Solubility In Supercritical CO2 Research Articles

Optimization of drug solubility inside the supercritical CO2 system via numerical simulation based on artificial intelligence approach

In this research paper, we explored the predictive capabilities of three different models of Polynomial Regression (PR), Extreme Gradient Boosting (XGB), and LASSO to estimate the density of supercritical carbon dioxide (SC-CO2) and the solubility of niflumic acid as functions of the input variables of temperature and pressure. The optimization of hyperparameters for these models is achieved using the innovative Barnacles Mating Optimizer (BMO) algorithm. For SC-CO2 density estimation, PR exhibits remarkable accuracy, showing an R-squared value of 0.99207 for data fitting. XGB performs admirably with an R2 of 0.92673, while LASSO model demonstrates good predictive ability, showing an R2 of 0.81917. Furthermore, we assess the models’ performance in predicting the solubility of niflumic acid. PR exhibits excellent predictive capabilities with an R2 of 0.96949. XGB also delivers strong performance, yielding an R-squared score of 0.92961. LASSO performs well, achieving an R-squared score of 0.82094. The results indicated promising performance of machine learning models and optimizer in estimating drug solubility in supercritical CO2 as the solvent applicable for pharmaceutical industry.

Determination of morphine sulfate anti-pain drug solubility in supercritical CO2 with machine learning method

Accurate solute solubility measuring and modeling in supercritical carbon dioxide (ScCO2) would address the best working conditions and thermodynamic boundaries for material processing with this type of fluid. Theory- and data-driven methods are two general modeling approaches. Using theory-driven methods, the solubility is estimated based on the principles of thermodynamics, while data-driven methods are developed by training the algorithms. Despite acceptance of each of these methods, more experimental solubility data are still needed to promote modeling performances. In this study, for the first time, solubility of morphine sulfate is determined and modeled by a set of 13 semi-empirical (theory-driven) and random forest (data-driven) models. Using a laboratory system with an ultraviolet-visible (UV-Vis) spectroscopy, the experimental solubilities including 48 data points were obtained at different temperatures (308–338 K) and pressures (12–27 MPa). The minimum (0.806 × 10−5) and maximum (5.902 × 10−5) equilibrium mole fractions were observed at working pressures of 12 and 27 MPa, respectively, both at the same temperature of 338 K. It was indicated that random forest model (with AARD% of 1.29%) had an excellent predictive performance against semi-empirical models (with AARD% from 9.33 to 19.76%). The results showed that solute molecular weight had the highest effect on random forest modeling. Using modeling results from Chrastil and Bartle models, total and vaporization enthalpies of dissolution of morphine sulfate in ScCO2 were found to be 35.12 and 59.04 kJ/mole, respectively.

Comprehensive study of medications solubility in supercritical CO2 with and without co-solvent; Laboratory, theoretical, and intelligent approaches

Determining the dissolution characteristics of medicines in supercritical CO2 is vital for formulating innovative drug delivery systems through an efficient supercritical process. This study investigates the solubility of three poorly bioavailable drugs −Topiramate, Meclizine, and Dimenhydrinate- in supercritical CO2, both with and without ethanol co-solvent, over a temperature range of 308 K to 348 K and pressures from 17 MPa to 41 MPa. The solubility of these medicines in supercritical CO2 (binary system) is notably low, ranging from 2.5 × 10-6 − 4.54 × 10-6, 0.26 × 10-5 − 2.3 × 10-5, and 0.20 × 10-5 − 1.91 × 10-5 in mole fraction, respectively. However, in the presence of ethanol (ternary system), their supercritical solubility significantly increases by factors of 2.75–5.84, 1.40–3.20, and 2.04–4.85, respectively.The supercritical solubility of the mentioned compounds are theoretically evaluated using several approaches, including empirical models, a machine learning methodology employing a multilayer perceptron neural network, thermodynamic models based on two cubic equations of state (Peng-Robinson (PR) and Soave–Redlich–Kwong (SRK)), and a non-cubic equation of state (perturbed chain-statistical associating fluid theory (PC-SAFT)), as well as two expanded liquid models (UNIQUAC and Wilson).The findings revealed that all the specified models demonstrate acceptable accuracy in correlating the experimental data of the specified drugs in both binary and ternary systems. Among these, the PR and SRK thermodynamic models, along with some empirical models, show the best results. Furthermore, the machine learning model exhibited outstanding accuracy in forecasting the supercritical solubility of the desired drugs, with over 99.9% alignment between their predicted and experimental data.

