A universal methodology for reliable predicting the non-steroidal anti-inflammatory drug solubility in supercritical carbon dioxide

Abstract

Understanding the drug solubility behavior is likely the first essential requirement for designing the supercritical technology for pharmaceutical processing. Therefore, this study utilizes different machine learning scenarios to simulate the solubility of twelve non-steroidal anti-inflammatory drugs (NSAIDs) in the supercritical carbon dioxide (SCCO2). The considered NSAIDs are Fenoprofen, Flurbiprofen, Ibuprofen, Ketoprofen, Loxoprofen, Nabumetone, Naproxen, Nimesulide, Phenylbutazone, Piroxicam, Salicylamide, and Tolmetin. Physical characteristics of the drugs (molecular weight and melting temperature), operating conditions (pressure and temperature), and solvent property (SCCO2 density) are effectively used to estimate the drug solubility. Monitoring and comparing the prediction accuracy of twelve intelligent paradigms from three categories (artificial neural networks, support vector regression, and hybrid neuro-fuzzy) approves that adaptive neuro-fuzzy inference is the best tool for the considered task. The hybrid optimization strategy adjusts the cluster radius of the subtractive clustering membership function to 0.6111. This model estimates 254 laboratory-measured solubility data with the AAPRE = 3.13%, MSE = 2.58 × 10–9, and R2 = 0.99919. The leverage technique confirms that outliers may poison less than four percent of the experimental data. In addition, the proposed hybrid paradigm is more reliable than the equations of state and available correlations in the literature. Experimental measurements, model predictions, and relevancy analyses justified that the drug solubility in SCCO2 increases by increasing temperature and pressure. The results show that Ibuprofen and Naproxen are the most soluble and insoluble drugs in SCCO2, respectively.

Prediction of Drug-like Compounds Solubility in Supercritical Carbon Dioxide: A Comparative Study between Classical Density Functional Theory and Machine Learning Approaches

“…Our next step was to present ML models developed for the combined data set (training set plus test set), i.e., for all data (named "combined set"). An independent test of the predictive ability of the ML model was carried out for a set of antiinflammatory drugs 54 (named "anti-inflammatory set"). These set included 258 records and did not overlap with the compounds in the set used to develop the model.…”

“…Additionally, we compared the performance of our previously developed cDFT-based approach with the ML-based model. To facilitate the comparison, we used a set of 12 recently investigated 54 nonsteroidal anti-inflammatory drugs.…”

“…At present, one of the most promising approaches for such a task involves the use of machine learning (ML) methods, as evidenced by the recent growth in the literature dedicated to the topic. − However, it is important to note that a majority of the constructed QSPR models are mostly used for the inter- or extrapolation of data, based on a rather small initial set. Notably, there are two noteworthy works , which utilize a larger data set of over a hundred drugs for model training, claiming that their models can successfully predict the properties of new compounds, expanding beyond the original training set.…”

Developing an accurate empirical correlation for predicting anti-cancer drugs’ dissolution in supercritical carbon dioxide

“…These characteristics have drawn attention to the SCFs as solvent media for supercritical extraction/purification purposes in a wide range of applications 1 . Carbon dioxide (CO 2 ) is likely the most trustful supercritical fluid in energy 3 , food 4 , pharmaceutical 5 , 6 , and bioactive agent delivery 7 – 10 applications. Indeed, the non-toxic, inflammable, and non-explosive nature of supercritical carbon dioxide (SCCO 2 ) is responsible for these trustful applications 2 .…”

Solubility Optimization of Loxoprofen as a Nonsteroidal Anti-Inflammatory Drug: Statistical Modeling and Optimization

“…The invention of novel drugs and the development of promising therapeutic approaches can be considered as the most important challenges in the pharmaceutical industry [1,2]. Perceiving the solubility behavior of various therapeutic drugs is known as a vital key point toward the efficient designation of the supercritical approach for the pharmaceutical industry [3]. Solubility can be defined as the capability of a solute to be dissolved in a particular solvent to obtain a homogenous Loxoprofen sodium is known as an important nonsteroidal anti-inflammatory drug (NSAID), which has considerable analgesic influence (10)(11)(12)(13)(14)(15)(16)(17)(18)(19)(20) times greater than ketoprofen or naproxen) that made it an appropriate anti-inflammatory and antipyretic agent [4].…”