{"id":"https://openalex.org/W7204033714","doi":"https://doi.org/10.64898/2026.08.21.746242","title":"A novel benchmark dataset for enzyme function prediction reveals the limitations of state-of-the-art models","display_name":"A novel benchmark dataset for enzyme function prediction reveals the limitations of state-of-the-art models","publication_year":2026,"publication_date":"2026-08-22","ids":{"openalex":"https://openalex.org/W7204033714","doi":"https://doi.org/10.64898/2026.08.21.746242"},"language":"en","primary_location":{"id":"doi:10.64898/2026.08.21.746242","doi":"https://doi.org/10.64898/2026.08.21.746242","is_oa":true,"landing_page_url":"https://doi.org/10.64898/2026.08.21.746242","pdf_url":"https://www.biorxiv.org/content/biorxiv/early/2026/08/22/2026.08.21.746242.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/2026/08/22/2026.08.21.746242.full.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5114159205","display_name":"Jo\u00e3o Sartori","orcid":"https://orcid.org/0009-0002-8173-6118","observed_orcids":["https://orcid.org/0009-0002-8173-6118"]},"institutions":[{"id":"https://openalex.org/I4405286966","display_name":"Instituto Oswaldo Cruz","ror":"https://ror.org/03pww0c55","country_code":"BR","type":"facility","lineage":["https://openalex.org/I4405286966","https://openalex.org/I52325"]},{"id":"https://openalex.org/I52325","display_name":"Funda\u00e7\u00e3o Oswaldo Cruz","ror":"https://ror.org/04jhswv08","country_code":"BR","type":"facility","lineage":["https://openalex.org/I52325"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Jo\u00e3o Sartori","raw_affiliation_strings":["Laborat\u00f3rio de Gen\u00f4mica Aplicada e Bioinova\u00e7\u00f5es, Instituto Oswaldo Cruz/Fiocruz, Rio de Janeiro, 21040-900, Brazil"],"raw_orcid":"https://orcid.org/0009-0002-8173-6118","affiliations":[{"raw_affiliation_string":"Laborat\u00f3rio de Gen\u00f4mica Aplicada e Bioinova\u00e7\u00f5es, Instituto Oswaldo Cruz/Fiocruz, Rio de Janeiro, 21040-900, Brazil","institution_ids":["https://openalex.org/I4405286966","https://openalex.org/I52325"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019125482","display_name":"Ana Carolina Ramos Guimar\u00e3es","orcid":"https://orcid.org/0000-0003-1260-543X","observed_orcids":["https://orcid.org/0000-0003-1260-543X"]},"institutions":[{"id":"https://openalex.org/I4405286966","display_name":"Instituto Oswaldo Cruz","ror":"https://ror.org/03pww0c55","country_code":"BR","type":"facility","lineage":["https://openalex.org/I4405286966","https://openalex.org/I52325"]},{"id":"https://openalex.org/I52325","display_name":"Funda\u00e7\u00e3o Oswaldo Cruz","ror":"https://ror.org/04jhswv08","country_code":"BR","type":"facility","lineage":["https://openalex.org/I52325"]}],"countries":["BR"],"is_corresponding":true,"raw_author_name":"Ana Carolina Ramos Guimar\u00e3es","raw_affiliation_strings":["Laborat\u00f3rio de Gen\u00f4mica Aplicada e Bioinova\u00e7\u00f5es, Instituto Oswaldo Cruz/Fiocruz, Rio de Janeiro, 21040-900, Brazil"],"raw_orcid":"https://orcid.org/0000-0003-1260-543X","affiliations":[{"raw_affiliation_string":"Laborat\u00f3rio de Gen\u00f4mica Aplicada e Bioinova\u00e7\u00f5es, Instituto Oswaldo Cruz/Fiocruz, Rio de Janeiro, 21040-900, Brazil","institution_ids":["https://openalex.org/I4405286966","https://openalex.org/I52325"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5035682634","display_name":"Lucas de Almeida Machado","orcid":"https://orcid.org/0000-0002-6575-1687","observed_orcids":["https://orcid.org/0000-0002-6575-1687"]},"institutions":[{"id":"https://openalex.org/I4405286280","display_name":"Instituto de Tecnologia em Imunobiol\u00f3gicos","ror":"https://ror.org/01q1w1b26","country_code":"BR","type":"government","lineage":["https://openalex.org/I4405286280","https://openalex.org/I52325"]},{"id":"https://openalex.org/I52325","display_name":"Funda\u00e7\u00e3o Oswaldo Cruz","ror":"https://ror.org/04jhswv08","country_code":"BR","type":"facility","lineage":["https://openalex.org/I52325"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Lucas de Almeida Machado","raw_affiliation_strings":["Institute of Technology on Immunobiologicals (Bio-Manguinhos), Fiocruz, Rio de Janeiro, Brazil"],"raw_orcid":"https://orcid.org/0000-0002-6575-1687","affiliations":[{"raw_affiliation_string":"Institute of Technology on Immunobiologicals (Bio-Manguinhos), Fiocruz, Rio de Janeiro, Brazil","institution_ids":["https://openalex.org/I4405286280","https://openalex.org/I52325"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5019125482"],"corresponding_institution_ids":["https://openalex.org/I4405286966","https://openalex.org/I52325"],"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/T12254","display_name":"Machine Learning