{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,23]],"date-time":"2026-10-23T19:44:28Z","timestamp":1792784668907,"version":"4.5.0"},"reference-count":45,"publisher":"American Chemical Society (ACS)","issue":"18","license":[{"start":{"date-parts":[[2026,9,7]],"date-time":"2026-09-07T00:00:00Z","timestamp":1788739200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,9,7]],"date-time":"2026-09-07T00:00:00Z","timestamp":1788739200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,9,7]],"date-time":"2026-09-07T00:00:00Z","timestamp":1788739200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-045"}],"funder":[{"name":"National Natural Science Foundation of China (NSFC)","award":["82273858"],"award-info":[{"award-number":["82273858"]}],"id":[{"id":"https:\/\/ror.org\/01h0zpd94","id-type":"ROR","asserted-by":"crossref"}]},{"name":"National Natural Science Foundation of China (NSFC)","award":["U23A20530"],"award-info":[{"award-number":["U23A20530"]}],"id":[{"id":"https:\/\/ror.org\/01h0zpd94","id-type":"ROR","asserted-by":"crossref"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026,9,28]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>As the concentration of compounds in aquatic environments rises, the degradation of aquatic habitats underscores the increasing importance of studying the impact of chemicals on different aquatic populations. In this study, we developed AquaTox-Predictor, a multitask, multimodal classification model that integrates molecular fingerprints, molecular graphs, and a Multi-gate Mixture-of-Experts (MMoE) framework for prediction of seven aquatic ecotoxicities of chemicals. The results of the validation sets demonstrated that our model outperformed other methods, achieving the highest average AUC with an improvement of up to 5.75% compared to existing approaches. Our method can correctly identify the substructures that define molecular properties as well as the differences and relationships between end points, thus enhancing interpretability. These results demonstrate that AquaTox-Predictor can achieve high accuracy in predicting various aquatic toxicities and conduct interpretability analysis on compounds, which is conducive to its application in research on other more complex toxicity end points. All the code and datasets are freely available online at https:\/\/github.com\/jwZhang-lab\/AquaTox-Predictor.<\/jats:p>","DOI":"10.1021\/acs.jcim.6c02770","type":"journal-article","created":{"date-parts":[[2026,9,7]],"date-time":"2026-09-07T07:01:32Z","timestamp":1788764492000},"page":"11902-11915","source":"Crossref","is-referenced-by-count":0,"title":["AquaTox-Predictor:\nAn MMoE-Enhanced Multimodal Deep\nLearning Framework for Aquatic Ecotoxicity Prediction"],"prefix":"10.1021","volume":"66","author":[{"given":"Jingwei","family":"Zhang","sequence":"first","affiliation":[{"name":"East China University of Science and Technology , , ,","place":["Shanghai, China, 200237"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Le","family":"Xiong","sequence":"additional","affiliation":[{"name":"East China University of Science and Technology , , ,","place":["Shanghai, China, 200237"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Fei","family":"Pan","sequence":"additional","affiliation":[{"name":"East China University of Science and Technology , , ,","place":["Shanghai, China, 200237"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7055-9836","authenticated-orcid":true,"given":"Weihua","family":"Li","sequence":"additional","affiliation":[{"name":"East China University of Science and Technology , , ,","place":["Shanghai, China, 200237"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xinxin","family":"Yu","sequence":"additional","affiliation":[{"name":"East China University of Science and Technology , , ,","place":["Shanghai, China, 200237"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wenxiang","family":"Song","sequence":"additional","affiliation":[{"name":"East China University of Science and Technology , , ,","place":["Shanghai, China, 