Solubility of supercritical CO2 in polystyrene

Expanded polystyrene (ePS) plays an important role in the food packaging industry. However, the foaming process is environmentally unfriendly. A sustainable alternative is dissolving supercritical CO2 (scCO2) in the polystyrene (PS) matrix. Most studies so far were performed at temperatures above the PS glass transition temperature; however, a more general temperature window is desirable. In this work, the solubility of scCO2 in polystyrene was measured at 323 K, 343 K, 363 K and 383 K and pressure up to 130 bar using a magnetic suspension balance (MSB). It was concluded that the solubility of CO2 in PS decreases with temperature and increases with pressure. The Sanchez-Lacombe Equation of State was utilized to estimate the degree of swelling. The model developed was able to derive the experimentally determined solubilities after correction for the swelling. The interaction parameter, k12, turned out to be only a function of temperature. With these results the solubility and swelling of PS in scCO2 can be more accurately assessed for different temperatures and pressures.

Thermodynamic modeling of anticancer drugs solubilities in supercritical CO2 using the PC-SAFT equation of state

In this research, the solubility of anticancer drugs in the supercritical CO2 is modeled using the PC-SAFT equation of state (EoS). Ten anticancer drugs containing Empagliflozin, Sorafenib tosylate, Verapamil, Sodium valproate, Aprepitant, Sunitinib malate, Tamsulosin, Imatinib mesylate, Capecitabine, and Docetaxel are studied to evaluate the model performance. For each component, three temperature-independent model parameters are optimized by the experimental solubility data. The CO2 is modeled as associative molecules with four associating sites and four association sites are considered on anticancer molecules. Therefore, the cross-association between anticancer and CO2 molecules is considered. The average ARD, RMSE, and AAD values of the PC-SAFT EoS for the aforementioned anticancer drugs are obtained 11.45 %, 0.067, and 0.00026 %, respectively. The PC-SAFT EoS results are compared to various types of cubic EoSs and semi-empirical models. The results show that the PC-SAFT EoS with three model parameters can be used as a robust and efficient thermodynamic model to calculate the solubility of complex molecules in supercritical CO2 up to high pressures and temperatures.

Supercritical CO2 extraction of Walnut (Juglans regia L.) oil: Extraction kinetics and solubility determination

Experimental and modelling investigations of supercritical CO2 extraction of oil from Juglans regia L. kernels were conducted at 200 and 400 bar, 313 and 333 K at a CO2 flow rate of 0.1 kg/h. Regardless of the pressure and the temperature, the highest achievable yield was estimated at about 0.7 kgoil / kgbiomass. The extraction kinetics were modeled with Sovová’s broken and intact cells model. Walnut oil apparent solubility in supercritical CO2 was determined and modelled with the Chrastil equation. A retrograde solubility behaviour was observed at 200 bar, the faster extraction kinetics were found at 400 bar and 333 K. The fatty acid composition of the supercritical CO2 extracted oil was compared to the quality of the oil extracted by press and n-hexane Soxhlet extraction.

Prediction of ionic liquid solubilities in supercritical CO2 + co-solvent systems using Peng–Robinson equation of state with accurate critical temperature

Supercritical fluid deposition (SCFD) using supercritical carbon dioxide (CO2) to impregnate substrates with ionic liquids (ILs) has attracted considerable attention for the preparation of porous-supported ILs. Because ILs are generally insoluble in pure CO2, it is essential to estimate the solubilities of ILs in supercritical CO2 + co-solvent systems for developing the SCFD process. In this study, a methodology was developed to predict the solubility of ILs in supercritical CO2 with co-solvents using the corresponding binary phase-equilibrium data. For the prediction, the binary interaction parameters for the Peng–Robinson equation of state (PR-EoS) were determined using the correlations to each phase-equilibrium system (i.e., IL + CO2, CO2 + co-solvent, and IL + co-solvent). The predictive model using the PR-EoS, which included a re-determined critical temperature as a pure component parameter of ILs, could reproduce the effects of the temperature, pressure, and co-solvent concentration on the IL solubilities in the supercritical fluid phase without any fitting parameters for the ternary systems. The average absolute relative deviations based on the logarithmic scale for the predictions were <23 %, indicating that the methodology was acceptable for describing the IL solubilities in the supercritical CO2 + co-solvent system.

