Method for predicting inhibitory activity of chemical on DNA gyrase

Abstract

The invention discloses a method for predicting the inhibitory activity of a chemical on DNA gyrase, which comprises the following steps of: obtaining a chemical structure and inhibitory activity data of the chemical structure on GyrA and GyrB from a public database, cleaning and scaling the structure, and dividing the obtained known data into a training set and a test set; constructing a multi-task graph neural network model taking the chemical SMILES codes as input; using the training set to determine an optimal hyper-parameter of the multi-task graph neural network model through cross validation so as to obtain an optimal inhibition activity prediction model; and obtaining predicted values of the scaling values of the inhibitory activity data of the to-be-evaluated chemicals to the GyrA and the GyrB by using the inhibitory activity prediction model. According to the method, the inhibition effect of environmental chemicals on GyrA and GyrB can be predicted at the same time only by inputting the molecular structure of the compound, rapid screening of molecular initial events of pollutants possibly inducing bacterial quinolone drug resistance is achieved, and the method has a wide application prospect.

Description

Technical Field

[0001] The invention relates to the technical field of chemical-induced bacterial resistance assessment, and in particular to a method for predicting the inhibitory activity of chemicals on DNA gyrase. Background Art

[0002] Since DNA gyrase is a key target for inducing quinolone resistance, the interaction between pollutants and DNA gyrase will also determine their ability to induce quinolone resistance. Pollutants with specific structures can inhibit DNA gyrase, thereby inhibiting DNA replication and inducing DNA damage, followed by a series of SOS and responses of the DNA replication and repair systems, ultimately leading to target mutations, thereby producing quinolone resistance. Therefore, rapid screening of environmental pollutants with DNA gyrase inhibitory activity is the key to identifying high-risk pollutants with the ability to induce bacterial quinolone resistance.

[0003] A large number of chemicals are added to industrial products and daily necessities. Therefore, computational methods are needed to speed up the screening of high-risk pollutants with the ability to induce bacterial quinolone resistance. Traditional methods for predicting the inhibitory activity of chemicals on proteins are mainly divided into two categories, namely ligand-based methods and receptor-based methods. The ligand-based method is to judge the potential effect of chemicals by comparing the structure with known active ligands. The ligand-based method is simple and effective under the condition of high ligand similarity, but due to the limitation of the known ligand structure space, the scope of application and accuracy of this method are restricted. The receptor-based method mainly uses molecular docking to judge the interaction mode between ligand and target protein by calculating the three-dimensional structure and interaction energy of the ligand-receptor complex. Although the receptor-based method fully considers the three-dimensional structural characteristics of the target protein, there are still some technical problems that have not been well solved. For example, the conformational flexibility of the protein, the accuracy of the scoring function, the solvent effect of water molecules, etc., all of which will affect the accuracy of the docking results.

[0004] Traditional methods for predicting the inhibitory activity of chemicals on proteins have problems such as low accuracy and a small scope of application. Therefore, it is urgent to propose and develop new methods for evaluating the inhibitory activity of chemicals on DNA gyrase to meet the needs of rapid screening of high-risk pollutants with the ability to induce bacterial quinolone resistance. In fact, with the rise of deep learning methods, methods for predicting chemical properties based on feature learning have gradually developed. This is because feature learning-based methods can apply deep learning algorithms to learn the characteristics of chemicals with known DNA gyrase inhibitory activity and infer the DNA gyrase inhibitory activity of unknown chemicals. In addition, relevant studies have shown that deep learning models perform better than molecular docking models and other machine learning models.

[0005] In summary, a deep learning model that can fully learn the characteristics of chemicals is needed to achieve direct mapping of chemical structure to properties and realize rapid screening of chemicals with DNA gyrase inhibitory activity. Limited by the amount of data from existing GyrB enzyme inhibition experiments, ordinary deep learning methods are difficult to further improve the prediction accuracy of the model and cannot accurately predict the inhibitory activity of chemicals on GyrB. Therefore, in order to further improve the prediction performance of the model on small samples, a multi-task model that shares part of the network structure was established, which can realize the inhibitory activity data (IC 50 ), it can improve the learning ability of the model and prevent overfitting by sharing parameters between tasks. Especially when the tasks are highly correlated, the GyrB prediction task can make full use of the feature expression of the GyrA prediction task and achieve better results than single-task learning. Summary of the invention

[0006] The purpose of the present invention is to provide a method for predicting the inhibitory activity of chemicals on DNA gyrase in view of the deficiencies of the prior art.

