{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,23]],"date-time":"2026-10-23T19:44:26Z","timestamp":1792784666922,"version":"4.5.0"},"reference-count":57,"publisher":"American Chemical Society (ACS)","issue":"19","license":[{"start":{"date-parts":[[2026,9,30]],"date-time":"2026-09-30T00:00:00Z","timestamp":1790726400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,9,30]],"date-time":"2026-09-30T00:00:00Z","timestamp":1790726400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,9,30]],"date-time":"2026-09-30T00:00:00Z","timestamp":1790726400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-045"}],"funder":[{"DOI":"10.13039\/na","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["22278053"],"award-info":[{"award-number":["22278053"]}],"id":[{"id":"10.13039\/na","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/na","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["22278268"],"award-info":[{"award-number":["22278268"]}],"id":[{"id":"10.13039\/na","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/na","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["22422801"],"award-info":[{"award-number":["22422801"]}],"id":[{"id":"10.13039\/na","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/na","name":"Fundamental and Interdisciplinary Disciplines Breakthrough Plan of the Ministry of Education of China","doi-asserted-by":"publisher","award":["JYB2025XDXIM414"],"award-info":[{"award-number":["JYB2025XDXIM414"]}],"id":[{"id":"10.13039\/na","id-type":"DOI","asserted-by":"publisher"},{"id":"https:\/\/ror.org\/03m01yf64","id-type":"ROR","asserted-by":"crossref"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026,10,12]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>Data-driven molecular property prediction is increasingly used to accelerate molecular discovery and computer-aided design. In flavor science, accurate prediction of molecular taste and odor attributes could facilitate the screening and rational design of candidate flavor molecules. However, this task remains challenging because structure\u2013flavor relationships are complex, single molecular representations may provide incomplete property-relevant information, and the available labels are highly imbalanced. To address these challenges, we implemented and evaluated Uni-Flavor, a multimodal prediction framework embedded in an integrated computational discovery workflow. Uni-Flavor combines three-dimensional molecular representations extracted from a LoRA-fine-tuned Uni-Mol2 model with stability-selected Mordred physicochemical descriptors through a dual-branch fusion architecture incorporating modality-specific projection, multiplicative late fusion, label-aware classification, and imbalance-aware optimization. Independent taste and odor models were trained separately under a common modeling and evaluation protocol, using curated datasets containing 17,202 taste molecules across six categories and 4,983 odor molecules across 138 labels. On held-out test sets, the taste model achieved an accuracy of 95.63% and an AUROC of 97.35%, an AUPRC of 82.05%, and an F1 score of 76.32%, whereas the corresponding values for the odor model were 96.03%, 89.97%, 38.00% and 36.94%. Branch-specific atom-level attribution analysis provided heuristic structural insights into the Uni-Mol2-derived component of the predictions by associating attribution patterns with specific molecular substructures. The trained models were subsequently used to screen approximately 670,000 natural products and coupled with a ScaffoldCAMD strategy for the constrained design of synthetic flavor candidates under chemical-validity, scaffold-assembly, and physicochemical-property constraints, followed by preliminary structural safety filtering. Molecular docking was further used to examine plausible