Method for predicting inhibitory activity of fructose-1, 6-diphosphatase inhibitor based on quantitative structure-activity relationship model

Abstract

The invention belongs to the technical field of drug activity prediction methods, and relates to a method for predicting the inhibitory activity of a fructose-1, 6-diphosphatase inhibitor based on a quantitative structure-activity relationship model. The method comprises the specific steps of collection of a sample set, processing and optimization of the sample set, establishment of an inhibitor molecule descriptor set, data set division, establishment of a QSAR linear model through a heuristic algorithm, establishment of a QSAR nonlinear model through a gradient boosting regression algorithm, and comparative analysis of two model results. In the initial development stage of the inhibitor, the molecular structure of the inhibitor is input through a computer, the inhibition concentration of the inhibitor is predicted based on HM and GBR methods, results of the two models are compared to solve the problem that prediction precision of a single linear model is not enough, the development risk of the inhibitor in the later stage is effectively reduced, and the research and development cost is reduced; the two established models are verified, so that the reliability of the models is proved; and meanwhile, a pioneer is created for application of the GBR algorithm in the field of computer-aided drug design.

Description

Technical field: [0001] The invention belongs to the technical field of drug activity prediction methods, and specifically relates to a method for predicting the inhibitory activity of fructose-1,6-bisphosphatase inhibitors based on a quantitative structure-activity relationship model, which is successively established according to the molecular structure and physical and chemical properties of the inhibitors Linear model and nonlinear model, and predict the inhibitory activity of the inhibitor, solve the problem of insufficient prediction accuracy of a single linear model, can effectively reduce the risk of later development of inhibitors, and reduce the cost of research and development. Background technique: [0002] Diabetes mellitus (DM), characterized by hyperglycemia, is a chronic metabolic disease whose incidence is increasing internationally. It can cause serious damage to the kidneys, blood vessels, eyes, nerves and heart. In addition, diabetes is closely related to...

AI Technical Summary

Problems solved by technology

The applicant consulted the information and found that there is no application of the GBR-based QSAR model to N-arylsulfonyl-indole-2-carboxamide derivatives. In order to study the N-arylsulfonyl-indole-2-carboxamide For the inhibitory effect of amide derivatives, the applicant applied linear methods and nonlinear methods to establish QSAR models, which brought bright prospects for further research on T2DM

Images