[0007] The object of the present invention is achieved through the following technical scheme: a method for predicting the inhibitory activity of a chemical on DNA gyrase, wherein the DNA gyrase includes GyrA and GyrB, and the method comprises the following steps:

[0008] S1. Obtain chemical structures and inhibitory activity data of chemicals on GyrA and GyrB, perform structural cleaning operations on chemical structures, perform scaling operations on inhibitory activity data of GyrA and GyrB to construct a data set, and randomly divide the data set into a training set and a test set in proportion;

[0009] S2. Construct a multi-task graph neural network model with chemical SMILES codes as input, and its output is the predicted value of the scaled value of the inhibitory activity data of chemicals on GyrA and GyrB;

[0010] S3. Use cross-validation to determine the optimal hyperparameters of the multi-task graph neural network model, and use the training set to train it to obtain the trained optimal multi-task graph neural network model, which is used as a DNA gyrase inhibitory activity prediction model to predict the inhibitory activity data scaling values ​​of chemicals on GyrA and GyrB;

[0011] S4. Input the SMILES code of the chemical to be tested in the test set or the SMILES code of the chemical to be evaluated into the DNA gyrase inhibitory activity prediction model to obtain the predicted value of the inhibitory activity data scaling value of the chemical on GyrA and GyrB.

[0012] Furthermore, the step S1 includes the following sub-steps:

[0013] S1.1. Obtain chemical structures and inhibitory activity data of chemicals against GyrA and GyrB from public databases; the chemical structures are chemical SMILES codes, and the inhibitory activity data are used to indicate the inhibitory activity of chemicals against GyrA and GyrB;

[0014] S1.2. Performing structure cleaning operations on chemical structures, specifically including: standardizing, removing solvents, charge correction, and deionizing chemical molecular structure cleaning operations on chemical SMILES codes to standardize and unify the form of chemical SMILES codes; wherein, the above-mentioned structure cleaning operations can perform molecular structure inspection processing to ensure that the structure of the molecule is chemically reasonable; correct drawing errors and standardize functional groups; hide hydrogen atoms; recalculate stereochemistry; remove covalently bonded impurities; ensure that the strongest acid group is ionized first; produce neutral molecules; standardize tautomers; remove salts and covalently bound metals contained in the compound;

[0015] S1.3, performing a scaling operation on the numerical range of the inhibitory activity data of the chemical on GyrA and GyrB by taking the negative logarithm of the original numerical value of the inhibitory activity data of the chemical on GyrA and GyrB;

[0016] S1.4, constructing GyrA and GyrB data sets according to the chemical SMILES codes after the structure cleaning operation in step S1.2 and the inhibitory activity data of GyrA and GyrB after the scaling operation in step S1.3;

[0017] S1.5. Randomly divide the GyrA and GyrB datasets into training and test sets in proportion.

[0018] Furthermore, the multi-task graph neural network model includes a task-specific input layer, a molecular graph embedding layer, a molecular fragment graph embedding layer, multiple molecular graph neural network encoders, multiple molecular fragment graph neural network encoders, a dual-path combiner and a task-specific predictor, wherein the task-specific input layer includes a parallel GyrA task input layer and a GyrB task input layer, the molecular graph neural network encoder and the molecular fragment graph neural network encoder are both composed of a neighborhood attention module, an information aggregation module, a gating mechanism update node feature module and a feature attention module, and the feature attention module includes a maximum pooling layer, a sum pooling layer, a multi-layer perceptron global pooling layer and an activation function; the dual-path combiner selects a graph convolutional attention layer, and the graph convolutional attention layer includes multiple attention heads and a ReLU activation function; the task-specific predictor includes 2 prediction heads, each of which includes n prediction heads. l Fully connected layer.

