{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,24]],"date-time":"2026-10-24T03:44:41Z","timestamp":1792813481076,"version":"4.5.0"},"reference-count":43,"publisher":"American Chemical Society (ACS)","issue":"40","license":[{"start":{"date-parts":[[2026,9,23]],"date-time":"2026-09-23T00:00:00Z","timestamp":1790121600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,9,23]],"date-time":"2026-09-23T00:00:00Z","timestamp":1790121600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,9,23]],"date-time":"2026-09-23T00:00:00Z","timestamp":1790121600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-045"}],"funder":[{"name":"Panzhihua Science and Technology Bureau Guiding Science and Technology Program Project","award":["No. 2024ZD-S-107"],"award-info":[{"award-number":["No. 2024ZD-S-107"]}]},{"name":"Science and Technology Project of Sichuan University?Suining City Strategic Cooperation ?Unveiling the List and Leading the Way?","award":["No. 2024CDSN-09"],"award-info":[{"award-number":["No. 2024CDSN-09"]}]},{"name":"National Key Research and Development Program","award":["No. 2018YFC1802605"],"award-info":[{"award-number":["No. 2018YFC1802605"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026,10,13]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>Selecting among hydroxyl (HO\u2022), sulfate (SO4\u2022\u2013), and carbonate (CO3\u2022\u2013) radical advanced oxidation processes requires reliable intrinsic second-order rate constants, yet the corresponding curated data sets contain 1250, 493, and 248 records, respectively. Reframing this imbalance as a cross-radical few-shot learning problem, we introduce maco, a radical-conditioned graph neural network that uses shared molecular representation learning, oxidant\/pH cross-attention, residual adapters, and a two-stage curriculum to transfer structural knowledge from the data-rich HO\u2022 task to the lower-data SO4\u2022\u2013 and CO3\u2022\u2013 tasks. On similarity-stratified held-out tests, maco achieved R2 = 0.855 (95% CI 0.711\u20130.906) for SO4\u2022\u2013 and 0.815 (0.269\u20130.944) for CO3\u2022\u2013; on the more stringent scaffold-disjoint Murcko tests, the corresponding values were 0.652 (0.447\u20130.779) and 0.715 (0.500\u20130.825). Temperature-conditioned sensitivity analyses showed no statistically discernible generalization gain under the highly asymmetric temperature coverage. Functional-group attention analysis identified radical- and pH-dependent reactive-site patterns, while applicability-domain assessment and ensemble uncertainty quantified prediction reliability for target-radical scaffold-novel contaminants. maco provides a reproducible screening input for prioritising radical\u2013contaminant measurements and process-specific evaluation. A browser-accessible WebUI further provides single-compound predictions, uncertainty estimates, and applicability-domain flags without local installation.<\/jats:p>","DOI":"10.1021\/acs.est.6c05985","type":"journal-article","created":{"date-parts":[[2026,9,23]],"date-time":"2026-09-23T08:02:21Z","timestamp":1790150541000},"page":"28829-28844","source":"Crossref","is-referenced-by-count":2,"title":["Cross-Radical Knowledge\nSharing via Graph Neural Networks\nfor Unified Prediction of Aqueous Organic Contaminant Second-Order\nRadical Reaction Rate Constants"],"prefix":"10.1021","volume":"60","author":[{"ORCID":"https:\/\/orcid.org\/0009-0006-9296-1504","authenticated-orcid":true,"given":"Zhi","family":"Huang","sequence":"first","affiliation":[{"name":"Chengdu University of Technology , , ,","place":["Chengdu, P. R. China, 610059"]},{"name":"Chengdu University of Technology , , Dongsanlu 1#, Erxianqiao , , ,","place":["Chengdu, Sichuan, P. R. China, 610059"]},{"name":"Southwest Petroleum University , , , ,","place":["Chengdu, Sichuan, P. R. China, 