200237"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Dian","family":"Sheng","sequence":"additional","affiliation":[{"name":"East China University of Science and Technology , , ,","place":["Shanghai, China, 200237"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2340-1109","authenticated-orcid":true,"given":"Yun","family":"Tang","sequence":"additional","affiliation":[{"name":"East China University of Science and Technology , , ,","place":["Shanghai, China, 200237"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9648-844X","authenticated-orcid":true,"given":"Guixia","family":"Liu","sequence":"additional","affiliation":[{"name":"East China University of Science and Technology , , ,","place":["Shanghai, China, 200237"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"316","published-online":{"date-parts":[[2026,9,7]]},"reference":[{"issue":"3","key":"2026092810063682700_cit1","doi-asserted-by":"publisher","first-page":"1510","DOI":"10.1021\/acs.est.1c04158","article-title":"Outside the Safe Operating\nSpace of the Planetary Boundary for Novel Entities","volume":"56","author":"Persson","year":"2022","journal-title":"Environ. Sci. Technol."},{"issue":"5790","key":"2026092810063682700_cit2","doi-asserted-by":"publisher","first-page":"1072","DOI":"10.1126\/science.1127291","article-title":"The Challenge of Micropollutants\nin Aquatic Systems","volume":"313","author":"Schwarzenbach","year":"2006","journal-title":"Science"},{"issue":"6476","key":"2026092810063682700_cit3","doi-asserted-by":"publisher","first-page":"384","DOI":"10.1126\/science.aay6637","article-title":"Learning from the Past and Considering\nthe Future of Chemicals in the Environment","volume":"367","author":"Johnson","year":"2020","journal-title":"Science"},{"issue":"9","key":"2026092810063682700_cit4","doi-asserted-by":"publisher","first-page":"655","DOI":"10.1080\/1062936X.2020.1797872","article-title":"Consensus QSAR Models Estimating Acute Toxicity to\nAquatic Organisms from Different Trophic Levels: Algae, Daphnia and Fish","volume":"31","author":"Lunghini","year":"2020","journal-title":"SAR QSAR Environ. Res."},{"issue":"120103","key":"2026092810063682700_cit5","doi-asserted-by":"publisher","first-page":"120103","DOI":"10.1016\/j.jenvman.2024.120103","article-title":"Contamination of Textile Dyes in\nAquatic Environment: Adverse Impacts\non Aquatic Ecosystem and Human Health, and Its Management Using Bioremediation","volume":"353","author":"Dutta","year":"2024","journal-title":"J. Environ. Manage"},{"issue":"1\u20132","key":"2026092810063682700_cit6","doi-asserted-by":"publisher","first-page":"109","DOI":"10.1016\/S0048-9697(98)00337-4","article-title":"Occurrence of Antibiotics\nin the Aquatic Environment","volume":"225","author":"Hirsch","year":"1999","journal-title":"Sci. Total Environ."},{"issue":"26","key":"2026092810063682700_cit7","doi-asserted-by":"publisher","first-page":"17595","DOI":"10.1039\/D3RA00723E","article-title":"Heavy Metal Pollution in the Aquatic\nEnvironment: Efficient and Low-Cost Removal Approaches to Eliminate\nTheir Toxicity: A Review","volume":"13","author":"Hama Aziz","year":"2023","journal-title":"RSC Adv."},{"key":"2026092810063682700_cit8","doi-asserted-by":"crossref","first-page":"103","DOI":"10.1016\/B978-0-323-85624-9.00011-7","volume-title":"Impact of Aquatic Pollution\non Fish Fauna, Bacterial Fish Diseases","author":"Jan","year":"2022"},{"issue":"5","key":"2026092810063682700_cit9","doi-asserted-by":"publisher","first-page":"685","DOI":"10.1289\/ehp.0800168","article-title":"The Toxicity Data Landscape for Environmental\nChemicals","volume":"117","author":"Judson","year":"2009","journal-title":"Environ. Health Perspect"},{"issue":"1","key":"2026092810063682700_cit10","doi-asserted-by":"publisher","first-page":"5","DOI":"10.1093\/toxsci\/kfl103","article-title":"The ToxCast\nProgram for Prioritizing Toxicity Testing\nof Environmental Chemicals","volume":"95","author":"Dix","year":"2007","journal-title":"Toxicol. Sci."