Solvent Screening for Solubility Enhancement of Theophylline in Neat, Binary and Ternary NADES Solvents: New Measurements and Ensemble Machine Learning (original) (raw)
Related papers
Molecules, 2024
Deep eutectic solvents (DESs) are popular green media used for various industrial, pharmaceutical, and biomedical applications. However, the possible compositions of eutectic systems are so numerous that it is impossible to study all of them experimentally. To remedy this limitation, the solubility landscape of selected active pharmaceutical ingredients (APIs) in choline chloride- and betaine-based deep eutectic solvents was explored using theoretical models based on machine learning. The available solubility data for the selected APIs, comprising a total of 8014 data points, were collected for the available neat solvents, binary solvent mixtures, and DESs. This set was augmented with new measurements for the popular sulfa drugs in dry DESs. The descriptors used in the machine learning protocol were obtained from the σ-profiles of the considered molecules computed within the COSMO-RS framework. A combination of six sets of descriptors and 36 regressors were tested. Taking into account both accuracy and generalization, it was concluded that the best regressor is nuSVR regressor-based predictive models trained using the relative intermolecular interactions and a twelve-step averaged simplification of the relative σ-profiles.
Molecules, 2023
This study explores the edaravone solubility space encompassing both neat and binary dissolution media. Efforts were made to reveal the inherent concentration limits of common pure and mixed solvents. For this purpose, the published solubility data of the title drug were scrupulously inspected and cured, which made the dataset consistent and coherent. However, the lack of some important types of solvents in the collection called for an extension of the available pool of edaravone solubility data. Hence, new measurements were performed to collect edaravone solubility values in polar non-protic and diprotic media. Such an extended set of data was used in the machine learning process for tuning the parameters of regressor models and formulating the ensemble for predicting new data. In both phases, namely the model training and ensemble formulation, close attention was paid not only to minimizing the deviation of computed values from the experimental ones but also to ensuring high predictive power and accurate solubility computations for new systems. Furthermore, the environmental friendliness characteristics determined based on the common green solvent selection criteria, were included in the analysis. Our applied protocol led to the conclusion that the solubility space defined by ordinary solvents is limited, and it is unlikely to find solvents that are better suited for edaravone dissolution than those described in this manuscript. The theoretical framework presented in this study provides a precise guideline for conducting experiments, as well as saving time and resources in the pursuit of new findings.
Recent Advances in Thermo and Fluid Dynamics, 2015
In this chapter, the applicability of two predictive activity coefficient-based models will be examined. The experimental data from five different types of VLE (vaporliquid equilibrium) and VLLE (vapor-liquid-liquid equilibrium) systems that are common in industry are used for the evaluation. The nonrandom two-liquid segment activity coefficient (NRTL-SAC) and universal functional activity coefficient (UNI-FAC) were selected to model the systems. The various thermodynamic relations existing in the open literature will be discussed and used to predict the solubility of active pharmaceutical ingredients and other small organic molecules in a single or a mixture of solvents. Equations of states, the activity coefficient, and predictive models will be discussed and used for this purpose. We shall also present some of our results on solvent screening using a single and a mixture of solvents.
Solubility Prediction of Drugs in Mixed Solvents Using Partial Solubility Parameters
Journal of Pharmaceutical Sciences, 2011
Solubility of drugs in binary and ternary solvent mixtures composed of water and pharmaceutical cosolvents at different temperatures were predicted using the Jouyban-Acree model and a combination of partial solubility parameters as interaction descriptors in the solution. The generally trained version of the model produced the overall mean percentage deviation values for the back-calculated solubility of drugs in binary solvents of 34.3% and the predicted solubilities in ternary solvent mixtures of 38.0%. In addition, the applicability of the trained model for predicting the solvent composition providing the maximum solubility of a drug was investigated. The results of collected solubility data of drugs in various mixed solvents and the newly measured solubility data of five drugs in ethanol + propylene glycol + water mixtures at 25 • C showed that the model provided acceptable predictions and could be used in the pharmaceutical industry.