610500"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6049-0182","authenticated-orcid":true,"given":"Jiang","family":"Yu","sequence":"additional","affiliation":[{"name":"Sichuan University , , ,","place":["Chengdu, P. R. China, 610065"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Pengxinyue","family":"Huang","sequence":"additional","affiliation":[{"name":"Sichuan University , , ,","place":["Chengdu, P. R. China, 610065"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Liangwei","family":"Han","sequence":"additional","affiliation":[{"name":"Sichuan University , , ,","place":["Chengdu, P. R. China, 610065"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xuetao","family":"Zhao","sequence":"additional","affiliation":[{"name":"Ministry of Ecology and Environment , , ,","place":["Beijing, P. R. China, 100012"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qian","family":"Zhang","sequence":"additional","affiliation":[{"name":"Ministry of Ecology and Environment , , ,","place":["Beijing, P. R. China, 100012"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"316","published-online":{"date-parts":[[2026,9,23]]},"reference":[{"key":"2026101310165959900_cit1","doi-asserted-by":"publisher","first-page":"4097","DOI":"10.1021\/es062695v","article-title":"Fate of endocrine disrupting\ncompounds in membrane bioreactor systems","volume":"41","author":"Hu","year":"2007","journal-title":"Environ.\nSci. Technol."},{"key":"2026101310165959900_cit2","doi-asserted-by":"publisher","first-page":"120610","DOI":"10.1016\/j.watres.2023.120610","article-title":"Hazard vs.\nexposure: Does it make\na difference in identifying chemicals with persistence and mobility\nconcerns?","volume":"245","author":"Zhang","year":"2023","journal-title":"Water Res."},{"key":"2026101310165959900_cit3","doi-asserted-by":"publisher","first-page":"140792","DOI":"10.1016\/j.jhazmat.2025.140792","article-title":"pH-dependent overestimation\nof heavy metals mobility risk in soils: Implications for soil quality\nassessment","volume":"501","author":"Wu","year":"2026","journal-title":"J. Hazard. Mater."},{"key":"2026101310165959900_cit4","doi-asserted-by":"publisher","first-page":"513","DOI":"10.1063\/1.555805","article-title":"Critical\nreview\nof rate constants for reactions of hydrated electrons, hydrogen atoms\nand hydroxyl radicals (\u00b7OH\/\u00b7O\u2013) in aqueous\nsolution","volume":"17","author":"Buxton","year":"1988","journal-title":"J. Phys. Chem. Ref. Data"},{"key":"2026101310165959900_cit5","doi-asserted-by":"publisher","first-page":"1027","DOI":"10.1063\/1.555808","article-title":"Rate constants for reactions of inorganic\nradicals in aqueous solution","volume":"17","author":"Neta","year":"1988","journal-title":"J. Phys. Chem.\nRef. Data"},{"key":"2026101310165959900_cit6","doi-asserted-by":"publisher","first-page":"1637","DOI":"10.1063\/1.555843","article-title":"Reduction\npotentials of one-electron couples involving free radicals in aqueous\nsolution","volume":"18","author":"Wardman","year":"1989","journal-title":"J. Phys. Chem. Ref. Data"},{"key":"2026101310165959900_cit7","doi-asserted-by":"publisher","first-page":"9182","DOI":"10.1021\/es051236b","article-title":"Photosensitizer method to determine rate constants\nfor the reaction of carbonate radical with organic compounds","volume":"39","author":"Canonica","year":"2005","journal-title":"Environ. Sci. Technol."