{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,18]],"date-time":"2026-08-18T10:28:07Z","timestamp":1787048887610,"version":"build-2736575974"},"reference-count":43,"publisher":"American Chemical Society (ACS)","issue":"10","license":[{"start":{"date-parts":[[2020,8,17]],"date-time":"2020-08-17T00:00:00Z","timestamp":1597622400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2020,8,17]],"date-time":"2020-08-17T00:00:00Z","timestamp":1597622400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2020,8,17]],"date-time":"2020-08-17T00:00:00Z","timestamp":1597622400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-045"}],"funder":[{"DOI":"10.13039\/501100004846","name":"Beijing University of Chinese Medicine","doi-asserted-by":"publisher","award":["2017-JYB-JS-175"],"award-info":[{"award-number":["2017-JYB-JS-175"]}],"id":[{"id":"10.13039\/501100004846","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["81573716"],"award-info":[{"award-number":["81573716"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2020,10,26]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>Oral bioavailability (OBA)-related pharmacokinetic properties, such as aqueous solubility, lipophilicity, and intestinal membrane permeability, play a significant role in drug discovery. However, their measurement is usually costly and time-consuming. Therefore, prediction models based on diverse approaches have been established in recent decades. Computational prediction of molecular properties has become an important step in drug discovery, aiming to identify potential drug-like candidates and reduce costs. However, limitations related to dataset capacity and algorithm adaptation still place restrictions on the applicability of the related models. In this study, we considered both dataset and algorithm optimization to address the challenge of predicting OBA-related molecular properties. Benchmark datasets of aqueous solubility (log S), lipophilicity (log D), and membrane permeability measured using the Caco-2 cell line (log Papp) were constructed by merging and calibrating experimental data from diverse articles and databases. Then, a novel molecular property prediction model, called a multiembedding-based synthetic network (MESN), was generated by applying a deep learning algorithm based on the synthesis of multiple types of molecular embeddings. MESN achieves performance improvements over other state-of-the-art methods for the prediction of aqueous solubility, lipophilicity, and membrane permeability. Results were also obtained using several other algorithms and independent validation datasets as a control study. Moreover, a dimension reduction analysis (based on t-distributed stochastic neighbor embedding, t-SNE) and an atomic feature similarity analysis showed that the molecular embeddings extracted from the MESN model exhibit good clustering and diversity. Overall, considering the fundamental role of the data and the superior prediction performance of the model, we highlight the applicability of MESN on benchmark datasets for further utility in drug discovery-related molecular property prediction.<\/jats:p>","DOI":"10.1021\/acs.jcim.0c00568","type":"journal-article","created":{"date-parts":[[2020,8,17]],"date-time":"2020-08-17T12:53:11Z","timestamp":1597668791000},"page":"4603-4613","source":"Crossref","is-referenced-by-count":34,"title":["Optimizing Pharmacokinetic Property Prediction Based\non Integrated Datasets and a Deep Learning Approach"],"prefix":"10.1021","volume":"60","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-1846-1118","authenticated-orcid":true,"given":"Xiting","family":"Wang","sequence":"first","affiliation":[{"name":"Beijing University of Chinese Medicine , , ,","place":["Beijing, China, 100029"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Meng","family":"Liu","sequence":"additional","affiliation":[{"name":"Beijing