{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T22:44:28Z","timestamp":1777502668046,"version":"3.51.4"},"reference-count":71,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2025,10,29]],"date-time":"2025-10-29T00:00:00Z","timestamp":1761696000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0"},{"start":{"date-parts":[[2025,10,29]],"date-time":"2025-10-29T00:00:00Z","timestamp":1761696000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["J Cheminform"],"DOI":"10.1186\/s13321-025-01103-3","type":"journal-article","created":{"date-parts":[[2025,10,29]],"date-time":"2025-10-29T13:20:44Z","timestamp":1761744044000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":5,"title":["Enhancing molecular property prediction through data integration and consistency assessment"],"prefix":"10.1186","volume":"17","author":[{"given":"Raquel","family":"Parrondo-Pizarro","sequence":"first","affiliation":[]},{"given":"Luca","family":"Menestrina","sequence":"additional","affiliation":[]},{"given":"Ricard","family":"Garcia-Serna","sequence":"additional","affiliation":[]},{"given":"Adri\u00e0","family":"Fern\u00e1ndez-Torras","sequence":"additional","affiliation":[]},{"given":"Jordi","family":"Mestres","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2025,10,29]]},"reference":[{"key":"1103_CR1","doi-asserted-by":"publisher","first-page":"529","DOI":"10.1016\/j.drudis.2021.09.013","volume":"27","author":"KV Danishuddin","year":"2022","unstructured":"Danishuddin KV, Faheem M, Woo Lee K (2022) A decade of machine learning-based predictive models for human pharmacokinetics: Advances and challenges. Drug Discov Today 27:529\u2013537. https:\/\/doi.org\/10.1016\/j.drudis.2021.09.013","journal-title":"Drug Discov Today"},{"key":"1103_CR2","doi-asserted-by":"publisher","first-page":"e13824","DOI":"10.1111\/cts.13824","volume":"17","author":"N Pillai","year":"2024","unstructured":"Pillai N, Abos A, Teutonico D, Mavroudis PD (2024) Machine learning framework to predict pharmacokinetic profile of small molecule drugs based on chemical structure. Clin Transl Sci 17:e13824. https:\/\/doi.org\/10.1111\/cts.13824","journal-title":"Clin Transl Sci"},{"key":"1103_CR3","doi-asserted-by":"publisher","first-page":"829","DOI":"10.1038\/nbt.4233","volume":"36","author":"M Wainberg","year":"2018","unstructured":"Wainberg M, Merico D, Delong A, Frey BJ (2018) Deep learning in biomedicine. Nat Biotechnol 36:829\u2013838. https:\/\/doi.org\/10.1038\/nbt.4233","journal-title":"Nat Biotechnol"},{"key":"1103_CR4","doi-asserted-by":"publisher","first-page":"102549","DOI":"10.1016\/j.is.2025.102549","volume":"132","author":"S Mohammed","year":"2025","unstructured":"Mohammed S, Budach L, Feuerpfeil M et al (2025) The effects of data quality on machine learning performance on tabular data. Inf Syst 132:102549. https:\/\/doi.org\/10.1016\/j.is.2025.102549","journal-title":"Inf Syst"},{"key":"1103_CR5","doi-asserted-by":"publisher","first-page":"102818","DOI":"10.1016\/j.sbi.2024.102818","volume":"86","author":"D van Tilborg","year":"2024","unstructured":"van Tilborg D, Brinkmann H, Criscuolo E et al (2024) Deep learning for low-data drug discovery: hurdles and opportunities. Curr Opin Struct Biol 86:102818. https:\/\/doi.org\/10.1016\/j.sbi.2024.102818","journal-title":"Curr Opin Struct Biol"},{"key":"1103_CR6","doi-asserted-by":"publisher","first-page":"92","DOI":"10.1016\/j.cell.2020.03.022","volume":"181","author":"J Goecks","year":"2020","unstructured":"Goecks J, Jalili V, Heiser LM, Gray JW (2020) How machine learning will transform biomedicine. Cell 