Model training method, molecular property information prediction method and device

Abstract

The present invention discloses a model training method and a method and apparatus for predicting molecular characteristic information, the method comprising the steps of acquiring data on a specified proteolysis-inducing chimeric molecule, constructing three-dimensional molecular graph data of the specified proteolysis-inducing chimeric molecule based on the data, inputting the three-dimensional molecular graph data of the specified proteolysis-inducing chimeric molecule into a prediction model to be trained and having the prediction model predict molecular characteristic information of the specified proteolysis-inducing chimeric molecule, and training the prediction model based on the difference between the predicted molecular characteristic information and the actual molecular characteristic information corresponding to the specified proteolysis-inducing chimeric molecule.

Description

[Technical Field]

[0001] The present invention relates to the fields of artificial intelligence and bioengineering, and in particular to a model training method and a method and apparatus for predicting molecular characteristic information. [Background technology]

[0002] The ubiquitination enzyme system is a classic method for protein degradation in the body. Using this classic method, proteolysis targeting chimeras (PROTACs) with bifunctional fragments can be designed to reduce or eliminate pathogenic proteins in the body. Here, proteolysis targeting chimeras are a targeted protein degradation technology that uses small molecule compounds to regulate protein levels. Their mode of action differs from that of conventional small molecule drugs, as they utilize unique targets to direct proteins into the proteasome to directly mediate the ubiquitination and degradation process of proteins.

[0003] Currently, proteolysis-inducing chimera technology is a hot topic in related pharmaceutical research, and such molecules are being used to develop therapeutic drugs for diseases including cancer, immune system disorders, and nervous system disorders. In particular, in the anti-cancer field, proteolysis-inducing chimeras can target proteins that induce the production of cancer cells and reduce the side effects of chemotherapy drugs.

[0004] Molecular property prediction is extremely important for applications such as drug discovery and protein design. Analyzing a molecular structure model to estimate its associated physical and chemical properties and then calculating accurate molecular properties can significantly improve the efficiency and accuracy of technological design. However, there is currently no effective method for accurately predicting molecular properties. Summary of the Invention

[0005] In order to solve some of the above problems in the prior art, the present invention provides a model training method, a method and apparatus for predicting molecular characteristic information. The present invention employs the following technical solutions:

[0006] In a first aspect, the present invention provides a model training method comprising the steps of acquiring data on a designated proteolysis-inducing chimeric molecule, constructing three-dimensional molecular graph data of the designated proteolysis-inducing chimeric molecule based on the data, inputting the three-dimensional molecular graph data of the designated proteolysis-inducing chimeric molecule into a prediction model to be trained and causing the prediction model to predict molecular characteristic information of the designated proteolysis-inducing chimeric molecule, and training the prediction model based on the difference between the predicted molecular characteristic information and the actual molecular characteristic information corresponding to the designated proteolysis-inducing chimeric molecule.

[0007] Optionally, the molecular characteristic information includes at least one of the lipophilicity of the designated proteolytic chimeric molecule, the pH of the designated proteolytic chimeric molecule, the molecular weight of the designated proteolytic chimeric molecule, the hydrogen bond donors and hydrogen bond acceptors in the designated proteolytic chimeric molecule, the solubility of the designated proteolytic chimeric molecule, and the permeability of the designated proteolytic chimeric molecule.

[0008] Optionally, the step of constructing three-dimensional molecular graph data of the specified proteolysis-induced chimeric molecule based on the data includes a step of representing edges between each atomic node by constructing an adjacency matrix corresponding to each atom, with each atom contained in the specified proteolysis-induced chimeric molecule as an atomic node, thereby obtaining the three-dimensional molecular graph data of the specified proteolysis-induced chimeric molecule, and the adjacency matrix is used to represent bonding information between each connected atom.

[0009] Optionally, an atom node of each atom included in the three-dimensional molecular graph data corresponds to node information, and the node information includes at least one of atom type information, atomic three-dimensional coordinate information, and nuclear charge number.

[0010] Optionally, for each atom included in the three-dimensional molecular graph data, the atom type information indicates to which atom the atom specifically belongs and is encoded using a one-hot encoding method, and the atomic three-dimensional coordinate information is the three-dimensional coordinate information of the atom in a predetermined three-dimensional coordinate system determined by projecting the atom onto the three-dimensional coordinate system, and the three-dimensional coordinate system includes a three-dimensional Cartesian coordinate system constructed with the molecular center of mass of the specified proteolysis-induced chimeric molecule as the coordinate origin.

[0011] Optionally, the step of inputting the three-dimensional molecular graph data of the designated proteolysis-induced chimeric molecule into a prediction model to be trained and having the prediction model predict molecular characteristic information of the designated proteolysis-induced chimeric molecule includes the steps of inputting the three-dimensional molecular graph data of the designated proteolysis-induced chimeric molecule into an embedding layer in the prediction model and obtaining an embedding vector corresponding to the three-dimensional molecular graph data by the embedding layer, inputting the embedding vector into an information update layer in the prediction model to determine target invariant features and target equivariant features of the designated proteolysis-induced chimeric molecule, and inputting the final invariant features and final equivariant features into an output layer in the prediction model and outputting the molecular characteristic information of the designated proteolysis-induced chimeric molecule predicted by the output layer.

[0012] Optionally, the step of inputting the three-dimensional molecular graph data of the specified proteolysis-induced chimeric molecule into an embedding layer in the prediction model and obtaining an embedding vector corresponding to the three-dimensional molecular graph data by the embedding layer includes the steps of: determining, for each atom in the specified proteolysis-induced chimeric molecule, atomic feature information corresponding to the atom based on the three-dimensional molecular graph data, wherein the atomic feature information includes at least one of atom type information of the atom, spacing information between the atom and other atoms, and neighboring atom information of the atom; and inputting the atomic feature information corresponding to each atom into an embedding layer in the prediction model and obtaining the embedding vector corresponding to the three-dimensional molecular graph data by the embedding layer.

[0013] Optionally, the embedding vector includes initial invariant features, and the step of inputting the embedding vector into an information update layer in the prediction model to determine target invariant features and target equivariant features of the specified proteolysis-induced chimeric molecule includes a step of determining, by the information update layer, attention weights corresponding to the initial invariant features and determining attention features corresponding to the specified proteolysis-induced chimeric molecule based on the attention weights, and a step of determining, by the information update layer, the target invariant features and the target equivariant features of the specified proteolysis-induced chimeric molecule based on the attention features.

