Protein post-translational modification and disease association prediction system and method

Abstract

The invention discloses a protein post-translation modification and disease association prediction system and method, and relates to the field of bioinformatics and medical diagnosis, and the system comprises a data cleaning module which is used for obtaining sequence data related to protein post-translation modification and corresponding disease label data, and cleaning the sequence data; the feature extraction module is used for learning feature embedding of the sequence data and extracting feature vectors containing feature information; the association prediction module is used for converting feature vectors through a multi-head attention mechanism and performing association prediction of diseases through a Transform structure; the function definition module is used for defining a loss function according to the feature complexity and purpose of the biological information; and the model evaluation module is used for inputting the sequence data into the trained network model and outputting an evaluation result. According to the technical scheme, relevance prediction of protein post-translational modification and disease development can be achieved, and the method has high application value.

Description

Technical Field

[0001] The present invention relates to the fields of bioinformatics and medical diagnosis, and in particular to a system and method for predicting the association between protein post-translational modification and disease. Background Art

[0002] Nowadays, human research on life sciences has entered the "protein era". Protein is the material basis of all life. Its functional expression not only depends on its amino acid sequence, but also is affected by post-translational modification. In the biomedical field, protein post-translational modification is a key mechanism for regulating protein function. It plays a vital role in maintaining normal physiological functions of the human body and preventing diseases. With the occurrence and development of certain cancers, the phosphorylation of some specific proteins will show abnormal states. These abnormalities may cause uncontrolled cell growth and eventually form tumors.

[0003] By detecting the modification status of specific proteins, it is possible to provide a strong basis for the early diagnosis of tumors and other diseases. The construction of relevant databases, the maturity of bioinformatics, and the diversification of natural language models have made this type of method a reality. Traditional research on the prediction of disease functions by post-translational modification of proteins has only focused on the sequence information of post-translational modification sites of proteins, ignoring the understanding of changes in protein function. The physiological or pathological state of proteins largely reflects the pathological or abnormal conditions of the body. Most existing disease prediction methods rely on simple machine learning models that can handle the high complexity and diversity of post-translational modification sites of proteins in maintaining protein function.

[0004] Therefore, based on this problem, the present application proposes a system and method for predicting the association between protein post-translational modification and disease. Summary of the invention

[0005] Technical Purpose In order to solve the above problems, the purpose of the present invention is to provide a protein post-translational modification and disease association prediction system and method, which can not only mine the disease information that may be carried by protein post-translational modification sites, but also establish a prediction bridge between protein post-translational modification and disease through bioinformatics tools and machine learning models, while ensuring rationality and timeliness. The system and method have a wide range of application scenarios, provide new perspectives and methods for medical diagnosis, and promote the research on disease diagnosis and pathogenesis.

[0006] Technical Solution In order to achieve the above-mentioned purpose, the present invention provides a system and method for predicting the association between protein post-translational modification and disease, proposes an innovative method integrating the fields of bioinformatics and medical diagnosis, aims to predict the occurrence and development of diseases by analyzing the bioinformatics data of protein post-translational modification, pre-constructs a sequence data set containing protein post-translational modification sequences and their disease labels, extracts features from the sequence data through the Word2Vec structure, processes the extracted feature vectors according to the multi-head attention mechanism of the Transformer structure, combines the cross entropy loss function and L2 regularization to optimize the prediction model, and uses the Adam algorithm to optimize the model parameters, thereby realizing the mining and prediction of possible disease information carried by protein post-translational modification sites, and providing a reference for bioinformatics analysis and disease diagnosis.

[0007] In a first aspect, the present invention provides a protein post-translational modification and disease association prediction system, comprising: A data cleaning module is used to obtain sequence data related to protein post-translational modification and corresponding disease label data, and clean the sequence data; Feature extraction module, used to learn feature embedding of sequence data and extract feature vectors containing feature information; The association prediction module is used to transform feature vectors through a multi-head attention mechanism and perform disease association prediction through a Transformer structure; Function definition module, which is used to define the loss function according to the feature complexity and purpose of biological information, and optimize the loss function through the Adam algorithm; The model evaluation module is used to input sequence data into the trained network model and output the evaluation results.

