{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,11,4]],"date-time":"2026-11-04T10:36:00Z","timestamp":1793788560612,"version":"4.6.1"},"reference-count":58,"publisher":"American Chemical Society (ACS)","issue":"17","license":[{"start":{"date-parts":[[2026,8,7]],"date-time":"2026-08-07T00:00:00Z","timestamp":1786060800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,8,7]],"date-time":"2026-08-07T00:00:00Z","timestamp":1786060800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,8,7]],"date-time":"2026-08-07T00:00:00Z","timestamp":1786060800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-045"}],"funder":[{"DOI":"10.13039\/100006192","name":"Advanced Scientific Computing Research","doi-asserted-by":"publisher","award":["DE-SC0023112"],"award-info":[{"award-number":["DE-SC0023112"]}],"id":[{"id":"10.13039\/100006192","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100014600","name":"MathWorks","doi-asserted-by":"publisher","award":["NA"],"award-info":[{"award-number":["NA"]}],"id":[{"id":"10.13039\/100014600","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/na","name":"Machine Learning for Pharmaceutical Discovery and Synthesis Consortium","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>Fast and accurate data-driven prediction of molecular properties is pivotal to scientific advancements across myriad chemical domains. Deep learning methods have recently garnered much attention, despite their inability to outperform classical machine learning methods when tested on practical, real-world benchmarks with limited training data. This study seeks to bridge this gap by introducing a new avenue for foundation model pretraining. We propose pretraining on low-noise, calculable molecular descriptors via supervised learning to obtain rich, highly transferable molecular representations. We demonstrate this strategy with CheMeleon, a O(10M) parameter foundation model that enables directed message-passing neural networks to finally exceed the performance of classical methods in the low-data regime. We evaluate on 58 benchmark data sets spanning a range of properties relevant to small-molecule drug discovery, sourced from the industry-led Polaris benchmarking initiative. Rigorous statistical comparisons show that CheMeleon outperforms classical baselines like Random Forest on molecular fingerprints and descriptors, as well as existing foundation models. We open-source the CheMeleon model and the pretraining framework to encourage adoption and extension of this pretraining strategy across chemical sciences.<\/jats:p>","DOI":"10.1021\/acs.jcim.6c01546","type":"journal-article","created":{"date-parts":[[2026,8,7]],"date-time":"2026-08-07T19:01:39Z","timestamp":1786129299000},"page":"10692-10701","source":"Crossref","is-referenced-by-count":5,"title":["Deep Learning Foundation\nModels for Low-Data Regimes\nfrom Classical Molecular Descriptors"],"prefix":"10.1021","volume":"66","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-0657-9426","authenticated-orcid":true,"given":"Jackson W.","family":"Burns","sequence":"first","affiliation":[{"name":"Massachusetts Institute of Technology , , 77 Massachusetts Avenue , , ,","place":["Cambridge, Massachusetts, United States, 02139"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9549-7547","authenticated-orcid":true,"given":"Akshat Shirish","family":"Zalte","sequence":"additional","affiliation":[{"name":"Massachusetts Institute of Technology , , 77 Massachusetts Avenue , , ,","place":["Cambridge, Massachusetts, United States, 02139"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Charlles R. A.","family":"Abreu","sequence":"additional","affiliation":[{"name":"Massachusetts Institute of Technology , , 77 Massachusetts Avenue , , ,","place":["Cambridge, Massachusetts, United States, 02139"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jochen","family":"Sieg","sequence":"additional","affiliation":[{"name":"BASF SE , ,","place":["Ludwigshafen, Germany, 67056"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3803-851X","authenticated-orcid":true,"given":"Christian","family":"Feldmann","sequence":"additional","affiliation":[{"name":"BASF SE , ,","place":["Ludwigshafen, Germany, 