Processing method and device for predicting binding site of molecular fragment

Abstract

The embodiment of the invention relates to a processing method and device for predicting a binding site of a molecular fragment. The method comprises the following steps: constructing a binding site prediction model; constructing a model training data set and recording the model training data set as a corresponding first data set; training the binding site prediction model based on the first data set; after model training is finished, two three-dimensional molecular fragment structures input by a user are received to serve as corresponding fragment structures A and B; and identifying the binding site information of the fragment structures A and B by using the binding site prediction model, and feeding back the identification information to the current user. According to the invention, the prediction efficiency can be improved, and the discovery capability of unknown connection modes can be enhanced.

Description

Technical Field

[0001] The present invention relates to the technical field of data processing, and in particular to a processing method and device for predicting binding sites of molecular fragments. Background Art

[0002] In the fields of molecular docking, synthetic chemistry, and molecular editing, different binding sites between molecular fragments (or synthetic building blocks) may lead to different binding efficiencies and overall molecular properties of the fragments (or building blocks) of the binding molecule (composed of two molecular fragments or two synthetic building blocks). Therefore, in the process of molecular docking / synthesis / editing and other molecular design tasks, a prediction method is required to predict the optimal binding sites of two molecular fragments (or two synthetic building blocks). At present, this prediction method still mainly relies on the artificial experience of scientific researchers. Specifically, some quantum computing tools are used to calculate some empirical parameters of two molecular fragments (or two synthetic building blocks) before prediction, and then the docking site analysis is performed based on the calculation results and artificial experience or a series of preset docking rules. Obviously, the defects of this conventional prediction method are quite obvious: 1) the prediction efficiency is relatively low; 2) due to the limitations of artificial experience / rules, the ability to discover new connection methods is relatively weak. Summary of the invention

[0003] The purpose of the present invention is to provide a method, device, electronic device and computer-readable storage medium for predicting the binding sites of molecular fragments in view of the defects of the prior art. The present invention constructs a binding site prediction model for predicting the binding sites of the first and second molecular fragments input by the model and outputting the corresponding binding probability prediction vector; and constructs a first data set through big data collection to train the binding site prediction model; after the model training is completed, the binding site prediction model is used to identify the binding site information of any two three-dimensional molecular fragment structures input by the user and the identification information is fed back to the current user. The end-to-end binding site prediction model provided by the present invention can improve the prediction efficiency on the one hand, and on the other hand, it can also improve the generalization of the model and enhance the ability to discover unknown connection modes through big data training.

[0004] To achieve the above object, a first aspect of an embodiment of the present invention provides a method for predicting binding sites of molecular fragments, the method comprising:

[0005] Constructing a binding site prediction model; the binding site prediction model is used to perform binding site prediction processing on the first and second molecular fragments input into the model and output a corresponding binding probability prediction vector;

[0006] Constructing a model training data set as the corresponding first data set; and training the binding site prediction model based on the first data set;

[0007] After the model training is completed, two three-dimensional molecular fragment structures input by the user are received as corresponding fragment structures A and B; and the binding site prediction model is used to identify the binding site information of the fragment structures A and B and the identification information is fed back to the current user.

[0008] Preferably, the first and second molecular fragments are each a three-dimensional molecular fragment structure;

[0009] The first molecular fragment includes a first set of atoms and a first set of chemical bonds;

[0010] The first atom set includes multiple first atoms; the atomic properties of the first atoms include at least a first atom identifier, a first atom type, a first atom coordinates, and a first atom chiral property set; the first atom identifier is a unique identifier of the current first atom; the first atom type is a chemical element type of the current first atom; the first atom coordinates are three-dimensional space coordinates of the current first atom; the first atom chiral property set consists of multiple first chiral properties; each of the first chiral properties consists of a corresponding property type and a property value; if the first atom is a chiral center atom, all property values ​​in the corresponding first atom chiral property set are not empty; if the first atom is not a chiral center atom, all property values ​​in the corresponding first atom chiral property set are empty;

[0011] The first chemical bond set includes multiple first chemical bonds; the chemical bond attributes of the first chemical bond include at least a first chemical bond identifier, a first chemical bond type, and a first bonding atom group; the first chemical bond identifier is a unique identifier of the current first chemical bond; the first chemical bond type includes multiple chemical bond types; the first bonding atom group consists of the first atom identifiers of the two first atoms currently connected by the first chemical bond;

[0012] The second molecular fragment includes a second set of atoms and a second set of chemical bonds;

[0013] The second atom set includes multiple second atoms; the atomic properties of the second atoms include at least a second atom identifier, a second atom type, a second atom coordinates, and a second atom chiral property set; the second atom identifier is a unique identifier of the current second atom; the second atom type is the chemical element type of the current second atom; the second atom coordinates are the three-dimensional space coordinates of the current second atom; the second atom chiral property set consists of multiple second chiral properties; each second chiral property consists of a corresponding property type and a property value; if the second atom is a chiral center atom, all property values ​​in the corresponding second atom chiral property set are not empty; if the second atom is not a chiral center atom, all property values ​​in the corresponding second atom chiral property set are empty;

[0014] The second chemical bond set includes multiple second chemical bonds; the chemical bond properties of the second chemical bond include at least a second chemical bond identifier, a second chemical bond type, and a second bonding atom group; the second chemical bond identifier is the unique identifier of the current second chemical bond; the second chemical bond type includes multiple chemical bond types; the second bonding atom group consists of the second atom identifiers of the two second atoms currently connected by the second chemical bond.

[0015] Preferably, the first and second model input ends of the binding site prediction model are used to receive the first and second molecular fragments input by the model respectively, and the model output end is used to output the corresponding binding probability prediction vector;

[0016] The binding site prediction model includes an encoding initialization module, a graph neural encoding network and an MLP network;

[0017] The first and second input terminals of the encoding initialization module are connected to the first and second model input terminals respectively, and the output terminal is connected to the input terminal of the graph neural encoding network; the output terminal of the graph neural encoding network is connected to the input terminal of the MLP network; the output terminal of the MLP network is connected to the output terminal of the model;

[0018] The encoding initialization module is used to construct a molecular graph according to the first and second molecular fragments input by the model to obtain a corresponding molecular graph G; and to perform state encoding initialization processing according to the molecular graph G to obtain a corresponding state encoding tensor H 0 Sending to the graph neural encoding network;

[0019] The molecular graph G includes a node set V and an edge set E;

[0020] The node set V consists of N 1 +N 2 Nodes v i The edge set E is composed of multiple edges ei,j Composition; 1≤node index i≤N 1 +N 2 , 1≤node index j≤N 1 +N 2 , j≠i, N 1 、N 2 The total number of atoms of the first and second molecular fragments respectively; the node v i corresponds to one of the first atoms or one of the second atoms; the edge e i,j corresponding to one of said first chemical bonds or one of said chemical bonds;

[0021] The state encoding tensor H 0 Including N 1 +N 2 The node state vector h 0,i ; The node state vector h 0,i With the node v i One-to-one correspondence; the node state vector h 0,i It consists of atomic type features, atomic coordinate features, chirality feature set, associated chemical bond feature set, and cross-fragment distance feature set;

[0022] The atomic type feature is the current node state vector h 0,i a one-hot encoding of the first or second atom type corresponding to the corresponding first or second atom;

