{"id":"https://openalex.org/W4408650424","doi":"https://doi.org/10.1186/s13040-025-00438-9","title":"Automatic detection and extraction of key resources from tables in biomedical papers","display_name":"Automatic detection and extraction of key resources from tables in biomedical papers","publication_year":2025,"publication_date":"2025-03-20","ids":{"openalex":"https://openalex.org/W4408650424","doi":"https://doi.org/10.1186/s13040-025-00438-9","pmid":"https://pubmed.ncbi.nlm.nih.gov/40114222"},"language":"en","primary_location":{"id":"doi:10.1186/s13040-025-00438-9","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13040-025-00438-9","pdf_url":null,"source":{"id":"https://openalex.org/S84409260","display_name":"BioData Mining","issn_l":"1756-0381","issn":["1756-0381"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320256","host_organization_name":"BioMed Central","host_organization_lineage":["https://openalex.org/P4310320256","https://openalex.org/P4310319965"],"host_organization_lineage_names":["BioMed Central","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"BioData Mining","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1186/s13040-025-00438-9","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5024882547","display_name":"\u0130brahim Burak \u00d6zyurt","orcid":"https://orcid.org/0000-0003-3944-1893"},"institutions":[{"id":"https://openalex.org/I36258959","display_name":"University of California San Diego","ror":"https://ror.org/0168r3w48","country_code":"US","type":"education","lineage":["https://openalex.org/I36258959"]},{"id":"https://openalex.org/I4210118524","display_name":"Universit\u00e9 Bourgogne Franche-Comt\u00e9","ror":"https://ror.org/02dn7x778","country_code":"FR","type":"education","lineage":["https://openalex.org/I4210118524"]}],"countries":["FR","US"],"is_corresponding":true,"raw_author_name":"Ibrahim Burak Ozyurt","raw_affiliation_strings":["FDI Lab Dept of Neuroscience, UCSD, 9500 Gilman Drive M/C 0608, La Jolla, CA, 92093-0608, USA. iozyurt@health.ucsd.edu","FDI Lab Dept of Neuroscience, UCSD, 9500 Gilman Drive M/C 0608, La Jolla, CA, 92093-0608, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"FDI Lab Dept of Neuroscience, UCSD, 9500 Gilman Drive M/C 0608, La Jolla, CA, 92093-0608, USA. iozyurt@health.ucsd.edu","institution_ids":["https://openalex.org/I36258959"]},{"raw_affiliation_string":"FDI Lab Dept of Neuroscience, UCSD, 9500 Gilman Drive M/C 0608, La Jolla, CA, 92093-0608, USA","institution_ids":["https://openalex.org/I36258959","https://openalex.org/I4210118524"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5058460697","display_name":"Anita Bandrowski","orcid":"https://orcid.org/0000-0002-5497-0243"},"institutions":[{"id":"https://openalex.org/I36258959","display_name":"University of California San Diego","ror":"https://ror.org/0168r3w48","country_code":"US","type":"education","lineage":["https://openalex.org/I36258959"]},{"id":"https://openalex.org/I4210118524","display_name":"Universit\u00e9 Bourgogne Franche-Comt\u00e9","ror":"https://ror.org/02dn7x778","country_code":"FR","type":"education","lineage":["https://openalex.org/I4210118524"]}],"countries":["FR","US"],"is_corresponding":false,"raw_author_name":"Anita Bandrowski","raw_affiliation_strings":["FDI Lab Dept of Neuroscience, UCSD, 9500 Gilman Drive M/C 0608, La Jolla, CA, 92093-0608, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"FDI Lab Dept of Neuroscience, UCSD, 9500 Gilman Drive M/C 0608, La Jolla, CA, 92093-0608, USA","institution_ids":["https://openalex.org/I36258959","https://openalex.org/I4210118524"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5024882547"],"corresponding_institution_ids":["https://openalex.org/I36258959","https://openalex.org/I4210118524"],"apc_list":{"value":2690,"currency":"USD","value_usd":2690},"apc_paid":{"value":2690,"currency":"USD","value_usd":2690},"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.02840894,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"18","issue":"1","first_page":"23","last_page":"23"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.7989000082015991,"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":0.7989000082015991,"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/T13083","display_name":"Advanced Text Analysis Techniques","score":0.08389999717473984,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.020999999716877937,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/computer-science","display_name":"Computer science","score":0.8530482649803162},{"id":"https://openalex.org/keywords/table","display_name":"Table (database)","score":0.755598783493042},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.6525100469589233},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5794364213943481},{"id":"https://openalex.org/keywords/table-of-contents","display_name":"Table of contents","score":0.5551193952560425},{"id":"https://openalex.org/keywords/resource","display_name":"Resource (disambiguation)","score":0.5528483390808105},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.46534478664398193},{"id":"https://openalex.org/keywords/information-extraction","display_name":"Information