67056"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3214-1487","authenticated-orcid":true,"given":"Miriam","family":"Mathea","sequence":"additional","affiliation":[{"name":"BASF SE , ,","place":["Ludwigshafen, Germany, 67056"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2603-9694","authenticated-orcid":true,"given":"William H.","family":"Green","sequence":"additional","affiliation":[{"name":"Massachusetts Institute of Technology , , 77 Massachusetts Avenue , , ,","place":["Cambridge, Massachusetts, United States, 02139"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"316","published-online":{"date-parts":[[2026,8,7]]},"reference":[{"key":"2026091409075076600_cit1","doi-asserted-by":"publisher","first-page":"107","DOI":"10.1021\/c160017a018","article-title":"The Generation\nof a Unique Machine Description for Chemical Structures-A Technique\nDeveloped at Chemical Abstracts Service","volume":"5","author":"Morgan","year":"1965","journal-title":"J.\nChem. Doc."},{"key":"2026091409075076600_cit2","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."},{"key":"2026091409075076600_cit3","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2306.17702","article-title":"Why Deep Models Often cannot Beat Non-deep Counterparts\non Molecular Property Prediction?","author":"Xia","year":"2023","journal-title":"arXiv"},{"key":"2026091409075076600_cit4","doi-asserted-by":"publisher","first-page":"73","DOI":"10.1186\/s13321-025-01013-4","article-title":"Generalizable, fast,\nand accurate DeepQSPR with fastprop","volume":"17","author":"Burns","year":"2025","journal-title":"J. Cheminf."},{"key":"2026091409075076600_cit5","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."},{"issue":"4","key":"2026091409075076600_cit6","doi-asserted-by":"publisher","first-page":"688","DOI":"10.1016\/j.cell.2020.01.021","article-title":"A Deep Learning Approach to Antibiotic\nDiscovery","volume":"180","author":"Stokes","year":"2020","journal-title":"Cell"},{"key":"2026091409075076600_cit7","doi-asserted-by":"publisher","first-page":"1152","DOI":"10.1039\/D1SC05677H","article-title":"Multi-fidelity\nprediction\nof molecular optical peaks with deep learning","volume":"13","author":"Greenman","year":"2022","journal-title":"Chem. Sci."},{"key":"2026091409075076600_cit8","doi-asserted-by":"publisher","first-page":"btae416","DOI":"10.1093\/bioinformatics\/btae416","article-title":"ADMET-AI: a machine\nlearning ADMET platform for evaluation of large-scale chemical libraries","volume":"40","author":"Swanson","year":"2024","journal-title":"Bioinformatics"},{"key":"2026091409075076600_cit9","doi-asserted-by":"publisher","first-page":"7497","DOI":"10.1038\/s41467-025-62717-7","article-title":"Data-driven organic\nsolubility prediction at the limit of aleatoric uncertainty","volume":"16","author":"Attia","year":"2025","journal-title":"Nat. Commun."},{"key":"2026091409075076600_cit10","doi-asserted-by":"publisher","first-page":"10832","DOI":"10.1021\/acs.jcim.5c00495","article-title":"RIGR: Resonance-Invariant\nGraph Representation for Molecular Property Prediction","volume":"65","author":"Zalte","year":"2025","journal-title":"J. Chem. Inf. Model."},{"key":"2026091409075076600_cit11","doi-asserted-by":"publisher","first-page":"45057","DOI":"10.1021\/jacs.5c13746","article-title":"Accurately Predicting Solubility\nCurves via a Thermodynamic Cycle, Machine Learning, and Solvent Ensembles","volume":"147","author":"Al Ibrahim","year":"2025","journal-title":"J. Am. Chem. Soc."},{"key":"2026091409075076600_cit12","doi-asserted-by":"publisher","first-page":"530","DOI":"10.1021\/acsengineeringau.5c00027","article-title":"Directed Message\nPassing Neural Networks for Accurate Prediction of Polymer\u2013Solvent\nInteraction Parameters","volume":"5","author":"Liao","year":"2025","journal-title":"ACS Eng. Au"},{"key":"2026091409075076600_cit13","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2005.14165","article-title":"Language\nModels are Few-Shot\nLearners","author":"Brown","year":"2020","journal-title":"arXiv"},{"key":"2026091409075076600_cit14","doi-asserted-by":"publisher","first-page":"1499","DOI":"10.1021\/jacsau.4c01160","article-title":"A Perspective\non Foundation Models\nin Chemistry","volume":"5","author":"Choi","year":"2025","journal-title":"JACS Au"},{"key":"2026091409075076600_cit15","doi-asserted-by":"publisher","first-page":"045024","DOI":"10.1088\/2632-2153\/aba947","article-title":"Self-referencing\nembedded strings (SELFIES): A 100%\nrobust molecular string representation","volume":"1","author":"Krenn","year":"2020","journal-title":"Mach.