{"id":"https://openalex.org/W7128622641","doi":"https://doi.org/10.5281/zenodo.18526760","title":"CPL-Code: a corpus annotated with bioinformatics tools names in executable code of Nextflow workflows","display_name":"CPL-Code: a corpus annotated with bioinformatics tools names in executable code of Nextflow workflows","publication_year":2026,"publication_date":"2026-02-01","ids":{"openalex":"https://openalex.org/W7128622641","doi":"https://doi.org/10.5281/zenodo.18526760"},"language":null,"primary_location":{"id":"doi:10.5281/zenodo.18526760","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.18526760","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Dataset"},"type":"dataset","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.5281/zenodo.18526760","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5069188227","display_name":"Cl\u00e9mence Sebe","orcid":"https://orcid.org/0000-0003-1988-1875"},"institutions":[{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"government","lineage":["https://openalex.org/I1294671590"]},{"id":"https://openalex.org/I277688954","display_name":"Universit\u00e9 Paris-Saclay","ror":"https://ror.org/03xjwb503","country_code":"FR","type":"education","lineage":["https://openalex.org/I277688954"]},{"id":"https://openalex.org/I4387152856","display_name":"Laboratoire Interdisciplinaire des Sciences du Num\u00e9rique","ror":"https://ror.org/00rd81916","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I277688954","https://openalex.org/I4387152856"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Sebe, Clemence","raw_affiliation_strings":["Universit\u00e9 Paris-Saclay, CNRS, LISN, 91400, Orsay, France"],"raw_orcid":"https://orcid.org/0000-0003-1988-1875","affiliations":[{"raw_affiliation_string":"Universit\u00e9 Paris-Saclay, CNRS, LISN, 91400, Orsay, France","institution_ids":["https://openalex.org/I277688954","https://openalex.org/I1294671590","https://openalex.org/I4387152856"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088565202","display_name":"Olivier Ferret","orcid":"https://orcid.org/0000-0003-0755-2361"},"institutions":[{"id":"https://openalex.org/I2738703131","display_name":"Commissariat \u00e0 l'\u00c9nergie Atomique et aux \u00c9nergies Alternatives","ror":"https://ror.org/00jjx8s55","country_code":"FR","type":"government","lineage":["https://openalex.org/I2738703131"]},{"id":"https://openalex.org/I277688954","display_name":"Universit\u00e9 Paris-Saclay","ror":"https://ror.org/03xjwb503","country_code":"FR","type":"education","lineage":["https://openalex.org/I277688954"]},{"id":"https://openalex.org/I4210085861","display_name":"Laboratoire d'Int\u00e9gration des Syst\u00e8mes et des Technologies","ror":"https://ror.org/000dbcc61","country_code":"FR","type":"government","lineage":["https://openalex.org/I2738703131","https://openalex.org/I2738703131","https://openalex.org/I277688954","https://openalex.org/I4210085861","https://openalex.org/I4210117989"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Ferret, Olivier","raw_affiliation_strings":["Universit\u00e9 Paris-Saclay, CEA, Institut LIST, 91191, Gif-sur-Yvette, France"],"raw_orcid":"https://orcid.org/0000-0003-0755-2361","affiliations":[{"raw_affiliation_string":"Universit\u00e9 Paris-Saclay, CEA, Institut LIST, 91191, Gif-sur-Yvette, France","institution_ids":["https://openalex.org/I277688954","https://openalex.org/I2738703131","https://openalex.org/I4210085861"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5125665592","display_name":"Aur\u00e9lie N\u00e9v\u00e9ol","orcid":null},"institutions":[{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"government","lineage":["https://openalex.org/I1294671590"]},{"id":"https://openalex.org/I277688954","display_name":"Universit\u00e9 Paris-Saclay","ror":"https://ror.org/03xjwb503","country_code":"FR","type":"education","lineage":["https://openalex.org/I277688954"]},{"id":"https://openalex.org/I4387152856","display_name":"Laboratoire Interdisciplinaire des Sciences du Num\u00e9rique","ror":"https://ror.org/00rd81916","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I277688954","https://openalex.org/I4387152856"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"N\u00e9v\u00e9ol, Aur\u00e9lie","raw_affiliation_strings":["Universit\u00e9 Paris-Saclay, CNRS, LISN, 91400, Orsay, France"],"raw_orcid":"https://orcid.org/0000-0002-1846-9144","affiliations":[{"raw_affiliation_string":"Universit\u00e9 Paris-Saclay, CNRS, LISN, 91400, Orsay, France","institution_ids":["https://openalex.org/I277688954","https://openalex.org/I1294671590","https://openalex.org/I4387152856"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5125679787","display_name":"Sarah COHEN-BOULAKIA","orcid":null},"institutions":[{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"government","lineage":["https://openalex.org/I1294671590"]},{"id":"https://openalex.org/I277688954","display_name":"Universit\u00e9 