receptor\u2013ligand interactions and provide preliminary receptor-level support for selected candidates. This work presents a common multimodal modeling strategy that integrates three-dimensional molecular representations with physicochemical descriptors and is instantiated independently for multilabel taste and odor prediction. Although developed for flavor-related prediction, evaluation on the SIDER dataset provides preliminary cross-task evidence that the multimodal integration strategy can be applied to another imbalanced multilabel molecular property problem; broader transferability to other property domains remains to be established.<\/jats:p>","DOI":"10.1021\/acs.jcim.6c02181","type":"journal-article","created":{"date-parts":[[2026,9,30]],"date-time":"2026-09-30T18:02:15Z","timestamp":1790791335000},"page":"12587-12603","source":"Crossref","is-referenced-by-count":0,"title":["A Multimodal Integration\nFramework for Taste and Odor\nPrediction and Flavor Molecule Discovery"],"prefix":"10.1021","volume":"66","author":[{"given":"Yingjie","family":"Song","sequence":"first","affiliation":[{"name":"Dalian University of Technology , , ,","place":["Dalian, China, 116024"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-5735-9343","authenticated-orcid":true,"given":"Kun","family":"Tang","sequence":"additional","affiliation":[{"name":"Dalian University of Technology , , ,","place":["Dalian, China, 116024"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Juntao","family":"Wang","sequence":"additional","affiliation":[{"name":"Dalian University of Technology , , ,","place":["Dalian, China, 116024"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Guang","family":"Luo","sequence":"additional","affiliation":[{"name":"Dalian University of Technology , , ,","place":["Dalian, China, 116024"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hanxiao","family":"Bao","sequence":"additional","affiliation":[{"name":"Dalian University of Technology , , ,","place":["Dalian, China, 116024"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jingyuan","family":"Sun","sequence":"additional","affiliation":[{"name":"Dalian University of Technology , , ,","place":["Dalian, China, 116024"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3879-1827","authenticated-orcid":true,"given":"Qilei","family":"Liu","sequence":"additional","affiliation":[{"name":"Dalian University of Technology , , ,","place":["Dalian, China, 116024"]},{"name":"Ningbo Institute of Dalian University of Technology , No. 26 Yucai Road , Jiangbei, ,","place":["Ningbo, China, 315032"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7667-4835","authenticated-orcid":true,"given":"Jian","family":"Du","sequence":"additional","affiliation":[{"name":"Dalian University of Technology , , ,","place":["Dalian, China, 116024"]},{"name":"Ningbo Institute of Dalian University of Technology , No. 26 Yucai Road , Jiangbei, ,","place":["Ningbo, China, 315032"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-5007-8788","authenticated-orcid":true,"given":"Jing","family":"Hu","sequence":"additional","affiliation":[{"name":"East China University of Science and Technology , , 130 Meilong Road , ,","place":["Shanghai, China, 200237"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7519-2858","authenticated-orcid":true,"given":"Lei","family":"Zhang","sequence":"additional","affiliation":[{"name":"Dalian University of Technology , , ,","place":["Dalian, China, 116024"]},{"name":"Ningbo Institute of Dalian University of Technology , No. 26 Yucai Road , Jiangbei, ,","place":["Ningbo, China, 315032"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"316","published-online":{"date-parts":[[2026,9,30]]},"reference":[{"issue":"9","key":"2026101208074696800_cit1","doi-asserted-by":"publisher","first-page":"1507","DOI":"10.1111\/j.1365-2621.2008.01780.x","article-title":"Application\nof sensory evaluation in food research","volume":"43","author":"Kemp","year":"2008","journal-title":"Int.