Small molecule drug hERG toxicity prediction method and device based on graph attention mechanism transfer learning

Abstract

The invention discloses a graph attention mechanism transfer learning-based small molecule drug hERG toxicity prediction method and device; the method comprises the following steps: S1, data set preprocessing: enabling a to-be-detected drug-like compound to generate a fingerprint sequence through molecular fingerprint generation software; s2, acquiring atom and chemical bond characteristics through the fingerprint sequence generated in the step S1, and constructing a molecular graph and graph characteristics through the atom and chemical bond characteristics; s3, processing the molecular map obtained in the step S2 through a map attention mechanism, and generating a feature vector of each atom in the molecule; s4, generating a molecular feature vector through a graph attention mechanism and the feature of each atom. According to the method, a molecular graph structure is processed based on a graph attention mechanism, a substructure which contributes to a predicted attribute value is effectively obtained, and a source domain data set and a target domain data set are processed based on transfer learning; and thereby, the problem that the sample size is insufficient is effectively solved.

Description

technical field [0001] The invention relates to a small molecule drug hERG toxicity prediction method and device based on graph attention mechanism transfer learning, which can be used in the technical field of artificial intelligence drug design. Background technique [0002] Small molecule drug toxicity is a kind of toxicology research. In the process of drug development, it plays an equally important role with pharmacokinetic research and pharmacodynamic research, and is one of the main reasons for the failure of drug research and development. Putting the toxicity evaluation of small molecule drugs in the early stage of new drug development can help shorten the development cycle and reduce the cost of research and development. It can be seen that the toxicity evaluation of small molecule drugs is very necessary. [0003] The traditional toxicity detection based on biological experiments is a common method for toxicity assessment of small molecule compounds. Although the t...

AI Technical Summary

Problems solved by technology

The general machine learning method needs to collect a large amount of sample data when building a model. However, due to the high requirements of the hERG experiment and the small amount of hERG sample data, it is difficult to build a good model for predicting hERG indicators.

Images