[0014] Optionally, the step of determining the target invariant feature and the target equivariant feature of the specified proteolysis-induced chimeric molecule based on the attention feature by the information update layer includes the steps of: obtaining, by the information update layer, an attention feature corresponding to an initial equivariant feature and an attention feature corresponding to the initial invariant feature, where the initial equivariant feature is a zero vector; updating the attention feature corresponding to the initial invariant feature based on the attention feature corresponding to the initial invariant feature to obtain an updated initial invariant feature; updating the attention feature corresponding to the initial invariant feature based on the attention feature corresponding to the initial invariant feature to obtain an updated initial invariant feature; and determining, by the information update layer, the target invariant feature based on the updated initial invariant feature and the attention feature corresponding to the initial invariant feature, and determining the target equivariant feature based on the updated initial equivariant feature, the updated initial invariant feature, and the attention feature corresponding to the initial invariant feature.

[0015] Optionally, in response to the number of information update layers being 1, the target equivariant feature and the target invariant feature are set as the final equivariant feature and the final invariant feature, respectively, and in response to the number of information update layers being greater than 1, the target equivariant feature and the target invariant feature determined by the last information update layer of the predictive model are set as the final equivariant feature and the final invariant feature, respectively.

[0016] In a second aspect, the present invention provides a method for predicting molecular characteristic information, comprising the steps of acquiring data on a target protein degradation-inducing chimeric molecule, constructing three-dimensional molecular graph data of the target protein degradation-inducing chimeric molecule based on the data, and inputting the three-dimensional molecular graph data of the target protein degradation-inducing chimeric molecule into a pre-trained prediction model to have the prediction model predict molecular characteristic information of the target protein degradation-inducing chimeric molecule, wherein the prediction model has been trained by the method described in the first aspect.

[0017] In a third aspect, the present invention provides a model training device comprising: an acquisition module for acquiring data of a specified proteolysis-inducing chimeric molecule; a construction module for constructing three-dimensional molecular graph data of the specified proteolysis-inducing chimeric molecule based on the data; a prediction module for inputting the three-dimensional molecular graph data of the specified proteolysis-inducing chimeric molecule into a prediction model to be trained, causing the prediction model to predict molecular characteristic information of the specified proteolysis-inducing chimeric molecule; and a training module for training the prediction model based on the difference between the predicted molecular characteristic information and the actual molecular characteristic information corresponding to the specified proteolysis-inducing chimeric molecule.

[0018] In a fourth aspect, the present invention provides a molecular characteristic information prediction device comprising: an acquisition module for acquiring data on a target protein degradation-inducing chimeric molecule; a construction module for constructing three-dimensional molecular graph data of the target protein degradation-inducing chimeric molecule based on the data; and a prediction module for inputting the three-dimensional molecular graph data of the target protein degradation-inducing chimeric molecule into a pre-trained prediction model and causing the prediction model to predict molecular characteristic information of the target protein degradation-inducing chimeric molecule, wherein the prediction model has been trained using the model training method of the first aspect.

[0019] In a fifth aspect, the present invention provides a computer-readable storage medium having stored thereon a computer program, the computer program being adapted to perform the model training method of the first aspect when executed by a processor.

[0020] In a sixth aspect, the present invention provides a computer-readable storage medium having a computer program stored thereon, the computer program being executed by a processor to perform the method for predicting molecular characteristic information of the second aspect.

[0021] In a seventh aspect, the present invention provides an electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, the electronic device performing the model training method of the first aspect when the processor executes the computer program.

[0022] In an eighth aspect, the present invention provides an electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, the electronic device performs the molecular characteristic information prediction method of the second aspect.

[0023] At least one of the above technical solutions adopted by the present invention can achieve the following beneficial effects:

[0024] As can be seen from the above method, the present invention can construct three-dimensional molecular graph data of a specified proteolysis-induced chimera using the obtained data of a specified proteolysis-induced chimera molecule, and this three-dimensional molecular graph data can fully represent various features of the molecular structure of the specified proteolysis-induced chimera molecule. After the three-dimensional molecular graph data is input into a prediction model, the prediction model predicts molecular characteristic information of the specified proteolysis-induced chimera molecule based on the three-dimensional molecular graph data. Thus, by training the prediction model based on the difference between the predicted molecular characteristic information and the actual molecular characteristic information corresponding to the specified proteolysis-induced chimera molecule, the prediction model can quickly and accurately obtain molecular characteristic information in the subsequent molecular characteristic information prediction process, thereby improving the efficiency and accuracy of determining molecular characteristic information. [Brief explanation of the drawings]

[0025] The drawings described herein are intended to provide a further understanding of the present invention and constitute a part of the present invention. The schematic examples of the present invention and their descriptions are intended to help interpret the present invention and are not intended to constitute an undue limitation of the present invention. [Figure 1]FIG. 1 is a schematic diagram illustrating the flow of a model training method according to the present invention. [Figure 2] 1 is a schematic diagram showing the process of a method for predicting molecular property information according to the present invention. [Figure 3] 1 is a schematic diagram illustrating the architecture of a molecular property prediction system according to the present invention. [Figure 4] 1 is a schematic diagram illustrating a model training apparatus according to the present invention; [Figure 5] 1 is a schematic diagram showing a molecular property information prediction device according to the present invention. [Figure 6] 1 is a schematic diagram illustrating the structure of an electronic device according to the present invention; DETAILED DESCRIPTION OF THE INVENTION

[0026] In order to clarify the objectives, technical solutions and advantages of the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to specific embodiments of the present invention and corresponding drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments described in the present invention, all other embodiments obtained by those skilled in the art without any creative efforts fall within the protection scope of the present invention.

[0027] Hereinafter, technical solutions provided by the embodiments of the present invention will be described in detail with reference to the accompanying drawings.

[0028] FIG. 1 is a schematic diagram showing the flow of the model training method according to the present invention, which includes the following steps:

[0029] S101: Data on the designated proteolysis-inducing chimeric molecule is obtained.

[0030] The execution entity of the model training method provided by the present invention may be a terminal device such as a desktop computer or a laptop computer, or may be a server. For convenience of explanation, the present invention will describe the provided model training method using only a terminal device as the execution entity.

