{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,21]],"date-time":"2026-09-21T19:38:21Z","timestamp":1790019501503,"version":"4.0.1"},"reference-count":47,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2025,12,8]],"date-time":"2025-12-08T00:00:00Z","timestamp":1765152000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2026,1,12]],"date-time":"2026-01-12T00:00:00Z","timestamp":1768176000000},"content-version":"vor","delay-in-days":35,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Sci Rep"],"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>\n                    Precise estimation of pharmaceutical solubility in supercritical carbon dioxide (scCO\n                    <jats:sub>2<\/jats:sub>\n                    ) is essential for optimizing pharmaceutical applications, including particle size reduction, the development of solid dispersions, and controlled-release formulations. In this research, we present a comparative analysis of three machine learning regression models\u2014Lasso Regression, Gaussian Process Regression (GPR), and Nu-Support Vector Regression (Nu-SVR)\u2014for predicting the solubility of exemestane (EXE), a poorly water-soluble anticancer drug, in scCO\n                    <jats:sub>2<\/jats:sub>\n                    under varying temperature and pressure conditions. The dataset used in this work consists of 45 experimental measurements encompassing temperature (T in K), pressure (P in MPa), and solubility (in g\/L) of EXE. The dataset was divided into training and testing data subsets to facilitate reliable model validation. Model performance was thoroughly evaluated using metrics such as the R\u00b2, RMSE, MAE, and AARD%. Additionally, decision surfaces and observed-versus-predicted plots were generated to visually assess model accuracy. Among the applied models, Gaussian Process Regression demonstrated superior predictive capability with an R\u00b2 score of 0.996, Maximum error of 3.27, significantly outperforming both Lasso and Nu-SVR models. These results indicate that GPR effectively captures the nonlinear relationship between process variables and drug solubility, offering high generalization and precision. Feature importance analysis confirmed that pressure has the most significant influence on solubility behavior, while temperature also contributes positively to solubility trends. Residual analysis further validated the consistency and reliability of the GPR-based model. This work contributes to the growing application of machine learning techniques in pharmaceutical process modeling, particularly in supercritical fluid-based drug delivery systems. The proposed GPR model provides a reliable and efficient tool for predicting solubility, supporting the design and optimization of scCO\n                    <jats:sub>2<\/jats:sub>\n                    -assisted drug formulation methods.\n                  <\/jats:p>","DOI":"10.1038\/s41598-025-31291-9","type":"journal-article","created":{"date-parts":[[2025,12,8]],"date-time":"2025-12-08T16:14:41Z","timestamp":1765210481000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["Developing Gaussian process regression, Lasso regression, and Nu-support vector regression models for predicting solubility of exemestane in supercritical CO2"],"prefix":"10.1038","volume":"16","author":[{"given":"Jawza A.","family":"Almutairi","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Thamir","family":"Malik","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2025,12,8]]},"reference":[{"issue":"3","key":"31291_CR1","doi-asserted-by":"publisher","first-page":"184","DOI":"10.2174\/1872211310666161103120006","volume":"10","author":"S Wairkar","year":"2016","unstructured":"Wairkar, S., Gaud, R. & Raghavan, A. Multi-particulate systems: cutting-edge technology for controlled drug delivery. Recent Pat. Drug Deliv. Formul. 10(3), 184\u2013191 (2016).","journal-title":"Recent Pat. Drug Deliv. Formul."