex.org/W3202724146","https://openalex.org/W6753969399"],"related_works":["https://openalex.org/W2748952813","https://openalex.org/W4244478748","https://openalex.org/W4223488648","https://openalex.org/W2134969820","https://openalex.org/W2251605416","https://openalex.org/W4389340727","https://openalex.org/W4205786897","https://openalex.org/W3150465815","https://openalex.org/W1997222214","https://openalex.org/W2802581102"],"abstract_inverted_index":{"MOTIVATION:":[0],"Pileup":[1],"analysis":[2],"is":[3,87,183],"a":[4,21,46,76,83,112,138,177,184,230],"building":[5],"block":[6],"of":[7,23,34,49,56,82,141,161,237],"many":[8],"bioinformatics":[9],"pipelines,":[10],"including":[11],"variant":[12],"calling":[13],"and":[14,79,114,136,152,168,196,222],"genotyping.":[15],"This":[16],"step":[17],"tends":[18],"to":[19,64,105,117,165,172],"become":[20],"bottleneck":[22],"the":[24,28,43,50,53,108,125,129,142,216],"entire":[25],"assay":[26],"since":[27],"straightforward":[29],"pileup":[30,84],"implementations":[31],"involve":[32],"processing":[33],"all":[35,39],"base":[36],"calls":[37],"from":[38,121],"alignments":[40],"sequentially.":[41],"On":[42],"other":[44,155],"hand,":[45],"distributed":[47,78,157,219],"version":[48],"algorithm":[51,85,103],"faces":[52],"intrinsic":[54],"challenge":[55],"splitting":[57],"reads-oriented":[58],"file":[59],"formats":[60],"into":[61],"self-contained":[62],"partitions":[63],"avoid":[65],"costly":[66],"data":[67,240],"exchange":[68],"between":[69],"computational":[70],"nodes.":[71],"RESULTS:":[72],"Here,":[73],"we":[74,97],"present":[75],"scalable,":[77],"efficient":[80],"implementation":[81],"that":[86,147,187],"suitable":[88],"for":[89,133,234],"deploying":[90],"in":[91,159,176,200,241],"cloud":[92,179],"computing":[93],"environments.":[94],"In":[95],"particular,":[96],"implemented:":[98],"(i)":[99],"our":[100,148,225],"custom":[101],"data-partitioning":[102],"optimized":[104],"work":[106],"with":[107,215,229],"alignment":[109,119],"reads,":[110],"(ii)":[111],"novel":[113,149],"unique":[115],"approach":[116,150],"process":[118],"events":[120],"sequencing":[122],"reads":[123],"using":[124,192],"MD":[126],"tags,":[127],"(iii)":[128],"source":[130],"code":[131],"micro-optimizations":[132],"recurrent":[134],"operations,":[135],"(iv)":[137],"modular":[139],"structure":[140],"algorithm.":[143],"We":[144],"have":[145],"proven":[146],"consistently":[151],"significantly":[153],"outperforms":[154],"state-of-the-art":[156],"tools":[158],"terms":[160],"execution":[162],"time":[163],"(up":[164,171],"6.5\u00d7":[166],"faster)":[167],"memory":[169],"usage":[170],"2\u00d7":[173],"less),":[174],"resulting":[175],"substantial":[178],"cost":[180],"reduction.":[181],"SeQuiLa":[182],"cloud-native":[185],"solution":[186],"can":[188],"be":[189],"easily":[190],"deployed":[191],"any":[193],"managed":[194],"Kubernetes":[195],"Hadoop":[197],"services":[198],"available":[199],"public":[201],"clouds,":[202],"like":[203],"Microsoft":[204],"Azure":[205],"Cloud,":[206],"Google":[207],"Cloud":[208],"Platform,":[209],"or":[210],"Amazon":[211],"Web":[212],"Services.":[213],"Together":[214],"already":[217],"implemented":[218],"range":[220],"join":[221],"coverage":[223],"calculations,":[224],"package":[226],"provides":[227],"end-users":[228],"unified":[231],"SQL":[232],"interface":[233],"convenient":[235],"analyses":[236],"population-scale":[238],"genomic":[239],"an":[242],"interactive":[243],"way.":[244],"AVAILABILITY":[245],"AND":[246],"IMPLEMENTATION:":[247],"https://biodatageeks.github.io/sequila/.":[248]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-08-11T07:18:39.950985","created_date":"2025-10-10T00:00:00"}