[0023] The atomic coordinate feature is the current node state vector h 0,i the atomic coordinates of the first or second atom corresponding to the first or second atom;

[0024] The chiral feature set is composed of multiple chiral attribute features; each chiral attribute feature is the current node state vector h 0,i a feature encoding vector of a first or second chiral property in the first or second atomic chiral property set corresponding to the first or second atom;

[0025] The associated chemical bond feature set is composed of one or more associated chemical bond features; the associated chemical bond features include chemical bond type features and chemical bond direction features; each of the associated chemical bond features is related to the current node state vector h 0,iThe first or second chemical bond corresponding to the corresponding first or second atom corresponds to one of the first or second chemical bonds; the chemical bond type feature is a one-hot encoding of the first or second chemical bond type of the current corresponding first or second chemical bond; the chemical bond direction feature is a three-dimensional displacement vector starting from the current corresponding first or second atom to another first or second atom indicated in the first or second bonding atom group of the current corresponding first or second chemical bond;

[0026] The cross-segment distance feature set is composed of multiple cross-segment distance features; if the current node state vector h 0,i Corresponding to one of the first atoms, each of the cross-fragment distance features is the square value of the straight-line distance between the currently corresponding first atom and one of the second atoms in the second molecular fragment; if the current node state vector h 0,i Corresponding to one of the second atoms, each of the cross-molecule distance features is the square value of the straight-line distance between the currently corresponding second atom and one of the first atoms in the first molecular fragment;

[0027] The graph neural coding network is composed of M layers of GNN layers connected in sequence, where the total number of coding layers M is a preset positive integer and the value is greater than 2; the GNN layer in the mth layer is used to encode the state input tensor H of this layer m-1 Perform state conversion processing to obtain the corresponding state encoding tensor H m , and when the current coding layer index m is less than M, the state coding tensor H m Send to the m+1th GNN layer, and when the current encoding layer index m is equal to M, the state encoding tensor H m＝M Send to the MLP network; 1≤ coding layer index m≤M; the state coding tensor H m Including N 1 +N 2 The node state vector h m,i , the node state vector h m,i With the node v i One to one correspondence;

[0028]

[0029] Feature d i,j The setting rule is: if the node v i 、v j The corresponding two atoms belong to the same molecular fragment, then the corresponding feature d i,j Fixed to 0; if node v i 、v j The corresponding two atoms belong to two molecular fragments, so the corresponding feature d i,jfixed to the corresponding cross-fragment distance feature;

[0030] f m is the state transition function of the GNN layer at the mth layer, θ m is the mth state transition function f m The model parameters of the corresponding m-th GNN layer;

[0031] The MLP network is used to encode the state tensor H output by the GNN layer of the Mth layer M Perform a combined probability prediction to obtain the corresponding combined probability prediction vector; the combined probability prediction vector is composed of N 1 +N 2 The predicted probability of a node is p i Composition; the node prediction probability p i With the node v i One to one correspondence;

[0032] P = f MLP (H M θ MLP );

[0033] P is the combined probability prediction vector, f MLP is the network mapping function of the MLP network, θ MLP are the model parameters of the MLP network.

[0034] Preferably, the first data set includes a plurality of first data records; the first data records include a first training molecule fragment, a second training molecule fragment and a first label vector;

[0035] The first and second training molecular fragments are each a three-dimensional molecular fragment structure;

[0036] The first label vector includes multiple first node labels; the total number of the first node labels is the sum of the total number of atoms in the first and second training molecular fragments; the label value of the first node label is 1 or 0; in the first label vector, only two of the first node labels have a label value of 1, and the rest are 0, and the two atoms corresponding to the two first node labels with the label value of 1 are not in the same training molecular fragment.

[0037] Preferably, the model building training data set is recorded as the corresponding first data set, specifically including:

[0038] Step 51, collecting data on the three-dimensional molecular structures of various compound molecules through multiple types of public data channels to obtain corresponding multiple first molecular structures;

[0039] The multiple types of public data channels include at least various public data sets, journals / magazines / scientific and technological documents / papers that publish molecular three-dimensional structures;

[0040] Step 52, taking each of the first molecular structures as the corresponding current molecular structure; and performing molecular fragment sampling on the current molecular structure to obtain a corresponding plurality of sampling fragments; and performing a round of traversal on all the sampling fragments of the current molecular structure; and in this round of traversal, taking the currently traversed sampling fragment as the corresponding current fragment; and extracting the other sampling fragments in the current molecular structure that are connected to the current fragment in a single-atom connection manner to form a corresponding associated fragment set; and taking the current fragment as a corresponding first training molecular fragment, and taking any one of the sampling fragments in the current associated fragment set as a corresponding second training molecular fragment, and forming a corresponding first fragment group by the first training molecular fragment corresponding to the current fragment and each of the second training molecular fragments; and performing deduplication processing on all the obtained first fragment groups at the end of this round of traversal;

[0041] Step 53, perform a round of traversal on all the first fragment groups; and in this round of traversal, use the first fragment group currently traversed as the corresponding current fragment group; calculate the sum of the total number of atoms of the first and second training molecular fragments of the current fragment group to obtain the corresponding current atomic sum; and set a first label vector whose vector length matches the current atomic sum; and initialize the label values ​​of all the first node labels of the current first label vector to 0; and after the vector initialization is completed, reset the label values ​​of the two first node labels corresponding to the two fragment connecting atoms of the first and second training molecular fragments of the current fragment group in the first label vector to 1; and form a corresponding first data record by the first training molecular fragment corresponding to the current fragment group, the second training molecular fragment and the first label vector; and at the end of this round of traversal, form the corresponding first data set by all the obtained first data records.

[0042] Preferably, the training of the binding site prediction model based on the first data set specifically includes:

[0043] Step 61, based on a preset first segmentation ratio, the first data set is divided into two sub-data sets which are recorded as a corresponding first training set and a first evaluation set;

[0044] Wherein, both the first training set and the first evaluation set are composed of a plurality of the first data records; the ratio of the total number of records in the first training set and the first evaluation set satisfies the first segmentation ratio;

[0045] Step 62, extracting the first first data record of the first training set as the corresponding current training record;

[0046] Step 63, inputting the first and second training molecular fragments of the current training record as the corresponding first and second molecular fragments into the binding site prediction model to perform binding site prediction processing and using the binding probability prediction vector output by the model as the corresponding first prediction vector;

[0047] Step 64, inputting the first prediction vector and the first label vector of the current training record into a preset first model loss function to calculate and obtain a corresponding first loss value;

[0048] Wherein, the first model loss function at least includes a binary cross entropy loss function;

[0049] Step 65, identifying whether the first loss value satisfies a preset first loss value range; if the first loss value satisfies the first loss value range, proceeding to step 66; if the first loss value does not satisfy the first loss value range, based on a preset first model optimizer, performing a round of modulation on the model parameters of the graph neural encoding network of the binding site prediction model and the MLP network in a direction that minimizes the first model loss function, and returning to step 63 at the end of this round of modulation;

[0050] Step 66, identifying whether the current training record is the last first data record of the first training set; if so, going to step 67; if not, extracting the next first data record of the first training set as the new current training record, and returning to step 63;

