Polymer graph neural network and its implementation method

Abstract

The present invention provides a computer-implemented method for predicting characteristic information of a polymer from its chemical structure. The present invention provides a method for graphically representing the chemical structure of a polymer, and a method and system for calculating characteristic information of the polymer from graph information of the polymer by machine learning the chemical structure of the polymer based on information defining the mutual connection relationships between each atom constituting the repeating unit of the polymer and the connection nodes to which the repeated repeating units are connected.

Description

Technical Field

[0001] The present invention relates to a method for representing the structure of a polymer in a manner recognizable by a computer device and a system therefor.

Background Art

[0002] In order to input the structure of a compound into a computer device and perform predetermined processing, various methods for representing the compound structure in a manner recognizable by the computer device have been proposed. Typically, there are methods such as representing the structure of a compound as a character string of SMILES or representing the character string converted to SMILES by descriptors.

[0003] However, for polymers that are not monomers, it is difficult to represent them using the SMILES method, so BigSMILES and hierarchical descriptors have been proposed.

[0004] However, such conventional technologies have problems that as the molecule becomes larger, the representation method becomes increasingly complex and only represents the polymer fragmentarily, there is no technology capable of processing molecules based on such representation, and it is impossible to properly represent the characteristics of a polymer in which the repeating unit is infinitely repeated.

[0005] The related conventional technologies are as follows.

Prior Art Documents

Patent Documents

[0006]

Patent Document 1

Patent Document 2

Summary of the Invention

Problems to be Solved by the Invention

[0007] The present invention aims to solve the above-mentioned problems by providing a data structure that represents polymeric substances using graphic information, and further by providing a method and system for predicting predetermined properties of polymers using a data structure that represents the graphic information of polymers. [Means for solving the problem]

[0008] To solve the problems of the conventional technology described above, the present invention provides a method for processing data of a polymer chemical structure, comprising: a polymer node connection variable setting step of setting the mutual connection relationships between nodes representing each atom constituting a selected repeating unit of the polymer and connection nodes connected to connection points, which are locations where the repeating unit is repeatedly connected, as polymer node connection variables; a polymer graph node connection information assignment step of assigning attribute values ​​of the mutual connection relationships between the nodes and connection nodes to the set polymer node connection variables; and a polymer graph node connection information assignment step of assigning attribute values ​​of the mutual connection relationships between the nodes and connection nodes to the set polymer node connection variables.

[0009] The data processing method for polymer chemical structures of the present invention may further include: a polymer node attribute variable setting step of setting attribute information of nodes corresponding to constituent atoms of a repeating unit forming a selected polymer and information of connected nodes among the nodes that are connected to connection points, which are locations where the repeating unit is repeatedly connected, as polymer node attribute variables; a polymer graph node attribute information assignment step of assigning attribute values ​​of the nodes and connected nodes to the set polymer node attribute variables; a polymer node attribute variable setting step of setting attribute information of nodes corresponding to each atom constituting a repeating unit forming a selected polymer and information of connected nodes among the nodes that are connected to connection points, which are locations where the repeating unit is repeatedly connected, as polymer node attribute variables; a polymer graph node attribute information assignment step of assigning attribute values ​​of the nodes and connected nodes to the set polymer node attribute variables; a polymer edge attribute variable setting step of setting information of edges that connect the nodes corresponding to each atom constituting a repeating unit forming a selected polymer to each other and connecting edges that connect at least one of the nodes to the connecting nodes, as polymer edge attribute variables; and a polymer graph edge attribute information assignment step of assigning attribute values ​​of the edges and connected edges to the set polymer edge attribute variables.

[0010] Furthermore, the present invention relates to a method for generating a computer-implemented model that graphically describes the chemical structure of a selected polymer and analyzes predetermined properties of the polymer, comprising: a basic data acquisition step consisting of known values ​​of chemical structure information and predetermined property information of a large number of learning polymers; a data preprocessing step of converting the chemical structure information of the learning polymer from the basic data into polymer graph information; a polymer property information prediction artificial neural network configuration step of configuring a polymer property information prediction artificial neural network to receive polymer graph information as input and output predetermined property information prediction values ​​of the polymer; a learning data input step of inputting the polymer graph information and predetermined property information of the learning polymer into the polymer property information prediction artificial neural network; and based on the comparison result between the predetermined property information prediction values ​​of the learning polymer output by the polymer property information prediction artificial neural network and the known values ​​of the predetermined property information of the learning polymer, the parameters of the polymer property information prediction artificial neural network are... The present invention provides a method for generating a polymer property analysis model, which includes a learning step for an artificial neural network that predicts polymer property information and updates a module, wherein the polymer graph information includes at least one of the following: polymer graph node connection information, which is information representing the connection relationships between nodes corresponding to each atom constituting the repeating units that form the polymer and connection nodes that are connected to connection points, which are locations where the repeating units are repeatedly connected; polymer node attribute information, which is information representing the attribute information of the nodes corresponding to each atom constituting the repeating units that form the polymer and the attributes of connection nodes that are connected to connection points, which are locations where the repeating units are repeatedly connected; and polymer edge attribute information, which is information representing the attributes of the edges that connect the nodes corresponding to each atom constituting the repeating units that form the polymer and connection edges that connect at least one of the nodes to the connection nodes.