University of Chinese Medicine , , ,","place":["Beijing, China, 100029"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lan","family":"Zhang","sequence":"additional","affiliation":[{"name":"Beijing University of Chinese Medicine , , ,","place":["Beijing, China, 100029"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yun","family":"Wang","sequence":"additional","affiliation":[{"name":"Beijing University of Chinese Medicine , , ,","place":["Beijing, China, 100029"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yu","family":"Li","sequence":"additional","affiliation":[{"name":"Beijing University of Chinese Medicine , , ,","place":["Beijing, China, 100029"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tao","family":"Lu","sequence":"additional","affiliation":[{"name":"Beijing University of Chinese Medicine , , ,","place":["Beijing, China, 100029"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"316","published-online":{"date-parts":[[2020,8,17]]},"reference":[{"key":"2026081804382136300_cit1","doi-asserted-by":"publisher","first-page":"11169","DOI":"10.1021\/acs.jmedchem.8b01259","article-title":"Lipophilic\nPermeability Efficiency Reconciles the Opposing Roles of Lipophilicity\nin Membrane Permeability and Aqueous Solubility","volume":"61","author":"Naylor","year":"2018","journal-title":"J. Med. Chem."},{"key":"2026081804382136300_cit2","doi-asserted-by":"publisher","first-page":"1784","DOI":"10.1016\/j.drudis.2018.06.016","article-title":"Neural network\nand deep-learning algorithms used in QSAR studies: merits and drawbacks","volume":"23","author":"Ghasemi","year":"2018","journal-title":"Drug Discovery Today"},{"key":"2026081804382136300_cit3","doi-asserted-by":"publisher","first-page":"10","DOI":"10.1016\/j.ecoenv.2016.03.002","article-title":"Developing a support vector machine based QSPR model\nfor prediction of half-life of some herbicides","volume":"129","author":"Samghani","year":"2016","journal-title":"Ecotoxicol. Environ. Saf."},{"key":"2026081804382136300_cit4","doi-asserted-by":"publisher","first-page":"99","DOI":"10.1016\/j.addr.2016.04.018","article-title":"The solubility-permeability\ninterplay and oral drug formulation design: Two heads are better than\none","volume":"101","author":"Dahan","year":"2016","journal-title":"Adv. Drug Delivery Rev."},{"key":"2026081804382136300_cit5","doi-asserted-by":"publisher","first-page":"315","DOI":"10.1124\/pr.112.005660","article-title":"Strategies to\naddress low drug solubility\nin discovery and development","volume":"65","author":"Williams","year":"2013","journal-title":"Pharmacol. Rev."},{"key":"2026081804382136300_cit6","doi-asserted-by":"publisher","first-page":"235","DOI":"10.1517\/17460441003605098","article-title":"Lipophilicity\nin drug discovery","volume":"5","author":"Waring","year":"2010","journal-title":"Expert Opin. Drug Discovery"},{"key":"2026081804382136300_cit7","doi-asserted-by":"publisher","first-page":"2564","DOI":"10.1002\/jps.23609","article-title":"Establishment\nof novel prediction system of intestinal absorption in humans using\nhuman intestinal tissues","volume":"102","author":"Miyake","year":"2013","journal-title":"J. Pharm. Sci."},{"key":"2026081804382136300_cit8","doi-asserted-by":"publisher","first-page":"bbz103","DOI":"10.1093\/bib\/bbz103","article-title":"Computational\/in silico methods in\ndrug target and lead prediction","author":"Agamah","year":"2019","journal-title":"Briefings Bioinf."},{"key":"2026081804382136300_cit9","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 Cent. Sci."