181:92\u2013101. https:\/\/doi.org\/10.1016\/j.cell.2020.03.022","journal-title":"Cell"},{"issue":"5","key":"1103_CR7","doi-asserted-by":"publisher","first-page":"2245","DOI":"10.1021\/acs.jmedchem.8b01263","volume":"62","author":"DA Smith","year":"2019","unstructured":"Smith DA, Beaumont K, Maurer TS, Di L (2019) Clearance in drug design. J Med Chem 62(5):2245\u20132255. https:\/\/doi.org\/10.1021\/acs.jmedchem.8b01263","journal-title":"J Med Chem"},{"key":"1103_CR8","doi-asserted-by":"publisher","first-page":"441","DOI":"10.1016\/j.ejmech.2012.06.043","volume":"57","author":"L Di","year":"2012","unstructured":"Di L, Keefer C, Scott DO et al (2012) Mechanistic insights from comparing intrinsic clearance values between human liver microsomes and hepatocytes to guide drug design. Eur J Med Chem 57:441\u2013448. https:\/\/doi.org\/10.1016\/j.ejmech.2012.06.043","journal-title":"Eur J Med Chem"},{"key":"1103_CR9","doi-asserted-by":"publisher","first-page":"312","DOI":"10.1038\/d41586-025-01067-2","volume":"640","author":"A Narayanan","year":"2025","unstructured":"Narayanan A, Kapoor S (2025) Why an overreliance on AI-driven modelling is bad for science. Nature 640:312\u2013314. https:\/\/doi.org\/10.1038\/d41586-025-01067-2","journal-title":"Nature"},{"key":"1103_CR10","doi-asserted-by":"crossref","unstructured":"Bala B, Behal S (2024) A Brief Survey of Data Preprocessing in Machine Learning and Deep Learning Techniques. In: 2024 8th International Conference on I-SMAC (IoT in Social, Mobile, Analytics and Cloud) (I-SMAC). pp 1755\u20131762","DOI":"10.1109\/I-SMAC61858.2024.10714767"},{"key":"1103_CR11","doi-asserted-by":"publisher","first-page":"844","DOI":"10.1001\/jama.2020.1166","volume":"323","author":"OJ Wouters","year":"2020","unstructured":"Wouters OJ, McKee M, Luyten J (2020) Estimated research and development investment needed to bring a new medicine to market, 2009\u20132018. JAMA 323:844\u2013853. https:\/\/doi.org\/10.1001\/jama.2020.1166","journal-title":"JAMA"},{"key":"1103_CR12","doi-asserted-by":"publisher","first-page":"817","DOI":"10.1038\/nrd.2016.184","volume":"15","author":"RK Harrison","year":"2016","unstructured":"Harrison RK (2016) Phase II and phase III failures: 2013\u20132015. Nat Rev Drug Discov 15:817\u2013818. https:\/\/doi.org\/10.1038\/nrd.2016.184","journal-title":"Nat Rev Drug Discov"},{"key":"1103_CR13","doi-asserted-by":"publisher","first-page":"495","DOI":"10.1038\/d41573-019-00074-z","volume":"18","author":"H Dowden","year":"2019","unstructured":"Dowden H, Munro J (2019) Trends in clinical success rates and therapeutic focus. Nat Rev Drug Discov 18:495\u2013496. https:\/\/doi.org\/10.1038\/d41573-019-00074-z","journal-title":"Nat Rev Drug Discov"},{"key":"1103_CR14","doi-asserted-by":"publisher","first-page":"3049","DOI":"10.1016\/j.apsb.2022.02.002","volume":"12","author":"D Sun","year":"2022","unstructured":"Sun D, Gao W, Hu H, Zhou S (2022) Why 90% of clinical drug development fails and how to improve it? Acta Pharm Sin B 12:3049\u20133062. https:\/\/doi.org\/10.1016\/j.apsb.2022.02.002","journal-title":"Acta Pharm Sin B"},{"key":"1103_CR15","doi-asserted-by":"publisher","first-page":"D1633","DOI":"10.1093\/nar\/gkae1075","volume":"53","author":"T Liu","year":"2025","unstructured":"Liu T, Hwang L, Burley SK et al (2025) BindingDB in 2024: a FAIR knowledgebase of protein-small molecule binding data. Nucleic Acids Res 53:D1633\u2013D1644. https:\/\/doi.org\/10.1093\/nar\/gkae1075","journal-title":"Nucleic Acids Res"},{"key":"1103_CR16","doi-asserted-by":"publisher","first-page":"4111","DOI":"10.1021\/jm048957q","volume":"48","author":"R Wang","year":"2005","unstructured":"Wang R, Fang X, Lu Y et al (2005) The