[0031] In the present invention, the terminal device may acquire raw structural data of various proteolysis-induced chimeric molecules to construct a dataset for training a model. This data may be collected from an external network or acquired in the form of file input. Exemplarily, the raw data may include a SMILES (Simplified Molecular-Input Line-Entry System) dataset of class proteolysis-induced chimeric molecules and actual proteolysis-induced chimeric molecules disclosed online. A SMILES dataset is a one-dimensional structural representation describing a compound.

[0032] After obtaining the above dataset, the terminal device needs to search for suitable data for training a predictive model from it; that is, not all of the data on various proteolytically induced chimeric molecules contained in the dataset are suitable as training samples; some of the data may have poorly labeled molecular fragments or may be considered "dirty data."

[0033] Therefore, the terminal device needs to search for a suitable proteolysis-induced chimeric molecule as a training sample from the dataset, i.e., determine a designated proteolysis-induced chimeric molecule. A specific implementation method may be to create an extensible three-dimensional molecular graph structure data generator and perform cleaning, reorganization, and optimization on the data of the class of proteolysis-induced chimeric molecules to determine the three-dimensional molecular graph data of the designated proteolysis-induced chimeric molecule as a training sample in a subsequent process. The designated proteolysis-induced chimeric molecule obtained after performing cleaning, reorganization, and optimization on the data of the class of proteolysis-induced chimeric compounds has logP values and PK values associated with the following invariant features and equivalent features: logP represents the oil-water partition coefficient of the compound, and the PK value represents its pharmacokinetic quality.

[0034] S102: Based on the data, three-dimensional molecular graph data of the specified proteolysis-inducing chimera is constructed.

[0035] In the present invention, the terminal device may determine data of the designated proteolysis-inducing chimera molecule from the above dataset, and then determine three-dimensional molecular graph data of the designated proteolysis-inducing chimera. The three-dimensional molecular graph data referred to here is used to represent structural features such as the type of each atom, the position of each atom (e.g., Cartesian coordinates), the number of nuclear charges of each atom, and the connection relationships between each atom in the designated proteolysis-inducing chimera molecule.

[0036] For example, each atom contained in a specified proteolysis-inducing chimeric molecule may be treated as an atomic node, and an adjacency matrix corresponding to each atom may be constructed to represent the edges between each atomic node, thereby forming part of the three-dimensional molecular graph data of the specified proteolysis-inducing chimeric molecule.

[0037] Here, the above-mentioned adjacency matrix is used to represent bonding information between each connected atom. For example, for two connected atoms, if the two atoms are connected by a single bond, it may be represented as "0", if they are connected by a double bond, it may be represented as "1", if they are connected by a triple bond, it may be represented as "2", and if they are connected by a quadruple bond, it may be represented as "3".

[0038] Furthermore, in the above three-dimensional molecular graph data, each atom's atomic node corresponds to corresponding node information, and for any one atom, the node information of the atom's atomic node may be to represent some inherent properties of the atom, for example, the node information of the atom's atomic node may include at least one of atom type information, atomic three-dimensional coordinate information, and nuclear charge number.

[0039] The atom type information is used to indicate to which atom the atom specifically belongs, such as carbon C, oxygen O, sulfur S, nitrogen N, fluorine F, chlorine Cl, etc. There are various specific ways to determine the atom type information, and for example, the atom type information may be determined in the form of one-hot encoding, or may be determined by a feature vector corresponding to each predetermined element symbol.

[0040] The three-dimensional atomic coordinate information of each atom may be determined by projecting each atom onto a predetermined three-dimensional coordinate system to determine the three-dimensional coordinate information of each atom in the three-dimensional coordinate system. In some examples, the predetermined three-dimensional coordinate system may be a three-dimensional Cartesian coordinate system constructed with the molecular center of mass of the designated proteolysis-inducing chimeric molecule as the coordinate origin. In another example, the predetermined three-dimensional coordinate system may be a three-dimensional coordinate system constructed with the first molecule of the designated proteolysis-inducing chimeric molecule as the coordinate origin. The present invention is not limited in this respect.

[0041] As can be seen from the above, the three-dimensional molecular graph data of the designated proteolysis-inducing chimeric molecule determined in the present invention makes it possible to consider the structural characteristics of the designated proteolysis-inducing chimeric molecule from multiple angles, thereby ensuring the accuracy and rationality of the prediction results of subsequent prediction models.

[0042] S103: The three-dimensional molecular graph data of the designated proteolysis-inducing chimeric molecule is input into a prediction model to be trained, and the prediction model is made to predict molecular property information of the designated proteolysis-inducing chimeric molecule.

[0043] In the present invention, an embedding layer is provided in the above prediction model, and the input three-dimensional molecular graph data is passed through the embedding layer to obtain an embedding vector, so that the molecular property information is predicted based on the embedding vector in the subsequent process.

[0044] In addition, the prediction model of the present invention may further include an information update layer, the main function of which is to input the above-mentioned embedding vector into the information update layer, and then perform multiple data update operations by the information update layer to obtain invariant features and equivariant features of the specified proteolysis-inducing chimeric molecule.The invariant features and equivariant features are then input into the output layer of the prediction model, and the output layer outputs molecular characteristic information of the predicted specified proteolysis-inducing chimeric molecule.

[0045] For each atom in the designated proteolysis-inducing chimeric molecule, the terminal device may first determine the atom characteristic information corresponding to the atom based on the three-dimensional molecular graph data. The atom characteristic information described here is intended to represent the properties of the atom, and may specifically include the atom type information of the atom (the atom type information is the information describing which atom the atom belongs to), the distance information between the atom and other atoms, and the neighboring atom information of the atom.

[0046] In the present invention, the distance information between two atoms may be determined in various ways. For example, after determining the three-dimensional coordinate information of each atom, the distance between the three-dimensional coordinates of the two atoms may be determined, and the determined distance may be directly used as the distance information between the two atoms. Alternatively, for example, the distance information between two atoms may be determined by a radial basis function (RBF). Determining the distance information by the radial basis function method may specifically refer to the following formula (1):

number

[0047] The neighboring atom information mentioned above may be determined by the following embedding formula (2):

number

number

[0048] After determining the atomic feature information corresponding to each atom, the atomic feature information corresponding to each atom may be input into an embedding layer in the prediction model to obtain an embedding vector corresponding to the three-dimensional molecular graph data through the embedding layer. For example, the embedding vector may include the initial invariant features shown in the following formula (3-1).

