{"id":"https://openalex.org/W2141287548","doi":"https://doi.org/10.1186/1751-0473-9-13","title":"biobambam: tools for read pair collation based algorithms on BAM files","display_name":"biobambam: tools for read pair collation based algorithms on BAM files","publication_year":2014,"publication_date":"2014-06-19","ids":{"openalex":"https://openalex.org/W2141287548","doi":"https://doi.org/10.1186/1751-0473-9-13","mag":"2141287548"},"language":"en","primary_location":{"id":"doi:10.1186/1751-0473-9-13","is_oa":true,"landing_page_url":"https://doi.org/10.1186/1751-0473-9-13","pdf_url":"https://scfbm.biomedcentral.com/track/pdf/10.1186/1751-0473-9-13","source":{"id":"https://openalex.org/S45786803","display_name":"Source Code for Biology and Medicine","issn_l":"1751-0473","issn":["1751-0473"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320256","host_organization_name":"BioMed Central","host_organization_lineage":["https://openalex.org/P4310320256","https://openalex.org/P4310319965"],"host_organization_lineage_names":["BioMed Central","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Source Code for Biology and Medicine","raw_type":"journal-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://scfbm.biomedcentral.com/track/pdf/10.1186/1751-0473-9-13","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5001423258","display_name":"German Tischler","orcid":null},"institutions":[{"id":"https://openalex.org/I2802476451","display_name":"Wellcome Sanger Institute","ror":"https://ror.org/05cy4wa09","country_code":"GB","type":"nonprofit","lineage":["https://openalex.org/I2802476451","https://openalex.org/I87048295"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"German Tischler","raw_affiliation_strings":["The Wellcome Trust Sanger Institute, Wellcome Trust Genome Campus, Hinxton, Cambridge, CB10 1SA, UK","The Wellcome Trust Sanger Institute, Wellcome Trust, Genome Campus, Hinxton, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Wellcome Trust Sanger Institute, Wellcome Trust Genome Campus, Hinxton, Cambridge, CB10 1SA, UK","institution_ids":["https://openalex.org/I2802476451"]},{"raw_affiliation_string":"The Wellcome Trust Sanger Institute, Wellcome Trust, Genome Campus, Hinxton, UK","institution_ids":["https://openalex.org/I2802476451"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5104077634","display_name":"Steven Leonard","orcid":null},"institutions":[{"id":"https://openalex.org/I2802476451","display_name":"Wellcome Sanger Institute","ror":"https://ror.org/05cy4wa09","country_code":"GB","type":"nonprofit","lineage":["https://openalex.org/I2802476451","https://openalex.org/I87048295"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Steven Leonard","raw_affiliation_strings":["The Wellcome Trust Sanger Institute, Wellcome Trust Genome Campus, Hinxton, Cambridge, CB10 1SA, UK","The Wellcome Trust Sanger Institute, Wellcome Trust, Genome Campus, Hinxton, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Wellcome Trust Sanger Institute, Wellcome Trust Genome Campus, Hinxton, Cambridge, CB10 1SA, UK","institution_ids":["https://openalex.org/I2802476451"]},{"raw_affiliation_string":"The Wellcome Trust Sanger Institute, Wellcome Trust, Genome Campus, Hinxton, UK","institution_ids":["https://openalex.org/I2802476451"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5001423258"],"corresponding_institution_ids":["https://openalex.org/I2802476451"],"apc_list":null,"apc_paid":null,"fwci":4.1264,"has_fulltext":true,"cited_by_count":357,"citation_normalized_percentile":{"value":0.94884711,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":"9","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":0.9998000264167786,"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":0.9998000264167786,"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/T10885","display_name":"Gene expression and cancer classification","score":0.9817000031471252,"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":0.9817000031471252,"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/collation","display_name":"Collation","score":0.9807400703430176},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8677847385406494},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.6513511538505554},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5945963263511658},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.5904778242111206},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5459482073783875},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.5085872411727905},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.4713311195373535},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.46452152729034424},{"id":"https://openalex.org/keywords/file-format","display_name":"File