[0008] Further, the sequence data is represented by X= , whose data distribution is , the disease label data is represented by Y= , whose data distribution is ; In the formula, The number of sequences that are post-translationally modified for the protein; is the number of relevant disease labels; X is the sequence of protein post-translational modification; Labels for related diseases.

[0009] Furthermore, for each protein post-translational modification event, the data cleaning module cuts and expands the sequence data centered on the modified amino acid.

[0010] Furthermore, the data cleaning module cuts and expands the sequence data based on the length of 15 amino acids, centered on the modified amino acid, and fills blank positions with the placeholder "_" during the expansion process.

[0011] Furthermore, the data cleaning module performs data cleaning in a manner that also includes operations such as protein post-translational modification type specification and redundant data deletion.

[0012] Furthermore, the feature extraction module learns feature embedding of sequence data by predicting context through a feature extractor. In addition to words that are a group of single amino acids, the corpus of the feature extractor also contains words that are a group of three consecutive amino acids. The feature extraction is achieved by converting the words in the corpus into feature vectors containing feature information. The feature vector extraction process is shown in the following formula:

[0013] In the formula, h is the feature vector, which represents the vector representation of a specific word in the feature space; T(x) represents the original input feature set; is an N-dimensional vector representing the i-th row in the hidden layer W.

[0014] Furthermore, the feature extractor is a Word2Vec structure.

[0015] Furthermore, the specified vector size in the feature extractor is 100 and the sliding window size is 5.

[0016] The Word2Vec structure is used to convert amino acid sequences into feature vectors rich in semantic information, which can better represent the context and biological characteristics of the sequence.

[0017] Furthermore, the association prediction module converts the feature vector in a specific manner by converting the feature vector of large dimension into multiple batches of feature vectors of small dimension. The feature vector is output as the association prediction result after passing through a multi-layer encoder cycle and a classifier composed of linear layers. The calculation process is shown in the following formula:

[0018] In the formula, is the probability value predicted by the model; classifier is the classifier; F represents the feature transformation part, which converts the original input T(x) into a form that the model can process; T(x) represents the original input feature set.

[0019] Furthermore, the predictor in the association prediction module is specifically a Transformer structure.

[0020] Furthermore, the hidden layer dimension of the position encoding part in the predictor is 256, and the number of multiple heads is 10.

[0021] The Transformer structure is used to capture the complex patterns and relationships in protein post-translational modification sequences, thereby improving the accuracy of system disease prediction. The multi-head attention mechanism is used to process high-dimensional feature vectors, thereby reducing noise and improving the generalization ability of the model.

[0022] Furthermore, the main body of the loss function is the cross entropy function, as shown in the following formula:

[0023] In the formula, is the probability value predicted by the model; is the value of the true label; The cross entropy loss function is used to quantify the difference between the model's predicted probability distribution and the true disease label, thereby improving the accuracy of disease prediction.

[0024] L2 regularization is added during the calculation of the loss function. The calculation formula of L2 regularization is as follows:

[0025] In the formula, is the weight attenuation coefficient; is the total number of features; is the weight vector of the model.

[0026] Furthermore, the attenuation coefficient of the L2 regularization is 0.25, and the cycle consistency loss is achieved through the L1 norm.

[0027] L2 regularization is used to penalize excessive weight values, reduce overfitting of the model to the training data, and improve the generalization ability of the model.

[0028] Furthermore, the function definition module optimizes the loss function based on accuracy, and updates and optimizes the weights of the parameter matrices of each layer during the back-propagation training of the model.

[0029] Furthermore, the weight attenuation loss of the learner is updated by the Adam algorithm, and the learning rate is reduced in steps according to the learning rate adjustment strategy, where the gamma value is 0.25 and the step size is 4.

[0030] Furthermore, in the process of the model evaluation module inputting sequence data into the network model, the Encoders of the Transformer structure perform multi-head learning and gradually evolve, so as to determine the optimal values ​​of the network model parameters, and finally reach a dynamic balance, complete the training of the network model and output the evaluation results.

[0031] Furthermore, feature extraction and association prediction are performed in each cycle and the loss value is calculated, and the gradient clipping strategy is executed after each round of back propagation to update the parameters of the predictor.

