{"id":"https://openalex.org/W7128437968","doi":"https://doi.org/10.1186/s13321-026-01164-y","title":"Enzyformer: a two-stage pretrained model for enzymatic retrosynthesis","display_name":"Enzyformer: a two-stage pretrained model for enzymatic retrosynthesis","publication_year":2026,"publication_date":"2026-02-09","ids":{"openalex":"https://openalex.org/W7128437968","doi":"https://doi.org/10.1186/s13321-026-01164-y","pmid":"https://pubmed.ncbi.nlm.nih.gov/41664113"},"language":"en","primary_location":{"id":"doi:10.1186/s13321-026-01164-y","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13321-026-01164-y","pdf_url":null,"source":{"id":"https://openalex.org/S180838163","display_name":"Journal of Cheminformatics","issn_l":"1758-2946","issn":["1758-2946"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320256","host_organization_name":"BioMed Central","host_organization_lineage":["https://openalex.org/P4310320256","https://openalex.org/P4310319965"],"host_organization_lineage_names":["BioMed Central","Springer Nature"],"type":"journal"},"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":"Journal of Cheminformatics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1186/s13321-026-01164-y","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Tiantao Liu","orcid":null},"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, Macau SAR, 999078, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Faculty of Applied Sciences, Macao Polytechnic University, Macau SAR, 999078, China","institution_ids":["https://openalex.org/I49835588"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5125468504","display_name":"Jiangcheng Xu","orcid":null},"institutions":[{"id":"https://openalex.org/I4210125098","display_name":"Hangzhou Vocational and Technical College","ror":"https://ror.org/03jjm4b17","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210125098"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiangcheng Xu","raw_affiliation_strings":["Hangzhou Vocational and Technical College, Hangzhou, 310014, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hangzhou Vocational and Technical College, Hangzhou, 310014, China","institution_ids":["https://openalex.org/I4210125098"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5022540460","display_name":"Xinke Zhan","orcid":"https://orcid.org/0000-0002-1235-3220"},"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":"Xinke Zhan","raw_affiliation_strings":["Faculty of Applied Sciences, Macao Polytechnic University, Macau SAR, 999078, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Faculty of Applied Sciences, Macao Polytechnic University, Macau SAR, 999078, China","institution_ids":["https://openalex.org/I49835588"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5125455419","display_name":"Shaolong Lin","orcid":null},"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":"Shaolong Lin","raw_affiliation_strings":["Faculty of Applied Sciences, Macao Polytechnic University, Macau SAR, 999078, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Faculty of Applied Sciences, Macao Polytechnic University, Macau SAR, 999078, China","institution_ids":["https://openalex.org/I49835588"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5125446170","display_name":"Shirley W. I. Siu","orcid":null},"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":true,"raw_author_name":"Shirley W. I. Siu","raw_affiliation_strings":["Faculty of Applied Sciences, Macao Polytechnic University, Macau SAR, 999078, China. shirleysiu@mpu.edu.mo"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Faculty of Applied Sciences, Macao Polytechnic University, Macau SAR, 999078, China. shirleysiu@mpu.edu.mo","institution_ids":["https://openalex.org/I49835588"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5125446170"],"corresponding_institution_ids":["https://openalex.org/I49835588"],"apc_list":{"value":2190,"currency":"USD","value_usd":2190},"apc_paid":{"value":2190,"currency":"USD","value_usd":2190},"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.12452453,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"18","issue":"1","first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10404","display_name":"Enzyme Catalysis and Immobilization","score":0.20800000429153442,"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/T10404","display_name":"Enzyme Catalysis and Immobilization","score":0.20800000429153442,"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/T11948","display_name":"Machine Learning in Materials Science","score":0.18330000340938568,"subfield":{"id":"https://openalex.org/subfields/2505","display_name":"Materials Chemistry"},"field":{"id":"https://openalex.org/fields/25","display_name":"Materials Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10252","display_name":"Microbial Natural Products and Biosynthesis","score":0.12110000103712082,"subfield":{"id":"https://openalex.org/subfields/2736","display_name":"Pharmacology"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/retrosynthetic-analysis","display_name":"Retrosynthetic