Optimized solubility and bioavailability of genistein based on cocrystal engineering

With various potential health-promoting bioactivities,genistein has great prospects in treatment of a series of complex diseases and metabolic syndromes such as cancer,diabetes,cardiovascular diseases,menopausal symptoms and so on.However,poor solubility and unsatisfactory bioavailability seriously limits its clinical application and market development.To optimize the solubility and bioavailability of genistein,the cocrystal of genistein and piperazine was prepared by grinding assisted with solvent based on the concept of cocrystal engineering.Using a series of analytical techniques including single-crystal X-ray diffraction,powder X-ray diffraction,Fourier transform infrared spectroscopy,differential scanning calorimetry and thermogravimetric analysis,the cocrystal was characterized and confirmed.Then,structure analysis on the basis of theoretical calculation and a series of evaluation on the stability,dissolution and bioavailability were carried out.The results indicated that the cocrystal of genistein and piperazine improved the solubility and bioavailability of genistein.Compared with the previous studies on the cocrystal of genistein,this is a systematic and comprehensive investigation from the aspects of preparation,characterization,structural analysis,stability,solubility and bioavailability evaluation.As a simple,efficient and green approach,cocrystal engineering can pave a new path to optimize the pharmaceutical properties of natural products for successful drug formulation and delivery.

Cocrystal virtual screening based on the XGBoost machine learning model

Co-crystal formation can improve the physicochemical properties of a compound,thus enhancing its druggability.Therefore,artificial intelligence-based co-crystal virtual screening in the early stage of drug development has attracted extensive attention from researchers.However,the complexity of developing and applying algorithms hinders it wide application.This study presents a data-driven co-crystal prediction method based on the XGBoost machine learning model of the scikit-learn package.The simplified molecular input line entry specification(SMILES)information of two compounds is simply inputted to determine whether a co-crystal can be formed.The data set includs the co-crystal records presented in the Cambridge Structural Database(CSD)and the records of no co-crystal formation from extant literature and experiments.RDKit molecular descriptors are adopted as the features of a compound in the data set.The developed model shows excellent performance in the proposed co-crystal training and validation sets with high accuracy,sensitivity,and F1 score.The prediction success rate of the model exceeds 90%.The model therefore provides a simple and feasible scheme for designing and screening co-crystal drugs efficiently and accurately.