[0049] As mentioned above, in the present invention, the information update layer is mainly used to input the embedding vector into the information update layer, and then perform multiple data update operations to finally obtain the invariant features and equivariant features of the proteolysis-induced chimeric molecule. In the present invention, the information update layer mainly uses an attention mechanism and a message passing mechanism to continuously update the invariant features and equivariant features, and after completing the feature update, predicts molecular characteristic information based on the updated features.

[0050] Specifically, after the embedding vector is input to the information update layer of the prediction model, the information update layer may determine attention weights corresponding to the initial invariant features, and then determine attention features corresponding to the initial invariant features of the specified proteolysis-inducing chimeric molecule based on the attention weights. Similarly, after the embedding vector is input to the information update layer of the prediction model, the information update layer may determine attention weights corresponding to the initial equivariant features, and then determine attention features corresponding to the initial equivariant features of the specified proteolysis-inducing chimeric molecule based on the attention weights. This process may be considered to be entirely performed in the information update layer.

[0051] The initial invariant characteristics of the designated proteolysis-induced chimeric molecule may be determined according to the following formula (3-1):

number

number

number

[0052] The initial equivariant features may be determined by numerical initialization, specifically, by referring to the following equation (3-2).

number

[0053] As can be seen from the above formula, the initial equivariant features are

number

[0054] After determining the initial equivariant features and initial invariant features, the two features may be updated to obtain target equivariant features and target invariant features, respectively.

[0055] Here, the prediction model may first obtain the embedding of query (Q) and key (K) through the attention mechanism in the information update layer, and specifically, may be determined by the following equations (4-1) and (4-2).

number

number

[0056] Then, the attention mechanism in the information update layer may determine the attention feature corresponding to the specified proteolysis-induced chimeric molecule based on the determined attention weight, specifically, by referring to the following equations (5-1) and (5-2).

number

number

[0057] For the initial equivariant features, the present invention may use the mechanism of VN-MLP equivariant multilayer perceptron to update them, specifically, refer to the following equations (6-1) and (6-2).

number

number

number

[0058] Then, attention features for the initial equivariant features may be determined using the attention weights corresponding to the determined equivariant features, and specifically, the following equation (7) may be referenced.

number

[0059] After obtaining attention features (which may be abbreviated as invariant features) for the initial invariant features and attention features (which may be abbreviated as equivariant features) for the initial equivariant features using the above method, the invariant features and equivariant features may be subsequently updated by an information update layer.

[0060] Specifically, the information update layer may update the invariant features based on the equivariant features to obtain the updated invariant features. Here, the above method first obtains the attention features corresponding to the initial equivariant features.

number

number

number

number

number

[0061] Regarding the update of equivariant features, the information update layer may update the equivariant features based on the invariant features to obtain the updated equivariant features. Specifically, this process involves first determining the attention features corresponding to the initial equivariant features based on the initial equivariant features, and then updating the invariant features S i Based on this, attention features corresponding to the initial equivariant features are

number

number

number

number

number

[0062] After obtaining the updated invariant features, the information update layer updates the updated invariant features S' i and attention features corresponding to the determined initial invariant features

number

number

number

number

[0063] For equivariant features, the updated equivariant features

number

number

number

number

[0064] Note that the target equivariant features and target invariant features obtained here are only the equivariant features and invariant features output by this information update layer, and in some examples, in response to the number of information update layers being 1, they may be output directly to the output layer of the model as the final equivariant features and invariant features, or in some examples, in response to the number of information update layers being greater than 1, they may be output to another information update layer to perform further updating and optimization on these features.

[0065] In the present invention, a prediction model may be provided with multiple information update layers, and continuous updating and optimization of invariant features and equivariant features is realized between the multiple information update layers through feature transmission, and finally, the invariant features and equivariant features after updating and optimization are input to the output layer in the prediction model.

[0066] Therefore, after determining the above target-invariant features and target-equivalent features, they may be combined into a feature combination such as the following formula (10-1).

number

[0067] Next, the feature combination and the original input are input to the next information update layer, the output result of the information update layer is obtained, and the output result is transmitted to the next information update layer, and so on. Specifically, the following equation (10-2) may be referred to.

number

number

number

[0068] In the final information update layer of the prediction model, the output target equivariant features and target invariant features are output as the final equivariant features and invariant features to the output layer of the model, which combines the final invariant features and equivariant features to perform the final molecular drug formation property prediction and obtain the molecular property information of the designated proteolysis-induced chimeric molecule.

[0069] As can be seen from the above, the determined invariant features of the specified proteolysis-induced chimeric molecule actually represent molecular features of the specified proteolysis-induced chimeric molecule that do not change depending on the molecular structure (the invariant features of each atom are actually determined by information such as the charge number of the atom, and this information usually does not change when the molecular structure is given), and the equivariant features of the specified proteolysis-induced chimeric molecule can represent the properties exhibited by some notable atoms in the molecular structure of the specified proteolysis-induced chimeric molecule (the equivariant features of each atom are actually determined by information such as the three-dimensional coordinate information of each atom, and for calculation simplicity, the initial equivariant features are set to 0 and the equivariant features are determined by the attention mechanism).

[0070] Therefore, the subsequent output layer may be understood to actually predict molecular property information of the specified proteolytic chimeric molecule based on the final equivariant and invariant features of the specified proteolytic chimeric molecule, some notable atomic properties in the molecular structure of the specified proteolytic chimeric molecule, and some fixed properties in the molecular structure of the specified proteolytic chimeric molecule.

[0071] S104: The prediction model is trained based on the difference between the predicted molecular characteristic information and the actual molecular characteristic information corresponding to the designated proteolysis-inducing chimeric molecule.

[0072] After predicting the molecular characteristic information, the difference between the molecular characteristic information and the actual molecular characteristic information corresponding to the designated proteolysis-inducing chimeric molecule may be determined, and a predictive model may be trained with the optimization goal of minimizing the difference.

[0073] The molecular characteristic information referred to in the present invention may include at least one of the lipophilicity of the specified proteolytic chimeric molecule, the pH of the specified proteolytic chimeric molecule, the molecular weight of the specified proteolytic chimeric molecule, the hydrogen bond donor and hydrogen bond acceptor in the specified proteolytic chimeric molecule, the solubility of the specified proteolytic chimeric molecule, and the permeability of the specified proteolytic chimeric molecule.