analysis","score":0.9639999866485596},{"id":"https://openalex.org/keywords/interpretability","display_name":"Interpretability","score":0.8454999923706055},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.560699999332428},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.5325999855995178},{"id":"https://openalex.org/keywords/workload","display_name":"Workload","score":0.44909998774528503},{"id":"https://openalex.org/keywords/drug-discovery","display_name":"Drug discovery","score":0.3587000072002411},{"id":"https://openalex.org/keywords/chemical-space","display_name":"Chemical space","score":0.33469998836517334}],"concepts":[{"id":"https://openalex.org/C42437451","wikidata":"https://www.wikidata.org/wiki/Q902227","display_name":"Retrosynthetic analysis","level":3,"score":0.9639999866485596},{"id":"https://openalex.org/C2781067378","wikidata":"https://www.wikidata.org/wiki/Q17027399","display_name":"Interpretability","level":2,"score":0.8454999923706055},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7089999914169312},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6071000099182129},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.560699999332428},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.5325999855995178},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5130000114440918},{"id":"https://openalex.org/C2778476105","wikidata":"https://www.wikidata.org/wiki/Q628539","display_name":"Workload","level":2,"score":0.44909998774528503},{"id":"https://openalex.org/C74187038","wikidata":"https://www.wikidata.org/wiki/Q1418791","display_name":"Drug discovery","level":2,"score":0.3587000072002411},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.33570000529289246},{"id":"https://openalex.org/C99726746","wikidata":"https://www.wikidata.org/wiki/Q906396","display_name":"Chemical space","level":3,"score":0.33469998836517334},{"id":"https://openalex.org/C68762167","wikidata":"https://www.wikidata.org/wiki/Q910164","display_name":"Cheminformatics","level":2,"score":0.334199994802475},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.32839998602867126},{"id":"https://openalex.org/C60048249","wikidata":"https://www.wikidata.org/wiki/Q37437","display_name":"Syntax","level":2,"score":0.32710000872612},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.29910001158714294},{"id":"https://openalex.org/C58328972","wikidata":"https://www.wikidata.org/wiki/Q184609","display_name":"Expert system","level":2,"score":0.29820001125335693},{"id":"https://openalex.org/C170858558","wikidata":"https://www.wikidata.org/wiki/Q1394144","display_name":"Automatic summarization","level":2,"score":0.2797999978065491},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.27570000290870667},{"id":"https://openalex.org/C2989108626","wikidata":"https://www.wikidata.org/wiki/Q904407","display_name":"Drug target","level":2,"score":0.2651999890804291},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.2639999985694885}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1186/s13321-026-01164-y","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13321-026-01164-y","pdf_url":null,"source":{"id":"https://openalex.org/S180838163","display_name":"Journal of Cheminformatics","issn_l":"1758-2946","issn":["1758-2946"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320256","host_organization_name":"BioMed Central","host_organization_lineage":["https://openalex.org/P4310320256","https://openalex.org/P4310319965"],"host_organization_lineage_names":["BioMed Central","Springer Nature"],"type":"journal"},"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":"Journal of Cheminformatics","raw_type":"journal-article"},{"id":"pmid:41664113","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/41664113","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of cheminformatics","raw_type":null},{"id":"pmh:oai:doaj.org/article:6408816ccebb4f2fae3e88dd12b0a33b","is_oa":true,"landing_page_url":"https://doaj.org/article/6408816ccebb4f2fae3e88dd12b0a33b","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Journal of Cheminformatics, Vol 18, Iss 1 (2026)","raw_type":"article"},{"id":"pmh:oai:pubmedcentral.nih.gov:12983858","is_oa":true,"landing_page_url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC12983858/","pdf_url":null,"source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"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":"J Cheminform","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.1186/s13321-026-01164-y","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13321-026-01164-y","pdf_url":null,"source":{"id":"https://openalex.org/S180838163","display_name":"Journal of Cheminformatics","issn_l":"1758-2946","issn":["1758-2946"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320256","host_organization_name":"BioMed Central","host_organization_lineage":["https://openalex.org/P4310320256","https://openalex.org/P4310319965"],"host_organization_lineage_names":["BioMed Central","Springer Nature"],"type":"journal"},"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":"Journal of Cheminformatics","raw_type":"journal-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/12","score":0.45548999309539795,"display_name":"Responsible