},{"key":"31291_CR2","doi-asserted-by":"crossref","unstructured":"Hillery, A. & Park, K. Drug Delivery: Fundamentals and Applications (CRC, 2016).","DOI":"10.1201\/9781315382579"},{"issue":"5","key":"31291_CR3","first-page":"e1637","volume":"12","author":"E Garbayo","year":"2020","unstructured":"Garbayo, E. et al. Nanomedicine and drug delivery systems in cancer and regenerative medicine. Wiley Interdisciplinary Reviews: Nanomed. Nanobiotechnol. 12(5), e1637 (2020).","journal-title":"Wiley Interdisciplinary Reviews: Nanomed. Nanobiotechnol."},{"issue":"1","key":"31291_CR4","first-page":"1","volume":"1","author":"MR Baig","year":"2018","unstructured":"Baig, M. R., Shahiwala, A. & Khan, S. Sensible use of technologies to increase solubility and bioavailability in formulation development. Advancements Bioequivalence Bioavailab. 1(1), 1\u20134 (2018).","journal-title":"Advancements Bioequivalence Bioavailab."},{"key":"31291_CR5","doi-asserted-by":"publisher","first-page":"115417","DOI":"10.1016\/j.molliq.2021.115417","volume":"328","author":"AS Taleghani","year":"2021","unstructured":"Taleghani, A. S. et al. Mesoporous silica nanoparticles as a versatile nanocarrier for cancer treatment: A review. J. Mol. Liq. 328, 115417 (2021).","journal-title":"J. Mol. Liq."},{"issue":"3","key":"31291_CR6","first-page":"1681","volume":"2","author":"M Yasir","year":"2010","unstructured":"Yasir, M. et al. Biopharmaceutical classification system: an account. Int. J. PharmTech Res. 2(3), 1681\u20131690 (2010).","journal-title":"Int. J. PharmTech Res."},{"issue":"3","key":"31291_CR7","doi-asserted-by":"publisher","first-page":"388","DOI":"10.1016\/j.addr.2007.03.025","volume":"60","author":"T Yasuji","year":"2008","unstructured":"Yasuji, T., Takeuchi, H. & Kawashima, Y. Particle design of poorly water-soluble drug substances using supercritical fluid technologies. Adv. Drug Deliv. Rev. 60(3), 388\u2013398 (2008).","journal-title":"Adv. Drug Deliv. Rev."},{"key":"31291_CR8","doi-asserted-by":"crossref","unstructured":"Notej, B. et al. Increasing solubility of phenytoin and raloxifene drugs: application of supercritical CO2 technology. J. Mol. Liq. 121246 (2023).","DOI":"10.1016\/j.molliq.2023.121246"},{"key":"31291_CR9","doi-asserted-by":"crossref","unstructured":"Alshahrani, S. M. et al. Measurement of metoprolol solubility in supercritical carbon dioxide; experimental and modeling study. Case Stud. Therm. Eng. 102764 (2023).","DOI":"10.1016\/j.csite.2023.102764"},{"key":"31291_CR10","doi-asserted-by":"publisher","first-page":"121247","DOI":"10.1016\/j.ijpharm.2021.121247","volume":"610","author":"P Tran","year":"2021","unstructured":"Tran, P. & Park, J. S. Application of supercritical fluid technology for solid dispersion to enhance solubility and bioavailability of poorly water-soluble drugs. Int. J. Pharm. 610, 121247 (2021).","journal-title":"Int. J. Pharm."},{"key":"31291_CR11","doi-asserted-by":"publisher","first-page":"116439","DOI":"10.1016\/j.molliq.2021.116439","volume":"337","author":"Y Cao","year":"2021","unstructured":"Cao, Y. et al. Recent advancements in molecular separation of gases using microporous membrane systems: A comprehensive review on the applied liquid absorbents. J. Mol. Liq. 337, 116439 (2021).","journal-title":"J. Mol. Liq."},{"key":"31291_CR12","doi-asserted-by":"publisher","first-page":"111806","DOI":"10.1016\/j.rser.2021.111806","volume":"154","author":"Z Cheng","year":"2022","unstructured":"Cheng, Z. et al. Post-combustion CO2 capture and separation in flue gas based on hydrate technology: A review. Renew. Sustain. Energy Rev. 154, 111806 (2022).","journal-title":"Renew. Sustain. Energy Rev."},{"issue":"11","key":"31291_CR13","doi-asserted-by":"publisher","first-page":"104180","DOI":"10.1016\/j.arabjc.2022.104180","volume":"15","author":"RM Alzhrani","year":"2022","unstructured":"Alzhrani, R. M., Almalki, A. H. & Alshehri, S. Novel numerical simulation of drug solubility in supercritical CO2 using machine learning technique: Lenalidomide case study. Arab. J. Chem. 15(11), 104180 (2022).","journal-title":"Arab. J. Chem."},{"key":"31291_CR14","doi-asserted-by":"publisher","first-page":"105626","DOI":"10.1016\/j.supflu.2022.105626","volume":"186","author":"MM Azim","year":"2022","unstructured":"Azim, M. M. et al. Modeling the solubility of non-steroidal anti-inflammatory drugs (ibuprofen and ketoprofen) in supercritical CO2 using PC-SAFT. J. Supercrit. Fluids. 