\nLearn. Sci. Technol."},{"key":"2026091409075076600_cit16","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2010.09885","article-title":"ChemBERTa: Large-Scale\nSelf-Supervised Pretraining for Molecular Property Prediction","author":"Chithrananda","year":"2020","journal-title":"arXiv"},{"key":"2026091409075076600_cit17","doi-asserted-by":"publisher","first-page":"1256","DOI":"10.1038\/s42256-022-00580-7","article-title":"Large-scale chemical\nlanguage representations capture molecular structure\nand properties","volume":"4","author":"Ross","year":"2022","journal-title":"Nat. Mach. Intell."},{"key":"2026091409075076600_cit18","doi-asserted-by":"publisher","first-page":"279","DOI":"10.1038\/s42256-022-00447-x","article-title":"Molecular contrastive\nlearning of representations via graph neural networks","volume":"4","author":"Wang","year":"2022","journal-title":"Nat. Mach. Intell."},{"key":"2026091409075076600_cit19","article-title":"Strategies for Pre-training Graph Neural Networks","volume-title":"International Conference on Learning Representations","author":"Hu","year":"2020"},{"key":"2026091409075076600_cit20","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2007.02835","article-title":"Self-Supervised\nGraph Transformer on Large-Scale Molecular Data","author":"Rong","year":"2020","journal-title":"arXiv"},{"key":"2026091409075076600_cit21","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2510.12719","article-title":"Multitask finetuning and acceleration\nof chemical pretrained models for small molecule drug property prediction","author":"Adrian","year":"2025","journal-title":"arXiv"},{"key":"2026091409075076600_cit22","doi-asserted-by":"publisher","first-page":"9431","DOI":"10.1038\/s41467-024-53751-y","article-title":"MolE: a foundation\nmodel for molecular\ngraphs using disentangled attention","volume":"15","author":"Me\u0301ndez-Lucio","year":"2024","journal-title":"Nat. Commun."},{"key":"2026091409075076600_cit23","doi-asserted-by":"publisher","first-page":"11676","DOI":"10.1038\/s41467-025-66685-w","article-title":"Molecular Motif Learning\nas a pretraining objective for molecular property prediction","volume":"16","author":"Liu","year":"2025","journal-title":"Nat. Commun."},{"key":"2026091409075076600_cit24","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2404.14986","article-title":"MiniMol: A Parameter-Efficient\nFoundation Model for Molecular Learning","author":"Kla\u0308ser","year":"2024","journal-title":"arXiv"},{"key":"2026091409075076600_cit25","doi-asserted-by":"crossref","DOI":"10.52202\/079017-0626","article-title":"On the Scalability\nof GNNs for Molecular Graphs","volume-title":"The Thirty-eighth\nAnnual Conference on Neural Information Processing Systems","author":"Sypetkowski","year":"2024"},{"key":"2026091409075076600_cit26","doi-asserted-by":"publisher","first-page":"25","DOI":"10.1186\/s13321-025-00970-0","article-title":"Pretraining\ngraph transformers with atom-in-a-molecule\nquantum properties for improved ADMET modeling","volume":"17","author":"Fallani","year":"2025","journal-title":"J. Cheminf."},{"key":"2026091409075076600_cit27","doi-asserted-by":"publisher","first-page":"1560","DOI":"10.1021\/acs.jcim.4c00049","article-title":"Combining IC50 or Ki\nValues from Different Sources\nIs a Source of Significant Noise","volume":"64","author":"Landrum","year":"2024","journal-title":"J. Chem. Inf.\nModel."},{"key":"2026091409075076600_cit28","doi-asserted-by":"publisher","first-page":"D1373","DOI":"10.1093\/nar\/gkac956","article-title":"PubChem 2023 update","volume":"51","author":"Kim","year":"2023","journal-title":"Nucleic Acids Res."},{"key":"2026091409075076600_cit29","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."},{"key":"2026091409075076600_cit30","doi-asserted-by":"publisher","first-page":"9398","DOI":"10.1021\/acs.jcim.5c01609","article-title":"Practically Significant Method Comparison Protocols\nfor Machine Learning in Small Molecule Drug Discovery","volume":"65","author":"Ash","year":"2025","journal-title":"J. Chem. Inf. Model."