consumption and production"}],"awards":[{"id":"https://openalex.org/G2845012449","display_name":null,"funder_award_id":"Y202456962","funder_id":"https://openalex.org/F4320325436","funder_display_name":"Department of Education of Zhejiang Province"}],"funders":[{"id":"https://openalex.org/F4320325436","display_name":"Department of Education of Zhejiang Province","ror":"https://ror.org/05gj07w56"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":49,"referenced_works":["https://openalex.org/W1757990252","https://openalex.org/W1985796525","https://openalex.org/W1988301066","https://openalex.org/W1992605830","https://openalex.org/W2010754031","https://openalex.org/W2018629291","https://openalex.org/W2022144691","https://openalex.org/W2040010296","https://openalex.org/W2053716538","https://openalex.org/W2099715980","https://openalex.org/W2114704115","https://openalex.org/W2160592148","https://openalex.org/W2324964582","https://openalex.org/W2580919858","https://openalex.org/W2621742623","https://openalex.org/W2799620402","https://openalex.org/W2919115771","https://openalex.org/W2947423323","https://openalex.org/W2950210985","https://openalex.org/W2978017171","https://openalex.org/W2987091515","https://openalex.org/W3008588639","https://openalex.org/W3034999214","https://openalex.org/W3088265803","https://openalex.org/W3088602465","https://openalex.org/W3120686965","https://openalex.org/W3123504295","https://openalex.org/W3123901912","https://openalex.org/W3189262114","https://openalex.org/W3189576964","https://openalex.org/W4213314063","https://openalex.org/W4226145240","https://openalex.org/W4226159083","https://openalex.org/W4229040393","https://openalex.org/W4286901673","https://openalex.org/W4292805535","https://openalex.org/W4360601951","https://openalex.org/W4362471278","https://openalex.org/W4386068004","https://openalex.org/W4387814399","https://openalex.org/W4388764403","https://openalex.org/W4388940266","https://openalex.org/W4393357134","https://openalex.org/W4400943748","https://openalex.org/W4404458588","https://openalex.org/W4410003735","https://openalex.org/W4410325189","https://openalex.org/W4413810566","https://openalex.org/W4414127859"],"related_works":[],"abstract_inverted_index":{"Although":[0],"enzymatic":[1,140,172,218],"retrosynthesis":[2,72,141],"planning":[3],"is":[4],"widely":[5],"used":[6],"to":[7,46,102,146,236],"accelerate":[8,256],"drug":[9,154,162,257,266],"synthesis":[10],"and":[11,26,44,53,68,76,137,150,156,178,188,252,259],"discovery,":[12],"it":[13],"still":[14],"faces":[15],"key":[16],"challenges,":[17],"including":[18],"limited":[19],"knowledge":[20],"transfer":[21],"from":[22],"general":[23],"chemical":[24],"space":[25],"incomplete":[27],"EC":[28,90,123,224],"number":[29,91,124,225],"prediction.":[30,125],"Here,":[31],"we":[32,113],"introduce":[33],"Enzyformer,":[34,166],"an":[35,196],"innovative":[36],"model":[37,101,170,235,247],"that":[38,245],"integrates":[39],"the":[40,49,54,81,109,115,135,158,183,189,250,262],"pretraining":[41,63,176,211],"of":[42,51,57,119,139,161,185,192,209,265],"molecules":[43,177],"reactions":[45],"capture":[47],"both":[48,182],"syntax":[50,184],"SMILES":[52,186],"transformation":[55,190],"rules":[56],"organic":[58,193],"reactions.":[59],"With":[60,108],"this":[61,246],"two-stage":[62,168],"strategy,":[64],"Enzyformer":[65,128,180],"improves":[66],"top-1":[67],"top-10":[69,200],"accuracies":[70],"in":[71,199],"prediction":[73,92,226],"by":[74],"7.5%":[75],"11.7%,":[77],"respectively,":[78],"compared":[79],"with":[80],"baseline":[82],"R-SMILES.":[83],"In":[84,126],"addition,":[85],"our":[86],"pipeline":[87,221],"also":[88,222],"includes":[89,223],"as":[93,227],"a":[94,98,130,167,206,228,232],"sequential":[95,229],"task,":[96,230],"using":[97,231],"contrastive":[99,110,233],"learning":[100,111,234],"improve":[103,237],"performance":[104,238],"on":[105,239],"ECREACT":[106,240],"dataset.":[107,241],"model,":[112],"achieve":[114],"highest":[116],"average":[117],"F1-score":[118],"0.924":[120],"for":[121,133,171,217,254],"first-level":[122],"conclusion,":[127],"offers":[129],"promising":[131],"solution":[132],"improving":[134],"accuracy":[136],"interpretability":[138],"prediction,":[142],"which":[143],"may":[144],"help":[145,260],"reduce":[147,249],"researchers\u2019":[148],"workload":[149,251],"cost":[151],"while":[152],"accelerating":[153],"design":[155],"mitigating":[157],"environmental":[159,263],"impact":[160,264],"synthesis.":[163,267],"We":[164,242],"present":[165],"pretrained":[169],"retrosynthesis.":[173,219],"By":[174],"jointly":[175],"reactions,":[179,194],"captures":[181],"strings":[187],"patterns":[191],"achieving":[195],"11.7%":[197],"improvement":[198],"retrosynthetic":[201],"accuracy.":[202],"This":[203],"study":[204],"provides":[205],"systematic":[207],"investigation":[208],"how":[210],"strategies":[212],"can":[213,248],"be":[214],"carefully":[215],"adapted":[216],"Our":[220],"are":[243],"confident":[244],"costs":[253],"researchers,":[255],"design,":[258],"mitigate":[261]},"counts_by_year":[],"updated_date":"2026-07-23T08:03:31.855105","created_date":"2026-02-10T00:00:00"}