\nJ. Food Sci. Technol."},{"key":"2026101208074696800_cit2","doi-asserted-by":"publisher","first-page":"115100","DOI":"10.1016\/j.foodres.2024.115100","article-title":"Flavor\nEngineering: A comprehensive\nreview of biological foundations, AI integration, industrial development,\nand socio-cultural dynamics","volume":"196","author":"Queiroz","year":"2024","journal-title":"Food Res. Int."},{"key":"2026101208074696800_cit3","doi-asserted-by":"publisher","first-page":"113036","DOI":"10.1016\/j.foodres.2023.113036","article-title":"Classification-based machine learning\napproaches to\npredict the taste of molecules: A review","volume":"171","author":"Rojas","year":"2023","journal-title":"Food\nRes. Int."},{"key":"2026101208074696800_cit4","doi-asserted-by":"publisher","first-page":"104794","DOI":"10.1016\/j.tifs.2024.104794","article-title":"Machine learning and\nflavoromics-based research strategies for determining the characteristic\nflavor of food: A review","volume":"154","author":"Cai","year":"2024","journal-title":"Trends Food Sci. Technol."},{"issue":"4","key":"2026101208074696800_cit5","doi-asserted-by":"publisher","first-page":"416","DOI":"10.1002\/jps.2600690414","article-title":"Molecular\nstructure influencing either a sweet or bitter taste among aldoximes","volume":"69","author":"Kier","year":"1980","journal-title":"J. Pharm. Sci."},{"issue":"8","key":"2026101208074696800_cit6","doi-asserted-by":"publisher","first-page":"933","DOI":"10.1002\/jps.2600700826","article-title":"Structure-activity\nstudies on sulfamate sweeteners\nII: semiquantitative structure-taste relationship for sulfamate (RNHSO-3)\nsweeteners-the role of R","volume":"70","author":"Spillane","year":"1981","journal-title":"J. Pharm. Sci."},{"issue":"6","key":"2026101208074696800_cit7","doi-asserted-by":"publisher","first-page":"906","DOI":"10.1021\/jm00156a006","article-title":"Structure-taste correlation\nof L-aspartyl dipeptides using SIMCA method","volume":"29","author":"Miyashita","year":"1986","journal-title":"J. Med. Chem."},{"issue":"6","key":"2026101208074696800_cit8","doi-asserted-by":"publisher","first-page":"636","DOI":"10.1002\/jcc.540090609","article-title":"Computer assisted structure\u2013taste studies on\nsulfamates by pattern recognition method using graph theoretical invariants","volume":"9","author":"Okuyama","year":"1988","journal-title":"J. Comput. Chem."},{"issue":"3","key":"2026101208074696800_cit9","doi-asserted-by":"publisher","first-page":"66","DOI":"10.1007\/s00214-016-1812-1","article-title":"Quantitative\nstructure\u2013activity relationships\nto predict sweet and non-sweet tastes","volume":"135","author":"Rojas","year":"2016","journal-title":"Theor.\nChem. Acc."},{"issue":"1","key":"2026101208074696800_cit10","doi-asserted-by":"publisher","first-page":"78","DOI":"10.4018\/IJQSPR.2016010104","article-title":"A New QSPR Study on Relative Sweetness","volume":"1","author":"Rojas","year":"2016","journal-title":"Int. J. Quant. Struct.-Prop. Relat."},{"key":"2026101208074696800_cit11","doi-asserted-by":"publisher","first-page":"2270","DOI":"10.1016\/j.crfs.2022.11.014","article-title":"Informed classification\nof sweeteners\/bitterants compounds\nvia explainable machine learning","volume":"5","author":"Maroni","year":"2022","journal-title":"Curr. Res.\nFood Sci."},{"issue":"12","key":"2026101208074696800_cit12","doi-asserted-by":"publisher","first-page":"6666","DOI":"10.1021\/acs.jcim.0c00707","article-title":"iUmami-SCM:\nA Novel Sequence-Based Predictor for Prediction and Analysis of Umami\nPeptides Using a Scoring Card Method with Propensity Scores of Dipeptides","volume":"60","author":"Charoenkwan","year":"2020","journal-title":"J. Chem. Inf. Model."