{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,6]],"date-time":"2026-10-06T21:28:58Z","timestamp":1791322138317,"version":"4.3.1"},"reference-count":51,"publisher":"American Chemical Society (ACS)","issue":"14","license":[{"start":{"date-parts":[[2026,7,13]],"date-time":"2026-07-13T00:00:00Z","timestamp":1783900800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,7,13]],"date-time":"2026-07-13T00:00:00Z","timestamp":1783900800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,7,13]],"date-time":"2026-07-13T00:00:00Z","timestamp":1783900800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-045"}],"funder":[{"DOI":"10.13039\/501100010888","name":"Wuhan Municipal Science and Technology Bureau","doi-asserted-by":"publisher","award":["2025051202030408"],"award-info":[{"award-number":["2025051202030408"]}],"id":[{"id":"10.13039\/501100010888","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","award":["2042026kf0055"],"award-info":[{"award-number":["2042026kf0055"]}],"id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100018537","name":"National Science and Technology Major Project","doi-asserted-by":"publisher","award":["2023ZD0120802"],"award-info":[{"award-number":["2023ZD0120802"]}],"id":[{"id":"10.13039\/501100018537","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026,7,27]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>Retrosynthesis is a cornerstone of drug discovery and organic synthesis. While data-driven deep learning models have shown remarkable progress, they are designed to autonomously learn reaction patterns from extensive retrosynthesis data sets with limited explicit integration of established chemical knowledge as priors. To address this limitation, we introduce RetroMPA, a molecular property-aware, posthoc enhancement module that injects chemical knowledge into the retrosynthesis pipeline. Rather than functioning as an independent, standalone SMILES sequence generator from scratch, RetroMPA is conceptualized as a broadly applicable, model-agnostic chemical filter designed to recalibrate and optimize the predictive pathways of various existing algorithms. This plug-and-play framework can be seamlessly integrated with a range of existing data-driven retrosynthesis methods, enhancing model outputs without necessitating any modifications to the original model architecture or requiring resource-intensive, model-specific retraining procedures. By operating at the molecular level and leveraging a property-aware latent embedding space, RetroMPA consistently improves top-1 accuracy across eight representative retrosynthesis models by an average of 5.50% on USPTO-50K. Furthermore, we demonstrate its scalability by validating its performance on the large-scale USPTO-Full data set, achieving an average improvement of about 2.03% across both template-based and template-free architectures. In addition, wet-lab experiments provide preliminary support for the practical utility of the framework. These syntheses confirmed viable, previously unreported substrate combinations for established, classic reaction paradigms\u2500specifically, the Suzuki\u2013Miyaura coupling, the Bucherer reaction, and the Friedel\u2013Crafts acylation, thereby suggesting that RetroMPA can operate beyond mere data fitting. The code is open-sourced at https:\/\/github.com\/MengzhouLu\/RetroMPA.