{"id":"https://openalex.org/W7225740931","doi":"https://doi.org/10.64898/2026.11.08.762986","title":"DecoyOpt: A two-stage pipeline for decoy-aware enzyme discrimination and EC number prediction","display_name":"DecoyOpt: A two-stage pipeline for decoy-aware enzyme discrimination and EC number prediction","publication_year":2026,"publication_date":"2026-11-10","ids":{"openalex":"https://openalex.org/W7225740931","doi":"https://doi.org/10.64898/2026.11.08.762986"},"language":"en","primary_location":{"id":"doi:10.64898/2026.11.08.762986","doi":"https://doi.org/10.64898/2026.11.08.762986","is_oa":true,"landing_page_url":"https://doi.org/10.64898/2026.11.08.762986","pdf_url":null,"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-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","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://doi.org/10.64898/2026.11.08.762986","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5086454174","display_name":"Tiantao Liu","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I49835588","display_name":"Macao Polytechnic University","ror":"https://ror.org/02sf5td35","country_code":"MO","type":"education","lineage":["https://openalex.org/I49835588"]}],"countries":["MO"],"is_corresponding":false,"raw_author_name":"Tiantao Liu","raw_affiliation_strings":["Faculty of Applied Sciences, Macao Polytechnic University, 999078, Macau SAR, China;"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Faculty of Applied Sciences, Macao Polytechnic University, 999078, Macau SAR, China;","institution_ids":["https://openalex.org/I49835588"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5161411494","display_name":"Junwen Deng","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I49835588","display_name":"Macao Polytechnic University","ror":"https://ror.org/02sf5td35","country_code":"MO","type":"education","lineage":["https://openalex.org/I49835588"]}],"countries":["MO"],"is_corresponding":false,"raw_author_name":"Junwen Deng","raw_affiliation_strings":["Faculty of Applied Sciences, Macao Polytechnic University, 999078, Macau SAR, China;"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Faculty of Applied Sciences, Macao Polytechnic University, 999078, Macau SAR, China;","institution_ids":["https://openalex.org/I49835588"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069640764","display_name":"Xiaodan Wang","orcid":"https://orcid.org/0000-0001-8553-309X","observed_orcids":["https://orcid.org/0000-0001-8553-309X"]},"institutions":[{"id":"https://openalex.org/I49835588","display_name":"Macao Polytechnic University","ror":"https://ror.org/02sf5td35","country_code":"MO","type":"education","lineage":["https://openalex.org/I49835588"]}],"countries":["MO"],"is_corresponding":false,"raw_author_name":"Xiaodan Wang","raw_affiliation_strings":["Faculty of Applied Sciences, Macao Polytechnic University, 999078, Macau SAR, China;"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Faculty of Applied Sciences, Macao Polytechnic University, 999078, Macau SAR, China;","institution_ids":["https://openalex.org/I49835588"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018337985","display_name":"Kepeng Chen","orcid":"https://orcid.org/0000-0002-2225-8112","observed_orcids":["https://orcid.org/0000-0002-2225-8112"]},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kepeng Chen","raw_affiliation_strings":["College of Pharmaceutical Sciences, Zhejiang University, Hangzhou 310058, Zhejiang, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Pharmaceutical Sciences, Zhejiang University, Hangzhou 310058, Zhejiang, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5126097543","display_name":"Dutao Zhang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I49835588","display_name":"Macao Polytechnic University","ror":"https://ror.org/02sf5td35","country_code":"MO","type":"education","lineage":["https://openalex.org/I49835588"]}],"countries":["MO"],"is_corresponding":false,"raw_author_name":"Dutao Zhang","raw_affiliation_strings":["Faculty of Applied Sciences, Macao Polytechnic University, 999078, Macau SAR, China;"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Faculty of Applied Sciences, Macao Polytechnic University, 999078, Macau SAR, China;","institution_ids":["https://openalex.org/I49835588"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5102848446","display_name":"Shirley W. I. Siu","orcid":"https://orcid.org/0000-0002-3695-7758","observed_orcids":["https://orcid.org/0000-0002-3695-7758"]},"institutions":[{"id":"https://openalex.org/I49835588","display_name":"Macao Polytechnic University","ror":"https://ror.org/02sf5td35","country_code":"MO","type":"education","lineage":["https://openalex.org/I49835588"]}],"countries":["MO"],"is_corresponding":false,"raw_author_name":"Shirley Weng In Siu","raw_affiliation_strings":["Faculty of Applied Sciences, Macao Polytechnic University, 999078, Macau SAR, China;"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Faculty of Applied Sciences, Macao Polytechnic University, 999078, Macau