Drug-target interaction prediction model method based on deep embedding learning of molecular graph and sequence

Abstract

The invention provides a drug-target interaction prediction model method based on deep embedding learning of a molecular graph and a sequence, and the method comprises the steps: building a map neural network based on an attention mechanism and an attention-oriented bidirectional LSTM to predict the interaction, wherein in order to achieve the more effective training, a pre-training model BERT is utilized to extract embedded vector representation of each sub-sequence from a protein sequence, and meanwhile, a local breadth-first search algorithm is designed to extract sub-graph information of a drug molecular graph, so that a graph neural network learns higher feature information. On one hand, in the aspect of drug molecules, better spatial features can be learned based on the molecular graph; on the other hand, the protein sequence data size is large, larger protein space can be covered, and the generalization ability is improved.

Description

technical field [0001] The invention belongs to the field of deep embedding learning medicine, in particular to a drug-target interaction prediction method based on graph and sequence deep embedding learning. Background technique [0002] The identification of drug-target interactions (DTIs) is an important task in drug discovery and chemogenomics research. Although experimentally measuring the binding force between a compound and a protein is the most accurate method, it is expensive and time-consuming. Therefore, scholars have proposed many computational models based on large data sets to predict DTI. [0003] Molecular docking methods are based on structure to predict and determine drug-target interactions. In drug design, this method is mainly used to search small molecule databases for small molecules with good affinity to receptor biomacromolecules, and to conduct pharmacological tests to discover new lead compounds. Meanwhile, machine learning methods are widely us...

AI Technical Summary

Problems solved by technology

[0006] The purpose of the present invention is to provide a drug-target interaction prediction method based on deep embedding learning of graphs and sequences to solve the problem that the existing target interaction prediction methods have limited data for training, limited model generalization ability, and limited coverage. small space problem

Images