[0051] Step 67, perform a round of traversal on all the first data records of the first evaluation set; and in this round of traversal, use the first data record currently traversed as the corresponding current evaluation record; and input the first and second training molecular fragments of the current evaluation record as the corresponding first and second molecular fragments into the binding site prediction model for binding site prediction processing and use the binding probability prediction vector output by the model as the corresponding second prediction vector; and form a corresponding prediction-label data pair by the second prediction vector and the first label vector of the current training record; and at the end of this round of traversal, calculate the accuracy, precision, recall and F1 score based on all the obtained prediction-label data pairs to obtain the corresponding first accuracy, first precision, first recall and first F1 score;

[0052] Step 68, identifying the first accuracy, the first precision, the first recall and the first F1 score; if the first accuracy does not meet the preset first accuracy range, or the first accuracy does not meet the preset first accuracy range, or the first recall does not meet the preset first recall range, or the first F1 score does not meet the preset first F1 score range, return to step 62 to continue training; if the first accuracy meets the first accuracy range, and the first accuracy meets the first accuracy range, and the first recall meets the first recall range, and the first F1 score meets the first F1 score range, stop training and confirm that the model training is completed.

[0053] Preferably, the using the binding site prediction model to identify the binding site information of the fragment structures A and B and feeding back the identification information to the current user specifically includes:

[0054] Step 71, inputting the fragment structures A and B as the corresponding first and second molecular fragments into the binding site prediction model for binding site prediction processing and using the binding probability prediction vector output by the model as the corresponding AB prediction vector;

[0055] Step 72: calculate the prediction probabilities p of all nodes corresponding to all atoms in the fragment structure A in the AB prediction vector. i Extract them to form a corresponding first probability set; and extract all the node prediction probabilities p corresponding to all atoms in the fragment structure B in the AB prediction vector i Extract them to form a corresponding second probability set;

[0056] Step 73: predict the probability p of the node with the largest probability value in the first probability set. i Recorded as the corresponding first maximum probability; and the predicted probability p of the node with the largest probability value in the second probability set i Recorded as the corresponding second maximum probability; and the atom identifier corresponding to the first maximum probability in the fragment structure A is used as the corresponding fragment A side binding atom identifier; and the atom identifier corresponding to the second maximum probability in the fragment structure B is used as the corresponding fragment B side binding atom identifier;

[0057] Step 74, the fragment A side is combined with the atom identifier and the corresponding first maximum probability to form the corresponding A fragment identification information; the fragment B side is combined with the atom identifier and the corresponding second maximum probability to form the corresponding B fragment identification information; and the A and B fragment identification information are combined to form the corresponding binding site identification information to feedback to the current user.

[0058] A second aspect of an embodiment of the present invention provides a device for implementing the processing method for predicting binding sites of molecular fragments described in the first aspect, the device comprising: a model building module, a model training module and a model application module;

[0059] The model building module is used to build a binding site prediction model; the binding site prediction model is used to perform binding site prediction processing on the first and second molecular fragments input by the model and output the corresponding binding probability prediction vector;

[0060] The model training module is used to construct a model training data set as a corresponding first data set; and train the binding site prediction model based on the first data set;

[0061] The model application module is used to receive two three-dimensional molecular fragment structures input by the user as corresponding fragment structures A and B after the model training is completed; and use the binding site prediction model to identify the binding site information of the fragment structures A and B and feed back the identification information to the current user.

[0062] A third aspect of an embodiment of the present invention provides an electronic device, including: a memory, a processor, and a transceiver;

[0063] The processor is used to couple with the memory, read and execute instructions in the memory, so as to implement the method steps described in the first aspect above;

[0064] The transceiver is coupled to the processor, and the processor controls the transceiver to send and receive messages.

[0065] A fourth aspect of an embodiment of the present invention provides a computer-readable storage medium, wherein the computer-readable storage medium stores computer instructions. When the computer instructions are executed by a computer, the computer executes the instructions of the method described in the first aspect above.

[0066] The embodiment of the present invention provides a processing method, device, electronic device and computer-readable storage medium for predicting the binding site of a molecular fragment. As can be seen from the above content, the embodiment of the present invention constructs a binding site prediction model for performing binding site prediction processing on the first and second molecular fragments input by the model and outputting the corresponding binding probability prediction vector; and constructs a first data set through big data collection to train the binding site prediction model; after the model training is completed, the binding site prediction model is used to identify the binding site information of any two three-dimensional molecular fragment structures input by the user and the identification information is fed back to the current user. The end-to-end binding site prediction model provided by the embodiment of the present invention improves the prediction efficiency on the one hand, and on the other hand, it can also improve the generalization of the model and enhance the ability to discover unknown connection methods through big data training. BRIEF DESCRIPTION OF THE DRAWINGS

[0067] Figure 1 A schematic diagram of a processing method for predicting binding sites of molecular fragments provided in Example 1 of the present invention;

[0068] Figure 2 This is a module structure diagram of the binding site prediction model provided in Example 1 of the present invention;

[0069] Figure 3 A module structure diagram of a processing device for predicting binding sites of molecular fragments provided in Embodiment 2 of the present invention;

[0070] Figure 4 A schematic diagram of the structure of an electronic device provided in Embodiment 3 of the present invention. DETAILED DESCRIPTION

[0071] In order to make the purpose, technical solution and advantages of the present invention clearer, the present invention will be further described in detail below in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0072] Embodiment 1 of the present invention provides a method for predicting the binding sites of molecular fragments, such as Figure 1 A schematic diagram of a method for predicting binding sites of molecular fragments provided in Example 1 of the present invention is shown. The method mainly includes the following steps:

[0073] Step 1: Construct a binding site prediction model.

[0074] Here, the binding site prediction model of the embodiment of the present invention is used to perform binding site prediction processing on the first and second molecular fragments input to the model and output the corresponding binding probability prediction vector.

[0075] It should be noted that the first and second molecular fragments inputted by the model are each a three-dimensional molecular fragment structure; here, the first and second molecular fragments can be two small fragments with a small number of atoms, or two synthetic building blocks with a large number of atoms and containing multiple small fragments; the data structures of the first and second molecular fragments are as follows:

[0076] 1) The first molecular fragment includes a first atom set and a first chemical bond set;

[0077] The first atom set includes multiple first atoms; the atomic properties of the first atoms include at least a first atom identifier, a first atom type, a first atom coordinates, and a first atom chiral property set; the first atom identifier is a unique identifier of the current first atom; the first atom type is the chemical element type of the current first atom; the first atom coordinates are the three-dimensional space coordinates of the current first atom; the first atom chiral property set consists of multiple first chiral properties; each first chiral property consists of a corresponding property type and a property value; if the first atom is a chiral center atom, all property values ​​in the corresponding first atom chiral property set are not empty; if the first atom is not a chiral center atom, all property values ​​in the corresponding first atom chiral property set are empty;

[0078] The first chemical bond set includes multiple first chemical bonds; the chemical bond attributes of the first chemical bond include at least a first chemical bond identifier, a first chemical bond type, and a first bonding atom group; the first chemical bond identifier is a unique identifier of the current first chemical bond; the first chemical bond type includes multiple chemical bond types; the first bonding atom group consists of the first atom identifiers of two first atoms connected by the current first chemical bond;