[0074] As can be seen from the above method, the model training method provided by the present invention refers to the structural features of the molecular structure of the specified proteolysis-induced chimeric molecule from multiple perspectives in the process of determining the three-dimensional molecular graph data of the specified proteolysis-induced chimeric molecule. Furthermore, when predicting the molecular characteristic information of the specified proteolysis-induced chimeric molecule, the structural features are determined based on the final invariant and isovariant features of the specified proteolysis-induced chimeric molecule. This method can fully represent the characteristics of the molecular structure of the specified proteolysis-induced chimeric molecule, ensuring that the prediction model subsequently predicts accurate and reasonable molecular characteristic information.

[0075] After the prediction model is trained, it can be used to predict molecular property information of a specified molecule in practical applications. The specific process is shown in the following figure:

[0076] FIG. 2 is a schematic diagram showing the process of the method for predicting molecular property information according to the present invention.

[0077] S201: Data on the targeted proteolysis-inducing chimeric molecule is acquired.

[0078] S202: Based on the data, three-dimensional molecular graph data of the target proteolysis-inducing chimeric molecule is constructed.

[0079] In the present invention, a terminal device may receive a molecular property prediction command for a target proteolysis-inducing chimeric molecule input by a user, obtain data on the target proteolysis-inducing chimeric molecule according to the molecular property prediction command, and construct three-dimensional molecular graph data for the target proteolysis-inducing chimeric molecule. Here, the molecular property prediction command for the target proteolysis-inducing chimeric molecule may include two fragment molecules provided by the user. The determination of the three-dimensional molecular graph data here is essentially the same as the process of determining three-dimensional molecular graph data in the model training described above, and therefore will not be described in detail here. The terminal device referred to here may be a desktop computer, laptop computer, or other device.

[0080] S203: The three-dimensional molecular graph data of the target protein degradation-inducing chimeric molecule is input into a pre-trained prediction model, and the prediction model is made to predict the molecular characteristic information of the target protein degradation-inducing chimeric molecule, and the prediction model is trained by the above-mentioned model training method.

[0081] The terminal device may input three-dimensional molecular graph data of the target protein degradation-inducing chimeric molecule into a prediction model arranged on the terminal device, and the prediction model outputs molecular characteristic information of the predicted target protein degradation-inducing chimeric molecule.

[0082] After obtaining molecular property information using the prediction model, the molecular property information can be displayed to the user, or information can be recommended to the user based on the molecular property information, such as recommending pharmaceutical compounds that bind well to the target proteolysis-inducing chimeric molecule. Of course, in actual applications, the three-dimensional molecular graph data of the target proteolysis-inducing chimeric molecule can be stored in association with the predicted molecular property information.

[0083] The present invention further provides a molecular property prediction system, as shown in FIG.

[0084] FIG. 3 is a schematic diagram illustrating the architecture of a molecular property prediction system according to the present invention.

[0085] As can be seen from Figure 3, the system mainly consists of the following components: a memory subsystem that stores the above dataset and is used in actual applications to store information such as molecular property information predicted by the prediction model and its pharmaceutical and chemical properties; a control subsystem that predicts molecular property information of a target proteolysis-inducing chimeric molecule based on the three-dimensional molecular graph data of the target proteolysis-inducing chimeric molecule input to the subsystem; and a molecular property prediction unit that includes a molecular feature extraction unit and a molecular property prediction unit that determine atomic property information for each atom from the three-dimensional molecular graph data and predict molecular property information of the target proteolysis-inducing chimeric molecule, respectively.

[0086] The above is a method according to one or more embodiments of the present invention. Based on the same idea, the present invention further provides a corresponding model training apparatus and a molecular characteristic information prediction apparatus, as shown in Figures 4 and 5.

[0087] Figure 4 is a schematic diagram showing a model training device according to the present invention, which includes an acquisition module 401 for acquiring data on a specified proteolysis-inducing chimeric molecule, a construction module 402 for constructing three-dimensional molecular graph data of the specified proteolysis-inducing chimeric molecule based on the data, a prediction module 403 for inputting the three-dimensional molecular graph data of the specified proteolysis-inducing chimeric molecule into a prediction model to be trained and causing the prediction model to predict molecular characteristic information of the specified proteolysis-inducing chimeric molecule, and a training module 404 for training the prediction model based on the difference between the predicted molecular characteristic information and the actual molecular characteristic information corresponding to the specified proteolysis-inducing chimeric molecule.

[0088] Optionally, the molecular characteristic information includes at least one of the lipophilicity of the designated proteolytic chimeric molecule, the pH of the designated proteolytic chimeric molecule, the molecular weight of the designated proteolytic chimeric molecule, the hydrogen bond donors and hydrogen bond acceptors in the designated proteolytic chimeric molecule, the solubility of the designated proteolytic chimeric molecule, and the permeability of the designated proteolytic chimeric molecule.

[0089] Optionally, the construction module 402 specifically constructs an adjacency matrix corresponding to each atom, representing the edges between each atom node, for each atom contained in the specified proteolysis-induced chimeric molecule, and is used to obtain the three-dimensional molecular graph data of the specified proteolysis-induced chimeric molecule, and the adjacency matrix is used to represent the bonding information between each connected atom.

[0090] Optionally, an atom node of each atom included in the three-dimensional molecular graph data corresponds to node information, and the node information includes at least one of atom type information, atomic three-dimensional coordinate information, and nuclear charge number.

[0091] Optionally, for each atom included in the three-dimensional molecular graph data, the atom type information indicates to which atom the atom specifically belongs and is encoded using a one-hot encoding method, and the atomic three-dimensional coordinate information is the three-dimensional coordinate information of the atom in a predetermined three-dimensional coordinate system determined by projecting the atom onto the three-dimensional coordinate system, and the three-dimensional coordinate system includes a three-dimensional Cartesian coordinate system constructed with the molecular center of mass of the specified proteolysis-induced chimeric molecule as the coordinate origin.

[0092] Optionally, the prediction module 403 is specifically used to input the three-dimensional molecular graph data of the specified proteolysis-induced chimeric molecule into an embedding layer in the prediction model, obtain an embedding vector corresponding to the three-dimensional molecular graph data through the embedding layer, input the embedding vector into an information update layer in the prediction model to determine target invariant features and target mutated features of the specified proteolysis-induced chimeric molecule, input the final invariant features and final mutated features into an output layer in the prediction model, and output the molecular characteristic information of the specified proteolysis-induced chimeric molecule predicted by the output layer.