},{"issue":"1","key":"2026101208074696800_cit13","doi-asserted-by":"publisher","first-page":"23450","DOI":"10.1038\/srep23450","article-title":"BitterX: a\ntool for understanding bitter taste in humans","volume":"6","author":"Huang","year":"2016","journal-title":"Sci. Rep."},{"issue":"12","key":"2026101208074696800_cit14","doi-asserted-by":"publisher","DOI":"10.1002\/minf.202300146","article-title":"Classification of tastants:\nA deep learning based approach","volume":"42","author":"Dutta","year":"2023","journal-title":"Mol. Inform."},{"issue":"1","key":"2026101208074696800_cit15","doi-asserted-by":"publisher","first-page":"47","DOI":"10.1038\/s41538-024-00287-6","article-title":"Predicting multiple taste sensations\nwith a multiobjective machine learning method","volume":"8","author":"Androutsos","year":"2024","journal-title":"Npj Sci. Food"},{"issue":"1","key":"2026101208074696800_cit16","doi-asserted-by":"publisher","first-page":"122","DOI":"10.1038\/s41538-025-00474-z","article-title":"A chemical\nlanguage model for molecular taste prediction","volume":"9","author":"Zimmermann","year":"2025","journal-title":"Npj Sci. Food"},{"issue":"8","key":"2026101208074696800_cit17","doi-asserted-by":"publisher","first-page":"3201","DOI":"10.1021\/cr950068a","article-title":"Structure\u2013odor\nrelationships","volume":"96","author":"Rossiter","year":"1996","journal-title":"Chem. Rev."},{"issue":"38","key":"2026101208074696800_cit18","doi-asserted-by":"publisher","first-page":"6254","DOI":"10.1002\/anie.200600782","article-title":"On the\nunpredictability of odor","volume":"45","author":"Sell","year":"2006","journal-title":"Angew. Chem., Int.\nEd."},{"key":"2026101208074696800_cit19","doi-asserted-by":"publisher","first-page":"104700","DOI":"10.1016\/j.tifs.2024.104700","article-title":"Bridging odorants and olfactory perception\nthrough machine learning: A review","volume":"153","author":"Zhong","year":"2024","journal-title":"Trends Food\nSci. Technol."},{"issue":"22","key":"2026101208074696800_cit20","doi-asserted-by":"publisher","first-page":"11999","DOI":"10.1021\/acs.analchem.7b02389","article-title":"Machine-Learning-Based Olfactometer:\nPrediction of Odor Perception from Physicochemical Features of Odorant\nMolecules","volume":"89","author":"Shang","year":"2017","journal-title":"Anal. Chem."},{"issue":"2","key":"2026101208074696800_cit21","doi-asserted-by":"publisher","first-page":"676","DOI":"10.1021\/acs.jcim.0c01288","article-title":"SMILES to Smell:\nDecoding the Structure-Odor Relationship of Chemical Compounds Using\nthe Deep Neural Network Approach","volume":"61","author":"Sharma","year":"2021","journal-title":"J. Chem. Inf.\nModel."},{"key":"2026101208074696800_cit22","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1910.10685","article-title":"Machine learning\nfor scent: Learning generalizable perceptual representations of small\nmolecules","author":"Sanchez-Lengeling","year":"2019","journal-title":"arXiv"},{"issue":"6661","key":"2026101208074696800_cit23","doi-asserted-by":"publisher","first-page":"999","DOI":"10.1126\/science.ade4401","article-title":"A principal\nodor map unifies diverse tasks in olfactory\nperception","volume":"381","author":"Lee","year":"2023","journal-title":"Science"},{"issue":"2","key":"2026101208074696800_cit24","doi-asserted-by":"publisher","first-page":"268","DOI":"10.1021\/acscentsci.7b00572","article-title":"Automatic\nChemical Design Using a Data-Driven Continuous Representation of Molecules","volume":"4","author":"Gomez-Bombarelli","year":"2018","journal-title":"ACS Cent. Sci."},{"issue":"1","key":"2026101208074696800_cit25","doi-asserted-by":"publisher","first-page":"10","DOI":"10.1038\/s41467-019-13807-w","article-title":"De novo generation\nof hit-like molecules from gene expression signatures using artificial\nintelligence","volume":"11","author":"Mendez-Lucio","year":"2020","journal-title":"Nat. Commun."