{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,8]],"date-time":"2026-09-08T14:06:54Z","timestamp":1788876414709,"version":"build-2803163510"},"reference-count":51,"publisher":"American Chemical Society (ACS)","issue":"35","license":[{"start":{"date-parts":[[2026,8,27]],"date-time":"2026-08-27T00:00:00Z","timestamp":1787788800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["21938004"],"award-info":[{"award-number":["21938004"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["22078172"],"award-info":[{"award-number":["22078172"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004147","name":"Tsinghua University","doi-asserted-by":"publisher","award":["20223080016"],"award-info":[{"award-number":["20223080016"]}],"id":[{"id":"10.13039\/501100004147","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","award":["2021YFC2100900"],"award-info":[{"award-number":["2021YFC2100900"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026,9,8]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>Promiscuous enzymes catalyze multiple biochemical reactions, but predicting their substrate profiles remains challenging because annotations are incomplete, reliable negative labels are scarce, and enzyme\u2013substrate relationships are inherently multilabel. Here, we present PreSEPM (Predictive Substrate Explorer for Promiscuous Enzymes), a sequence-only, closed-set framework that combines pretrained protein representations, Gaussian mixture modeling, cluster\u2013substrate alignment, and Bayesian optimization of decision thresholds. PreSEPM operates within a predefined substrate panel and does not require explicit substrate or structural descriptors. On a UniProt-derived triacylglycerol lipase data set, PreSEPM achieved an AUROC of 0.86, an AUPRC of 0.73, and a maximum F1 score of 0.71, outperforming the evaluated conventional machine learning baselines. On an independent high-throughput lipase screen, PreSEPM also outperformed a strong single-task logistic-regression baseline under enzyme-wise cross-validation, increasing Macro-AUPRC from 0.65 to 0.68 and F1 max from 0.63 to 0.69. Under the cross-data set setting, SMOTE-based augmentation increased AUPRC from 0.62 to 0.70. These results support PreSEPM as a useful sequence-based baseline for substrate profile completion and experimental prioritization within promiscuous enzyme families when annotations are sparse and structural or ligand-level information is unavailable.<\/jats:p>","DOI":"10.1021\/acsomega.5c11697","type":"journal-article","created":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T16:04:55Z","timestamp":1788278695000},"page":"52427-52438","source":"Crossref","is-referenced-by-count":0,"title":["A Novel Unsupervised\nLearning Model with Bayesian\nHyperparameter Optimization for Predicting Substrates of Promiscuous\nEnzymes"],"prefix":"10.1021","volume":"11","author":[{"given":"Rongsheng","family":"Gao","sequence":"first","affiliation":[{"name":"Tsinghua University , , ,","place":["Beijing, China, 100084"]},{"name":"State Key Laboratory of Green Biomanufacturing , ,","place":["Beijing, China, 100084"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-2615-9817","authenticated-orcid":true,"given":"Chengye","family":"Duan","sequence":"additional","affiliation":[{"name":"Tsinghua University , , ,","place":["Beijing, China, 100084"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-5948-1493","authenticated-orcid":true,"given":"Nan","family":"Qin","sequence":"additional","affiliation":[{"name":"Tsinghua University , , ,","place":["Beijing, China, 100084"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Youmeng","family":"Liu","sequence":"additional","affiliation":[{"name":"Tsinghua University , , ,","place":["Beijing, China, 100084"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kunyu","family":"Liu","sequence":"additional","affiliation":[{"name":"Tsinghua University , , ,","place":["Beijing, China, 100084"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tatsuhisa","family":"Tsuboi","sequence":"additional","affiliation":[{"name":"Tsinghua Shenzhen International Graduate School , , ,","place":["Shenzhen, China, 518055"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3792-5544","authenticated-orcid":true,"given":"Zhen","family":"Chen","sequence":"additional","affiliation":[{"name":"Tsinghua