},{"issue":"3","key":"2026092810063682700_cit11","doi-asserted-by":"publisher","first-page":"1253","DOI":"10.1021\/acs.jcim.8b00785","article-title":"Predictive Multitask Deep Neural\nNetwork Models for ADME-Tox Properties: Learning from Large Data Sets","volume":"59","author":"Wenzel","year":"2019","journal-title":"J. Chem. Inf. Model"},{"issue":"W1","key":"2026092810063682700_cit12","doi-asserted-by":"publisher","first-page":"W432","DOI":"10.1093\/nar\/gkae298","article-title":"admetSAR3.0: A Comprehensive Platform\nfor Exploration, Prediction and Optimization of Chemical ADMET Properties","volume":"52","author":"Gu","year":"2024","journal-title":"Nucleic Acids Res."},{"issue":"4","key":"2026092810063682700_cit13","doi-asserted-by":"publisher","first-page":"1401","DOI":"10.1021\/acs.jproteome.6b00618","article-title":"Deep-Learning-Based\nDrug-Target Interaction Prediction","volume":"16","author":"Wen","year":"2017","journal-title":"J. Proteome\nRes."},{"issue":"1","key":"2026092810063682700_cit14","doi-asserted-by":"publisher","first-page":"103","DOI":"10.1021\/acs.jmedchem.1c01205","article-title":"Discovery of Pyrazolo [3, 4-d] Pyridazinone Derivatives as Selective\nDDR1 Inhibitors via Deep Learning Based Design, Synthesis, and Biological\nEvaluation","volume":"65","author":"Tan","year":"2022","journal-title":"J. Med. Chem."},{"issue":"7698","key":"2026092810063682700_cit15","doi-asserted-by":"publisher","first-page":"604","DOI":"10.1038\/nature25978","article-title":"Planning\nChemical Syntheses with\nDeep Neural Networks and Symbolic AI","volume":"555","author":"Segler","year":"2018","journal-title":"Nature"},{"key":"2026092810063682700_cit16","doi-asserted-by":"publisher","first-page":"568","DOI":"10.1039\/D4FD00093E","article-title":"Re-Evaluating\nRetrosynthesis Algorithms with Syntheseus","volume":"256","author":"Maziarz","year":"2025","journal-title":"Faraday\nDiscuss"},{"issue":"11","key":"2026092810063682700_cit17","doi-asserted-by":"publisher","first-page":"3319","DOI":"10.1021\/acs.jcim.3c00579","article-title":"Molecular Generation with Reduced\nLabeling through Constraint Architecture","volume":"63","author":"Wang","year":"2023","journal-title":"J.\nChem. Inf. Model"},{"key":"2026092810063682700_cit18","doi-asserted-by":"publisher","first-page":"827606","DOI":"10.3389\/fphar.2021.827606","article-title":"Cross-Adversarial Learning for Molecular\nGeneration in Drug Design","volume":"12","author":"Wu","year":"2021","journal-title":"Front. Pharmacol"},{"issue":"13","key":"2026092810063682700_cit19","doi-asserted-by":"publisher","first-page":"3191","DOI":"10.1021\/acs.jcim.2c00671","article-title":"Exploring Low-Toxicity Chemical Space\nwith Deep Learning for Molecular\nGeneration","volume":"62","author":"Yang","year":"2022","journal-title":"J. Chem. Inf. Model"},{"key":"2026092810063682700_cit20","doi-asserted-by":"publisher","first-page":"80","DOI":"10.3389\/fenvs.2015.00080","article-title":"Toxicity Prediction\nUsing Deep Learning","volume":"3","author":"Mayr","year":"2016","journal-title":"Front. Environ. Sci."},{"issue":"5","key":"2026092810063682700_cit21","doi-asserted-by":"publisher","first-page":"741","DOI":"10.1021\/tx400371w","article-title":"Multispecies\nQSAR Modeling\nfor Predicting the Aquatic Toxicity of Diverse Organic Chemicals for\nRegulatory Toxicology","volume":"27","author":"Singh","year":"2014","journal-title":"Chem. Res. Toxicol"},{"issue":"2","key":"2026092810063682700_cit22","doi-asserted-by":"publisher","first-page":"653","DOI":"10.1021\/acs.jcim.0c01164","article-title":"Large-Scale\nModeling of Multispecies Acute Toxicity End Points Using Consensus\nof Multitask Deep Learning Methods","volume":"61","author":"Jain","year":"2021","journal-title":"J. Chem.\nInf. Model"},{"issue":"6","key":"2026092810063682700_cit23","doi-asserted-by":"publisher","first-page":"3091","DOI":"10.1021\/acs.jcim.6c00033","article-title":"Dual-Modal\nFusion Based on Peptide Sequence and Molecular Graph with Bidirectional\nCross-Attention for Precise Peptide Toxicity Prediction","volume":"66","author":"Li","year":"2026","journal-title":"J. Chem. Inf. Model"},{"issue":"2","key":"2026092810063682700_cit24","doi-asserted-by":"publisher","first-page":"1766","DOI":"10.1021\/acs.jmedchem.5c03551","article-title":"Multimodal Multi-Granularity Fusion\nModel with Mamba Architecture for Ames Mutagenicity Prediction","volume":"69","author":"Han","year":"2026","journal-title":"J. Med. Chem."