[0079] 2) the second molecular fragment includes a second set of atoms and a second set of chemical bonds;

[0080] The second atom set includes multiple second atoms; the atomic properties of the second atoms include at least a second atom identifier, a second atom type, a second atom coordinates, and a second atom chiral property set; the second atom identifier is a unique identifier of the current second atom; the second atom type is the chemical element type of the current second atom; the second atom coordinates are the three-dimensional space coordinates of the current second atom; the second atom chiral property set consists of multiple second chiral properties; each second chiral property consists of a corresponding property type and a property value; if the second atom is a chiral center atom, all property values ​​in the corresponding second atom chiral property set are not empty; if the second atom is not a chiral center atom, all property values ​​in the corresponding second atom chiral property set are empty;

[0081] The second chemical bond set includes multiple second chemical bonds; the chemical bond properties of the second chemical bond include at least a second chemical bond identifier, a second chemical bond type, and a second bonding atom group; the second chemical bond identifier is a unique identifier of the current second chemical bond; the second chemical bond type includes multiple chemical bond types; the second bonding atom group consists of the second atom identifiers of two second atoms connected by the current second chemical bond.

[0082] It should also be noted that the first and second model input ends of the binding site prediction model are used to receive the first and second molecular fragments of the model input respectively, and the model output end is used to output the corresponding binding probability prediction vector; Figure 2This is a module structure diagram of the binding site prediction model provided in Example 1 of the present invention.

[0083] The model components of the binding site prediction model include an encoding initialization module, a graph neural encoding network, and an MLP network.

[0084] The connection relationship between each model component is: the first and second input terminals of the encoding initialization module are respectively connected to the first and second model input terminals, and the output terminal is connected to the input terminal of the graph neural encoding network; the output terminal of the graph neural encoding network is connected to the input terminal of the MLP network; and the output terminal of the MLP network is connected to the model output terminal.

[0085] The component functions of each model component are as follows.

[0086] 1) Encoding initialization module:

[0087] The encoding initialization module of the binding site prediction model is used to construct a molecular graph according to the first and second molecular fragments input by the model to obtain the corresponding molecular graph G; and to perform state encoding initialization processing according to the molecular graph G to obtain the corresponding state encoding tensor H 0 Send to the graph neural encoding network.

[0088] Here, the molecular graph G of the embodiment of the present invention includes a node set V and an edge set E; wherein the node set V is composed of N 1 +N 2 Nodes v i The edge set E consists of multiple edges e i,j Composition; 1≤node index i≤N 1 +N 2 , 1≤node index j≤N 1 +N 2 , j≠i, N 1 、N 2 The total number of atoms in the first and second molecular fragments respectively; node v i Corresponding to a first atom or a second atom; edge e i,j Corresponding to a first chemical bond or a chemical bond.

[0089] The state encoding tensor H of the embodiment of the present invention 0 Including N 1 +N 2 The node state vector h 0,i ; Node state vector h 0,i With node v i One-to-one correspondence; node state vector h 0,i It consists of atomic type features, atomic coordinate features, chiral feature sets, associated chemical bond feature sets, and cross-fragment distance feature sets; among them:

[0090] a. The atomic type feature is the current node state vector h 0,i the one-hot encoding of the first or second atom type corresponding to the corresponding first or second atom;

[0091] b. The atomic coordinate feature is the current node state vector h 0,i the atomic coordinates of the first or second atom corresponding to the first or second atom;

[0092] c. The chiral feature set consists of multiple chiral attribute features; each chiral attribute feature is the current node state vector h 0,i a feature encoding vector of a first or second chiral property in a first or second atomic chiral property set corresponding to the corresponding first or second atom;

[0093] d. The associated chemical bond feature set consists of one or more associated chemical bond features; the associated chemical bond features include chemical bond type features and chemical bond direction features; each associated chemical bond feature is related to the current node state vector h 0,i a first or second chemical bond corresponding to the corresponding first or second atom; a chemical bond type feature is a one-hot encoding of the first or second chemical bond type of the current corresponding first or second chemical bond; a chemical bond direction feature is a three-dimensional displacement vector from the current corresponding first or second atom to another first or second atom indicated in the first or second bonding atom group of the current corresponding first or second chemical bond;

[0094] e. The cross-fragment distance feature set consists of multiple cross-fragment distance features; if the current node state vector h 0,i Corresponding to a first atom, each cross-fragment distance feature is the square value of the straight-line distance between the current corresponding first atom and a second atom in the second molecular fragment; if the current node state vector h 0,i Corresponding to a second atom, each cross-molecule distance feature is the square value of the straight-line distance between the currently corresponding second atom and a first atom in the first molecular fragment.

[0095] 2) Graph Neural Encoding Network:

[0096] The graph neural encoding network of the binding site prediction model is composed of M layers of graph neural network (GNN) layers connected in sequence; wherein the total number of encoding layers M is a preset positive integer and the value is greater than 2.

[0097] The mth GNN layer is used to encode the state tensor H of the input of this layer. m-1 Perform state conversion processing to obtain the corresponding state encoding tensor H m , and when the current encoding layer index m is less than M, the state encoding tensor H mSend it to the m+1th GNN layer, and when the current encoding layer index m is equal to M, the state encoding tensor H m＝M Send to the MLP network;

[0098] Here, 1≤ encoding layer index m≤M; the state encoding tensor H m Including N 1 +N 2 The node state vector h m,i , node state vector h m,i With node v i One to one correspondence.

[0099] Node state vector h m,i The reasoning process is:

[0100]

[0101] Among them, feature d i,j The setting rule is: if the node v i 、v j The corresponding two atoms belong to the same molecular fragment, then the corresponding feature d i,j Fixed to 0; if node v i 、v j The corresponding two atoms belong to two molecular fragments, so the corresponding feature d i,j is fixed to the corresponding cross-fragment distance feature. m is the state transition function of the mth GNN layer, θ m is the mth state transition function f m The corresponding model parameters of the m-th GNN layer.

[0102] 3) MLP network:

[0103] The MLP network of the binding site prediction model is used to encode the state tensor H according to the output of the Mth GNN layer M Perform combined probability prediction to obtain the corresponding combined probability prediction vector.

[0104] Here, the combined probability prediction vector of the embodiment of the present invention is composed of N 1 +N 2 The predicted probability of a node is p i Composition; node prediction probability p i With node v i One to one correspondence;

[0105] The reasoning process combining the probability prediction vector is: P = f MLP (H M θ MLP );

[0106] Among them, P is the combined probability prediction vector, fMLP is the network mapping function of the MLP network, θ MLP are the model parameters of the MLP network.