},{"key":"2026081804382136300_cit10","doi-asserted-by":"publisher","first-page":"1157","DOI":"10.1016\/j.drudis.2019.03.015","article-title":"ADMET modeling\napproaches in drug\ndiscovery","volume":"24","author":"Ferreira","year":"2019","journal-title":"Drug Discovery Today"},{"key":"2026081804382136300_cit11","doi-asserted-by":"publisher","first-page":"4311","DOI":"10.1021\/acs.molpharmaceut.8b00930","article-title":"Artificial\nIntelligence for Drug Discovery, Biomarker Development, and Generation\nof Novel Chemistry","volume":"15","author":"Zhavoronkov","year":"2018","journal-title":"Mol. Pharm."},{"key":"2026081804382136300_cit12","doi-asserted-by":"publisher","first-page":"463","DOI":"10.1038\/s41573-019-0024-5","article-title":"Applications\nof machine learning in drug discovery and development","volume":"18","author":"Vamathevan","year":"2019","journal-title":"Nat. Rev. Drug Discovery"},{"key":"2026081804382136300_cit13","doi-asserted-by":"publisher","first-page":"1978","DOI":"10.3390\/ijms10051978","article-title":"Current mathematical methods used in QSAR\/QSPR studies","volume":"10","author":"Liu","year":"2009","journal-title":"Int. J. Mol. Sci."},{"key":"2026081804382136300_cit14","doi-asserted-by":"publisher","first-page":"626","DOI":"10.1016\/j.drudis.2017.12.001","article-title":"Network-based technologies for early drug discovery","volume":"23","author":"Fotis","year":"2018","journal-title":"Drug Discovery Today"},{"key":"2026081804382136300_cit15","doi-asserted-by":"publisher","first-page":"1680","DOI":"10.1016\/j.drudis.2017.08.010","article-title":"From machine learning to deep learning:\nprogress in machine intelligence for rational drug discovery","volume":"22","author":"Zhang","year":"2017","journal-title":"Drug Discovery Today"},{"key":"2026081804382136300_cit16","doi-asserted-by":"publisher","first-page":"8749","DOI":"10.1021\/acs.jmedchem.9b00959","article-title":"Pushing the Boundaries of Molecular Representation for Drug Discovery\nwith the Graph Attention Mechanism","volume":"63","author":"Xiong","year":"2020","journal-title":"J. Med.\nChem."},{"key":"2026081804382136300_cit17","doi-asserted-by":"publisher","first-page":"2148","DOI":"10.1109\/jbhi.2018.2879744","article-title":"Exploring Joint AB-LSTM With Embedded\nLemmas for Adverse Drug Reaction Discovery","volume":"23","author":"Santiso","year":"2019","journal-title":"IEEE J. Biomed. Health Inform."},{"key":"2026081804382136300_cit18","doi-asserted-by":"publisher","first-page":"595","DOI":"10.1007\/s10822-016-9938-8","article-title":"Molecular\ngraph convolutions: moving beyond fingerprints","volume":"30","author":"Kearnes","year":"2016","journal-title":"J. Comput.-Aided Mol. Des."},{"key":"2026081804382136300_cit19","doi-asserted-by":"publisher","first-page":"143","DOI":"10.1038\/s41597-019-0151-1","article-title":"AqSolDB, a\ncurated reference set\nof aqueous solubility and 2D descriptors for a diverse set of compounds","volume":"6","author":"Sorkun","year":"2019","journal-title":"Sci. Data"},{"key":"2026081804382136300_cit20","doi-asserted-by":"publisher","first-page":"1545","DOI":"10.1002\/jps.10408","article-title":"Biological,\npharmaceutical, and analytical considerations\nwith respect to the transport media used in the absorption screening\nsystem, Caco-2","volume":"92","author":"Ingels","year":"2003","journal-title":"J. Pharm. Sci."},{"key":"2026081804382136300_cit21","doi-asserted-by":"publisher","first-page":"3630","DOI":"10.1016\/j.xphs.2019.07.014","article-title":"Constructing\nan In Silico Three-Class Predictor of Human Intestinal Absorption\nWith Caco-2 Permeability and Dried-DMSO Solubility","volume":"108","author":"Esaki","year":"2019","journal-title":"J. Pharm. Sci."},{"key":"2026081804382136300_cit22","article-title":"Deeply Learning Molecular Structure-Property\nRelationships Using Attention-And Gate-Augmented Graph Convolutional\nNetwork","author":"Ryu","year":"2018"},{"key":"2026081804382136300_cit23","doi-asserted-by":"publisher","first-page":"3069","DOI":"10.1021\/acs.molpharmaceut.7b00286","article-title":"Continuous Intestinal\nAbsorption\nModel Based on the Convection-Diffusion Equation","volume":"14","author":"Nagar","year":"2017","journal-title":"Mol. Pharm."