Molecule generation method and device, computer readable storage medium and terminal equipment

Abstract

The embodiment of the invention discloses a molecule generation method and device, a computer readable storage medium and terminal equipment, and is applied to the technical field of information processing of artificial intelligence. The molecule generation device can determine activity information of generated molecules formed after the seed molecules are subjected to shape change, so that the combination stability of the generated molecules and a receptor is considered; meanwhile, the molecule generation device can compare the first pharmacophore characteristics of the generation molecules with higher activity with the second pharmacophore characteristics of the seed molecules to obtain the generation molecules with the similarity in a preset range as new seed molecules, and then the newgeneration molecules are formed. When the similarity of the pharmacophore characteristics is small, the skeleton difference between the generated molecules and the seed molecules is large, such thatthe generated molecules with characteristics of rich skeleton and high activity can be obtained when the new generated molecules are formed through the new seed molecules so as to accelerate the discovery of the new drug.

Description

technical field [0001] The invention relates to the technical field of information processing of artificial intelligence, in particular to a molecular generation method, device, computer-readable storage medium and terminal equipment. Background technique [0002] In the field of drug design, in order to design more accurate drugs, not only the spatial information of the drug, that is, the shape and structure of the molecule represented by the drug, but also the way the drug acts as a ligand and receptor, and the way the drug works series of conditions, etc. [0003] With the development of artificial intelligence, the practical application of artificial intelligence is more and more extensive, and the application of artificial intelligence to the field of drug design can make drug design more accurate, specifically, through convolutional neural network (Convolutional Neural Network, CNN) and long-short Long Short-Term Memory (LSTM) network, after combining any molecule wit...

AI Technical Summary

Problems solved by technology

However, there may be differences in the similarity between the molecules obtained by the existing methods and the molecules in the original input network, which will affect the docking results of the generated molecules as ligands and receptors, resulting in a decrease in the expected ratio of generated molecules

Images