Empirical correlations of drug-and plant-based bioactive compound solubility in supercritical CO2: A comparative evaluation study

Over the last few decades, supercritical fluid extraction process has greatly assisted the search for more medicinal and therapeutic properties of bioactive compounds from an extensive range of botanical matrices. The yield of supercritical fluid extraction is often limited by the solubility of a targeted solute in the solvent and thus knowledge on solubility has become one of the fundamental variables of interest in the extraction process. However, the studies to evaluate the performance of density-based empirical models in estimating the solubility of different drug- and plant-based bioactive compounds were scarce. Therefore, this study aimed to gather the solubility data of 33 drugs and 40 plant-based bioactive compounds at varying temperatures and pressures and correlated them with 26 most widely used density-based models. The solubility data were critically analysed and reported from two perspectives: well-studied solubility-influencing factors such as pressure, temperature, and additional influencing factors what o such as molecular structure and weight. Then, a thorough evaluation of the existing empirical solubility models involving 26 predictive models for 73 bioactive compounds was performed. From the results and findings, it was evident that the 8-parameter Belghait et al. model showed the overall highest accuracies indicated by the lowest absolute average relative deviation of 7.42 %, 10.16 %, and 6.57 %, respectively for all bioactive compounds, drug-based bioactive compounds, and plant-based bioactive compounds. Belghait et al. model is also superior since its predictive performances are the best for 54 % of the bioactive compounds studied. Meanwhile, Kumar and Johnston's, Sung and Shim's, and Sodeifian et al's models demonstrated the best solubility predictions for 3-, 4-, and 6-parameter empirical models, respectively, for both plant and drug-based compounds. As the effects of pressure and temperature on solubility have widely acknowledged, this study also highlights the influence of molecular structure complexity on solubility. The main findings from this comparative evaluation proved that density-based models are efficacious in predicting solubility of both plant and drug-based bioactive compounds.

Experimental and thermodynamic investigation of gemifloxacin solubility in supercritical CO2 for the production of nanoparticles

The effective use of the supercritical technology in the production of new pharmaceutical formulations with greater bioavailability requires the determination of the solubility of pharmaceutical substances in supercritical CO2 (scCO2) at different conditions. In the current work, the solubility of an antibacterial compound, Gemifloxacin, was measured at various temperatures (308 to 338 K), and pressures (120 to 300 bar). This compound has a poor solubility in scCO2 (0.02 × 10−4 to 0.67 × 10−4 mole fraction or 0.0156 to 0.5891 g.kg−1). Furthermore, some popular empirical models and three thermodynamic approaches (SRK and PR equations of state, and the regular solution model) were applied to correlate and predict the solubility of Gemifloxacin in scCO2. The regular solution model with temperature-dependent solubility parameter (mean AARD% = 2.32–4.34) and the SRK-based model (mean AARD% = 7.47), exhibited the highest accuracy in fitting the experimental data.

Chromatography-like propagation of water along raw material bed in supercritical fluid extraction

A chromatography-like propagation of water through the material bed was observed while performing supercritical fluid extraction of aroma plants having high moisture content. While parts of raw material bed placed at the inlet of the extraction vessel get dried after appropriate extraction time, the parts closer to the outlet not only stay wet but, in fact, gain more moisture than initial raw material. Presumably, water and other extractables with limited solubility in supercritical CO2, get re-adsorbed onto the plant material surface along the extraction column and then desorbed further on. If the effect is of general nature, it might be important for modeling kinetics of supercritical fluid extraction of non-volatile compounds.

Modeling cobalt (III) acetylacetonate and iron (III) acetylacetonate solubilities in supercritical CO2 with PC-SAFT based on experimentally-determined solid–liquid equilibria in organic solvents

A methodology to model the solubilities of metal complexes in supercritical CO2 is indispensable for effectively designing the supercritical CO2-based deposition method. Herein, the solubility of two metal acetylacetonates (acac), Co(acac)3 and Fe(acac)3, in supercritical CO2 was modeled based on the perturbed-chain statistical associating fluid theory (PC-SAFT) and experimentally-determined solid–liquid equilibria in organic solvents. This modeling approach is more predictive than conventional cubic-type equations of state or semi-empirical correlation models. The pure-component parameters of PC-SAFT for metal acetylacetonates are obtained by fitting the obtained solubility data to four typical organic solvents (toluene, acetone, 2-butanone, and ethyl acetate). By applying these PC-SAFT parameters, the model satisfactorily reproduced the solubilities of the metal complexes in supercritical CO2, particularly under low-temperature conditions even with the kij (binary interaction parameter) set to 0 in the combining rule. The isobaric solubilities can also be described by PC-SAFT by generalizing the temperature dependence of kij.

