{"id":"https://openalex.org/W4416059031","doi":"https://doi.org/10.1093/bib/bbaf571","title":"BioWorkflow: Retrieving comprehensive bioinformatics workflows from publications","display_name":"BioWorkflow: Retrieving comprehensive bioinformatics workflows from publications","publication_year":2025,"publication_date":"2025-11-01","ids":{"openalex":"https://openalex.org/W4416059031","doi":"https://doi.org/10.1093/bib/bbaf571","pmid":"https://pubmed.ncbi.nlm.nih.gov/41206112"},"language":"en","primary_location":{"id":"doi:10.1093/bib/bbaf571","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bib/bbaf571","pdf_url":null,"source":{"id":"https://openalex.org/S91767247","display_name":"Briefings in Bioinformatics","issn_l":"1467-5463","issn":["1467-5463","1477-4054"],"is_oa":true,"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":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Briefings in Bioinformatics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1093/bib/bbaf571","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100604305","display_name":"Yidan Wang","orcid":"https://orcid.org/0000-0002-0476-6367"},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yidan Wang","raw_affiliation_strings":["School of Computer Science and Technology, Faculty of Electronics and Information Engineering, Xi'an Jiaotong University , No. 28 Xianning West Road, Beilin District, Xi'an, Shaanxi 710049 ,","Shaanxi Engineering Research Center of Medical and Health Big Data, Xi'an Jiaotong University , No. 28 Xianning West Road, Beilin District, Xi'an 710049 ,","School of Computer Science and Technology, Faculty of Electronics and Information Engineering, Xi'an Jiaotong University, No. 28 Xianning West Road, Beilin District, Xi'an, Shaanxi 710049, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Faculty of Electronics and Information Engineering, Xi'an Jiaotong University , No. 28 Xianning West Road, Beilin District, Xi'an, Shaanxi 710049 ,","institution_ids":["https://openalex.org/I87445476"]},{"raw_affiliation_string":"Shaanxi Engineering Research Center of Medical and Health Big Data, Xi'an Jiaotong University , No. 28 Xianning West Road, Beilin District, Xi'an 710049 ,","institution_ids":["https://openalex.org/I87445476"]},{"raw_affiliation_string":"School of Computer Science and Technology, Faculty of Electronics and Information Engineering, Xi'an Jiaotong University, No. 28 Xianning West Road, Beilin District, Xi'an, Shaanxi 710049, China","institution_ids":["https://openalex.org/I87445476"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5027360778","display_name":"Jiayin Wang","orcid":"https://orcid.org/0000-0002-3862-6557"},"institutions":[{"id":"https://openalex.org/I4210131893","display_name":"Second Affiliated Hospital of Xi'an Jiaotong University","ror":"https://ror.org/03aq7kf18","country_code":"CN","type":"healthcare","lineage":["https://openalex.org/I4210131893"]},{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiayin Wang","raw_affiliation_strings":["School of Computer Science and Technology, Faculty of Electronics and Information Engineering, Xi'an Jiaotong University , No. 28 Xianning West Road, Beilin District, Xi'an, Shaanxi 710049 ,","Shaanxi Engineering Research Center of Medical and Health Big Data, Xi'an Jiaotong University , No. 28 Xianning West Road, Beilin District, Xi'an 710049 ,","The Second Affiliated Hospital of Xi'an Jiaotong University , No. 157 Xiwu Road, Beilin District, Xi'an 710003 , Shaanxi,","School of Computer Science and Technology, Faculty of Electronics and Information Engineering, Xi'an Jiaotong University, No. 28 Xianning West Road, Beilin District, Xi'an, Shaanxi 710049, China","The Second Affiliated Hospital of Xi'an Jiaotong University, No. 157 Xiwu Road, Beilin District, Xi'an 710003, Shaanxi, China"],"raw_orcid":"https://orcid.org/0000-0002-3862-6557","affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Faculty of Electronics and Information Engineering, Xi'an Jiaotong University , No. 28 Xianning West Road, Beilin District, Xi'an, Shaanxi 710049 ,","institution_ids":["https://openalex.org/I87445476"]},{"raw_affiliation_string":"Shaanxi Engineering Research Center of Medical and Health Big Data, Xi'an Jiaotong University , No. 28 Xianning West Road, Beilin District, Xi'an 710049 ,","institution_ids":["https://openalex.org/I87445476"]},{"raw_affiliation_string":"The Second Affiliated Hospital of Xi'an Jiaotong University , No. 157 Xiwu Road, Beilin District, Xi'an 710003 , Shaanxi,","institution_ids":["https://openalex.org/I4210131893"]},{"raw_affiliation_string":"School of Computer Science and Technology, Faculty of Electronics and Information Engineering, Xi'an Jiaotong University, No. 28 Xianning West Road, Beilin District, Xi'an, Shaanxi 710049, China","institution_ids":["https://openalex.org/I87445476"]},{"raw_affiliation_string":"The Second Affiliated Hospital of Xi'an Jiaotong University, No. 157 Xiwu Road, Beilin District, Xi'an 