186, 105626 (2022).","journal-title":"J. Supercrit. Fluids"},{"issue":"25","key":"31291_CR15","doi-asserted-by":"publisher","first-page":"2381","DOI":"10.1056\/NEJMoa1103507","volume":"364","author":"PE Goss","year":"2011","unstructured":"Goss, P. E. et al. Exemestane for breast-cancer prevention in postmenopausal women. N. Engl. J. Med. 364(25), 2381\u20132391 (2011).","journal-title":"N. Engl. J. Med."},{"key":"31291_CR16","doi-asserted-by":"publisher","first-page":"675","DOI":"10.2165\/00003495-199958040-00007","volume":"58","author":"LJ Scott","year":"1999","unstructured":"Scott, L. J. & Wiseman, L. R. Exemestane. Drugs. 58, 675\u2013680 (1999).","journal-title":"Drugs"},{"key":"31291_CR17","doi-asserted-by":"crossref","unstructured":"Chaturvedi, S. & Garg, A. A comprehensive review on novel delivery approaches for exemestane. J. Drug Deliv. Sci. Technol. 103655 (2022).","DOI":"10.1016\/j.jddst.2022.103655"},{"key":"31291_CR18","doi-asserted-by":"publisher","first-page":"105673","DOI":"10.1016\/j.jtice.2024.105673","volume":"164","author":"Y Shang","year":"2024","unstructured":"Shang, Y. et al. Artificial neural network hyperparameters optimization for predicting the thermal conductivity of MXene\/graphene nanofluids. J. Taiwan Inst. Chem. Eng. 164, 105673 (2024).","journal-title":"J. Taiwan Inst. Chem. Eng."},{"key":"31291_CR19","doi-asserted-by":"publisher","first-page":"101180","DOI":"10.1016\/j.cscee.2025.101180","volume":"11","author":"MS Graish","year":"2025","unstructured":"Graish, M. S. et al. Prediction of the viscosity of iron-CuO\/water-ethylene glycol non-Newtonian hybrid nanofluids using different machine learning algorithms. Case Stud. Chem. Environ. Eng. 11, 101180 (2025).","journal-title":"Case Stud. Chem. Environ. Eng."},{"key":"31291_CR20","doi-asserted-by":"crossref","unstructured":"Ismail, M. A. et al. Machine learning-based optimization and dynamic performance analysis of a hybrid geothermal-solar multi-output system for electricity, cooling, desalinated water, and hydrogen production: A case study. App. Therm. Eng. 267, 125834 (2025).","DOI":"10.1016\/j.applthermaleng.2025.125834"},{"key":"31291_CR21","doi-asserted-by":"publisher","first-page":"113378","DOI":"10.1016\/j.solener.2025.113378","volume":"291","author":"H Togun","year":"2025","unstructured":"Togun, H. et al. Advancing organic photovoltaic cells for a sustainable future: the role of artificial intelligence (AI) and deep learning (DL) in enhancing performance and innovation. Sol. Energy. 291, 113378 (2025).","journal-title":"Sol. Energy"},{"issue":"1","key":"31291_CR22","doi-asserted-by":"publisher","first-page":"p1986","DOI":"10.1038\/s41598-025-85236-3","volume":"15","author":"T Hai","year":"2025","unstructured":"Hai, T. et al. Optimizing ternary hybrid nanofluids using neural networks, gene expression programming, and multi-objective particle swarm optimization: a computational intelligence strategy. Sci. Rep. 15(1), p1986 (2025).","journal-title":"Sci. Rep."},{"issue":"7","key":"31291_CR23","doi-asserted-by":"publisher","first-page":"9448","DOI":"10.3390\/s120709448","volume":"12","author":"D Bhatt","year":"2012","unstructured":"Bhatt, D. et al. An enhanced mems error modeling approach based on nu-support vector regression. Sensors 12(7), 9448\u20139466 (2012).","journal-title":"Sensors"},{"key":"31291_CR24","doi-asserted-by":"crossref","unstructured":"Martin, M. On-line support vector machine regression. In European Conference on Machine Learning. (Springer, 2002).","DOI":"10.1007\/3-540-36755-1_24"},{"issue":"14","key":"31291_CR25","doi-asserted-by":"publisher","first-page":"4357","DOI":"10.3390\/molecules27144357","volume":"27","author":"M Alqarni","year":"2022","unstructured":"Alqarni, M. et al. Solubility optimization of loxoprofen as a nonsteroidal anti-inflammatory drug: statistical modeling and optimization. Molecules 27(14), 4357 (2022).","journal-title":"Molecules"},{"issue":"1","key":"31291_CR26","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1016\/j.jmp.2011.08.004","volume":"56","author":"SJ Gershman","year":"2012","unstructured":"Gershman, S. J. & Blei, D. M. A tutorial on Bayesian nonparametric models. J. Math. Psychol. 