{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,14]],"date-time":"2026-09-14T14:17:12Z","timestamp":1789395432965,"version":"build-2803163510"},"reference-count":65,"publisher":"American Chemical Society (ACS)","issue":"17","license":[{"start":{"date-parts":[[2026,8,18]],"date-time":"2026-08-18T00:00:00Z","timestamp":1787011200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,8,18]],"date-time":"2026-08-18T00:00:00Z","timestamp":1787011200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,8,18]],"date-time":"2026-08-18T00:00:00Z","timestamp":1787011200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-045"}],"funder":[{"DOI":"10.13039\/na","name":"Center for Smart Infrastructure and Sustainability, SUNY Polytechnic Institute","doi-asserted-by":"publisher","award":["NA"],"award-info":[{"award-number":["NA"]}],"id":[{"id":"10.13039\/na","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026,9,14]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>Accurate prediction of molecular properties is fundamental to environmental chemistry, yet remains challenging when experimental data are limited. Multimodal fusion provides a promising strategy for integrating complementary molecular representations; however, the relative contributions of molecular representation, fusion strategy, and learning algorithm to the predictive accuracy and uncertainty remain poorly understood. Five molecular modalities (RDKit descriptors, Mol2Vec embeddings, graph neural network embeddings, SMILES representations, and MS2 fragmentation spectra) were evaluated by using early and late fusion strategies with four learning algorithms (LightGBM, RF, AttentiveFP, and DMPNN). Across 14 physicochemical properties, multimodal models exhibited modest numerical improvements over the best unimodal models, although these differences were generally not statistically significant. In contrast, uncertainty quantification revealed clearer distinctions among the modeling strategies. Multimodal integration significantly improved the alignment between prediction error and estimated uncertainty. The fusion strategy had a modest influence on epistemic uncertainty, with significant early versus late differences observed only for selected modality combinations, whereas meta-learner selection had the greatest effect on uncertainty calibration. Ablation, grouped SHAP, and RDKit descriptor reduction analyses showed that RDKit descriptors remained consistently informative despite substantial descriptor reduction, while Mol2Vec, SMILES, GNN embeddings, and MS2 contributed in a property-dependent and partially redundant manner. Computational cost increased substantially with multimodal complexity, whereas predictive accuracy exhibited diminishing returns, indicating that intermediate multimodal configurations often provided the most favorable balance among computational efficiency, predictive performance, and uncertainty reliability. Overall, the results demonstrate that successful multimodal learning depends on the coordinated selection of complementary molecular representations, fusion strategy, and learning algorithm rather than simply increasing the number of integrated modalities. Multimodal integration may provide particular value by improving the reliability of uncertainty estimation.