{"id":"https://openalex.org/W2207378558","doi":"https://doi.org/10.17877/de290r-7242","title":"Parallelization, scalability, and reproducibility in next generation sequencing analysis","display_name":"Parallelization, scalability, and reproducibility in next generation sequencing analysis","publication_year":2014,"publication_date":"2014-01-01","ids":{"openalex":"https://openalex.org/W2207378558","doi":"https://doi.org/10.17877/de290r-7242","mag":"2207378558"},"language":"en","primary_location":{"id":"pmh:oai:eldorado.tu-dortmund.de:2003/33940","is_oa":true,"landing_page_url":"http://hdl.handle.net/2003/33940","pdf_url":"http://hdl.handle.net/2003/33940","source":{"id":"https://openalex.org/S4306400811","display_name":"Technische Universit\u00e4t Dortmund Eldorado (Technische Universit\u00e4t Dortmund)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210148506","host_organization_name":"Erich-Brost-Institut","host_organization_lineage":["https://openalex.org/I4210148506"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"doc-type:Text"},"type":"book","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"http://hdl.handle.net/2003/33940","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5005124395","display_name":"Johannes K\u00f6ster","orcid":"https://orcid.org/0000-0001-9818-9320"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"K\u00f6ster, Johannes","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5005124395"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.13044043,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"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":0.9986000061035156,"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":0.9986000061035156,"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/T11287","display_name":"Cancer Genomics and Diagnostics","score":0.9911999702453613,"subfield":{"id":"https://openalex.org/subfields/1306","display_name":"Cancer Research"},"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":0.982699990272522,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.6862784624099731},{"id":"https://openalex.org/keywords/reproducibility","display_name":"Reproducibility","score":0.6489968299865723},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6219161152839661},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.525867223739624},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.14417827129364014},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.09582504630088806},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.08344852924346924}],"concepts":[{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.6862784624099731},{"id":"https://openalex.org/C9893847","wikidata":"https://www.wikidata.org/wiki/Q1425625","display_name":"Reproducibility","level":2,"score":0.6489968299865723},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6219161152839661},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.525867223739624},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.14417827129364014},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.09582504630088806},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.08344852924346924}],"mesh":[],"locations_count":3,"locations":[{"id":"pmh:oai:eldorado.tu-dortmund.de:2003/33940","is_oa":true,"landing_page_url":"http://hdl.handle.net/2003/33940","pdf_url":"http://hdl.handle.net/2003/33940","source":{"id":"https://openalex.org/S4306400811","display_name":"Technische Universit\u00e4t Dortmund Eldorado (Technische Universit\u00e4t Dortmund)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210148506","host_organization_name":"Erich-Brost-Institut","host_organization_lineage":["https://openalex.org/I4210148506"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"doc-type:Text"},{"id":"doi:10.17877/de290r-7242","is_oa":true,"landing_page_url":"https://doi.org/10.17877/de290r-7242","pdf_url":null,"source":{"id":"https://openalex.org/S4306400811","display_name":"Technische Universit\u00e4t Dortmund Eldorado (Technische Universit\u00e4t Dortmund)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210148506","host_organization_name":"Erich-Brost-Institut","host_organization_lineage":["https://openalex.org/I4210148506"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article-journal"},{"id":"mag:2207378558","is_oa":false,"landing_page_url":"https://eldorado.tu-dortmund.de/bitstream/2003/33940/1/Dissertation.pdf","pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":null}],"best_oa_location":{"id":"pmh:oai:eldorado.tu-dortmund.de:2003/33940","is_oa":true,"landing_page_url":"http://hdl.handle.net/2003/33940","pdf_url":"http://hdl.handle.net/2003/33940","source":{"id":"https://openalex.org/S4306400811","display_name":"Technische