Molecular volume calculation method based on variable radius Gaussian ball and molecular three-dimensional similarity scoring method for virtual drug screening

Abstract

The invention relates to the technical field of computer-aided drug research and development, in particular to a molecular volume calculation method based on a variable radius Gaussian ball and a molecular three-dimensional similarity scoring method for virtual drug screening. According to the method, the value taking method of the Gaussian sphere radius is improved, that is, the Gaussian sphere radius is not equal to the Van der Waals radius of the corresponding atom but smaller than the Van der Waals radius of the atom, and the changed proportion is related to the chemical environment where the atom is located, so that the error caused by mutual overlapping of Gaussian spheres is eliminated, and the virtual screening precision of the medicine is effectively improved; further selecting multi-dimensional similarity as a characteristic parameter, and giving a final comprehensive score through the transformation of a deep neural network. According to the scoring method, the drug screening accuracy is remarkably improved, and meanwhile, the calculation speed of screening high throughput is kept, so that molecules with potential biological activity can be screened out from a database containing a large number of molecules as much as possible, and the problem of false positive or false negative is solved.

Description

technical field [0001] The invention relates to the technical field of computer-aided drug research and development, in particular to a molecular volume calculation method based on a variable-radius Gaussian sphere and a molecular three-dimensional similarity scoring method for virtual drug screening. Background technique [0002] Drug R&D has the characteristics of large investment, high risk, and long cycle. Usually, a drug R&D cycle is more than 10 years, and the R&D investment is hundreds of millions of dollars, and it shows an upward trend year by year. Drug screening is a key link in drug discovery, and high-throughput drug virtual screening can greatly reduce screening time and cost, which is of great significance for accelerating drug development. [0003] In drug virtual screening, molecular screening and ranking based on molecular three-dimensional similarity scoring methods are commonly used. This type of scoring method includes the similarity of molecular shape ...

AI Technical Summary

Problems solved by technology

However, the significant problem of the scoring method used above is that the accuracy is poor, which leads to high false positives or false negatives in drug virtual screening; on the other hand, because the molecular volume is related to the molecular shape, the traditional three-dimensional volume of drug molecules The calculation method is calculated by a group of superimposed Gaussian spherical models. For example, the invention patent with the publication number CN102799779A and the patent name "A Method for Comparing the Shape of Drug Molecules" has a method for calculating the three-dimensional volume of molecules in its technical proposal. Yes: according to the type of each atom in the molecule, the corresponding van der Waals radius is obtained, and the three-dimensional structure information of the molecule is converted into a set of Gaussian spheres representing each atom in the molecule. The value of the radius of each Gaussian sphere is equal to the van der Waals radius of the corresponding atom, And the position of each Gaussian sphere is the same as the coordinates of the corresponding atom; on this basis, the three-dimensional volume of the molecule is calculated, and then the similarity between the shapes of the two molecules is compared

However, the defect of the above calculation method is that the radius of the Gaussian sphere representing the atomic volume in the molecule is the van der Waals radius of the corresponding atom. The result of this does not eliminate the error caused by the overlapping of Gaussian spheres, which also makes the drug virtual screening The accuracy of the

Images