[0011] Furthermore, the present invention is a computer implementation method for graphically describing the chemical structure of a selected polymer and analyzing predetermined properties of the polymer, comprising: a polymer property information calculation artificial neural network configuration step which generates an artificial neural network that is machine-trained to predict predetermined properties of the polymer based at least partially on chemical structure data associated with the selected polymer; a polymer graph information acquisition step which acquires polymer graph information that graphically describes the chemical structure of the selected polymer; a polymer graph input step which provides the acquired polymer graph information as input to the machine-trained graph neural network; and a step which receives prediction data describing the predetermined properties of the selected polymer as output to the machine-trained graph neural network. Polymer graph information that describes the chemical structure of the polymer using graph information is characterized by including at least one of the following: polymer graph node connection information, which is information that represents the connection relationships between nodes corresponding to each atom constituting the repeating unit that forms the polymer and connection nodes that are connected to connection points, which are locations where the repeating unit is repeatedly connected among the nodes; polymer node attribute information, which is information that represents the attribute of the nodes corresponding to each atom constituting the repeating unit that forms the polymer and the attribute of the connection nodes that are connected to connection points, which are locations where the repeating unit is repeatedly connected among the nodes; and polymer edge attribute information, which is information that represents the attribute of the edges that connect the nodes corresponding to each atom constituting the repeating unit that forms the polymer and the connection edges that connect at least one of the nodes to the connection nodes.

[0012] In this case, the step of providing the acquired polymer graph information as input to the machine-learned graph neural network includes a polymer adjacency matrix construction step of constructing an adjacency matrix representing the interconnection relationships between two or more nodes representing each atom constituting the single molecule, and a polymer adjacency matrix input step of inputting the constructed graph matrix as the graph neural network, wherein the polymer adjacency matrix may further include information on the interconnection relationships between the connected nodes. [Effects of the Invention]

[0013] According to the present invention, by providing a data structure that allows polymers to be represented by computer-usable graphical information, it is possible to realize a method and system for predicting the properties of polymer materials by machine learning the relationship between the molecular structure and property information of polymer materials using a graph neural network (GNN) or a message-passing neural network (MPNN). Furthermore, it is possible to provide a method and system for predicting polymer property information with improved accuracy compared to conventional techniques.

[0014] The drawings accompanying this specification illustrate preferred embodiments of the present invention and are intended to further illustrate the technical idea of ​​the invention along with the content of the invention; therefore, the present invention shall not be construed as being limited only to what is shown in the drawings. [Brief explanation of the drawing]

[0015] [Figure 1] (a) and (b) are diagrams showing graphic representation methods of monomers and polymers in the conventional technology. [Figure 2] (a) and (b) are diagrams showing graphic representations of polymers according to the present invention. [Figure 3](a) and (b) are exemplary diagrams for explaining the graphic representation of the polymer according to the present invention. [Figure 4] (a) and (b) are diagrams showing the progress mode of learning based on message passing according to the graphic representation of the polymer according to the present invention. [Figure 5] (a) and (b) are diagrams showing procedures for realizing an artificial neural network that calculates characteristic information of a polymer using the graphic representation of the polymer according to the present invention. [Figure 6] It is a diagram showing a polymer characteristic information prediction system according to the present invention. [Figure 7a] It is a diagram showing examples of conventional techniques and polymer graph informationization according to the present invention. [Figure 7b] It is a diagram showing examples of conventional techniques and polymer graph informationization according to the present invention. [Figure 8a] It is a diagram showing other examples of conventional techniques and polymer graph informationization according to the present invention. [Figure 8b] It is a diagram showing other examples of conventional techniques and polymer graph informationization according to the present invention.

Mode for Carrying Out the Invention

[0016] 1. Graph Representation Method of Polymer According to the Present Invention

[0017] First, a method for graphically representing a polymer according to the present invention will be described based on FIGS. 1 and 2.

[0018] (a) and (b) of FIG. 1 are diagrams showing different polymers and the structures of monomers forming each polymer. However, when trying to process molecular structure data using an artificial neural network, especially when trying to represent the molecular structure by a graph for application to, for example, a GNN, there has been no method for effectively representing the chemical structure of a polymer by a graph.

[0019] Although the monomers forming the polymers shown in Figures 1(a) and (b) are different from each other, they are identical except for a small portion of the monomer ends. Therefore, their monomer graphs appear very similar, and it was inaccurate to simply represent the polymer graph as a monomer graph and the polymer graph as a repetition of the monomer graph.

[0020] Therefore, in this invention, we propose a novel graph representation method for polymers as shown in Figure 2. The graph information representation method for polymers according to the present invention will be described below based on Figure 2.

[0021] First, in the polymer graph representation method of the present invention, monomers constituting the polymer and repeating units that repeatedly constitute the polymer are derived. Figure 1 shows an example of a conventional polymer representation and a representation of the monomers constituting the polymer, and Figure 2 shows the repeating units constituting the polymer in Figure 1. In the repeating units in Figure 2, for the polymer representation method of the present invention, each atom is represented by a node 10, and the bonds between the atoms are represented by edges 20. Next, in one of the features of the present invention, when the repeating units repeat to form a polymer, the points where the repeating units are repeatedly connected are represented by attachment points 30, and the nodes to which the attachment points are connected are represented by "attachment nodes". Furthermore, the attachment points 30 virtually represent the attachment nodes of adjacent repeating units that are repeatedly connected, and the connections between the attachment points and the attachment nodes are represented by attachment edges 40.