[0019] Further, the task-specific input layer extracts data of GyrA and GyrB respectively through the parallel GyrA task input layer and the GyrB task input layer and inputs the data into the shared network of the multi-task graph neural network model for subsequent reasoning, wherein the shared network of the multi-task graph neural network model includes a molecular graph embedding layer, a molecular fragment graph embedding layer, a plurality of molecular graph neural network encoders, a plurality of molecular fragment graph neural network encoders and a dual-pathway combiner;

[0020] The molecular graph embedding layer calculates the molecular graph of the chemical according to the chemical SMILES code by using RDKit to extract the molecular graph features from the molecular graph; wherein the molecular graph features include a×d at The atomic feature matrix, the adjacency matrix of length b, and the b×d bt The chemical bond characteristic matrix is: a is the number of atoms in the chemical, b is twice the number of chemical bonds in the chemical, and d is at is the number of atomic features, d bt is the number of chemical bond features, and the adjacency matrix is ​​used to represent the atomic numbers of the bonding atom pairs in the molecular graph;

[0021] The molecular fragment graph embedding layer calculates the molecular graph of the chemical according to the SMILES code of the chemical by using RDKit, and extracts the molecular fragment features from the molecular graph based on the BRICS principle; wherein the molecular fragment features include a×d at The atomic feature matrix of length b f The molecular fragment adjacency matrix, b f ×d bt The chemical bond feature matrix of the molecular fragments and the molecular fragment index list of length a, where b f It is twice the number of chemical bonds remaining after the molecule is broken into molecular fragments. The molecular fragment index list is used to indicate the index of the molecular fragment where each atom in the chemical is located;

[0022] The various molecular graph features and molecular fragment features extracted from the molecular graph embedding layer and the molecular fragment graph embedding layer are first transformed into a length of d h Then, each type of feature vector is input into the molecular graph neural network encoder and the molecular fragment graph neural network encoder to obtain the molecular graph feature sequence and the molecular fragment feature sequence, respectively. hThe length of is the same as the size of the hidden layer; wherein, in the molecular graph neural network encoder and the molecular fragment graph neural network encoder, the molecular graph neural network encoder and the molecular fragment graph neural network encoder update the node features of the molecular graph and the molecular fragment graph through their respective neighborhood attention modules and information aggregation modules, and then update the node feature module through a gating mechanism to balance between retaining the original information and using the new information, and in the feature attention module, the global features of the molecular graph are extracted through the maximum pooling layer and the sum pooling layer, and the attention weights are generated by the multi-layer perceptron, and the features of the nodes are weighted and adjusted, and finally the features of all nodes are aggregated into a global feature vector through the global pooling layer and the activation function, so as to obtain the molecular graph feature sequence and the molecular fragment feature sequence;

[0023] The molecular graph feature sequence and the molecular fragment feature sequence are input into the dual-path combiner. The dual-path combiner uses the graph convolution attention layer to learn the relationship between the molecular graph feature sequence and the molecular fragment feature sequence. Specifically, it adopts n h Each attention head independently calculates the attention weights of different molecular fragments, and performs nonlinear transformation through the ReLU activation function to obtain the molecule-molecular fragment interaction feature sequence;

[0024] Then, the molecule-molecule fragment interaction feature sequence and the molecular graph feature sequence output by the molecular graph neural network encoder are concatenated and input into the task-specific predictor, respectively, after passing through the n prediction heads of the two prediction heads. l After the fully connected layers, the predicted values ​​of the inhibitory activity data scaling values ​​of the chemicals on GyrA and GyrB are output respectively.

[0025] Furthermore, the step S3 includes the following sub-steps:

[0026] S3.1. Preset multiple sets of different model hyperparameters as {lr, weight-decay, batchsize_a, batchsize_b, dropout, depth, feature-dimension, n-slices, r}, where lr is the learning rate, weight-decay is the weight decay parameter, batchsize_a and batchsize_b are the number of samples of GyrA and GyrB selected for one training, dropout is the random dropout regularization parameter, depth is the number of encoder layers, feature-dimension is the size of the hidden layer, n-slices is the number of slices, r is the decay rate, lr is used to control the progress of convergence to the local minimum, weight-decay and dropout are used to prevent model overfitting, depth, feature-dimension, n-slices and r are used to adjust the model complexity, and the size of batchsize_a and batchsize_b affects the optimization degree and speed of the model;

[0027] S3.2. For each set of model hyperparameters, use the GyrA and GyrB data in the training set to train a multi-task graph neural network model. f The multi-task graph neural network model corresponding to the set of model hyperparameters was evaluated by fold cross-validation based on statistical parameters to determine the optimal model hyperparameters, and the trained multi-task graph neural network model corresponding to the optimal model hyperparameters was obtained, which was used as a DNA gyrase inhibitory activity prediction model to predict the inhibitory activity data scaling values ​​of chemicals on GyrA and GyrB.

