{"id":"https://openalex.org/W2132378736","doi":"https://doi.org/10.1093/bioinformatics/btu314","title":"<i>SAMBLASTER</i>: fast duplicate marking and structural variant read extraction","display_name":"<i>SAMBLASTER</i>: fast duplicate marking and structural variant read extraction","publication_year":2014,"publication_date":"2014-05-07","ids":{"openalex":"https://openalex.org/W2132378736","doi":"https://doi.org/10.1093/bioinformatics/btu314","mag":"2132378736"},"language":"en","primary_location":{"id":"doi:10.1093/bioinformatics/btu314","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btu314","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/30/17/2503/48927353/bioinformatics_30_17_2503.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":["arxiv","crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://academic.oup.com/bioinformatics/article-pdf/30/17/2503/48927353/bioinformatics_30_17_2503.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5091480053","display_name":"Gregory G. Faust","orcid":"https://orcid.org/0000-0002-8233-9408"},"institutions":[{"id":"https://openalex.org/I51556381","display_name":"University of Virginia","ror":"https://ror.org/0153tk833","country_code":"US","type":"education","lineage":["https://openalex.org/I51556381"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Gregory G. Faust","raw_affiliation_strings":["1 \u00a01Department of Biochemistry and Molecular Genetics and 2Center for Public Health Genomics, University of Virginia, Charlottesville, VA 22908, USA"],"affiliations":[{"raw_affiliation_string":"1 \u00a01Department of Biochemistry and Molecular Genetics and 2Center for Public Health Genomics, University of Virginia, Charlottesville, VA 22908, USA","institution_ids":["https://openalex.org/I51556381"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5026920706","display_name":"Ira M. Hall","orcid":"https://orcid.org/0000-0003-4442-6655"},"institutions":[{"id":"https://openalex.org/I51556381","display_name":"University of Virginia","ror":"https://ror.org/0153tk833","country_code":"US","type":"education","lineage":["https://openalex.org/I51556381"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ira M. Hall","raw_affiliation_strings":["1 \u00a01Department of Biochemistry and Molecular Genetics and 2Center for Public Health Genomics, University of Virginia, Charlottesville, VA 22908, USA"],"affiliations":[{"raw_affiliation_string":"1 \u00a01Department of Biochemistry and Molecular Genetics and 2Center for Public Health Genomics, University of Virginia, Charlottesville, VA 22908, USA","institution_ids":["https://openalex.org/I51556381"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5091480053"],"corresponding_institution_ids":["https://openalex.org/I51556381"],"apc_list":{"value":3618,"currency":"USD","value_usd":3618},"apc_paid":{"value":3618,"currency":"USD","value_usd":3618},"fwci":9.9498,"has_fulltext":true,"cited_by_count":1002,"citation_normalized_percentile":{"value":0.98816992,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":100},"biblio":{"volume":"30","issue":"17","first_page":"2503","last_page":"2505"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.9995999932289124,"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":0.9995999932289124,"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":0.9711999893188477,"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/T11970","display_name":"Molecular Biology Techniques and Applications","score":0.9562000036239624,"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/computer-science","display_name":"Computer science","score":0.8768700957298279},{"id":"https://openalex.org/keywords/bottleneck","display_name":"Bottleneck","score":0.8274973034858704},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.7355396151542664},{"id":"https://openalex.org/keywords/source-code","display_name":"Source code","score":0.5281130075454712},{"id":"https://openalex.org/keywords/pipeline-transport","display_name":"Pipeline transport","score":0.5160729289054871},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.4435453414916992},{"id":"https://openalex.org/keywords/overhead","display_name":"Overhead (engineering)","score":0.44037431478500366},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.4402506947517395},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.33265161514282227},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.33156031370162964},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.30280566215515137},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.24150827527046204},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.15084177255630493}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8768700957298279},{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.8274973034858704},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.7355396151542664},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.5281130075454712},{"id":"https://openalex.org/C175309249","wikidata":"https://www.wikidata.org/wiki/Q725864","display_name":"Pipeline