[0022] According to this graph representation method for polymers of the present invention, when learning an artificial neural network model based on the chemical structure of a polymer, particularly when applying a message-passing-based MPNN (message-passing neural network) or GNN (graph neural network) artificial neural network model, it becomes possible to learn by passing information from the opposite node to which the monomer is connected, even with only minimal additional information on top of the monomer structure information. This enables learning that reflects the unit repeatability characteristics of the polymer.

[0023] Figure 4 shows an example of representing the structural information of monomers and polymers in the form of a binary tree. In addition to the monomer binary tree in Figure 4(a), Figure 4(b) shows that by adding a connection tree, the information of the opposite node can be included.

[0024] 2. Converting the graphical representation of the polymer according to the present invention into data that can be used on a computer.

[0025] This invention converts the chemical structure of a polymer into a data structure usable for computer processing, i.e., "graph data," by using a graph representation method that graphically represents the molecular or chemical structure of the polymer described above. In this invention, this is referred to as "polymer graph data."

[0026] The polymer graph information according to the present invention, which describes the chemical structure of a predetermined or selected polymer using graphic information, includes at least one of the following pieces of information: node data, which is data associated with nodes 10 and 10, representing two or more nodes that represent each atom constituting a repeating unit of monomers forming the polymer; edge data, which is data associated with one or more edges 20 that represent the bonds between each of the nodes; attaching node data, which is data associated with at least one attachment node, which is a location where the repeating units forming the polymer are repeatedly connected; and attaching edge data, which is data associated with an attachment edge 40, which is a connection connecting the attachment point 30 and the attachment node.

[0027] The difference between monomer graph information and polymer graph information of the present invention lies in the fact that, in the representation of graph information of repeating units including the monomer graph information, the polymer graph information of the present invention represents the node 10 connected to the connection point 30 and its edge information using connection nodes and connection edges.

[0028] 2.1. Adjacency matrix and feature matrix

[0029] When converting the graph structure of a monomer into data usable by a computer, a wide variety of data representation methods are possible, but typically, the edge information and node information can be represented by the adjacency matrix and characteristic matrix, respectively. Edge information is information related to the bonds between atoms, and node information is information related to each atom.

[0030] According to the polymer representation method of the present invention, in addition to the conventional monomer graph representation method, information on the nodes connected to the connection points 30 and the connection edges 40 can be added to convert the polymer graph into data that can be recognized by a computer.

[0031] (1) Representation of the adjacency matrix of a monomer graph

[0032] To simplify the explanation, if we take a simple structure as shown in Figure 3 as an example, the adjacency matrix A of a monomer repeating unit composed of nodes 1, 2, 3, and 4 can be expressed as follows.

[0033]

number

[0034] The adjacency matrix A has a number of rows and columns corresponding to the number of nodes, and each component A- i,j This represents information indicating whether the i-th node (i=1, ..., 4) and the j-th node (j=1, ..., 4) are connected. The value of each matrix element indicates the connection information with other nodes. For example, node 1 is connected only to node 2 and not to nodes 1, 3, and 4, so the adjacency matrix A 1,j (j=1, …,4) can be represented as [0 1 0 0].

[0035] (2) Representation of the adjacency matrix of the polymer graph according to the present invention

[0036] According to the polymer graph information representation method of the present invention, the polymer adjacence matrix PA, which is a representation of the adjacency matrix of the polymer graph illustrated in Figure 3, can be represented as follows.

[0037]

number

[0038] As shown in Figure 3, the polymer adjacency matrix PA has two additional connection points 5 and 6, which represent nodes 4 and 1 of the adjacent monomers, respectively. Therefore, nodes 1 and 4 are represented as being connected to nodes 4 and 1, respectively. In other words, in the monomer, there is no node to which nodes 1 and 4 are connected, so the matrix value representing the connection relationship between node 1 and node 4 is A. 1,4 =0, A 4,1 Although it was =0, in the polymer representation method of the present invention, nodes 1 and 4 are connected to nodes 4 and 1 of adjacent monomers, respectively, so the PA of the polymer adjacency matrix PA 1,4 =1, PA 4,1 The value =1 indicates that it contains repeating connection information for the polymer. In other words, nodes 1 and 4, which were not connected in the monomer, are connected to each other in the polymer, and therefore, in the polymer adjacency matrix that displays the connection edge information, they are represented as being connected to each other.

[0039] However, in this case, since nodes 1 and 4 are not connected to each other within the monomer, to indicate that the connection is not within the monomer but with a node of an adjacent repeating unit, the node connection relationship can be represented by a negative number and the polymer adjacency matrix can be represented as shown below, or a "connected node" characteristic that connects to the connection point can be assigned to the node's characteristics in the node characteristics matrix described later, or an adjacent repeating unit connection attribute can be assigned to the edge characteristics matrix to distinguish it.

[0040]

number

[0041] To reiterate, the graph information that graphically represents the chemical structure of the polymer according to the present invention and describes it using graphic data includes, in addition to graph information of monomer repeating units, connection node information representing connection nodes which are nodes to which monomers are repeatedly connected, and information of connection edges 40 connected to the connection nodes.

[0042] According to the representation method of the polymer adjacency matrix PA described above, a monomer repeating unit composed of nodes 1, 2, 3, and 4 is shown to be repeated by being connected at nodes 1 and 4 to nodes 4 and 1 of adjacent repeating units, respectively. However, in this case, nodes 1 and 4 in Figure 3 are not connected to each other within the monomer, but rather to the nodes of adjacent repeating units. Therefore, these nodes can be designated as "connecting nodes" and distinguished by assigning a connecting node attribute to the node characteristic matrix or an adjacent repeating unit connection attribute to the edge characteristic matrix.