56(1), 1\u201312 (2012).","journal-title":"J. Math. Psychol."},{"key":"31291_CR27","doi-asserted-by":"crossref","unstructured":"Williams, C. K. Prediction with Gaussian processes: from linear regression to linear prediction and beyond. In Learning in Graphical Models 599\u2013621 (Springer, 1998).","DOI":"10.1007\/978-94-011-5014-9_23"},{"key":"31291_CR28","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1016\/j.jmp.2018.03.001","volume":"85","author":"E Schulz","year":"2018","unstructured":"Schulz, E., Speekenbrink, M. & Krause, A. A tutorial on Gaussian process regression: Modelling, exploring, and exploiting functions. J. Math. Psychol. 85, 1\u201316 (2018).","journal-title":"J. Math. Psychol."},{"key":"31291_CR29","doi-asserted-by":"crossref","unstructured":"Hoang, N. D. et al. Estimating compressive strength of high performance concrete with Gaussian process regression model. Adv. Civil Eng. 2016 (2016).","DOI":"10.1155\/2016\/2861380"},{"issue":"2","key":"31291_CR30","doi-asserted-by":"publisher","first-page":"271","DOI":"10.1016\/j.jkss.2014.09.003","volume":"44","author":"C Kim","year":"2015","unstructured":"Kim, C. et al. Case influence diagnostics in the Lasso regression. J. Korean Stat. Soc. 44(2), 271\u2013279 (2015).","journal-title":"J. Korean Stat. Soc."},{"issue":"3","key":"31291_CR31","doi-asserted-by":"publisher","first-page":"203","DOI":"10.1016\/j.supflu.2009.06.015","volume":"50","author":"M Hojjati","year":"2009","unstructured":"Hojjati, M. et al. Supercritical CO2 and highly selective aromatase inhibitors: Experimental solubility and empirical data correlation. J. Supercrit. Fluids. 50(3), 203\u2013209 (2009).","journal-title":"J. Supercrit. Fluids"},{"key":"31291_CR32","doi-asserted-by":"publisher","first-page":"103324","DOI":"10.1016\/j.bspc.2021.103324","volume":"72","author":"S Chakraborty","year":"2022","unstructured":"Chakraborty, S. & Mali, K. Biomedical image segmentation using fuzzy multilevel soft thresholding system coupled modified cuckoo search. Biomed. Signal Process. Control. 72, 103324 (2022).","journal-title":"Biomed. Signal Process. Control"},{"key":"31291_CR33","doi-asserted-by":"crossref","unstructured":"Yang, X. S. & Deb, S. Cuckoo Search Via L\u00e9vy flights. In 2009 World Congress on Nature & Biologically Inspired Computing (NaBIC) (IEEE, 2009).","DOI":"10.1109\/NABIC.2009.5393690"},{"key":"31291_CR34","doi-asserted-by":"publisher","first-page":"105241","DOI":"10.1016\/j.chemolab.2024.105241","volume":"254","author":"Y Liu","year":"2024","unstructured":"Liu, Y. et al. Machine learning based modeling for estimation of drug solubility in supercritical fluid by adjusting important parameters. Chemometr. Intell. Lab. Syst. 254, 105241 (2024).","journal-title":"Chemometr. Intell. Lab. Syst."},{"key":"31291_CR35","doi-asserted-by":"publisher","first-page":"104207","DOI":"10.1016\/j.bspc.2022.104207","volume":"79","author":"Y Wang","year":"2023","unstructured":"Wang, Y. et al. Prognostic staging of esophageal cancer based on prognosis index and cuckoo search algorithm-support vector machine. Biomed. Signal Process. Control. 79, 104207 (2023).","journal-title":"Biomed. Signal Process. Control"},{"key":"31291_CR36","doi-asserted-by":"publisher","first-page":"123229","DOI":"10.1016\/j.molliq.2023.123229","volume":"391","author":"AJ Obaidullah","year":"2023","unstructured":"Obaidullah, A. J. & Almehizia, A. A. Machine learning-based prediction and mathematical optimization of capecitabine solubility through the supercritical CO2 system. J. Mol. Liq. 391, 123229 (2023).","journal-title":"J. Mol. Liq."},{"issue":"18","key":"31291_CR37","doi-asserted-by":"publisher","first-page":"7407","DOI":"10.1016\/j.eswa.2013.06.077","volume":"40","author":"R Grbi\u0107","year":"2013","unstructured":"Grbi\u0107, R., Kurtagi\u0107, D. & Sli\u0161kovi\u0107, D. Stream water temperature prediction based on Gaussian process regression. Expert Syst. Appl. 40(18), 7407\u20137414 (2013).","journal-title":"Expert Syst. Appl."