Pharmacokinetic Properties and Toxicity Prediction Method of Drug Molecules Based on Capsule Network

Abstract

Pharmacokinetic Properties and Toxicity Prediction Method of Drug Molecules Based on Capsule Network. After constructing comprehensive molecular fingerprints and molecular descriptors and preparatory work for establishing models, the low-level feature content of molecules is extracted from the upper-level low-level features through convolution or restricted Boltzmann machine operations, and then the capsule network method is used in the next step. The high-level features of molecules are abstracted from a layer of high-level features, and the relationship between high-level features and active labels is fitted by a dynamic routing algorithm to predict the pharmacokinetic properties and toxicity classification of unknown small molecules. The present invention does not need to collect large-scale data sets for training, and realizes automatic dimensionality reduction through end-to-end optimization of the input, updates the coupling coefficient through iterative dynamic routing process, and dynamic routing transfers all the features of the upper layer capsule to any one of the lower layer In the capsule, the hierarchical position relationship between the low-level features and high-level features is greatly preserved. Better predictive performance than traditional machine learning methods.

Description

technical field [0001] The invention relates to the field of computer-aided drug molecule design, in particular to a method for predicting pharmacokinetic properties and toxicity of drug molecules based on a capsule network. Background technique [0002] The great success of a drug depends not only on its good efficacy, but also on its excellent pharmacokinetic properties and low toxicity. According to statistics, the poor absorption, distribution, metabolism, excretion and toxicity of candidate drugs account for more than 50% of the reasons for the failure of drug development. Therefore, it is possible to exclude and optimize compounds with poor pharmacokinetic properties and toxicity in the early stage of drug development Greatly improve the success rate of drug development. In recent years, although in vitro high-throughput screening methods can be used to measure the pharmacokinetic properties and toxicity of compounds, experimental-based assays are not only expensive a...

AI Technical Summary

Problems solved by technology

This method is based on the molecular fingerprints and molecular descriptors of ligands, and uses deep learning capsule networks to establish the relationship between molecular fingerprints and molecular descriptors, pharmacokinetic properties and toxicity, and overcomes the inadequacy of predicting classification effects in the prior art. Good, the original information of molecular fingerprints and molecular descriptors that characterize ligands is seriously lost, and the accuracy of prediction is greatly dependent on the size of the training set.

Images