PDBbind database: methodologies and updates. J Med Chem 48:4111\u20134119. https:\/\/doi.org\/10.1021\/jm048957q","journal-title":"J Med Chem"},{"key":"1103_CR17","doi-asserted-by":"publisher","first-page":"525","DOI":"10.1021\/cr60274a001","volume":"71","author":"A Leo","year":"1971","unstructured":"Leo A, Hansch C, Elkins D (1971) Partition coefficients and their uses. Chem Rev 71:525\u2013616. https:\/\/doi.org\/10.1021\/cr60274a001","journal-title":"Chem Rev"},{"key":"1103_CR18","doi-asserted-by":"publisher","first-page":"1385","DOI":"10.1124\/dmd.108.020479","volume":"36","author":"RS Obach","year":"2008","unstructured":"Obach RS, Lombardo F, Waters NJ (2008) Trend analysis of a database of intravenous pharmacokinetic parameters in humans for 670 drug compounds. Drug Metab Dispos 36:1385\u20131405. https:\/\/doi.org\/10.1124\/dmd.108.020479","journal-title":"Drug Metab Dispos"},{"key":"1103_CR19","doi-asserted-by":"publisher","first-page":"169","DOI":"10.1080\/17425255.2017.1316449","volume":"14","author":"KR Przybylak","year":"2018","unstructured":"Przybylak KR, Madden JC, Covey-Crump E et al (2018) Characterisation of data resources forin silicomodelling: benchmark datasets for ADME properties. Expert Opin Drug Metab Toxicol 14:169\u2013181. https:\/\/doi.org\/10.1080\/17425255.2017.1316449","journal-title":"Expert Opin Drug Metab Toxicol"},{"key":"1103_CR20","doi-asserted-by":"publisher","unstructured":"Huang K, Fu T, Gao W, et al (2021) Therapeutics data commons: machine learning datasets and tasks for drug discovery and development. Preprint at https:\/\/doi.org\/10.48550\/arXiv.2102.09548.","DOI":"10.48550\/arXiv.2102.09548"},{"key":"1103_CR21","doi-asserted-by":"publisher","first-page":"143","DOI":"10.1038\/s41597-019-0151-1","volume":"6","author":"MC Sorkun","year":"2019","unstructured":"Sorkun MC, Khetan A, Er S (2019) AqSolDB, a curated reference set of aqueous solubility and 2D descriptors for a diverse set of compounds. Sci Data 6:143. https:\/\/doi.org\/10.1038\/s41597-019-0151-1","journal-title":"Sci Data"},{"key":"1103_CR22","doi-asserted-by":"publisher","first-page":"308","DOI":"10.3390\/pharmaceutics17030308","volume":"17","author":"L Menestrina","year":"2025","unstructured":"Menestrina L, Parrondo-Pizarro R, Gomez I et al (2025) Refined ADME profiles for ATC drug classes. Pharmaceutics 17:308. https:\/\/doi.org\/10.3390\/pharmaceutics17030308","journal-title":"Pharmaceutics"},{"key":"1103_CR23","doi-asserted-by":"publisher","first-page":"1892","DOI":"10.1021\/acs.molpharmaceut.4c01086","volume":"22","author":"JA Napoli","year":"2025","unstructured":"Napoli JA, Reutlinger M, Brandl P et al (2025) Multitask deep learning models of combined industrial absorption, distribution, metabolism, and excretion datasets to improve generalization. Mol Pharm 22:1892\u20131900. https:\/\/doi.org\/10.1021\/acs.molpharmaceut.4c01086","journal-title":"Mol Pharm"},{"key":"1103_CR24","doi-asserted-by":"publisher","unstructured":"Liyaqat T, Ahmad T, Saxena C (2024) Advancements in molecular property prediction: a survey of single and multimodal approaches. Preprint at https:\/\/doi.org\/10.48550\/arXiv.2408.09461.","DOI":"10.48550\/arXiv.2408.09461"},{"key":"1103_CR25","doi-asserted-by":"publisher","first-page":"346","DOI":"10.1093\/bib\/bbz153","volume":"22","author":"B G\u00fcven\u00e7 Paltun","year":"2021","unstructured":"G\u00fcven\u00e7 Paltun B, Mamitsuka H, Kaski S (2021) Improving drug response prediction by integrating multiple data sources: matrix factorization, kernel and network-based approaches. Brief Bioinform 22:346\u2013359. https:\/\/doi.org\/10.1093\/bib\/bbz153","journal-title":"Brief Bioinform"},{"key":"1103_CR26","unstructured":"Salesforce, Inc. Tableau Desktop (2025.2.1) [Computer software]. Salesforce, Inc., San Francisco, CA 94105, United States. https:\/\/www.tableau.com\/. Accessed 2 Aug 2025."