[0043] This can be used as an embedding procedure to convert the chemical structure of a polymer into computer-processable data. This is achieved using a polymer edge variable setting step, which sets the connection relationships between nodes representing each atom constituting the monomer repeating unit of a selected polymer and connection nodes, which are the locations where the monomers are repeatedly connected, as polymer connection edge variables, and a polymer graph edge information assignment step, which assigns attribute values ​​of the connection relationships between the nodes and connection nodes to the set polymer edge variables. As is clear from the polymer adjacency matrix PA above, the attribute values ​​of the connection relationships between the nodes and connection nodes can be determined as "1" or "0" indicating connected / disconnected, and the polymer adjacency matrix is ​​a matrix representation of this. The polymer adjacency matrix of the present invention has component values, similar to a normal adjacency matrix, except that, as mentioned above, it differs because connection nodes are added to the normal monomolecule graph nodes.

[0044] (3) Characteristic matrix of monomer graph

[0045] In addition to the adjacency matrix that shows the connection relationships between nodes, the graph representation of a compound can also include a characteristic matrix as graph information that represents predetermined attribute information for each node and predetermined attribute information for each edge. In the exemplary monomer graph of Figure 3, the monomer node characteristic matrix that has attribute value information for each atom (exemplary, three pieces of attribute information) can be represented as follows.

[0046]

number

[0047] The node characteristic matrix NF has a number of rows corresponding to the number of nodes and a number of columns corresponding to the number of types of characteristic values ​​to be represented for each node, and can represent the predetermined attributes to be represented for each atom. i,j This has the j-th characteristic value of the i-th node. The monomer characteristic matrix NF is shown as an example where each node has three arbitrary attribute values ​​for illustrative purposes.

[0048] A monomer graph can be represented by an edge characteristic matrix EF, where each row represents an edge of the monomer, and the column data in each row represents a predetermined attribute value of that edge. Possible edge attribute values ​​include the type of chemical bond (single bond, double bond, etc.), the presence or absence of rings, and the presence or absence of conjugation. For example, in the case of the monomer in Figure 3, there are three connecting edges, so its edge characteristic matrix has three rows, and the edge attribute values ​​to be contained are assigned to each column. An example of an edge characteristic matrix with three arbitrary edge attribute values ​​is shown below.

[0049]

number

[0050] (4) Characteristic matrix of polymer graph according to the present invention

[0051] The polymer graph information according to the present invention may have additional attribute values ​​in addition to the attribute values ​​of the monomer node feature matrix described above. For example, the polymer node feature matrix PF (Polymer Feature matrix), which is the feature matrix of the exemplary polymer graph in Figure 3, may also have additional attribute information in the third column, as shown in the example below, and this can be represented by an attribute value indicating whether or not each node is a connected node. For example, the polymer node feature matrix PNF below may have connected node attribute information in the fourth column, as shown below, in addition to the monomer node feature matrix NF which contains the three types of attribute information of the four nodes mentioned above. In the example in Figure 3, nodes 1 and 4 are connected nodes that are connected to adjacent repeating units, so they have a value of "1", and the other nodes are represented as having a value of "0" in the fourth column.

[0052]

number

[0053] This is accomplished using a polymer node variable setting step, in which each atom of the monomers forming the selected polymer and the connection nodes, which are the locations where the monomers are repeatedly connected, are set as polymer node variables; and a polymer graph node information assignment step, in which connection nodes connected to the set polymer node variables are assigned and node attribute values ​​are assigned to each node. The node attribute values ​​assigned to the nodes may include atomic number, hybridization (SP3, SP2, etc.), number of hydrogens, number of electrons, presence or absence of rings, and in particular, in one embodiment of the present invention, the node may have a connection node attribute value which is an attribute value indicating the presence or absence of a node connected to an adjacent repeating unit value.

[0054] In another embodiment of the present invention, connection node information can be represented by an edge characteristic matrix. For example, instead of representing whether or not a node is connected by a node attribute value, as in the polymer node characteristic matrix described above, or in conjunction with it, the edge characteristic matrix can represent attribute values ​​indicating the presence or absence of a connected edge. In the following example representing Figure 3(b), it can be seen that the fourth and fifth rows of data have been added to accommodate the information of the edges connecting connection nodes 1 and 4, i.e., edges 5_1 and 4_6 in Figure 3(b), and an attribute information column indicating the presence or absence of a connected edge has been added to the fourth column.

[0055]

number

[0056] In other words, according to the present invention, the method for representing the structure of a polymer graphically and converting it into data usable by a computer can be selected from one or more of the following methods.

[0057] 1) In an adjacency matrix representing the connection relationships of each node in a repeating unit consisting of at least one monomer, the components of "connecting nodes" that are connected to adjacent repeating units are assigned as the "connection" attribute.

[0058] 2) A node attribute matrix representing the attributes of each node in the repeating unit is given a "connection status" attribute field, and the "connection status" attribute field of the "connected node" is assigned "connected".

[0059] 3) Add the edges connected to the connected node to the edge attribute matrix of the repeating unit to the connected edge, assign the edge attribute a "connected" attribute field, and assign "connected" to the field of the connected edge.