<\/jats:p>","DOI":"10.1021\/acs.jcim.6c01878","type":"journal-article","created":{"date-parts":[[2026,8,18]],"date-time":"2026-08-18T15:14:54Z","timestamp":1787066094000},"page":"11106-11121","source":"Crossref","is-referenced-by-count":0,"title":["Unimodal vs Multimodal\nLearning: A Systematic Evaluation\nof Fusion Strategies and Model Design for Molecular Property Prediction\nand Uncertainty Quantification"],"prefix":"10.1021","volume":"66","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-2465-4020","authenticated-orcid":true,"given":"Joseph","family":"Wasswa","sequence":"first","affiliation":[{"name":"SUNY Polytechnic Institute , , 100 Seymour Road , , ,","place":["Utica, New York, United States, 13502"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2012-8197","authenticated-orcid":true,"given":"George William","family":"Kajjumba","sequence":"additional","affiliation":[{"name":"The Water Research Foundation , 1199 N. Fairfax Street, Ste. 900 , , ,","place":["Alexandria, Virginia, United States, 22314"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8450-4262","authenticated-orcid":true,"given":"Bharath","family":"Ramsundar","sequence":"additional","affiliation":[{"name":"Deep Forest Sciences , , ,","place":["Palo Alto, California, United States, 94306"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"316","published-online":{"date-parts":[[2026,8,18]]},"reference":[{"key":"2026091409082953700_cit1","doi-asserted-by":"publisher","first-page":"12741","DOI":"10.1021\/acs.est.1c01339","article-title":"Machine Learning:\nNew Ideas and Tools in Environmental Science and Engineering","volume":"55","author":"Zhong","year":"2021","journal-title":"Environ. Sci. Technol."},{"key":"2026091409082953700_cit2","doi-asserted-by":"publisher","first-page":"14392","DOI":"10.1021\/acssuschemeng.2c06310","article-title":"Data Science for the Transformation\nof Environmental and Chemical Research and Development","volume":"10","author":"Ren","year":"2022","journal-title":"ACS Sustainable Chem. Eng."},{"key":"2026091409082953700_cit3","doi-asserted-by":"publisher","first-page":"2124","DOI":"10.1021\/acs.est.1c06157","article-title":"Data-Driven\nMachine\nLearning in Environmental Pollution: Gains and Problems","volume":"56","author":"Liu","year":"2022","journal-title":"Environ. Sci. Technol."},{"key":"2026091409082953700_cit4","doi-asserted-by":"publisher","first-page":"149","DOI":"10.1016\/j.jpba.2017.07.044","article-title":"Quality Assurance Procedures\nfor Mass Spectrometry Untargeted Metabolomics: A Review","volume":"147","author":"Dudzik","year":"2018","journal-title":"J. Pharm. Biomed. Anal."},{"key":"2026091409082953700_cit5","doi-asserted-by":"publisher","first-page":"8736","DOI":"10.1021\/acs.chemrev.3c00189","article-title":"Machine Learning\nMethods for Small Data Challenges in Molecular Science","volume":"123","author":"Dou","year":"2023","journal-title":"Chem. Rev."},{"key":"2026091409082953700_cit6","doi-asserted-by":"publisher","first-page":"16690","DOI":"10.1021\/acs.est.4c03088","article-title":"Perspectives on Advancing\nMultimodal Learning in Environmental\nScience and Engineering Studies","volume":"58","author":"Liu","year":"2024","journal-title":"Environ. Sci.\nTechnol."},{"key":"2026091409082953700_cit7","doi-asserted-by":"publisher","first-page":"10286","DOI":"10.1021\/acs.est.4c13813","article-title":"Predicting\nBioconcentration\nFactors of Per- and Polyfluoroalkyl Substances Using a Directed Message\nPassing Neural Network with Multimodal Feature Fusion","volume":"59","author":"Yao","year":"2025","journal-title":"Environ. Sci. Technol."