[0032] Furthermore, the settings of hyperparameters include: batch size is 32; training is 50 epochs; learning rate is 0.00025; number of input channels is 15; number of threads is 4.

[0033] Furthermore, the authenticated sequence data is input into the trained restoration network model to obtain the final evaluation result.

[0034] Further, the system also includes a temporal prediction module for learning feature representations of protein sequences by capturing temporal dependencies and contextual information in sequence data; The update formula of the hidden state is as follows:

[0035] In the formula, is the time step The hidden state of is the weight matrix between hidden states, used to transfer the information of the previous time step; is the time step The hidden state of is the weight matrix between input and hidden state; is the time step The input feature vector of The weight matrix is ​​a unique feature of protein post-translational modification, which is used to capture the specific biological characteristics of protein post-translational modification sites; is the time step The protein post-translational modification-specific feature vector; is the bias term; is an activation function used to introduce nonlinearity.

[0036] By capturing time dependency and contextual information to identify key functional regions and domains in protein sequences, the model can understand the function of the protein and its role in disease. By analyzing the contextual information in the sequence, the model can more accurately predict protein post-translational modification sites, thereby improving the accuracy of disease association predictions.

[0037] In a second aspect, the present invention further provides a method for predicting the association between protein post-translational modification and disease, the method being based on the system described in the first aspect, comprising: Step 1: Obtain sequence datasets related to protein post-translational modifications and corresponding disease label datasets; Step 2: Clean the sequence data set, cut and expand the sequence data set, and use the placeholder "_" if there is a blank position; Step 3: Learn the feature embedding of the sequence data and extract the feature vector containing the feature information; Step 4: Transform the feature vector through the multi-head attention mechanism and perform disease association prediction through the Transformer structure; Step 5: Define the loss function according to the feature complexity and purpose of biological information, and optimize the loss function through the Adam algorithm; Step 6: Input the sequence test set into the network model for training, gradually evolve, determine the optimal values ​​of the network model parameters, and finally reach a dynamic balance to complete the training of the network model; Step 7: Input the sequence data to be predicted into the network model and output the evaluation results.

[0038] In a third aspect, the present invention also provides a computer device, comprising a processor and a memory, wherein the processor is connected to the memory, the memory is used to store a computer program, and the processor is used to execute the computer program stored in the memory, so that the computer device performs at least one step of the aforementioned method for predicting the association between post-translational modification of protein and disease.

[0039] In a fourth aspect, the present invention further provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, at least one step of the aforementioned method for predicting the association between protein post-translational modification and disease is implemented.

[0040] The present invention pre-constructs a sequence data set containing protein post-translational modification sequences and their disease labels, extracts features from the sequence data through the Word2Vec structure, and processes the extracted feature vectors according to the multi-head attention mechanism of the Transformer structure; combines the cross entropy loss function and L2 regularization to optimize the prediction model, and uses the Adam algorithm to optimize the model parameters; learns the feature representation of protein sequences by capturing the time dependency and context information in the sequence data. The system and method have a wide range of application scenarios, provide new perspectives and methods for medical diagnosis, and promote the research on disease diagnosis and pathogenesis.

[0041] Beneficial Effects By implementing the protein post-translational modification and disease association prediction system and method provided by the present invention, the following technical effects are achieved: (1) The present invention pre-constructs a sequence data set containing protein post-translational modification sequences and their disease labels, extracts features from the sequence data using the Word2Vec structure, and processes the extracted feature vectors using the multi-head attention mechanism of the Transformer structure. The Word2Vec structure converts the amino acid sequence into a feature vector rich in semantic information, which can better represent the context and biological characteristics of the sequence; the Transformer structure captures the complex patterns and relationships in the protein post-translational modification sequence, which improves the accuracy of system disease prediction; and the multi-head attention mechanism processes high-dimensional feature vectors, which reduces noise and improves the generalization ability of the model.

[0042] (2) The cross entropy loss function and L2 regularization are combined to optimize the prediction model, and the Adam algorithm is used to optimize the model parameters. The cross entropy loss function quantifies the difference between the model prediction probability distribution and the true disease label, which improves the accuracy of disease prediction; L2 regularization penalizes excessive weight values, reduces the overfitting of the model to the training data, and improves the generalization ability of the model.