},{"key":"31291_CR38","doi-asserted-by":"crossref","unstructured":"Rasmussen, C. E. Gaussian processes in machine learning. In Summer School on Machine Learning (Springer, 2003).","DOI":"10.1007\/978-3-540-28650-9_4"},{"key":"31291_CR39","doi-asserted-by":"publisher","first-page":"119159","DOI":"10.1016\/j.molliq.2022.119159","volume":"358","author":"H Jin","year":"2022","unstructured":"Jin, H. et al. Computational simulation using machine learning models in prediction of CO2 absorption in environmental applications. J. Mol. Liq. 358, 119159 (2022).","journal-title":"J. Mol. Liq."},{"key":"31291_CR40","doi-asserted-by":"publisher","first-page":"120178","DOI":"10.1016\/j.molliq.2022.120178","volume":"365","author":"Y Lu","year":"2022","unstructured":"Lu, Y. et al. Molecular separation and computational simulation of contaminant removal from wastewater using zirconium UiO-66-(CO2H) 2 metal\u2013organic framework. J. Mol. Liq. 365, 120178 (2022).","journal-title":"J. Mol. Liq."},{"key":"31291_CR41","first-page":"3011","volume":"11","author":"CE Rasmussen","year":"2010","unstructured":"Rasmussen, C. E. & Nickisch, H. Gaussian processes for machine learning (GPML) toolbox. J. Mach. Learn. Res. 11, 3011\u20133015 (2010).","journal-title":"J. Mach. Learn. Res."},{"key":"31291_CR42","unstructured":"Drucker, H. et al. Support vector regression machines. Adv. Neural. Inf. Process. Syst. 9 (1996)."},{"key":"31291_CR43","doi-asserted-by":"crossref","unstructured":"M\u00fcller, K. R. et al. Predicting time series with support vector machines. In International Conference on Artificial Neural Networks. (Springer, 1997).","DOI":"10.1007\/BFb0020283"},{"issue":"3","key":"31291_CR44","doi-asserted-by":"publisher","first-page":"273","DOI":"10.1023\/A:1022627411411","volume":"20","author":"C Cortes","year":"1995","unstructured":"Cortes, C. & Vapnik, V. Support-vector networks. Mach. Learn. 20(3), 273\u2013297 (1995).","journal-title":"Mach. Learn."},{"key":"31291_CR45","doi-asserted-by":"crossref","unstructured":"Catoni, O. Challenging the empirical mean and empirical variance: a deviation study. In Annales de l\u2019IHP Probabilit\u00e9s et statistiques. (2012).","DOI":"10.1214\/11-AIHP454"},{"key":"31291_CR46","doi-asserted-by":"crossref","unstructured":"Naidu, G., Zuva, T. & Sibanda, E. M. A review of evaluation metrics in machine learning algorithms. In Computer Science On-line Conference. (Springer, 2023).","DOI":"10.1007\/978-3-031-35314-7_2"},{"issue":"9","key":"31291_CR47","doi-asserted-by":"publisher","first-page":"102905","DOI":"10.1016\/j.asej.2024.102905","volume":"15","author":"A Alamri","year":"2024","unstructured":"Alamri, A. & Alafnan, A. Artificial intelligence optimization of Alendronate solubility in CO2 supercritical system: Computational modeling and predictive simulation. Ain Shams Eng. J. 15(9), 102905 (2024).","journal-title":"Ain Shams Eng. J."}],"container-title":["Scientific Reports"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.nature.com\/articles\/s41598-025-31291-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41598-025-31291-9","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41598-025-31291-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,13]],"date-time":"2026-01-13T22:05:07Z","timestamp":1768341907000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.nature.com\/articles\/s41598-025-31291-9"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12,8]]},"references-count":47,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2026,12]]}},"alternative-id":["31291"],"URL":"https:\/\/doi.org\/10.1038\/s41598-025-31291-9","relation":{},"ISSN":["2045-2322"],"issn-type":[{"value":"2045-2322","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,12,8]]},"assertion":[{"value":"5 October 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"2 December 2025","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"8 December 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":"The authors declare no competing interests.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"1531"}}