{"id":"https://openalex.org/W7171518978","doi":"https://doi.org/10.1145/3807503.3819359","title":"An Active Learning Framework for Data-Efficient, Human-in-the-Loop Enzyme Function Prediction","display_name":"An Active Learning Framework for Data-Efficient, Human-in-the-Loop Enzyme Function Prediction","publication_year":2026,"publication_date":"2026-06-30","ids":{"openalex":"https://openalex.org/W7171518978","doi":"https://doi.org/10.1145/3807503.3819359"},"language":null,"primary_location":{"id":"doi:10.1145/3807503.3819359","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3807503.3819359","pdf_url":null,"source":null,"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 17th ACM International Conference on Bioinformatics, Computational Biology and Health Informatics","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3807503.3819359","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5045156137","display_name":"Ashley Babjac","orcid":"https://orcid.org/0000-0002-0991-7726"},"institutions":[{"id":"https://openalex.org/I165733156","display_name":"University of Georgia","ror":"https://ror.org/00te3t702","country_code":"US","type":"education","lineage":["https://openalex.org/I165733156"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ashley Babjac","raw_affiliation_strings":["University of Georgia, Athens, Georgia, USA"],"raw_orcid":"https://orcid.org/0000-0002-0991-7726","affiliations":[{"raw_affiliation_string":"University of Georgia, Athens, Georgia, USA","institution_ids":["https://openalex.org/I165733156"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5030673913","display_name":"Adrienne Hoarfrost","orcid":"https://orcid.org/0000-0003-1006-9661"},"institutions":[{"id":"https://openalex.org/I165733156","display_name":"University of Georgia","ror":"https://ror.org/00te3t702","country_code":"US","type":"education","lineage":["https://openalex.org/I165733156"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Adrienne Hoarfrost","raw_affiliation_strings":["University of Georgia, Athens, Georgia, USA"],"raw_orcid":"https://orcid.org/0000-0003-1006-9661","affiliations":[{"raw_affiliation_string":"University of Georgia, Athens, Georgia, USA","institution_ids":["https://openalex.org/I165733156"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I165733156"],"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":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":null,"topics":[],"keywords":[{"id":"https://openalex.org/keywords/active-learning","display_name":"Active learning (machine learning)","score":0.4952000081539154},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.446399986743927},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.301800012588501},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.2526000142097473},{"id":"https://openalex.org/keywords/enzyme","display_name":"Enzyme","score":0.2313999980688095}],"concepts":[{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5120000243186951},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5044999718666077},{"id":"https://openalex.org/C77967617","wikidata":"https://www.wikidata.org/wiki/Q4677561","display_name":"Active learning (machine learning)","level":2,"score":0.4952000081539154},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.446399986743927},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3197000026702881},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.301800012588501},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.2526000142097473},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.23499999940395355},{"id":"https://openalex.org/C181199279","wikidata":"https://www.wikidata.org/wiki/Q8047","display_name":"Enzyme","level":2,"score":0.2313999980688095},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.22429999709129333}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3807503.3819359","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3807503.3819359","pdf_url":null,"source":null,"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 17th ACM International Conference on Bioinformatics, Computational Biology and Health Informatics","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3807503.3819359","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3807503.3819359","pdf_url":null,"source":null,"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 17th ACM International Conference on Bioinformatics, Computational Biology and Health Informatics","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G3857877006","display_name":null,"funder_award_id":"HR00112530301","funder_id":"https://openalex.org/F4320337531","funder_display_name":"Defense Sciences Office, DARPA"}],"funders":[{"id":"https://openalex.org/F4320337531","display_name":"Defense Sciences Office, DARPA","ror":"https://ror.org/0447fe631"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":16,"referenced_works":["https://openalex.org/W1568139284","https://openalex.org/W2108955812","https://openalex.org/W2110910681","https://openalex.org/W2179512327","https://openalex.org/W2292640198","https://openalex.org/W2892210937","https://openalex.org/W3144239152","https://openalex.org/W3146944767","https://openalex.org/W3194729882","https://openalex.org/W4322494707","https://openalex.org/W4362471278","https://openalex.org/W4368374056","https://openalex.org/W4398197017","https://openalex.org/W4408363707","https://openalex.org/W4415799131","https://openalex.org/W7133208798"],"related_works":[],"abstract_inverted_index":{"Generalizable":[0],"protein":[1,114],"function":[2,38,85,100],"prediction":[3,86],"is":[4],"increasingly":[5],"constrained":[6],"by":[7,40],"the":[8,19,42],"growing":[9],"mismatch":[10],"between":[11],"exponentially":[12],"expanding":[13],"sequences":[14],"of":[15,23],"environmental":[16],"proteins":[17,45],"and":[18,126],"comparatively":[20],"slow":[21],"accumulation":[22],"experimentally":[24,47],"verified":[25],"functional":[26],"data.":[27],"Active":[28],"learning":[29,75,91,105],"offers":[30],"a":[31,68],"promising":[32],"path":[33],"forward":[34],"for":[35,49,64,97],"accelerating":[36],"biological":[37,98],"prediction,":[39,101],"selecting":[41],"most":[43],"informative":[44],"to":[46,81,93,109],"annotate":[48],"data-efficient":[50],"training,":[51],"yet":[52],"its":[53],"potential":[54],"remains":[55],"largely":[56],"unexplored.":[57],"We":[58,88],"introduce":[59],"HATTER":[60],"(Human-in-the-loop":[61],"Adaptive":[62],"Toolkit":[63],"Transferable":[65],"Enzyme":[66],"Representations),":[67],"modular":[69],"framework":[70],"that":[71,103],"integrates":[72],"multiple":[73],"active":[74,90,104],"strategies":[76],"with":[77],"human-in-the-loop":[78],"experimental":[79],"annotation":[80],"efficiently":[82],"fine":[83],"tune":[84],"models.":[87],"compare":[89],"training":[92,96,111],"standard":[94,110],"supervised":[95],"enzyme":[99],"demonstrating":[102],"achieves":[106],"performance":[107],"comparable":[108],"across":[112],"diverse":[113],"sequence":[115],"evaluation":[116],"datasets":[117],"while":[118],"requiring":[119],"fewer":[120],"model":[121],"updates,":[122],"processing":[123],"less":[124],"data,":[125],"substantially":[127],"reducing":[128],"computational":[129],"cost.":[130]},"counts_by_year":[],"updated_date":"2026-07-30T17:31:21.811387","created_date":"2026-07-29T00:00:00"}