{"id":"https://openalex.org/W7212045300","doi":"https://doi.org/10.48550/arxiv.2609.07897","title":"The Accuracy Paradox: Empirical Diagnostic of Default Decision Thresholds in Multi-Label Enzyme Commission Prediction [With Code]","display_name":"The Accuracy Paradox: Empirical Diagnostic of Default Decision Thresholds in Multi-Label Enzyme Commission Prediction [With Code]","publication_year":2026,"publication_date":"2026-09-07","ids":{"openalex":"https://openalex.org/W7212045300","doi":"https://doi.org/10.48550/arxiv.2609.07897"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2609.07897","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.07897","pdf_url":"https://arxiv.org/pdf/2609.07897","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/2609.07897","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5150969829","display_name":"Bilal Ahmad","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I115592961","display_name":"Jiangsu University","ror":"https://ror.org/03jc41j30","country_code":"CN","type":"education","lineage":["https://openalex.org/I115592961"]},{"id":"https://openalex.org/I142732210","display_name":"University of Engineering and Technology Lahore","ror":"https://ror.org/0051w2v06","country_code":"PK","type":"education","lineage":["https://openalex.org/I142732210"]}],"countries":["CN","PK"],"is_corresponding":false,"raw_author_name":"Ahmad, Bilal","raw_affiliation_strings":["Department of Computer Science and Engineering , Jiangsu University , Jiangsu , China","The Department of Electrical, Electronics and Telecommunication Engineering , UET Lahore , Pakistan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering , Jiangsu University , Jiangsu , China","institution_ids":["https://openalex.org/I115592961"]},{"raw_affiliation_string":"The Department of Electrical, Electronics and Telecommunication Engineering , UET Lahore , Pakistan","institution_ids":["https://openalex.org/I142732210"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5138822429","display_name":"Rajed Mehmood","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I142732210","display_name":"University of Engineering and Technology Lahore","ror":"https://ror.org/0051w2v06","country_code":"PK","type":"education","lineage":["https://openalex.org/I142732210"]}],"countries":["PK"],"is_corresponding":false,"raw_author_name":"Mehmood, Rajed","raw_affiliation_strings":["The Department of Electrical, Electronics and Telecommunication Engineering , UET Lahore , Pakistan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Department of Electrical, Electronics and Telecommunication Engineering , UET Lahore , Pakistan","institution_ids":["https://openalex.org/I142732210"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"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/T10211","display_name":"Computational Drug Discovery Methods","score":0.47119998931884766,"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"}},"topics":[{"id":"https://openalex.org/T10211","display_name":"Computational Drug Discovery Methods","score":0.47119998931884766,"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/T12254","display_name":"Machine Learning in Bioinformatics","score":0.47049999237060547,"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/T11652","display_name":"Imbalanced Data Classification Techniques","score":0.015599999576807022,"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/multi-label-classification","display_name":"multi-label classification","score":0.9169999957084656},{"id":"https://openalex.org/keywords/decision-threshold-optimization","display_name":"decision threshold optimization","score":0.777999997138977},{"id":"https://openalex.org/keywords/class-imbalance","display_name":"class imbalance","score":0.9860000014305115},{"id":"https://openalex.org/keywords/conformal-calibration","display_name":"conformal calibration","score":0.7770000100135803},{"id":"https://openalex.org/keywords/post-processing","display_name":"post-processing","score":0.48500001430511475},{"id":"https://openalex.org/keywords/topological-indices","display_name":"topological