Universit\u00e4t Dortmund Eldorado (Technische Universit\u00e4t Dortmund)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210148506","host_organization_name":"Erich-Brost-Institut","host_organization_lineage":["https://openalex.org/I4210148506"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"doc-type:Text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W2207378558.pdf"},"referenced_works_count":97,"referenced_works":["https://openalex.org/W26356079","https://openalex.org/W109386094","https://openalex.org/W127947978","https://openalex.org/W134178062","https://openalex.org/W831477978","https://openalex.org/W1496357020","https://openalex.org/W1498160656","https://openalex.org/W1504625555","https://openalex.org/W1513982482","https://openalex.org/W1525240758","https://openalex.org/W1530476857","https://openalex.org/W1535630884","https://openalex.org/W1593185626","https://openalex.org/W1596062789","https://openalex.org/W1647671624","https://openalex.org/W1835740130","https://openalex.org/W1971584645","https://openalex.org/W1972314001","https://openalex.org/W1981509058","https://openalex.org/W1982088757","https://openalex.org/W1984656893","https://openalex.org/W1985211757","https://openalex.org/W1985462363","https://openalex.org/W1988431525","https://openalex.org/W1990061958","https://openalex.org/W1990293955","https://openalex.org/W1996181407","https://openalex.org/W2001914359","https://openalex.org/W2005271647","https://openalex.org/W2009570821","https://openalex.org/W2011301426","https://openalex.org/W2015831381","https://openalex.org/W2036827038","https://openalex.org/W2037748100","https://openalex.org/W2060108852","https://openalex.org/W2061680337","https://openalex.org/W2066047894","https://openalex.org/W2066827579","https://openalex.org/W2072770570","https://openalex.org/W2073433320","https://openalex.org/W2074231493","https://openalex.org/W2075773711","https://openalex.org/W2087064593","https://openalex.org/W2095680943","https://openalex.org/W2096435507","https://openalex.org/W2097065948","https://openalex.org/W2097438318","https://openalex.org/W2100751585","https://openalex.org/W2103116338","https://openalex.org/W2103441770","https://openalex.org/W2104266030","https://openalex.org/W2104570606","https://openalex.org/W2106379008","https://openalex.org/W2107744418","https://openalex.org/W2107745473","https://openalex.org/W2107830007","https://openalex.org/W2108165346","https://openalex.org/W2108234281","https://openalex.org/W2110065044","https://openalex.org/W2112113834","https://openalex.org/W2117608012","https://openalex.org/W2117683095","https://openalex.org/W2119298573","https://openalex.org/W2123100726","https://openalex.org/W2128374023","https://openalex.org/W2128986460","https://openalex.org/W2129714591","https://openalex.org/W2133687564","https://openalex.org/W2136482257","https://openalex.org/W2138270253","https://openalex.org/W2138601221","https://openalex.org/W2139523073","https://openalex.org/W2139747296","https://openalex.org/W2141458291","https://openalex.org/W2143173327","https://openalex.org/W2145186114","https://openalex.org/W2146290346","https://openalex.org/W2147733682","https://openalex.org/W2152528713","https://openalex.org/W2155729921","https://openalex.org/W2156715753","https://openalex.org/W2158322625","https://openalex.org/W2166694026","https://openalex.org/W2167817111","https://openalex.org/W2168103533","https://openalex.org/W2168133698","https://openalex.org/W2168909179","https://openalex.org/W2169456326","https://openalex.org/W2170551349","https://openalex.org/W2171111703","https://openalex.org/W2242564872","https://openalex.org/W2290195878","https://openalex.org/W2341350247","https://openalex.org/W2395527326","https://openalex.org/W2611200784","https://openalex.org/W3145128584","https://openalex.org/W3215037115"],"related_works":["https://openalex.org/W2266598580","https://openalex.org/W2395782743","https://openalex.org/W2612624119","https://openalex.org/W2615492520","https://openalex.org/W2750488819","https://openalex.org/W576737241","https://openalex.org/W2567265394","https://openalex.org/W2306752666","https://openalex.org/W2267513979","https://openalex.org/W634773260","https://openalex.org/W2775843108","https://openalex.org/W2602579275","https://openalex.org/W2257132815","https://openalex.org/W2335295532","https://openalex.org/W2269958554","https://openalex.org/W2598