[0093] Optionally, the prediction module 403 specifically determines, for each atom in the specified proteolysis-induced chimeric molecule, atomic feature information corresponding to the atom based on the three-dimensional molecular graph data, where the atomic feature information includes at least one of the atom type information of the atom, the distance information between the atom and other atoms, and the neighboring atom information of the atom, and inputs the atomic feature information corresponding to each atom into an embedding layer in the prediction model, which is used by the embedding layer to obtain the embedding vector corresponding to the three-dimensional molecular graph data.

[0094] Optionally, the embedding vector includes initial invariant features, and the prediction module 403 is specifically used to determine attention weights corresponding to the initial invariant features by the information update layer, determine attention features corresponding to the specified proteolysis-induced chimeric molecule based on the attention weights, and determine the target invariant features and the target mutated features of the specified proteolysis-induced chimeric molecule based on the attention features by the information update layer.

[0095] Optionally, the prediction module 403 specifically obtains, by the information update layer, attention features corresponding to initial equivariant features and attention features corresponding to the initial invariant features, where the initial equivariant features are zero vectors, updates the attention features corresponding to the initial invariant features based on the attention features corresponding to the initial equivariant features to obtain updated initial invariant features, updates the attention features corresponding to the initial equivariant features based on the attention features corresponding to the initial invariant features to obtain updated initial equivariant features, determines, by the information update layer, the target invariant features based on the updated initial invariant features and the attention features corresponding to the initial invariant features, and is used to determine the target equivariant features based on the updated initial equivariant features, the updated initial invariant features, and the attention features corresponding to the initial invariant features.

[0096] Optionally, the prediction module 403 is specifically used to set the target equivariant feature and the target invariant feature as the final equivariant feature and the final invariant feature, respectively, in response to the number of information update layers being 1, and to set the target equivariant feature and the target invariant feature determined by the last information update layer of the prediction model as the final equivariant feature and the final invariant feature, respectively, in response to the number of information update layers being greater than 1.

[0097] Figure 5 is a schematic diagram showing a molecular characteristic information prediction device according to the present invention, which includes an acquisition module 501 for acquiring data on a target proteolysis-inducing chimeric molecule, a construction module 502 for constructing three-dimensional molecular graph data of the target proteolysis-inducing chimeric molecule based on the data, and a prediction module 503 for inputting the three-dimensional molecular graph data of the target proteolysis-inducing chimeric molecule into a pre-trained prediction model to have the prediction model predict the molecular characteristic information of the target proteolysis-inducing chimeric molecule, the prediction model being trained using the model training method described above.

[0098] The present invention further provides a computer-readable storage medium having a computer program stored thereon, which can be used to perform the model training method provided by Figure 1 or the molecular characteristic information prediction method provided by Figure 2. The computer-readable storage medium may be a non-volatile storage medium.

[0099] The present invention further provides a schematic diagram of the structure of an electronic device corresponding to Fig. 1 or Fig. 2, shown in Fig. 6. As shown in Fig. 6, the electronic device includes a processor, an internal memory, and a non-volatile memory, and may also include other hardware required for operation, such as a network interface, an internal bus, etc. The processor loads the corresponding computer program from the non-volatile memory into the internal memory and executes it to implement the model training method described in Fig. 1 or the molecular property information prediction method described in Fig. 2 above.

[0100] Of course, in addition to realization by software, the present invention does not exclude other realization methods, such as logical devices or a combination of hardware and software. In other words, the entity that executes the following processing process is not limited to each logical unit, but may also be hardware or a logical device.

[0101] In the 1990s, technological improvements could be clearly divided into hardware improvements (such as improvements to circuit structures like diodes, transistors, and switches) and software improvements (such as improvements to methodology). However, with technological advances, many current methodology improvements can be considered direct improvements to hardware circuit structures. Designers often obtain the corresponding hardware circuit structure by programming the improved methodology into the hardware circuit. Therefore, it is not necessarily true that methodology improvements cannot be realized using physical hardware modules. For example, programmable logic devices (PLDs) (e.g., field programmable gate arrays, or FPGAs) are such integrated circuits, whose logical functions are determined by user programming of the device. Instead of chip manufacturers designing and manufacturing dedicated integrated circuit chips, designers program and "integrate" digital systems onto a single PLD.Nowadays, instead of handcrafting integrated circuit chips, this programming is often achieved using software called a "logic compiler," which is similar to a software compiler used to write a program. To compile the original code, it must be written in a specific programming language called a Hardware Description Language (HDL). There is not just one HDL; there are many, including ABEL (Advanced Boolean Expression Language), AHDL (Altera Hardware Description Language), Confluence, CUPL (Cornell University Programming Language), HDCal, JHDL (Java Hardware Description Language), Lava, Lola, MyHDL, PALASM, and RHDL (Ruby Hardware Description Language). The most commonly used HDLs are VHDL (Very-High-Speed Integrated Circuit Hardware Description Language) and Verilog. It should be clear to those skilled in the art that a hardware circuit embodying a method flow can be easily obtained by simply logically programming the method flow in one of the above hardware description languages and programming it into an integrated circuit.

[0102] The controller may be implemented in any suitable manner. For example, the controller may take the form of a microprocessor or processor, a computer-readable storage medium storing computer-readable program code (e.g., software or firmware) executable by the (micro)processor, logic gates, switches, application-specific integrated circuits (ASICs), programmable logic controllers, and embedded microcontrollers. Examples of controllers include, but are not limited to, microcontrollers such as the ARC 625D, Atmel AT91SAM, Microchip PIC18F26K20, and Silicone Labs C8051F320. A memory controller may also be implemented as part of the control logic of a memory. It will be apparent to those skilled in the art that, in addition to implementing the controller purely with computer-readable program code, it is entirely possible to logically program method steps to cause the controller to perform the same functions in the form of logic gates, switches, application-specific integrated circuits, programmable logic controllers, embedded microcontrollers, and the like. Therefore, such a controller may be considered a hardware component, and the devices included therein for implementing various functions may also be considered structures within the hardware component. Alternatively, the apparatus for realizing various functions may be considered to be software modules for realizing methods or structures within hardware components.