},{"issue":"12","key":"2026101208074696800_cit26","doi-asserted-by":"publisher","first-page":"10875","DOI":"10.1021\/acsomega.2c07176","article-title":"Generating Flavor\nMolecules Using Scientific Machine Learning","volume":"8","author":"Queiroz","year":"2023","journal-title":"ACS Omega"},{"issue":"23","key":"2026101208074696800_cit27","doi-asserted-by":"publisher","first-page":"9062","DOI":"10.1021\/acs.iecr.3c00722","article-title":"Transfer\nLearning\nApproach to Develop Natural Molecules with Specific Flavor Requirements","volume":"62","author":"Queiroz","year":"2023","journal-title":"Ind. Eng. Chem. Res."},{"issue":"10","key":"2026101208074696800_cit28","doi-asserted-by":"publisher","first-page":"4818","DOI":"10.1021\/acs.jcim.5c00209","article-title":"Navigating the Fragrance\nSpace Using Graph Generative Models and Predicting Odors","volume":"65","author":"Sharma","year":"2025","journal-title":"J. Chem. Inf. Model."},{"issue":"9","key":"2026101208074696800_cit29","doi-asserted-by":"publisher","DOI":"10.1002\/aic.17748","article-title":"De novo drug\ndesign framework based on mathematical programming method and deep\nlearning model","volume":"68","author":"Zhao","year":"2022","journal-title":"AIChE J."},{"issue":"4","key":"2026101208074696800_cit30","doi-asserted-by":"publisher","first-page":"2140","DOI":"10.1021\/acs.jcim.5c02871","article-title":"Accelerating\nSiloxane-Based Ionizable Lipid Design for LNPs with Data-Efficient\nKolmogorov-Arnold Networks","volume":"66","author":"Zhao","year":"2026","journal-title":"J. Chem. Inf. Model."},{"key":"2026101208074696800_cit31","doi-asserted-by":"publisher","first-page":"104423","DOI":"10.1016\/j.fbio.2024.104423","article-title":"Unraveling\nthe characteristic aroma compounds in Longjing tea and their interaction\nmechanisms with S-curve and broad-spectrum olfactory receptors using\nmolecular docking","volume":"60","author":"Xiao","year":"2024","journal-title":"Food Biosci."},{"issue":"Pt 4","key":"2026101208074696800_cit32","doi-asserted-by":"publisher","first-page":"146125","DOI":"10.1016\/j.foodchem.2025.146125","article-title":"Characterization of\nthe key aroma-active\ncompounds causing the Douchi aroma in high-temperature Daqu via integrated\nmolecular sensory science, metabolomics, and molecular docking","volume":"493","author":"He","year":"2025","journal-title":"Food Chem."},{"key":"2026101208074696800_cit33","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2406.14969","article-title":"Uni-mol2: Exploring molecular pretraining model at\nscale","author":"Ji","year":"2024","journal-title":"arXiv"},{"issue":"1","key":"2026101208074696800_cit34","doi-asserted-by":"publisher","first-page":"4","DOI":"10.1186\/s13321-018-0258-y","article-title":"Mordred: a molecular\ndescriptor calculator","volume":"10","author":"Moriwaki","year":"2018","journal-title":"J. Cheminf."},{"issue":"2","key":"2026101208074696800_cit35","doi-asserted-by":"publisher","first-page":"455","DOI":"10.1002\/jcc.21334","article-title":"AutoDock Vina: improving\nthe speed and accuracy of\ndocking with a new scoring function, efficient optimization, and multithreading","volume":"31","author":"Trott","year":"2010","journal-title":"J. Comput. Chem."},{"issue":"11","key":"2026101208074696800_cit36","doi-asserted-by":"publisher","first-page":"7076","DOI":"10.1111\/1750-3841.17298","article-title":"FlavorDB2: An updated database of\nflavor molecules","volume":"89","author":"Goel","year":"2024","journal-title":"J. Food Sci."},{"issue":"D1","key":"2026101208074696800_cit37","doi-asserted-by":"publisher","first-page":"D1645","DOI":"10.1093\/nar\/gkae1044","article-title":"BitterDB: 2024 update\non bitter ligands and taste receptors","volume":"53","author":"Ziaikin","year":"2025","journal-title":"Nucleic\nAcids Res."