Pharmaceutics, 2022
The solubility of active pharmaceutical ingredients is a mandatory physicochemical characteristic in pharmaceutical practice. However, the number of potential solvents and their mixtures prevents direct measurements of all possible combinations for finding environmentally friendly, operational and cost-effective solubilizers. That is why support from theoretical screening seems to be valuable. Here, a collection of acetaminophen and phenacetin solubility data in neat and binary solvent mixtures was used for the development of a nonlinear deep machine learning model using new intuitive molecular descriptors derived from COSMO-RS computations. The literature dataset was augmented with results of new measurements in aqueous binary mixtures of 4-formylmorpholine, DMSO and DMF. The solubility values back-computed with the developed ensemble of neural networks are in perfect agreement with the experimental data, which enables the extensive screening of many combinations of solvents not studied experimentally within the applicability domain of the trained model. The final predictions were presented not only in the form of the set of optimal hyperparameters but also in a more intuitive way by the set of parameters of the Jouyban–Acree equation often used in the co-solvency domain. This new and effective approach is easily extendible to other systems, enabling the fast and reliable selection of candidates for new solvents and directing the experimental solubility screening of active pharmaceutical ingredients.
Nature Communications
Solubility prediction remains a critical challenge in drug development, synthetic route and chemical process design, extraction and crystallisation. Here we report a successful approach to solubility prediction in organic solvents and water using a combination of machine learning (ANN, SVM, RF, ExtraTrees, Bagging and GP) and computational chemistry. Rational interpretation of dissolution process into a numerical problem led to a small set of selected descriptors and subsequent predictions which are independent of the applied machine learning method. These models gave significantly more accurate predictions compared to benchmarked open-access and commercial tools, achieving accuracy close to the expected level of noise in training data (LogS ± 0.7). Finally, they reproduced physicochemical relationship between solubility and molecular properties in different solvents, which led to rational approaches to improve the accuracy of each models.
Pharmaceutical Sciences, 2019
Background: To overcome low solubility of naproxen (NAP), deep eutectic solvents (DESs) based on choline chloride (ChCl) with glycerol (G) and oxalic acid (OA) as green solvents have been used up to 0.9 mole fraction of DES at T = (298.15 to 313.15) K. Methods: DESs were prepared by combination of the two components with the molar ratios: ChCl/glycerol (1:2) and ChCl/oxalic acid (1:1). The solubility of NAP in the aqueous DESs solutions was measured at different temperatures with shake flask method. Results: The solubility in these solvents increased with increasing the weight fraction of DESs, especially in ChCl/OA. The solubility data were correlated by e-NRTL, Wilson and UNIQUAC models. Also, the thermodynamic functions, Gibbs energy, enthalpy, and entropy of dissolution were obtained. Conclusion: Oxalic acid based DES exhibits higher solubility than glycerol based DES. The thermodynamic models were successfully used to correlate solubility data. In addition, the results show tha...
Current Medicinal Chemistry, 2006
The dimethyl sulfoxide (DMSO) solubility data from Enamine and two UCB pharma compound collections were analyzed using 8 different machine learning methods and 12 descriptor sets. The analyzed data sets were highly imbalanced with 1.7−5.8% nonsoluble compounds. The libraries' enrichment by soluble molecules from the set of 10% of the most reliable predictions was used to compare prediction performances of the methods. The highest accuracies were calculated using a C4.5 decision classification tree, random forest, and associative neural networks. The performances of the methods developed were estimated on individual data sets and their combinations. The developed models provided on average a 2-fold decrease of the number of nonsoluble compounds amid all compounds predicted as soluble in DMSO. However, a 4−9-fold enrichment was observed if only 10% of the most reliable predictions were considered. The structural features influencing compounds to be soluble or nonsoluble in DMSO were also determined. The best models developed with the publicly available Enamine data set are freely available online at
The E and C model for predicting the solubility of drugs in pure solvents
International Journal of Pharmaceutics, 1996
The E and C model for hydrogen bonding is used together with nonspecific solubility parameters to predict the solubility of a Lewis base solute in a series of solvents of several chemical classes. A linear relationship between enthalpies of hydrogen bonding calculated from the Drago model and entropies obtained from a few experimental solubilities allows the prediction of the entropy contribution for the other solvents. Correct orders of magnitude are predicted in solvents of all polarities (from benzene to glycerin) which were not used to obtain the empirical relationships. The results suggest that the E and C model may be useful to reduce the experimental work usually needed for predicting solubility of drugs in pure solvents of different acid-base characteristics.