<\/jats:p>","DOI":"10.1021\/acs.jcim.6c01506","type":"journal-article","created":{"date-parts":[[2026,7,13]],"date-time":"2026-07-13T20:15:57Z","timestamp":1783973757000},"page":"8188-8202","source":"Crossref","is-referenced-by-count":1,"title":["RetroMPA: A Molecular\nProperty-Aware Auxiliary Framework\nfor Enhancing Retrosynthesis Prediction"],"prefix":"10.1021","volume":"66","author":[{"ORCID":"https:\/\/orcid.org\/0009-0008-8696-8317","authenticated-orcid":true,"given":"Mianzhi","family":"Liu","sequence":"first","affiliation":[{"name":"Wuhan University , , ,","place":["Wuhan, China, 430072"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Fan","family":"Xiao","sequence":"additional","affiliation":[{"name":"Wuhan University , , ,","place":["Wuhan, China, 430072"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhiliang","family":"Yu","sequence":"additional","affiliation":[{"name":"Wuhan University , , ,","place":["Wuhan, China, 430072"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Huayang","family":"Huang","sequence":"additional","affiliation":[{"name":"Wuhan University , , ,","place":["Wuhan, China, 430072"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuke","family":"Li","sequence":"additional","affiliation":[{"name":"Wuhan University , , ,","place":["Wuhan, China, 430072"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yi","family":"Yang","sequence":"additional","affiliation":[{"name":"Zhejiang University , , ,","place":["Hangzhou, China, 310027"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2687-557X","authenticated-orcid":true,"given":"Wenbo","family":"Liu","sequence":"additional","affiliation":[{"name":"Wuhan University , , ,","place":["Wuhan, China, 430072"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yu","family":"Wu","sequence":"additional","affiliation":[{"name":"Wuhan University , , ,","place":["Wuhan, China, 430072"]},{"name":"Wuhan University , , ,","place":["Wuhan, China, 430072"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"316","published-online":{"date-parts":[[2026,7,13]]},"reference":[{"key":"2026072709093403400_cit1","doi-asserted-by":"publisher","first-page":"2333","DOI":"10.1021\/acs.jmedchem.4c02749","article-title":"Artificial\nIntelligence in Retrosynthesis Prediction\nand its Applications in Medicinal Chemistry","volume":"68","author":"Long","year":"2025","journal-title":"J. Med. Chem."},{"key":"2026072709093403400_cit2","doi-asserted-by":"publisher","first-page":"558","DOI":"10.1039\/D3DD00252G","article-title":"Models matter: The\nimpact of single-step retrosynthesis on synthesis planning","volume":"3","author":"Torren-Peraire","year":"2024","journal-title":"Digital Discovery"},{"key":"2026072709093403400_cit3","unstructured":"Li, X.; Wang, S.; Lin, Y.; Wu, Y.; Yang, Y.\n          Retro-Expert: Collaborative Reasoning for Interpretable\nRetrosynthesis\n          Proc. 43rd Int. Conf. Mach.\nLearning, arXiv.org e-Printarchive arXiv:2508.10967, 202610.48550\/arXiv.2508.10967."},{"key":"2026072709093403400_cit4","doi-asserted-by":"publisher","first-page":"568","DOI":"10.1039\/D4FD00093E","article-title":"Re-evaluating retrosynthesis\nalgorithms with syntheseus","volume":"256","author":"Maziarz","year":"2025","journal-title":"Faraday Discuss."},{"key":"2026072709093403400_cit5","first-page":"9405","article-title":"Learning Graph\nModels for Retrosynthesis Prediction","author":"Somnath","year":"2021","journal-title":"Adv. Neural\nInf. Process. Syst."},{"key":"2026072709093403400_cit6","doi-asserted-by":"publisher","first-page":"31","DOI":"10.1021\/ci00057a005","article-title":"SMILES, a\nchemical language and information system. 1. Introduction to methodology\nand encoding rules","volume":"28","author":"Weininger","year":"1988","journal-title":"J. Chem. Inf. Comput. Sci."},{"key":"2026072709093403400_cit7","unstructured":"Wang, H.; Li, W.; Jin, X.; Cho, K.; Ji, H.; Han, J.; Burke, M. D.