[0043] (3) Learn the feature representation of protein sequences by capturing the time dependency and context information in the sequence data. By capturing the time dependency and context information to identify the key functional regions and domains in the protein sequence, it helps the model understand the function of the protein and its role in the disease; by analyzing the context information in the sequence, the model can more accurately predict the protein post-translational modification sites, thereby improving the accuracy of disease association prediction. BRIEF DESCRIPTION OF THE DRAWINGS

[0044] In order to make the above-mentioned protein post-translational modification and disease association prediction system and method of the present invention more obvious and easy to understand, the drawings required for use in the specific embodiments of the present invention are briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative work.

[0045] Figure 1 A schematic diagram showing the flow of the method for predicting the association between protein post-translational modification and disease; Figure 2 A schematic diagram showing the data acquisition and cleaning process; Figure 3 Represents a schematic diagram of the Word2Vec structure; Figure 4 Schematic diagram showing the principle of association prediction. DETAILED DESCRIPTION

[0046] Embodiment 1: A protein post-translational modification and disease association prediction system and method are provided. The protein post-translational modification and disease association prediction system includes: a data cleaning module, a feature extraction module, an association prediction module, a function definition module and a model evaluation module. The protein post-translational modification and disease association prediction method flow chart is as follows Figure 1 As shown, the protein post-translational modification and disease association prediction system and method are specifically described in the following steps.

[0047] The data cleaning module is used to obtain sequence data related to protein post-translational modification and corresponding disease label data, and clean the sequence data. The data acquisition and cleaning process is as follows: Figure 2 shown.

[0048] The sequence data is represented by X= , whose data distribution is , the disease label data is represented by Y= , whose data distribution is ; In the formula, The number of sequences that are post-translationally modified for the protein; is the number of relevant disease labels; X is the sequence of protein post-translational modification; Labels for related diseases.

[0049] For each protein post-translational modification event, the data cleaning module cuts and expands the sequence data centered on the modified amino acid.

[0050] The data cleaning module cuts and expands the sequence data based on the length of 15 amino acids before and after the modified amino acid, and fills the blank positions with the placeholder "_" during the expansion process.

[0051] The data cleaning module also performs data cleaning in a manner that includes protein post-translational modification type specification, redundant data deletion, and other operations.

[0052] The feature extraction module is used to learn the feature embedding of sequence data and extract feature vectors containing feature information.

[0053] The feature extraction module learns feature embedding of sequence data by predicting context through a feature extractor. In addition to words that are a group of single amino acids, the corpus of the feature extractor also contains words that are a group of three consecutive amino acids. The feature extraction is achieved by converting the words in the corpus into feature vectors containing feature information. The feature vector extraction process is shown in the following formula:

[0054] In the formula, h is the feature vector, which represents the vector representation of a specific word in the feature space; T(x) represents the original input feature set; is an N-dimensional vector representing the i-th row in the hidden layer W.

[0055] The feature extractor is a Word2Vec structure, and the Word2Vec structure is as follows: Figure 3 shown.

[0056] The specified vector size in the feature extractor is 100 and the sliding window size is 5.

[0057] The association prediction module is used to transform feature vectors through the multi-head attention mechanism and perform disease association prediction through the Transformer structure. The association prediction principle is as follows Figure 4 shown.

[0058] The association prediction module converts the feature vector in a specific way by converting the feature vector of large dimension into multiple batches of feature vectors of small dimension. The feature vector is output as the association prediction result after passing through a multi-layer encoder cycle and a classifier composed of linear layers. The calculation process is shown in the following formula:

[0059] In the formula, is the probability value predicted by the model; classifier is the classifier; F represents the feature transformation part, which converts the original input T(x) into a form that the model can process; T(x) represents the original input feature set.

[0060] The predictor in the association prediction module is specifically a Transformer structure.

[0061] The hidden layer dimension of the position encoding part in the predictor is 256, and the number of multiple heads is 10.

[0062] The function definition module is used to define the loss function according to the characteristic complexity and purpose of biological information, and optimize the loss function through the Adam algorithm.

[0063] The main body of the loss function is the cross entropy function, as shown in the following formula:

[0064] In the formula, is the probability value predicted by the model; is the value of the true label; L2 regularization is added during the calculation of the loss function. The calculation formula of L2 regularization is as follows:

[0065] In the formula, is the weight attenuation coefficient; is the total number of features; is the weight vector of the model.

