{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,23]],"date-time":"2026-09-23T09:01:56Z","timestamp":1790154116888,"version":"4.0.1"},"reference-count":70,"publisher":"American Chemical Society (ACS)","issue":"5","license":[{"start":{"date-parts":[[2026,6,10]],"date-time":"2026-06-10T00:00:00Z","timestamp":1781049600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026,9,16]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>Linear solvation energy relationship (LSER) models are nowadays often used to predict physicochemical properties of chemicals, such as partition coefficients, retention factors in chromatography, and solubilities. Due to their mechanistic foundation and transferability across phases, LSER models are particularly valuable for predicting partition coefficients in data-poor systems where experimental data sets are not available. However, their broader applicability is currently constrained by the limited availability of experimentally determined solute descriptors. We developed three different models, based on three different approaches, to predict the solute descriptors S, E, A, B, and L for LSER applications: (1) a group contribution model that includes an initial screening algorithm to identify functional groups as structural patterns, (2) a k-nearest neighbors model, and (3) a graph-convolutional neural network. All models were developed on the same curated data set for each solute descriptor. An independent test set was used to evaluate the overall model performance, with rmse values ranging from 0.08\u20130.13 for A, 0.10\u20130.15 for B, 0.17\u20130.23 for S, 0.09\u20130.19 for E, and 0.25\u20130.45 for L across the three approaches. By enabling the prediction of these descriptors directly from molecular structure, our modeling framework addresses a key bottleneck that has so far limited the scalability and broader application of the LSER models. In addition, we investigated whether a consensus approach would enhance overall prediction quality. Additionally, the predicted solute descriptors were directly used to derive environmentally and analytically relevant partition coefficients, demonstrating that reliable LSER-based property predictions are feasible even for chemicals lacking experimental descriptor data or large property-specific training sets. By enabling descriptor generation at scale, this work improves the practical applicability of LSER modeling and strengthens its role as a transferable and data-efficient tool for environmental fate and risk assessment.<\/jats:p>","DOI":"10.1021\/acsenvironau.6c00063","type":"journal-article","created":{"date-parts":[[2026,6,10]],"date-time":"2026-06-10T11:36:47Z","timestamp":1781091407000},"page":"851-863","source":"Crossref","is-referenced-by-count":1,"title":["Prediction\nof Solute Descriptors for Linear Solvation\nEnergy Relationships Using K-Nearest Neighbors, Group Contributions,\nand Graph-Convolutional Neural Networks"],"prefix":"10.1021","volume":"6","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-1267-0429","authenticated-orcid":true,"given":"Nadin","family":"Ulrich","sequence":"first","affiliation":[{"name":"Helmholtz Centre for Environmental Research \u2212 UFZ , , Permoserstrasse 15 , ,","place":["Leipzig, Germany, D-04318"]},{"name":"PAULY , Essener Stra\u00dfe 100 , ,","place":["Leipzig, Germany, D-04357"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Valentin","family":"Istomin","sequence":"additional","affiliation":[{"name":"Helmholtz Centre for Environmental Research \u2212 UFZ , , Permoserstrasse 15 , ,","place":["Leipzig, Germany, D-04318"]},{"name":"PAULY , Essener Stra\u00dfe 100 , ,","place":["Leipzig, Germany, D-04357"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Anton","family":"Kudria","sequence":"additional","affiliation":[{"name":"Helmholtz Centre for Environmental Research \u2212 UFZ , , Permoserstrasse 15 , ,","place":["Leipzig, Germany, D-04318"]},{"name":"PAULY , Essener Stra\u00dfe 100 , ,","place":["Leipzig, Germany, D-04357"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1874-051X","authenticated-orcid":true,"given":"Alexander","family":"Bo\u0308hme","sequence":"additional","affiliation":[{"name":"Helmholtz Centre for Environmental Research \u2212 UFZ , , Permoserstrasse 15 , ,","place":["Leipzig, Germany, D-04318"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Karsten","family":"Voigt","sequence":"additional","affiliation":[{"name":"PAULY , Essener Stra\u00dfe 100 , ,","place":["Leipzig, Germany, D-04357"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"316","published-online":{"date-parts":[[2026,6,10]]},"reference":[{"issue":"1","key":"2026092222565432900_cit1","doi-asserted-by":"publisher","first-page":"10","DOI":"10.1186\/s13321-018-0263-1","article-title":"OPERA models for\npredicting physicochemical properties and environmental fate endpoints","volume":"10","author":"Mansouri","year":"2018","journal-title":"J. Cheminf."},{"key":"2026092222565432900_cit2","doi-asserted-by":"publisher","first-page":"100114","DOI":"10.1016\/j.comtox.2019.100114","article-title":"Artificial Intelligence\nfor chemical risk assessment","volume":"13","author":"Wittwehr","year":"2020","journal-title":"Comput. Toxicol"},{"issue":"4","key":"2026092222565432900_cit3","doi-asserted-by":"publisher","first-page":"168","DOI":"10.1021\/acscentsci.5b00131","article-title":"Modeling\nEpoxidation of Drug-like\nMolecules with a Deep Machine Learning Network","volume":"1","author":"Hughes","year":"2015","journal-title":"ACS Central Sci"},{"key":"2026092222565432900_cit4","doi-asserted-by":"publisher","first-page":"7","DOI":"10.1021\/acs.jcim.0c00971","article-title":"OpenChem:\nA Deep Learning\nToolkit for Computational Chemistry and Drug Design","volume":"61","author":"Korshunova","year":"2021","journal-title":"J. Chem. Inf. Model"},{"issue":"3","key":"2026092222565432900_cit5","doi-asserted-by":"publisher","first-page":"343","DOI":"10.1021\/accountsmr.1c00238","article-title":"Learning Matter: Materials Design\nwith Machine Learning and Atomistic Simulations","volume":"3","author":"Axelrod","year":"2022","journal-title":"Acc. Mater. Res"},{"issue":"2","key":"2026092222565432900_cit6","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":"2026092222565432900_cit7","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1706.06689","article-title":"Chemception: A Deep Neural Network\nwith Minimal Chemistry Knowledge Matches the Performance of Expert-developed\nQSAR\/QSPR Models","author":"Goh","year":"2017","journal-title":"arXiv"},{"issue":"1","key":"2026092222565432900_cit8","doi-asserted-by":"publisher","first-page":"55","DOI":"10.1186\/s13321-025-01000-9","article-title":"Prediction of the water solubility by a graph convolutional-based\nneural network on a highly curated dataset","volume":"17","author":"Ulrich","year":"2025","journal-title":"J. Cheminf"},{"issue":"20","key":"2026092222565432900_cit9","doi-asserted-by":"publisher","first-page":"1444","DOI":"10.1002\/jcc.25213","article-title":"TopP\u2013S: Persistent\nhomology-based multi-task deep neural networks for simultaneous predictions\nof partition coefficient and aqueous solubility","volume":"39","author":"Wu","year":"2018","journal-title":"J. Comput. Chem"},{"issue":"1","key":"2026092222565432900_cit10","doi-asserted-by":"publisher","first-page":"90","DOI":"10.1038\/s42004-021-00528-9","article-title":"Exploring\nthe octanol\u2013water\npartition coefficient dataset using deep learning techniques and data\naugmentation","volume":"4","author":"Ulrich","year":"2021","journal-title":"Commun. Chem"},{"issue":"16","key":"2026092222565432900_cit11","doi-asserted-by":"publisher","first-page":"4555","DOI":"10.1039\/C9GC01968E","article-title":"Predictive deep learning\nmodels for environmental properties: the\ndirect