University , , ,","place":["Beijing, China, 100084"]},{"name":"State Key Laboratory of Green Biomanufacturing , ,","place":["Beijing, China, 100084"]},{"name":"Tsinghua University , , ,","place":["Beijing, China, 100084"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"316","published-online":{"date-parts":[[2026,8,27]]},"reference":[{"issue":"5","key":"2026090809093616200_cit1","doi-asserted-by":"publisher","first-page":"400","DOI":"10.2174\/0929866527666191223141205","article-title":"Enzyme promiscuous activity: How to define it and its\nevolutionary aspects","volume":"27","author":"De Luca","year":"2020","journal-title":"Protein Pept. Lett."},{"issue":"8","key":"2026090809093616200_cit2","doi-asserted-by":"publisher","first-page":"1458","DOI":"10.1016\/j.biotechadv.2013.07.005","article-title":"Perspectives\nand industrial potential of PGA selectivity and promiscuity","volume":"31","author":"Grulich","year":"2013","journal-title":"Biotechnol. Adv."},{"issue":"11","key":"2026090809093616200_cit3","doi-asserted-by":"publisher","first-page":"4504","DOI":"10.1039\/c003811c","article-title":"Hydrolases: catalytically\npromiscuous enzymes for non-conventional reactions in organic synthesis","volume":"39","author":"Busto","year":"2010","journal-title":"Chem. Soc. Rev."},{"issue":"4","key":"2026090809093616200_cit4","doi-asserted-by":"publisher","first-page":"555","DOI":"10.1016\/j.procbio.2012.01.011","article-title":"Lipase promiscuity\nand its biochemical applications","volume":"47","author":"Kapoor","year":"2012","journal-title":"Process Biochem."},{"issue":"7","key":"2026090809093616200_cit5","doi-asserted-by":"publisher","first-page":"1306","DOI":"10.1111\/febs.15116","article-title":"Mechanisms\nof promiscuity among drug metabolizing enzymes and drug transporters","volume":"287","author":"Atkins","year":"2020","journal-title":"FEBS J."},{"issue":"5","key":"2026090809093616200_cit6","doi-asserted-by":"publisher","first-page":"374","DOI":"10.2174\/138920008784746337","article-title":"The challenges of\ndealing with promiscuous drug-metabolizing enzymes,\nreceptors and transporters","volume":"9","author":"Ma","year":"2008","journal-title":"Curr. Drug Metab."},{"issue":"2","key":"2026090809093616200_cit7","doi-asserted-by":"publisher","first-page":"200","DOI":"10.1016\/j.cbpa.2009.11.028","article-title":"What makes an enzyme promiscuous?","volume":"14","author":"Babtie","year":"2010","journal-title":"Curr. Opin. Chem. Biol."},{"issue":"21","key":"2026090809093616200_cit8","doi-asserted-by":"publisher","first-page":"6887","DOI":"10.1007\/s00253-022-12198-1","article-title":"Insights into promiscuous\nchitosanases: The known and the unknown","volume":"106","author":"Su","year":"2022","journal-title":"Appl.\nMicrobiol. Biotechnol."},{"issue":"10","key":"2026090809093616200_cit9","doi-asserted-by":"publisher","first-page":"1095","DOI":"10.3390\/catal12101095","article-title":"Not a mistake\nbut a feature: Promiscuous activity of\nenzymes meeting mycotoxins","volume":"12","author":"Lyagin","year":"2022","journal-title":"Catalysts"},{"issue":"12","key":"2026090809093616200_cit10","doi-asserted-by":"publisher","first-page":"105421","DOI":"10.1016\/j.jbc.2023.105421","article-title":"Structural and functional\nstudies reveal the molecular basis of substrate promiscuity of a glycosyltransferase\noriginating from a major agricultural pest","volume":"299","author":"Arriaza","year":"2023","journal-title":"J. Biol. Chem."},{"key":"2026090809093616200_cit11","doi-asserted-by":"publisher","first-page":"50","DOI":"10.1016\/j.biochi.2020.05.004","article-title":"Protein\npromiscuity in drug discovery,\ndrug-repurposing and antibiotic resistance","volume":"175","author":"Gupta","year":"2020","journal-title":"Biochimie"},{"issue":"7","key":"2026090809093616200_cit12","doi-asserted-by":"publisher","first-page":"1343","DOI":"10.1111\/febs.15284","article-title":"Enzyme promiscuity, metabolite damage, and metabolite\ndamage control systems of the tricarboxylic acid cycle","volume":"287","author":"Niehaus","year":"2020","journal-title":"FEBS J."},{"issue":"5","key":"2026090809093616200_cit13","doi-asserted-by":"publisher","first-page":"1175","DOI":"10.1042\/BCJ20200988","article-title":"Promiscuous\nenzymes generating d-amino acids in mammals:\nWhy they may still surprise us?","volume":"478","author":"Wolosker","year":"2021","journal-title":"Biochem. J."