Theoretical investigations on the manufacture of drug nanoparticles using green supercritical processing: Estimation and prediction of drug solubility in the solvent using advanced methods

We studied the possibility of development of a novel green methodology for preparation of nanomedicine. The designed process does not use organic solvent in the manufacturing the drug and supercritical gas is used as solvent in the process. The method is efficient to enhance the drug efficacy for the patients. We used a dataset of solubility data in our study, which includes two inputs, pressure, and temperature, as well as one output, solubility, in order to carry out the study. In fact, the solubility of a drug namely Tolmetin has been predicted in supercritical carbon dioxide as the solvent using machine learning based models. As part of this research, a heap-based optimizer (HBO) was used on three selected machine learning models to obtain optimal estimators that can be used in the future. Machine learning models are multilayer perceptron (MLP), polynomial support vector regression (PSVR), and ridge regression. PSVR, Ridge, and MLP each have R2-scores of 0.976, 0.749, and 0.957, and MSEs of 1.81 × 10−8, 1.40 × 10−7, and 4.18 × 10−8, respectively. So, PSVR was selected as the most accurate model among all models assessed in this work for description of Tolmetin solubility in supercritical CO2. The results indicated that the developed models are robust and accurate enough for prediction of the pharmaceutical solubility in different solvents and operational ranges.

Development of machine learning model and analysis study of drug solubility in supercritical solvent for green technology development

The current research is focused on development of machine learning model for estimation of pharmaceutical solubility in supercritical CO2 as the green solvent. The main aim is to assess the suitability of supercritical processing for preparation of nanomedicine. Oxaprozin was taken as model drug for the solubility measurements, and its solubility was determined at different operational conditions by variation of temperature and pressure of the process. Artificial Neural Network (ANN) model was implemented for simulation of the drug solubility, and the best model was obtained with R2 greater than 0.99 for the training and validation as well. The tested model was then exploited to understand the process, and it turned out that both pressure and temperature had major and considerable influence on the solubility of Oxaprozin in supercritical carbon dioxide as solvent. However, the effect of pressure was shown to be more significant on the solubility compared to the effect of pressure, which was attributed to the effect of pressure on the density of the supercritical solvent. The developed ANN model was indicated to be robust in estimating the values of drug solubility in wide range of conditions which can save time and cost of the measurements.

Estimating the Dissolution of Anticancer Drugs in Supercritical Carbon Dioxide with a Stacked Machine Learning Model.

Synthesizing micro-/nano-sized pharmaceutical compounds with an appropriate size distribution is a method often followed to enhance drug delivery and reduce side effects. Supercritical CO2 (carbon dioxide) is a well-known solvent utilized in the pharmaceutical synthesis process. Reliable knowledge of a drug’s solubility in supercritical CO2 is necessary for feasible study, modeling, design, optimization, and control of such a process. Therefore, the current study constructs a stacked/ensemble model by combining three up-to-date machine learning tools (i.e., extra tree, gradient boosting, and random forest) to predict the solubility of twelve anticancer drugs in supercritical CO2. An experimental databank comprising 311 phase equilibrium samples was gathered from the literature and applied to design the proposed stacked model. This model estimates the solubility of anticancer drugs in supercritical CO2 as a function of solute and solvent properties and operating conditions. Several statistical indices, including average absolute relative deviation (AARD = 8.62%), mean absolute error (MAE = 2.86 × 10−6), relative absolute error (RAE = 2.42%), mean squared error (MSE = 1.26 × 10−10), and regression coefficient (R2 = 0.99809) were used to validate the performance of the constructed model. The statistical, sensitivity, and trend analyses confirmed that the suggested stacked model demonstrates excellent performance for correlating and predicting the solubility of anticancer drugs in supercritical CO2.