\n          Chemical-Reaction-Aware Molecule Representation Learning\n          International Conference on Learning Representations, arXiv.org e-Printarchive arXiv:2109.09888 202210.48550\/arXiv.2109.0988."},{"key":"2026072709093403400_cit8","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-023-43214-1","article-title":"A knowledge-guided\npre-training framework for improving molecular\nrepresentation learning","volume":"14","author":"Li","year":"2023","journal-title":"Nat. Commun."},{"key":"2026072709093403400_cit9","doi-asserted-by":"publisher","first-page":"5026","DOI":"10.1021\/acs.jcim.9b00538","article-title":"Prediction\nand Interpretable Visualization of Retrosynthetic Reactions Using\nGraph Convolutional Networks","volume":"59","author":"Ishida","year":"2019","journal-title":"J. Chem. Inf.\nModel."},{"key":"2026072709093403400_cit10","doi-asserted-by":"crossref","unstructured":"Wang, S.; Guo, Y.; Wang, Y.; Sun, H.; Huang, J.; et al.\n          SMILES-BERT: Large Scale Unsupervised Pre-Training\nfor Molecular Property Prediction; Proceedings of the 10th\nACM International Conference on Bioinformatics, Computational Biology\nand Health Informatics. New York, NY, ACM, 2019; pp 429\u2013436.","DOI":"10.1145\/3307339.3342186"},{"key":"2026072709093403400_cit11","doi-asserted-by":"publisher","first-page":"1181","DOI":"10.1021\/jacsau.2c00157","article-title":"Quantum Chemical Calculations\nto Trace Back Reaction Paths for the Prediction of Reactants","volume":"2","author":"Sumiya","year":"2022","journal-title":"JACS Au"},{"key":"2026072709093403400_cit12","doi-asserted-by":"publisher","first-page":"663","DOI":"10.1039\/D3DD00006K","article-title":"Quantum chemical data generation\nas fill-in for reliability enhancement of machine-learning reaction\nand retrosynthesis planning","volume":"2","author":"Toniato","year":"2023","journal-title":"Digital Discovery"},{"key":"2026072709093403400_cit13","doi-asserted-by":"publisher","DOI":"10.1002\/aic.18092","article-title":"Computer-assisted\nsynthetic planning considering reaction kinetics based on transition\nstate automated generation method","volume":"69","author":"Liu","year":"2023","journal-title":"AIChE J."},{"key":"2026072709093403400_cit14","doi-asserted-by":"publisher","DOI":"10.1002\/wcms.1694","article-title":"Recent advances in deep learning\nfor retrosynthesis","volume":"14","author":"Zhong","year":"2024","journal-title":"Wiley Interdiscip. Rev.:Comput.\nMol. Sci."},{"key":"2026072709093403400_cit15","doi-asserted-by":"publisher","first-page":"6943","DOI":"10.1039\/D5SC01476J","article-title":"Directly optimizing\nfor synthesizability in generative\nmolecular design using retrosynthesis models","volume":"16","author":"Guo","year":"2025","journal-title":"Chem. Sci."},{"key":"2026072709093403400_cit16","doi-asserted-by":"publisher","first-page":"3093","DOI":"10.1021\/ci200379p","article-title":"A collection\nof robust organic synthesis reactions for in silico molecule design","volume":"51","author":"Hartenfeller","year":"2011","journal-title":"J. Chem. Inf. Model."},{"key":"2026072709093403400_cit17","doi-asserted-by":"publisher","first-page":"5904","DOI":"10.1002\/anie.201506101","article-title":"Computer-assisted\nsynthetic planning: the end of the beginning","volume":"55","author":"Szymkuc\u0301","year":"2016","journal-title":"Angew. Chem., Int. Ed."},{"key":"2026072709093403400_cit18","doi-asserted-by":"publisher","first-page":"434","DOI":"10.1021\/acscentsci.7b00064","article-title":"Prediction\nof Organic Reaction Outcomes Using Machine Learning","volume":"3","author":"Coley","year":"2017","journal-title":"ACS Central Sci."