},{"key":"2026101310165959900_cit8","doi-asserted-by":"publisher","first-page":"477","DOI":"10.1016\/1359-0197(91)90065-A","article-title":"Electron transfer\nreaction rates\nand equilibria of the carbonate and sulfate radical anions","volume":"38","author":"Huie","year":"1991","journal-title":"Int. J. Radiat. Appl. Instrum., Part C"},{"key":"2026101310165959900_cit9","doi-asserted-by":"publisher","first-page":"1014","DOI":"10.1016\/j.chemosphere.2018.12.156","article-title":"Rate constants of sulfate radical\nanion reactions with\norganic molecules: A review","volume":"220","author":"Wojna\u0301rovits","year":"2019","journal-title":"Chemosphere"},{"key":"2026101310165959900_cit10","doi-asserted-by":"publisher","first-page":"1111","DOI":"10.1016\/j.watres.2012.11.033","article-title":"QSAR models for\noxidation of organic micropollutants\nin water based on ozone and hydroxyl radical rate constants and their\nchemical classification","volume":"47","author":"Sudhakaran","year":"2013","journal-title":"Water Res."},{"key":"2026101310165959900_cit11","doi-asserted-by":"publisher","first-page":"12437","DOI":"10.1021\/acs.est.1c04326","article-title":"pySiRC:\nmachine learning combined with molecular fingerprints to predict the\nreaction rate constant of the radical-based oxidation processes of\naqueous organic contaminants","volume":"55","author":"Sanches-Neto","year":"2021","journal-title":"Environ. Sci.\nTechnol."},{"key":"2026101310165959900_cit12","doi-asserted-by":"publisher","first-page":"121141","DOI":"10.1016\/j.jhazmat.2019.121141","article-title":"A deep neural network\ncombined with molecular fingerprints (DNN-MF) to develop predictive\nmodels for hydroxyl radical rate constants of water contaminants","volume":"383","author":"Zhong","year":"2020","journal-title":"J. Hazard. Mater."},{"key":"2026101310165959900_cit13","doi-asserted-by":"publisher","first-page":"681","DOI":"10.1021\/acs.est.1c04883","article-title":"Machine learning-assisted\nQSAR models\non contaminant reactivity toward four oxidants: combining small data\nsets and knowledge transfer","volume":"56","author":"Zhong","year":"2022","journal-title":"Environ. Sci. Technol."},{"key":"2026101310165959900_cit14","doi-asserted-by":"publisher","first-page":"140660","DOI":"10.1016\/j.chemosphere.2023.140660","article-title":"Prediction of free\nradical reactions toward organic pollutants with easily accessible\nmolecular descriptors","volume":"346","author":"Zhang","year":"2024","journal-title":"Chemosphere"},{"key":"2026101310165959900_cit15","unstructured":"Gilmer, J.; Schoenholz, S. S.; Riley, P. F.; Vinyals, O.; Dahl, G. E.\n          Neural message\npassing for quantum chemistry.  International\nConference on Machine Learning, 2017; pp 1263\u20131272."},{"key":"2026101310165959900_cit16","first-page":"2224","article-title":"Convolutional networks\non graphs for learning molecular fingerprints","volume":"28","author":"Duvenaud","year":"2015","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"2026101310165959900_cit17","doi-asserted-by":"publisher","first-page":"8749","DOI":"10.1021\/acs.jmedchem.9b00959","article-title":"Pushing the boundaries of molecular representation for drug discovery\nwith the graph attention mechanism","volume":"63","author":"Xiong","year":"2020","journal-title":"J. Med.\nChem."},{"key":"2026101310165959900_cit18","doi-asserted-by":"publisher","first-page":"3370","DOI":"10.1021\/acs.jcim.9b00237","article-title":"Analyzing\nlearned molecular representations for property\nprediction","volume":"59","author":"Yang","year":"2019","journal-title":"J. Chem. Inf. Model."},{"key":"2026101310165959900_cit19","doi-asserted-by":"publisher","first-page":"133355","DOI":"10.1016\/j.jhazmat.2023.133355","article-title":"AI-enhanced\nchemical paradigm: From molecular graphs\nto accurate prediction and mechanism","volume":"465","author":"Huang","year":"2024","journal-title":"J. Hazard.\nMater."},{"key":"2026101310165959900_cit20","doi-asserted-by":"publisher","first-page":"108113","DOI":"10.1016\/j.psep.2025.108113","article-title":"Large-scale\nchemical language models for accurate and interpretable prediction\nof reactivity and toxicity","volume":"204","author":"Huang","year":"2025","journal-title":"Process Saf. Environ.\nProt."