calculation of octanol\u2013water partition coefficients\nfrom molecular graphs","volume":"21","author":"Wang","year":"2019","journal-title":"Green Chem"},{"issue":"23","key":"2026092222565432900_cit12","doi-asserted-by":"publisher","first-page":"24296","DOI":"10.1021\/acsomega.5c00205","article-title":"Prediction of Melting\nPoints of Chemicals with a Data Augmentation-Based Neural Network\nApproach","volume":"10","author":"Austermeier","year":"2025","journal-title":"ACS Omega"},{"issue":"2","key":"2026092222565432900_cit13","doi-asserted-by":"publisher","first-page":"457","DOI":"10.1021\/ci0004614","article-title":"A Quantum\nMechanical\/Neural Net Model\nfor Boiling Points with Error Estimation","volume":"41","author":"Chalk","year":"2001","journal-title":"J.\nChem. Inf. Comput. Sci"},{"key":"2026092222565432900_cit14","doi-asserted-by":"publisher","first-page":"108149","DOI":"10.1016\/j.jmgm.2022.108149","article-title":"Graph convolutional\nneural network applied to the prediction of normal boiling point","volume":"112","author":"Qu","year":"2022","journal-title":"J. Mol. Graphics Modell"},{"issue":"18","key":"2026092222565432900_cit15","doi-asserted-by":"publisher","first-page":"4501","DOI":"10.1021\/acs.jpcb.4c08757","article-title":"Assessing the Effectiveness\nof Neural Networks and Molecular Dynamics Simulations in Predicting\nViscosity of Small Organic Molecules","volume":"129","author":"Yue","year":"2025","journal-title":"J. Phys.\nChem. B"},{"issue":"3","key":"2026092222565432900_cit16","doi-asserted-by":"publisher","first-page":"1253","DOI":"10.1021\/acs.jcim.8b00785","article-title":"Predictive Multitask\nDeep Neural\nNetwork Models for ADME-Tox Properties: Learning from Large Data Sets","volume":"59","author":"Wenzel","year":"2019","journal-title":"J. Chem. Inf. Model"},{"issue":"1","key":"2026092222565432900_cit17","doi-asserted-by":"publisher","first-page":"98","DOI":"10.1186\/s13321-021-00575-3","article-title":"Prediction of small-molecule\ncompound solubility in\norganic solvents by machine learning algorithms","volume":"13","author":"Ye","year":"2021","journal-title":"J. Cheminf"},{"issue":"1","key":"2026092222565432900_cit18","doi-asserted-by":"publisher","first-page":"29","DOI":"10.1016\/j.chroma.2003.12.004","article-title":"Determination of sets of solute descriptors\nfrom chromatographic measurements","volume":"1037","author":"Abraham","year":"2004","journal-title":"J. Chromatogr.\nA"},{"issue":"3","key":"2026092222565432900_cit19","doi-asserted-by":"publisher","first-page":"1500","DOI":"10.1002\/jps.21922","article-title":"Prediction of solubility of drugs\nand other compounds in organic solvents","volume":"99","author":"Abraham","year":"2010","journal-title":"J.\nPharm. Sci"},{"key":"2026092222565432900_cit20","doi-asserted-by":"publisher","first-page":"188","DOI":"10.1016\/j.chemosphere.2014.06.037","article-title":"A simple\nmethod for estimating in vitro air-tissue and in vivo blood-tissue\npartition coefficients","volume":"120","author":"Abraham","year":"2015","journal-title":"Chemosphere"},{"key":"2026092222565432900_cit21","unstructured":"Ulrich, N.; Endo, S.; Brown, T. N.; Watanabe, N.; Bronner, G.; Abraham, M. H.; Goss, K. U.\n          UFZ-LSER database\nv 3.2\n          Helmholtz Centre for Environmental\nResearch\n          2017."