},{"key":"2026091409082953700_cit8","doi-asserted-by":"publisher","first-page":"18335","DOI":"10.1021\/acs.est.4c05022","article-title":"Tracing Microplastic\nAging Processes Using Multimodal Deep Learning: A Predictive Model\nfor Enhanced Traceability","volume":"58","author":"Li","year":"2024","journal-title":"Environ. Sci. Technol."},{"key":"2026091409082953700_cit9","doi-asserted-by":"publisher","first-page":"13857","DOI":"10.1021\/acs.est.5c04143","article-title":"Multimodal\nLearning-Assisted\nIdentification of Effluent Water Quality and Toxicity in Wastewater\nTreatment Plants","volume":"59","author":"Hu","year":"2025","journal-title":"Environ. Sci. Technol."},{"key":"2026091409082953700_cit10","doi-asserted-by":"publisher","first-page":"1944","DOI":"10.1021\/acs.est.3c08016","article-title":"Multimodal\nModel to Predict Tissue-to-Blood Partition Coefficients of Chemicals\nin Mammals and Fish","volume":"58","author":"Zhang","year":"2024","journal-title":"Environ. Sci. Technol."},{"key":"2026091409082953700_cit11","doi-asserted-by":"publisher","first-page":"7383","DOI":"10.1021\/acsestwater.5c00850","article-title":"PHYSPROPNET: A Benchmarking Study\nof Machine Learning\nModels for Physicochemical Property Prediction in Data-Limited Environmental\nResearch","volume":"5","author":"Wasswa","year":"2025","journal-title":"ACS EST Water"},{"key":"2026091409082953700_cit12","doi-asserted-by":"publisher","DOI":"10.1002\/qua.26870","article-title":"Molecular Representations for Machine\nLearning Applications\nin Chemistry","volume":"122","author":"Raghunathan","year":"2022","journal-title":"Int. J. Quantum Chem."},{"key":"2026091409082953700_cit13","doi-asserted-by":"publisher","DOI":"10.1002\/wcms.1603","article-title":"A Review of Molecular Representation\nin the Age of Machine Learning","volume":"12","author":"Wigh","year":"2022","journal-title":"WIREs Comput.\nMol. Sci."},{"key":"2026091409082953700_cit14","doi-asserted-by":"publisher","first-page":"8705","DOI":"10.1021\/acs.jmedchem.0c00385","article-title":"Learning\nMolecular Representations\nfor Medicinal Chemistry: Miniperspective","volume":"63","author":"Chuang","year":"2020","journal-title":"J.\nMed. Chem."},{"key":"2026091409082953700_cit15","doi-asserted-by":"publisher","first-page":"arXiv.2207.06010","DOI":"10.48550\/arXiv.2207.06010","article-title":"Does GNN\nPretraining Help Molecular Representation?","author":"Sun","year":"2022","journal-title":"arXiv"},{"key":"2026091409082953700_cit16","doi-asserted-by":"publisher","first-page":"279","DOI":"10.1038\/s42256-022-00447-x","article-title":"Molecular\nContrastive Learning of Representations via Graph Neural Networks","volume":"4","author":"Wang","year":"2022","journal-title":"Nat. Mach. Intell."},{"key":"2026091409082953700_cit17","doi-asserted-by":"publisher","DOI":"10.1002\/9783527613106","volume-title":"Handbook\nof Molecular Descriptors","author":"Todeschini","year":"2000","edition":"1"},{"key":"2026091409082953700_cit18","doi-asserted-by":"publisher","first-page":"125","DOI":"10.1021\/ci500535s","article-title":"How Experimental\nErrors Influence Drug Metabolism and\nPharmacokinetic QSAR\/QSPR Models","volume":"55","author":"Wenlock","year":"2015","journal-title":"J. Chem. Inf.\nModel."},{"key":"2026091409082953700_cit19","doi-asserted-by":"publisher","first-page":"2697","DOI":"10.1021\/acs.jcim.0c01489","article-title":"XGraphBoost: Extracting Graph Neural\nNetwork-Based Features for Improved\nMolecular Property Prediction","volume":"61","author":"Deng","year":"2021","journal-title":"J. Chem. Inf.\nModel."