BP neural net model method for preparing pharmaceutical composition

Abstract

The invention discloses the drug compound with BP neural net model. The method comprises the following steps: building non-linear mapping model of dosage and drug-effect with BP neural net; defining BP neural net model parameters; building BP neural net model non-linear mapping model. The method completely and fully utilizes the laboratory data, and uses computer to replace a great amount of animal experiment works. According to the BP neural net model, the method forecasts matching relation.

Description

technical field [0001] The invention relates to a series of pharmaceutical compositions, a preparation method and its application, in particular to a pharmaceutical composition prepared by a BP neural network model and a new pharmaceutical application. Background technique [0002] The regression method is often used for modeling in medicine, but the regression method requires the data to meet certain prerequisites. For example, linear regression can only be applied when the data meet the conditions of independence, linearity, normality, and homogeneity of variance; the regression effect directly depends on Therefore, after the model is established, it is necessary to test the rationality of the basic assumptions of the regression model. When applying nonlinear regression, there are many difficulties and problems in model selection, preliminary analysis, initial value determination, parameter and variable transformation, parameter solution, as well as model correction, compa...

AI Technical Summary

Problems solved by technology

When applying nonlinear regression, there are many difficulties and problems in model selection, preliminary analysis, initial value determination, parameter and variable transformation, parameter solution, as well as model correction, comparison and inspection, convergence and fitting evaluation , these will affect the effect of fitting nonlinear data, and even affect the establishment of the model

A large number of studies have shown that there is a complex nonlinear relationship between the taste and dosage of compound prescriptions and pharmacodynamics. There is no suitable model for this nonlinear relationship at present, which makes it difficult to use traditional nonlinear regression methods to build When modeling, there are difficulties in model selection, initial value determination, parameter transformation solution, model inspection, etc., which affect the effect of nonlinear modeling

Images