Method and apparatus for molecular toxicity prediction based on multi-task graph neural network

Abstract

The invention discloses a method and an apparatus for molecular toxicity prediction based on a multi-task graph neural network. The method comprises the following steps: S1, preparing a toxicity data set, and obtaining toxicity data represented by a chemical molecule standard expression; S2, generating an atomic node eigenvector by using the toxicity data which is obtained in the step S1 and represented by the chemical molecule standard expression; S3, generating a side information eigenvector by using the toxicity data which is obtained in the step S1 and represented by the chemical molecule standard expression; S4, on the basis of the atomic node eigenvector obtained in the step S2 and the side information eigenvector obtained in the step S3, constructing a molecular toxicity prediction model based on a multi-task graph neural network; S5, verifying performance of the model. According to the multi-task graph neural network designed for molecular toxicity datasets, an automatic learning molecular graph structure information model is constructed, and the performance of a toxicity prediction task can be improved by using a multi-task learning method in combination with the relevance between molecular toxicity tasks.

Description

technical field [0001] The invention relates to a molecular toxicity prediction method and device based on a multi-task graph neural network, which can be used in the technical field of artificial intelligence medicine. Background technique [0002] Drug toxicity refers to adverse effects on an organism due to the action or metabolism of a compound. In the early stages of drug discovery, molecular toxicity prediction is critical for early exclusion of drug candidates in clinical trials. About 30% of new drug development failures are due to safety and toxicity issues, so toxicity prediction is crucial in the drug discovery and development cycle. [0003] Traditionally, evaluating drug toxicity through in vivo biological experiments is usually time-consuming and labor-intensive, and drug toxicity prediction based on machine learning is an important supplement. Toxicity prediction based on machine learning starts from the molecular structure of the compound, and builds a mach...

AI Technical Summary

Problems solved by technology

In addition, when molecular toxicity is predicted based on traditional machine learning methods, the molecular characteristics of compounds are mainly extracted manually, which requires researchers to have a high professional knowledge background and a high threshold

Images