710003, Shaanxi, China","institution_ids":["https://openalex.org/I4210131893"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":{"value":4011,"currency":"USD","value_usd":4011},"apc_paid":{"value":4011,"currency":"USD","value_usd":4011},"fwci":0.8477,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.74653373,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":97,"max":98},"biblio":{"volume":"26","issue":"6","first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.7577999830245972,"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/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.7577999830245972,"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":0.1736000031232834,"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/T11937","display_name":"Research Data Management Practices","score":0.00800000037997961,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/workflow","display_name":"Workflow","score":0.9089999794960022},{"id":"https://openalex.org/keywords/consistency","display_name":"Consistency (knowledge bases)","score":0.7429999709129333},{"id":"https://openalex.org/keywords/parsing","display_name":"Parsing","score":0.6870999932289124},{"id":"https://openalex.org/keywords/reuse","display_name":"Reuse","score":0.6126999855041504},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.5246000289916992},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.49970000982284546},{"id":"https://openalex.org/keywords/workflow-management-system","display_name":"Workflow management system","score":0.36149999499320984},{"id":"https://openalex.org/keywords/workflow-engine","display_name":"Workflow engine","score":0.3605000078678131}],"concepts":[{"id":"https://openalex.org/C177212765","wikidata":"https://www.wikidata.org/wiki/Q627335","display_name":"Workflow","level":2,"score":0.9089999794960022},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8651000261306763},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.7429999709129333},{"id":"https://openalex.org/C186644900","wikidata":"https://www.wikidata.org/wiki/Q194152","display_name":"Parsing","level":2,"score":0.6870999932289124},{"id":"https://openalex.org/C206588197","wikidata":"https://www.wikidata.org/wiki/Q846574","display_name":"Reuse","level":2,"score":0.6126999855041504},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.534500002861023},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.5246000289916992},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.49970000982284546},{"id":"https://openalex.org/C140824633","wikidata":"https://www.wikidata.org/wiki/Q2808660","display_name":"Workflow management system","level":3,"score":0.36149999499320984},{"id":"https://openalex.org/C188220564","wikidata":"https://www.wikidata.org/wiki/Q3325097","display_name":"Workflow engine","level":3,"score":0.3605000078678131},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.35850000381469727},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3571999967098236},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.33809998631477356},{"id":"https://openalex.org/C19612761","wikidata":"https://www.wikidata.org/wiki/Q8034836","display_name":"Workflow technology","level":3,"score":0.3181999921798706},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.3075000047683716},{"id":"https://openalex.org/C200288055","wikidata":"https://www.wikidata.org/wiki/Q2621792","display_name":"Element (criminal law)","level":2,"score":0.289000004529953},{"id":"https://openalex.org/C2984968299","wikidata":"https://www.wikidata.org/wiki/Q1077784","display_name":"Software tool","level":3,"score":0.26989999413490295},{"id":"https://openalex.org/C2780966255","wikidata":"https://www.wikidata.org/wiki/Q5474306","display_name":"Foundation (evidence)","level":2,"score":0.26440000534057617},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.26429998874664307},{"id":"https://openalex.org/C4924752","wikidata":"https://www.wikidata.org/wiki/Q184148","display_name":"Plug-in","level":2,"score":0.257999986410141},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.25780001282691956},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.25769999623298645},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.2554999887943268},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.2522999942302704}],"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":"D011642","descriptor_name":"Publications","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D011642","descriptor_name":"Publications","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":"D016247","descriptor_name":"Information Storage and Retrieval","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D016247","descriptor_name":"Information Storage and Retrieval","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D057188","descriptor_name":"Workflow","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D057188","descriptor_name":"Workflow","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true}],"locations_count":3,"locations":[{"id":"doi:10.1093/bib/bbaf571","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bib/bbaf571","pdf_url":null,"source":{"id":"https://openalex.org/S91767247","display_name":"Briefings in Bioinformatics","issn_l":"1467-5463","issn":["1467-5463","1477-4054"],"is_oa":true,"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":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Briefings