{"id":"https://openalex.org/W7215856779","doi":"https://doi.org/10.48550/arxiv.2610.01616","title":"Can LLMs Reliably Annotate Bioassay Metadata to Improve Data Readiness?","display_name":"Can LLMs Reliably Annotate Bioassay Metadata to Improve Data Readiness?","publication_year":2026,"publication_date":"2026-10-01","ids":{"openalex":"https://openalex.org/W7215856779","doi":"https://doi.org/10.48550/arxiv.2610.01616"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2610.01616","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2610.01616","pdf_url":"https://arxiv.org/pdf/2610.01616","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"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":"text"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2610.01616","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5095837867","display_name":"Laura van Weesep","orcid":"https://orcid.org/0009-0009-5524-7960","observed_orcids":["https://orcid.org/0009-0009-5524-7960"]},"institutions":[{"id":"https://openalex.org/I123387679","display_name":"Uppsala University","ror":"https://ror.org/048a87296","country_code":"SE","type":"education","lineage":["https://openalex.org/I123387679"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"van Weesep, Laura","raw_affiliation_strings":["Department of Information Technology , Uppsala University","Molecular AI, Discovery Sciences R&D , AstraZeneca"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Information Technology , Uppsala University","institution_ids":["https://openalex.org/I123387679"]},{"raw_affiliation_string":"Molecular AI, Discovery Sciences R&D , AstraZeneca","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5115024078","display_name":"Riccardo Tedoldi","orcid":"https://orcid.org/0009-0002-1477-0121","observed_orcids":["https://orcid.org/0009-0002-1477-0121"]},"institutions":[{"id":"https://openalex.org/I86987016","display_name":"KTH Royal Institute of Technology","ror":"https://ror.org/026vcq606","country_code":"SE","type":"education","lineage":["https://openalex.org/I86987016"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"Tedoldi, Riccardo","raw_affiliation_strings":["Molecular AI, Discovery Sciences R&D , AstraZeneca","Robotics, Perception & Learning , KTH Royal Institute of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Molecular AI, Discovery Sciences R&D , AstraZeneca","institution_ids":[]},{"raw_affiliation_string":"Robotics, Perception & Learning , KTH Royal Institute of Technology","institution_ids":["https://openalex.org/I86987016"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032491456","display_name":"Jens Sj\u00f6lund","orcid":"https://orcid.org/0000-0002-9099-3522","observed_orcids":["https://orcid.org/0000-0002-9099-3522"]},"institutions":[{"id":"https://openalex.org/I123387679","display_name":"Uppsala University","ror":"https://ror.org/048a87296","country_code":"SE","type":"education","lineage":["https://openalex.org/I123387679"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"Sj\u00f6lund, Jens","raw_affiliation_strings":["Department of Information Technology , Uppsala University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Information Technology , Uppsala University","institution_ids":["https://openalex.org/I123387679"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071284506","display_name":"Hossein Azizpour","orcid":"https://orcid.org/0000-0001-5211-6388","observed_orcids":["https://orcid.org/0000-0001-5211-6388"]},"institutions":[{"id":"https://openalex.org/I2800139495","display_name":"Science for Life Laboratory","ror":"https://ror.org/04ev03g22","country_code":"SE","type":"facility","lineage":["https://openalex.org/I2800139495"]},{"id":"https://openalex.org/I86987016","display_name":"KTH Royal Institute of Technology","ror":"https://ror.org/026vcq606","country_code":"SE","type":"education","lineage":["https://openalex.org/I86987016"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"Azizpour, Hossein","raw_affiliation_strings":["Robotics, Perception & Learning , KTH Royal Institute of Technology","Science for Life Laboratory , Stockholm , Sweden"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Robotics, Perception & Learning , KTH Royal Institute of Technology","institution_ids":["https://openalex.org/I86987016"]},{"raw_affiliation_string":"Science for Life Laboratory , Stockholm , Sweden","institution_ids":["https://openalex.org/I2800139495"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006529178","display_name":"Susanne