RESUMEN
OBJECTIVE@#The compatibility of Eucommia ulmoides (Eu) and Psoralea corylifolia (Pc) on the pharmacokinetic (PK) properties in the rat was explored in this study.@*METHODS@#Eu extract, Pc extract and the combined extracts (crude drug ratio was 2:1) was administered by gavage, respectively. Two PK experiments were conducted. In first one, the blood samples were collected via the occuli chorioideae vein to get the PK properties of the components. In second one, the blood samples were simultaneously collected via the internal jugular vein or portal vein at different time points and the concentrations of target ingredients were detected by LC/MS/MS to clear the location where the interaction of Eu and Pc took place in vivo.@*RESULTS@#Eight of 11 ingredients in Eu and Pc extract were determined in rat plasma. The exposure levels of geniposidic acid (GPA), aucubin (AU), geniposide (GP), pinoresinol diglucoside (PDG), psoralen glycosides (PLG) and isopsoralen glycosides (IPLG) were decreased 1/5-2/3 after administration of combined extracts. Comparing to the combined administration, the exposure of GPA and AU in plasma of single Eu administration collected via the portal vein were decreased 1/3-2/3, and the values of AUC0-24h and AUC0-∞ of GP collected from the portal vein or internal jugular vein were double increased. The other components' parameters were not significantly changed.@*CONCLUSION@#In summary, the Pc and Eu combined administration could affect the exposure of the main components of Eu extract in rats due to the changed intestinal absorption. The research on the compatibility of Pc and Eu was helpful to guide the clinical administration of Eu and Pc simultaneously.
RESUMEN
@#Human intestinal absorption (HIA) is a crucial indicator for measuring the oral bioavailability of drugs.This study aims to use artificial intelligence methods to predict and evaluate the HIA of drugs in the early stages of drug discovery, thus accelerating the drug discovery process and reducing costs.This study used MOE''s 2D, 3D descriptors, and ECFP4 (extended connectivity fingerprints) to characterize the molecules and established eight models, including support vector machine (SVM), random forest (RF), and deep neural network (DNN).The results showed that the SVM model constructed using a combination of 2D, 3D descriptors and ECFP4 fingerprints was the optimal model according to comprehensive evaluation of various evaluation indicators.The area under the receiver operating characteristic curve (AUC), Matthews correlation coefficient, and Kappa coefficient of the optimal model were 0.94, 0.75, and 0.74, respectively.In conclusion, this study established a robust and generalizable machine learning model for predicting HIA properties, which can provide guidance for early molecular screening and the study of pharmacokinetic properties of drugs.