Establishment method and data model of data set in drug blood-brain barrier permeability prediction

Abstract

The present invention relates to the computer field, and in particular to a method for establishing a data set and a data model in the prediction of drug blood-brain barrier permeability. The number of symptoms shown by a nervous system disease; the number of symptoms will be set to form the feature data set of the drug and the blood-brain barrier permeability of the drug in the feature data set of the drug will be combined into the feature matrix of the drug; A preset number of feature matrices of drugs with known blood-brain barrier permeability are combined to form the data set. In the present invention, a data set is formed by correlating the permeability of the blood-brain barrier of the drug with known blood-brain barrier permeability and the curative effect of the drug on nervous system diseases, so that the data set has a wide range of application and is applicable to the data set The trained blood-brain barrier permeability prediction model can also accurately predict the blood-brain barrier permeability of drugs in a larger range.

Description

technical field [0001] The invention relates to the field of computers, in particular to a method for establishing data sets and a data model in the prediction of drug blood-brain barrier permeability. Background technique [0002] The blood-brain barrier is a strict permeability barrier to maintain the homeostasis of the central nervous system. Determining the permeability of the compound to the blood-brain barrier is a prerequisite for the discovery of neurological drugs. Only after determining the permeability of the constituent compounds of the drug to the blood-brain barrier can it be predicted Drug permeability across the blood-brain barrier. [0003] Existing methods for predicting the blood-brain barrier permeability of drugs are based on the physical properties and chemical structures of the drug, but this method is only suitable for small molecule compounds that pass through the blood-brain barrier through passive diffusion, while for more If there are more and mo...

AI Technical Summary

Problems solved by technology

[0003] Existing methods for predicting the blood-brain barrier permeability of drugs are based on the physical properties and chemical structures of the drug, but this method is only suitable for small molecule compounds that pass through the blood-brain barrier through passive diffusion, while for more More and more complex penetration pathways, this method is powerless

[0004] It can be seen that the data set range of the existing prediction method for the blood-brain barrier permeability of drugs is too narrow, which makes the use of the prediction method more limited and cannot meet the needs of modern medicine

Images