},{"key":"1103_CR27","unstructured":"Seshadri R. AutoViz: The One-Line Automatic Data Visualization Library (0.1.905) [Computer software]. GitHub. https:\/\/github.com\/AutoViML\/AutoViz. Accessed 2 Aug 2025"},{"key":"1103_CR28","unstructured":"Landrum G. RDKit: Open-source cheminformatics (2024.09.4). https:\/\/www.rdkit.org. Accessed 2 Aug 2025."},{"key":"1103_CR29","doi-asserted-by":"publisher","first-page":"261","DOI":"10.1038\/s41592-019-0686-2","volume":"17","author":"P Virtanen","year":"2020","unstructured":"Virtanen P, Gommers R, Oliphant TE et al (2020) Scipy 1.0: fundamental algorithms for scientific computing in Python. Nat Methods 17:261\u2013272. https:\/\/doi.org\/10.1038\/s41592-019-0686-2","journal-title":"Nat Methods"},{"key":"1103_CR30","doi-asserted-by":"publisher","first-page":"861","DOI":"10.21105\/joss.00861","volume":"3","author":"L McInnes","year":"2018","unstructured":"McInnes L, Healy J, Saul N, Gro\u00dfberger L (2018) UMAP: Uniform manifold approximation and projection. J Open Source Softw 3:861. https:\/\/doi.org\/10.21105\/joss.00861","journal-title":"J Open Source Softw"},{"key":"1103_CR31","doi-asserted-by":"publisher","first-page":"90","DOI":"10.1109\/MCSE.2007.55","volume":"9","author":"JD Hunter","year":"2007","unstructured":"Hunter JD (2007) Matplotlib: a 2D graphics environment. Comput Sci Eng 9:90\u201395. https:\/\/doi.org\/10.1109\/MCSE.2007.55","journal-title":"Comput Sci Eng"},{"issue":"60","key":"1103_CR32","doi-asserted-by":"publisher","first-page":"3021","DOI":"10.21105\/joss.03021","volume":"6","author":"ML Waskom","year":"2021","unstructured":"Waskom ML (2021) Seaborn: statistical data visualization. J Open Source Softw 6(60):3021. https:\/\/doi.org\/10.21105\/joss.03021","journal-title":"J Open Source Softw"},{"key":"1103_CR33","doi-asserted-by":"publisher","first-page":"1466","DOI":"10.1124\/dmd.118.082966","volume":"46","author":"F Lombardo","year":"2018","unstructured":"Lombardo F, Berellini G, Obach RS (2018) Trend analysis of a database of intravenous pharmacokinetic parameters in humans for 1352 drug compounds. Drug Metab Dispos 46:1466\u20131477. https:\/\/doi.org\/10.1124\/dmd.118.082966","journal-title":"Drug Metab Dispos"},{"key":"1103_CR34","doi-asserted-by":"publisher","first-page":"3080","DOI":"10.1021\/acs.jcim.3c02030","volume":"64","author":"J Fan","year":"2024","unstructured":"Fan J, Shi S, Xiang H et al (2024) Predicting elimination of small-molecule drug half-life in pharmacokinetics using ensemble and consensus machine learning methods. J Chem Inf Model 64:3080\u20133092. https:\/\/doi.org\/10.1021\/acs.jcim.3c02030","journal-title":"J Chem Inf Model"},{"key":"1103_CR35","doi-asserted-by":"publisher","first-page":"W422","DOI":"10.1093\/nar\/gkae236","volume":"52","author":"L Fu","year":"2024","unstructured":"Fu L, Shi S, Yi J et al (2024) ADMETlab 3.0: an updated comprehensive online ADMET prediction platform enhanced with broader coverage, improved performance, API functionality and decision support. Nucleic Acids Res 52:W422\u2013W431. https:\/\/doi.org\/10.1093\/nar\/gkae236","journal-title":"Nucleic Acids Res"},{"key":"1103_CR36","doi-asserted-by":"publisher","first-page":"D1180","DOI":"10.1093\/nar\/gkad1004","volume":"52","author":"B Zdrazil","year":"2024","unstructured":"Zdrazil B, Felix E, Hunter F et al (2024) The ChEMBL database in 2023: a drug discovery platform spanning