Modeling and computational study on prediction of pharmaceutical solubility in supercritical CO2 for manufacture of nanomedicine for enhanced bioavailability

• Computational modeling of pharmaceutical solubility in supercritical conditions. • Evaluation of the effect of temperature and pressure on the solubility. • Analysis of the data and models in terms of fitting accuracy. Enhancement of drug bioavailability for poorly water-soluble drugs is of great importance for pharmaceutical industry. In this work, a computational task was carried out in order to predict the solubility of a drug model, namely salsalate in supercritical carbon dioxide as the solvent. The experimental data was collected for the solubility at different values of temperature and pressure to understand the effect of operational parameters on the solubility of salsalate. Several machine learning data was employed to predict the solubility data as function of input parameters, i.e., temperature (T) and pressure (P). On the provided data, we employed Linear SVR (Support Vector Regression), Nu SVR, and Bayesian Ridge Regression (BRR) models with two inputs, including X1 = P(bar) and X2 = T(K), and only one output which is the drug solubility (mole fraction unit). The simulation results indicated that linear SVR, Nu SVR, and BRR have R-squared scores of 0.784, 0.998, and 0. 876, respectively. In addition, they exhibit MAE error rates of 3.71 × 10 −4 , 8.41 × 10 −5 , and 3.04 × 10 −4 . Another statistic which was considered in the predictions is RMSE, which indicated error rates of 4.21 × 10 −4 , 1.39 × 10 −4 , and 3.60 × 10 −4 for linear SVR, Nu SVR, and BRR, respectively. Indeed, the model of Nu SVR was chosen as the best model based on these statistical metrics and some visual examination, and it was utilized to discover optimal values that can be summarized as a vector: (X1 = 400, X2 = 338, Y = 0.00387). The results revealed that the developed models are capable pf predicting the solubility of salsalate for a wide range, and can be also employed for development of nanomedicine manufacturing based on supercritical-based processing.

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

Industrial-based application of supercritical CO2 (SCCO2) has emerged as a promising technology in numerous scientific fields due to offering brilliant advantages, such as simplicity of application, eco-friendliness, and high performance. Loxoprofen sodium (chemical formula C15H18O3) is known as an efficient nonsteroidal anti-inflammatory drug (NSAID), which has been long propounded as an effective alleviator for various painful disorders like musculoskeletal conditions. Although experimental research plays an important role in obtaining drug solubility in SCCO2, the emergence of operational disadvantages such as high cost and long-time process duration has motivated the researchers to develop mathematical models based on artificial intelligence (AI) to predict this important parameter. Three distinct models have been used on the data in this work, all of which were based on decision trees: K-nearest neighbors (KNN), NU support vector machine (NU-SVR), and Gaussian process regression (GPR). The data set has two input characteristics, P (pressure) and T (temperature), and a single output, Y = solubility. After implementing and fine-tuning to the hyperparameters of these ensemble models, their performance has been evaluated using a variety of measures. The R-squared scores of all three models are greater than 0.9, however, the RMSE error rates are 1.879 × 10−4, 7.814 × 10−5, and 1.664 × 10−4 for the KNN, NU-SVR, and GPR models, respectively. MAE metrics of 1.116 × 10−4, 6.197 × 10−5, and 8.777 × 10−5errors were also discovered for the KNN, NU-SVR, and GPR models, respectively. A study was also carried out to determine the best quantity of solubility, which can be referred to as the (x1 = 40.0, x2 = 338.0, Y = 1.27 × 10−3) vector.

Solubility of prazosin hydrochloride (alpha blocker antihypertensive drug) in supercritical CO2: Experimental and thermodynamic modelling

The solubility of prazosin hydrochloride (PRH, alpha-blocker antihypertensive drug) in supercritical CO2 (SC-CO2) was measured at temperatures between 308 and 338 K and pressures between 120 and 270 bar. The dissolved mole fractions of PRH ranged from 1.59 × 10−5 to 7.2 × 10−5, corresponding to solubilities of 0.003–0.022 g/L. PRH solubility data of the experiments were correlated using three models: (1) based on functional dependencies, eight established density-based models with 3–6 parameters; (2)ECM-PR EoS using a conventional mixing rule; and (3) SLE-based model. Moreover, a new modified EoS model was tested by correlating the solubility of PRH. All examined models could generate satisfactory fit to the solubility data. However, among the applied models, Sodeifian et al., model achieved superiority based on AARD criterion, while the new modified EoS model achieved superiority based on AICc criterion. Additionally, some thermodynamic properties of PRH solubility in SC-CO2 were estimated.