[0107] Step 2, constructing a model training data set and recording it as the corresponding first data set; and training the binding site prediction model based on the first data set;

[0108] Specifically comprising: step 21, constructing a model training data set and recording it as the corresponding first data set;

[0109] Wherein, the first data set includes multiple first data records; the first data record includes a first training molecular fragment, a second training molecular fragment and a first label vector; the first and second training molecular fragments are each a three-dimensional molecular fragment structure; the first label vector includes multiple first node labels; the total number of first node labels is the sum of the total number of atoms of the first and second training molecular fragments; the label value of the first node label is 1 or 0; in the first label vector, only two first node labels have a label value of 1, and the rest are 0, and the two atoms corresponding to the two first node labels with a label value of 1 are not in the same training molecular fragment;

[0110] The current step 21 specifically includes:

[0111] Step 211, collecting data on the three-dimensional molecular structures of various compound molecules through multiple types of public data channels to obtain corresponding multiple first molecular structures;

[0112] Among them, multiple types of public data channels include at least various public data sets, journals / magazines / scientific and technological literature / papers that publish molecular three-dimensional structures;

[0113] Step 212, taking each first molecular structure as the corresponding current molecular structure; and performing molecular fragment sampling on the current molecular structure to obtain a corresponding plurality of sampling fragments; and performing a round of traversal on all the sampling fragments of the current molecular structure; and in this round of traversal, taking the currently traversed sampling fragment as the corresponding current fragment; and extracting other sampling fragments in the current molecular structure that are connected to the current fragment in a single-atom connection manner to form a corresponding associated fragment set; and taking the current fragment as a corresponding first training molecular fragment, and taking any sampling fragment in the current associated fragment set as a corresponding second training molecular fragment, and forming a corresponding first fragment group by the first training molecular fragment corresponding to the current fragment and each second training molecular fragment; and performing deduplication processing on all the obtained first fragment groups at the end of this round of traversal;

[0114] Step 213, perform a round of traversal on all first fragment groups; and in this round of traversal, use the currently traversed first fragment group as the corresponding current fragment group; calculate the sum of the total number of atoms of the first and second training molecular fragments of the current fragment group to obtain the corresponding current atomic sum; and set a first label vector whose vector length matches the current atomic sum; and initialize the label values ​​of all first node labels of the current first label vector to 0; and after the vector initialization is completed, reset the label values ​​of the two first node labels corresponding to the two fragment connecting atoms of the first and second training molecular fragments of the current fragment group in the first label vector to 1; and form a corresponding first data record by the first training molecular fragment, the second training molecular fragment and the first label vector corresponding to the current fragment group; and at the end of this round of traversal, all the obtained first data records form a corresponding first data set;

[0115] Step 22, training a binding site prediction model based on the first data set;

[0116] Specifically comprising: step 221, based on a preset first segmentation ratio, dividing the first data set into two sub-data sets recorded as a corresponding first training set and a first evaluation set;

[0117] The first segmentation ratio is a preset ratio parameter, such as 8:2; the first training set and the first evaluation set are both composed of a plurality of first data records; the ratio of the total number of records in the first training set and the first evaluation set satisfies the first segmentation ratio;

[0118] Step 222, extracting the first first data record of the first training set as the corresponding current training record;

[0119] Step 223, inputting the first and second training molecular fragments of the current training record as the corresponding first and second molecular fragments into the binding site prediction model to perform binding site prediction processing and using the binding probability prediction vector output by the model as the corresponding first prediction vector;

[0120] Step 224, inputting the first prediction vector and the first label vector of the current training record into a preset first model loss function to calculate and obtain a corresponding first loss value;

[0121] Wherein, the first model loss function at least includes a binary cross entropy loss function;

[0122] Step 225, identifying whether the first loss value satisfies a preset first loss value range; if the first loss value satisfies the first loss value range, proceeding to step 226; if the first loss value does not satisfy the first loss value range, a round of modulation of the model parameters of the graph neural encoding network of the binding site prediction model and the MLP network is performed in a direction that minimizes the first model loss function based on a preset first model optimizer, and returning to step 223 at the end of this round of modulation;

[0123] Here, the first loss value range is a preset value range; the first model optimizer includes at least an SGD optimizer and an Adam optimizer;

[0124] Step 226, identifying whether the current training record is the last first data record of the first training set; if so, go to step 227; if not, extract the next first data record of the first training set as the new current training record, and return to step 223;

[0125] Step 227, perform a round of traversal on all first data records of the first evaluation set; and in this round of traversal, use the first data record currently traversed as the corresponding current evaluation record; and input the first and second training molecular fragments of the current evaluation record as the corresponding first and second molecular fragments into the binding site prediction model for binding site prediction processing and use the binding probability prediction vector output by the model as the corresponding second prediction vector; and form a corresponding prediction-label data pair by the second prediction vector and the first label vector of the current training record; and at the end of this round of traversal, calculate the accuracy, precision, recall and F1 score based on all the obtained prediction-label data pairs to obtain the corresponding first accuracy, first precision, first recall and first F1 score;

[0126] Step 228, identify the first accuracy, the first precision, the first recall rate and the first F1 score; if the first accuracy does not meet the preset first accuracy range, or the first accuracy does not meet the preset first accuracy range, or the first recall rate does not meet the preset first recall rate range, or the first F1 score does not meet the preset first F1 score range, return to step 222 to continue training; if the first accuracy meets the first accuracy range, and the first accuracy meets the first accuracy range, and the first recall rate meets the first recall rate range, and the first F1 score meets the first F1 score range, stop training and confirm that the model training is completed.

[0127] Here, the first accuracy range, the first precision range, the first recall range and the first F1 score range are four preset value ranges.

[0128] Step 3: After the model training is completed, two three-dimensional molecular fragment structures input by the user are received as corresponding fragment structures A and B; and the binding site prediction model is used to identify the binding site information of the fragment structures A and B and the identification information is fed back to the current user;

[0129] Specifically, it includes: step 31, after the model training is completed, receiving two three-dimensional molecular fragment structures input by the user as corresponding fragment structures A and B;

[0130] Step 32, using the binding site prediction model to identify the binding site information of the fragment structures A and B and feeding back the identification information to the current user;

[0131] Specifically comprising: step 321, inputting the fragment structures A and B as the corresponding first and second molecular fragments into the binding site prediction model for binding site prediction processing and using the binding probability prediction vector output by the model as the corresponding AB prediction vector;

[0132] Step 322: predict all nodes corresponding to all atoms of the fragment structure A in the AB prediction vector with the prediction probability p i Extract them to form the corresponding first probability set; and predict all the node prediction probabilities p corresponding to all atoms of the fragment structure B in the AB prediction vector i Extract them to form a corresponding second probability set;

[0133] Step 323: predict the probability p of the node with the largest probability value in the first probability set. i Recorded as the corresponding first maximum probability; and the predicted probability p of the node with the largest probability value in the second probability set i Recorded as the corresponding second maximum probability; and the atom identifier corresponding to the first maximum probability in the fragment structure A is used as the corresponding fragment A side binding atom identifier; and the atom identifier corresponding to the second maximum probability in the fragment structure B is used as the corresponding fragment B side binding atom identifier;

[0134] Step 324, the fragment A side combines the atom identifier and the corresponding first maximum probability to form the corresponding A fragment identification information; the fragment B side combines the atom identifier and the corresponding second maximum probability to form the corresponding B fragment identification information; and the A and B fragment identification information form the corresponding binding site identification information and feed it back to the current user.

[0135] Figure 3 The module structure diagram of a processing device for predicting the binding sites of molecular fragments provided in the second embodiment of the present invention is a terminal device or server that implements the aforementioned method embodiment, and can also be a device that enables the aforementioned terminal device or server to implement the aforementioned method embodiment. For example, the device can be a device or chip system of the aforementioned terminal device or server. Figure 3 As shown, the device includes: a model building module 201, a model training module 202 and a model application module 203.