format","score":0.4367341995239258},{"id":"https://openalex.org/keywords/sorting","display_name":"Sorting","score":0.43404215574264526},{"id":"https://openalex.org/keywords/block","display_name":"Block (permutation group theory)","score":0.4256817102432251},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.15447187423706055},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.08068075776100159},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.07612106204032898}],"concepts":[{"id":"https://openalex.org/C505175697","wikidata":"https://www.wikidata.org/wiki/Q14953108","display_name":"Collation","level":2,"score":0.9807400703430176},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8677847385406494},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.6513511538505554},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5945963263511658},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.5904778242111206},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5459482073783875},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5085872411727905},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.4713311195373535},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.46452152729034424},{"id":"https://openalex.org/C97250363","wikidata":"https://www.wikidata.org/wiki/Q235557","display_name":"File format","level":2,"score":0.4367341995239258},{"id":"https://openalex.org/C111696304","wikidata":"https://www.wikidata.org/wiki/Q2303697","display_name":"Sorting","level":2,"score":0.43404215574264526},{"id":"https://openalex.org/C2777210771","wikidata":"https://www.wikidata.org/wiki/Q4927124","display_name":"Block (permutation group theory)","level":2,"score":0.4256817102432251},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.15447187423706055},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.08068075776100159},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.07612106204032898},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1186/1751-0473-9-13","is_oa":true,"landing_page_url":"https://doi.org/10.1186/1751-0473-9-13","pdf_url":"https://scfbm.biomedcentral.com/track/pdf/10.1186/1751-0473-9-13","source":{"id":"https://openalex.org/S45786803","display_name":"Source Code for Biology and Medicine","issn_l":"1751-0473","issn":["1751-0473"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320256","host_organization_name":"BioMed Central","host_organization_lineage":["https://openalex.org/P4310320256","https://openalex.org/P4310319965"],"host_organization_lineage_names":["BioMed Central","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Source Code for Biology and Medicine","raw_type":"journal-article"},{"id":"pmh:oai:arXiv.org:1306.0836","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1306.0836","pdf_url":"https://arxiv.org/pdf/1306.0836","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:CiteSeerX.psu:10.1.1.767.6234","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.767.6234","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://arxiv.org/pdf/1306.0836.pdf","raw_type":"text"},{"id":"pmh:oai:pubmedcentral.nih.gov:4075596","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/4075596","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Source Code Biol Med","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.1186/1751-0473-9-13","is_oa":true,"landing_page_url":"https://doi.org/10.1186/1751-0473-9-13","pdf_url":"https://scfbm.biomedcentral.com/track/pdf/10.1186/1751-0473-9-13","source":{"id":"https://openalex.org/S45786803","display_name":"Source Code for Biology and Medicine","issn_l":"1751-0473","issn":["1751-0473"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320256","host_organization_name":"BioMed Central","host_organization_lineage":["https://openalex.org/P4310320256","https://openalex.org/P4310319965"],"host_organization_lineage_names":["BioMed Central","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Source Code for Biology and Medicine","raw_type":"journal-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/9","score":0.4699999988079071,"display_name":"Industry, innovation and infrastructure"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320311904","display_name":"Wellcome