{"id":"https://openalex.org/W7214736486","doi":"https://doi.org/10.64898/2026.09.24.754045","title":"A low-annotation-budget PubMedBERT classifier for chondrogenesis regulator discovery via active learning","display_name":"A low-annotation-budget PubMedBERT classifier for chondrogenesis regulator discovery via active learning","publication_year":2026,"publication_date":"2026-09-29","ids":{"openalex":"https://openalex.org/W7214736486","doi":"https://doi.org/10.64898/2026.09.24.754045"},"language":"en","primary_location":{"id":"doi:10.64898/2026.09.24.754045","doi":"https://doi.org/10.64898/2026.09.24.754045","is_oa":true,"landing_page_url":"https://doi.org/10.64898/2026.09.24.754045","pdf_url":"https://www.biorxiv.org/content/biorxiv/early/2026/09/29/2026.09.24.754045.full.pdf","source":{"id":"https://openalex.org/S4306402567","display_name":"bioRxiv (Cold Spring Harbor Laboratory)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I2750212522","host_organization_name":"Cold Spring Harbor Laboratory","host_organization_lineage":["https://openalex.org/I2750212522"],"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":"bioRxiv","raw_type":"posted-content"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://www.biorxiv.org/content/biorxiv/early/2026/09/29/2026.09.24.754045.full.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5092236706","display_name":"Ana Mariya Anhel","orcid":"https://orcid.org/0000-0002-4097-3638","observed_orcids":["https://orcid.org/0000-0002-4097-3638"]},"institutions":[{"id":"https://openalex.org/I146655781","display_name":"University of Liverpool","ror":"https://ror.org/04xs57h96","country_code":"GB","type":"education","lineage":["https://openalex.org/I146655781"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Ana-Mariya Anhel","raw_affiliation_strings":["Institute of Systems, Molecular and Integrative Biology, University of Liverpool, Liverpool L69 7ZB, UK"],"raw_orcid":"https://orcid.org/0000-0002-4097-3638","affiliations":[{"raw_affiliation_string":"Institute of Systems, Molecular and Integrative Biology, University of Liverpool, Liverpool L69 7ZB, UK","institution_ids":["https://openalex.org/I146655781"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014541944","display_name":"Mandy Jayne Peffers","orcid":"https://orcid.org/0000-0001-6979-0440","observed_orcids":["https://orcid.org/0000-0001-6979-0440"]},"institutions":[{"id":"https://openalex.org/I146655781","display_name":"University of Liverpool","ror":"https://ror.org/04xs57h96","country_code":"GB","type":"education","lineage":["https://openalex.org/I146655781"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Mandy Jayne Peffers","raw_affiliation_strings":["Institute of Life Course and Medical Sciences, University of Liverpool, Liverpool L7 8TX, UK"],"raw_orcid":"https://orcid.org/0000-0001-6979-0440","affiliations":[{"raw_affiliation_string":"Institute of Life Course and Medical Sciences, University of Liverpool, Liverpool L7 8TX, UK","institution_ids":["https://openalex.org/I146655781"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025695140","display_name":"David Alan Young","orcid":"https://orcid.org/0000-0002-7078-6745","observed_orcids":["https://orcid.org/0000-0002-7078-6745"]},"institutions":[{"id":"https://openalex.org/I84884186","display_name":"Newcastle University","ror":"https://ror.org/01kj2bm70","country_code":"GB","type":"education","lineage":["https://openalex.org/I84884186"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"David A Young","raw_affiliation_strings":["Biosciences Institute, Newcastle University, Newcastle upon Tyne NE1 3BZ, UK"],"raw_orcid":"https://orcid.org/0000-0002-7078-6745","affiliations":[{"raw_affiliation_string":"Biosciences Institute, Newcastle University, Newcastle upon Tyne NE1 3BZ, UK","institution_ids":["https://openalex.org/I84884186"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5032957076","display_name":"Jamie