indices","score":0.6259999871253967},{"id":"https://openalex.org/keywords/molecular-fingerprints","display_name":"molecular fingerprints","score":0.8230000138282776}],"concepts":[{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.7476999759674072},{"id":"https://openalex.org/C42023084","wikidata":"https://www.wikidata.org/wiki/Q5249231","display_name":"Decision boundary","level":3,"score":0.63919997215271},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6345000267028809},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5730000138282776},{"id":"https://openalex.org/C81669768","wikidata":"https://www.wikidata.org/wiki/Q2359161","display_name":"Precision and recall","level":2,"score":0.5031999945640564},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4925999939441681},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4537999927997589},{"id":"https://openalex.org/C152124472","wikidata":"https://www.wikidata.org/wiki/Q1204361","display_name":"Redundancy (engineering)","level":2,"score":0.4090999960899353},{"id":"https://openalex.org/C165838908","wikidata":"https://www.wikidata.org/wiki/Q736777","display_name":"Calibration","level":2,"score":0.396699994802475},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.3727000057697296},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3682999908924103},{"id":"https://openalex.org/C120936955","wikidata":"https://www.wikidata.org/wiki/Q2155640","display_name":"Empirical research","level":2,"score":0.3637999892234802},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.36039999127388},{"id":"https://openalex.org/C84839998","wikidata":"https://www.wikidata.org/wiki/Q5249245","display_name":"Decision rule","level":2,"score":0.314300000667572},{"id":"https://openalex.org/C149782125","wikidata":"https://www.wikidata.org/wiki/Q160039","display_name":"Econometrics","level":1,"score":0.3098999857902527},{"id":"https://openalex.org/C117220453","wikidata":"https://www.wikidata.org/wiki/Q5172842","display_name":"Correlation","level":2,"score":0.3050999939441681},{"id":"https://openalex.org/C100660578","wikidata":"https://www.wikidata.org/wiki/Q18733","display_name":"Recall","level":2,"score":0.3028999865055084},{"id":"https://openalex.org/C45942800","wikidata":"https://www.wikidata.org/wiki/Q245652","display_name":"Ensemble learning","level":2,"score":0.29899999499320984},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2955999970436096},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.288100004196167},{"id":"https://openalex.org/C148483581","wikidata":"https://www.wikidata.org/wiki/Q446488","display_name":"Feature selection","level":2,"score":0.2840000092983246},{"id":"https://openalex.org/C2776836416","wikidata":"https://www.wikidata.org/wiki/Q1364844","display_name":"False alarm","level":2,"score":0.27619999647140503},{"id":"https://openalex.org/C41426520","wikidata":"https://www.wikidata.org/wiki/Q1192065","display_name":"Point estimation","level":2,"score":0.271699994802475},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.2694999873638153},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.2678000032901764},{"id":"https://openalex.org/C83546350","wikidata":"https://www.wikidata.org/wiki/Q1139051","display_name":"Regression","level":2,"score":0.26030001044273376},{"id":"https://openalex.org/C166955791","wikidata":"https://www.wikidata.org/wiki/Q629579","display_name":"Macro","level":2,"score":0.25290000438690186},{"id":"https://openalex.org/C774472","wikidata":"https://www.wikidata.org/wiki/Q6760393","display_name":"Margin (machine learning)","level":2,"score":0.25220000743865967},{"id":"https://openalex.org/C136389625","wikidata":"https://www.wikidata.org/wiki/Q334384","display_name":"Supervised