[0136] The model building module 201 is used to build a binding site prediction model; the binding site prediction model is used to perform binding site prediction processing on the first and second molecular fragments input into the model and output the corresponding binding probability prediction vector.

[0137] The model training module 202 is used to construct a model training data set recorded as the corresponding first data set; and train the binding site prediction model based on the first data set.

[0138] The model application module 203 is used to receive two three-dimensional molecular fragment structures input by the user as corresponding fragment structures A and B after the model training is completed; and use the binding site prediction model to identify the binding site information of the fragment structures A and B and feed back the identification information to the current user.

[0139] An embodiment of the present invention provides a processing device for predicting the binding sites of molecular fragments, which can execute the method steps in the above method embodiment. Its implementation principle and technical effects are similar and will not be repeated here.

[0140] It should be noted that it should be understood that the division of the various modules of the above device is only a division of logical functions. In actual implementation, they can be fully or partially integrated into one physical entity, or they can be physically separated. And these modules can all be implemented in the form of software called by processing elements; they can also be all implemented in the form of hardware; some modules can also be implemented in the form of software called by processing elements, and some modules can be implemented in the form of hardware. For example, the model building module can be a separately established processing element, or it can be integrated in a chip of the above device. In addition, it can also be stored in the memory of the above device in the form of program code, and called and executed by a processing element of the above device. The function of the above-mentioned module is determined. The implementation of other modules is similar. In addition, these modules can be fully or partially integrated together, or they can be implemented independently. The processing element described here can be an integrated circuit with signal processing capabilities. In the implementation process, each step of the above method or each module above can be completed by an integrated logic circuit of hardware in the processor element or instructions in the form of software.

[0141] For example, the above modules may be one or more integrated circuits configured to implement the above methods, such as one or more application specific integrated circuits (ASIC), or one or more digital signal processors (DSP), or one or more field programmable gate arrays (FPGA). For another example, when a module above is implemented in the form of a processing element scheduling program code, the processing element may be a general-purpose processor, such as a central processing unit (CPU) or other processor that can call program code. For another example, these modules may be integrated together and implemented in the form of a system-on-a-chip (SOC).

[0142] In the above embodiments, all or part of the embodiments may be implemented by software, hardware, firmware or any combination thereof. When implemented by software, all or part of the embodiments may be implemented in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, all or part of the processes or functions described in the above method embodiments are generated. The above computer may be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices. The above-mentioned computer instructions can be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the above-mentioned computer instructions can be transmitted from one website, computer, server or data center to another website, computer, server or data center through wired (such as coaxial cable, optical fiber, digital subscriber line (DSL)) or wireless (such as infrared, wireless, Bluetooth, microwave, etc.) methods. The above-mentioned computer-readable storage medium can be any available medium that can be accessed by a computer or a data storage device such as a server or data center that includes one or more available media integrated. The above-mentioned available medium can be a magnetic medium (such as a floppy disk, a hard disk, a tape), an optical medium (such as a DVD), or a semiconductor medium (such as a solid state disk (SSD)), etc.

[0143] Figure 4 This is a schematic diagram of the structure of an electronic device provided in Embodiment 3 of the present invention. The electronic device may be a terminal device or a server for implementing the method of the aforementioned embodiment, or may be a terminal device or a server for implementing the method of the aforementioned embodiment connected to the aforementioned terminal device or server. Figure 4As shown, the electronic device may include: a processor 301 (such as a CPU), a memory 302, and a transceiver 303; the transceiver 303 is coupled to the processor 301, and the processor 301 controls the transceiver 303. Various instructions may be stored in the memory 302 to complete various processing functions and implement the processing steps described in the aforementioned embodiment method. Preferably, the electronic device involved in the embodiment of the present invention also includes: a power supply 304, a system bus 305 and a communication port 306. The system bus 305 is used to realize the communication connection between components. The above-mentioned communication port 306 is used for connecting and communicating between the electronic device and other peripherals.

[0144] exist Figure 4 The system bus 305 mentioned in the figure can be a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus, etc. The system bus can be divided into an address bus, a data bus, a control bus, etc. For ease of representation, only one thick line is used in the figure, but it does not mean that there is only one bus or one type of bus. The communication interface is used to realize the communication between the database access device and other devices (such as clients, read-write libraries, and read-only libraries). The memory may include random access memory (RAM), and may also include non-volatile memory (Non-Volatile Memory), such as at least one disk storage.

[0145] The above-mentioned processor can be a general-purpose processor, including a central processing unit CPU, a network processor (Network Processor, NP), a graphics processing unit (Graphics Processing Unit, GPU), etc.; it can also be a digital signal processor DSP, an application-specific integrated circuit ASIC, a field programmable gate array FPGA or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components.

[0146] It should be noted that an embodiment of the present invention further provides a computer-readable storage medium, in which instructions are stored. When the computer-readable storage medium is run on a computer, the computer executes the method and processing process provided in the above embodiments.

[0147] The embodiment of the present invention provides a processing method, device, electronic device and computer-readable storage medium for predicting the binding site of a molecular fragment. As can be seen from the above content, the embodiment of the present invention constructs a binding site prediction model for performing binding site prediction processing on the first and second molecular fragments input by the model and outputting the corresponding binding probability prediction vector; and constructs a first data set through big data collection to train the binding site prediction model; after the model training is completed, the binding site prediction model is used to identify the binding site information of any two three-dimensional molecular fragment structures input by the user and the identification information is fed back to the current user. The end-to-end binding site prediction model provided by the embodiment of the present invention improves the prediction efficiency on the one hand, and on the other hand, it can also improve the generalization of the model and enhance the ability to discover unknown connection methods through big data training.

[0148] The steps of the method or algorithm described in conjunction with the embodiments disclosed herein may be implemented using hardware, a software module executed by a processor, or a combination of the two. The software module may be placed in a random access memory (RAM), a memory, a read-only memory (ROM), an electrically programmable ROM, an electrically erasable programmable ROM, a register, a hard disk, a removable disk, a CD-ROM, or any other form of storage medium known in the art.

[0149] The specific implementation methods described above further illustrate the objectives, technical solutions and beneficial effects of the present invention in detail. It should be understood that the above description is only a specific implementation method of the present invention and is not intended to limit the scope of protection of the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the scope of protection of the present invention.

Claims

1. A method for predicting binding sites of molecular fragments, characterized in that: The method comprises: Constructing a binding site prediction model; the binding site prediction model is used to perform binding site prediction processing on the first and second molecular fragments input into the model and output a corresponding binding probability prediction vector; Constructing a model training data set is recorded as the corresponding first data set; and training the binding site prediction model based on the first data set; After the model training is completed, two three-dimensional molecular fragment structures input by the user are received as corresponding fragment structures A and B; and the binding site prediction model is used to identify the binding site information of the fragment structures A and B and the identification information is fed back to the current user.

