{"id":"https://openalex.org/W7128610778","doi":"https://doi.org/10.5281/zenodo.18526700","title":"CPL-Article: a corpus annotated with bioinformatics tools names in publications describing workflows","display_name":"CPL-Article: a corpus annotated with bioinformatics tools names in publications describing workflows","publication_year":2026,"publication_date":"2026-02-01","ids":{"openalex":"https://openalex.org/W7128610778","doi":"https://doi.org/10.5281/zenodo.18526700"},"language":null,"primary_location":{"id":"pmh:doi:10.5281/zenodo.18526699","is_oa":true,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4406922384","display_name":"Open MIND","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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":"Dataset"},"type":"dataset","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":null,"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/workflow","display_name":"Workflow","score":0.8411999940872192},{"id":"https://openalex.org/keywords/annotation","display_name":"Annotation","score":0.8069999814033508},{"id":"https://openalex.org/keywords/agency","display_name":"Agency (philosophy)","score":0.48539999127388},{"id":"https://openalex.org/keywords/work","display_name":"Work (physics)","score":0.27390000224113464}],"concepts":[{"id":"https://openalex.org/C177212765","wikidata":"https://www.wikidata.org/wiki/Q627335","display_name":"Workflow","level":2,"score":0.8411999940872192},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.8069999814033508},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7419999837875366},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.499099999666214},{"id":"https://openalex.org/C108170787","wikidata":"https://www.wikidata.org/wiki/Q3951828","display_name":"Agency (philosophy)","level":2,"score":0.48539999127388},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.44369998574256897},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3926999866962433},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.3434999883174896},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2863999903202057},{"id":"https://openalex.org/C18762648","wikidata":"https://www.wikidata.org/wiki/Q42213","display_name":"Work (physics)","level":2,"score":0.27390000224113464},{"id":"https://openalex.org/C2777889803","wikidata":"https://www.wikidata.org/wiki/Q25047676","display_name":"Named entity","level":2,"score":0.26969999074935913}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:doi:10.5281/zenodo.18526699","is_oa":true,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4406922384","display_name":"Open MIND","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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":"Dataset"},{"id":"doi:10.5281/zenodo.18526700","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.18526700","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":"pmh:doi:10.5281/zenodo.18526699","is_oa":true,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4406922384","display_name":"Open MIND","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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":"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-Article":[0],"is":[1,30],"a":[2,45,80],"corpus":[3,29],"describing":[4,11],"bioinformatics":[5,12],"tools":[6],"names":[7],"in":[8,18],"English":[9],"publications":[10],"workflows.":[13],"These":[14],"annotations":[15],"are":[16,66,75],"available":[17],"the":[19,84,115,120],"BRAT":[20],"Rapid":[21],"Annotation":[22],"Tool":[23],"(BRAT)":[24],"standoff":[25],"format":[26],"(https://brat.nlplab.org/standoff.html).":[27],"This":[28,87,110],"composed":[31],"of":[32,47,83],"26":[33],"articles":[34,65,101],"related":[35],"to":[36,55,79,90,126],"Nextflow":[37],"workflows":[38],"randomly":[39],"selected":[40],"from":[41,114],"PubMed":[42],"Central":[43],"with":[44,124],"total":[46],"36,564":[48],"tokens":[49,53],"and":[50],"701":[51],"annotated":[52],"corresponding":[54,78],"669":[56],"tool":[57],"occurences":[58],"(282":[59],"unique":[60],"tools).":[61],"Repository":[62],"organisation":[63],"The":[64,96],"separated":[67],"into":[68],"six":[69],"different":[70,81,94],"directories:":[71],"Five":[72],"folders":[73],"(iteration_{i})":[74],"provided,":[76],"each":[77],"split":[82],"training":[85],"data.":[86],"allows":[88],"experiments":[89],"be":[91],"run":[92],"on":[93],"splits.":[95],"last":[97],"folder":[98],"contains":[99],"five":[100],"used":[102],"for":[103],"testing.":[104],"Contact":[105],"Cl\u00e9mence":[106],"Sebe,":[107],"clemence.sebe@universite-paris-saclay.fr":[108],"Funding":[109],"work":[111],"received":[112],"support":[113],"National":[116],"Research":[117],"Agency":[118],"under":[119],"France":[121],"2030":[122],"program,":[123],"reference":[125],"ANR-22-PESN-0007.":[127]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-02-12T00:00:00"}