Paris-Saclay","ror":"https://ror.org/03xjwb503","country_code":"FR","type":"education","lineage":["https://openalex.org/I277688954"]},{"id":"https://openalex.org/I4387152856","display_name":"Laboratoire Interdisciplinaire des Sciences du Num\u00e9rique","ror":"https://ror.org/00rd81916","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I277688954","https://openalex.org/I4387152856"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"COHEN-BOULAKIA, Sarah","raw_affiliation_strings":["Universit\u00e9 Paris-Saclay, CNRS, LISN, 91400, Orsay, France"],"raw_orcid":"https://orcid.org/0000-0002-7439-1441","affiliations":[{"raw_affiliation_string":"Universit\u00e9 Paris-Saclay, CNRS, LISN, 91400, Orsay, France","institution_ids":["https://openalex.org/I277688954","https://openalex.org/I1294671590","https://openalex.org/I4387152856"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":null,"topics":[],"keywords":[{"id":"https://openalex.org/keywords/executable","display_name":"Executable","score":0.9157000184059143},{"id":"https://openalex.org/keywords/workflow","display_name":"Workflow","score":0.7663000226020813},{"id":"https://openalex.org/keywords/annotation","display_name":"Annotation","score":0.7613999843597412},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.49729999899864197},{"id":"https://openalex.org/keywords/source-code","display_name":"Source code","score":0.42969998717308044}],"concepts":[{"id":"https://openalex.org/C160145156","wikidata":"https://www.wikidata.org/wiki/Q778586","display_name":"Executable","level":2,"score":0.9157000184059143},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7705000042915344},{"id":"https://openalex.org/C177212765","wikidata":"https://www.wikidata.org/wiki/Q627335","display_name":"Workflow","level":2,"score":0.7663000226020813},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.7613999843597412},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.49729999899864197},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4345000088214874},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.42969998717308044},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.39879998564720154},{"id":"https://openalex.org/C108170787","wikidata":"https://www.wikidata.org/wiki/Q3951828","display_name":"Agency (philosophy)","level":2,"score":0.3928000032901764},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3637999892234802},{"id":"https://openalex.org/C45235069","wikidata":"https://www.wikidata.org/wiki/Q278425","display_name":"Table (database)","level":2,"score":0.3610999882221222},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.3546000123023987},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.2676999866962433}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.5281/zenodo.18526760","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.18526760","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"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":"Dataset"}],"best_oa_location":{"id":"doi:10.5281/zenodo.18526760","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.18526760","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Dataset"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"CPL-Code":[0],"is":[1,30],"a":[2,44,79],"corpus":[3,29],"describing":[4],"bioinformatics":[5],"tools":[6],"names":[7],"in":[8,18],"executable":[9],"code":[10],"of":[11,32,46,82],"Nextflow":[12,37],"workflows.":[13],"These":[14],"annotations":[15],"are":[16,65,74],"available":[17],"the":[19,83,114,119],"BRAT":[20],"Rapid":[21],"Annotation":[22],"Tool":[23],"(BRAT)":[24],"standoff":[25],"format":[26],"(https://brat.nlplab.org/standoff.html).":[27],"This":[28,86,109],"composed":[31],"797":[33],"processes":[34],"related":[35],"to":[36,54,78,89,125],"workflows":[38],"randomly":[39],"selected":[40],"from":[41,113],"Github":[42],"with":[43,123],"total":[45],"78,562":[47],"tokens":[48,52],"and":[49],"1,914":[50],"annotated":[51],"corresponding":[53,77],"1,911":[55],"tool":[56],"occurences":[57],"(421":[58],"unique":[59],"tools).":[60],"Repository":[61],"organisation":[62],"The":[63,95],"articles":[64,100],"separated":[66],"into":[67],"six":[68],"different":[69,80,93],"directories:":[70],"Five":[71],"folders":[72],"(iteration_{i})":[73],"provided,":[75],"each":[76],"split":[81],"training":[84],"data.":[85],"allows":[87],"experiments":[88],"be":[90],"run":[91],"on":[92],"splits.":[94],"last":[96],"folder":[97],"contains":[98],"five":[99],"used":[101],"for":[102],"testing.":[103],"Contact":[104],"Cl\u00e9mence":[105],"Sebe,":[106],"clemence.sebe@universite-paris-saclay.fr":[107],"Funding":[108],"work":[110],"received":[111],"support":[112],"National":[115],"Research":[116],"Agency":[117],"under":[118],"France":[120],"2030":[121],"program,":[122],"reference":[124],"ANR-22-PESN-0007.":[126]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-02-12T00:00:00"}