},{"key":"2026081804382136300_cit24","doi-asserted-by":"publisher","first-page":"2564","DOI":"10.1002\/jps.23609","article-title":"Establishment\nof novel prediction system of intestinal absorption in humans using\nhuman intestinal tissues","volume":"102","author":"Miyake","year":"2013","journal-title":"J. Pharm. Sci."},{"key":"2026081804382136300_cit25","doi-asserted-by":"publisher","first-page":"915","DOI":"10.1016\/j.xphs.2015.11.035","article-title":"Application of a Human Intestinal Epithelial Cell Monolayer\nto the Prediction of Oral Drug Absorption in Humans as a Superior\nAlternative to the Caco-2 Cell Monolayer","volume":"105","author":"Takenaka","year":"2016","journal-title":"J.\nPharm. Sci."},{"key":"2026081804382136300_cit26","doi-asserted-by":"publisher","first-page":"530","DOI":"10.1002\/jps.22796","article-title":"Optimization\nof a parallel artificial membrane permeability assay for the fast\nand simultaneous prediction of human intestinal absorption and plasma\nprotein binding of drug candidates: application to dibenz\u00ad[b,f]\u00adazepine-5-carboxamide\nderivatives","volume":"101","author":"Fortuna","year":"2012","journal-title":"J. Pharm. Sci."},{"key":"2026081804382136300_cit27","doi-asserted-by":"publisher","first-page":"1798","DOI":"10.1016\/j.xphs.2018.03.015","article-title":"Exploring a Kinetic Model Approach\nin Biopharmaceutics: Estimating the Fraction Absorbed of Orally Administered\nDrugs in Humans","volume":"107","author":"Chiang","year":"2018","journal-title":"J. Pharm. Sci."},{"key":"2026081804382136300_cit28","doi-asserted-by":"publisher","first-page":"679","DOI":"10.1016\/j.ejps.2013.05.019","article-title":"In silico\npredictions of gastrointestinal drug absorption in pharmaceutical\nproduct development: application of the mechanistic absorption model\nGI-Sim","volume":"49","author":"Sjo\u0308gren","year":"2013","journal-title":"Eur. J. Pharm. Sci."},{"key":"2026081804382136300_cit29","doi-asserted-by":"publisher","first-page":"275","DOI":"10.1016\/j.ijpharm.2016.01.019","article-title":"Polar interactions\ndrug\/phospholipids\nestimated by IAM-HPLC vs cultured cell line passage data: Their relationships\nand comparison of their effectiveness in predicting drug human intestinal\nabsorption","volume":"500","author":"Grumetto","year":"2016","journal-title":"Int. J. Pharm."},{"key":"2026081804382136300_cit30","doi-asserted-by":"publisher","first-page":"1444","DOI":"10.1002\/jcc.25213","article-title":"TopP-S: 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."},{"key":"2026081804382136300_cit31","doi-asserted-by":"publisher","first-page":"519","DOI":"10.1208\/s12248-011-9290-9","article-title":"BDDCS applied to over 900 drugs","volume":"13","author":"Benet","year":"2011","journal-title":"AAPS J."},{"key":"2026081804382136300_cit32","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":"2026081804382136300_cit33","doi-asserted-by":"publisher","first-page":"275","DOI":"10.1016\/j.ijpharm.2016.01.019","article-title":"Polar interactions drug\/phospholipids\nestimated by IAM-HPLC vs cultured cell line passage data: Their relationships\nand comparison of their effectiveness in predicting drug human intestinal\nabsorption","volume":"500","author":"Grumetto","year":"2016","journal-title":"Int. J. Pharm."},{"key":"2026081804382136300_cit34","doi-asserted-by":"publisher","first-page":"1950","DOI":"10.1016\/j.chroma.2010.01.071","article-title":"A high\nthroughput dried DMSO LogD lipophilicity measurement based on 96-well\nshake-flask and atmospheric pressure photoionization mass spectrometry\ndetection","volume":"1217","author":"Alelyunas","year":"2010","journal-title":"J. Chromatogr. A"},{"key":"2026081804382136300_cit35","doi-asserted-by":"publisher","first-page":"32","DOI":"10.1002\/med.21377","article-title":"Strategies for the\nOptimization of\nNatural Leads to Anticancer Drugs or Drug Candidates","volume":"36","author":"Xiao","year":"2016","journal-title":"Med. Res. Rev."