Soul","orcid":"https://orcid.org/0000-0003-2255-6459","observed_orcids":["https://orcid.org/0000-0003-2255-6459"]},"institutions":[{"id":"https://openalex.org/I146655781","display_name":"University of Liverpool","ror":"https://ror.org/04xs57h96","country_code":"GB","type":"education","lineage":["https://openalex.org/I146655781"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Jamie Soul","raw_affiliation_strings":["Computational Biology Facility, University of Liverpool, Liverpool L69 7ZB, UK","Institute of Systems, Molecular and Integrative Biology, University of Liverpool, Liverpool L69 7ZB, UK"],"raw_orcid":"https://orcid.org/0000-0003-2255-6459","affiliations":[{"raw_affiliation_string":"Computational Biology Facility, University of Liverpool, Liverpool L69 7ZB, UK","institution_ids":["https://openalex.org/I146655781"]},{"raw_affiliation_string":"Institute of Systems, Molecular and Integrative Biology, University of Liverpool, Liverpool L69 7ZB, UK","institution_ids":["https://openalex.org/I146655781"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5032957076"],"corresponding_institution_ids":["https://openalex.org/I146655781"],"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":0.9965999722480774,"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":0.9965999722480774,"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/T10028","display_name":"Topic Modeling","score":0.0003000000142492354,"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/T12072","display_name":"Machine Learning and Algorithms","score":0.00019999999494757503,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/chondrogenic-differentiation","display_name":"chondrogenic differentiation","score":0.9940000176429749},{"id":"https://openalex.org/keywords/active-learning-machine-learning","display_name":"active learning (machine learning)","score":0.7540000081062317},{"id":"https://openalex.org/keywords/pubmedbert","display_name":"PubMedBERT","score":0.8880000114440918},{"id":"https://openalex.org/keywords/annotation-cost-reduction","display_name":"annotation cost reduction","score":0.8009999990463257},{"id":"https://openalex.org/keywords/large-language-models-comparison","display_name":"large language models comparison","score":0.7450000047683716},{"id":"https://openalex.org/keywords/biomedical-text-classification","display_name":"biomedical text classification","score":0.5569999814033508},{"id":"https://openalex.org/keywords/gene-ontology","display_name":"Gene Ontology","score":0.7450000047683716}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.682200014591217},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.6252999901771545},{"id":"https://openalex.org/C77967617","wikidata":"https://www.wikidata.org/wiki/Q4677561","display_name":"Active learning (machine learning)","level":2,"score":0.534600019454956},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5239999890327454},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.5144000053405762},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4645000100135803},{"id":"https://openalex.org/C6929976","wikidata":"https://www.wikidata.org/wiki/Q3771881","display_name":"Regulator","level":3,"score":0.3806000053882599},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.3499999940395355},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.3197999894618988},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.29829999804496765},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.28929999470710754},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.28439998626708984},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.2736999988555908},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.26669999957084656}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.64898/2026.09.24.754045","doi":"https://doi.org/10.64898/2026.09.24.754045","is_oa":true,"landing_page_url":"https://doi.org/10.64898/2026.09.24.754045","pdf_url":"https://www.biorxiv.org/content/biorxiv/early/2026/09/29/2026.09.24.754045.full.pdf","source":{"id":"https://openalex.org/S4306402567","display_name":"bioRxiv (Cold Spring Harbor Laboratory)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I2750212522","host_organization_name":"Cold Spring Harbor Laboratory","host_organization_lineage":["https://openalex.org/I2750212522"],"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":"bioRxiv","raw_type":"posted-content"}],"best_oa_location":{"id":"doi:10.64898/2026.09.24.754045","doi":"https://doi.org/10.64898/2026.09.24.754045","is_oa":true,"landing_page_url":"https://doi.org/10.64898/2026.09.24.754045","pdf_url":"https://www.biorxiv.org/content/biorxiv/early/2026/09/29/2026.09.24.754045.full.pdf","source":{"id":"https://openalex.org/S4306402567","display_name":"bioRxiv (Cold Spring Harbor Laboratory)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I2750212522","host_organization_name":"Cold Spring Harbor Laboratory","host_organization_lineage":["https://openalex.org/I2750212522"],"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":"bioRxiv","raw_type":"posted-content"},"sustainable_development_goals":[],"study_designs":[],"awards":[{"id":"https://openalex.org/G4005161464","display_name":"NLD (Newcastle-Liverpool-Durham) Doctoral Training Partnership 3","funder_award_id":"BB/T008695/1","funder_id":"https://openalex.org/F4320334629","funder_display_name":"Biotechnology and Biological Sciences Research Council"}],"funders":[{"id":"https://openalex.org/F4320332167","display_name":"Directorate for Biological Sciences","ror":"https://ror.org/001xhss06"},{"id":"https://openalex.org/F4320334629","display_name":"Biotechnology and Biological Sciences Research Council","ror":"https://ror.org/00cwqg982"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7214736486.pdf","grobid_xml":"https://content.openalex.org/works/W7214736486.grobid-xml"},"referenced_works_count":72,"referenced_works":["https://openalex.org/W1965887320","https://openalex.org/W1990205367","https://openalex.org/W2040298461","https://openalex.org/W2090247362","https://openalex.org/W2092156139","https://openalex.org/W2097960255","https://openalex.org/W2103017472","https://openalex.org/W2109098567","https://openalex.org/W2110910681","https://openalex.org/W2115150863","https://openalex.org/W2123036291","https://openalex.org/W2132910334","https://openalex.org/W2138250184","https://openalex.org/W2159620792","https://openalex.org/W2160091014","https://openalex.org/W2160445739","https://openalex.org/W2165086927","https://openalex.org/W2195753191","https://openalex.org/W2605218377","https://openalex.org/W2774918944","https://openalex.org/W2808272687","https://openalex.org/W2915623326","https://openalex.org/W2949071206","https://openalex.org/W3001060565","https://openalex.org/W3006007721","https://openalex.org/W3026298482","https://openalex.org/W3036473471","https://openalex.org/W3046375318","https://openalex.org/W3080945644","https://openalex.org/W3081978500","https://openalex.org/W3105522431","https://openalex.org/W3157189172","https://openalex.org/W3198980621","https://openalex.org/W3200735940","https://openalex.org/W3212619984","https://openalex.org/W3216092102","https://openalex.org/W4205735465","https://openalex.org/W4205999808","https://openalex.org/W4221153690","https://openalex.org/W4281697262","https://openalex.org/W4297253404","https://openalex.org/W4306165653","https://openalex.org/W4313381334","https://openalex.org/W4322718191","https://openalex.org/W4377093904","https://openalex.org/W4385573087","https://openalex.org/W4387420637","https://openalex.org/W4387561528","https://openalex.org/W4387744370","https://openalex.org/W4387934104","https://openalex.org/W4390886900","https://openalex.org/W4391144737","https://openalex.org/W4391483196","https://openalex.org/W4391742151","https://openalex.org/W4392190584","https://openalex.org/W4392822465","https://