[0103] The systems, devices, modules, or units described in the above embodiments may be specifically implemented by a computer chip, an entity, or a product having some function. A typical implementation device is a computer. Specifically, the computer may be, for example, a personal computer, a laptop computer, a mobile phone, a camera phone, a smartphone, a personal digital assistant, a media player, a navigation device, an email device, a game console, a tablet, a wearable device, or any combination of these devices.

[0104] For the sake of convenience, the above-described device will be described by dividing it into various units according to their functions. Of course, when implementing the present invention, the functions of each unit may be realized by the same or multiple pieces of software and / or hardware.

[0105] As will be appreciated by those skilled in the art, embodiments of the present invention may be provided as a method, a system, or a computer program product. Accordingly, the present invention may utilize embodiments consisting entirely of hardware, entirely of software, or a combination of software and hardware. Furthermore, the present invention may take the form of a computer program product embodied in one or more computer-usable storage media (including, but not limited to, magnetic disk memory, CD-ROM, optical memory, etc.) containing computer-usable program code.

[0106] The present invention will be described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each flow and / or block in the flowcharts and / or block diagrams, and combinations of flows and / or blocks in the flowcharts and / or block diagrams, may be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, whereby the instructions, executed by the processor of the computer or other programmable data processing device, generate an apparatus for implementing the functions specified in one or more flows in the flowcharts and / or one or more blocks in the block diagrams.

[0107] These computer program instructions may be stored in a computer-readable memory that can direct a computer or other programmable data processing device to operate in a particular manner, such that the instructions stored in the computer-readable memory result in an article of manufacture that includes an instruction apparatus that implements the functions specified in one or more flows of the flowcharts and / or one or more blocks of the block diagrams.

[0108] These computer program instructions may be loaded into a computer or other programmable data processing device, whereby a series of operational steps are executed on the computer or other programmable device to generate a computer-implemented process, whereby the instructions executed on the computer or other programmable device provide steps for implementing the functions specified in one or more flows of the flowcharts and / or one or more blocks of the block diagrams.

[0109] In a typical configuration, a computing device includes one or more processors (CPUs), input / output interfaces, network interfaces, and memory.

[0110] The memory may include volatile memory, random access memory (RAM), and / or non-volatile memory, such as read-only memory (ROM) or flash memory (flash RAM), among other computer-readable storage media. The memory is one example of a computer-readable storage medium.

[0111] Computer-readable storage media include nonvolatile and volatile media, removable and non-removable media, and may implement any method or technology for information storage. Information may be computer-readable instructions, data structures, program modules, or other data. Computer storage media include, but are not limited to, Phase Change Memory (PRAM), Static Random-Access Memory (SRAM), Dynamic Random Access Memory (DRAM), other types of Random Access Memory (RAM), Read-Only Memory (ROM), Electrically Erasable Programmable Read-Only Memory (EEPROM), flash memory or other memory technology, Compact Disc Read-Only Memory (CD-ROM), Digital Versatile Disc (DVD) or other optical storage, magnetic cassette tape, magnetic tape magnetic disk storage or other magnetic storage devices, or any other non-transmission medium that can be used to store information accessible by a computing device. As defined herein, computer readable storage media does not include transitory computer readable storage media, such as modulated data signals and carriers.

[0112] Additionally, the terms "comprise," "contain," or any other variation thereof, are intended to include a non-exclusive inclusion, whereby a process, method, article, or device that includes a set of elements not only includes those elements, but also includes other elements not expressly listed, or includes the inherent elements of such process, method, article, or device. Absent more limitations, elements qualified by the phrase "comprise..." do not exclude the presence of further identical elements in a process, method, article, or device that includes said elements.

[0113] As will be appreciated by those skilled in the art, embodiments of the present invention may be provided as a method, a system, or a computer program product. Accordingly, the present invention may utilize embodiments consisting entirely of hardware, entirely of software, or a combination of software and hardware. Furthermore, the present invention may take the form of a computer program product embodied in one or more computer-usable storage media (including, but not limited to, magnetic disk memory, CD-ROM, optical memory, etc.) containing computer-usable program code.

[0114] The invention may be described in the general context of computer-executable instructions, such as program modules, being executed by a computer. Generally, program modules include routines, programs, objects, components, data structures, etc. that perform particular tasks or implement particular abstract data types. The invention may also be practiced in distributed computing environments where tasks are performed by remote processing devices that are linked through a communications network. In a distributed computing environment, program modules may be located in both local and remote computer storage media, including memory storage devices.

[0115] Each embodiment of the present invention will be described in a stepwise manner, and the same or similar parts between the embodiments may be referred to each other, and the emphasis of each embodiment will be on the differences from other embodiments. In particular, the system embodiments will be described briefly because they are basically similar to the method embodiments, and the relevant parts may be referred to the description of some of the method embodiments.

[0116] The above is merely an example of the present invention and is not intended to limit the present invention. Those skilled in the art will appreciate that the present invention can be modified and changed in various ways. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principles of the present invention are intended to be included within the scope of the claims of the present invention.

Claims

1. acquiring data on the designated proteolysis-inducing chimeric molecule; constructing three-dimensional molecular graph data of the designated proteolysis-inducing chimeric molecule based on the data; inputting the three-dimensional molecular graph data of the designated proteolysis-inducing chimeric molecule into a prediction model to be trained, and having the prediction model predict molecular property information of the designated proteolysis-inducing chimeric molecule; training the prediction model based on the difference between the predicted molecular characteristic information and the actual molecular characteristic information corresponding to the designated proteolysis-directed chimeric molecule; A model training method comprising:

2. The molecular characteristic information includes at least one of the lipophilicity of the designated proteolytic chimeric molecule, the pH of the designated proteolytic chimeric molecule, the molecular weight of the designated proteolytic chimeric molecule, the hydrogen bond donor and hydrogen bond acceptor in the designated proteolytic chimeric molecule, the solubility of the designated proteolytic chimeric molecule, and the permeability of the designated proteolytic chimeric molecule.

2. The method of claim 1 .

3. The step of constructing three-dimensional molecular graph data of the designated proteolysis-inducing chimeric molecule based on the data includes: a step of constructing an adjacency matrix corresponding to each atom, with each atom contained in the designated proteolysis-inducing chimeric molecule as an atomic node, to represent edges between each atomic node, and obtaining the three-dimensional molecular graph data of the designated proteolysis-inducing chimeric molecule; The adjacency matrix is used to represent the bonding information between each connected atom.

