Constructing an Intelligent Model Based on Support Vector Regression to Simulate the Solubility of Drugs in Polymeric Media

Abstract

This study constructs a machine learning method to simultaneously analyze the thermodynamic behavior of many polymer–drug systems. The solubility temperature of Acetaminophen, Celecoxib, Chloramphenicol, D-Mannitol, Felodipine, Ibuprofen, Ibuprofen Sodium, Indomethacin, Itraconazole, Naproxen, Nifedipine, Paracetamol, Sulfadiazine, Sulfadimidine, Sulfamerazine, and Sulfathiazole in 1,3-bis[2-pyrrolidone-1-yl] butane, Polyvinyl Acetate, Polyvinylpyrrolidone (PVP), PVP K12, PVP K15, PVP K17, PVP K25, PVP/VA, PVP/VA 335, PVP/VA 535, PVP/VA 635, PVP/VA 735, Soluplus analyzes from a modeling perspective. The least-squares support vector regression (LS-SVR) designs to approximate the solubility temperature of drugs in polymers from polymer and drug types and drug loading in polymers. The structure of this machine learning model is well-tuned by conducting trial and error on the kernel type (i.e., Gaussian, polynomial, and linear) and methods used for adjusting the LS-SVR coefficients (i.e., leave-one-out and 10-fold cross-validation scenarios). Results of the sensitivity analysis showed that the Gaussian kernel and 10-fold cross-validation is the best candidate for developing an LS-SVR for the given task. The built model yielded results consistent with 278 experimental samples reported in the literature. Indeed, the mean absolute relative deviation percent of 8.35 and 7.25 is achieved in the training and testing stages, respectively. The performance on the largest available dataset confirms its applicability. Such a reliable tool is essential for monitoring polymer–drug systems’ stability and deliverability, especially for poorly soluble drugs in polymers, which can be further validated by adopting it to an actual implementation in the future.

Analyzing the adverse effects of childhood stress on adult anxiety behaviors by testing on male rats and addressing it with a period of aerobic exercise during adolescence

“…Therefore, it is necessary to randomly divide the experimental data into training and testing collections. [26] Thus, most animal models of early-life stress have manipulated maternal interaction, disrupting either the quantity or quality of maternal care early in life [27][28]. For any model of early-life stress, the detection of a behavioral outcome depends on several variables.…”

Multi‐source data‐driven approach for prediction of melt density during polymer compounding

“…Bovo et al developed a soft sensor for PVC tube quality using polynomial regression and support vector regression (SVR) algorithms, achieving 98.83% and 98.35% accuracy by incorporating filler data, showcasing an innovative approach in extrusion manufacturing 10 . Senceroglu et al used the least‐squares SVR approach to analyze the thermodynamic behavior of various polymer‐drug systems, achieving a mean absolute relative deviation percent of 8.35 and 7.25 in the training and testing stages, respectively 11 . Castéran utilized twin‐screw extrusion at varying high temperatures and process conditions to create a dataset for HDPE and UHMWPE, developing accurate viscosity estimations and molecular weight predictions using SVR and sPGD indicating their potential for rapid and precise simulation, emphasizing the need for data accuracy in such applications 12 .…”

“…10 Senceroglu et al used the least-squares SVR approach to analyze the thermodynamic behavior of various polymerdrug systems, achieving a mean absolute relative deviation percent of 8.35 and 7.25 in the training and testing stages, respectively. 11 Castéran utilized twin-screw extrusion at varying high temperatures and process conditions to create a dataset for HDPE and UHMWPE, developing accurate viscosity estimations and molecular weight predictions using SVR and sPGD indicating their potential for rapid and precise simulation, emphasizing the need for data accuracy in such applications. 12 Munir compares various machine learning methods, including recursive feature elimination, ridge regression, least absolute shrinkage and selection operator, RF, and so on, for predicting PLA's molecular weight and mechanical properties.…”

Predicting anti‑cancer drugs’ dissolution in supercritical carbon dioxide

“…The structure of this machine learning model is well-tuned by conducting trial and error on the kernel type (i.e., Gaussian, polynomial, and linear) and methods used for adjusting the LS-SVR coefficients (i.e., leave-one-out and 10-fold cross validation scenarios). (34) The current research briefly reviewed ten well-known and reliable empirical correlations for estimating solid solubility in supercritical CO235. After that, a universal approach based on the modified Arrhenius model is introduced to relate the anti-cancer drug solubility in SCCO2.…”

“…On the other hand, PVP K12, PVP K15, and VP dimer are polyvinyl pyrrolidone-based polymers with different molecular weights. Therefore, it is expected that the solubility temperature of D-Mannitol in these polymers is almost equal (34).…”