openalex.org/W4394737844","https://openalex.org/W4399109812","https://openalex.org/W4401042631","https://openalex.org/W4401306886","https://openalex.org/W4402535087","https://openalex.org/W4402901255","https://openalex.org/W4406128255","https://openalex.org/W4407342688","https://openalex.org/W4412676279","https://openalex.org/W4412781332","https://openalex.org/W4414939355","https://openalex.org/W4416084097","https://openalex.org/W6928838538","https://openalex.org/W7123911138","https://openalex.org/W7125419375","https://openalex.org/W7131793457"],"related_works":["https://openalex.org/W2950905432","https://openalex.org/W4402317944","https://openalex.org/W3135245391","https://openalex.org/W4399726892","https://openalex.org/W4319323476","https://openalex.org/W2617577134","https://openalex.org/W2132910334","https://openalex.org/W3212115119","https://openalex.org/W3088039990","https://openalex.org/W4389815089"],"abstract_inverted_index":{"Abstract":[0],"Motivation":[1],"Biomedical":[2],"natural":[3],"language":[4,40],"processing":[5],"(Bio-NLP)":[6],"classification":[7],"tasks":[8],"are":[9,26,201,219],"often":[10],"limited":[11],"by":[12,34],"the":[13,122,129,138,176],"cost":[14,33],"of":[15,71,103,109,133,155,187],"manual":[16],"annotation,":[17,45],"especially":[18],"for":[19],"specialised":[20],"extraction":[21],"problems":[22],"where":[23],"labelled":[24],"corpora":[25],"scarce.":[27],"Active":[28],"learning":[29,59,92],"can":[30,60],"reduce":[31],"this":[32],"prioritising":[35],"informative":[36],"samples,":[37],"while":[38,136],"large":[39],"models":[41],"(LLMs)":[42],"avoid":[43],"task-specific":[44],"but":[46],"at":[47,64,197,203],"high":[48],"computational":[49,67],"cost.":[50],"We":[51,88],"ask":[52],"whether":[53],"an":[54,90,107],"encoder":[55],"trained":[56],"via":[57],"active":[58,91],"match":[61],"LLM":[62],"performance":[63],"a":[65,78,222],"lower":[66],"cost,":[68],"using":[69,111],"identification":[70],"chondrogenesis":[72],"regulators":[73,102,186],"from":[74],"PubMed":[75],"abstracts":[76],"as":[77,101],"test":[79],"case":[80],"applicable":[81],"to":[82,94,97,144,160,175,184],"other":[83,188],"under-annotated":[84],"Bio-NLP":[85],"problems.":[86],"Results":[87],"built":[89],"framework":[93],"fine-tune":[95],"PubMedBERT":[96,120],"classify":[98],"gene":[99,146],"mentions":[100],"chondrocyte":[104,161],"differentiation,":[105],"achieving":[106],"AUC-ROC":[108,126],"0.93":[110],"1,238":[112],"annotated":[113],"sentences.":[114],"Against":[115],"open-weight":[116],"LLMs":[117,124],"(Qwen3,":[118],"Llama-3.1),":[119],"matched":[121],"top-performing":[123],"on":[125],"and":[127,166,192],"achieved":[128],"highest":[130],"precision":[131],"(0.69)":[132],"any":[134],"model,":[135],"classifying":[137],"full":[139],"corpus":[140],"far":[141],"faster.":[142],"Applied":[143],"67,111":[145],"mentions,":[147],"it":[148,180],"identified":[149],"1,128":[150],"candidate":[151],"regulators,":[152],"recovered":[153],"79%":[154],"Gene":[156],"Ontology-annotated":[157],"genes":[158,164],"related":[159],"differentiation":[162],"(94":[163],"recovered),":[165],"proposed":[167],"981":[168],"new":[169],"candidates.":[170],"The":[171],"pipeline":[172],"is":[173,195,209],"agnostic":[174],"target":[177],"process,":[178],"suggesting":[179],"could":[181],"be":[182],"adapted":[183],"identify":[185],"biological":[189],"processes.":[190],"Availability":[191],"Implementation":[193],"Code":[194],"available":[196,202,210,220],"https://github.com/ChondroTextomics/ALRegulatorDiscovery":[198],".":[199,206],"Data":[200],"Zenodo:":[204],"https://doi.org/10.5281/zenodo.22746090":[205],"Final":[207],"model":[208],"in":[211,221],"HuggingFace":[212],"Hub":[213],"amav/pubmedbert-chondrogenesis-classifier":[214],"Supplementary":[215,217],"information":[216],"data":[218],"separate":[223],"file":[224]},"counts_by_year":[],"updated_date":"2026-11-09T13:22:03.289127","created_date":"2026-09-30T00:00:00"}