[0028] Furthermore, the statistical parameter is one of a coefficient of determination, a root mean square error, a mean square error, and a mean absolute error.

[0029] Furthermore, for each set of model hyperparameters, the multi-task graph neural network model is trained using the data in the training set, through n f The fold cross validation evaluates the multi-task graph neural network model corresponding to the set of model hyperparameters based on statistical parameters to determine the optimal model hyperparameters, including:

[0030] S3.2.1. Train the multi-task graph neural network model based on a set of preset model hyperparameters, using n f The data in the training set is randomly divided into n f subsets, each time one of the subsets is used as the validation set, and the remaining n f-1 subsets to train the multi-task graph neural network model. During the training process, the statistical parameters are calculated based on the predicted values ​​of the inhibitory activity data scaling values ​​of the chemicals on GyrA and GyrB output by the multi-task graph neural network model and the corresponding true values ​​in the training set. The parameters of the multi-task graph neural network model are adjusted with the optimal statistical parameters as the optimization goal, and then the multi-task graph neural network model is verified using the data in the validation set to calculate the corresponding statistical parameters. The above process is repeated for training n f times, and finally get n f Statistical parameters and calculate n f The average value of the statistical parameters;

[0031] S3.2.2. Repeat step S3.2.1 to obtain the statistical parameter averages corresponding to all groups of model hyperparameters, and select a group of model hyperparameters corresponding to the optimal statistical parameter averages as the optimal model hyperparameters.

[0032] Compared with the prior art, the present invention has the following beneficial effects:

[0033] (1) The present invention can make full use of existing high-throughput experimental big data, use chemical SMILES codes as inputs to the inhibitory activity prediction model, and does not require artificially defined quantifiable structural parameters as molecular descriptors, thereby saving time and computing resources for molecular descriptor calculation and descriptor selection, and has lower requirements for computational chemistry foundations when applied;

[0034] (2) Compared with existing methods, the method of the present invention has high-precision prediction performance, which is helpful for the rapid discovery of new environmental pollutants that induce bacterial resistance, and has broad application prospects in the fields of chemical risk assessment and environmental safety assessment;

[0035] (3) The structure of the inhibitory activity prediction model in the present invention is flexible, which greatly improves the predictive ability of the inhibitory activity prediction model and realizes high-precision prediction of the inhibitory activity of chemicals on GyrA and GyrB, which is conducive to the rapid discovery of new environmental pollutants that induce bacterial resistance and can also be extended to the study of different key molecular initiation events. BRIEF DESCRIPTION OF THE DRAWINGS

[0036] Figure 1 A flow chart of a method for predicting the inhibitory activity of a chemical substance of the present invention on DNA gyrase;

[0037] Figure 2 This is a schematic diagram of the structure of the multi-task graph neural network model network in Example 1 of the present invention. DETAILED DESCRIPTION

[0038] Exemplary embodiments will be described in detail herein, examples of which are shown in the accompanying drawings. When the following description refers to the drawings, the same numbers in different drawings represent the same or similar elements unless otherwise indicated. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the present invention. Instead, they are merely examples of devices and methods consistent with some aspects of the present invention as detailed in the appended claims.

[0039] The terms used in the present invention are only for the purpose of describing specific embodiments and are not intended to limit the present invention. The singular forms "a", "the" and "the" used in the present invention and the appended claims are also intended to include plural forms unless the context clearly indicates other meanings. It should also be understood that the term "and / or" used herein refers to and includes any or all possible combinations of one or more associated listed items.

[0040] It should be understood that although the terms first, second, third, etc. may be used in the present invention to describe various information, these information should not be limited to these terms. These terms are only used to distinguish the same type of information from each other. For example, without departing from the scope of the present invention, the first information may also be referred to as the second information, and similarly, the second information may also be referred to as the first information. Depending on the context, the word "if" as used herein may be interpreted as "at the time of" or "when" or "in response to determining".

