Molecular generation model training method and device, equipment and storage medium

Abstract

The invention provides a training method of a molecular generation model. The method comprises the steps of obtaining basic molecules and target molecules; encoding the basic molecule through an encoding layer to obtain a first graph node feature and a first tree node feature, and encoding the target molecule to obtain a second graph node feature and a second tree node feature; matching the firstgraph node feature with the second graph node feature through the alignment layer to obtain a first similarity feature, and matching the first tree node feature with the second tree node feature to obtain a second similarity feature; generating a graph node feature through a generation layer according to the first similarity feature and the first graph node feature, and generating a tree node feature according to the second similarity feature and the first tree node feature; respectively decoding the graph node characteristics and the tree node characteristics through a decoding layer to obtain prediction molecules; updating model parameters based on the difference between the prediction molecule and the target molecule; and through the obtained model, generating high-attribute molecules with partial structures of basic molecules reserved.

Description

technical field [0001] The present application relates to artificial intelligence technology, and in particular to a training method, device, equipment and computer-readable storage medium for a molecular generation model. Background technique [0002] Artificial intelligence (AI, Artificial Intelligence) is a comprehensive technology of computer science. By studying the design principles and implementation methods of various intelligent machines, the machines have the functions of perception, reasoning and decision-making. Artificial intelligence technology is a comprehensive subject that involves a wide range of fields, such as natural language processing technology and machine learning / deep learning. It is believed that with the development of technology, artificial intelligence technology will be applied in more fields and play a more important role. increasingly important value. [0003] Applying artificial intelligence technology to molecular generation, through the m...

AI Technical Summary

Problems solved by technology

[0003] Applying artificial intelligence technology to molecular generation, through the machine's reasoning and decision-making functions, molecules with high attributes can be generated based on some basic molecules with low attributes, thereby reducing the time spent on manually discovering molecules with high attributes; however, related technologies The training process of the molecular generation model is cumbersome and time-consuming, and because the structural similarity between molecules cannot be discovered, the generated molecules cannot retain the structural information of the original molecules, and the rationality is low.

Images