},{"issue":"5","key":"2026090809093616200_cit14","doi-asserted-by":"publisher","first-page":"231","DOI":"10.1016\/j.tibtech.2007.03.002","article-title":"Enzyme promiscuity: mechanism and applications","volume":"25","author":"Hult","year":"2007","journal-title":"Trends In Biotechnol."},{"issue":"5","key":"2026090809093616200_cit15","doi-asserted-by":"publisher","first-page":"498","DOI":"10.1016\/j.cbpa.2006.08.011","article-title":"Enzyme promiscuity: evolutionary\nand mechanistic aspects","volume":"10","author":"Khersonsky","year":"2006","journal-title":"Curr. Opin. Chem. Biol."},{"key":"2026090809093616200_cit16","doi-asserted-by":"publisher","first-page":"gzab013","DOI":"10.1093\/protein\/gzab013","article-title":"Evolution\nof \u03b2-lactamases and enzyme promiscuity","volume":"34","author":"Fro\u0308hlich","year":"2021","journal-title":"Protein Eng., Des. Sel."},{"issue":"15","key":"2026090809093616200_cit17","doi-asserted-by":"publisher","DOI":"10.1002\/anie.202422109","article-title":"Promiscuity Guided\nEvolution of Decarboxylative Aldolases for Synthesis of Tertiary \u03b3-Hydroxy\nAmino Acids","volume":"64","author":"Campbell","year":"2025","journal-title":"Angew. Chem. Int. Ed."},{"issue":"16","key":"2026090809093616200_cit18","doi-asserted-by":"publisher","first-page":"8202","DOI":"10.1039\/D4CS00196F","article-title":"Navigating the landscape of enzyme\ndesign: from molecular simulations\nto machine learning","volume":"53","author":"Zhou","year":"2024","journal-title":"Chem. Soc. Rev."},{"key":"2026090809093616200_cit19","doi-asserted-by":"publisher","first-page":"281","DOI":"10.1016\/bs.mie.2020.05.005","article-title":"Machine learning-assisted enzyme\nengineering","volume":"643","author":"Siedhoff","year":"2020","journal-title":"Methods Enzymol."},{"key":"2026090809093616200_cit20","doi-asserted-by":"publisher","first-page":"30","DOI":"10.5121\/mlaij.2015.2404","article-title":"Classification of\nenzymes using machine learning based\napproaches: A review","volume":"2","author":"Yadav","year":"2015","journal-title":"Mach. Learn. Appl."},{"issue":"15","key":"2026090809093616200_cit21","doi-asserted-by":"publisher","first-page":"2455","DOI":"10.1039\/D1CC04635G","article-title":"High-throughput screening, next generation sequencing\nand machine learning: advanced methods in enzyme engineering","volume":"58","author":"Vanella","year":"2022","journal-title":"Chem. Commun."},{"issue":"28","key":"2026090809093616200_cit22","doi-asserted-by":"publisher","first-page":"13996","DOI":"10.1073\/pnas.1821905116","article-title":"Deep learning enables high-quality\nand high-throughput prediction of enzyme commission numbers","volume":"116","author":"Ryu","year":"2019","journal-title":"Proc. Natl. Acad. Sci. U. S. A."},{"issue":"1","key":"2026090809093616200_cit23","doi-asserted-by":"publisher","first-page":"100372","DOI":"10.1016\/j.crmeth.2022.100372","article-title":"Embracing enzyme\npromiscuity with activity-based compressed\nbiosensing","volume":"3","author":"Holt","year":"2023","journal-title":"Cell Rep. Methods"},{"key":"2026090809093616200_cit24","doi-asserted-by":"publisher","DOI":"10.26434\/chemrxiv-2023-913g7-v2","article-title":"Exploration\nof bioinformatic\ndomain based on data mining, reaction and enzyme promiscuity predictions","author":"Zhang","year":"2024","journal-title":"Chemrxiv"},{"issue":"7","key":"2026090809093616200_cit25","doi-asserted-by":"publisher","first-page":"1323","DOI":"10.1111\/febs.15185","article-title":"How enzyme promiscuity and horizontal\ngene transfer contribute to metabolic innovation","volume":"287","author":"Glasner","year":"2020","journal-title":"FEBS J."},{"issue":"5","key":"2026090809093616200_cit26","doi-asserted-by":"publisher","first-page":"868","DOI":"10.13345\/j.cjb.190370","article-title":"Recent progress in 2-haloacid dehalogenases","volume":"36","author":"Wang","year":"2020","journal-title":"Chin. J. Biotechnol."