728933","https://openalex.org/W2620245003","https://openalex.org/W2616361539","https://openalex.org/W2266244200","https://openalex.org/W2551676701"],"abstract_inverted_index":{"The":[0,56,91,132,262,332,369],"analysis":[1,46,277],"of":[2,23,47,65,121,143,169,178,231,240,252,278,293,330,364,371],"next-generation":[3],"sequencing":[4],"(NGS)":[5],"data":[6,81,248,280,289],"is":[7,60,116,136,154,164,184,255,334],"a":[8,70,79,147,158,237,245,344,388],"major":[9,42],"topic":[10],"in":[11,126,157,192,267],"bioinformatics:":[12],"short":[13,67],"reads":[14,68],"obtained":[15],"from":[16,186],"DNA,":[17],"the":[18,21,45,63,66,76,111,122,179,182,187,194,206,209,222,268,273,276,306,362,378],"molecule":[19],"encoding":[20],"genome":[22,149],"living":[24],"organisms,":[25],"are":[26,260,265,374],"processed":[27],"to":[28,41,61,137,146,190,204,317,342,347,387],"provide":[29,216],"insight":[30],"into":[31,208],"biological":[32,171,241],"or":[33,355,361],"medical":[34],"questions.":[35],"This":[36],"thesis":[37],"provides":[38,314],"novel":[39,80],"solutions":[40],"topics":[43],"within":[44,69],"NGS":[48,279,393],"data,":[49],"focusing":[50],"on":[51,272],"parallelization,":[52],"scalability":[53],"and":[54,99,215,257,291,323,384,391],"reproducibility.":[55],"read":[57,84,112,124,318,382],"mapping":[58,85,113,383],"problem":[59,135],"find":[62],"origin":[64],"given":[71],"reference":[72,148],"genome.":[73],"We":[74,304],"contribute":[75],"q-group":[77,92],"index,":[78],"structure":[82,249],"for":[83,220,250,321,381],"with":[86,95,211,227,236],"particularly":[87],"small":[88],"memory":[89,359],"footprint.":[90],"index":[93,247],"comes":[94],"massively":[96],"parallel":[97],"build":[98],"query":[100],"algorithms":[101],"targeted":[102],"towards":[103],"modern":[104],"graphics":[105],"processing":[106],"units":[107],"(GPUs).":[108],"On":[109],"top,":[110],"software":[114,269],"PEANUT":[115],"presented,":[117],"which":[118,313],"outperforms":[119],"state":[120,177],"art":[123,180],"mappers":[125],"speed":[127],"while":[128],"maintaining":[129],"their":[130],"accuracy.":[131],"variant":[133,162,232,385],"calling":[134,163,210,233,386],"infer":[138],"(i.e.,":[139],"call)":[140],"genetic":[141],"variants":[142,168],"individuals":[144],"compared":[145],"using":[150,372],"mapped":[151],"reads.":[152],"It":[153],"usually":[155],"solved":[156],"Bayesian":[159],"way.":[160],"Often,":[161],"followed":[165],"by":[166,300,336,376],"filtering":[167,183,207],"different":[170],"samples":[172],"against":[173],"each":[174],"other.":[175],"With":[176],"solutions,":[181],"decoupled":[185],"calling,":[188],"leading":[189],"difficulties":[191],"controlling":[193,221],"false":[195,223],"discovery":[196,224],"rate.":[197],"In":[198],"this":[199],"work,":[200],"we":[201],"show":[202],"how":[203],"integrate":[205],"an":[212,217,315,337],"algebraic":[213],"approach":[214],"intuitive":[218],"solution":[219],"rate":[225],"along":[226],"solving":[228],"other":[229,283],"challenges":[230],"like":[234,367],"scaling":[235],"growing":[238],"set":[239],"samples.":[242],"For":[243],"this,":[244],"hierarchical":[246],"storage":[251],"preprocessing":[253],"results":[254],"presented":[256,379],"compression":[258],"strategies":[259],"provided.":[261],"developed":[263],"methods":[264],"implemented":[266],"ALPACA.":[270],"Depending":[271],"research":[274],"question,":[275],"entails":[281],"many":[282],"steps,":[284],"typically":[285],"involving":[286],"diverse":[287],"tools,":[288],"transformations":[290],"aggregation":[292],"results.":[294],"These":[295],"steps":[296],"can":[297],"be":[298],"orchestrated":[299],"work":[301,309,325,345],"ow":[302,310,346],"management.":[303],"present":[305],"general":[307],"purpose":[308],"system":[311],"Snakemake,":[312],"easy":[316],"domain-specific":[319],"language":[320,333],"defining":[322],"documenting":[324],"ows,":[326],"thereby":[327],"ensuring":[328],"reproducibility":[329],"analyses.":[331],"complemented":[335],"execution":[338],"environment":[339],"that":[340],"allows":[341],"scale":[343],"available":[348,365],"resources,":[349],"including":[350],"parallelization":[351],"across":[352],"CPU":[353],"cores":[354],"cluster":[356],"nodes,":[357],"restricting":[358],"usage":[360],"number":[363],"coprocessors":[366],"GPUs.":[368],"benefits":[370],"Snakemake":[373],"exemplified":[375],"combining":[377],"approaches":[380],"complete,":[389],"scalable":[390],"reproducible":[392],"analysis.":[394]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-03-11T14:59:36.786465","created_date":"2025-10-10T00:00:00"}