[0041] The present invention is described in detail below in conjunction with the accompanying drawings. In the absence of conflict, the features of the following embodiments and implementations can be combined with each other.

[0042] The method for predicting the inhibitory activity of chemicals on DNA gyrase of the present invention is based on the chemical SMILES (Simplified Molecular Input Line Entry System) code, which avoids the limitations of traditional methods such as low accuracy and small application range. Compared with other similar methods, the method of the present invention has the most superior prediction ability in current research.

[0043] It should be understood that SMILES is a specification that uses an ASCII string to clearly describe a molecular structure, and the SMILES code can be used to describe the three-dimensional chemical structure of a compound.

[0044] The basic principle of the present invention is: the input of the model is the SMILES code of the chemical in the GyrA and GyrB data sets; first, the GyrA and GyrB data are obtained by the task-specific input layer, and then the data and model network parameters are shared through the shared network of the model, which is conducive to knowledge transfer and significantly improves the learning efficiency of new tasks. Among them, in the shared network of the model, the atomic feature matrix, adjacency matrix and chemical bond feature matrix are obtained through the molecular graph embedding layer, and the molecular fragment features are obtained through the molecular fragment graph embedding layer, specifically including the atomic feature matrix, the molecular fragment adjacency matrix, the chemical bond feature matrix of the molecular fragments and the molecular fragment index list; then the various feature vectors extracted from the molecular graph embedding layer and the molecular fragment graph embedding layer are respectively input into the molecular graph neural network encoder and the molecular fragment graph neural network encoder, and the molecular graph feature sequence and the molecular fragment feature sequence are obtained accordingly, and the intrinsic connection between molecules and molecular fragments is captured by the dual-path combiner, and finally the task-specific predictor outputs the inhibitory activity data (IC) of the chemical on GyrA and GyrB. 50 ) scaled values.

[0045] See also Figure 1 , the method for predicting the inhibitory activity of a chemical on DNA gyrase of the present invention, wherein the DNA gyrase includes GyrA and GyrB, the method specifically comprises the following steps:

[0046] S1. Obtain chemical structures and inhibitory activity data (IC 50 ), and performed structural cleaning operations on the chemical structures, and performed scaling operations on the inhibitory activity data of GyrA and GyrB to construct a data set, and then randomly divided it into a training set and a test set in proportion.

[0047] S1.1. Obtain chemical structures and inhibitory activity data of chemicals on GyrA and GyrB from public databases; wherein the chemical structures are chemical SMILES codes, and the inhibitory activity data are used to indicate the inhibitory activity of chemicals on GyrA and GyrB.

[0048] S1.2. Perform structural cleaning operations on chemical structures, including: standardizing chemical SMILES codes, removing solvents, charge correction, deionization and other chemical molecular structure cleaning operations, so as to standardize and unify the form of chemical SMILES codes, which can effectively avoid interference in subsequent calculations. Among them, these structural cleaning operations can perform molecular structure inspection to ensure that the structure of the molecule is chemically reasonable; correct common drawing errors and standardize functional groups; hide hydrogen atoms; recalculate stereochemistry; remove covalently bonded impurities; ensure that the strongest acid group is ionized first; produce neutral molecules as much as possible; standardize tautomers; and remove salts and covalently bound metals contained in the compound.

[0049] S1.3. By taking the negative logarithm of the original numerical value of the inhibitory activity data of the chemical on GyrA and GyrB, the numerical range of the inhibitory activity data of the chemical on GyrA and GyrB is scaled, thereby reducing the numerical range of the inhibitory activity data.

[0050] S1.4. Construct the GyrA and GyrB data sets based on the chemical SMILES codes after the structure cleaning operation in step S1.2 and the inhibitory activity data of GyrA and GyrB after the scaling operation in step S1.3.

[0051] S1.5. Randomly divide the GyrA and GyrB datasets into training sets and test sets according to a certain ratio. T% of the data is used as the training set to train and optimize the multi-task graph neural network model; w% of the data is used as the test set to evaluate the performance of the final model.

[0052] S2. Construct a multi-task graph neural network model with chemical SMILES codes as input, and its output is the predicted value of the inhibitory activity data scaling value of the chemical on GyrA and GyrB.

