{"id":"https://openalex.org/W6949416734","doi":"https://doi.org/10.5281/zenodo.14900544","title":"BioToFlow: a corpus annotated with bioinformatics workflows information","display_name":"BioToFlow: a corpus annotated with bioinformatics workflows information","publication_year":2025,"publication_date":"2025-02-19","ids":{"openalex":"https://openalex.org/W6949416734","doi":"https://doi.org/10.5281/zenodo.14900544"},"language":"en","primary_location":{"id":"doi:10.5281/zenodo.14900544","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.14900544","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.14900544","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Sebe, Cl\u00e9mence","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, Cl\u00e9mence","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/I1294671590","https://openalex.org/I277688954","https://openalex.org/I4387152856"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Cohen-Boulakia, Sarah","orcid":"https://orcid.org/0000-0002-7439-1441"},"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/I1294671590","https://openalex.org/I277688954","https://openalex.org/I4387152856"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Ferret, Olivier","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, List, F-91120, Palaiseau, France"],"raw_orcid":"https://orcid.org/0000-0003-0755-2361","affiliations":[{"raw_affiliation_string":"Universit\u00e9 Paris-Saclay, CEA, List, F-91120, Palaiseau, France","institution_ids":["https://openalex.org/I2738703131","https://openalex.org/I277688954","https://openalex.org/I4210085861"]}]},{"author_position":"last","author":{"id":null,"display_name":"N\u00e9v\u00e9ol, Aur\u00e9lie","orcid":"https://orcid.org/0000-0002-1846-9144"},"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/I1294671590","https://openalex.org/I277688954","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":true,"primary_topic":null,"topics":[],"keywords":[{"id":"https://openalex.org/keywords/workflow","display_name":"Workflow","score":0.7874000072479248},{"id":"https://openalex.org/keywords/annotation","display_name":"Annotation","score":0.7572000026702881},{"id":"https://openalex.org/keywords/information-extraction","display_name":"Information extraction","score":0.4781000018119812},{"id":"https://openalex.org/keywords/named-entity-recognition","display_name":"Named-entity recognition","score":0.41929998993873596},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.35989999771118164},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.3158999979496002}],"concepts":[{"id":"https://openalex.org/C177212765","wikidata":"https://www.wikidata.org/wiki/Q627335","display_name":"Workflow","level":2,"score":0.7874000072479248},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.7572000026702881},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7149999737739563},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5716999769210815},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5468000173568726},{"id":"https://openalex.org/C195807954","wikidata":"https://www.wikidata.org/wiki/Q1662562","display_name":"Information extraction","level":2,"score":0.4781000018119812},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.42419999837875366},{"id":"https://openalex.org/C2779135771","wikidata":"https://www.wikidata.org/wiki/Q403574","display_name":"Named-entity recognition","level":3,"score":0.41929998993873596},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.35989999771118164},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.3531999886035919},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.3158999979496002},{"id":"https://openalex.org/C2777889803","wikidata":"https://www.wikidata.org/wiki/Q25047676","display_name":"Named entity","level":2,"score":0.313400000333786},{"id":"https://openalex.org/C532629269","wikidata":"https://www.wikidata.org/wiki/Q865083","display_name":"Corpus