},{"issue":"2","key":"2026092222565432900_cit22","doi-asserted-by":"publisher","first-page":"162","DOI":"10.1016\/j.chroma.2007.10.058","article-title":"Characterization\nof the sorption of gaseous and organic solutes onto polydimethyl siloxane\nsolid-phase microextraction surfaces using the Abraham model","volume":"1175","author":"Sprunger","year":"2007","journal-title":"J. Chromatogr. A"},{"key":"2026092222565432900_cit23","doi-asserted-by":"publisher","first-page":"106137","DOI":"10.1016\/j.ejps.2022.106137","article-title":"Linear\nsolvation energy relationships (LSERs) for robust\nprediction of partition coefficients between low density polyethylene\nand water. Part I: Experimental partition coefficients and model calibration","volume":"172","author":"Egert","year":"2022","journal-title":"Eur. J. Pharm. Sci"},{"issue":"24","key":"2026092222565432900_cit24","doi-asserted-by":"publisher","first-page":"10786","DOI":"10.1021\/acs.est.4c01994","article-title":"Polyparameter\nLinear Free Energy Relationships for Partitioning of\nNeutral Organic Compounds to Storage Lipids","volume":"58","author":"Liu","year":"2024","journal-title":"Environ. Sci. Technol"},{"issue":"17","key":"2026092222565432900_cit25","doi-asserted-by":"publisher","first-page":"9519","DOI":"10.1021\/es301921w","article-title":"Partitioning\nof Organic Chemicals\nto Storage Lipids: Elucidating the Dependence on Fatty Acid Composition\nand Temperature","volume":"46","author":"Geisler","year":"2012","journal-title":"Environ. Sci. Technol"},{"key":"2026092222565432900_cit26","doi-asserted-by":"publisher","first-page":"1506","DOI":"10.1002\/etc.4744","article-title":"Yolk\/water\npartitioning of neutral organic compounds in the model organism Danio\nrerio","volume":"39","author":"Ulrich","year":"2020","journal-title":"Environ. Toxicol. Chem"},{"key":"2026092222565432900_cit27","doi-asserted-by":"publisher","first-page":"95","DOI":"10.1016\/j.chroma.2012.09.051","article-title":"Linear solvation energy relationships as classifiers in non-target\nanalysis - a gas chromatographic approach","volume":"1264","author":"Ulrich","year":"2012","journal-title":"J.\nChromatogr. A"},{"key":"2026092222565432900_cit28","doi-asserted-by":"publisher","first-page":"139","DOI":"10.1016\/j.chroma.2013.02.037","article-title":"Prediction\nof gas chromatographic\nretention indices as classifier in non-target analysis of environmental\nsamples","volume":"1285","author":"Ulrich","year":"2013","journal-title":"J. Chromatogr. A"},{"key":"2026092222565432900_cit29","doi-asserted-by":"publisher","first-page":"463682","DOI":"10.1016\/j.chroma.2022.463682","article-title":"Recent advances\nfor estimating environmental properties\nfor small molecules from chromatographic measurements and the solvation\nparameter model","volume":"1687","author":"Poole","year":"2023","journal-title":"J. Chromatogr. A"},{"issue":"45","key":"2026092222565432900_cit30","doi-asserted-by":"publisher","first-page":"8192","DOI":"10.1016\/j.chroma.2011.09.031","article-title":"Linear Solvation Energy\nRelationships as classifiers in non-target analysis\u2013a capillary\nliquid chromatography approach","volume":"1218","author":"Ulrich","year":"2011","journal-title":"J. Chromatogr.\nA"},{"key":"2026092222565432900_cit31","doi-asserted-by":"publisher","first-page":"96","DOI":"10.1016\/j.chroma.2013.11.023","article-title":"Linear solvation\nenergy relationships as classifier in non-target analysis\u2013an\napproach for isocratic liquid chromatography","volume":"1324","author":"Ulrich","year":"2014","journal-title":"J. Chromatogr. A"},{"issue":"4","key":"2026092222565432900_cit32","doi-asserted-by":"publisher","first-page":"1006","DOI":"10.1021\/jo902388n","article-title":"Equations for the Transfer of Neutral\nMolecules and\nIonic Species from Water to Organic phases","volume":"75","author":"Abraham","year":"2010","journal-title":"J. Org. Chem"},{"key":"2026092222565432900_cit33","doi-asserted-by":"publisher","first-page":"48","DOI":"10.1016\/j.chemosphere.2016.03.086","article-title":"Equations for water-triolein partition coefficients\nfor neutral species; comparison with other water-solvent partitions,\nand environmental and toxicological processes","volume":"154","author":"Abraham","year":"2016","journal-title":"Chemosphere"},{"issue":"6","key":"2026092222565432900_cit34","doi-asserted-by":"publisher","first-page":"797","DOI":"10.1039\/P29870000797","article-title":"Determination of Olive Oil-Gas and\nHexadecane-Gas Partition-Coefficients, and Calculation of the Corresponding\nOlive Oil-Water and Hexadecane-Water Partition-Coefficients","author":"Abraham","year":"1987","journal-title":"J. Chem. Soc., Perkin Trans. 