[0060] 2.2. Method for converting the chemical structure of polymers into computer-processable data.

[0061] In this invention, when training an artificial neural network model described later and predicting the properties of a polymer substance using the trained artificial neural network, the chemical structure of the polymer substance must be converted into data that can be processed by a computer. This data conversion is carried out according to the method of this invention described below.

[0062] (1) Repeated unit information acquisition step

[0063] This step involves obtaining information about repeating units, which are units formed by the repetition of monomers to create a polymer. One of the features of the present invention is obtaining information about repeating units that form a polymer in order to digitize the connection node information in the repeating units. The repeating unit information involves confirming whether the repeating units that form a polymer are repeated as a single monomer or as a combination of single monomers, and describing the repeating units using a graphical representation. A repeating unit can be a single monomer as shown in Figure 2(a), or two monomers connected as shown in Figure 2(b). In the case shown in Figure 2(b), an already adjacent node becomes the attachment point.

[0064] (2) Polymer graph node connection information assignment step

[0065] The present invention provides a method for processing polymer graph information, which involves setting as variables the connection relationships between nodes representing each atom constituting a repeating unit of a polymer selected as the target of analysis, and connection nodes connected to connection points, which are locations where the repeating units are repeatedly connected.

[0066] In this way, attribute values ​​representing the interconnections between the nodes and connected nodes are assigned to the polymer node connection variables. The polymer adjacency matrix, which was given as an example above, can be used to assign attribute values ​​for each interconnection to the polymer node connection variables.

[0067] (3) Polymer graph node attribute information assignment step

[0068] Furthermore, the polymer graph information processing method of the present invention may include a polymer node attribute variable setting step in which attribute information of nodes corresponding to each atom constituting the repeating unit that forms the selected polymer, and attribute information of connection nodes connected to connection points, which are locations where the repeating unit is repeatedly connected, are set as polymer node attribute variables.

[0069] The polymer graph node attribute information assignment step further includes assigning attribute values ​​of the node and connected nodes to the polymer node attribute variables set in this manner. The node attribute information has an attribute value indicating whether the node is a connected node or not, and as node attribute information for a connected node, a connected node attribute value is given that indicates that, unlike a node that is not a connected node, it is connected to a connected node of an adjacent repeating unit within the polymer.

[0070] (4) Polymer graph edge attribute information assignment step

[0071] Furthermore, the polymer graph information processing method of the present invention may include a polymer edge attribute variable setting step, in which information of the edges that connect nodes corresponding to each atom constituting the repeating unit forming the selected polymer, and the connecting edges that connect at least one of the nodes to the connecting node, is set as polymer edge attribute variables. A connecting edge is an edge that connects a connecting node to another node.

[0072] Furthermore, the present invention includes a polymer graph edge attribute information assignment step in which attribute values ​​of the edge and connected edge are assigned to the set polymer edge attribute variable, wherein a connected edge is assigned a connected edge attribute value as its edge attribute variable, which means that the connected node connects to other nodes.

[0073] <Examples and Comparative Examples>

[0074] An example of how polymer graph information can be represented according to the present invention described above will now be explained.

[0075] Figure 7a shows a method of representing the molecular structure of polyethylene terephthalate (PET) as an example of a polymer using graph information according to conventional technology, and Figure 7b shows a method of representing polymer graph information according to the present invention.

[0076] According to the conventional method, as shown in Figure 7a, only the unit structure of the polymer is converted into a graph. In this case, the atomic number, presence or absence of rings, and number of hydrogen atoms were used as node attribute values ​​in the node characteristic matrix. The edge characteristic matrix has the type of bond, whether it is aromatic or not, and presence or absence of conjugation as edge attribute values.

[0077] In contrast, the graph information representation method according to the present invention, as shown in Figure 7b, further includes connected node attribute information as node attribute values ​​in the node characteristic matrix, and in the example, since node 1 and node 14 are connected, the connected node attribute information value is "1". The edge characteristic matrix further includes edge attribute values ​​as connected edge attribute information, and the connected edge "14-1" has attribute information "1" as a connected edge.

[0078] Figure 8 shows an example of visualizing the molecular structure of another polymer, polyvinyl benzyl chloride (PVBC), as graph information.

[0079] Figure 8a shows the adjacency matrix, node characteristic matrix, and edge characteristic matrix as represented by conventional methods.

[0080] Figure 8b shows an example of the method according to the present invention in which the molecular structure of PVBC is represented as graph information. Compared to the conventional method shown in Figure 8a, the node characteristic matrix further includes connected node attribute information, and in the example, nodes 1, 2, 11, and 12 are connected nodes, so the node attribute information values ​​of these nodes are set to "1". In cases like PVBC, where already adjacent nodes of a repeating unit become attachment points, the graph information is converted using a repeating unit to which two monomers are connected. This is the case explained in relation to Figure 2(b). As shown in the figure, the edge characteristic matrix further includes connected edge attribute information, and the connected edge attribute information of connected edges "2-11" and "1-12" is set to "1".

[0081] 3. Method for analyzing polymer properties using a graphical representation of polymers according to the present invention

[0082] The following describes a method for processing polymer data in an artificial neural network, in accordance with the polymer graph representation method of the present invention described above.

[0083] The present invention provides a method for constructing an artificial neural network model to analyze predetermined properties of a polymer by applying the above-described graph representation method of the polymer, and for calculating predetermined properties of the polymer through machine learning.