in Bioinformatics","raw_type":"journal-article"},{"id":"pmid:41206112","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/41206112","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":"Briefings in bioinformatics","raw_type":null},{"id":"pmh:oai:europepmc.org:11405196","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/12596265","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":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Text"}],"best_oa_location":{"id":"doi:10.1093/bib/bbaf571","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bib/bbaf571","pdf_url":null,"source":{"id":"https://openalex.org/S91767247","display_name":"Briefings in Bioinformatics","issn_l":"1467-5463","issn":["1467-5463","1477-4054"],"is_oa":true,"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":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Briefings in Bioinformatics","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2715084110","display_name":null,"funder_award_id":"62402376","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3180425335","display_name":null,"funder_award_id":"72293581","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G516663181","display_name":null,"funder_award_id":"72274152","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6671363317","display_name":null,"funder_award_id":"62572389","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W2567253780","https://openalex.org/W2885079199","https://openalex.org/W2951097674","https://openalex.org/W2952862139","https://openalex.org/W2972522091","https://openalex.org/W3001279689","https://openalex.org/W4220963010","https://openalex.org/W4289783315","https://openalex.org/W4297899309","https://openalex.org/W4375958611","https://openalex.org/W4376652993","https://openalex.org/W4383605243","https://openalex.org/W4389984066","https://openalex.org/W4390889686","https://openalex.org/W4391376072","https://openalex.org/W4391833078","https://openalex.org/W4395065280","https://openalex.org/W4400370724","https://openalex.org/W4401978780","https://openalex.org/W4403780966","https://openalex.org/W4405253988","https://openalex.org/W4405562108","https://openalex.org/W4407691690","https://openalex.org/W4415063826","https://openalex.org/W4416118085"],"related_works":[],"abstract_inverted_index":{"Reconstructing":[0],"bioinformatics":[1],"workflows":[2],"from":[3,81],"the":[4,7,13,56],"literature":[5],"is":[6,41],"foundation":[8],"of":[9,161,194],"scientific":[10],"analysis.":[11],"However,":[12],"required":[14],"details-processing":[15],"steps,":[16,127],"software":[17],"tools,":[18,128],"versions,":[19,129],"and":[20,30,40,47,54,87,95,100,120,130,132,142,150,172,180,191],"parameter":[21],"settings-are":[22],"dispersed":[23],"across":[24],"narrative":[25],"text,":[26,93],"tables,":[27,94],"figure":[28],"captions,":[29],"supplemental":[31],"files.":[32],"Manual":[33],"reconstruction":[34],"typically":[35],"takes":[36],"hours":[37],"per":[38,187],"paper":[39],"error-prone,":[42],"while":[43],"existing":[44,167],"question-answering":[45],"(QA)":[46],"retrieval":[48,119],"systems":[49],"focus":[50],"on":[51,154],"local":[52],"passages":[53],"lack":[55],"full-text,":[57],"multimodal":[58],"capabilities":[59],"needed":[60],"to":[61,138,147,184],"automatically":[62],"rebuild":[63],"complete":[64],"workflows.":[65],"We":[66],"introduce":[67],"BioWorkflow,":[68],"a":[69,89,122],"large":[70],"language":[71],"model":[72],"(LLM)-based,":[73],"retrieval-augmented":[74],"framework":[75],"that":[76,125],"automates":[77],"end-to-end":[78],"workflow":[79,124,162],"extraction":[80],"publications":[82],"by":[83,174],"(i)":[84],"parsing":[85],"PDFs":[86],"building":[88],"unified":[90],"index":[91],"over":[92,176],"figures":[96],"with":[97,106],"chunk-level":[98],"summaries":[99],"embeddings;":[101],"(ii)":[102],"hierarchically":[103],"decomposing":[104],"queries":[105],"dynamic":[107],"reformulation":[108],"when":[109],"new":[110],"entities":[111],"or":[112],"ambiguities":[113],"emerge;":[114],"(iii)":[115],"performing":[116],"iterative,":[117],"context-aware":[118],"assembling":[121],"directed":[123],"captures":[126],"parameters;":[131],"(iv)":[133],"linking":[134],"each":[135],"predicted":[136],"element":[137],"its":[139],"cited":[140],"evidence":[141],"running":[143],"automated":[144],"consistency":[145],"checks":[146],"suppress":[148],"hallucinations":[149],"ensure":[151],"traceability.":[152],"Evaluated":[153],"100":[155],"expert-annotated":[156],"papers,":[157],"BioWorkflow":[158],"recovers":[159],"~80%":[160],"steps":[163],"(versus":[164],"~20%":[165],"for":[166],"tools),":[168],"improves":[169],"reproducibility,":[170],"completeness,":[171],"accuracy":[173],">20%":[175],"strong":[177],"LLM":[178],"baselines,":[179],"reduces":[181],"curation":[182],"time":[183],"3-5":[185],"minutes":[186],"paper,":[188],"enabling":[189],"rapid":[190],"reliable":[192],"reuse":[193],"published":[195],"pipelines.":[196]},"counts_by_year":[{"year":2026,"cited_by_count":2}],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2025-11-09T00:00:00"}