},{"issue":"23","key":"2026092810063682700_cit25","doi-asserted-by":"publisher","first-page":"12799","DOI":"10.1021\/acs.jcim.5c02280","article-title":"Multimodal\nFeature Fusion for Bone Toxicity Prediction and Local Platform","volume":"65","author":"Pan","year":"2025","journal-title":"J. Chem. Inf. Model"},{"issue":"10","key":"2026092810063682700_cit26","doi-asserted-by":"publisher","first-page":"6924","DOI":"10.1021\/acs.jmedchem.1c00421","article-title":"Mining Toxicity Information\nfrom Large Amounts of Toxicity Data","volume":"64","author":"Wu","year":"2021","journal-title":"J. Med.\nChem."},{"key":"2026092810063682700_cit27","doi-asserted-by":"publisher","first-page":"477","DOI":"10.1016\/j.jare.2024.06.002","article-title":"Multi-Task\nAquatic Toxicity Prediction\nModel Based on Multi-Level Features Fusion","volume":"68","author":"Yang","year":"2025","journal-title":"J. Adv. Res."},{"issue":"107244","key":"2026092810063682700_cit28","doi-asserted-by":"publisher","first-page":"107244","DOI":"10.1016\/j.aquatox.2025.107244","article-title":"CLSSATP: Contrastive\nLearning and Self-Supervised Learning Model\nfor Aquatic Toxicity Prediction","volume":"279","author":"Lin","year":"2025","journal-title":"Aquat. Toxicol"},{"issue":"4","key":"2026092810063682700_cit29","doi-asserted-by":"publisher","DOI":"10.1111\/jcmm.71067","article-title":"ADFC-ATP:\nAttention-Guided Dual-View Fusion and Contrastive Pretraining for\nRobust Aquatic Toxicity Prediction","volume":"30","author":"Jia","year":"2026","journal-title":"J. Cell.\nMol. Med."},{"issue":"5","key":"2026092810063682700_cit30","doi-asserted-by":"publisher","first-page":"742","DOI":"10.1021\/ci100050t","article-title":"Extended-Connectivity\nFingerprints","volume":"50","author":"Rogers","year":"2010","journal-title":"J. Chem.\nInf. Model"},{"issue":"6","key":"2026092810063682700_cit31","doi-asserted-by":"publisher","first-page":"1273","DOI":"10.1021\/ci010132r","article-title":"Reoptimization of\nMDL Keys for Use in Drug Discovery","volume":"42","author":"Durant","year":"2002","journal-title":"J. Chem.\nInf. Comput. Sci."},{"issue":"1","key":"2026092810063682700_cit32","doi-asserted-by":"publisher","first-page":"51","DOI":"10.1186\/s13321-020-00456-1","article-title":"An Open\nSource Chemical Structure Curation Pipeline Using RDKit","volume":"12","author":"Bento","year":"2020","journal-title":"J. Cheminform"},{"key":"2026092810063682700_cit33","doi-asserted-by":"crossref","first-page":"593","DOI":"10.1007\/978-3-319-93417-4_38","article-title":"Modeling\nRelational Data with\nGraph Convolutional Networks","volume-title":"The Semantic\nWeb","author":"Schlichtkrull","year":"2018"},{"key":"2026092810063682700_cit34","doi-asserted-by":"crossref","first-page":"1930","DOI":"10.1145\/3219819.3220007","article-title":"Modeling Task Relationships in Multi-Task Learning with Multi-Gate\nMixture-of-Experts","volume-title":"Proceedings of the\n24th ACM SIGKDD International Conference on Knowledge Discovery &\nData Mining","author":"Ma","year":"2018"},{"issue":"162736","key":"2026092810063682700_cit35","doi-asserted-by":"publisher","first-page":"162736","DOI":"10.1016\/j.scitotenv.2023.162736","article-title":"Ecotoxicological QSAR Study of Fused\/Non-Fused\nPolycyclic Aromatic Hydrocarbons (FNFPAHs): Assessment and Priority\nRanking of the Acute Toxicity to Pimephales Promelas by QSAR and Consensus\nModeling Methods","volume":"876","author":"Chen","year":"2023","journal-title":"Sci. Total Environ."},{"issue":"2","key":"2026092810063682700_cit36","doi-asserted-by":"publisher","first-page":"452","DOI":"10.1039\/C4TX00174E","article-title":"In Silico Prediction\nof Chemical Aquatic Toxicity with Chemical Category Approaches and\nSubstructural Alerts","volume":"4","author":"Sun","year":"2015","journal-title":"Toxicol Res."