[0084] 3.1. Method for generating polymer property analysis models

[0085] Figure 5(a) shows a method for generating a polymer property analysis model according to the present invention. Based on this, a method for generating a computer-implemented polymer property analysis model that predicts predetermined property information of a selected polymer from its chemical structure, in accordance with the graph information representation method of the present invention, will be described.

[0086] (1) Preparation of training data (T10)

[0087] First, the system includes a learning data preparation process (T10) in which the chemical structure information of a large number of learning polymers, each with known predetermined characteristic information, is converted into polymer graph information of the present invention using the method described above, based on basic data consisting of chemical structure information of a large number of learning polymers and predetermined known characteristic information of said polymers. This corresponds to the data preprocessing process of the basic data. The learning data prepared in this way may consist of a large number of datasets, each set containing {learning polymer graph information, known predetermined characteristic information of said polymer}. Here, known predetermined characteristic information of a polymer means measured values, actual values, or defined characteristic information of the polymer's characteristic information.

[0088] (2) Construction of an artificial neural network and input of training data (T20)

[0089] Next, an artificial neural network model to be trained is constructed using the training data. In this invention, known artificial neural network models can be used, and in particular, message-passing-based MPNN (message passing neural network) and GNN (graph neural network) models can be applied.

[0090] For example, when applying a GNN, in the case of supervised learning, molecular learning data consisting of a set of {polymer graph information and predetermined property information of the polymer} constructed earlier is input to the graph neural network (GNN) model. Examples of the predetermined property information of the polymer include the refractive index, glass transition temperature, and density of the polymer.

[0091] In this case, the polymer graph information is the input value of the neural network model, and the predetermined characteristic information of the polymer is input as the true value (labeled data) of the output value. The input polymer graph information includes at least one of the polymer graph node connection information, polymer graph node attribute information, and polymer graph edge attribute information mentioned above, and can be input embedded in the polymer adjacency matrix and polymer node / edge characteristic matrix.

[0092] (3) Training steps of the artificial neural network model (T30)

[0093] This process involves updating the parameters of a neural network model based on input polymer graph information and predetermined polymer characteristic information to train the neural network model. The neural network training process conforms to known neural network model training processes. For example, the parameters of the artificial neural network are updated to minimize the error function, which is defined as the difference between the predicted polymer characteristic information calculated by the neural network model upon input of the polymer graph information and the predetermined polymer characteristic information from the training data.

[0094] 3.2. Methods for Analyzing Polymer Properties

[0095] This method involves inputting graph information of a selected polymer into an artificial neural network generated according to the polymer property analysis model generation method of the present invention described above, in order to predict the property information of the selected polymer. This will be explained with reference to Figure 5(b).

[0096] (1) Polymer graph information preprocessing process (S10)

[0097] A preprocessing step is performed to obtain polymer graph information from the chemical structure of the selected polymer whose characteristic information is to be predicted. As mentioned above, the polymer graph information includes node and edge information of the monomers constituting the polymer, as well as information on connection nodes and connection edges 40 between repeating monomers. In other words, the polymer graph information is preprocessed to include at least one of the polymer graph node connection information, polymer graph node attribute information, and polymer graph edge attribute information described above.

[0098] (2) Polymer graph information input step (S20)

[0099] This step involves inputting polymer graph information, based on the chemical structure of the selected polymer, into a previously trained neural network model. The input polymer graph information includes at least one of the polymer graph node connection information, polymer graph node attribute information, and polymer graph edge attribute information mentioned above, and can be embedded in the polymer adjacency matrix and polymer node / edge characteristic matrix.

[0100] (3) Polymer property information prediction step (S30)

[0101] This step involves calculating and outputting the characteristic information of the selected polymer from the polymer graph information of the input selected polymer using the trained artificial neural network model.

[0102] 4. Polymer property information prediction system 300 according to the present invention

[0103] Based on Figure 6, the polymer property information prediction system according to the present invention will be described.

[0104] (1) Polymer graph information input unit 100

[0105] Polymer graph information The input unit 100 is a component that receives input by converting the chemical structure of the selected polymer into polymer graph information, which describes the polymer's structure using graphical data.

[0106] Polymer graph information The input unit 100 includes a polymer graph information acquisition unit 110 that acquires polymer graph information from the chemical structure of a selected polymer whose characteristic information is to be predicted.

[0107] The polymer graph information acquisition unit 110 generates polymer graph information by assigning connection node and connection edge information between repeating units to its respective variables, in addition to the node and edge information of the monomers constituting the polymer as described above, and processing it. That is, the polymer graph information is a dataset that includes at least one of the polymer graph node connection information, polymer graph node attribute information, and polymer graph edge attribute information described above, and the polymer graph connection information is information that represents the connection relationships between nodes corresponding to each atom constituting the repeating units that form the polymer and connection nodes that are connected to connection points, which are the locations where the repeating units are repeatedly connected.

[0108] Polymer graph information The input unit 100 receives polymer graph information into an artificial neural network, which will be described later. 210 The system may further include a matrix transformation unit 120 that generates and inputs a polymer adjacency matrix, which includes a polymer adjacency matrix representing the interconnection relationships between two or more nodes representing each atom constituting a single molecule of polymer, and connection relationship information between the connected nodes, as well as attribute information of one or more edges representing the connections between each node and the connected nodes.