},{"key":"2026091409082953700_cit20","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1007\/3-540-45014-9_1","article-title":"Ensemble Methods in Machine Learning","volume-title":"Multiple Classifier Systems","author":"Dietterich","year":"2000"},{"key":"2026091409082953700_cit21","doi-asserted-by":"publisher","first-page":"bbab569","DOI":"10.1093\/bib\/bbab569","article-title":"Multimodal\nDeep Learning for Biomedical\nData Fusion: A Review","volume":"23","author":"Stahlschmidt","year":"2022","journal-title":"Briefings Bioinf."},{"key":"2026091409082953700_cit22","doi-asserted-by":"publisher","first-page":"nwaf495","DOI":"10.1093\/nsr\/nwaf495","article-title":"Multimodal Pre-Training\nModels of Molecular Representation for Drug Discovery","volume":"13","author":"Wang","year":"2026","journal-title":"Natl. Sci. Rev."},{"key":"2026091409082953700_cit23","doi-asserted-by":"publisher","first-page":"arXiv.2411.17040","DOI":"10.48550\/arXiv.2411.17040","article-title":"Multimodal Alignment\nand Fusion: A Survey","author":"Li","year":"2024","journal-title":"arXiv"},{"key":"2026091409082953700_cit24","doi-asserted-by":"publisher","first-page":"345","DOI":"10.1007\/s00530-010-0182-0","article-title":"Multimodal\nFusion for Multimedia Analysis: A Survey","volume":"16","author":"Atrey","year":"2010","journal-title":"Multimed.\nSyst."},{"issue":"24","key":"2026091409082953700_cit25","doi-asserted-by":"publisher","first-page":"13386","DOI":"10.1021\/acs.jcim.5c02322","article-title":"Attention-Based Multimodal Fusion\nand Variational Graph Learning for SM\u2013miRNA Association Prediction","volume":"65","author":"Tao","year":"2025","journal-title":"J. Chem. Inf. Model."},{"key":"2026091409082953700_cit26","doi-asserted-by":"publisher","first-page":"arXiv.2107.00135","DOI":"10.48550\/arXiv.2107.00135","article-title":"Attention Bottlenecks for Multimodal\nFusion","author":"Nagrani","year":"2022","journal-title":"arXiv"},{"key":"2026091409082953700_cit27","doi-asserted-by":"publisher","first-page":"3714","DOI":"10.1016\/j.csbj.2024.10.004","article-title":"Improving Compound-Protein\nInteraction Prediction by Focusing on Intra-Modality and Inter-Modality\nDynamics with a Multimodal Tensor Fusion Strategy","volume":"23","author":"Wang","year":"2024","journal-title":"Comput. Struct. Biotechnol. J."},{"key":"2026091409082953700_cit28","doi-asserted-by":"publisher","first-page":"102536","DOI":"10.1016\/j.inffus.2024.102536","article-title":"Deep Learning-Based\nMultimodal Biomedical Data Fusion: An Overview and Comparative Review","volume":"112","author":"Duan","year":"2024","journal-title":"Inf. Fusion"},{"issue":"14","key":"2026091409082953700_cit29","doi-asserted-by":"publisher","first-page":"6743","DOI":"10.1021\/acs.jctc.5c00605","article-title":"Fusing Domain Knowledge\nwith a Fine-Tuned Large Language Model for Enhanced Molecular Property\nPrediction","volume":"21","author":"Xie","year":"2025","journal-title":"J. Chem. Theory Comput."},{"key":"2026091409082953700_cit30","doi-asserted-by":"publisher","first-page":"1666","DOI":"10.1016\/j.csbj.2024.04.030","article-title":"Multimodal\nFused Deep Learning for Drug Property Prediction: Integrating Chemical\nLanguage and Molecular Graph","volume":"23","author":"Lu","year":"2024","journal-title":"Comput. Struct.\nBiotechnol. J."},{"key":"2026091409082953700_cit31","doi-asserted-by":"publisher","DOI":"10.1021\/acs.jctc.6c00695","article-title":"Integrating Conformational\nSampling and Siamese Learning to Predict Mutation-Induced Binding\nAffinity Changes in Abelson Tyrosine Kinase and Its Ligands","author":"Xie","year":"2026","journal-title":"J. Chem. Theory Comput."