Prediction of the Ibuprofen Loading Capacity of MOFs by Machine Learning

Abstract

Metal-organic frameworks (MOFs) have been widely researched as drug delivery systems due to their intrinsic porous structures. Herein, machine learning (ML) technologies were applied for the screening of MOFs with high drug loading capacity. To achieve this, first, a comprehensive dataset was gathered, including 40 data points from more than 100 different publications. The organic linkers, metal ions, and the functional groups, as well as the surface area and the pore volume of the investigated MOFs, were chosen as the model’s inputs, and the output was the ibuprofen (IBU) loading capacity. Thereafter, various advanced and powerful machine learning algorithms, such as support vector regression (SVR), random forest (RF), adaptive boosting (AdaBoost), and categorical boosting (CatBoost), were employed to predict the ibuprofen loading capacity of MOFs. The coefficient of determination (R2) of 0.70, 0.72, 0.66, and 0.76 were obtained for the SVR, RF, AdaBoost, and CatBoost approaches, respectively. Among all the algorithms, CatBoost was the most reliable, exhibiting superior performance regarding the sparse matrices and categorical features. Shapley additive explanations (SHAP) analysis was employed to explore the impact of the eigenvalues of the model’s outputs. Our initial results indicate that this methodology is a well generalized, straightforward, and cost-effective method that can be applied not only for the prediction of IBU loading capacity, but also in many other biomaterials projects.

Drug Delivery on Mg-MOF-74: The Effect of Drug Solubility on Pharmacokinetics

“…To gain a better understanding of the relationship between drug characteristics and pharmacokinetic performance of the MOF nanocarrier, the raw drug concentrations determined from HPLC experiments were normalized, and the resulting delivery profiles were fitted with the Higuchi model. , The pharmacokinetic profiles are presented in Figure , while the estimated release rate constants ( k ) are listed in Table for all samples studied. Looking at the normalized release rate profiles, the maximum C / C 0 value was achieved by MOF-Flu-30, which was 98% after 10 h of release time, whereas the least amount released was 59%, which was displayed by MOF-Cur-80.…”

“…After synthesis and activation and prior to drug impregnation, the MOF samples were dried overnight under vacuum at 100 °C. Then, the desired amount of ibuprofen, 5-fluorouracil, and curcumin (i.e., 30, 50, and 80 wt %) was incorporated into the MOF structure via the wet-impregnation technique that has been described in detail in previous works . Briefly, the desired amount of the three aforementioned drugs was dissolved in 10 mL of MeOH/0.05 g drug by sonication at room temperature for 15 min until the solution became clear.…”

“…Then, the desired amount of ibuprofen, 5-fluorouracil, and curcumin (i.e., 30, 50, and 80 wt %) was incorporated into the MOF structure via the wet-impregnation technique that has been described in detail in previous works. 10 Briefly, the desired amount of the three aforementioned drugs was dissolved in 10 mL of MeOH/0.05 g drug by sonication at room temperature for 15 min until the solution became clear. Then, 0.1 g of Mg-MOF-74 was added to the solution, and the flask was sealed and placed on a magnetic stirring plate and stirred at 200 rpm for 24 h at room temperature.…”

“…As another example, Hartleib et al loaded ibuprofen onto CD-MOF and demonstrated an uptake of 23–26 wt % of the drug within the CD-MOF. Owing to their adoptable framework for functionalization and fine-tuning, and weak coordination bonds, MOFs are promising candidates as nanocarriers for incorporation of various drugs. − …”