[0109] In this case, the polymer graph information may include, as described above, polymer graph node connection information which represents the connection relationships between nodes corresponding to each atom constituting the repeating unit that forms the polymer and connection nodes that are connected to connection points, which are locations where the repeating unit is repeatedly connected; polymer node attribute information which represents the attributes of the nodes corresponding to each atom constituting the repeating unit that forms the polymer and connection nodes that are connected to connection points, which are locations where the repeating unit is repeatedly connected; and polymer edge attribute information which represents the attributes of the edges that connect the nodes corresponding to each atom constituting the repeating unit that forms the polymer and connection edges that connect at least one of the nodes to the connection node.

[0110] (2) Polymer property information prediction unit 200

[0111] The polymer property information prediction unit 200 comprises an artificial neural network 210 that has been trained to predict and calculate predetermined property information of the polymer from the polymer graph information.

[0112] The artificial neural network is configured to receive the aforementioned polymer graph information as input and output a predetermined characteristic information prediction value for the polymer. It calculates the predetermined characteristic information prediction value for the polymer from the polymer graph information of a predetermined learning polymer, and updates the parameters of the neural network according to the procedure described above so that the error function, defined as the difference between the characteristic information and the predicted value, is minimized.

[0113] (3) Computer equipment

[0114] The polymer property information prediction system 300 according to the present invention may consist of a single computing system or a computer device in which multiple computing systems are connected by a network. The computer device may consist of the polymer graph information input unit 100 and the polymer property information prediction unit 200 described above, as well as a memory device 310 and a computing device 320 that constitute the computer device. That is, the computer device 300 comprises a memory device 310 and a computing device 320, and the polymer graph information input unit 100 and the polymer property information prediction unit 200 described above occupy predetermined functions and parts of the memory device 310 and the computing device 320.

[0115] The polymer graph information input unit 100 and the polymer property information prediction unit 200 may include, or be composed of, a computer algorithm that is stored in the memory device 310 of the computer device and read from the arithmetic unit 320 to perform each procedure when generating and processing the polymer graph information.

[0116] The reference numerals and names of the elements used in the description of this invention are as follows: [Explanation of Symbols]

[0117] 10...nodes 20…Edge 30…Connection point 40…Connection Edge 100... Polymer graph information input section 110... Polymer graph information acquisition unit 120... Matrix transformation section 200... Polymer property information prediction unit 210…Artificial Neural Networks 310...Memory device 320...Arithmetic device

Claims

1. A method for converting the chemical structure of a polymer into data that can be processed by a computer, which is performed by a computer's computing unit, A polymer adjacency matrix setting step, which sets the mutual connection relationships between nodes representing each atom constituting the repeating unit of the selected polymer and connection nodes connected to connection points, which are locations where the repeating unit is repeatedly connected, as a polymer adjacency matrix stored in the computer's memory device, A polymer graph node connection information assignment step, which assigns attribute values ​​of the mutual connection relationships between the node and the connected node to the set polymer adjacency matrix, A polymer node characteristic matrix setting step, which sets attribute information of nodes corresponding to each atom constituting the repeating unit that forms the selected polymer, and information of connection nodes among the nodes that are connected to connection points where the repeating unit is repeatedly connected, as a polymer node characteristic matrix on the computer's memory device, A polymer graph node attribute information assignment step involves assigning polymer node attribute information, which is information representing the attribute information of the node and the attribute of the connected node, to the set polymer node characteristic matrix. Includes, The polymer node attribute information includes a connection node attribute value that identifies whether the node is a connection node connected to an adjacent repeating unit, The polymer adjacency matrix and the polymer node characteristic matrix are used as input data for an artificial neural network to predict polymer characteristic information. Data processing methods for polymer chemical structures.

2. A polymer edge characteristic matrix setting step, which sets information of the edges connecting nodes corresponding to each atom constituting the repeating unit forming the selected polymer, and the connecting edges connecting at least one of the nodes to the connecting node, as a polymer edge characteristic matrix on the computer's memory device, A polymer graph edge attribute information assignment step involves assigning attribute values ​​of the edge and the connected edge to the set polymer edge characteristic matrix, A method for processing data of a polymer chemical structure according to claim 1, further comprising:

3. A method for generating a computer-implemented model that graphically describes the chemical structure of a selected polymer and analyzes predetermined properties of the polymer, A basic data acquisition step consisting of known values ​​of chemical structure information and predetermined characteristic information of a large number of learning polymers, Of the aforementioned basic data, a data preprocessing process is performed to convert the chemical structure information of the learning polymer into polymer graph information, A step of configuring an artificial neural network for predicting polymer properties, which receives polymer graph information as input and outputs predetermined characteristic information prediction values ​​for the polymer; A learning data input step involves inputting polymer graph information of the learning polymer and predetermined characteristic information of the learning polymer into the polymer characteristic information prediction artificial neural network. A learning step for the polymer property information prediction artificial neural network, in which the parameters of the polymer property information prediction artificial neural network are updated based on the comparison result between the predetermined property information prediction value of the learned polymer output by the polymer property information prediction artificial neural network and the known value of the predetermined property information of the learned polymer, Includes, The aforementioned polymer graph information is Polymer graph node connection information is information that represents the mutual connection relationships between nodes corresponding to each atom constituting the repeating unit that forms the polymer and connection nodes that are connected to connection points, which are locations where the repeating unit is repeatedly connected. Polymer node attribute information includes attribute information of nodes corresponding to each atom constituting the repeating unit that forms the polymer, and information representing the attributes of connection nodes among the nodes that are connected to connection points, which are locations where the repeating unit is repeatedly connected, and includes a connection node attribute value that identifies whether or not the node is a connection node connected to an adjacent repeating unit. Polymer edge attribute information is information representing the attributes of the edges that connect to each atom corresponding to each atom constituting the repeating unit forming the polymer, and the connecting edges that connect at least one of the nodes to the connecting node. Including at least one of the following: Method for generating polymer property analysis models.