multiple bioactivity data types and time periods. Nucleic Acids Res 52:D1180\u2013D1192. https:\/\/doi.org\/10.1093\/nar\/gkad1004","journal-title":"Nucleic Acids Res"},{"key":"1103_CR37","doi-asserted-by":"publisher","first-page":"baab083","DOI":"10.1093\/database\/baab083","volume":"2022","author":"Q Li","year":"2022","unstructured":"Li Q, Ma S, Zhang X et al (2022) DDPD 1.0: a manually curated and standardized database of digital properties of approved drugs for drug-likeness evaluation and drug development. Database 2022:baab083. https:\/\/doi.org\/10.1093\/database\/baab083","journal-title":"Database"},{"key":"1103_CR38","doi-asserted-by":"publisher","first-page":"1540","DOI":"10.1093\/bioinformatics\/bts186","volume":"28","author":"E Pihan","year":"2012","unstructured":"Pihan E, Colliandre L, Guichou J-F, Douguet D (2012) E-drug 3D: 3D structure collections dedicated to drug repurposing and fragment-based drug design. Bioinformatics 28:1540\u20131541. https:\/\/doi.org\/10.1093\/bioinformatics\/bts186","journal-title":"Bioinformatics"},{"key":"1103_CR39","doi-asserted-by":"publisher","unstructured":"Experimental in vitro DMPK and physicochemical data on a set of publicly disclosed compounds (2025) Wenlock M, Tomkinson N. https:\/\/doi.org\/10.6019\/CHEMBL3301361. Accessed 8 Aug 2025","DOI":"10.6019\/CHEMBL3301361"},{"key":"1103_CR40","doi-asserted-by":"publisher","first-page":"4057","DOI":"10.1021\/acs.jcim.2c00318","volume":"62","author":"H Iwata","year":"2022","unstructured":"Iwata H, Matsuo T, Mamada H et al (2022) Predicting total drug clearance and volumes of distribution using the machine learning-mediated multimodal method through the imputation of various nonclinical data. J Chem Inf Model 62:4057\u20134065. https:\/\/doi.org\/10.1021\/acs.jcim.2c00318","journal-title":"J Chem Inf Model"},{"key":"1103_CR41","doi-asserted-by":"publisher","first-page":"D1100","DOI":"10.1093\/nar\/gkr777","volume":"40","author":"A Gaulton","year":"2012","unstructured":"Gaulton A, Bellis LJ, Bento AP et al (2012) ChEMBL: a large-scale bioactivity database for drug discovery. Nucleic Acids Res 40:D1100\u2013D1107. https:\/\/doi.org\/10.1093\/nar\/gkr777","journal-title":"Nucleic Acids Res"},{"key":"1103_CR42","doi-asserted-by":"publisher","first-page":"178","DOI":"10.1177\/0091270012440282","volume":"53","author":"F Lombardo","year":"2013","unstructured":"Lombardo F, Waters NJ, Argikar UA et al (2013) Comprehensive assessment of human pharmacokinetic prediction based on in vivo animal pharmacokinetic data, Part 2: Clearance. J Clin Pharmacol 53:178\u2013191. https:\/\/doi.org\/10.1177\/0091270012440282","journal-title":"J Clin Pharmacol"},{"key":"1103_CR43","doi-asserted-by":"publisher","first-page":"948","DOI":"10.1021\/ci400001u","volume":"53","author":"VK Gombar","year":"2013","unstructured":"Gombar VK, Hall SD (2013) Quantitative structure-activity relationship models of clinical pharmacokinetics: clearance and volume of distribution. J Chem Inf Model 53:948\u2013957. https:\/\/doi.org\/10.1021\/ci400001u","journal-title":"J Chem Inf Model"},{"key":"1103_CR44","doi-asserted-by":"publisher","first-page":"4844","DOI":"10.1021\/jm900403j","volume":"52","author":"MVS Varma","year":"2009","unstructured":"Varma MVS, Feng B, Obach RS et al (2009) Physicochemical determinants of human renal clearance. J Med Chem 52:4844\u20134852. https:\/\/doi.org\/10.1021\/jm900403j","journal-title":"J Med Chem"},{"key":"1103_CR45","doi-asserted-by":"publisher","first-page":"1098","DOI":"10.1021\/jm901371v","volume":"53","author":"MVS Varma","year":"2010","unstructured":"Varma MVS, Obach RS, Rotter C et al (2010) Physicochemical space for optimum oral bioavailability: contribution of human intestinal absorption and first-pass elimination. J Med Chem 53:1098\u20131108. https:\/\/doi.org\/10.1021\/jm901371v","journal-title":"J Med Chem"},{"key":"1103_CR46","unstructured":"(2025) PubChem Bioassay Record for AID 1159394, Source: ChEMBL. In: Natl. Cent. Biotechnol. Inf. from https:\/\/pubchem.ncbi.nlm.nih.gov\/bioassay\/1159394. Accessed 7 Mar 2025"},{"key":"1103_CR47","unstructured":"(2025) PubChem Bioassay Record for AID 1159396, Source: ChEMBL. In: Natl. Cent. Biotechnol. Inf. https:\/\/pubchem.ncbi.nlm.nih.gov\/bioassay\/1159396. Accessed 7 Mar 2025"},{"key":"1103_CR48","doi-asserted-by":"publisher","first-page":"124","DOI":"10.3109\/00498254.2010.530700","volume":"41","author":"JA Foster","year":"2011","unstructured":"Foster JA, Houston JB, Hallifax D (2011) Comparison of intrinsic clearances in human liver microsomes and suspended hepatocytes from the same donor livers: clearance-dependent relationship and implications for prediction of in vivo clearance. Xenobiotica 41:124\u2013136. https:\/\/doi.org\/10.3109\/00498254.2010.530700","journal-title":"Xenobiotica"},{"key":"1103_CR49","doi-asserted-by":"publisher","first-page":"513","DOI":"10.1177\/0091270009333209","volume":"49","author":"NA Hosea","year":"2009","unstructured":"Hosea NA, Collard WT, Cole S et al (2009) Prediction of human pharmacokinetics from preclinical information: comparative accuracy of quantitative prediction approaches. J Clin Pharmacol 49:513\u2013533. https:\/\/doi.org\/10.1177\/0091270009333209","journal-title":"J Clin Pharmacol"},{"key":"1103_CR50","doi-asserted-by":"publisher","first-page":"D1516","DOI":"10.1093\/nar\/gkae1059","volume":"53","author":"S Kim","year":"2025","unstructured":"Kim S, Chen J, Cheng T et al (2025) PubChem 2025 update. Nucleic Acids Res 53:D1516\u2013D1525. https:\/\/doi.org\/10.1093\/nar\/gkae1059","journal-title":"Nucleic Acids Res"},{"key":"1103_CR51","unstructured":"WHO Collaborating Centre for Drug Statistics Methodology, (2025) ATC classification index with DDDs. 2024. Oslo, Norway. https:\/\/www.who.int\/tools\/atc-ddd-toolkit\/atc-classification. Accessed 8 Nov 2024."},{"key":"1103_CR52","first-page":"2825","volume":"12","author":"F Pedregosa","year":"2011","unstructured":"Pedregosa F, Varoquaux G, Gramfort A et al (2011) Scikit-learn: machine learning in python. J Mach Learn Res 12:2825\u20132830","journal-title":"J Mach Learn Res"},{"key":"1103_CR53","unstructured":"Bergstra J, Yamins D, Cox DD (2013) Making a Science of Model Search: Hyperparameter Optimization in Hundreds of Dimensions for Vision Architectures. In: Sanjoy D, McAllester D (eds). Proceedings of the 30th International Conference on Machine Learning. Proceedings of Machine Learning Research, vol 28. PMLR, p 115\u2013123."},{"key":"1103_CR54","doi-asserted-by":"publisher","first-page":"6086","DOI":"10.1038\/s41598-024-56706-x","volume":"14","author":"O Rainio","year":"2024","unstructured":"Rainio O, Teuho J, Kl\u00e9n R (2024) Evaluation metrics and statistical tests for machine learning. Sci Rep 14:6086. https:\/\/doi.org\/10.1038\/s41598-024-56706-x","journal-title":"Sci Rep"},{"key":"1103_CR55","doi-asserted-by":"publisher","unstructured":"Ash JR, Wognum C, Rodr\u00edguez-P\u00e9rez R, et al (2025) Practically significant method comparison protocols for machine learning in small molecule drug discovery. J Chem Inf Model 65:9398\u20139411. https:\/\/doi.org\/10.1021\/acs.jcim.5c01609","DOI":"10.1021\/acs.jcim.5c01609"},{"key":"1103_CR56","doi-asserted-by":"publisher","first-page":"415","DOI":"10.1111\/j.1365-2885.2004.00605.x","volume":"27","author":"PL