{"id":"https://openalex.org/W2136207878","doi":"https://doi.org/10.1093/bioinformatics/btu595","title":"BigDataScript: a scripting language for data pipelines","display_name":"BigDataScript: a scripting language for data pipelines","publication_year":2014,"publication_date":"2014-09-03","ids":{"openalex":"https://openalex.org/W2136207878","doi":"https://doi.org/10.1093/bioinformatics/btu595","mag":"2136207878","pmid":"https://pubmed.ncbi.nlm.nih.gov/25189778"},"language":"en","primary_location":{"id":"doi:10.1093/bioinformatics/btu595","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btu595","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/31/1/10/49012894/bioinformatics_31_1_10.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/31/1/10/49012894/bioinformatics_31_1_10.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5009682091","display_name":"Pablo Cingolani","orcid":"https://orcid.org/0000-0003-1553-0920"},"institutions":[{"id":"https://openalex.org/I4210148969","display_name":"McGill University and G\u00e9nome Qu\u00e9bec Innovation Centre","ror":"https://ror.org/0589bxs97","country_code":"CA","type":"education","lineage":["https://openalex.org/I4210148969"]}],"countries":["CA"],"is_corresponding":true,"raw_author_name":"Pablo Cingolani","raw_affiliation_strings":["1 McGill University School of Computer Science, 3480 University Street, Montreal, Qu\u00e9bec H3A 0E9 and 2 McGill University and G\u00e9nome Qu\u00e9bec Innovation Centre, 740 Dr. Penfield Avenue, Montr\u00e9al, Qu\u00e9bec H3A 0G1, Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"1 McGill University School of Computer Science, 3480 University Street, Montreal, Qu\u00e9bec H3A 0E9 and 2 McGill University and G\u00e9nome Qu\u00e9bec Innovation Centre, 740 Dr. Penfield Avenue, Montr\u00e9al, Qu\u00e9bec H3A 0G1, Canada","institution_ids":["https://openalex.org/I4210148969"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005999411","display_name":"Robert Sladek","orcid":"https://orcid.org/0000-0002-2730-1204"},"institutions":[{"id":"https://openalex.org/I4210148969","display_name":"McGill University and G\u00e9nome Qu\u00e9bec Innovation Centre","ror":"https://ror.org/0589bxs97","country_code":"CA","type":"education","lineage":["https://openalex.org/I4210148969"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Rob Sladek","raw_affiliation_strings":["1 McGill University School of Computer Science, 3480 University Street, Montreal, Qu\u00e9bec H3A 0E9 and 2 McGill University and G\u00e9nome Qu\u00e9bec Innovation Centre, 740 Dr. Penfield Avenue, Montr\u00e9al, Qu\u00e9bec H3A 0G1, Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"1 McGill University School of Computer Science, 3480 University Street, Montreal, Qu\u00e9bec H3A 0E9 and 2 McGill University and G\u00e9nome Qu\u00e9bec Innovation Centre, 740 Dr. Penfield Avenue, Montr\u00e9al, Qu\u00e9bec H3A 0G1, Canada","institution_ids":["https://openalex.org/I4210148969"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5065720651","display_name":"Mathieu Blanchette","orcid":"https://orcid.org/0000-0002-9555-860X"},"institutions":[{"id":"https://openalex.org/I4210148969","display_name":"McGill University and G\u00e9nome Qu\u00e9bec Innovation Centre","ror":"https://ror.org/0589bxs97","country_code":"CA","type":"education","lineage":["https://openalex.org/I4210148969"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Mathieu Blanchette","raw_affiliation_strings":["1 McGill University School of Computer Science, 3480 University Street, Montreal, Qu\u00e9bec H3A 0E9 and 2 McGill University and G\u00e9nome Qu\u00e9bec Innovation Centre, 740 Dr. Penfield Avenue, Montr\u00e9al, Qu\u00e9bec H3A 0G1, Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"1 McGill University School of Computer Science, 3480 University Street, Montreal, Qu\u00e9bec H3A 0E9 and 2 McGill University and G\u00e9nome Qu\u00e9bec Innovation Centre, 740 Dr. Penfield Avenue, Montr\u00e9al, Qu\u00e9bec H3A 0G1, Canada","institution_ids":["https://openalex.org/I4210148969"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5009682091"],"corresponding_institution_ids":["https://openalex.org/I4210148969"],"apc_list":{"value":3618,"currency":"USD","value_usd":3618},"apc_paid":{"value":3618,"currency":"USD","value_usd":3618},"fwci":1.3015,"has_fulltext":true,"cited_by_count":39,"citation_normalized_percentile":{"value":0.79683215,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":"31","issue":"1","first_page":"10","last_page":"16"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.41999998688697815,"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":0.41999998688697815,"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/T11986","display_name":"Scientific Computing and Data Management","score":0.3240000009536743,"subfield":{"id":"https://openalex.org/subfields/1802","display_name":"Information Systems and