Prediction method for blood brain barrier permeability of medicine

Abstract

The invention discloses a prediction method for the blood brain barrier permeability of a medicine, which is characterized in that a non-linear model for predicting the blood brain barrier permeability of a medicine is established by utilizing a group contribution method and an artificial neural network. According to the method, a prediction model is established by adopting an artificial neural network, a nonlinear model for predicting the blood brain barrier permeability of a medicine is established, a nonlinear method which better conforms to the relationship between the structure and the property of a medicine is provided for prediction and evaluation of the blood brain barrier permeability of the medicine, and the method is a novel method for predicting the blood brain barrier permeability of a medicine. Based on the group contribution method and the artificial neural network, the nonlinear prediction model for predicting the blood-brain barrier permeability of a medicine is established, the molecular structure of a medicine is utilized to predict the blood brain barrier permeability of the medicine, the defects that traditional experiments are large in difficulty, time-consuming, expensive and the like are overcome, and a prediction method which is more in line with the nonlinear relationship between the molecular structure and the blood brain barrier permeability of a medicine, and is high in accuracy and strong in applicability is provided for predicting the blood-brain barrier permeability of a medicine.

Description

technical field [0001] The present invention relates to the technical field of calculation of blood-brain barrier permeability of drugs, in particular to a method for predicting blood-brain barrier permeability of drugs based on group contribution method and artificial neural network, which is suitable for permeation of blood-brain barrier according to molecular structure information of drugs predictability. Background technique [0002] Quantitative structure-activity relationship (Quantitative structure-activity relationship, QSAR) is an important method to study the relationship between the structural characteristics and activity of compounds. Prediction, evaluation and screening of the nature or activity of the drug, etc., to provide basic data for further safety evaluation. Free and Wilson proposed a QSAR research method in the 1960s, namely the Free-Wilson group contribution method. The theoretical basis of this method is to divide a compound into several functional ...

AI Technical Summary

Problems solved by technology

[0007] The purpose of the present invention is to overcome the defects of poor prediction accuracy and weak applicability in the prior art, provide a method for predicting the blood-brain barrier permeability of drugs based on group contribution method and artificial neural network, and improve the accuracy and accuracy of model prediction. applicability

Images