2"},{"issue":"1\u20132","key":"2026092222565432900_cit35","doi-asserted-by":"publisher","first-page":"143","DOI":"10.1016\/j.chroma.2006.06.074","article-title":"The chemical interpretation and practice of linear\nsolvation energy relationships in chromatography","volume":"1126","author":"Vitha","year":"2006","journal-title":"J. Chromatogr. A"},{"issue":"9","key":"2026092222565432900_cit36","doi-asserted-by":"publisher","first-page":"599","DOI":"10.1002\/jctb.5700280902","article-title":"Estimates\nof Properties of Liquids","volume":"28","author":"Mcgowan","year":"1978","journal-title":"J. Appl. Chem. Biotechnol"},{"key":"2026092222565432900_cit37","doi-asserted-by":"publisher","first-page":"460841","DOI":"10.1016\/j.chroma.2019.460841","article-title":"Wayne State\nUniversity experimental descriptor database for use with the solvation\nparameter model","volume":"1617","author":"Poole","year":"2020","journal-title":"J. Chromatogr. A"},{"issue":"1","key":"2026092222565432900_cit38","doi-asserted-by":"publisher","first-page":"51","DOI":"10.1080\/1062936X.2013.841286","article-title":"Predicting\nhexadecane\u2013air equilibrium partition coefficients (L) using\na group contribution approach constructed from high quality data","volume":"25","author":"Brown","year":"2014","journal-title":"SAR QSAR Environ. Res"},{"issue":"1","key":"2026092222565432900_cit39","doi-asserted-by":"publisher","first-page":"65","DOI":"10.1186\/s13321-024-00853-w","article-title":"Identifying\nuncertainty in physical\u2013chemical\nproperty estimation with IFSQSAR","volume":"16","author":"Brown","year":"2024","journal-title":"J. Cheminf"},{"key":"2026092222565432900_cit40","doi-asserted-by":"publisher","first-page":"113349","DOI":"10.1016\/j.fluid.2021.113349","article-title":"Can deep learning algorithms\nenhance the prediction of solute descriptors\nfor linear solvation energy relationship approaches?","volume":"555","author":"Ulrich","year":"2022","journal-title":"Fluid Phase Equilib"},{"issue":"3","key":"2026092222565432900_cit41","doi-asserted-by":"publisher","first-page":"2054","DOI":"10.1021\/acs.est.1c05398","article-title":"Predicting Solute Descriptors for Organic Chemicals by a Deep Neural\nNetwork (DNN) Using Basic Chemical Structures and a Surrogate Metric","volume":"56","author":"Zhang","year":"2022","journal-title":"Environ. Sci. Technol"},{"key":"2026092222565432900_cit42","doi-asserted-by":"publisher","first-page":"518","DOI":"10.3390\/liquids4030029","article-title":"AbraLlama: Predicting\nAbraham Model Solute Descriptors\nand Modified Solvent Parameters Using Llama","volume":"4","author":"Lang","year":"2024","journal-title":"Liquids"},{"issue":"20","key":"2026092222565432900_cit43","doi-asserted-by":"publisher","first-page":"3714","DOI":"10.1021\/jm000942e","article-title":"Fast Calculation of Molecular Polar\nSurface Area as a Sum of Fragment-Based Contributions and Its Application\nto the Prediction of Drug Transport Properties","volume":"43","author":"Ertl","year":"2000","journal-title":"J. Med. Chem"},{"issue":"1","key":"2026092222565432900_cit44","doi-asserted-by":"publisher","first-page":"36","DOI":"10.1186\/s13321-017-0225-z","article-title":"An algorithm\nto identify functional groups in organic molecules","volume":"9","author":"Ertl","year":"2017","journal-title":"J. Cheminf"},{"issue":"1","key":"2026092222565432900_cit45","doi-asserted-by":"publisher","first-page":"108","DOI":"10.1002\/minf.201200085","article-title":"Read-Across\nPrediction of the Acute\nToxicity of Organic Compounds toward the Water Flea Daphnia magna","volume":"32","author":"Ku\u0308hne","year":"2013","journal-title":"Mol. Inform"},{"issue":"7825","key":"2026092222565432900_cit46","doi-asserted-by":"publisher","first-page":"357","DOI":"10.1038\/s41586-020-2649-2","article-title":"Array programming with NumPy","volume":"585","author":"Harris","year":"2020","journal-title":"Nature"},{"key":"2026092222565432900_cit47","unstructured":"Landrum, G.; Tosco, P.; Kelley, B.; Rodriguez, R.; Cosgrove, D.; Vianello, R.; Sriniker; ; Gedeck, P.; Jones, G.; Kawashima, E.; et al., rdkit\/rdkit: 2025_09_5 (Q3 2025) Release\n(Release_2025_09_5). Zenodo. 