Management"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T13937","display_name":"Genetics, Bioinformatics, and Biomedical Research","score":0.03970000147819519,"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":0.8804720044136047},{"id":"https://openalex.org/keywords/pipeline-transport","display_name":"Pipeline transport","score":0.6261205673217773},{"id":"https://openalex.org/keywords/software-portability","display_name":"Software portability","score":0.620118260383606},{"id":"https://openalex.org/keywords/serialization","display_name":"Serialization","score":0.564158022403717},{"id":"https://openalex.org/keywords/scripting-language","display_name":"Scripting language","score":0.5490116477012634},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.5456342101097107},{"id":"https://openalex.org/keywords/debugging","display_name":"Debugging","score":0.5132133960723877},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.47655680775642395},{"id":"https://openalex.org/keywords/python","display_name":"Python (programming language)","score":0.4377753734588623},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.39147865772247314}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8804720044136047},{"id":"https://openalex.org/C175309249","wikidata":"https://www.wikidata.org/wiki/Q725864","display_name":"Pipeline transport","level":2,"score":0.6261205673217773},{"id":"https://openalex.org/C63000827","wikidata":"https://www.wikidata.org/wiki/Q3080428","display_name":"Software portability","level":2,"score":0.620118260383606},{"id":"https://openalex.org/C52723943","wikidata":"https://www.wikidata.org/wiki/Q1127410","display_name":"Serialization","level":2,"score":0.564158022403717},{"id":"https://openalex.org/C61423126","wikidata":"https://www.wikidata.org/wiki/Q187432","display_name":"Scripting language","level":2,"score":0.5490116477012634},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.5456342101097107},{"id":"https://openalex.org/C168065819","wikidata":"https://www.wikidata.org/wiki/Q845566","display_name":"Debugging","level":2,"score":0.5132133960723877},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.47655680775642395},{"id":"https://openalex.org/C519991488","wikidata":"https://www.wikidata.org/wiki/Q28865","display_name":"Python (programming language)","level":2,"score":0.4377753734588623},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.39147865772247314},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C87717796","wikidata":"https://www.wikidata.org/wiki/Q146326","display_name":"Environmental engineering","level":1,"score":0.0}],"mesh":[{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D011381","descriptor_name":"Programming Languages","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D011381","descriptor_name":"Programming Languages","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D011381","descriptor_name":"Programming Languages","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":"D012984","descriptor_name":"Software","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"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":"D057188","descriptor_name":"Workflow","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D057188","descriptor_name":"Workflow","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D057188","descriptor_name":"Workflow","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D059014","descriptor_name":"High-Throughput Nucleotide Sequencing","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D059014","descriptor_name":"High-Throughput Nucleotide Sequencing","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D059014","descriptor_name":"High-Throughput Nucleotide Sequencing","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false}],"locations_count":3,"locations":[{"id":"doi:10.1093/bioinformatics/btu595","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btu595","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/31/1/10/49012894/bioinformatics_31_1_10.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":"pmid:25189778","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/25189778","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:europepmc.org:3256907","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/4271142","pdf_url":null,"source":{"id":"https://openalex.org/S4306400806","display_name":"Europe PMC (PubMed Central)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1303153112","host_organization_name":"European Bioinformatics Institute","host_organization_lineage":["https://openalex.org/I1303153112"],"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":null,"raw_type":"Text"}],"best_oa_location":{"id":"doi:10.1093/bioinformatics/btu595","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btu595","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/31/1/10/49012894/bioinformatics_31_1_10.