Experimental analysis and thermodynamic modelling of lenalidomide solubility in supercritical carbon dioxide

• Lenalidomide (LND) solubility in supercritical CO 2 (sc-CO 2 ) was measured for the first time. • Solubility data were correlated by different density-based models. • Experimental data was also correlated by Modeified Wilson and SRK models. • The accuracy of the models was evaluated by statistical criteria (AARD %), ( Radj ). • Thermodynamic enthalpies of Lenalidomide were estimated. Reduction of the size of pharmaceutical particles to micro/nano scale is an approved strategy to enhance their dissolution rate at decremented side effects. Production of drug micro/nanoparticles via a supercritical carbon dioxide (sc-CO 2 )- based process requires accurate data on the drug solubility in sc-CO 2 . In this study, the solubility of Lenalidomide (LND), an anti-cancer, was experimentally determined in sc-CO 2 at various temperatures (308–338 K) and pressures (120–300 bar). Furthermore, the obtained solubility data were correlated by different theoretical methods. LND solubility, in terms of mole fraction, was obtained in the range of 0.02 × 10 −4 –1.08 × 10 −4 depending on the conditions. The empirical models with different adjustable parameters, Soave–Redlich–Kwong equation of state (SRK-EoS) with two parameters van der Waals (vdW2) mixing rule, and expanded liquid theory (modified Wilson’s model) were applied for experimental data correlation. According to the results, modified Wilson’s model can correlate LND solubility in sc-CO 2 with high accuracy. However, the SRK-EoS did not show acceptable accuracy in the correlation of LND solubility in sc-CO 2 . Among the empirical models, Alwi and Garlapati, Sung and Shim, Ch and Madras, Hozhabr et al. , Garlapati and Madras, Keshmiri et al. , Sparks et al. , Reddy and Garlapati, Bian et al. (2011) and Belghait et al. showed R adj values higher than 0.99 and produced the best correlation with 3,4, 5, 6 and 8 adjustable parameters, respectively. Moreover, the approximate values of total mixing heat ( Δ H total ) as well as vaporization ( Δ H vap ), and solvation ( Δ H sol ) enthalpies were computed.

Dewatering black liquor and lignin with supercritical CO2

Black liquor, the residue remaining from pulping wood chips for papermaking, is used as fuel to power the mill. For energy efficiency, black liquor must be concentrated to over 65% solids prior to combustion. Supercritical CO2 achieves this by precipitating lignin by dropping the pH below the pKa of the phenolic groups in lignin, thereby depositing solids and creating a porous liquid/solid matrix. It then displaces the water from the matrix in a manner analogous to the dewatering of materials such as biomass, coal, and sludge. Thus, the supercritical CO2 performs a dual role of generating a porous matrix from the black liquor and then dewatering it. The amount of water removed far exceeds its solubility in supercritical CO2 and is proportional to the boiling point rise of black liquor. This opens the possibility of replacing one or more stages of a multi-effect evaporator with a supercritical CO2 dewatering unit. A similar approach applies to lignin deposited from black liquor for use as biofuel or as a chemical feedstock. Porosity appears to control displacement efficiency, with the process being more facile for open structures.

RETRACTED: Prediction of busulfan solubility in supercritical CO2 using tree-based and neural network-based methods

Drug solubility is a critical parameter in the pharmaceutical industry for developing efficient processes for production of nanomedicine at industrial scale. Several attempts have been made in recent years to investigate and obtain this parameter using various data mining methods, including neural networks. In this study, to reduce the error rate in predicting solubility, three methods including Multi-layer Perceptron (MLP), decision tree, and random forest have been applied to 32 rows of experimental data collected from literature for solubility of a model drug in supercritical CO2. Afterwards, the results of these models are examined and compared with measured data to calibrate and validate the developed models. Finally, the mean squared error improved to 1.77 e −5 in Random Forest Model. MLP and decision tree models mean squared errors are equal to 6.72 e −5 and 3.28 e −5, respectively which is a good result, especially when we can guarantee that the model did not have more problems in predicting the drug solubility and can be used as reliable methods in the pharmaceutical area.