Winiwarter","orcid":"https://orcid.org/0000-0002-9808-1683","observed_orcids":["https://orcid.org/0000-0002-9808-1683"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Winiwarter, Susanne","raw_affiliation_strings":["Drug Metabolism and Pharmacokinetics , Research and Early Development, Cardiovascular, Renal and Metabolism (CVRM) , BioPharmaceuticals R&D , AstraZeneca","Molecular AI, Discovery Sciences R&D , AstraZeneca"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Drug Metabolism and Pharmacokinetics , Research and Early Development, Cardiovascular, Renal and Metabolism (CVRM) , BioPharmaceuticals R&D , AstraZeneca","institution_ids":[]},{"raw_affiliation_string":"Molecular AI, Discovery Sciences R&D , AstraZeneca","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076975589","display_name":"Ola Engkvist","orcid":"https://orcid.org/0000-0003-4970-6461","observed_orcids":["https://orcid.org/0000-0003-4970-6461"]},"institutions":[{"id":"https://openalex.org/I66862912","display_name":"Chalmers University of Technology","ror":"https://ror.org/040wg7k59","country_code":"SE","type":"education","lineage":["https://openalex.org/I66862912"]},{"id":"https://openalex.org/I881427289","display_name":"University of Gothenburg","ror":"https://ror.org/01tm6cn81","country_code":"SE","type":"education","lineage":["https://openalex.org/I881427289"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"Engkvist, Ola","raw_affiliation_strings":["Department of Computer Science and Engineering , Chalmers University of Technology and University of Gothenburg , Sweden","Molecular AI, Discovery Sciences R&D , AstraZeneca"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering , Chalmers University of Technology and University of Gothenburg , Sweden","institution_ids":["https://openalex.org/I66862912","https://openalex.org/I881427289"]},{"raw_affiliation_string":"Molecular AI, Discovery Sciences R&D , AstraZeneca","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030485362","display_name":"Jon Paul Janet","orcid":"https://orcid.org/0000-0001-7825-4797","observed_orcids":["https://orcid.org/0000-0001-7825-4797"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Janet, Jon Paul","raw_affiliation_strings":["Molecular AI, Discovery Sciences R&D , AstraZeneca"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Molecular AI, Discovery Sciences R&D , AstraZeneca","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006219866","display_name":"Samuel Genheden","orcid":"https://orcid.org/0000-0002-7624-7363","observed_orcids":["https://orcid.org/0000-0002-7624-7363"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Genheden, Samuel","raw_affiliation_strings":["Molecular AI, Discovery Sciences R&D , AstraZeneca"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Molecular AI, Discovery Sciences R&D , AstraZeneca","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5085770766","display_name":"Juan Viguera Diez","orcid":"https://orcid.org/0000-0002-0526-1766","observed_orcids":["https://orcid.org/0000-0002-0526-1766"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Diez, Juan Viguera","raw_affiliation_strings":["Molecular AI, Discovery Sciences R&D , AstraZeneca"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Molecular AI, Discovery Sciences R&D , AstraZeneca","institution_ids":[]}]}],"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":true,"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":{"id":"https://openalex.org/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.9282000064849854,"subfield":{"id":"https://openalex.org/subfields/2718","display_name":"Health Informatics"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},"topics":[{"id":"https://openalex.org/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.9282000064849854,"subfield":{"id":"https://openalex.org/subfields/2718","display_name":"Health Informatics"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},{"id":"https://openalex.org/T10211","display_name":"Computational Drug Discovery Methods","score":0.0544000007212162,"subfield":{"id":"https://openalex.org/subfields/3002","display_name":"Drug Discovery"},"field":{"id":"https://openalex.org/fields/30","display_name":"Pharmacology, Toxicology and Pharmaceutics"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T11948","display_name":"Machine Learning in Materials Science","score":0.0034000000450760126,"subfield":{"id":"https://openalex.org/subfields/2505","display_name":"Materials Chemistry"},"field":{"id":"https://openalex.org/fields/25","display_name":"Materials Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/large-language-models","display_name":"large