4. A computer implementation method for graphically describing the chemical structure of a selected polymer and analyzing predetermined properties of the polymer, A polymer property information computation artificial neural network configuration step generates an artificial neural network that is machine-learned to predict predetermined properties of the polymer based at least partially on the selected polymer and associated chemical structure data, A polymer graph information acquisition step involves acquiring polymer graph information that describes the chemical structure of the selected polymer using graphical data, A polymer graph information input step provides the acquired polymer graph information as input to the machine-learned graph neural network, The steps include receiving predictive data describing the predetermined properties of the selected polymer as the output of the machine learning-trained graph neural network, It includes, Polymer graph information that describes the chemical structure of the selected polymer using graph information is: Polymer graph node connection information is information that represents the mutual connection relationships between nodes corresponding to each atom constituting the repeating unit that forms the polymer and connection nodes that are connected to connection points, which are locations where the repeating unit is repeatedly connected. Polymer node attribute information includes attribute information of nodes corresponding to each atom constituting the repeating unit that forms the polymer, and information representing the attributes of connection nodes among the nodes that are connected to connection points, which are locations where the repeating unit is repeatedly connected, and includes a connection node attribute value that identifies whether or not the node is a connection node connected to an adjacent repeating unit. Polymer edge attribute information is information representing the attributes of the edges that connect to each atom corresponding to each atom constituting the repeating unit forming the polymer, and the connecting edges that connect at least one of the nodes to the connecting node. A computer implementation method characterized by including at least one of the following.

5. The polymer graph information input step, which provides the acquired polymer graph information as input to the machine-learned graph neural network, A polymer adjacency matrix construction step, which involves constructing an adjacency matrix that represents the mutual connection relationships between two or more nodes representing each atom constituting the repeating unit forming the polymer, A polymer adjacency matrix input step in which the polymer adjacency matrix constructed above is input as the graph neural network, Includes, The aforementioned polymer adjacency matrix is, The computer implementation method according to claim 4, further comprising connection relationship information between the connection node and the node.

6. The polymer graph information input step, which provides the acquired polymer graph information as input to the machine-learned graph neural network, A polymer edge attribute matrix input step involves generating and inputting a polymer edge attribute matrix that includes attribute information of one or more edges representing the connections between each of the aforementioned nodes and connection edges representing the connections between the nodes and the connection nodes, The computer implementation method according to claim 5, characterized by including the following:

7. The step of obtaining a graph neural network, which has been machine-trained to predict predetermined properties of a polymer based at least partially on chemical structure data associated with the polymer, using one or more computer devices, is: The steps include: acquiring training data using one or more computer devices, which includes the chemical structures of multiple exemplary polymers and predetermined characteristic label values ​​that describe predetermined properties of the exemplary polymers having the chemical structures of the exemplary polymers; A learning step involves acquiring graph information that graphically describes the chemical structure of the exemplary polymer and inputting it into a graph neural network, and training the graph neural network so that it outputs predetermined characteristic labels that describe predetermined characteristics of the exemplary polymer, which are output by the graph neural network. The computer implementation method according to claim 4, including the method described in claim 4.

8. The graphical information describing the chemical structure of the aforementioned exemplary polymer is: Two or more node information representing each atom constituting the repeating unit that forms the polymer, One or more edge pieces representing the bonds between each of the aforementioned atoms, The connection node information is the location where the repeating unit is repeatedly connected, Connection edge information representing the connection between the atom and the connection node, The computer implementation method according to claim 7, characterized by comprising the following:

9. A system for graphically describing the chemical structure of a selected polymer and analyzing predetermined properties of the polymer, A polymer graph information input unit that represents the chemical structure of the selected polymer using polymer graph information and receives polymer graph information as input, A polymer characteristic information prediction unit that outputs predicted values ​​of predetermined characteristic information of the selected polymer from the polymer graph information, It is equipped with, The aforementioned polymer graph information is Polymer graph node connection information is information that represents the mutual connection relationships between nodes corresponding to each atom constituting the repeating unit that forms the polymer, and connection nodes that are connected to connection points, which are locations where the repeating unit is repeatedly connected. Polymer node attribute information, which includes attribute information of nodes corresponding to each atom constituting the repeating unit that forms the polymer, and information representing the attributes of connection nodes among the nodes that are connected to connection points which are locations where the repeating unit is repeatedly connected, and which includes connection node attribute values ​​that identify whether the node is a connection node connected to an adjacent repeating unit, and The polymer edge attribute information includes at least one of the following: an edge that connects nodes corresponding to each atom constituting the repeating unit forming the polymer, and information that represents the attributes of a connecting edge that connects at least one of the nodes to the connecting node. The polymer property information prediction unit is A polymer property information prediction system comprising an artificial neural network trained to output a predetermined polymer property information prediction value from polymer graph information including at least one of the polymer graph node connection information, the polymer node attribute information, and the polymer edge attribute information.

Images