2026."},{"key":"2026092222565432900_cit48","doi-asserted-by":"crossref","DOI":"10.25080\/TCWV9851","article-title":"Exploring Network\nStructure, Dynamics, and Function using NetworkX","volume-title":"Proceedings of the 7th Python in Science Conference","author":"Hagberg","year":"2008"},{"issue":"3","key":"2026092222565432900_cit49","doi-asserted-by":"publisher","first-page":"261","DOI":"10.1038\/s41592-019-0686-2","article-title":"SciPy 1.0: fundamental\nalgorithms for scientific computing in Python","volume":"17","author":"Virtanen","year":"2020","journal-title":"Nat. Methods"},{"key":"2026092222565432900_cit50","unstructured":"Newville, M.; Nelson, A.; Stensitzki, T.; Ingargiola, A.; Allan, D. L.\n          Non-Linear Least-Squares\nMinimization and Curve-Fitting for Python. V 1.3.2. GitHub. 2025."},{"issue":"3","key":"2026092222565432900_cit51","doi-asserted-by":"publisher","first-page":"1061","DOI":"10.1021\/acs.jcim.4c02268","article-title":"EFGs: A Complete\nand Accurate Implementation of Ertl\u2019s Functional Group Detection\nAlgorithm in RDKit","volume":"65","author":"Colmenarejo","year":"2025","journal-title":"J. Chem. Inf. Model"},{"key":"2026092222565432900_cit52","unstructured":"The pandas development team.\n          \n          pandas-dev\/pandas:\nPandas (v3.0.0). Zenodo2026."},{"key":"2026092222565432900_cit53","doi-asserted-by":"crossref","unstructured":"McKinney, W.\n          \n          Data Structures\nfor Statistical Computing in Python. SciPy2010.","DOI":"10.25080\/Majora-92bf1922-00a"},{"key":"2026092222565432900_cit54","first-page":"1","article-title":"The igraph\nsoftware package for complex network research","volume":"1695","author":"Csa\u0301rdi","year":"2006","journal-title":"Complex Syst."},{"issue":"85","key":"2026092222565432900_cit55","first-page":"2825","article-title":"E\u0301douard Duchesnay.\nScikit-learn: Machine Learning in Python","volume":"12","author":"Pedregosa","year":"2011","journal-title":"J.\nMach. Learn. Res."},{"key":"2026092222565432900_cit56","doi-asserted-by":"crossref","DOI":"10.1145\/3292500.3330701","article-title":"Optuna: A Next-generation Hyperparameter\nOptimization Framework","volume-title":"Proceedings of\nthe 25th ACM SIGKDD International Conference on Knowledge Discovery\n& Data Mining","author":"Akiba","year":"2019"},{"issue":"3","key":"2026092222565432900_cit57","doi-asserted-by":"publisher","first-page":"90","DOI":"10.1109\/MCSE.2007.55","article-title":"Matplotlib:\nA 2D Graphics Environment","volume":"9","author":"Hunter","year":"2007","journal-title":"Comput. Sci. Eng"},{"key":"2026092222565432900_cit58","unstructured":"TensorFlow.\n          \n          Large-scale machine learning on heterogeneous\nsystems\n          https:\/\/www.tensorflow.org\/. Accessed 07 January 2026."},{"key":"2026092222565432900_cit59","unstructured":"Keras.\n          \n          A superpower for ML developers. https:\/\/keras.io. Accessed 07 January\n2026."},{"key":"2026092222565432900_cit60","unstructured":"Ramsundar, B.\n          \n          Democratizing\nDeep-Learning for Drug Discovery, Quantum Chemistry, Materials Science\nand Biology. GitHub2016."