Novel deep learning model for predicting compound protein affinity, computer equipment and storage medium

Abstract

The invention discloses a novel deep learning model for predicting compound protein affinity. The novel depth model comprises a BiGRU (Bipolar Gated Recirculation Unit) model, a GCN (Graph Convolutional Neural Network) model and a CNN (Convolutional Neural Network) model, wherein the whole network architecture is BiGRU / BiGRU / GCN-CNN. The bidirectional gating cycle unit model comprises a sequence processing model composed of two gating cycle units (GRU), one input is forward input, the other input is reverse input, and the bidirectional gating cycle unit model is a bidirectional recurrent neural network with only an input gate and a forgetting gate. The input of the model is a compound one-dimensional SMILES sequence, a protein sequence and a compound two-dimensional molecular diagram, andthe three sequences are respectively input into a BiGRU / BiGRU / GCN model. BiGRU / BiGRU / GCN output represents a feature vector of the compound and a feature vector of the protein. The CNN model is composed of a convolution layer, a pooling layer and a full connection layer, and inputs of the model are a feature vector of a compound and a feature vector of a protein; The final output of the BiGRU / BiGRU / GCN-CNN model is a root mean square error value for predicting a compound protein affinity value.

Description

technical field [0001] The invention relates to the field of molecular feature extraction of compound proteins, in particular to a new deep learning model for predicting the affinity of compound proteins, computer equipment, and storage media. Background technique [0002] Successfully identifying compound-protein interactions is a critical step in discovering new uses for existing compounds. The field continues to expand as new compounds are discovered, and the repurposing and new interactions of existing compounds are of interest to many researchers. Drug repositioning, that is, finding new uses of approved drugs, will greatly shorten the time to develop new drugs, which has also attracted the attention of many researchers. Therefore, based on the interactions that have been measured in clinical trials, using statistical and machine learning models to predict the strength of drug-target interactions is an important alternative. Such as support vector machines, logistic r...

AI Technical Summary

Problems solved by technology

[0004] The purpose of the present invention is to solve the problem of the loss of important information of the above-mentioned compound molecules and improve the prediction accuracy. The embodiment of the present invention provides a new deep learning model for predicting the protein affinity of compounds, computer equipment, and storage media. The combination of molecular graph structure information and one-dimensional SMILES string information can extract more information about compound molecules, and use deep learning methods to improve the accuracy of predicting compound protein affinity values

Images