extraction","score":0.44216811656951904},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.40990781784057617},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.37414443492889404},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.37119096517562866},{"id":"https://openalex.org/keywords/computer-security","display_name":"Computer security","score":0.13279753923416138}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8530482649803162},{"id":"https://openalex.org/C45235069","wikidata":"https://www.wikidata.org/wiki/Q278425","display_name":"Table (database)","level":2,"score":0.755598783493042},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.6525100469589233},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5794364213943481},{"id":"https://openalex.org/C68476402","wikidata":"https://www.wikidata.org/wiki/Q1456936","display_name":"Table of contents","level":2,"score":0.5551193952560425},{"id":"https://openalex.org/C206345919","wikidata":"https://www.wikidata.org/wiki/Q20380951","display_name":"Resource (disambiguation)","level":2,"score":0.5528483390808105},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.46534478664398193},{"id":"https://openalex.org/C195807954","wikidata":"https://www.wikidata.org/wiki/Q1662562","display_name":"Information extraction","level":2,"score":0.44216811656951904},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.40990781784057617},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.37414443492889404},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.37119096517562866},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.13279753923416138},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.1186/s13040-025-00438-9","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13040-025-00438-9","pdf_url":null,"source":{"id":"https://openalex.org/S84409260","display_name":"BioData Mining","issn_l":"1756-0381","issn":["1756-0381"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320256","host_organization_name":"BioMed Central","host_organization_lineage":["https://openalex.org/P4310320256","https://openalex.org/P4310319965"],"host_organization_lineage_names":["BioMed Central","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"BioData Mining","raw_type":"journal-article"},{"id":"pmid:40114222","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/40114222","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":"BioData mining","raw_type":"Journal Article"},{"id":"pmh:oai:escholarship.org:ark:/13030/qt5v6514p4","is_oa":true,"landing_page_url":"https://escholarship.org/uc/item/5v6514p4","pdf_url":"https://escholarship.org/content/qt5v6514p4/qt5v6514p4.pdf","source":{"id":"https://openalex.org/S4306400115","display_name":"eScholarship (California Digital Library)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I2801248553","host_organization_name":"California Digital Library","host_organization_lineage":["https://openalex.org/I2801248553"],"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":"BioData Mining, vol 18, iss 1","raw_type":"article"},{"id":"pmh:oai:pubmedcentral.nih.gov:11924859","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/11924859","pdf_url":null,"source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","issn_l":null,"issn":null,"is_oa":true,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"BioData Min","raw_type":"Text"},{"id":"pmh:oai:doaj.org/article:b0e9754fde0744d594316810616c639e","is_oa":true,"landing_page_url":"https://doaj.org/article/b0e9754fde0744d594316810616c639e","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","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":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"BioData Mining, Vol 18, Iss 1, Pp 1-18 (2025)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1186/s13040-025-00438-9","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13040-025-00438-9","pdf_url":null,"source":{"id":"https://openalex.org/S84409260","display_name":"BioData Mining","issn_l":"1756-0381","issn":["1756-0381"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320256","host_organization_name":"BioMed Central","host_organization_lineage":["https://openalex.org/P4310320256","https://openalex.org/P4310319965"],"host_organization_lineage_names":["BioMed Central","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"BioData Mining","raw_type":"journal-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/8","score":0.49000000953674316,"display_name":"Decent work and economic growth"}],"awards":[{"id":"https://openalex.org/G1028798007","display_name":"From RRID to Resource Watch: A Knowledgebase of Biomedical Research Resources","funder_award_id":"1r24gm144308-01","funder_id":"https://openalex.org/F4320332161","funder_display_name":"National Institutes of Health"},{"id":"https://openalex.org/G2470528019","display_name":null,"funder_award_id":"R24GM144308","funder_id":"https://openalex.org/F4320337354","funder_display_name":"National Institute of General Medical Sciences"}],"funders":[{"id":"https://openalex.org/F4320306192","display_name":"Silicon Valley Community Foundation","ror":"https://ror.org/001ader08"},{"id":"https://openalex.org/F4320332161","display_name":"National Institutes of Health","ror":"https://ror.org/01cwqze88"},{"id":"https://openalex.org/F4320337354","display_name":"National Institute of General Medical