language models","score":0.9670000076293945},{"id":"https://openalex.org/keywords/pubchem","display_name":"PubChem","score":0.765999972820282},{"id":"https://openalex.org/keywords/chembl","display_name":"ChEMBL","score":0.878000020980835},{"id":"https://openalex.org/keywords/annotation-reliability","display_name":"annotation reliability","score":0.40400001406669617},{"id":"https://openalex.org/keywords/data-curation","display_name":"data curation","score":0.5529999732971191},{"id":"https://openalex.org/keywords/molecular-property-prediction","display_name":"molecular property prediction","score":0.753000020980835}],"concepts":[{"id":"https://openalex.org/C93518851","wikidata":"https://www.wikidata.org/wiki/Q180160","display_name":"Metadata","level":2,"score":0.7702999711036682},{"id":"https://openalex.org/C158180186","wikidata":"https://www.wikidata.org/wiki/Q278487","display_name":"PubChem","level":2,"score":0.7541000247001648},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.6516000032424927},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6358000040054321},{"id":"https://openalex.org/C199521495","wikidata":"https://www.wikidata.org/wiki/Q181487","display_name":"Audit","level":2,"score":0.476500004529953},{"id":"https://openalex.org/C104488531","wikidata":"https://www.wikidata.org/wiki/Q864212","display_name":"Bioassay","level":2,"score":0.45750001072883606},{"id":"https://openalex.org/C25810664","wikidata":"https://www.wikidata.org/wiki/Q44325","display_name":"Ontology","level":2,"score":0.45590001344680786},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.364300012588501},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.36239999532699585},{"id":"https://openalex.org/C2778383056","wikidata":"https://www.wikidata.org/wiki/Q873636","display_name":"Namespace","level":2,"score":0.35120001435279846},{"id":"https://openalex.org/C56666940","wikidata":"https://www.wikidata.org/wiki/Q788790","display_name":"Documentation","level":2,"score":0.3476000130176544},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.32850000262260437},{"id":"https://openalex.org/C2778473407","wikidata":"https://www.wikidata.org/wiki/Q1459574","display_name":"Compendium","level":2,"score":0.32749998569488525},{"id":"https://openalex.org/C155261790","wikidata":"https://www.wikidata.org/wiki/Q1122544","display_name":"DrugBank","level":3,"score":0.3073999881744385},{"id":"https://openalex.org/C2781162219","wikidata":"https://www.wikidata.org/wiki/Q26250693","display_name":"Replicate","level":2,"score":0.3010999858379364},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.2939999997615814},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.2856000065803528},{"id":"https://openalex.org/C43214815","wikidata":"https://www.wikidata.org/wiki/Q7310987","display_name":"Reliability (semiconductor)","level":3,"score":0.28380000591278076},{"id":"https://openalex.org/C153048206","wikidata":"https://www.wikidata.org/wiki/Q3454922","display_name":"Metadata repository","level":3,"score":0.2831999957561493},{"id":"https://openalex.org/C71901391","wikidata":"https://www.wikidata.org/wiki/Q7126699","display_name":"Upload","level":2,"score":0.27410000562667847},{"id":"https://openalex.org/C81669768","wikidata":"https://www.wikidata.org/wiki/Q2359161","display_name":"Precision and recall","level":2,"score":0.2720000147819519},{"id":"https://openalex.org/C2992692520","wikidata":"https://www.wikidata.org/wiki/Q3931124","display_name":"Reality check","level":3,"score":0.27149999141693115},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.25859999656677246}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2610.01616","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2610.01616","pdf_url":"https://arxiv.org/pdf/2610.01616","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"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":"text"},{"id":"doi:10.48550/arxiv.2610.01616","doi":"https://doi.org/10.48550/arxiv.2610.01616","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2610.01616","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2610.01616","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2610.01616","pdf_url":"https://arxiv.org/pdf/2610.01616","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"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":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320307770","display_name":"AstraZeneca","ror":"https://ror.org/04r9x1a08"},{"id":"https://openalex.org/F4320322327","display_name":"Knut och Alice Wallenbergs