},{"key":"2026091409075076600_cit31","doi-asserted-by":"publisher","first-page":"5938","DOI":"10.1021\/acs.jcim.2c01073","article-title":"Exposing the Limitations\nof Molecular Machine Learning with Activity Cliffs","volume":"62","author":"van Tilborg","year":"2022","journal-title":"J. Chem. Inf. Model."},{"key":"2026091409075076600_cit32","doi-asserted-by":"publisher","first-page":"D1100","DOI":"10.1093\/nar\/gkr777","article-title":"ChEMBL:\na large-scale bioactivity database for drug discovery","volume":"40","author":"Gaulton","year":"2012","journal-title":"Nucleic Acids Res."},{"key":"2026091409075076600_cit33","doi-asserted-by":"publisher","first-page":"1225","DOI":"10.1021\/acs.chemrestox.6b00135","article-title":"ToxCast Chemical Landscape: Paving the Road to 21st Century Toxicology","volume":"29","author":"Richard","year":"2016","journal-title":"Chem. Res. Toxicol."},{"key":"2026091409075076600_cit34","doi-asserted-by":"publisher","first-page":"503172","DOI":"10.1016\/j.mrgentox.2020.503172","article-title":"Key read across\nframework components and biology based improvements","volume":"853","author":"Ball","year":"2020","journal-title":"Mutat. Res., Genet. Toxicol. Environ. Mutagen."},{"key":"2026091409075076600_cit35","doi-asserted-by":"publisher","first-page":"4382","DOI":"10.1038\/s41467-025-59634-0","article-title":"A self-conformation-aware\npre-training framework for molecular property prediction with substructure\ninterpretability","volume":"16","author":"Qiao","year":"2025","journal-title":"Nat. Commun."},{"key":"2026091409075076600_cit36","doi-asserted-by":"publisher","first-page":"12978","DOI":"10.1021\/acs.jcim.5c01915","article-title":"MAPCliff-WMGR:\nExploring Activity Cliffs in Molecular Activity Prediction Enhanced\nby Weighted Molecular Graph Representations","volume":"65","author":"Chen","year":"2025","journal-title":"J. Chem. Inf. Model."},{"key":"2026091409075076600_cit37","doi-asserted-by":"publisher","first-page":"28","DOI":"10.1021\/acs.jcim.5c02332","article-title":"Chemprop v2: An Efficient, Modular Machine Learning\nPackage for Chemical Property Prediction","volume":"66","author":"Graff","year":"2026","journal-title":"J.\nChem. Inf. Model."},{"key":"2026091409075076600_cit38","doi-asserted-by":"publisher","first-page":"17","DOI":"10.1021\/ja01193a005","article-title":"Structural\nDetermination of Paraffin Boiling Points","volume":"69","author":"Wiener","year":"1947","journal-title":"J.\nAm. Chem. Soc."},{"key":"2026091409075076600_cit39","doi-asserted-by":"publisher","first-page":"599","DOI":"10.1002\/jctb.5700280902","article-title":"Estimates\nof the Properties of Liquids","volume":"28","author":"McGowan","year":"1978","journal-title":"J. Chem. Technol.\nBiotechnol."},{"key":"2026091409075076600_cit40","volume-title":"zarrs: A High-Performance\nRust Library for the Zarr Array Storage Format","author":"Deakin","year":"2025"},{"key":"2026091409075076600_cit41","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2102.09548","article-title":"Therapeutics\nData Commons: Machine Learning Datasets and Tasks for Drug Discovery\nand Development","author":"Huang","year":"2021","journal-title":"arXiv"},{"key":"2026091409075076600_cit42","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1910.13124","article-title":"Multitask\nLearning\nOn Graph Neural Networks Applied To Molecular Property Predictions","author":"Capela","year":"2019","journal-title":"arXiv"},{"key":"2026091409075076600_cit43","doi-asserted-by":"publisher","first-page":"139","DOI":"10.1186\/s13321-024-00934-w","article-title":"Be aware of overfitting\nby hyperparameter\noptimization!","volume":"16","author":"Tetko","year":"2024","journal-title":"J. Cheminf."},{"key":"2026091409075076600_cit44","doi-asserted-by":"publisher","first-page":"513","DOI":"10.1039\/C7SC02664A","article-title":"MoleculeNet: a benchmark\nfor molecular machine learning","volume":"9","author":"Wu","year":"2018","journal-title":"Chem. Sci."},{"key":"2026091409075076600_cit45","unstructured":"Walters, P.\n          \n          We Need Better Benchmarks\nfor Machine Learning in Drug Discovery; https:\/\/practicalcheminformatics.blogspot.com\/2023\/08\/we-need-better-benchmarks-for-machine.html. [Accessed 13\u201305\u20132025]."