},{"key":"2026101310165959900_cit21","doi-asserted-by":"publisher","first-page":"140631","DOI":"10.1016\/j.jhazmat.2025.140631","article-title":"Radical-Net: A chemistry-enhanced transformer for elementary radical\nreactions in pollutant chemistry","volume":"501","author":"Huang","year":"2026","journal-title":"J. Hazard.\nMater."},{"key":"2026101310165959900_cit22","doi-asserted-by":"publisher","first-page":"1111","DOI":"10.1002\/anie.199311113","article-title":"Electron\ntransfer reactions in chemistry: theory and experiment (Nobel lecture)","volume":"32","author":"Marcus","year":"1993","journal-title":"Angew. Chem., Int. Ed. Engl."},{"key":"2026101310165959900_cit23","doi-asserted-by":"publisher","first-page":"41","DOI":"10.1023\/A:1007379606734","article-title":"Multitask\nlearning","volume":"28","author":"Caruana","year":"1997","journal-title":"Mach. Learn."},{"key":"2026101310165959900_cit24","doi-asserted-by":"publisher","first-page":"1345","DOI":"10.1109\/TKDE.2009.191","article-title":"A survey on transfer learning","volume":"22","author":"Pan","year":"2010","journal-title":"IEEE Trans.\nKnowl. Data Eng."},{"key":"2026101310165959900_cit25","unstructured":"Hu, W.; Liu, B.; Gomes, J.; Zitnik, M.; Liang, P.; Pande, V.; Leskovec, J.\n          Strategies for pre-training graph\nneural networks.  International Conference\non Learning Representations, 2020."},{"key":"2026101310165959900_cit26","doi-asserted-by":"publisher","first-page":"108627","DOI":"10.1016\/j.neunet.2026.108627","article-title":"Cross-category spatiotemporal consensus and discriminative\nnetworks\nfor weakly-supervised temporal action localization","volume":"198","author":"Wu","year":"2026","journal-title":"Neural Netw."},{"key":"2026101310165959900_cit27","first-page":"5998","article-title":"Attention\nis all you need","volume":"30","author":"Vaswani","year":"2017","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"2026101310165959900_cit28","unstructured":"RDKit: Open-Source Cheminformatics. 2024; https:\/\/www.rdkit.org (accessed\nJuly 15, 2018)."},{"key":"2026101310165959900_cit29","doi-asserted-by":"publisher","first-page":"55","DOI":"10.1109\/TIT.1968.1054102","article-title":"On the mean\naccuracy of statistical pattern recognizers","volume":"14","author":"Hughes","year":"1968","journal-title":"IEEE Trans. Inf. Theory"},{"key":"2026101310165959900_cit30","doi-asserted-by":"publisher","first-page":"2887","DOI":"10.1021\/jm9602928","article-title":"The properties of\nknown drugs. 1. Molecular frameworks","volume":"39","author":"Bemis","year":"1996","journal-title":"J. Med.\nChem."},{"key":"2026101310165959900_cit31","doi-asserted-by":"publisher","first-page":"9","DOI":"10.1186\/s40537-016-0043-6","article-title":"A survey of transfer learning","volume":"3","author":"Weiss","year":"2016","journal-title":"J. Big Data"},{"key":"2026101310165959900_cit32","unstructured":"Standley, T.; Zamir, A.; Chen, D.; Guibas, L.; Malik, J.; Savarese, S.\n          Which Tasks Should Be Learned Together\nin Multi-task\nLearning?.  Proceedings of the 37th International\nConference on Machine Learning, 2020; pp 9120\u20139132."},{"key":"2026101310165959900_cit33","doi-asserted-by":"crossref","unstructured":"Chen, T.; Guestrin, C.\n          Xgboost: A scalable\ntree boosting system.  Proceedings of the 22nd\nAcm SIGKDD International Conference on Knowledge Discovery and Data\nMining2016, 785\u2013794.","DOI":"10.1145\/2939672.2939785"},{"key":"2026101310165959900_cit34","doi-asserted-by":"publisher","first-page":"5","DOI":"10.1023\/A:1010933404324","article-title":"Random forests","volume":"45","author":"Breiman","year":"2001","journal-title":"Mach. Learn."},{"key":"2026101310165959900_cit35","doi-asserted-by":"publisher","first-page":"580","DOI":"10.1002\/jcc.22885","article-title":"Multiwfn: A Multifunctional\nWavefunction Analyzer","volume":"33","author":"Lu","year":"2012","journal-title":"J. Comput. Chem."