[0053] In this embodiment, the multi-task graph neural network model includes a task-specific input layer, a molecular graph embedding layer, a molecular fragment graph embedding layer, multiple molecular graph neural network encoders, multiple molecular fragment graph neural network encoders, a dual-pathway combiner and a task-specific predictor, wherein the task-specific input layer includes a parallel GyrA task input layer and a GyrB task input layer, and the molecular graph neural network encoder and the molecular fragment graph neural network encoder are both composed of a neighborhood attention module, an information aggregation module, a gating mechanism to update node feature module and a feature attention module, but their parameters are different, such as Figure 2 As shown in Figure 1, the feature attention module includes a maximum pooling layer, a sum pooling layer, a multi-layer perceptron global pooling layer and an activation function; the dual-path combiner uses a graph convolutional attention layer, which includes multiple attention heads and a ReLU activation function; the task-specific predictor includes two prediction heads, each of which includes n l Fully connected layer.

[0054] Specifically, the task-specific input layer extracts the data of GyrA and GyrB respectively through the parallel GyrA task input layer and the GyrB task input layer and inputs them into the shared network of the multi-task graph neural network model for subsequent reasoning, wherein the shared network of the multi-task graph neural network model includes a molecular graph embedding layer, a molecular fragment graph embedding layer, multiple molecular graph neural network encoders, multiple molecular fragment graph neural network encoders and a dual-pathway combiner.

[0055] It should be understood that since the prediction of the inhibitory activity of chemicals on GyrA and GyrB has different emphases, it is necessary to first extract the data of GyrA and GyrB through the task-specific input layer, and then input it into the shared network of the multi-task graph neural network model to perform the subsequent reasoning process, and then use the task-specific predictor to output the corresponding inhibitory activity prediction results using the prediction heads corresponding to GyrA and GyrB.

[0056] The molecular graph embedding layer uses RDKit to calculate the molecular graph of the chemical according to the chemical SMILES code to extract the molecular graph features from the molecular graph; the molecular graph features include a×d at The atomic feature matrix, the adjacency matrix of length b, and the b×d bt The chemical bond characteristic matrix is: a is the number of atoms in the chemical, b is twice the number of chemical bonds in the chemical, and d is at is the number of atomic features, d bt is the number of chemical bond features, and the adjacency matrix is ​​used to represent the atomic numbers of the bonding atom pairs in the molecular graph.

[0057] The molecular fragment graph embedding layer uses RDKit to calculate the molecular graph of chemicals according to the SMILES code of chemicals, and extracts molecular fragment features from the molecular graph based on the BRICS principle (Bonds Representing Interaction Clusters); the molecular fragment features include a×d at The atomic feature matrix of length b f The molecular fragment adjacency matrix, b f ×d bt The chemical bond feature matrix of the molecular fragments and the molecular fragment index list of length a, where b f It is twice the number of chemical bonds remaining after the molecule is broken into molecular fragments. The molecular fragment index list is used to indicate the index of the molecular fragment where each atom in the chemical is located.

[0058] The various molecular graph features and molecular fragment features extracted from the molecular graph embedding layer and the molecular fragment graph embedding layer are first transformed into a length of d h Then, each type of feature vector is input into the molecular graph neural network encoder and the molecular fragment graph neural network encoder to obtain the molecular graph feature sequence and the molecular fragment feature sequence, respectively. hThe length of is the same as the size of the hidden layer. In the molecular graph neural network encoder and the molecular fragment graph neural network encoder, the molecular graph neural network encoder and the molecular fragment graph neural network encoder update the node features of the molecular graph and the molecular fragment graph through their respective neighborhood attention modules and information aggregation modules, and then update the node feature module through the gating mechanism to balance between retaining the original information and using the new information. In the feature attention module, the global features of the molecular graph are extracted through the maximum pooling layer and the sum pooling layer, and the attention weights are generated by the multi-layer perceptron to weight the features of the nodes. Finally, the features of all nodes are aggregated into a global feature vector through the global pooling layer and the activation function, thereby obtaining the molecular graph feature sequence and the molecular fragment feature sequence.