linguistics","level":2,"score":0.30390000343322754},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.2856999933719635}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.5281/zenodo.14900544","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.14900544","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.14900544","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.14900544","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":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"BioToFlow":[0,87],"is":[1,26],"a":[2,47,109,172,275],"corpus":[3,25,174,331],"describing":[4],"bioinformatics":[5],"workflows":[6,36,303],"in":[7,14,88,108,126,135,181],"English":[8],"publications.":[9],"These":[10],"annotations":[11],"are":[12,61,262],"available":[13],"the":[15,69,72,77,254,279,326,330,342,345,359,364],"BRAT":[16],"Rapid":[17],"Annotation":[18],"Tool":[19],"(BRAT)":[20],"standoff":[21],"format":[22],"(https://brat.nlplab.org/standoff.html).":[23],"This":[24,354],"composed":[27],"of":[28,49,178,257,284,329,344,347],"52":[29],"articles":[30,32,60,70,81,203,261,334],"(26":[31],"related":[33],"to":[34,147,370],"Nextflow":[35],"and":[37,76,155,175,266,286,338],"26":[38],"on":[39,114,278],"Snakemake":[40],"workflows,":[41],"randomly":[42],"selected":[43],"from":[44,358],"PubMed)":[45],"with":[46,79,157,264,272,274,332,336,368],"total":[48],"78":[50],"419":[51],"tokens":[52],"27":[53],"786":[54],"annotated":[55,263,335],"tokens.":[56],"Repository":[57],"organisation":[58],"The":[59,259],"separated":[62],"into":[63],"two":[64],"directories:":[65],"one":[66],"containing":[67],"all":[68],"for":[71,82],"training":[73],"phases":[74],"(39)":[75],"other":[78],"13":[80],"test.":[83],"Papers":[84],"Please":[85],"cite":[86],"any":[89],"research":[90],"that":[91],"uses":[92],"or":[93],"extends":[94],"it":[95],":":[96],"Sebe,":[97,185,351],"C.,":[98,290],"Cohen-Boulakia,":[99,187],"S.,":[100],"Ferret,":[101,189],"O.,":[102],"N\u00e9v\u00e9ol,":[103],"A.":[104,297],"(2025).":[105],"Extracting":[106],"Information":[107],"Low-Resource":[110],"Setting:":[111],"Case":[112],"Study":[113],"Bioinformatics":[115],"Workflows.":[116],"In:":[117],"Krempl,":[118],"G.,":[119],"Puolam\u00e4ki,":[120],"K.,":[121],"Miliou,":[122],"I.":[123],"(eds)":[124],"Advances":[125],"Intelligent":[127],"Data":[128],"Analysis":[129],"XXIII.":[130],"IDA":[131,148],"2025.":[132],"Lecture":[133],"Notes":[134],"Computer":[136],"Science,":[137],"vol":[138],"15669.":[139],"Springer,":[140],"Cham.":[141],"https://doi.org/10.1007/978-3-031-91398-3_21":[142],"In":[143,247,319],"this":[144,248,320],"article":[145,249,321],"accepted":[146],"2025":[149],"(in":[150,250,322],"English),":[151],"we":[152,169,252,324],"present":[153,253,325],"*BioToFlow*":[154],"experiments":[156,271],"few":[158],"shot":[159],"named":[160],"entity":[161],"recognition":[162],"(NER)":[163],"using":[164],"an":[165],"autoregressive":[166],"language":[167],"model,":[168],"also":[170],"use":[171],"pre-existing":[173],"test":[176],"integration":[177],"workflow":[179],"knowledge":[180],"NER":[182,273],"models.":[183],"Cl\u00e9mence":[184,350],"Sarah":[186],"Olivier":[188],"Aur\u00e9lie":[190],"N\u00e9v\u00e9ol.":[191],"Extraction":[192,299,311],"d\u2019entit\u00e9s":[193],"nomm\u00e9es":[194],"d\u00e9crivant":[195],"des":[196,202,221,228,237,314],"cha\u00eenes":[197],"de":[198,307],"traitement":[199],"bioinformatiques":[200],"dans":[201],"scientifiques":[204,304],"en":[205,231],"anglais.":[206],"35emes":[207],"Journ\u00e9es":[208],"d\u2019\u00c9tudes":[209],"sur":[210,217,301],"la":[211,308],"Parole":[212],"(JEP":[213],"2024)":[214,225],"31eme":[215],"Conf\u00e9rence":[216],"le":[218,234],"Traitement":[219,235],"Automatique":[220,236],"Langues":[222,238],"Naturelles":[223],"(TALN":[224],"26eme":[226],"Rencontre":[227],"\u00c9tudiants":[229],"Chercheurs":[230],"Informatique":[232],"pour":[233],"(RECITAL":[239],"2024),":[240],"Jul":[241],"2024,":[242],"Toulouse,":[243],"France.":[244],"pp.422-434.":[245],"hal-04623033.":[246],"French),":[251,323],"second":[255],"version":[256,328],"*BioToFlow*.":[258],"new":[260],"entities":[265,337],"attributes.":[267],"We":[268,340],"conduct":[269],"preliminary":[270],"specific":[276],"focus":[277],"memorization":[280],"vs.":[281],"generalization":[282],"abilities":[283],"statistical":[285],"rule-based":[287],"methods.":[288],"Sebe":[289],"N\u00e9v\u00e9ol":[291],"A.,":[292],"Cohen-Boulakia":[293],"S.":[294],"&":[295],"Gaignard":[296],"(2023).":[298],"d\u2019informations":[300],"les":[302],"\u00e0":[305],"partir":[306],"litt\u00e9rature.":[309],"volume":[310],"et":[312],"Gestion":[313],"Connaissances,":[315],"RNTI-E-39,":[316],"p.":[317],"313.":[318],"first":[327],"24":[333],"relations.":[339],"show":[341],"feasibility":[343],"task":[346],"NER.":[348],"Contact":[349],"clemence.sebe@universite-paris-saclay.fr":[352],"Funding":[353],"work":[355],"received":[356],"support":[357],"National":[360],"Research":[361],"Agency":[362],"under":[363],"France":[365],"2030":[366],"program,":[367],"reference":[369],"ANR-22-PESN-0007.":[371]},"counts_by_year":[],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2025-10-10T00:00:00"}