},{"issue":"10","key":"2026090809093616200_cit27","doi-asserted-by":"publisher","first-page":"1529","DOI":"10.3390\/biom12101529","article-title":"EP-Pred: a machine learning tool for bioprospecting\npromiscuous ester hydrolases","volume":"12","author":"Xiang","year":"2022","journal-title":"Biomolecules"},{"key":"2026090809093616200_cit28","doi-asserted-by":"publisher","DOI":"10.7717\/peerj.3095","article-title":"Automatic\nsingle-and multi-label enzymatic function prediction by machine learning","volume":"5","author":"Amidi","year":"2017","journal-title":"PeerJ"},{"issue":"1","key":"2026090809093616200_cit29","doi-asserted-by":"publisher","first-page":"225","DOI":"10.1021\/acschembio.7b00996","article-title":"Determinants and prediction\nof esterase substrate promiscuity patterns","volume":"13","author":"Marti\u0301nez-Marti\u0301nez","year":"2018","journal-title":"ACS Chem. Biol."},{"issue":"2","key":"2026090809093616200_cit30","doi-asserted-by":"publisher","first-page":"bbae089","DOI":"10.1093\/bib\/bbae089","article-title":"High-throughput\nprediction of enzyme\npromiscuity based on substrate\u2013product pairs","volume":"25","author":"Xing","year":"2024","journal-title":"Briefings Bioinf."},{"issue":"6639","key":"2026090809093616200_cit31","doi-asserted-by":"publisher","first-page":"1358","DOI":"10.1126\/science.adf2465","article-title":"Enzyme function\nprediction using contrastive learning","volume":"379","author":"Yu","year":"2023","journal-title":"Science"},{"issue":"8090","key":"2026090809093616200_cit32","doi-asserted-by":"publisher","first-page":"639","DOI":"10.1038\/s41586-025-09697-2","article-title":"Enzyme specificity prediction using\ncross-attention graph neural networks","volume":"647","author":"Cui","year":"2025","journal-title":"Nature"},{"issue":"1","key":"2026090809093616200_cit33","doi-asserted-by":"publisher","first-page":"2787","DOI":"10.1038\/s41467-023-38347-2","article-title":"A general model\nto predict small molecule substrates of enzymes based on machine and\ndeep learning","volume":"14","author":"Kroll","year":"2023","journal-title":"Nat. Commun."},{"key":"2026090809093616200_cit34","unstructured":"Ni, Z.\n          \n          Data-driven\napproaches\nto predict and utilize enzyme promiscuity for novel biosynthesis design., Dissertations & Theses; Northwestern University,\nProQuest, 2022."},{"issue":"5","key":"2026090809093616200_cit35","doi-asserted-by":"publisher","first-page":"3336","DOI":"10.1021\/acscatal.3c04461","article-title":"Discovery of toxin-degrading enzymes with positive unlabeled deep\nlearning","volume":"14","author":"Zhang","year":"2024","journal-title":"ACS Catal."},{"issue":"8083","key":"2026090809093616200_cit36","doi-asserted-by":"publisher","first-page":"108","DOI":"10.1038\/s41586-025-09519-5","article-title":"Connecting chemical\nand protein sequence space to predict biocatalytic reactions","volume":"646","author":"Paton","year":"2025","journal-title":"Nature"},{"issue":"2","key":"2026090809093616200_cit37","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pcbi.1009853","article-title":"Machine learning modeling of family\nwide enzyme-substrate specificity screens","volume":"18","author":"Goldman","year":"2022","journal-title":"PLoS\nComput. Biol."},{"issue":"6637","key":"2026090809093616200_cit38","doi-asserted-by":"publisher","first-page":"1123","DOI":"10.1126\/science.ade2574","article-title":"Evolutionary-scale\nprediction of atomic-level protein structure with a language model","volume":"379","author":"Lin","year":"2023","journal-title":"Science"},{"issue":"8","key":"2026090809093616200_cit39","doi-asserted-by":"publisher","first-page":"2102","DOI":"10.1093\/bioinformatics\/btac020","article-title":"ProteinBERT: a universal deep-learning model of protein\nsequence and function","volume":"38","author":"Brandes","year":"2022","journal-title":"Bioinformatics"},{"issue":"17","key":"2026090809093616200_cit40","doi-asserted-by":"publisher","first-page":"2756","DOI":"10.1093\/bioinformatics\/btx302","article-title":"POSSUM: a\nbioinformatics toolkit for generating numerical sequence feature descriptors\nbased on PSSM profiles","volume":"33","author":"Wang","year":"2017","journal-title":"Bioinformatics"},{"issue":"14","key":"2026090809093616200_cit41","doi-asserted-by":"publisher","first-page":"2499","DOI":"10.1093\/bioinformatics\/bty140","article-title":"iFeature: a python package and web server for features\nextraction and selection from protein and peptide sequences","volume":"34","author":"Chen","year":"2018","journal-title":"Bioinformatics"},{"issue":"1","key":"2026090809093616200_cit42","doi-asserted-by":"publisher","first-page":"19164","DOI":"10.1038\/s41598-023-44608-3","article-title":"Avoiding inferior clusterings with\nmisspecified Gaussian mixture\nmodels","volume":"13","author":"Kasa","year":"2023","journal-title":"Sci. Rep."