SAR, China;","institution_ids":["https://openalex.org/I49835588"]}]}],"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":false,"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":0.9922000169754028,"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":0.9922000169754028,"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":0.003000000026077032,"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":0.0007999999797903001,"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":[],"concepts":[{"id":"https://openalex.org/C2779179475","wikidata":"https://www.wikidata.org/wiki/Q3545649","display_name":"Decoy","level":3,"score":0.8691999912261963},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.7638999819755554},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6169999837875366},{"id":"https://openalex.org/C189430467","wikidata":"https://www.wikidata.org/wiki/Q7293293","display_name":"Ranking (information retrieval)","level":2,"score":0.5842999815940857},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5594000220298767},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.49950000643730164},{"id":"https://openalex.org/C181199279","wikidata":"https://www.wikidata.org/wiki/Q8047","display_name":"Enzyme","level":2,"score":0.462799996137619},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4300000071525574},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4203999936580658},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.40880000591278076},{"id":"https://openalex.org/C169903167","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Test set","level":2,"score":0.4020000100135803},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.3375000059604645},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.3203999996185303},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3100999891757965},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.3082999885082245}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.64898/2026.11.08.762986","doi":"https://doi.org/10.64898/2026.11.08.762986","is_oa":true,"landing_page_url":"https://doi.org/10.64898/2026.11.08.762986","pdf_url":null,"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-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"bioRxiv","raw_type":"posted-content"}],"best_oa_location":{"id":"doi:10.64898/2026.11.08.762986","doi":"https://doi.org/10.64898/2026.11.08.762986","is_oa":true,"landing_page_url":"https://doi.org/10.64898/2026.11.08.762986","pdf_url":null,"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-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","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":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Accurate":[0],"and":[1,17,57,70,84,92,118,162,181,190],"efficient":[2],"EC":[3,58,100,136],"number":[4,59,137],"prediction":[5,138],"is":[6],"essential":[7],"for":[8,53,177],"elucidating":[9],"the":[10,106,140,151],"catalytic":[11],"roles":[12],"of":[13,116,123],"enzymes.":[14,104],"Although":[15],"similarity-based":[16],"deep":[18],"learning-based":[19],"approaches":[20],"have":[21],"advanced":[22],"this":[23],"task,":[24],"they":[25],"often":[26],"fail":[27],"to":[28,42,102,148],"distinguish":[29],"active":[30],"enzymes":[31,88,161],"from":[32,89],"closely":[33],"related":[34],"decoys":[35,67,93],"inactivated":[36],"by":[37],"local":[38],"functional-site":[39,66],"mutations,":[40],"leading":[41],"high":[43],"false-positive":[44],"rates":[45],"(FPRs).":[46],"We":[47,171],"propose":[48],"DecoyOpt,":[49],"a":[50,95,119],"two-stage":[51],"pipeline":[52],"decoy-aware":[54],"enzyme":[55,152],"discrimination":[56],"prediction.":[60],"Specifically,":[61],"we":[62],"generated":[63],"putatively":[64],"inactive":[65,166,169],"using":[68],"ESM3":[69],"evaluated":[71],"16":[72],"protein":[73],"language":[74],"models":[75],"across":[76],"three":[77],"splits.":[78],"An":[79],"MLP":[80],"trained":[81],"with":[82,184],"classification":[83],"ranking":[85],"losses":[86],"distinguishes":[87],"unannotated":[90],"proteins":[91,180],"before":[94],"contrastive":[96],"learning":[97],"model":[98],"assigns":[99],"numbers":[101],"predicted":[103],"On":[105],"most":[107],"stringent":[108],"GraphPart":[109],"40%":[110],"split,":[111],"DecoyOpt":[112,174],"achieves":[113],"an":[114],"MCC":[115],"0.899":[117],"D0":[120],"decoy":[121],"FPR":[122],"6.17%,":[124],"outperforming":[125],"retrained":[126],"baselines.":[127],"Across":[128],"all":[129,158,164],"splits,":[130],"it":[131],"outperforms":[132],"these":[133],"baselines":[134],"in":[135,186],"on":[139,150],"full":[141],"test":[142],"set":[143],"while":[144],"maintaining":[145],"performance":[146],"close":[147],"CLEAN":[149],"subset.":[153],"It":[154],"also":[155],"correctly":[156],"annotates":[157],"four":[159],"wild-type":[160],"rejects":[163],"eight":[165],"or":[167],"nearly":[168],"variants.":[170],"believe":[172],"that":[173],"has":[175],"potential":[176],"annotating":[178],"uncharacterized":[179],"their":[182],"variants,":[183],"applications":[185],"genomics,":[187],"synthetic":[188],"biology,":[189],"biocatalysis.":[191]},"counts_by_year":[],"updated_date":"2026-11-11T12:16:26.678958","created_date":"2026-11-11T00:00:00"}