in Bioinformatics","score":0.9696999788284302,"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/T12254","display_name":"Machine Learning in Bioinformatics","score":0.9696999788284302,"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/T10044","display_name":"Protein Structure and Dynamics","score":0.019099999219179153,"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/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.0034000000450760126,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/enzyme-function-prediction","display_name":"enzyme function prediction","score":0.9990000128746033},{"id":"https://openalex.org/keywords/ec-number-prediction","display_name":"EC number prediction","score":0.6669999957084656},{"id":"https://openalex.org/keywords/benchmark-dataset","display_name":"benchmark dataset","score":0.800000011920929},{"id":"https://openalex.org/keywords/catalytic-residues","display_name":"catalytic residues","score":0.8479999899864197},{"id":"https://openalex.org/keywords/homology-based-annotation","display_name":"homology-based annotation","score":0.7749999761581421},{"id":"https://openalex.org/keywords/contrastive-learning","display_name":"contrastive learning","score":0.7020000219345093},{"id":"https://openalex.org/keywords/protein-language-models","display_name":"protein language models","score":0.9660000205039978}],"concepts":[{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.6279000043869019},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.6276000142097473},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5720999836921692},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5543000102043152},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5324000120162964},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.4560999870300293},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.44839999079704285},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.4269999861717224},{"id":"https://openalex.org/C2986374874","wikidata":"https://www.wikidata.org/wiki/Q8054","display_name":"Protein function","level":3,"score":0.4259999990463257},{"id":"https://openalex.org/C86251818","wikidata":"https://www.wikidata.org/wiki/Q816754","display_name":"Benchmarking","level":2,"score":0.42570000886917114},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.40130001306533813},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.3774000108242035},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.3630000054836273},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.3449999988079071},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.3138999938964844},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.3012999892234802},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.29249998927116394},{"id":"https://openalex.org/C89566754","wikidata":"https://www.wikidata.org/wiki/Q2273828","display_name":"Genome project","level":4,"score":0.2922999858856201},{"id":"https://openalex.org/C141231307","wikidata":"https://www.wikidata.org/wiki/Q7020","display_name":"Genome","level":3,"score":0.28940001130104065},{"id":"https://openalex.org/C66024118","wikidata":"https://www.wikidata.org/wiki/Q1122506","display_name":"Computational model","level":2,"score":0.2842000126838684},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2840000092983246},{"id":"https://openalex.org/C207201462","wikidata":"https://www.wikidata.org/wiki/Q182505","display_name":"Bayes' theorem","level":3,"score":0.28110000491142273},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.27559998631477356},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.2736999988555908},{"id":"https://openalex.org/C111364199","wikidata":"https://www.wikidata.org/wiki/Q2915896","display_name":"Protein methods","level":4,"score":0.26899999380111694},{"id":"https://openalex.org/C18051474","wikidata":"https://www.wikidata.org/wiki/Q899656","display_name":"Protein structure prediction","level":3,"score":0.2547000050544739},{"id":"https://openalex.org/C10010492","wikidata":"https://www.wikidata.org/wiki/Q3142557","display_name":"Protein sequencing","level":4,"score":0.2533000111579895}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.64898/2026.08.21.746242","doi":"https://doi.org/10.64898/2026.08.21.746242","is_oa":true,"landing_page_url":"https://doi.org/10.64898/2026.08.21.746242","pdf_url":"https://www.biorxiv.org/content/biorxiv/early/2026/08/22/2026.08.21.746242.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:10.64898/2026.08.21.746242","doi":"https://doi.org/10.64898/2026.08.21.746242","is_oa":true,"landing_page_url":"https://doi.org/10.64898/2026.08.21.746242","pdf_url":"https://www.biorxiv.org/content/biorxiv/early/2026/08/22/2026.08.21.746242.