},{"key":"2026101208074696800_cit38","doi-asserted-by":"publisher","first-page":"100090","DOI":"10.1016\/j.fochms.2022.100090","article-title":"ChemTastesDB: A curated database\nof molecular tastants","volume":"4","author":"Rojas","year":"2022","journal-title":"Food Chem."},{"key":"2026101208074696800_cit39","doi-asserted-by":"publisher","first-page":"1421","DOI":"10.1016\/j.foodchem.2016.10.145","article-title":"Sweetness prediction of natural compounds","volume":"221","author":"Cheron","year":"2017","journal-title":"Food Chem."},{"issue":"1","key":"2026101208074696800_cit40","doi-asserted-by":"publisher","first-page":"7155","DOI":"10.1038\/s41598-019-43664-y","article-title":"Building\nmachine learning models\nfor predicting the bitter and sweet taste of small molecules","volume":"9","author":"Tuwani","year":"2019","journal-title":"Sci. Rep."},{"issue":"23","key":"2026101208074696800_cit41","doi-asserted-by":"publisher","first-page":"13124","DOI":"10.3390\/ijms222313124","article-title":"UMPred-FRL: A New Approach for Accurate\nPrediction\nof Umami Peptides Using Feature Representation Learning","volume":"22","author":"Charoenkwan","year":"2021","journal-title":"Int. J. Mol. Sci."},{"issue":"18","key":"2026101208074696800_cit42","doi-asserted-by":"publisher","first-page":"6789","DOI":"10.1021\/acs.jafc.3c00909","article-title":"Data-Driven Elucidation of Flavor Chemistry","volume":"71","author":"Kou","year":"2023","journal-title":"J. Agric. Food Chem."},{"key":"2026101208074696800_cit43","doi-asserted-by":"publisher","first-page":"751712","DOI":"10.3389\/fphar.2021.751712","article-title":"PlantMolecularTasteDB:\nA Database of Taste Active Phytochemicals","volume":"12","author":"Gradinaru","year":"2022","journal-title":"Front.\nPharmacol."},{"issue":"4","key":"2026101208074696800_cit44","doi-asserted-by":"publisher","first-page":"2044","DOI":"10.1021\/acs.jcim.0c00025","article-title":"Improving Conformer\nGeneration for Small Rings and Macrocycles Based on Distance Geometry\nand Experimental Torsional-Angle Preferences","volume":"60","author":"Wang","year":"2020","journal-title":"J. Chem. Inf. Model."},{"issue":"4","key":"2026101208074696800_cit45","doi-asserted-by":"publisher","first-page":"417","DOI":"10.1111\/j.1467-9868.2010.00740.x","article-title":"Stability\nselection Series B (Statistical Methodology","volume":"72","author":"Meinshausen","year":"2010","journal-title":"J. R. Stat. Soc."},{"key":"2026101208074696800_cit46","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2009.14119","article-title":"Asymmetric\nloss for multi-label\nclassification","author":"Ben-Baruch","year":"2020","journal-title":"arXiv"},{"issue":"D1","key":"2026101208074696800_cit47","doi-asserted-by":"publisher","first-page":"D634","DOI":"10.1093\/nar\/gkae1063","article-title":"COCONUT 2.0:\na comprehensive overhaul\nand curation of the collection of open natural products database","volume":"53","author":"Chandrasekhar","year":"2025","journal-title":"Nucleic Acids Res."},{"issue":"201","key":"2026101208074696800_cit48","first-page":"1","article-title":"Understanding\nhow dimension reduction tools work: an empirical approach to deciphering\nt-SNE, UMAP, TriMAP, and PaCMAP for data visualization","volume":"22","author":"Wang","year":"2021","journal-title":"J. Mach. Learn. Res."},{"issue":"6","key":"2026101208074696800_cit49","doi-asserted-by":"publisher","first-page":"1336","DOI":"10.1109\/TKDE.2012.51","article-title":"Nonnegative matrix factorization: A comprehensive review","volume":"25","author":"Wang","year":"2013","journal-title":"IEEE Trans. Knowl. Data Eng."