Trust","ror":"https://ror.org/029chgv08"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2141287548.pdf","grobid_xml":"https://content.openalex.org/works/W2141287548.grobid-xml"},"referenced_works_count":18,"referenced_works":["https://openalex.org/W1990393483","https://openalex.org/W2025213429","https://openalex.org/W2075996757","https://openalex.org/W2097341408","https://openalex.org/W2103441770","https://openalex.org/W2105708056","https://openalex.org/W2108234281","https://openalex.org/W2119556995","https://openalex.org/W2124985265","https://openalex.org/W2129016996","https://openalex.org/W2139760555","https://openalex.org/W2142619120","https://openalex.org/W2159084616","https://openalex.org/W2170551349","https://openalex.org/W2171777347","https://openalex.org/W2885727518","https://openalex.org/W4247053599","https://openalex.org/W4254674227"],"related_works":["https://openalex.org/W2386910960","https://openalex.org/W2388990957","https://openalex.org/W2387546720","https://openalex.org/W2367418752","https://openalex.org/W2354578030","https://openalex.org/W2348687995","https://openalex.org/W2355720236","https://openalex.org/W2371975126","https://openalex.org/W2353491461","https://openalex.org/W2388432780"],"abstract_inverted_index":{"Sequence":[0],"alignment":[1],"data":[2,38,260,272],"is":[3,124,181,235,249],"often":[4,214],"ordered":[5],"by":[6,104,119,199],"coordinate":[7],"(id":[8],"of":[9,33,43,81,92,99,117,133,148,173,183,197,223],"the":[10,16,19,31,36,40,46,58,71,78,82,96,152,166,171,184,195,203,224,254],"reference":[11,41],"sequence":[12,17],"plus":[13],"position":[14],"on":[15,95,268],"where":[18,122],"fragment":[20],"was":[21],"mapped)":[22],"when":[23],"stored":[24],"in":[25,57,101,143,170,221],"BAM":[26,102,144,149,204,231],"files,":[27],"as":[28,251,253],"this":[29,50,85,123,137],"simplifies":[30],"extraction":[32],"variants":[34,44],"between":[35],"mapped":[37,47],"and":[39,113,146,228,244,262,270],"or":[42,68,207],"within":[45],"data.":[48],"In":[49,84,187],"order":[51],"paired":[52],"reads":[53],"are":[54],"usually":[55],"separated":[56],"file,":[59],"which":[60,74],"complicates":[61],"some":[62],"other":[63,177],"applications":[64],"like":[65,140,202],"duplicate":[66,141,247],"marking":[67,142,209,248],"conversion":[69,147,234],"to":[70,76,151,192,205,232],"FastQ":[72,153,206,233],"format":[73,154],"require":[75],"access":[77],"full":[79],"information":[80],"pairs.":[83],"paper":[86],"we":[87],"introduce":[88],"biobambam,":[89],"a":[90,130],"set":[91],"tools":[93],"based":[94],"efficient":[97],"collation":[98,109,167,196],"alignments":[100,118,198],"files":[103,145,150],"read":[105,120,200],"name.":[106],"The":[107],"employed":[108],"algorithm":[110,138,168],"avoids":[111],"time":[112],"space":[114],"consuming":[115],"sorting":[116],"name":[121,201],"possible":[125],"without":[126],"using":[127],"more":[128,219],"than":[129,237,264],"specified":[131],"amount":[132],"main":[134,226],"memory.":[135],"Using":[136],"tasks":[139],"can":[155,213],"be":[156],"performed":[157],"very":[158],"efficiently":[159,220],"with":[160,189],"limited":[161],"resources.":[162],"We":[163],"also":[164],"make":[165],"available":[169],"form":[172],"an":[174,216],"API":[175,180],"for":[176,258],"projects.":[178],"This":[179],"part":[182],"libmaus":[185],"package.":[186],"comparison":[188],"previous":[190],"approaches":[191],"problems":[193],"involving":[194],"duplication":[208],"utilities":[210],"our":[211],"approach":[212],"perform":[215],"equivalent":[217],"task":[218],"terms":[222],"required":[225],"memory":[227],"run-time.":[229],"Our":[230,246],"faster":[236,263],"all":[238,265],"widely":[239],"known":[240,266],"alternatives":[241,267],"including":[242],"Picard":[243],"bamUtil.":[245],"about":[250],"fast":[252],"closest":[255],"competitor":[256],"bamUtil":[257],"small":[259],"sets":[261],"large":[269],"complex":[271],"sets.":[273]},"counts_by_year":[{"year":2026,"cited_by_count":12},{"year":2025,"cited_by_count":27},{"year":2024,"cited_by_count":49},{"year":2023,"cited_by_count":77},{"year":2022,"cited_by_count":36},{"year":2021,"cited_by_count":41},{"year":2020,"cited_by_count":41},{"year":2019,"cited_by_count":30},{"year":2018,"cited_by_count":15},{"year":2017,"cited_by_count":20},{"year":2016,"cited_by_count":6},{"year":2015,"cited_by_count":2},{"year":2014,"cited_by_count":1}],"updated_date":"2026-06-19T15:47:20.252518","created_date":"2025-10-10T00:00:00"}