},{"key":"2026091409082953700_cit32","doi-asserted-by":"publisher","first-page":"851","DOI":"10.1021\/acs.jmedchem.4c03044","article-title":"Real-World Applications and Experiences\nof AI\/ML Deployment for Drug Discovery","volume":"68","author":"Pitt","year":"2025","journal-title":"J. Med.\nChem."},{"key":"2026091409082953700_cit33","doi-asserted-by":"publisher","first-page":"759","DOI":"10.1021\/acs.chemrestox.5c00033","article-title":"Machine Learning for Toxicity Prediction\nUsing Chemical Structures: Pillars for Success in the Real World","volume":"38","author":"Seal","year":"2025","journal-title":"Chem. Res. Toxicol."},{"key":"2026091409082953700_cit34","doi-asserted-by":"publisher","first-page":"arXiv.2501.03282","DOI":"10.48550\/arXiv.2501.03282","article-title":"From Aleatoric to Epistemic: Exploring\nUncertainty\nQuantification Techniques in Artificial Intelligence","author":"Wang","year":"2025","journal-title":"arXiv"},{"key":"2026091409082953700_cit35","doi-asserted-by":"publisher","first-page":"4012","DOI":"10.1021\/acs.jcim.3c00373","article-title":"Characterizing Uncertainty\nin Machine Learning for Chemistry","volume":"63","author":"Heid","year":"2023","journal-title":"J. Chem.\nInf. Model."},{"key":"2026091409082953700_cit36","doi-asserted-by":"publisher","first-page":"6585","DOI":"10.1021\/acs.jcim.5c00550","article-title":"Assessing\nUncertainty in Machine Learning for Polymer\nProperty Prediction: A Benchmark Study","volume":"65","author":"Tang","year":"2025","journal-title":"J. Chem.\nInf. Model."},{"key":"2026091409082953700_cit37","doi-asserted-by":"publisher","first-page":"3262","DOI":"10.1038\/s41467-025-58503-0","article-title":"Uncertainty Quantification\nwith Graph Neural Networks for Efficient\nMolecular Design","volume":"16","author":"Chen","year":"2025","journal-title":"Nat. Commun."},{"key":"2026091409082953700_cit38","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":"2026091409082953700_cit39","unstructured":"Landrum, G. A.\n          \n          RDKit: Open-Source\nCheminformatics Software. http:\/\/www.rdkit.org (accessed 04\n07, 2026)."},{"key":"2026091409082953700_cit40","volume-title":"Deep Learning for the Life Sciences:\nApplying Deep Learning to Genomics, Microscopy, Drug Discovery, and\nMore","author":"Ramsundar","year":"2019"},{"issue":"7","key":"2026091409082953700_cit41","doi-asserted-by":"publisher","first-page":"703","DOI":"10.1002\/jms.1777","article-title":"MassBank:\nA Public Repository for\nSharing Mass Spectral Data for Life Sciences","volume":"45","author":"Horai","year":"2010","journal-title":"J. Mass Spectrom."},{"issue":"1","key":"2026091409082953700_cit42","doi-asserted-by":"publisher","first-page":"177","DOI":"10.1021\/ci049714+","article-title":"ZINC\u2500A Free Database of Commercially Available\nCompounds for Virtual Screening","volume":"45","author":"Irwin","year":"2005","journal-title":"J. Chem. Inf.\nModel."},{"key":"2026091409082953700_cit43","doi-asserted-by":"publisher","first-page":"27","DOI":"10.1021\/acs.jcim.7b00616","article-title":"Mol2vec: Unsupervised\nMachine Learning\nApproach with Chemical Intuition","volume":"58","author":"Jaeger","year":"2018","journal-title":"J. Chem. Inf.\nModel."},{"key":"2026091409082953700_cit44","doi-asserted-by":"publisher","first-page":"8749","DOI":"10.1021\/acs.jmedchem.9b00959","article-title":"Pushing the Boundaries\nof Molecular Representation for Drug Discovery\nwith the Graph Attention Mechanism","volume":"63","author":"Xiong","year":"2020","journal-title":"J. Med.