Drug screening model construction method, a drug screening model construction device, a drug screening method, apparatus and a medium

1 . A drug screening model construction method, which is used for protein crystal structure screening, comprising:

obtaining a drug training set, wherein the drug training set comprises a chemical formula of a drug protein, a chemical formula of a small molecule, and a classification label;

based on the chemical formula, drawing an initial graph network of the drug protein and the small molecule, wherein atoms are nodes and wherein chemical bonds are edges connecting nodes;

using a random initialization vector to identify an initial weight vector of each node in the initial graph network;

reconstructing each node of the initial graph network according to the initial weight vector of the node, weight vectors of nodes connected to the node, and a connection relationship of the initial graph network to obtain a reconstruction network, repeating the reconstruction steps to obtain at least two layers of reconstruction networks;

respectively extracting hierarchical network features from the initial graph network and at least two layers of reconstruction graph networks; and

constructing a drug screening model by performing deep learning on the hierarchical network features according to the classification labels.

2 . The method according to claim 1 , wherein the initial graph network for drawing the drug protein and small molecule based on chemical formulas further comprises:

performing molecular docking between the drug protein and the small molecule based on traditional molecular dynamics to obtain a target molecule; and

according to a chemical formula of the target molecule, drawing the initial graph network of the drug protein and the small molecule.

3 . The method according to claim 1 , wherein, based on the chemical formula, the initial graph network for drawing the drug protein and the small molecule further comprises:

drawing the initial graph network of the drug protein and the small molecule based on the chemical formula, wherein the initial graph network includes the initial graph network of the drug protein and the initial graph network of the small molecule.

4 . The method according to claim 1 , wherein using the random initialization vector to identify the weight vector of each node in the initial graph network further comprises:

using at least one subset of a set comprising uniform distribution and normal distribution to select a value of (0, 1) interval to generate an initialization vector and assigning the initialization vector to a node as the weight vector.

5 . The method according to claim 1 , wherein reconstructing each node of the initial graph network according to the connection relationship of the initial graph network to obtain a reconstruction graph network, further comprises:

obtaining the weight vector of each node and the associated weight vector of the associated node connected with the node according to the connection relationship of the initial graph network;

integrating the weight vector with the associated weight vector to obtain the reconstruction weight vector of the node; and

generating the reconstruction graph network according to the reconstruction weight vector.

6 . The method according to claim 1 , wherein extracting the hierarchical network features further comprising:

performing feature extraction on the initial graph network and at least two layers of reconstruction graph networks by functions to obtain function vector features; and

normalizing the function vector features in a probability space to obtain hierarchical network features.

7 . The method according to claim 1 , further comprising:

drawing a target initial graph network based on the chemical formula of the target protein and small molecule;

inputting the target initial graph network into the drug screening model, and

outputting an analysis result of the target protein and small molecule.

8 . A drug screening model reconstruction device, comprising:

a training set acquisition module, used to acquire a drug training set, wherein the drug training set includes a chemical formula of a target protein, a chemical formula of a small molecule, and a classification label;

a graph network drawing module, used to draw an initial graph network based on the chemical formula, in which atoms are nodes and chemical bonds are edges connecting nodes;

a vector identification module, used to identify a weight vector of each node in the initial graph network by using a random initialization vector;

a reconstruction module, used to reconstruct each node of the initial graph network according to an initial weight vector of the node, weight vectors of nodes connected to the node, and a connection relationship of the initial graph network to obtain a reconstruction graph network, and repeating the reconstruction steps to obtain at least two layers of reconstruction networks; and

a model training module, used to respectively extract hierarchical network features from the initial graph network and at least two layers of reconstruction graph networks, and construct a drug screening model by performing deep learning on a hierarchical network features according to the classification label.

9 . A computer-readable storage medium on which a computer program is stored, characterized in that, when the computer program is executed by a processor, the steps of a method comprising:

obtaining a drug training set, wherein the drug training set comprises a chemical formula of a drug protein, a chemical formula of a small molecule, and a classification label;

based on the chemical formula, drawing an initial graph network of the drug protein and the small molecule, wherein atoms are nodes and wherein chemical bonds are edges connecting nodes;

using a random initialization vector to identify an initial weight vector of each node in the initial graph network;

reconstructing each node of the initial graph network according to the initial weight vector of the node, weight vectors of nodes connected to the node, and a connection relationship of the initial graph network to obtain a reconstruction network, repeating the reconstruction steps to obtain at least two layers of reconstruction networks;

respectively extracting hierarchical network features from the initial graph network and the at least two layers of reconstruction graph networks; and

constructing a drug screening model by performing deep learning on the hierarchical network features according to the classification labels.