transport","level":2,"score":0.5160729289054871},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.4435453414916992},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.44037431478500366},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.4402506947517395},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.33265161514282227},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.33156031370162964},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.30280566215515137},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.24150827527046204},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.15084177255630493},{"id":"https://openalex.org/C87717796","wikidata":"https://www.wikidata.org/wiki/Q146326","display_name":"Environmental engineering","level":1,"score":0.0},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1093/bioinformatics/btu314","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btu314","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/30/17/2503/48927353/bioinformatics_30_17_2503.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:arXiv.org:1403.7486","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1403.7486","pdf_url":"https://arxiv.org/pdf/1403.7486","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"pmh:oai:pubmedcentral.nih.gov:4147885","is_oa":true,"landing_page_url":"http://doi.org/10.1093/bioinformatics/btu314","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.1093/bioinformatics/btu314","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btu314","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/30/17/2503/48927353/bioinformatics_30_17_2503.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":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320332161","display_name":"National Institutes of Health","ror":"https://ror.org/01cwqze88"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2132378736.pdf","grobid_xml":"https://content.openalex.org/works/W2132378736.grobid-xml"},"referenced_works_count":3,"referenced_works":["https://openalex.org/W2103011829","https://openalex.org/W2108234281","https://openalex.org/W2171791108"],"related_works":["https://openalex.org/W4380433113","https://openalex.org/W4386072068","https://openalex.org/W252339960","https://openalex.org/W2390529043","https://openalex.org/W2378320433","https://openalex.org/W2358343511","https://openalex.org/W2051877971","https://openalex.org/W1970117064","https://openalex.org/W1787170397","https://openalex.org/W4292347844"],"abstract_inverted_index":{"Motivation:":[0],"Illumina":[1],"DNA":[2,79],"sequencing":[3],"is":[4,33,65,84,116,157],"now":[5],"the":[6,34,55,97],"predominant":[7],"source":[8],"of":[9,57,142],"raw":[10],"genomic":[11],"data,":[12],"and":[13,40,124,145,154,161],"data":[14],"volumes":[15],"are":[16,22,62],"growing":[17],"rapidly.":[18],"Bioinformatic":[19],"analysis":[20],"pipelines":[21,32],"having":[23],"trouble":[24],"keeping":[25],"pace.":[26],"A":[27],"common":[28],"bottleneck":[29],"in":[30,70,140],"such":[31,59],"requirement":[35],"to":[36,67,86],"read,":[37],"write,":[38],"sort":[39],"compress":[41],"large":[42],"BAM":[43],"files":[44,73,96],"multiple":[45],"times.":[46],"Results:":[47],"We":[48],"present":[49],"SAMBLASTER,":[50],"a":[51,75,127],"tool":[52],"that":[53],"reduces":[54],"number":[56],"times":[58],"costly":[60],"operations":[61],"performed.":[63],"SAMBLASTER":[64,156],"designed":[66],"mark":[68],"duplicates":[69],"read-sorted":[71],"SAM":[72],"as":[74],"piped":[76],"post-pass":[77],"on":[78],"aligner":[80],"output":[81,93],"before":[82],"it":[83,90,132],"compressed":[85],"BAM.":[87],"In":[88],"addition,":[89],"can":[91],"simultaneously":[92],"into":[94],"separate":[95],"discordant":[98],"read-pairs":[99],"and/or":[100],"split-read":[101],"mappings":[102],"used":[103],"for":[104,164],"structural":[105],"variant":[106],"calling.":[107],"As":[108,126],"an":[109],"alignment":[110],"post-pass,":[111],"its":[112],"own":[113],"runtime":[114],"overhead":[115],"negligible,":[117],"while":[118,148],"dramatically":[119],"reducing":[120],"overall":[121],"pipeline":[122],"complexity":[123],"runtime.":[125],"stand-alone":[128],"duplicate":[129],"marking":[130],"tool,":[131],"performs":[133],"significantly":[134],"better":[135],"than":[136],"PICARD":[137],"or":[138],"SAMBAMBA":[139],"terms":[141],"both":[143],"speed":[144],"memory":[146],"usage,":[147],"achieving":[149],"nearly":[150],"identical":[151],"results.":[152],"Availability":[153],"implementation:":[155],"open-source":[158],"C++":[159],"code":[160],"freely":[162],"available":[163],"download":[165],"from":[166],"https://github.com/GregoryFaust/samblaster.":[167],"Contact:":[168],"imh4y@virginia.edu":[169]},"counts_by_year":[{"year":2026,"cited_by_count":26},{"year":2025,"cited_by_count":121},{"year":2024,"cited_by_count":158},{"year":2023,"cited_by_count":112},{"year":2022,"cited_by_count":129},{"year":2021,"cited_by_count":137},{"year":2020,"cited_by_count":118},{"year":2019,"cited_by_count":76},{"year":2018,"cited_by_count":54},{"year":2017,"cited_by_count":26},{"year":2016,"cited_by_count":27},{"year":2015,"cited_by_count":13},{"year":2014,"cited_by_count":4}],"updated_date":"2026-03-12T08:34:05.389933","created_date":"2016-06-24T00:00:00"}