},{"key":"2026081804382136300_cit36","doi-asserted-by":"publisher","first-page":"1250","DOI":"10.1021\/jm021053p","article-title":"A comparison\nof physiochemical property profiles of development and marketed oral\ndrugs","volume":"46","author":"Wenlock","year":"2003","journal-title":"J. Med. Chem."},{"key":"2026081804382136300_cit37","doi-asserted-by":"publisher","first-page":"99","DOI":"10.1016\/j.addr.2016.04.018","article-title":"The solubility-permeability\ninterplay and oral drug formulation design: Two heads are better than\none","volume":"101","author":"Dahan","year":"2016","journal-title":"Adv. Drug Delivery Rev."},{"key":"2026081804382136300_cit38","doi-asserted-by":"publisher","first-page":"370","DOI":"10.1039\/C8SC04228D","article-title":"A graph-convolutional\nneural network\nmodel for the prediction of chemical reactivity","volume":"10","author":"Coley","year":"2019","journal-title":"Chem. Sci."},{"key":"2026081804382136300_cit39","doi-asserted-by":"publisher","first-page":"4131","DOI":"10.1021\/acs.jcim.9b00628","article-title":"Graph Convolutional\nNeural Networks for Predicting\nDrug-Target Interactions","volume":"59","author":"Torng","year":"2019","journal-title":"J. Chem. Inf. Model."},{"key":"2026081804382136300_cit40","doi-asserted-by":"publisher","first-page":"919","DOI":"10.1093\/bib\/bbz042","article-title":"Graph convolutional networks for computational drug development and\ndiscovery","volume":"21","author":"Sun","year":"2020","journal-title":"Briefings Bioinf."},{"key":"2026081804382136300_cit41","doi-asserted-by":"publisher","first-page":"29","DOI":"10.1016\/j.ejps.2016.07.016","article-title":"Solubility, lipophilicity and membrane permeability\nof some fluoroquinolone antimicrobials","volume":"93","author":"Blokhina","year":"2016","journal-title":"Eur.\nJ. Pharm. Sci."},{"key":"2026081804382136300_cit42","doi-asserted-by":"publisher","first-page":"84","DOI":"10.1016\/j.ijpharm.2017.10.058","article-title":"Active intestinal drug\nabsorption and the solubility-permeability\ninterplay","volume":"537","author":"Porat","year":"2018","journal-title":"Int. J. Pharm."},{"key":"2026081804382136300_cit43","doi-asserted-by":"publisher","first-page":"11","DOI":"10.1016\/j.addr.2015.01.001","article-title":"Advances in computationally modeling\nhuman oral bioavailability","volume":"86","author":"Wang","year":"2015","journal-title":"Adv. Drug Delivery\nRev."}],"container-title":["Journal of Chemical Information and Modeling"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/pubs.acs.org\/doi\/pdf\/10.1021\/acs.jcim.0c00568","content-type":"application\/pdf","content-version":"vor","intended-application":"unspecified"},{"URL":"https:\/\/pubs.acs.org\/jcisd8\/article-pdf\/60\/10\/4603\/8899588\/ci0c00568.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/pubs.acs.org\/jcisd8\/article-pdf\/60\/10\/4603\/8899588\/ci0c00568.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,18]],"date-time":"2026-08-18T09:53:50Z","timestamp":1787046830000},"score":1,"resource":{"primary":{"URL":"https:\/\/pubs.acs.org\/jcisd8\/article\/60\/10\/4603\/849762\/Optimizing-Pharmacokinetic-Property-Prediction"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,8,17]]},"references-count":43,"journal-issue":{"issue":"10","published-online":{"date-parts":[[2020,8,17]]},"published-print":{"date-parts":[[2020,10,26]]}},"URL":"https:\/\/doi.org\/10.1021\/acs.jcim.0c00568","relation":{},"ISSN":["1549-9596","1549-960X"],"issn-type":[{"value":"1549-9596","type":"print"},{"value":"1549-960X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020,8,17]]}}}