Toutain","year":"2004","unstructured":"Toutain PL, Bousquet-M\u00e9lou A (2004) Plasma clearance. J Vet Pharmacol Ther 27:415\u2013425. https:\/\/doi.org\/10.1111\/j.1365-2885.2004.00605.x","journal-title":"J Vet Pharmacol Ther"},{"key":"1103_CR57","doi-asserted-by":"publisher","first-page":"10","DOI":"10.2165\/00003088-198400091-00002","volume":"9","author":"M Rowland","year":"1984","unstructured":"Rowland M (1984) Protein binding and drug clearance. Clin Pharmacokinet 9:10\u201317. https:\/\/doi.org\/10.2165\/00003088-198400091-00002","journal-title":"Clin Pharmacokinet"},{"key":"1103_CR58","doi-asserted-by":"publisher","first-page":"427","DOI":"10.1111\/j.1365-2885.2004.00600.x","volume":"27","author":"PL Toutain","year":"2004","unstructured":"Toutain PL, Bousquet-M\u00e9lou A (2004) Plasma terminal half-life. J Vet Pharmacol Ther 27:427\u2013439. https:\/\/doi.org\/10.1111\/j.1365-2885.2004.00600.x","journal-title":"J Vet Pharmacol Ther"},{"key":"1103_CR59","doi-asserted-by":"publisher","first-page":"4273","DOI":"10.1021\/acs.jmedchem.7b00969","volume":"61","author":"DA Smith","year":"2018","unstructured":"Smith DA, Beaumont K, Maurer TS, Di L (2018) Relevance of half-life in drug design. J Med Chem 61:4273\u20134282. https:\/\/doi.org\/10.1021\/acs.jmedchem.7b00969","journal-title":"J Med Chem"},{"key":"1103_CR60","doi-asserted-by":"publisher","first-page":"75","DOI":"10.1186\/s13321-021-00557-5","volume":"13","author":"V Venkatraman","year":"2021","unstructured":"Venkatraman V (2021) FP-ADMET: a compendium of fingerprint-based ADMET prediction models. J Cheminform 13:75. https:\/\/doi.org\/10.1186\/s13321-021-00557-5","journal-title":"J Cheminform"},{"key":"1103_CR61","doi-asserted-by":"publisher","first-page":"1698","DOI":"10.3390\/molecules24091698","volume":"24","author":"S Kausar","year":"2019","unstructured":"Kausar S, Falcao AO (2019) Analysis and comparison of vector space and metric space representations in QSAR modeling. Molecules 24:1698. https:\/\/doi.org\/10.3390\/molecules24091698","journal-title":"Molecules"},{"key":"1103_CR62","doi-asserted-by":"publisher","first-page":"179","DOI":"10.1007\/s10822-020-00361-7","volume":"35","author":"A Sato","year":"2021","unstructured":"Sato A, Miyao T, Jasial S, Funatsu K (2021) Comparing predictive ability of QSAR\/QSPR models using 2D and 3D molecular representations. J Comput Aided Mol Des 35:179\u2013193. https:\/\/doi.org\/10.1007\/s10822-020-00361-7","journal-title":"J Comput Aided Mol Des"},{"key":"1103_CR63","doi-asserted-by":"publisher","first-page":"15","DOI":"10.1002\/qub2.30","volume":"12","author":"Y Xia","year":"2024","unstructured":"Xia Y, Wang Y, Wang Z, Zhang W (2024) A comprehensive review of molecular optimization in artificial intelligence-based drug discovery. Quant Biol 12:15\u201329. https:\/\/doi.org\/10.1002\/qub2.30","journal-title":"Quant Biol"},{"key":"1103_CR64","doi-asserted-by":"publisher","first-page":"2953","DOI":"10.1002\/jps.23614","volume":"102","author":"T Bohnert","year":"2013","unstructured":"Bohnert T, Gan L-S (2013) Plasma protein binding: from discovery to development. J Pharm Sci 102:2953\u20132994. https:\/\/doi.org\/10.1002\/jps.23614","journal-title":"J Pharm Sci"},{"key":"1103_CR65","doi-asserted-by":"publisher","first-page":"189","DOI":"10.1517\/17425250903405622","volume":"6","author":"P Chao","year":"2010","unstructured":"Chao P, Uss AS, Cheng K (2010) Use of intrinsic clearance for prediction of human hepatic clearance. Expert Opin Drug Metab Toxicol 6:189\u2013198. https:\/\/doi.org\/10.1517\/17425250903405622","journal-title":"Expert