learning","level":3,"score":0.25}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2609.07897","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.07897","pdf_url":"https://arxiv.org/pdf/2609.07897","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.2609.07897","doi":"https://doi.org/10.48550/arxiv.2609.07897","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2609.07897","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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2609.07897","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.07897","pdf_url":"https://arxiv.org/pdf/2609.07897","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":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7212045300.pdf","grobid_xml":"https://content.openalex.org/works/W7212045300.grobid-xml"},"referenced_works_count":14,"referenced_works":["https://openalex.org/W1953606363","https://openalex.org/W2111973517","https://openalex.org/W2114315281","https://openalex.org/W2118978333","https://openalex.org/W2148143831","https://openalex.org/W2338318698","https://openalex.org/W2559588208","https://openalex.org/W2908663744","https://openalex.org/W2918408501","https://openalex.org/W4205450485","https://openalex.org/W4280571589","https://openalex.org/W4281700276","https://openalex.org/W4403245213","https://openalex.org/W7128439489"],"related_works":["https://openalex.org/W4391338829","https://openalex.org/W7120165331","https://openalex.org/W4412807054","https://openalex.org/W4388891993","https://openalex.org/W2948948096","https://openalex.org/W4407275359","https://openalex.org/W7171502437","https://openalex.org/W4379087313","https://openalex.org/W7126209807","https://openalex.org/W3027087787"],"abstract_inverted_index":{"Automated":[0],"prediction":[1],"of":[2,47,87],"Enzyme":[3],"Commission":[4],"(EC)":[5],"numbers":[6],"plays":[7],"a":[8,43,73,82,118],"central":[9],"role":[10],"in":[11,117,163],"functional":[12],"annotation":[13],"and":[14,93,107,171,185],"computational":[15],"drug":[16],"discovery.":[17],"However,":[18],"standard":[19,157],"multi-label":[20,79],"machine":[21,183],"learning":[22,184,187],"pipelines":[23],"frequently":[24],"rely":[25],"on":[26],"default":[27],"decision":[28,50,120],"thresholds":[29],"(t=0.50),":[30],"assuming":[31],"balanced":[32],"prior":[33],"distributions":[34],"across":[35,57],"target":[36,102],"heads.":[37],"In":[38],"this":[39,152],"study,":[40],"we":[41],"present":[42],"systematic":[44],"empirical":[45],"diagnostic":[46,153],"uncalibrated":[48],"fixed":[49],"boundaries":[51],"operating":[52],"under":[53],"severe":[54,98],"class":[55],"imbalance":[56],"N":[58],"=":[59,126,133],"14,096":[60],"annotated":[61],"compounds":[62],"categorized":[63],"into":[64],"six":[65],"primary":[66],"EC":[67],"classes":[68,103,111],"(EC1-EC6).":[69],"Our":[70],"results":[71],"highlight":[72],"pronounced":[74],"Accuracy":[75],"Paradox:":[76],"while":[77],"the":[78,89],"system":[80],"achieves":[81],"deceivingly":[83],"high":[84,140],"mean":[85],"accuracy":[86],"77.16%,":[88],"macro":[90,94],"F1-score":[91],"(0.3976)":[92],"recall":[95,114],"(0.3872)":[96],"reveal":[97],"predictive":[99],"breakdown.":[100],"Majority":[101],"suffer":[104],"from":[105],"hyper-sensitivity":[106],"over-prediction,":[108],"whereas":[109],"minority":[110],"exhibit":[112],"sharp":[113],"decay,":[115],"culminating":[116],"total":[119],"boundary":[121],"collapse":[122],"for":[123,180],"EC6":[124],"(Recall":[125],"0.00%)":[127],"despite":[128],"underlying":[129],"discriminative":[130],"power":[131],"(ROC-AUC":[132],"0.5857).":[134],"Feature":[135],"correlation":[136],"analysis":[137],"further":[138],"reveals":[139],"linear":[141],"redundancy":[142],"among":[143],"topological":[144],"indices":[145],"relative":[146],"to":[147],"fingerprint":[148],"density":[149],"metrics.":[150],"Ultimately,":[151],"study":[154],"demonstrates":[155],"that":[156],"point":[158],"predictions":[159],"mask":[160],"critical":[161],"errors":[162],"bioinformatics":[164],"workflows.":[165],"We":[166],"establish":[167],"target-specific":[168],"threshold":[169],"optimization":[170],"post-hoc":[172],"conformal":[173],"calibration":[174],"as":[175],"essential,":[176],"open-source":[177],"post-processing":[178],"safeguards":[179],"reliable":[181],"applied":[182],"deep":[186],"architectures.":[188]},"counts_by_year":[],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2026-09-10T00:00:00"}