[0059] It should be understood that feature conversion refers to compressing or amplifying feature dimensions, as well as calculating activation functions, to convert various molecular graph features and molecular fragment features into corresponding feature vectors. In addition, in deep learning models, except for the input layer and the output layer, the remaining network layers can be called hidden layers.

[0060] The molecular graph feature sequence and the molecular fragment feature sequence are input into the dual-path combiner. The dual-path combiner first adopts the interactive attention strategy to capture the intrinsic connection between molecules and molecular fragments, and uses the graph convolutional attention layer to learn the relationship between the molecular graph feature sequence and the molecular fragment feature sequence. Specifically, it adopts n h Each attention head independently calculates the attention weights of different molecular fragments, which can better capture the characteristics of molecular fragments, and obtains the molecular-molecular fragment interaction feature sequence through nonlinear transformation through the ReLU activation function. Then, the molecule-molecular fragment interaction feature sequence and the molecular graph feature sequence output by the molecular graph neural network encoder are spliced ​​and input into the task-specific predictor, and then passed through n prediction heads of two prediction heads. l After the fully connected layer, the inhibitory activity data of chemicals on GyrA and GyrB (IC 50 ) scaled values.

[0061] S3. Use cross-validation to determine the optimal hyperparameters of the multi-task graph neural network model, and train it using the training set to obtain the trained optimal multi-task graph neural network model, which is used as a DNA gyrase inhibitory activity prediction model to predict the inhibitory activity data scaling values ​​of chemicals on GyrA and GyrB.

[0062] S3.1. Based on experience, we preset multiple sets of different model hyperparameters as {lr, weight-decay, batchsize_a, batchsize_b, dropout, depth, feature-dimension, n-slices, r}, where lr is the learning rate, weight-decay is the weight decay parameter, batchsize_a and batchsize_b are the number of samples of GyrA and GyrB selected for one training respectively, dropout is the random dropout regularization term parameter, depth is the number of encoder layers, feature-dimension is the size of the hidden layer, n-slices is the number of slices, r is the decay rate, lr is used to control the progress of convergence to the local minimum, weight-decay and dropout are used to prevent the model from overfitting, depth, feature-dimension, n-slices and r are used to adjust the model complexity, and the size of batchsize_a and batchsize_b affects the optimization degree and speed of the model.

[0063] S3.2. For each set of model hyperparameters, use the GyrA and GyrB data in the training set to train a multi-task graph neural network model. f The multi-task graph neural network model corresponding to the set of model hyperparameters was evaluated by fold cross-validation based on statistical parameters to determine the optimal model hyperparameters, and the trained multi-task graph neural network model corresponding to the optimal model hyperparameters was obtained, which was used as a DNA gyrase inhibitory activity prediction model to predict the inhibitory activity data scaling values ​​of chemicals on GyrA and GyrB.

[0064] Furthermore, the statistical parameter is the coefficient of determination (R 2 ), root mean square error (RMSE), mean square error (MSE), mean absolute error (MAE), and their calculation formulas are:

[0065]

[0066] Where n represents the number of samples, y i represents the true value of the inhibitory activity data scaling value of the chemical corresponding to the i-th sample on GyrA and GyrB, represents the predicted value of the inhibitory activity scaling value of the chemical corresponding to the i-th sample on GyrA and GyrB, Represents the average of all true values.

[0067] It should be noted that when using statistical parameters to evaluate the multi-task graph neural network model, the statistical parameters of the GyrA task and the statistical parameters of the GyrB task can be added as the final method for evaluating the predictive ability of the multi-task graph neural network model.

[0068] Furthermore, for each set of model hyperparameters, the multi-task graph neural network model is trained using the data in the training set. f The fold cross validation evaluates the multi-task graph neural network model corresponding to the set of model hyperparameters based on statistical parameters to determine the optimal model hyperparameters, including:

[0069] S3.2.1. Train the multi-task graph neural network model based on a set of preset model hyperparameters, using n f The data in the training set is randomly divided into n f subsets, each time one of the subsets is used as the validation set, and the remaining n f -1 subsets to train the multi-task graph neural network model. During the training process, the statistical parameters are calculated based on the predicted values ​​of the inhibitory activity data scaling values ​​of the chemicals on GyrA and GyrB output by the multi-task graph neural network model and the corresponding true values ​​in the training set. The parameters of the multi-task graph neural network model are adjusted with the optimal statistical parameters as the optimization goal, and then the multi-task graph neural network model is verified using the data in the validation set to calculate the corresponding statistical parameters. The above process is repeated for training n f times, and finally get n f Statistical parameters, take n f The average value of the statistical parameters is used to evaluate the predictive ability of the multi-task graph neural network model when different model hyperparameters are selected.

