Method and device for predicting binding free energy of protein and ligand molecules

Abstract

The invention provides a method and device for predicting the binding free energy of protein and ligand molecules, and the method comprises the steps: S1, constructing a local database; s2, analyzingthe data to obtain a ligand molecule and an amino acid molecule in a protein binding pocket taking the ligand molecule as a center; s3, calculating the MACCS secret keys of the ligand molecules and the near amino acids; s4, calculating ECFP fingerprints of ligand molecules and near amino acids; s5, converting the MACCS key and ECFP fingerprint information of the ligand molecule and protein into aone-dimensional tensor to form a training set and a test set; s6, establishing a machine learning model, and training the machine learning model; s7, calculating and comparing a Pearson correlation coefficient and an absolute error, and verifying a prediction result of the machine learning model; and S8, predicting the binding constant of the protein and the ligand molecule by using the trained machine learning model, and calculating the binding free energy. Compared with the prediction result of a single fingerprint, the prediction result of the combined fingerprint is obviously better, and the accuracy of free energy prediction is improved.

Description

technical field [0001] The invention relates to the technical field of computer-aided drug screening, in particular to a method and device for predicting the binding free energy of proteins and ligand molecules. Background technique [0002] How to screen and obtain the final lead molecule from tens of millions of molecules is the key technology of drug screening. Free energy calculation methods are at the core of high-throughput drug screening. With the rapid development of computer technology and computational theoretical methods, new drug development methods using computer-aided drug design have emerged. [0003] Computer-aided drug design is the science of drug design based on physical laws with the help of high-performance computers. The application of computer in the field of drug design marks that people's research and development of drugs has reached the stage of rational design from blind screening. With the development of computer performance, the demand for pre...

AI Technical Summary

Problems solved by technology

[0007] In view of the above problems, the present invention provides a method and device for predicting the binding free energy of proteins and ligand molecules, which effectively solves the technical problem that the prediction accuracy of existing methods is not high

Images