},{"key":"2026101310165959900_cit36","doi-asserted-by":"publisher","first-page":"384","DOI":"10.3390\/pr12020384","article-title":"Utilizing Machine Learning Models\nwith Molecular Fingerprints and Chemical Structures to Predict the\nSulfate Radical Rate Constants of Water Contaminants","volume":"12","author":"Tang","year":"2024","journal-title":"Processes"},{"key":"2026101310165959900_cit37","doi-asserted-by":"publisher","first-page":"137899","DOI":"10.1016\/j.jhazmat.2025.137899","article-title":"Beyond the\nreaction kinetics: Interpretable machine learning reveals unique pathways\nof sulfate and carbonate radicals","volume":"491","author":"Huang","year":"2025","journal-title":"J. Hazard.\nMater."},{"key":"2026101310165959900_cit38","doi-asserted-by":"publisher","first-page":"438","DOI":"10.1016\/j.cclet.2021.06.061","article-title":"Prediction of second-order\nrate constants between carbonate radical and organics by deep neural\nnetwork combined with molecular fingerprints","volume":"33","author":"Sun","year":"2022","journal-title":"Chin. Chem. Lett."},{"key":"2026101310165959900_cit39","doi-asserted-by":"publisher","first-page":"688","DOI":"10.1016\/j.cej.2018.06.137","article-title":"Radiation-induced degradation\nof sulfamethoxazole in the presence\nof various inorganic anions","volume":"351","author":"Wang","year":"2018","journal-title":"Chem. Eng. J."},{"key":"2026101310165959900_cit40","doi-asserted-by":"publisher","first-page":"107377","DOI":"10.1016\/j.envint.2022.107377","article-title":"UV activated\nsodium percarbonate to accelerate degradation of atrazine: mechanism,\nintermediates, and evaluation on residual toxicity by metabolomics","volume":"166","author":"Yu","year":"2022","journal-title":"Environ. Int."},{"key":"2026101310165959900_cit41","doi-asserted-by":"publisher","first-page":"142","DOI":"10.29356\/jmcs.v55i3.812","article-title":"Chemical\nReactivity of Atrazine Employing the Fukui\nFunction","volume":"55","author":"Mendoza-Huizar","year":"2011","journal-title":"J. Mex. Chem. Soc."},{"key":"2026101310165959900_cit42","doi-asserted-by":"publisher","first-page":"arXiv:1802.03426","DOI":"10.48550\/arXiv.1802.03426","article-title":"UMAP: Uniform manifold approximation\nand projection for dimension reduction","author":"McInnes","year":"2018","journal-title":"arXiv"},{"key":"2026101310165959900_cit43","doi-asserted-by":"publisher","first-page":"18410","DOI":"10.1021\/acs.est.3c04086","article-title":"Predicting Transformation Products\nduring Aqueous Oxidation\nProcesses: Current State and Outlook","volume":"57","author":"Minakata","year":"2023","journal-title":"Environ.\nSci. Technol."}],"container-title":["Environmental Science &amp;\nTechnology"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/pubs.acs.org\/doi\/pdf\/10.1021\/acs.est.6c05985","content-type":"application\/pdf","content-version":"vor","intended-application":"unspecified"},{"URL":"https:\/\/pubs.acs.org\/esthag\/article-pdf\/60\/40\/28829\/68613426\/acs.est.6c05985.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/pubs.acs.org\/esthag\/article-pdf\/60\/40\/28829\/68613426\/acs.est.6c05985.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,10,13]],"date-time":"2026-10-13T16:33:44Z","timestamp":1791909224000},"score":1,"resource":{"primary":{"URL":"https:\/\/pubs.acs.org\/esthag\/article\/60\/40\/28829\/5436164\/Cross-Radical-Knowledge-Sharing-via-Graph-Neural"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,9,23]]},"references-count":43,"journal-issue":{"issue":"40","published-online":{"date-parts":[[2026,9,23]]},"published-print":{"date-parts":[[2026,10,13]]}},"URL":"https:\/\/doi.org\/10.1021\/acs.est.6c05985","relation":{},"ISSN":["0013-936X","1520-5851"],"issn-type":[{"value":"0013-936X","type":"print"},{"value":"1520-5851","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,9,23]]}}}