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":[{"display_name":"Industry, innovation and infrastructure","score":0.6700000166893005,"id":"https://metadata.un.org/sdg/9"}],"awards":[{"id":"https://openalex.org/G4153561205","display_name":"Identifying variants causal for Type 2 Diabetes in Major human populations","funder_award_id":"4u01dk085545-05","funder_id":"https://openalex.org/F4320332161","funder_display_name":"National Institutes of Health"},{"id":"https://openalex.org/G574117291","display_name":null,"funder_award_id":"U01DK085545","funder_id":"https://openalex.org/F4320337357","funder_display_name":"National Institute of Diabetes and Digestive and Kidney Diseases"},{"id":"https://openalex.org/G6679582602","display_name":null,"funder_award_id":"U01 DK085545-01","funder_id":"https://openalex.org/F4320337357","funder_display_name":"National Institute of Diabetes and Digestive and Kidney Diseases"}],"funders":[{"id":"https://openalex.org/F4320310638","display_name":"McGill University","ror":"https://ror.org/01pxwe438"},{"id":"https://openalex.org/F4320332161","display_name":"National Institutes of Health","ror":"https://ror.org/01cwqze88"},{"id":"https://openalex.org/F4320334506","display_name":"Canadian Institutes of Health Research","ror":"https://ror.org/01gavpb45"},{"id":"https://openalex.org/F4320334593","display_name":"Natural Sciences and Engineering Research Council of Canada","ror":"https://ror.org/01h531d29"},{"id":"https://openalex.org/F4320337357","display_name":"National Institute of Diabetes and Digestive and Kidney Diseases","ror":"https://ror.org/00adh9b73"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2136207878.pdf","grobid_xml":"https://content.openalex.org/works/W2136207878.grobid-xml"},"referenced_works_count":13,"referenced_works":["https://openalex.org/W1891842933","https://openalex.org/W1919257374","https://openalex.org/W1986818660","https://openalex.org/W2029641872","https://openalex.org/W2097438318","https://openalex.org/W2103441770","https://openalex.org/W2106578986","https://openalex.org/W2110417468","https://openalex.org/W2119180969","https://openalex.org/W2123100726","https://openalex.org/W2148238464","https://openalex.org/W2156268797","https://openalex.org/W2163346902"],"related_works":["https://openalex.org/W3023169329","https://openalex.org/W4389470870","https://openalex.org/W2782165897","https://openalex.org/W4300438041","https://openalex.org/W2054104202","https://openalex.org/W2139703748","https://openalex.org/W2761254753","https://openalex.org/W1024825291","https://openalex.org/W4254242184","https://openalex.org/W2188981919"],"abstract_inverted_index":{"MOTIVATION:":[0],"The":[1],"analysis":[2],"of":[3,49,93,115,142],"large":[4,19],"biological":[5],"datasets":[6],"often":[7],"requires":[8],"complex":[9,143],"processing":[10,68],"pipelines":[11,84,123],"that":[12],"run":[13,86],"for":[14,66],"a":[15,26,32,90,97],"long":[16],"time":[17],"on":[18,89],"computational":[20],"infrastructures.":[21],"We":[22,59],"designed":[23],"and":[24,34,39,43,51,76,106,118,140,150],"implemented":[25],"simple":[27],"script-like":[28],"programming":[29,64,133],"language":[30,65,134],"with":[31,78],"clean":[33],"minimalist":[35],"syntax":[36],"to":[37,46,85,100,124],"develop":[38],"manage":[40],"pipeline":[41,130],"execution":[42,139],"provide":[44],"robustness":[45,110],"various":[47],"types":[48],"software":[50],"hardware":[52,74],"failures":[53],"as":[54,56,153,155],"well":[55,154],"portability.":[57],"RESULTS:":[58],"introduce":[60],"the":[61,113],"BigDataScript":[62,161],"(BDS)":[63],"data":[67],"pipelines,":[69,145],"which":[70],"improves":[71],"abstraction":[72,81],"from":[73,96,126],"resources":[75],"assists":[77],"robustness.":[79],"Hardware":[80],"allows":[82],"BDS":[83,108,136],"without":[87],"modification":[88],"wide":[91],"range":[92],"computer":[94],"architectures,":[95],"small":[98],"laptop":[99],"multi-core":[101],"servers,":[102],"server":[103],"farms,":[104],"clusters":[105],"clouds.":[107],"achieves":[109],"by":[111],"incorporating":[112],"concepts":[114,131],"absolute":[116],"serialization":[117],"lazy":[119],"processing,":[120],"thus":[121],"allowing":[122],"recover":[125],"errors.":[127],"By":[128],"abstracting":[129],"at":[132,167],"level,":[135],"simplifies":[137],"implementation,":[138],"management":[141],"bioinformatics":[144],"resulting":[146],"in":[147],"reduced":[148],"development":[149],"debugging":[151],"cycles":[152],"cleaner":[156],"code.":[157],"AVAILABILITY":[158],"AND":[159],"IMPLEMENTATION:":[160],"is":[162],"available":[163],"under":[164],"open-source":[165],"license":[166],"http://pcingola.github.io/BigDataScript.":[168]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":4},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":10},{"year":2018,"cited_by_count":8},{"year":2017,"cited_by_count":4},{"year":2016,"cited_by_count":4},{"year":2015,"cited_by_count":2}],"updated_date":"2026-08-06T08:24:18.245995","created_date":"2025-10-10T00:00:00"}