Sciences","ror":"https://ror.org/04q48ey07"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W28412257","https://openalex.org/W1569639771","https://openalex.org/W1592986776","https://openalex.org/W1597533204","https://openalex.org/W1995296910","https://openalex.org/W2064675550","https://openalex.org/W2074231493","https://openalex.org/W2102189859","https://openalex.org/W2128863362","https://openalex.org/W2137998699","https://openalex.org/W2250539671","https://openalex.org/W2346015361","https://openalex.org/W2786162033","https://openalex.org/W2913991821","https://openalex.org/W2951325952","https://openalex.org/W2963341956","https://openalex.org/W2980011270","https://openalex.org/W3034997246","https://openalex.org/W3094030525","https://openalex.org/W3096609285","https://openalex.org/W3107064625","https://openalex.org/W3217518891","https://openalex.org/W4200474128","https://openalex.org/W4250156895","https://openalex.org/W4385991106","https://openalex.org/W4387213419","https://openalex.org/W4390902490","https://openalex.org/W4402670299","https://openalex.org/W6739901393"],"related_works":["https://openalex.org/W4394360958","https://openalex.org/W2948670949","https://openalex.org/W4288047943","https://openalex.org/W4394193569","https://openalex.org/W2140798747","https://openalex.org/W1797990060","https://openalex.org/W2948169060","https://openalex.org/W4232484699","https://openalex.org/W4256318226","https://openalex.org/W4253980046"],"abstract_inverted_index":{"BACKGROUND:":[0],"Tables":[1],"are":[2,84,362],"useful":[3],"information":[4,25,123],"artifacts":[5],"that":[6,40,76,83,105,146],"allow":[7,309],"easy":[8],"detection":[9,311],"of":[10,24,55,61,97,119,131,258,278,281,304,314,326,349],"missing":[11],"data":[12,239,361],"and":[13,30,37,108,121,151,158,175,205,312,345,359],"have":[14,51,91,139,284],"been":[15,93],"deployed":[16],"by":[17,64,265,287],"several":[18],"publishers":[19],"to":[20,44,86,173,245,334],"improve":[21,116,346],"the":[22,42,53,62,98,117,132,137,266,310,324,347],"amount":[23],"present":[26],"for":[27,193,202,220],"key":[28,48,57,74,143,178,194,251,259,315,339],"resources":[29,75,126,316,340],"reagents":[31],"such":[32,72],"as":[33,73],"antibodies,":[34],"cell":[35],"lines,":[36],"other":[38],"tools":[39,331],"constitute":[41],"inputs":[43],"a":[45,128,142,162,212,242,272,288,301],"study.":[46],"STAR*Methods":[47],"resource":[49,144,179,195,252,260,329],"tables":[50,180,222,261,318],"increased":[52],"\"findability\"":[54],"these":[56,110],"resources,":[58],"improving":[59,250],"transparency":[60],"paper":[63],"warning":[65],"authors":[66,138,336],"(before":[67],"publication)":[68],"about":[69,124],"any":[70],"problems,":[71],"cannot":[77],"be":[78,87,149,155],"uniquely":[79],"identified":[80,157],"or":[81],"those":[82],"known":[85],"problematic,":[88],"but":[89],"they":[90],"not":[92],"commonly":[94],"available":[95],"outside":[96],"Cell":[99],"Press":[100],"journal":[101],"family.":[102],"We":[103,166,209,230],"believe":[104],"processing":[106],"preprints":[107],"adding":[109],"'resource":[111],"table":[112,147,170,196,203,206],"candidates'":[113],"automatically":[114],"will":[115],"availability":[118],"structured":[120],"linked":[122],"research":[125,328],"in":[127,184,262,271,342],"broader":[129],"swath":[130],"scientific":[133,221,228],"literature.":[134],"However,":[135],"if":[136],"already":[140],"added":[141],"table,":[145],"must":[148,154],"detected,":[150],"each":[152],"entity":[153],"correctly":[156],"faithfully":[159,176],"restructured":[160],"into":[161],"standard":[163],"format.":[164,186],"METHODS:":[165],"introduce":[167,211],"four":[168],"end-to-end":[169],"extraction":[171,253,257,313,330],"pipelines":[172,188,283,308],"extract":[174],"reconstruct":[177],"from":[181,317],"biomedical":[182],"papers":[183],"PDF":[185,263],"The":[187,256,352],"employ":[189],"machine":[190],"learning":[191],"approaches":[192],"page":[197],"identification,":[198],"\"Table":[199],"Transformer\"":[200],"models":[201],"detection,":[204],"structure":[207],"recognition.":[208],"also":[210],"character-level":[213],"generative":[214],"pre-trained":[215,223],"transformer":[216],"(GPT)":[217],"language":[218,234,296,355],"model":[219,235],"on":[224,332],"over":[225],"11":[226],"million":[227],"tables.":[229],"fine-tuned":[231],"our":[232,282],"table-specific":[233,295,354],"with":[236,241,294,319],"synthetic":[237],"training":[238,358],"generated":[240],"novel":[243],"approach":[244],"alleviate":[246],"row":[247,298],"over-segmentation":[248],"significantly":[249],"performance.":[254],"RESULTS:":[255],"files":[264],"popular":[267],"GROBID":[268,286],"tool":[269],"resulted":[270],"Grid":[273],"Table":[274],"Similarity":[275],"(GriTS)":[276],"score":[277,303],"0.12.":[279],"All":[280],"outperformed":[285],"large":[289],"margin.":[290],"Our":[291,307],"best":[292],"pipeline":[293],"model-based":[297],"merger":[299],"achieved":[300],"GriTS":[302],"0.90.":[305],"CONCLUSIONS:":[306],"much":[320],"higher":[321],"accuracy,":[322],"enabling":[323],"deployment":[325],"automated":[327],"BioRxiv":[333],"help":[335],"correct":[337],"unidentifiable":[338],"detected":[341],"their":[343,350],"articles":[344],"reproducibility":[348],"findings.":[351],"code,":[353],"model,":[356],"annotated":[357],"evaluation":[360],"publicly":[363],"available.":[364]},"counts_by_year":[],"updated_date":"2026-08-29T07:29:34.045763","created_date":"2025-10-10T00:00:00"}