\nChem."},{"key":"2026091409082953700_cit45","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":"2026091409082953700_cit46","doi-asserted-by":"publisher","first-page":"2099","DOI":"10.1093\/bib\/bbz125","article-title":"A Novel Molecular\nRepresentation with BiGRU Neural Networks for Learning Atoms","volume":"21","author":"Lin","year":"2020","journal-title":"Briefings Bioinf."},{"key":"2026091409082953700_cit47","unstructured":"Ke, G.; Meng, Q.; Finley, T.; Wang, T.; Chen, W.; Ma, W.; Ye, Q.; Liu, T.-Y.\n          LightGBM: A Highly Efficient Gradient Boosting Decision Tree. In  Advances in Neural Information Processing Systems 30\n(NeurIPS 2017); Curran Associates, Inc., 2017; pp 3146\u20133154."},{"key":"2026091409082953700_cit48","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":"2026091409082953700_cit49","unstructured":"Lundberg, S. M.; Lee, S.-I.\n          A Unified Approach\nto Interpreting Model Predictions. In  Advances\nin Neural Information Processing Systems 30 (NeurIPS 2017); Curran Associates, Inc., 2017; pp 4765\u20134774."},{"key":"2026091409082953700_cit50","doi-asserted-by":"publisher","first-page":"423","DOI":"10.1109\/TPAMI.2018.2798607","article-title":"Multimodal Machine\nLearning: A Survey\nand Taxonomy","volume":"41","author":"Baltrus\u030caitis","year":"2019","journal-title":"IEEE Trans. Pattern Anal. Mach.\nIntell."},{"key":"2026091409082953700_cit51","doi-asserted-by":"publisher","first-page":"7516","DOI":"10.1021\/acs.jcim.5c01003","article-title":"Explainable\nGraph Neural Networks in Chemistry: Combining Attribution and Uncertainty\nQuantification","volume":"65","author":"Komissarov","year":"2025","journal-title":"J. Chem. Inf. Model."},{"key":"2026091409082953700_cit52","doi-asserted-by":"publisher","first-page":"2697","DOI":"10.1021\/acs.jcim.9b00975","article-title":"Evaluating\nScalable Uncertainty Estimation Methods for Deep Learning-Based Molecular\nProperty Prediction","volume":"60","author":"Scalia","year":"2020","journal-title":"J. Chem. Inf. Model."},{"key":"2026091409082953700_cit53","doi-asserted-by":"publisher","first-page":"6377","DOI":"10.1021\/acs.jcim.4c00904","article-title":"Spatially Resolved\nUncertainties for Machine Learning Potentials","volume":"64","author":"Heid","year":"2024","journal-title":"J. Chem. Inf. Model."},{"key":"2026091409082953700_cit54","doi-asserted-by":"publisher","first-page":"arXiv.2504.07260","DOI":"10.48550\/arXiv.2504.07260","article-title":"Quantifying Epistemic\nUncertainty in Absolute Pose Regression","author":"Zangeneh","year":"2025","journal-title":"arXiv"},{"key":"2026091409082953700_cit55","doi-asserted-by":"publisher","first-page":"025006","DOI":"10.1088\/2632-2153\/ab7e1a","article-title":"Methods for Comparing Uncertainty\nQuantifications for\nMaterial Property Predictions","volume":"1","author":"Tran","year":"2020","journal-title":"Mach. Learn.:\nSci. Technol."},{"key":"2026091409082953700_cit56","doi-asserted-by":"publisher","first-page":"121","DOI":"10.1186\/s13321-023-00790-0","article-title":"Uncertain\nof Uncertainties?\nA Comparison of Uncertainty Quantification Metrics for Chemical Data\nSets","volume":"15","author":"Rasmussen","year":"2023","journal-title":"J. Cheminf."},{"key":"2026091409082953700_cit57","doi-asserted-by":"publisher","first-page":"200","DOI":"10.1038\/s42004-025-01586-z","article-title":"Multimodal Fusion with Relational\nLearning for Molecular Property Prediction","volume":"8","author":"Zhou","year":"2025","journal-title":"Commun. Chem."