},{"key":"2026072709093403400_cit19","doi-asserted-by":"publisher","first-page":"593","DOI":"10.1021\/ci800228y","article-title":"Route Designer: A Retrosynthetic Analysis Tool Utilizing\nAutomated Retrosynthetic Rule Generation","volume":"49","author":"Law","year":"2009","journal-title":"J.\nChem. Inf. Model."},{"key":"2026072709093403400_cit20","doi-asserted-by":"publisher","first-page":"992","DOI":"10.1021\/jacsau.3c00737","article-title":"Node-Aligned\nGraph-to-Graph: Elevating Template-free Deep Learning Approaches in\nSingle-Step Retrosynthesis","volume":"4","author":"Yao","year":"2024","journal-title":"JACS Au"},{"key":"2026072709093403400_cit21","first-page":"11248","article-title":"RetroXpert:\nDecompose Retrosynthesis Prediction Like\nA Chemist","author":"Yan","year":"2020","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"2026072709093403400_cit22","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-024-50617-1","article-title":"Retrosynthesis prediction\nwith an\niterative string editing model","volume":"15","author":"Han","year":"2024","journal-title":"Nat. Commun."},{"key":"2026072709093403400_cit23","doi-asserted-by":"publisher","first-page":"5113","DOI":"10.1609\/aaai.v37i4.25640","article-title":"Learning Chemical\nRules of Retrosynthesis with Pre-training","volume":"37","author":"Jiang","year":"2023","journal-title":"Proc.\nAAAI Conf. Artific. Intell."},{"key":"2026072709093403400_cit24","doi-asserted-by":"publisher","first-page":"9023","DOI":"10.1039\/D2SC02763A","article-title":"Root-aligned\nSMILES:\na tight representation for chemical reaction prediction","volume":"13","author":"Zhong","year":"2022","journal-title":"Chem. Sci."},{"key":"2026072709093403400_cit25","unstructured":"Wan, Y.; Hsieh, C.-Y.; Liao, B.; Zhang, S.\n          Retroformer: Pushing the Limits of End-to-end Retrosynthesis\nTransformer; Proceedings of the 39th International Conference\non Machine Learning, PMLR, 2022; pp 22475\u201322490."},{"key":"2026072709093403400_cit26","doi-asserted-by":"publisher","first-page":"3273","DOI":"10.1021\/acs.jcim.1c00537","article-title":"Molecule Edit Graph Attention Network: Modeling Chemical\nReactions as Sequences of Graph Edits","volume":"61","author":"Sacha","year":"2021","journal-title":"J. Chem.\nInf. Model."},{"key":"2026072709093403400_cit27","doi-asserted-by":"publisher","first-page":"334","DOI":"10.1021\/ja01607a027","article-title":"A correlation\nof reaction rates","volume":"77","author":"Hammond","year":"1955","journal-title":"J. Am. Chem. Soc."},{"key":"2026072709093403400_cit28","doi-asserted-by":"publisher","first-page":"2004","DOI":"10.1002\/1521-3773(20010601)40:11&lt;2004::AID-ANIE2004&gt;3.0.CO;2-5","article-title":"Click chemistry:\ndiverse chemical\nfunction from a few good reactions","volume":"40","author":"Kolb","year":"2001","journal-title":"Angew. Chem.,\nInt. Ed."},{"key":"2026072709093403400_cit29","doi-asserted-by":"publisher","first-page":"2008","DOI":"10.1002\/1521-3773(20020617)41:12&lt;2008::AID-ANIE2008&gt;3.0.CO;2-4","article-title":"Asymmetric\ncatalysis: science and opportunities (Nobel lecture)","volume":"41","author":"Noyori","year":"2002","journal-title":"Angew. Chem., Int. Ed."},{"key":"2026072709093403400_cit30","doi-asserted-by":"publisher","first-page":"19","DOI":"10.1351\/pac196714010019","article-title":"General\nmethods for the construction of complex molecules","volume":"14","author":"Corey","year":"1967","journal-title":"Pure Appl. Chem."},{"key":"2026072709093403400_cit31","doi-asserted-by":"publisher","first-page":"2336","DOI":"10.1021\/acs.jcim.6b00564","article-title":"What\u2019s what: The (nearly)\ndefinitive guide to reaction role assignment","volume":"56","author":"Schneider","year":"2016","journal-title":"J. Chem. Inf. Model."