2. The method of claim 1 .

4. an atomic node of each atom included in the three-dimensional molecular graph data corresponds to node information, and the node information includes at least one of atom type information, atomic three-dimensional coordinate information, and nuclear charge number; 4. The method of claim 3.

5. For each atom included in the three-dimensional molecular graph data, The atom type information indicates which atom the atom belongs to, and is encoded using one-hot encoding; the atomic three-dimensional coordinate information is three-dimensional coordinate information of the atom in a predetermined three-dimensional coordinate system, determined by projecting the atom onto the three-dimensional coordinate system, and the three-dimensional coordinate system includes a three-dimensional Cartesian coordinate system constructed with the molecular mass center of the designated proteolysis-inducing chimeric molecule as the coordinate origin; 5. The method of claim 4.

6. The step of inputting the three-dimensional molecular graph data of the designated proteolysis-inducing chimeric molecule into a prediction model to be trained and having the prediction model predict molecular characteristic information of the designated proteolysis-inducing chimeric molecule includes: inputting the three-dimensional molecular graph data of the designated proteolysis-inducing chimeric molecule into an embedding layer in the prediction model to obtain an embedding vector corresponding to the three-dimensional molecular graph data by the embedding layer; inputting the embedding vector into an information update layer in the prediction model to determine target invariant features and target mutated features of the designated proteolysis-induced chimeric molecule; inputting the final invariant features and the final equivariant features into an output layer in the prediction model, and outputting the molecular property information of the designated proteolysis-induced chimeric molecule predicted by the output layer; 2. The method of claim 1 .

7. The step of inputting the three-dimensional molecular graph data of the specified proteolysis-inducing chimeric molecule into an embedding layer in the prediction model to obtain an embedding vector corresponding to the three-dimensional molecular graph data by the embedding layer includes: determining, for each atom in the designated proteolysis-induced chimeric molecule, atomic feature information corresponding to the atom based on the three-dimensional molecular graph data, wherein the atomic feature information includes at least one of atom type information of the atom, distance information between the atom and other atoms, and neighboring atom information of the atom; inputting atomic feature information corresponding to each atom into an embedding layer in the prediction model to obtain the embedding vector corresponding to the three-dimensional molecular graph data through the embedding layer; 7. The method of claim 6.

8. The embedding vector includes initial invariant features, and the step of inputting the embedding vector into an information update layer in the prediction model to determine target invariant features and target mutated features of the specified proteolysis-induced chimeric molecule includes: determining, by the information update layer, attention weights corresponding to the initial invariant features, and determining attention features corresponding to the designated proteolysis-inducing chimeric molecule based on the attention weights; and determining, by the information update layer, the target invariant feature and the target mutated feature of the designated proteolysis-inducing chimeric molecule based on the attention feature.

7. The method of claim 6.

9. The step of determining the target invariant feature and the target mutated feature of the designated proteolysis-inducing chimeric molecule based on the attention feature by the information update layer includes: obtaining attention features corresponding to the initial equivariant features and attention features corresponding to the initial invariant features by the information update layer, where the initial equivariant features are zero vectors; updating the attention feature corresponding to the initial invariant feature based on the attention feature corresponding to the initial invariant feature to obtain an updated initial invariant feature; updating the attention feature corresponding to the initial equivariant feature based on the attention feature corresponding to the initial invariant feature to obtain an updated initial equivariant feature; determining, by the information update layer, the target invariant features based on the updated initial invariant features and attention features corresponding to the initial invariant features; and determining the target invariant features based on the updated initial invariant features, the updated initial invariant features, and attention features corresponding to the initial invariant features.

9. The method of claim 8.

10. In response to the number of the information update layers being 1, the target equivariant feature and the target invariant feature are set as the final equivariant feature and the final invariant feature, respectively; In response to the number of information update layers being greater than 1, the target equivariant features and the target invariant features determined by a last information update layer of the predictive model are set as the final equivariant features and the final invariant features, respectively.

7. The method of claim 6.

11. acquiring data on the targeted proteolysis-inducing chimeric molecule; constructing three-dimensional molecular graph data of the target proteolysis-inducing chimeric molecule based on the data; and inputting the three-dimensional molecular graph data of the target proteolysis-inducing chimeric molecule into a pre-trained prediction model to allow the prediction model to predict molecular characteristic information of the target proteolysis-inducing chimeric molecule, The predictive model is trained by a method according to any one of claims 1 to 10. A method for predicting molecular property information.

12. an acquisition module for acquiring data on the designated proteolysis-induced chimeric molecule; a construction module for constructing three-dimensional molecular graph data of the designated proteolysis-inducing chimeric molecule based on the data; a prediction module that inputs the three-dimensional molecular graph data of the designated proteolysis-inducing chimeric molecule into a prediction model to be trained, and causes the prediction model to predict molecular characteristic information of the designated proteolysis-inducing chimeric molecule; a training module for training the prediction model based on a difference between the predicted molecular characteristic information and the actual molecular characteristic information corresponding to the designated proteolysis-induced chimeric molecule; A model training device characterized by:

13. an acquisition module for acquiring data on the target proteolysis-inducing chimeric molecule; a construction module for constructing three-dimensional molecular graph data of the target proteolysis-inducing chimeric molecule based on the data; a prediction module for inputting the three-dimensional molecular graph data of the target proteolysis-inducing chimeric molecule into a pre-trained prediction model and causing the prediction model to predict molecular characteristic information of the target proteolysis-inducing chimeric molecule; The predictive model is trained by a method according to any one of claims 1 to 10. A molecular property information prediction device characterized by:

14. A computer-readable storage medium having stored thereon a computer program, the computer program being executed by a processor to perform the method of any one of claims 1 to 10. A computer-readable storage medium comprising:

15. A computer-readable storage medium having a computer program stored thereon, the computer program performing the method of claim 11 when executed by a processor. A computer-readable storage medium comprising:

16. An electronic device comprising a memory, a processor and a computer program stored in the memory and executable on the processor, the electronic device performing the method of any one of claims 1 to 10 when the processor executes the computer program. An electronic device characterized by:

17. 12. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, the computer program, when executed by the processor, performing the method of claim 11. An electronic device characterized by:

Images