},{"key":"2026091409082953700_cit58","doi-asserted-by":"publisher","first-page":"arXiv.2509.04606","DOI":"10.48550\/arXiv.2509.04606","article-title":"Sample-Efficient\nIntegration of New Modalities into Large Language Models","author":"I\u0307nce","year":"2025","journal-title":"arXiv"},{"key":"2026091409082953700_cit59","doi-asserted-by":"publisher","first-page":"579","DOI":"10.1007\/s11634-024-00587-5","article-title":"View Selection in Multi-View\nStacking: Choosing the Meta-Learner","volume":"19","author":"Van Loon","year":"2025","journal-title":"Adv. Data\nAnal. Classi."},{"key":"2026091409082953700_cit60","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3617827","article-title":"Dynamic\nMultimodal Fusion via Meta-Learning toward Micro-Video Recommendation","volume":"42","author":"Liu","year":"2024","journal-title":"ACM Trans. Inf. Syst."},{"issue":"2","key":"2026091409082953700_cit61","first-page":"65","article-title":"A Simple Sequentially\nRejective Multiple Test Procedure","volume":"6","author":"Holm","year":"1979","journal-title":"Scand. J.\nStat."},{"issue":"10","key":"2026091409082953700_cit62","doi-asserted-by":"publisher","first-page":"1254","DOI":"10.1136\/ard-2024-225537","article-title":"Adjustment\nof p Values for Multiple Hypotheses: Why, When, and\nHow","volume":"83","author":"Lydersen","year":"2024","journal-title":"Ann. Rheum. Dis."},{"key":"2026091409082953700_cit63","doi-asserted-by":"publisher","first-page":"arXiv.2501.10089","DOI":"10.48550\/arXiv.2501.10089","article-title":"Classifier\nEnsemble for Efficient Uncertainty Calibration of Deep Neural Networks\nfor Image Classification","author":"Schulze","year":"2025","journal-title":"arXiv"},{"key":"2026091409082953700_cit64","doi-asserted-by":"publisher","first-page":"10194","DOI":"10.1021\/acs.jcim.5c01873","article-title":"Approach and\nConsensus Framework for Possibly Carcinogenic\nChemicals","volume":"65","author":"Duy","year":"2025","journal-title":"J. Chem. Inf. Model."},{"key":"2026091409082953700_cit65","doi-asserted-by":"publisher","first-page":"104473","DOI":"10.1016\/j.cviu.2025.104473","article-title":"Multimodal vs. Unimodal\nApproaches\nto Uncertainty in 3D Image Segmentation under Distribution Shifts","volume":"260","author":"Javanbakhat","year":"2025","journal-title":"Comput. Vis. Image Underst."}],"container-title":["Journal of Chemical Information\nand Modeling"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/pubs.acs.org\/doi\/pdf\/10.1021\/acs.jcim.6c01878","content-type":"application\/pdf","content-version":"vor","intended-application":"unspecified"},{"URL":"https:\/\/pubs.acs.org\/jcisd8\/article-pdf\/66\/17\/11106\/66812378\/acs.jcim.6c01878.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/pubs.acs.org\/jcisd8\/article-pdf\/66\/17\/11106\/66812378\/acs.jcim.6c01878.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,14]],"date-time":"2026-09-14T13:23:23Z","timestamp":1789392203000},"score":1,"resource":{"primary":{"URL":"https:\/\/pubs.acs.org\/jcisd8\/article\/66\/17\/11106\/5272952\/Unimodal-vs-Multimodal-Learning-A-Systematic"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8,18]]},"references-count":65,"journal-issue":{"issue":"17","published-online":{"date-parts":[[2026,8,18]]},"published-print":{"date-parts":[[2026,9,14]]}},"URL":"https:\/\/doi.org\/10.1021\/acs.jcim.6c01878","relation":{},"ISSN":["1549-9596","1549-960X"],"issn-type":[{"value":"1549-9596","type":"print"},{"value":"1549-960X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,8,18]]}}}