},{"issue":"4","key":"2026101208074696800_cit50","doi-asserted-by":"publisher","first-page":"FSO149","DOI":"10.4155\/fsoa-2016-0058","article-title":"Analog series-based\nscaffolds: computational design and exploration of a new type of molecular\nscaffolds for medicinal chemistry","volume":"2","author":"Dimova","year":"2016","journal-title":"Future Sci.\nOA"},{"issue":"3","key":"2026101208074696800_cit51","doi-asserted-by":"publisher","first-page":"1743","DOI":"10.1007\/s11030-023-10684-w","article-title":"Network pharmacology,\nmolecular docking, and molecular dynamics simulation to elucidate\nthe mechanism of anti-aging action of Tinospora cordifolia","volume":"28","author":"Bisht","year":"2024","journal-title":"Mol. Divers."},{"issue":"D1","key":"2026101208074696800_cit52","doi-asserted-by":"publisher","first-page":"D437","DOI":"10.1093\/nar\/gkaa1038","article-title":"RCSB Protein\nData Bank: powerful new tools for exploring 3D structures of biological\nmacromolecules for basic and applied research and education in fundamental\nbiology, biomedicine, biotechnology, bioengineering and energy sciences","volume":"49","author":"Burley","year":"2021","journal-title":"Nucleic Acids Res."},{"issue":"10","key":"2026101208074696800_cit53","doi-asserted-by":"publisher","first-page":"2778","DOI":"10.1021\/ci200227u","article-title":"LigPlot+:\nmultiple ligand\u2013protein interaction\ndiagrams for drug discovery","volume":"51","author":"Laskowski","year":"2011","journal-title":"J. Chem. Inf. Model."},{"key":"2026101208074696800_cit54","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1703.01365","article-title":"Axiomatic Attribution for Deep\nNetworks","author":"Sundararajan","year":"2017","journal-title":"arXiv"},{"issue":"1","key":"2026101208074696800_cit55","doi-asserted-by":"publisher","first-page":"9","DOI":"10.1021\/acs.jcim.3c01250","article-title":"Chemprop:\nA Machine Learning Package for Chemical Property Prediction","volume":"64","author":"Heid","year":"2024","journal-title":"J. Chem. Inf. Model."},{"issue":"12","key":"2026101208074696800_cit56","doi-asserted-by":"publisher","first-page":"1256","DOI":"10.1038\/s42256-022-00580-7","article-title":"Large-scale\nchemical language representations capture molecular structure\nand properties","volume":"4","author":"Ross","year":"2022","journal-title":"Nat. Mach. Intell."},{"issue":"1","key":"2026101208074696800_cit57","doi-asserted-by":"publisher","DOI":"10.1111\/1541-4337.70068","article-title":"Artificial intelligence\nand food flavor: How AI models are shaping the future and revolutionary\ntechnologies for flavor food development","volume":"24","author":"Cui","year":"2025","journal-title":"Compr.\nRev. Food Sci. Food Saf."}],"container-title":["Journal of Chemical Information\nand Modeling"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/pubs.acs.org\/doi\/pdf\/10.1021\/acs.jcim.6c02181","content-type":"application\/pdf","content-version":"vor","intended-application":"unspecified"},{"URL":"https:\/\/pubs.acs.org\/jcisd8\/article-pdf\/66\/19\/12587\/68715766\/acs.jcim.6c02181.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/pubs.acs.org\/jcisd8\/article-pdf\/66\/19\/12587\/68715766\/acs.jcim.6c02181.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,10,12]],"date-time":"2026-10-12T12:15:08Z","timestamp":1791807308000},"score":1,"resource":{"primary":{"URL":"https:\/\/pubs.acs.org\/jcisd8\/article\/66\/19\/12587\/5442651\/A-Multimodal-Integration-Framework-for-Taste-and"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,9,30]]},"references-count":57,"journal-issue":{"issue":"19","published-online":{"date-parts":[[2026,9,30]]},"published-print":{"date-parts":[[2026,10,12]]}},"URL":"https:\/\/doi.org\/10.1021\/acs.jcim.6c02181","relation":{},"ISSN":["1549-9596","1549-960X"],"issn-type":[{"value":"1549-9596","type":"print"},{"value":"1549-960X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,9,30]]}}}