},{"issue":"1","key":"2026090809093616200_cit43","doi-asserted-by":"publisher","first-page":"216","DOI":"10.1186\/s12859-021-04134-3","article-title":"CarSite-II:\nan integrated\nclassification algorithm for identifying carbonylated sites based\non K-means similarity-based undersampling and synthetic minority oversampling\ntechniques","volume":"22","author":"Zuo","year":"2021","journal-title":"BMC Bioinf."},{"key":"2026090809093616200_cit44","doi-asserted-by":"publisher","first-page":"1305543","DOI":"10.3389\/fneur.2024.1305543","article-title":"Synthetic\nminority over-sampling technique-enhanced machine learning models\nfor predicting recurrence of postoperative chronic subdural hematoma","volume":"15","author":"Ni","year":"2024","journal-title":"Front. Neurol."},{"issue":"8","key":"2026090809093616200_cit45","doi-asserted-by":"publisher","first-page":"4098","DOI":"10.1021\/acs.jcim.0c00489","article-title":"Improving\nenzyme optimum temperature\nprediction with resampling strategies and ensemble learning","volume":"60","author":"Gado","year":"2020","journal-title":"J. Chem. Inf. Model."},{"issue":"6","key":"2026090809093616200_cit46","doi-asserted-by":"publisher","first-page":"2806","DOI":"10.1021\/acs.jcim.4c02357","article-title":"FusionESP: Improved\nEnzyme\u2013Substrate Pair Prediction by Fusing Protein and Chemical\nKnowledge","volume":"65","author":"Du","year":"2025","journal-title":"J. Chem. Inf. Model."},{"issue":"2","key":"2026090809093616200_cit47","doi-asserted-by":"publisher","first-page":"220","DOI":"10.1038\/s42256-024-00795-w","article-title":"Protein function\nprediction as approximate semantic entailment","volume":"6","author":"Kulmanov","year":"2024","journal-title":"Nat. Mach. Intell."},{"issue":"3","key":"2026090809093616200_cit48","doi-asserted-by":"publisher","first-page":"btad094","DOI":"10.1093\/bioinformatics\/btad094","article-title":"PFresGO: an\nattention mechanism-based deep-learning approach for protein annotation\nby integrating gene ontology inter-relationships","volume":"39","author":"Pan","year":"2023","journal-title":"Bioinformatics"},{"key":"2026090809093616200_cit49","first-page":"3094","article-title":"Care: A benchmark\nsuite for the classification and\nretrieval of enzymes","volume-title":"Advances in Neural Information\nProcessing Systems.","author":"Yang","year":"2024"},{"issue":"1","key":"2026090809093616200_cit50","doi-asserted-by":"publisher","first-page":"491","DOI":"10.1074\/jbc.M508414200","article-title":"Obese yeast: triglyceride\nlipolysis is functionally\nconserved from mammals to yeast","volume":"281","author":"Kurat","year":"2006","journal-title":"J. Biol. Chem."},{"issue":"3","key":"2026090809093616200_cit51","doi-asserted-by":"publisher","first-page":"209","DOI":"10.1074\/mcp.M300082-MCP200","article-title":"Synergistic\ncomputational and experimental proteomics approaches for more accurate\ndetection of active serine hydrolases in yeast","volume":"3","author":"Baxter","year":"2004","journal-title":"Mol. Cell. Proteomics"}],"container-title":["ACS Omega"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/pubs.acs.org\/doi\/pdf\/10.1021\/acsomega.5c11697","content-type":"application\/pdf","content-version":"vor","intended-application":"unspecified"},{"URL":"https:\/\/pubs.acs.org\/acsodf\/article-pdf\/11\/35\/52427\/67467753\/acsomega.5c11697.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/pubs.acs.org\/acsodf\/article-pdf\/11\/35\/52427\/67467753\/acsomega.5c11697.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,8]],"date-time":"2026-09-08T13:09:44Z","timestamp":1788872984000},"score":1,"resource":{"primary":{"URL":"https:\/\/pubs.acs.org\/acsodf\/article\/11\/35\/52427\/5335021\/A-Novel-Unsupervised-Learning-Model-with-Bayesian"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8,27]]},"references-count":51,"journal-issue":{"issue":"35","published-online":{"date-parts":[[2026,8,27]]},"published-print":{"date-parts":[[2026,9,8]]}},"URL":"https:\/\/doi.org\/10.1021\/acsomega.5c11697","relation":{},"ISSN":["2470-1343"],"issn-type":[{"value":"2470-1343","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,8,27]]}}}