Stiftelse","ror":"https://ror.org/004hzzk67"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7215856779.pdf","grobid_xml":"https://content.openalex.org/works/W7215856779.grobid-xml"},"referenced_works_count":19,"referenced_works":["https://openalex.org/W2000818167","https://openalex.org/W2008951000","https://openalex.org/W2016976521","https://openalex.org/W2049415080","https://openalex.org/W2053154970","https://openalex.org/W2096541451","https://openalex.org/W2096560421","https://openalex.org/W2133614244","https://openalex.org/W2302501749","https://openalex.org/W3015572666","https://openalex.org/W3164540570","https://openalex.org/W4365504163","https://openalex.org/W4388455891","https://openalex.org/W4404511389","https://openalex.org/W4404793875","https://openalex.org/W4410202920","https://openalex.org/W4416254417","https://openalex.org/W6907797058","https://openalex.org/W7214122975"],"related_works":["https://openalex.org/W7128682674","https://openalex.org/W4414206965","https://openalex.org/W7163089262","https://openalex.org/W7170070297","https://openalex.org/W7092284795","https://openalex.org/W6949182392","https://openalex.org/W2163841005","https://openalex.org/W7130346936","https://openalex.org/W7214101183","https://openalex.org/W7156163671"],"abstract_inverted_index":{"The":[0],"emergence":[1],"of":[2,13,44,139,178,211,246],"foundation":[3],"models":[4,69,231],"for":[5,49,123,154,164],"molecular":[6],"property":[7],"prediction":[8],"requires":[9],"a":[10,106,161,195,199],"high":[11],"degree":[12],"AI":[14],"data":[15],"readiness,":[16],"including":[17],"reliable":[18],"metadata":[19,76],"annotation.":[20],"However,":[21],"both":[22],"public":[23],"repositories":[24],"and":[25,56,61,65,74,109,133,142,156,229,244,253],"industrial":[26,201],"screening":[27],"databases":[28],"suffer":[29],"from":[30,79,131],"missing,":[31],"inconsistent,":[32],"or":[33,115],"conflated":[34],"assay":[35,54,81,103,113,158,247],"annotations.":[36],"In":[37,83],"this":[38],"work,":[39],"we":[40,86,135],"quantify":[41],"the":[42,50,80,89,121,137,206,223,241],"extent":[43],"missing":[45],"annotations":[46,77],"in":[47,194],"PubChem":[48,132],"BioAssay":[51,107],"Ontology":[52],"(BAO)":[53],"format":[55,114],"physical":[57],"detection":[58,116,165],"method":[59],"fields":[60],"investigate":[62],"whether":[63],"open-source":[64,141,230],"proprietary":[66,143,228],"large":[67],"language":[68],"(LLMs)":[70],"can":[71,217,239],"reliably":[72],"predict":[73],"audit":[75],"directly":[78],"text.":[82],"our":[84],"assessment,":[85],"found":[87],"that":[88,176],"annotation":[90,243],"coverage":[91],"across":[92],"PubChem's":[93],"$\\sim$2":[94],"million":[95],"bioassays":[96],"is":[97,150],"critically":[98],"sparse,":[99],"36\\%":[100],"lacking":[101],"an":[102],"format,":[104],"89\\%":[105],"type,":[108],">99.9\\%":[110],"any":[111],"BAO-mapped":[112],"technology":[117],"term.":[118],"This":[119],"motivates":[120],"need":[122],"automated":[124],"test-metadata":[125],"curation.":[126],"Using":[127],"evaluation":[128],"sets":[129],"derived":[130],"ChEMBL,":[134],"assess":[136],"agreement":[138],"seven":[140],"LLMs":[144,216,238],"with":[145,160,198],"existing":[146],"silver":[147,186],"labels.":[148],"Recall":[149],"at":[151],"least":[152],"0.96":[153],"biochemical":[155],"cell-based":[157],"formats,":[159],"similar":[162],"pattern":[163],"technology,":[166],"although":[167],"disagreements":[168,180],"increase":[169],"on":[170],"under-represented":[171],"classes.":[172],"Manual":[173],"inspection":[174],"shows":[175],"many":[177],"these":[179,235],"trace":[181],"back":[182],"to":[183,190,208],"inconsistencies":[184],"between":[185,227],"sources":[187],"rather":[188],"than":[189],"LLM":[191],"error.":[192],"Moreover,":[193],"qualitative":[196],"study":[197],"senior":[200],"curator,":[202],"LLM-generated":[203],"evidence":[204],"prompted":[205],"expert":[207],"revise":[209],"some":[210],"their":[212],"own":[213],"labels,":[214],"showing":[215],"flag":[218],"potentially":[219],"mislabeled":[220],"assays.":[221],"Across":[222],"study,":[224],"performance":[225],"differences":[226],"were":[232],"small.":[233],"Together,":[234],"results":[236],"suggest":[237],"support":[240],"large-scale":[242],"auditing":[245],"metadata,":[248],"though":[249],"per-class":[250],"reliability":[251],"estimates":[252],"targeted":[254],"human":[255],"review":[256],"remain":[257],"necessary":[258],"before":[259],"such":[260],"labels":[261],"enter":[262],"downstream":[263],"ML":[264],"pipelines.":[265]},"counts_by_year":[],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2026-10-03T00:00:00"}