Opin Drug Metab Toxicol"},{"key":"1103_CR66","doi-asserted-by":"publisher","unstructured":"Jiang N, Quazi M, Schweikert C, et al (2023) Enhancing ADMET Property Models Performance through Combinatorial Fusion Analysis. https:\/\/doi.org\/10.26434\/chemrxiv-2023-dh70x.","DOI":"10.26434\/chemrxiv-2023-dh70x"},{"key":"1103_CR67","doi-asserted-by":"publisher","first-page":"2150","DOI":"10.1007\/s11095-010-0218-3","volume":"27","author":"D Hallifax","year":"2010","unstructured":"Hallifax D, Foster JA, Houston JB (2010) Prediction of human metabolic clearance from in vitro systems: retrospective analysis and prospective view. Pharm Res 27:2150\u20132161. https:\/\/doi.org\/10.1007\/s11095-010-0218-3","journal-title":"Pharm Res"},{"key":"1103_CR68","doi-asserted-by":"publisher","first-page":"43","DOI":"10.1109\/JPROC.2020.3004555","volume":"109","author":"F Zhuang","year":"2021","unstructured":"Zhuang F, Qi Z, Duan K et al (2021) A comprehensive survey on transfer learning. Proc IEEE 109:43\u201376. https:\/\/doi.org\/10.1109\/JPROC.2020.3004555","journal-title":"Proc IEEE"},{"key":"1103_CR69","unstructured":"Finn C, Abbeel P, Levine S (2017) Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks. In: Precup D, Teh Y W (eds) Proceedings of the 34th International Conference on Machine Learning. Proceedings of Machine Learning Research, vol 70. PMLR, p 1126\u20131135"},{"key":"1103_CR70","doi-asserted-by":"publisher","first-page":"418","DOI":"10.1038\/s41563-019-0332-5","volume":"18","author":"B Bhhatarai","year":"2019","unstructured":"Bhhatarai B, Walters WP, Hop CECA et al (2019) Opportunities and challenges using artificial intelligence in ADME\/tox. Nat Mater 18:418\u2013422. https:\/\/doi.org\/10.1038\/s41563-019-0332-5","journal-title":"Nat Mater"},{"key":"1103_CR71","doi-asserted-by":"publisher","first-page":"423","DOI":"10.1038\/s42256-025-00991-2","volume":"7","author":"T Hanser","year":"2025","unstructured":"Hanser T, Ahlberg E, Amberg A et al (2025) Data-driven federated learning in drug discovery with knowledge distillation. Nat Mach Intell 7:423\u2013436. https:\/\/doi.org\/10.1038\/s42256-025-00991-2","journal-title":"Nat Mach Intell"}],"container-title":["Journal of Cheminformatics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s13321-025-01103-3.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1186\/s13321-025-01103-3\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s13321-025-01103-3.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,29]],"date-time":"2025-10-29T13:20:47Z","timestamp":1761744047000},"score":1,"resource":{"primary":{"URL":"https:\/\/jcheminf.biomedcentral.com\/articles\/10.1186\/s13321-025-01103-3"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,29]]},"references-count":71,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2025,12]]}},"alternative-id":["1103"],"URL":"https:\/\/doi.org\/10.1186\/s13321-025-01103-3","relation":{},"ISSN":["1758-2946"],"issn-type":[{"value":"1758-2946","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,10,29]]},"assertion":[{"value":"5 June 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"21 September 2025","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"29 October 2025","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"R.P., L.M, R.G., A.F.-T, and J. M. are currently employees of the company Chemotargets, of which J. M. is co-founder and co-owner. The company had no role in the design of the study; in the collection, analyses, or interpretation of data; in the writing of the manuscript; or in the decision to publish the results.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"163"}}