},{"issue":"113940","key":"2026092810063682700_cit37","doi-asserted-by":"publisher","first-page":"113940","DOI":"10.1016\/j.ecoenv.2022.113940","article-title":"Modeling and\nInsights into the Structural Basis of Chemical Acute Aquatic Toxicity","volume":"242","author":"Zhang","year":"2022","journal-title":"Ecotoxicol. Environ. Saf"},{"issue":"105962","key":"2026092810063682700_cit38","doi-asserted-by":"crossref","first-page":"105962","DOI":"10.1016\/j.aquatox.2021.105962","article-title":"Identification of\nConcealed Structural Alerts Using QSTR Modeling for Pseudokirchneriella\nSubcapitata","volume":"239","author":"Masand","year":"2021","journal-title":"Aquat. Toxicol"},{"issue":"Pt 2","key":"2026092810063682700_cit39","doi-asserted-by":"publisher","first-page":"117239","DOI":"10.1016\/j.envres.2023.117239","article-title":"Global Classification\nModels for Predicting Acute Toxicity of Chemicals towards Daphnia\nMagna","volume":"238","author":"Yu","year":"2023","journal-title":"Environ. Res."},{"issue":"6","key":"2026092810063682700_cit40","doi-asserted-by":"publisher","first-page":"1520","DOI":"10.1002\/etc.5324","article-title":"The ECOTOXicology\nKnowledgebase:\nA Curated Database of Ecologically Relevant Toxicity Tests to Support\nEnvironmental Research and Risk Assessment","volume":"41","author":"Olker","year":"2022","journal-title":"Environ. Toxicol. Chem."},{"issue":"8","key":"2026092810063682700_cit41","doi-asserted-by":"publisher","first-page":"861","DOI":"10.1016\/j.patrec.2005.10.010","article-title":"An Introduction\nto ROC Analysis","volume":"27","author":"Fawcett","year":"2006","journal-title":"Pattern Recognit. Lett."},{"issue":"1","key":"2026092810063682700_cit42","doi-asserted-by":"publisher","first-page":"29","DOI":"10.1148\/radiology.143.1.7063747","article-title":"The Meaning and Use of the Area under a Receiver Operating\nCharacteristic (ROC) Curve","volume":"143","author":"Hanley","year":"1982","journal-title":"Radiology"},{"issue":"4","key":"2026092810063682700_cit43","doi-asserted-by":"publisher","first-page":"427","DOI":"10.1016\/j.ipm.2009.03.002","article-title":"A Systematic Analysis of Performance Measures for Classification\nTasks","volume":"45","author":"Sokolova","year":"2009","journal-title":"Inf. Process. Manag"},{"issue":"5","key":"2026092810063682700_cit44","doi-asserted-by":"publisher","first-page":"bbab017","DOI":"10.1093\/bib\/bbab017","article-title":"PySmash:\nPython Package and Individual Executable Program for Representative\nSubstructure Generation and Application","volume":"22","author":"Yang","year":"2021","journal-title":"Brief\nBioinform"},{"issue":"12","key":"2026092810063682700_cit45","doi-asserted-by":"publisher","first-page":"7003","DOI":"10.1021\/acs.jcim.6c00967","article-title":"A Reproducible\nHierarchical Virtual\nScreening Framework Integrating Scaffold-Aware Machine Learning, Ensemble\nDocking, and Molecular Dynamics: Application to IDO1","volume":"66","author":"Tomarchio","year":"2026","journal-title":"J. Chem. Inf. Model"}],"container-title":["Journal of Chemical Information\nand Modeling"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/pubs.acs.org\/doi\/pdf\/10.1021\/acs.jcim.6c02770","content-type":"application\/pdf","content-version":"vor","intended-application":"unspecified"},{"URL":"https:\/\/pubs.acs.org\/jcisd8\/article-pdf\/66\/18\/11902\/68398651\/acs.jcim.6c02770.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/pubs.acs.org\/jcisd8\/article-pdf\/66\/18\/11902\/68398651\/acs.jcim.6c02770.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,28]],"date-time":"2026-09-28T14:30:09Z","timestamp":1790605809000},"score":1,"resource":{"primary":{"URL":"https:\/\/pubs.acs.org\/jcisd8\/article\/66\/18\/11902\/5422062\/AquaTox-Predictor-An-MMoE-Enhanced-Multimodal-Deep"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,9,7]]},"references-count":45,"journal-issue":{"issue":"18","published-online":{"date-parts":[[2026,9,7]]},"published-print":{"date-parts":[[2026,9,28]]}},"URL":"https:\/\/doi.org\/10.1021\/acs.jcim.6c02770","relation":{},"ISSN":["1549-9596","1549-960X"],"issn-type":[{"value":"1549-9596","type":"print"},{"value":"1549-960X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,9,7]]}}}