[0066] The decay coefficient of the L2 regularization is 0.25, and the cycle consistency loss is implemented by the L1 norm.

[0067] The function definition module optimizes the loss function based on accuracy, and during the back-propagation training process of the model, updates and optimizes the weights of the parameter matrices of each layer.

[0068] The weight attenuation loss of the learner is updated through the Adam algorithm, and the learning rate is reduced in steps according to the learning rate adjustment strategy, where the gamma value is 0.25 and the step size is 4.

[0069] The model evaluation module is used to input sequence data into the trained network model and output the evaluation results.

[0070] In the process of the model evaluation module inputting sequence data into the network model, the Encoders of the Transformer structure perform multi-head learning and gradually evolve, so as to determine the optimal values ​​of the network model parameters, and finally achieve dynamic balance, complete the training of the network model and output the evaluation results.

[0071] In each cycle, feature extraction and association prediction are performed and the loss value is calculated. After each round of backpropagation, the gradient clipping strategy is performed to update the parameters of the predictor.

[0072] The settings of hyperparameters include: batch size is 32; training is 50 epochs; learning rate is 0.00025; number of input channels is 15; number of threads is 4.

[0073] The authenticated sequence data is input into the trained restoration network model to obtain the final evaluation result.

[0074] Embodiment 2: Based on the above-mentioned embodiment, the system adds a time series prediction module for learning the feature representation of protein sequences by capturing the time dependency and context information in the sequence data.

[0075] Protein sequences with protein post-translational modification sites are collected, and sequences with similarity exceeding a certain threshold are removed using a protein sequence clustering tool. The de-redundant protein sequences are then cleaned and site annotation information with low credibility is deleted.

[0076] The length of the protein sequence is normalized by zero padding or clipping, and the protein sequence is encoded.

[0077] Feature extraction module is used to extract features from protein sequences.

[0078] The recurrent neural network model is designed with a dynamic "series" structure to improve the average sensitivity of the model, where the update formula of the hidden state is as follows:

[0079] In the formula, is the time step The hidden state of is the weight matrix between hidden states, used to transfer the information of the previous time step; is the time step The hidden state of is the weight matrix between input and hidden state; is the time step The input feature vector of The weight matrix is ​​a unique feature of protein post-translational modification, which is used to capture the specific biological characteristics of protein post-translational modification sites; is the time step The protein post-translational modification-specific feature vector; is the bias term; is an activation function used to introduce nonlinearity.

[0080] The Adam optimizer in the function definition module is used to update the gradient of the recurrent neural network, and the loss function still uses the cross entropy function.

[0081] Early stopping was used to prevent the model from overfitting.

[0082] The protein sequence to be tested is input into the recurrent neural network model to predict the correlation between protein post-translational modification and disease.

[0083] For example, suppose the following data exists: The protein sequence is A, represented by one-hot encoding; the protein post-translational modification feature is none, represented by a zero vector; the disease label is 1, indicating that the patient has a disease.

[0084] Assume the following parameters: ; ; ; ; ; .

[0085] Initialize hidden state , time step 1: Input Features : of Encoding, assuming (a 20-dimensional vector with only the first position being 1); Protein post-translational modification characteristics : ; For hidden state Calculation: ; According to the hidden state Calculated output: .

[0086] According to the output results, the patient's probability of getting the disease is about 70%.

[0087] The effect of the timing prediction module is shown in Table 1.

[0088] Table 1. Summary of timing prediction modules index Before deep learning module application After deep learning module application Test mean square error high Low Prediction accuracy Low high Ability to handle long sequences limited powerful Short-term memory none have Training complexity Low high Demand for large-scale data Low high According to the experimental table, the deep learning model requires a larger data set and a more complex training process to learn features, but its mean square error during testing is lower, which means that the application of this model can make the prediction results closer to the true value and improve the accuracy of the prediction. After the model is applied, the system has a stronger ability to process long sequence data and has short-term memory capabilities, which is helpful for processing and analyzing sequence data.

[0089] It will be appreciated by those skilled in the art that embodiments of the present invention may be provided as methods, systems or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present invention may take the form of a computer program product implemented on one or more computer-usable non-transient storage media containing computer-usable program code.