},{"key":"2026072709093403400_cit32","doi-asserted-by":"publisher","first-page":"1612","DOI":"10.1021\/jacsau.1c00246","article-title":"Deep Retrosynthetic Reaction Prediction\nusing Local Reactivity and\nGlobal Attention","volume":"1","author":"Chen","year":"2021","journal-title":"JACS Au"},{"key":"2026072709093403400_cit33","doi-asserted-by":"crossref","first-page":"817","DOI":"10.1007\/978-3-030-30493-5_78","article-title":"A transformer model for retrosynthesis","volume-title":"Artificial Neural Networks Mach. Learning \u2013 ICANN\n2019: Workshop and Special Sessions","author":"Karpov","year":"2019"},{"key":"2026072709093403400_cit34","doi-asserted-by":"crossref","unstructured":"Zhang, X.; Mo, Y.; Wang, W.; Yang, Y.\n          Retrosynthesis prediction enhanced by in-silico reaction\ndata augmentation\n          2024\n          https:\/\/arxiv.org\/abs\/2402.00086.","DOI":"10.21203\/rs.3.rs-3995587\/v1"},{"key":"2026072709093403400_cit35","doi-asserted-by":"publisher","first-page":"5330","DOI":"10.1609\/aaai.v37i4.25664","article-title":"Retrosynthesis\nPrediction with Local Template Retrieval","volume":"37","author":"Xie","year":"2023","journal-title":"Proc.\nAAAI Conf. Artif. Intell."},{"key":"2026072709093403400_cit36","unstructured":"Milvus Project Milvus Documentation.2025. https:\/\/milvus.io\/docs."},{"key":"2026072709093403400_cit37","first-page":"2579","article-title":"Visualizing Data using t-SNE","volume":"9","author":"van der Maaten","year":"2008","journal-title":"J. Mach. Learning Res."},{"key":"2026072709093403400_cit38","doi-asserted-by":"crossref","unstructured":"Edwards, C. N.; Zhai, C. X.; Ji, H.\n          Text2Mol: Cross-Modal Molecule Retrieval\nwith Natural Language Queries; Proceedings of the 2021 Conference\non Empirical Methods in Natural Language Processing, Association for Computational Linguistics, 2021; pp 595\u2013607.","DOI":"10.18653\/v1\/2021.emnlp-main.47"},{"key":"2026072709093403400_cit39","unstructured":"Fang, Y.; Liang, X.; Zhang, N.; Liu, K.; Huang, R.; Chen, Z.; Fan, X.; Chen, H.\n          Mol-Instructions:\nA Large-Scale Biomolecular Instruction Dataset for Large Language\nModels\n          Int. Conf. Learning Representations, arXiv.org e-Printarchive arXiv:2306.08018, 202410.48550\/arXiv.2306.08018."},{"key":"2026072709093403400_cit40","doi-asserted-by":"publisher","first-page":"1447","DOI":"10.1038\/s42256-023-00759-6","article-title":"Multi-modal\nmolecule structure\u2013text model for text-based retrieval and\nediting","volume":"5","author":"Liu","year":"2023","journal-title":"Nat. Mach. Intell."},{"key":"2026072709093403400_cit41","unstructured":"Dai, H.; Li, C.; Coley, C. W.; Dai, B.; Song, L.\n          Retrosynthesis Prediction with\nConditional Graph\nLogic Network\n          2020\n          https:\/\/arxiv.org\/abs\/2001.01408."},{"key":"2026072709093403400_cit42","doi-asserted-by":"publisher","first-page":"11047","DOI":"10.1021\/acs.jcim.5c01508","article-title":"Rethinking Retrosynthesis:\nCurriculum Learning Reshapes Transformer-Based\nSmall-Molecule Reaction Prediction","volume":"65","author":"Sheshanarayana","year":"2025","journal-title":"J. Chem.\nInf. Model."},{"key":"2026072709093403400_cit43","unstructured":"Landrum, G.\n          \n          RDKit: Open-source\ncheminformatics\n          2013\n          https:\/\/www.rdkit.org."},{"key":"2026072709093403400_cit44","doi-asserted-by":"crossref","unstructured":"Bushuiev, R.; Bushuiev, A.; de Jonge, N. F.; Young, A.; et al.