},{"key":"2026091409075076600_cit46","doi-asserted-by":"publisher","first-page":"36","DOI":"10.1186\/s13321-016-0148-0","article-title":"Comparing structural fingerprints using a literature-based\nsimilarity benchmark","volume":"8","author":"O\u2019Boyle","year":"2016","journal-title":"J. Cheminf."},{"key":"2026091409075076600_cit47","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1201.0490","article-title":"Scikit-learn:\nMachine Learning in Python","author":"Pedregosa","year":"2012","journal-title":"arXiv"},{"key":"2026091409075076600_cit48","doi-asserted-by":"publisher","DOI":"10.26434\/chemrxiv-2023-fzqwd","article-title":"Scikit-Mol brings cheminformatics\nto Scikit-Learn","author":"Bjerrum","year":"2023","journal-title":"ChemRxiv"},{"key":"2026091409075076600_cit49","doi-asserted-by":"publisher","first-page":"1947","DOI":"10.1021\/ci034160g","article-title":"Random Forest: A Classification and\nRegression Tool for Compound Classification and QSAR Modeling","volume":"43","author":"Svetnik","year":"2003","journal-title":"J. Chem. Inf. Comput. Sci."},{"key":"2026091409075076600_cit50","doi-asserted-by":"publisher","first-page":"551","DOI":"10.1039\/D4FD00095A","article-title":"Analysis of\nuncertainty of neural\nfingerprint-based models","volume":"256","author":"Feldmann","year":"2025","journal-title":"Faraday Discuss."},{"key":"2026091409075076600_cit51","unstructured":"Landrum, G.\n          \n          rdkit; Zenodo, 2025. https:\/\/zenodo.org\/doi\/10.5281\/zenodo.591637."},{"key":"2026091409075076600_cit52","article-title":"Towards Foundational\nModels for Molecular Learning on Large-Scale Multi-Task Datasets","volume-title":"International Conference on Learning Representations (ICLR)","author":"Beaini","year":"2024"},{"key":"2026091409075076600_cit53","doi-asserted-by":"crossref","first-page":"92","DOI":"10.25080\/Majora-92bf1922-011","article-title":"Statsmodels: Econometric\nand Statistical Modeling with\nPython","volume":"7","author":"Seabold","year":"2010","journal-title":"Scipy"},{"key":"2026091409075076600_cit54","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2508.06199","article-title":"Benchmarking Pretrained Molecular\nEmbedding Models For Molecular Representation Learning","author":"Praski","year":"2025","journal-title":"arXiv"},{"key":"2026091409075076600_cit55","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1805.01978","article-title":"Unsupervised Feature Learning via\nNon-Parametric\nInstance-level Discrimination","author":"Wu","year":"2018","journal-title":"arXiv"},{"key":"2026091409075076600_cit56","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2104.14294","article-title":"Emerging Properties in Self-Supervised\nVision Transformers","author":"Caron","year":"2021","journal-title":"arXiv"},{"key":"2026091409075076600_cit57","volume-title":"CheMeleon Training Data","author":"Zalte","year":"2025"},{"key":"2026091409075076600_cit58","volume-title":"CheMeleon Foundation\nModel","author":"Burns","year":"2025"}],"container-title":["Journal of Chemical Information\nand Modeling"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/pubs.acs.org\/doi\/pdf\/10.1021\/acs.jcim.6c01546","content-type":"application\/pdf","content-version":"vor","intended-application":"unspecified"},{"URL":"https:\/\/pubs.acs.org\/jcisd8\/article-pdf\/66\/17\/10692\/66462174\/acs.jcim.6c01546.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/pubs.acs.org\/jcisd8\/article-pdf\/66\/17\/10692\/66462174\/acs.jcim.6c01546.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,14]],"date-time":"2026-09-14T13:16:41Z","timestamp":1789391801000},"score":1,"resource":{"primary":{"URL":"https:\/\/pubs.acs.org\/jcisd8\/article\/66\/17\/10692\/5250516\/Deep-Learning-Foundation-Models-for-Low-Data"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8,7]]},"references-count":58,"journal-issue":{"issue":"17","published-online":{"date-parts":[[2026,8,7]]},"published-print":{"date-parts":[[2026,9,14]]}},"URL":"https:\/\/doi.org\/10.1021\/acs.jcim.6c01546","relation":{},"ISSN":["1549-9596","1549-960X"],"issn-type":[{"value":"1549-9596","type":"print"},{"value":"1549-960X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,8,7]]}}}