},{"key":"2026092222565432900_cit61","volume-title":"Deep Learning for the Life Sciences","author":"Ramsundar","year":"2019"},{"issue":"2","key":"2026092222565432900_cit62","doi-asserted-by":"publisher","first-page":"166","DOI":"10.1021\/acs.estlett.4c01003","article-title":"PubChemLite\nPlus Collision Cross Section (CCS) Values for Enhanced\nInterpretation of Nontarget Environmental Data","volume":"12","author":"Elapavalore","year":"2025","journal-title":"Environ. Sci. Technol. Lett"},{"key":"2026092222565432900_cit63","unstructured":"Schymanski, E.; Kondic, T.; Thiessen, P.; Zhang, J.; Bolton, E.\n          PubChemLite for Exposomic.\n2.6.0\n          Zenodo\n          2025."},{"issue":"4","key":"2026092222565432900_cit64","doi-asserted-by":"publisher","first-page":"1166","DOI":"10.1021\/acs.jcim.2c01253","article-title":"ZINC-22\u2500A\nFree Multi-Billion-Scale Database of Tangible Compounds for Ligand\nDiscovery","volume":"63","author":"Tingle","year":"2023","journal-title":"J. Chem. Inf. Model"},{"issue":"11","key":"2026092222565432900_cit65","doi-asserted-by":"publisher","first-page":"2864","DOI":"10.1021\/ci300415d","article-title":"Enumeration of 166\nBillion Organic Small Molecules in the Chemical Universe Database\nGDB-17","volume":"52","author":"Ruddigkeit","year":"2012","journal-title":"J. Chem. Inf. Model"},{"issue":"1","key":"2026092222565432900_cit66","doi-asserted-by":"publisher","first-page":"69","DOI":"10.1186\/s13321-016-0182-y","article-title":"A novel applicability\ndomain technique for mapping predictive reliability across the chemical\nspace of a QSAR: reliability-density neighbourhood","volume":"8","author":"Aniceto","year":"2016","journal-title":"J. Cheminf"},{"issue":"1","key":"2026092222565432900_cit67","doi-asserted-by":"publisher","first-page":"44","DOI":"10.1186\/s12302-025-01072-2","article-title":"Consolidated\noctanol\/water partition\ncoefficients: combining multiple estimates from different methods\nto reduce uncertainties in log KOW","volume":"37","author":"Nendza","year":"2025","journal-title":"Environ.\nSci. Eur"},{"issue":"22","key":"2026092222565432900_cit68","doi-asserted-by":"publisher","first-page":"5457","DOI":"10.1021\/acs.jcim.2c01013","article-title":"Explainable Solvation Free Energy\nPrediction Combining Graph Neural Networks with Chemical Intuition","volume":"62","author":"Low","year":"2022","journal-title":"J. Chem. Inf. Model"},{"issue":"47","key":"2026092222565432900_cit69","doi-asserted-by":"publisher","first-page":"19777","DOI":"10.1039\/D4SC05115G","article-title":"HANNA: hard-constraint\nneural network for consistent\nactivity coefficient prediction","volume":"15","author":"Specht","year":"2024","journal-title":"Chem. Sci"},{"key":"2026092222565432900_cit70","doi-asserted-by":"publisher","first-page":"108153","DOI":"10.1016\/j.compchemeng.2023.108153","article-title":"Graph neural\nnetworks for temperature-dependent activity coefficient prediction\nof solutes in ionic liquids","volume":"171","author":"Rittig","year":"2023","journal-title":"Comput. Chem. Eng"}],"container-title":["ACS Environmental Au"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/pubs.acs.org\/doi\/pdf\/10.1021\/acsenvironau.6c00063","content-type":"application\/pdf","content-version":"vor","intended-application":"unspecified"},{"URL":"https:\/\/pubs.acs.org\/aeacc4\/article-pdf\/6\/5\/851\/66255944\/acsenvironau.6c00063.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/pubs.acs.org\/aeacc4\/article-pdf\/6\/5\/851\/66255944\/acsenvironau.6c00063.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,23]],"date-time":"2026-09-23T08:10:20Z","timestamp":1790151020000},"score":1,"resource":{"primary":{"URL":"https:\/\/pubs.acs.org\/aeacc4\/article\/6\/5\/851\/5232381\/Prediction-of-Solute-Descriptors-for-Linear"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6,10]]},"references-count":70,"journal-issue":{"issue":"5","published-online":{"date-parts":[[2026,6,10]]},"published-print":{"date-parts":[[2026,9,16]]}},"URL":"https:\/\/doi.org\/10.1021\/acsenvironau.6c00063","relation":{},"ISSN":["2694-2518"],"issn-type":[{"value":"2694-2518","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,6,10]]}}}