2. The method for predicting the binding sites of molecular fragments according to claim 1, characterized in that: The first and second molecular fragments are each a three-dimensional molecular fragment structure; The first molecular fragment includes a first set of atoms and a first set of chemical bonds; The first atom set includes multiple first atoms; the atomic properties of the first atoms include at least a first atom identifier, a first atom type, a first atom coordinates, and a first atom chiral property set; the first atom identifier is a unique identifier of the current first atom; the first atom type is a chemical element type of the current first atom; the first atom coordinates are three-dimensional space coordinates of the current first atom; the first atom chiral property set consists of multiple first chiral properties; each of the first chiral properties consists of a corresponding property type and a property value; if the first atom is a chiral center atom, all property values ​​in the corresponding first atom chiral property set are not empty; If the first atom is not a chiral center atom, all attribute values ​​in the corresponding first atom chiral attribute set are empty; The first chemical bond set includes multiple first chemical bonds; the chemical bond attributes of the first chemical bond include at least a first chemical bond identifier, a first chemical bond type, and a first bonding atom group; the first chemical bond identifier is a unique identifier of the current first chemical bond; the first chemical bond type includes multiple chemical bond types; the first bonding atom group consists of the first atom identifiers of the two first atoms currently connected by the first chemical bond; The second molecular fragment includes a second set of atoms and a second set of chemical bonds; The second atom set includes multiple second atoms; the atomic properties of the second atoms include at least a second atom identifier, a second atom type, a second atom coordinates, and a second atom chiral property set; the second atom identifier is a unique identifier of the current second atom; the second atom type is a chemical element type of the current second atom; the second atom coordinates are the three-dimensional space coordinates of the current second atom; the second atom chiral property set consists of multiple second chiral properties; each second chiral property consists of a corresponding property type and a property value; if the second atom is a chiral center atom, all property values ​​in the corresponding second atom chiral property set are not empty; If the second atom is not a chiral center atom, all attribute values ​​in the corresponding second atom chiral attribute set are empty; The second chemical bond set includes multiple second chemical bonds; the chemical bond properties of the second chemical bond include at least a second chemical bond identifier, a second chemical bond type, and a second bonding atom group; the second chemical bond identifier is the unique identifier of the current second chemical bond; the second chemical bond type includes multiple chemical bond types; the second bonding atom group consists of the second atom identifiers of the two second atoms currently connected by the second chemical bond.

3. The method for predicting the binding sites of molecular fragments according to claim 2, characterized in that: The first and second model input ends of the binding site prediction model are used to receive the first and second molecular fragments input by the model respectively, and the model output end is used to output the corresponding binding probability prediction vector; The binding site prediction model includes an encoding initialization module, a graph neural encoding network and an MLP network; The first and second input terminals of the encoding initialization module are connected to the first and second model input terminals respectively, and the output terminal is connected to the input terminal of the graph neural encoding network; the output terminal of the graph neural encoding network is connected to the input terminal of the MLP network; the output terminal of the MLP network is connected to the output terminal of the model; The encoding initialization module is used to construct a molecular graph according to the first and second molecular fragments input by the model to obtain a corresponding molecular graph G; and to perform state encoding initialization processing according to the molecular graph G to obtain a corresponding state encoding tensor H0 and send it to the graph neural encoding network; The molecular graph G includes a node set V and an edge set E; The node set V consists of N1+N2 nodes v i The edge set E is composed of multiple edges e i,j composition; 1≤node index i≤N1+N2, 1≤node index j≤N1+N2, j≠i, N1 and N2 are the total number of atoms of the first and second molecular fragments respectively; the node v i corresponds to one of the first atoms or one of the second atoms; the edge e i,j corresponding to one of said first chemical bonds or one of said chemical bonds; The state encoding tensor H0 includes N1+N2 node state vectors h 0,i ; The node state vector h 0,i With the node v i One-to-one correspondence; the node state vector h 0,i It consists of atomic type features, atomic coordinate features, chirality feature set, associated chemical bond feature set, and cross-fragment distance feature set; The atomic type feature is the current node state vector h 0,i a one-hot encoding of the first or second atom type corresponding to the corresponding first or second atom; The atomic coordinate feature is the current node state vector h 0,i the atomic coordinates of the first or second atom corresponding to the first or second atom; The chiral feature set is composed of multiple chiral attribute features; each chiral attribute feature is the current node state vector h 0,i a feature encoding vector of a first or second chiral property in the first or second atomic chiral property set corresponding to the first or second atom; The associated chemical bond feature set is composed of one or more associated chemical bond features; the associated chemical bond features include chemical bond type features and chemical bond direction features; each of the associated chemical bond features is related to the current node state vector h 0,i a first or second chemical bond corresponding to the corresponding first or second atom; the chemical bond type feature is a one-hot encoding of the first or second chemical bond type of the current corresponding first or second chemical bond; The chemical bond direction feature is a three-dimensional displacement vector starting from the first or second atom currently corresponding to the first or second atom to another first or second atom indicated in the first or second bonding atom group of the first or second chemical bond currently corresponding to the first or second chemical bond; The cross-segment distance feature set is composed of multiple cross-segment distance features; if the current node state vector h 0,i Corresponding to one of the first atoms, each of the cross-fragment distance features is the square value of the straight-line distance between the currently corresponding first atom and one of the second atoms in the second molecular fragment; if the current node state vector h 0,i Corresponding to one of the second atoms, each of the cross-molecule distance features is the square value of the straight-line distance between the currently corresponding second atom and one of the first atoms in the first molecular fragment; The graph neural coding network is composed of M layers of GNN layers connected in sequence, where the total number of coding layers M is a preset positive integer and the value is greater than 2; the GNN layer in the mth layer is used to encode the state input tensor H of this layer m-1 Perform state conversion processing to obtain the corresponding state encoding tensor H m , and when the current coding layer index m is less than M, the state coding tensor H m Send to the m+1th GNN layer, and when the current encoding layer index m is equal to M, the state encoding tensor H m＝M Send to the MLP network; 1≤ coding layer index m≤M; the state coding tensor H m Includes N1+N2 node state vectors h m,i , the node state vector h m,i With the node v i One to one correspondence; Feature d i,j The setting rule is: if the node v i 、v j The corresponding two atoms belong to the same molecular fragment, then the corresponding feature d i,j Fixed to 0; if node v i 、v j The corresponding two atoms belong to two molecular fragments, so the corresponding feature d i,j fixed to the corresponding cross-fragment distance feature; f m is the state transition function of the GNN layer at the mth layer, θ m is the mth state transition function f m The model parameters of the corresponding m-th GNN layer; The MLP network is used to encode the state tensor H output by the GNN layer of the Mth layer M Perform combined probability prediction to obtain the corresponding combined probability prediction vector; the combined probability prediction vector is composed of N1+N2 node prediction probabilities p i Composition; the node prediction probability p i With the node v i One to one correspondence; P=f MLP (H M ;θ MLP ); P is the combined probability prediction vector, f MLP is the network mapping function of the MLP network, θ MLP are the model parameters of the MLP network.

4. The method for predicting the binding sites of molecular fragments according to claim 3, The first data set includes a plurality of first data records; the first data records include a first training molecule fragment, a second training molecule fragment and a first label vector; The first and second training molecular fragments are each a three-dimensional molecular fragment structure; The first label vector includes multiple first node labels; the total number of the first node labels is the sum of the total number of atoms in the first and second training molecular fragments; the label value of the first node label is 1 or 0; in the first label vector, only two of the first node labels have a label value of 1, and the rest are 0, and the two atoms corresponding to the two first node labels with the label value of 1 are not in the same training molecular fragment.