[0090] The present invention can provide computer program instructions to a processor of a general-purpose computer, a special-purpose computer, an embedded processor or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device produce means for implementing the system.

[0091] These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer-readable memory produce a product including an instruction device that implements the functions of the system.

[0092] These computer program instructions may also be loaded onto a computer or other programmable data processing device so that a series of operational steps are executed on the computer or other programmable device to produce a computer-implemented process, whereby the instructions executed on the computer or other programmable device provide steps for implementing the functions of the system.

Claims

1. A protein post-translational modification and disease association prediction system, characterized in that: include: A data cleaning module is used to obtain sequence data related to protein post-translational modification and corresponding disease label data, and clean the sequence data; Feature extraction module, used to learn feature embedding of sequence data and extract feature vectors containing feature information; The association prediction module is used to transform feature vectors through a multi-head attention mechanism and perform disease association prediction through a Transformer structure; Function definition module, which is used to define the loss function according to the feature complexity and purpose of biological information, and optimize the loss function through the Adam algorithm; The model evaluation module is used to input sequence data into the trained network model and output the evaluation results.

2. The system according to claim 1, characterized in that: For each protein post-translational modification event, the data cleaning module cuts and expands the sequence data centered on the modified amino acid.

3. The system according to claim 1, characterized in that: The feature extraction module learns feature embedding of sequence data by predicting context through a feature extractor. In addition to words that are a group of single amino acids, the corpus of the feature extractor also contains words that are a group of three consecutive amino acids. The feature extraction is achieved by converting the words in the corpus into feature vectors containing feature information. The feature vector extraction process is shown in the following formula: In the formula, h is the feature vector, which represents the vector representation of a specific word in the feature space; T(x) represents the original input feature set; is an N-dimensional vector representing the i-th row in the hidden layer W.

4. The system according to claim 1, characterized in that: The association prediction module converts the feature vector in a specific way by converting the feature vector of large dimension into multiple batches of feature vectors of small dimension. The feature vector is output as the association prediction result after passing through a multi-layer encoder cycle and a classifier composed of linear layers. The calculation process is shown in the following formula: In the formula, is the probability value predicted by the model; classifier is the classifier; F represents the feature transformation part, which converts the original input T(x) into a form that the model can process; T(x) represents the original input feature set.

5. The system according to claim 1, characterized in that: The main body of the loss function is the cross entropy function, as shown in the following formula: In the formula, is the probability value predicted by the model; is the value of the true label; L2 regularization is added during the calculation of the loss function. The calculation formula of L2 regularization is as follows: In the formula, is the weight attenuation coefficient; is the total number of features; is the weight vector of the model.

6. The system according to claim 1, characterized in that: The system also includes a temporal prediction module for learning feature representations of protein sequences by capturing temporal dependencies and contextual information in sequence data.

7. A method for predicting the association between protein post-translational modification and disease, characterized in that: The method is implemented based on the system according to any one of claims 1 to 6: The method comprises: Step 1: Obtain sequence datasets related to protein post-translational modifications and corresponding disease label datasets; Step 2: Clean the sequence data set, cut and expand the sequence data set, and use the placeholder "_" if there is a blank position; Step 3: Learn the feature embedding of the sequence data and extract the feature vector containing the feature information; Step 4: Transform the feature vector through the multi-head attention mechanism and perform disease association prediction through the Transformer structure; Step 5: Define the loss function according to the feature complexity and purpose of biological information, and optimize the loss function through the Adam algorithm; Step 6: Input the sequence test set into the network model for training, gradually evolve, determine the optimal values ​​of the network model parameters, and finally reach a dynamic balance to complete the training of the network model; Step 7: Input the sequence data to be predicted into the network model and output the evaluation results.

8. A computer device comprising a processor and a memory, wherein the processor is connected to the memory, and the memory is used to store a computer program, wherein: The processor is configured to execute the computer program stored in the memory, so that the computer device performs at least one step of the method according to claim 7.

9. A computer-readable storage medium, wherein a computer program is stored in the computer-readable storage medium, characterized in that: When the computer program is executed, at least one step of the method of claim 7 is implemented.

Images