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":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7204033714.pdf","grobid_xml":"https://content.openalex.org/works/W7204033714.grobid-xml"},"referenced_works_count":31,"referenced_works":["https://openalex.org/W130193107","https://openalex.org/W1970294718","https://openalex.org/W2148000475","https://openalex.org/W2154545304","https://openalex.org/W2155733474","https://openalex.org/W2258180218","https://openalex.org/W2750714005","https://openalex.org/W2766352633","https://openalex.org/W2892210937","https://openalex.org/W2985502476","https://openalex.org/W3035847987","https://openalex.org/W3035910717","https://openalex.org/W3143063265","https://openalex.org/W3146944767","https://openalex.org/W3211795435","https://openalex.org/W4205773061","https://openalex.org/W4221054427","https://openalex.org/W4310957810","https://openalex.org/W4318071656","https://openalex.org/W4322490093","https://openalex.org/W4327550249","https://openalex.org/W4388665407","https://openalex.org/W4389696354","https://openalex.org/W4393944737","https://openalex.org/W4396675754","https://openalex.org/W4399426087","https://openalex.org/W4404458588","https://openalex.org/W4409577420","https://openalex.org/W4415799131","https://openalex.org/W7120165331","https://openalex.org/W7126209807"],"related_works":["https://openalex.org/W4412807054","https://openalex.org/W7202162614","https://openalex.org/W7208793548","https://openalex.org/W4401669909","https://openalex.org/W7162686567","https://openalex.org/W7204614090","https://openalex.org/W4400571117","https://openalex.org/W7161064709","https://openalex.org/W2766352633","https://openalex.org/W2892210937"],"abstract_inverted_index":{"Abstract":[0],"Accurate":[1],"computational":[2,214],"prediction":[3,93],"of":[4,35,59,69,151,166],"enzyme":[5,21],"function,":[6],"standardized":[7],"by":[8],"Enzyme":[9],"Commission":[10],"(EC)":[11],"numbers,":[12],"is":[13,206],"essential":[14],"for":[15,139,208],"large-scale":[16],"genome":[17],"annotation":[18,99],"and":[19,75,81,108,131,193,204],"generative":[20],"design.":[22],"However,":[23],"it":[24],"remains":[25],"unclear":[26],"whether":[27],"state-of-the-art":[28],"predictors":[29,182],"learn":[30],"the":[31,144,149,152,164],"intrinsic":[32],"structural":[33],"determinants":[34],"catalytic":[36,73,153],"activity":[37],"or":[38],"merely":[39],"rely":[40],"on":[41],"global":[42],"sequence":[43],"similarity":[44],"to":[45,126,172,185],"annotated":[46,87],"homologues.":[47],"To":[48],"address":[49],"this":[50,96],"gap,":[51],"we":[52,194],"introduce":[53],"EnzymARC,":[54],"a":[55,109],"novel":[56],"benchmark":[57],"dataset":[58],"putative":[60],"non-functional":[61],"decoy":[62],"sequences":[63],"generated":[64],"via":[65],"structure-guided,":[66],"systematic":[67],"disruption":[68],"active":[70],"sites":[71],"(targeting":[72],"residues":[74],"surrounding":[76],"5":[77],"\u00c5,":[78,80],"10":[79],"15":[82],"\u00c5":[83],"radii)":[84],"from":[85,190],"experimentally":[86],"enzymes.":[88],"We":[89,177],"evaluated":[90],"three":[91],"distinct":[92],"paradigms":[94],"against":[95],"dataset:":[97],"homology-based":[98],"(DIAMOND),":[100],"contrastive":[101],"learning":[102,111],"with":[103],"protein":[104],"language":[105],"models":[106,122,170,212],"(CLEAN),":[107],"deep":[110],"model":[112],"incorporating":[113],"non-enzyme":[114],"discrimination":[115],"(DeepEC).":[116],"Our":[117],"findings":[118],"reveal":[119],"that":[120,179,196],"current":[121],"are":[123],"highly":[124],"vulnerable":[125],"phylogenetic":[127],"shortcuts.":[128],"Both":[129],"DIAMOND":[130],"CLEAN":[132],"exhibited":[133],"false":[134],"positive":[135],"rates":[136],"exceeding":[137],"90%":[138],"low-perturbation":[140],"decoys,":[141],"confidently":[142],"assigning":[143],"original":[145],"EC":[146,181],"numbers":[147],"despite":[148],"destruction":[150],"machinery.":[154],"While":[155],"DeepEC":[156],"demonstrated":[157],"improved":[158],"sensitivity":[159],"at":[160],"higher":[161],"perturbation":[162],"levels\u2014highlighting":[163],"benefit":[165],"negative":[167,199],"training":[168,203],"examples\u2014all":[169],"struggled":[171],"identify":[173],"targeted":[174],"active-site":[175],"disruptions.":[176],"demonstrate":[178],"modern":[180],"largely":[183],"fail":[184],"distinguish":[186],"catalytically":[187],"incompetent":[188],"variants":[189],"functional":[191],"enzymes,":[192],"propose":[195],"integrating":[197],"structure-aware":[198],"examples":[200],"into":[201],"both":[202],"benchmarking":[205],"critical":[207],"developing":[209],"functionally":[210],"robust":[211],"in":[213],"enzymology.":[215]},"counts_by_year":[],"updated_date":"2026-11-10T11:39:43.021295","created_date":"2026-08-24T00:00:00"}