5. According to the processing method for predicting the binding sites of molecular fragments according to claim 4, the model building training data set is recorded as the corresponding first data set, specifically comprising: Step 51, collecting data on the three-dimensional molecular structures of various compound molecules through multiple types of public data channels to obtain corresponding multiple first molecular structures; in, The multiple types of public data channels include at least various public data sets, journals / magazines / scientific and technological documents / papers that publish molecular three-dimensional structures; Step 52, taking each of the first molecular structures as the corresponding current molecular structure; and performing molecular fragment sampling on the current molecular structure to obtain a corresponding plurality of sampling fragments; and performing a round of traversal on all the sampling fragments of the current molecular structure; and in this round of traversal, taking the currently traversed sampling fragment as the corresponding current fragment; and extracting the other sampling fragments in the current molecular structure that are connected to the current fragment in a single-atom connection manner to form a corresponding associated fragment set; and taking the current fragment as a corresponding first training molecular fragment, and taking any one of the sampling fragments in the current associated fragment set as a corresponding second training molecular fragment, and forming a corresponding first fragment group by the first training molecular fragment corresponding to the current fragment and each of the second training molecular fragments; and performing deduplication processing on all the obtained first fragment groups at the end of this round of traversal; Step 53, performing a round of traversal on all the first fragment groups; and in this round of traversal, taking the first fragment group currently traversed as the corresponding current fragment group; Calculating the sum of the total number of atoms of the first and second training molecular fragments of the current fragment group to obtain the corresponding current atomic sum; and setting a first label vector whose vector length matches the current atom sum; and initializing the label values ​​of all the first node labels of the current first label vector to 0; After the vector initialization is completed, the label values ​​of the two first node labels corresponding to the two segment connecting atoms of the first and second training molecular segments of the current segment group in the first label vector are reset to 1; and the first training molecular segment, the second training molecular segment and the first label vector corresponding to the current segment group form a corresponding first data record; And at the end of this round of traversal, all the first data records obtained form the corresponding first data set.

6. The method for predicting binding sites of molecular fragments according to claim 4, wherein the step of training the binding site prediction model based on the first data set comprises: Step 61, based on a preset first segmentation ratio, the first data set is divided into two sub-data sets which are recorded as a corresponding first training set and a first evaluation set; in, The first training set and the first evaluation set are both composed of a plurality of the first data records; the ratio of the total number of records in the first training set and the first evaluation set meets the first segmentation ratio; Step 62, extracting the first first data record of the first training set as the corresponding current training record; Step 63, inputting the first and second training molecular fragments of the current training record as the corresponding first and second molecular fragments into the binding site prediction model to perform binding site prediction processing and using the binding probability prediction vector output by the model as the corresponding first prediction vector; Step 64, inputting the first prediction vector and the first label vector of the current training record into a preset first model loss function to calculate and obtain a corresponding first loss value; Wherein, the first model loss function at least includes a binary cross entropy loss function; Step 65, identifying whether the first loss value satisfies a preset first loss value range; if the first loss value satisfies the first loss value range, proceeding to step 66; if the first loss value does not satisfy the first loss value range, based on a preset first model optimizer, performing a round of modulation on the model parameters of the graph neural encoding network of the binding site prediction model and the MLP network in a direction that minimizes the first model loss function, and returning to step 63 at the end of this round of modulation; Step 66, identifying whether the current training record is the last first data record of the first training set; if so, going to step 67; if not, extracting the next first data record of the first training set as the new current training record, and returning to step 63; Step 67, perform a round of traversal on all the first data records of the first evaluation set; and in this round of traversal, use the first data record currently traversed as the corresponding current evaluation record; and input the first and second training molecular fragments of the current evaluation record as the corresponding first and second molecular fragments into the binding site prediction model for binding site prediction processing and use the binding probability prediction vector output by the model as the corresponding second prediction vector; and form a corresponding prediction-label data pair by the second prediction vector and the first label vector of the current training record; and at the end of this round of traversal, calculate the accuracy, precision, recall and F1 score based on all the obtained prediction-label data pairs to obtain the corresponding first accuracy, first precision, first recall and first F1 score; Step 68, identifying the first accuracy, the first precision, the first recall and the first F1 score; if the first accuracy does not meet the preset first accuracy range, or the first accuracy does not meet the preset first accuracy range, or the first recall does not meet the preset first recall range, or the first F1 score does not meet the preset first F1 score range, return to step 62 to continue training; if the first accuracy meets the first accuracy range, and the first accuracy meets the first accuracy range, and the first recall meets the first recall range, and the first F1 score meets the first F1 score range, stop training and confirm that the model training is completed.

7. The method for predicting the binding sites of molecular fragments according to claim 3, wherein the binding site prediction model is used to identify the binding site information of the fragment structures A and B and the identification information is fed back to the current user, specifically comprising: Step 71, inputting the fragment structures A and B as the corresponding first and second molecular fragments into the binding site prediction model for binding site prediction processing and using the binding probability prediction vector output by the model as the corresponding AB prediction vector; Step 72: calculate the prediction probabilities p of all nodes corresponding to all atoms in the fragment structure A in the AB prediction vector. i Extract them to form a corresponding first probability set; and extract all the node prediction probabilities p corresponding to all atoms in the fragment structure B in the AB prediction vector i Extract them to form a corresponding second probability set; Step 73: predict the probability p of the node with the largest probability value in the first probability set. i Recorded as the corresponding first maximum probability; and the predicted probability p of the node with the largest probability value in the second probability set i Recorded as the corresponding second maximum probability; and the atom identifier corresponding to the first maximum probability in the fragment structure A is used as the corresponding fragment A side binding atom identifier; and the atom identifier corresponding to the second maximum probability in the fragment structure B is used as the corresponding fragment B side binding atom identifier; Step 74, the fragment A side is combined with the atom identifier and the corresponding first maximum probability to form the corresponding A fragment identification information; the fragment B side is combined with the atom identifier and the corresponding second maximum probability to form the corresponding B fragment identification information; and the A and B fragment identification information are combined to form the corresponding binding site identification information to feedback to the current user.

8. A device for executing the method for predicting binding sites of molecular fragments according to any one of claims 1 to 7, characterized in that: The device comprises: a model building module, a model training module and a model application module; The model building module is used to build a binding site prediction model; the binding site prediction model is used to perform binding site prediction processing on the first and second molecular fragments input by the model and output the corresponding binding probability prediction vector; The model training module is used to construct a model training data set recorded as the corresponding first data set; and train the binding site prediction model based on the first data set; The model application module is used to receive two three-dimensional molecular fragment structures input by the user as corresponding fragment structures A and B after the model training is completed; and use the binding site prediction model to identify the binding site information of the fragment structures A and B and feed back the identification information to the current user.

9. An electronic device, characterized in that: include: memory, processors, and transceivers; The processor is used to couple with the memory, read and execute instructions in the memory, so as to implement the method according to any one of claims 1 to 7; The transceiver is coupled to the processor, and the processor controls the transceiver to send and receive messages.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer instructions, and when the computer instructions are executed by a computer, the computer is enabled to execute the method according to any one of claims 1 to 7.

Images