\n          MassSpecGym:\nA Benchmark for the Discovery and Identification of Molecules\n          Adv. Neural Inf. Process. Syst. 37 (Datasets Benchmarks\nTrack)\n          2024.","DOI":"10.52202\/079017-3491"},{"key":"2026072709093403400_cit45","doi-asserted-by":"crossref","unstructured":"Liu, Z.; Li, S.; Luo, Y.; Fei, H.; Cao, Y.; Kawaguchi, K.; Wang, X.; Chua, T.-S.\n          MolCA:\nMolecular Graph-Language Modeling with Cross-Modal Projector and Uni-Modal\nAdapter; Proceedings of the 2023 Conference on Empirical\nMethods in Natural Language Processing, Association\nfor Computational Linguistics, 2023;\npp 15623\u201315638.","DOI":"10.18653\/v1\/2023.emnlp-main.966"},{"key":"2026072709093403400_cit46","unstructured":"Li, J.; Li, D.; Savarese, S.; Hoi, S.\n          Blip-2: Bootstrapping language-image pre-training\nwith frozen image encoders and large language models; Proceedings\nof the 40th International Conference on Machine Learning, PMLR, 2023; pp 19730\u201319742."},{"key":"2026072709093403400_cit47","doi-asserted-by":"crossref","unstructured":"Feng, Y.; Gu, S.; Guo, D.; Yang, Z.; Shao, C.\n          Guiding Teacher Forcing with Seer Forcing for Neural Machine\nTranslationProceedings of the 59th Annual Meeting of the\nAssociation for Computational Linguistics and the 11th International\nJoint Conference on Natural Language Processing (Volume 1: Long Papers), Association for Computational Linguistics, 2021; pp 2862\u20132872.","DOI":"10.18653\/v1\/2021.acl-long.223"},{"key":"2026072709093403400_cit48","doi-asserted-by":"publisher","first-page":"2713","DOI":"10.1021\/acs.jcim.2c00495","article-title":"Improving\nMolecular\nContrastive Learning via Faulty Negative Mitigation and Decomposed\nFragment Contrast","volume":"62","author":"Wang","year":"2022","journal-title":"J. Chem. Inf. Model."},{"key":"2026072709093403400_cit49","unstructured":"Xia, J.; Wu, L.; Wang, G.; Li, S. Z.\n          ProGCL: Rethinking Hard Negative Mining in Graph\nContrastive Learning\n          Int. Conf. Mach. Learning, arXiv.org e-Printarchive arXiv:2110.02027v3, 202210.48550\/arXiv.2110.02027."},{"key":"2026072709093403400_cit50","unstructured":"Vaswani, A.; Shazeer, N.; Parmar, N.; Uszkoreit, J.; Jones, L.; Gomez, A. N.; Kaiser, \u0141.; Polosukhin, I.\n          Attention is all you need\n          Adv. Neural Inf. Process. Syst., arXiv.org e-Printarchive\narXiv:1706.03762, 201710.48550\/arXiv.1706.03762."},{"key":"2026072709093403400_cit51","unstructured":"Loshchilov, I.; Hutter, F.\n          Decoupled\nWeight Decay Regularization\n          Int. Conf. Learning\nRepresentations\n          2019."}],"container-title":["Journal of Chemical Information\nand Modeling"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/pubs.acs.org\/doi\/pdf\/10.1021\/acs.jcim.6c01506","content-type":"application\/pdf","content-version":"vor","intended-application":"unspecified"},{"URL":"https:\/\/pubs.acs.org\/jcisd8\/article-pdf\/66\/14\/8188\/65897325\/acs.jcim.6c01506.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/pubs.acs.org\/jcisd8\/article-pdf\/66\/14\/8188\/65897325\/acs.jcim.6c01506.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,27]],"date-time":"2026-07-27T13:31:59Z","timestamp":1785159119000},"score":1,"resource":{"primary":{"URL":"https:\/\/pubs.acs.org\/jcisd8\/article\/66\/14\/8188\/5207686\/RetroMPA-A-Molecular-Property-Aware-Auxiliary"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7,13]]},"references-count":51,"journal-issue":{"issue":"14","published-online":{"date-parts":[[2026,7,13]]},"published-print":{"date-parts":[[2026,7,27]]}},"URL":"https:\/\/doi.org\/10.1021\/acs.jcim.6c01506","relation":{},"ISSN":["1549-9596","1549-960X"],"issn-type":[{"value":"1549-9596","type":"print"},{"value":"1549-960X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,7,13]]}}}