[0070] S3.2.2. Repeat step S3.2.1 to obtain the statistical parameter averages corresponding to all groups of model hyperparameters, and select a group of model hyperparameters corresponding to the optimal statistical parameter averages as the optimal model hyperparameters.

[0071] It should be understood that when different statistical parameters are selected, the requirements for the optimal statistical parameters are also different. For example, when the statistical parameter is RMSE, the smaller the RMSE, the better the statistical parameter; when the statistical parameter is R 2 When R 2 The larger the value, the better the statistical parameter.

[0072] S4. Input the SMILES code of the chemical to be tested in the test set or the SMILES code of the chemical to be evaluated into the DNA gyrase inhibitory activity prediction model to obtain the predicted value s of the inhibitory activity data scaling value of the chemical on GyrA and GyrB. out_a and out_bThe larger the predicted value is, the stronger the inhibitory activity of the chemical on GyrA and GyrB is considered to be, and vice versa.

[0073] In summary, the present invention utilizes the SMILES code of chemicals to avoid the application limitations of traditional prediction models, and greatly improves the prediction ability of the model, thereby achieving high-precision prediction of the inhibitory activity of chemicals on DNA gyrase; in addition, the present invention uses a shared network of a multi-task graph neural network model to enable the multi-task graph neural network model to learn the characteristics of chemicals more fully, so as to achieve accurate and rapid screening of key molecular initiation events of pollutant-induced bacterial resistance, clarify the structural basis of pollutant-induced bacterial resistance, and has broad application prospects in the field of chemical health risk assessment.

[0074] The technical solution of the present invention is further described below by means of specific embodiments in combination with the accompanying drawings. It should be noted that the following specific embodiments are only used as examples, and the protection scope of the present invention is not limited thereto.

[0075] Example 1

[0076] See also Figure 1-Figure 2 This embodiment implements a method for predicting the inhibitory activity of chemicals on DNA gyrase (GyrA and GyrB) based on a multi-task graph neural network model, specifically comprising the following steps:

[0077] (1) Acquisition and preprocessing of chemical structures and inhibitory activity data on GyrA and GyrB.

[0078] First, the UniProtIDs of bacterial GyrA and GyrB were obtained from the UniProt database. Based on these UniProtIDs, the inhibitory activity data of GyrA and GyrB were found in the UniProt database and ChEMBL database, which contained chemical SMILES codes and inhibitory activity data (IC 50 ) numerical value. The inhibitory activity data indicates the strength of the compound's inhibitory activity on the enzyme.

[0079] Subsequently, the chemical SMILES codes in the DNA gyrase inhibitory activity data of the chemicals were standardized; desolvation; charge correction; deionization and other chemical molecular structure cleaning operations were performed to avoid interference in subsequent calculations. These SMILES code cleaning operations can perform molecular structure inspection to ensure that the structure of the molecule is chemically reasonable; correct common drawing errors and standardize functional groups; hide hydrogen atoms; recalculate stereochemistry; remove covalently bonded impurities; ensure that the strongest acid group is ionized first; produce neutral molecules as much as possible; standardize tautomers; and remove salts and covalently bound metals contained in the compound. By using the half inhibitory concentration (IC50) of each chemical 50) to scale the inhibitory activity range.

[0080] Finally, the preprocessed chemical SMILES codes and the inhibitory activity data of the chemicals on DNA gyrase A subunit were randomly divided into training set and test set in a ratio of 8:2.

[0081] (2) Construction, training and hyperparameter search of multi-task graph neural network models.

[0082] The constructed multi-task graph neural network model includes a task-specific input layer, a molecular graph embedding layer, a molecular fragment graph embedding layer, three molecular graph neural network encoders, three molecular fragment graph neural network encoders, a dual-pathway combiner and a task-specific predictor, such as Figure 2 shown.

[0083] The SMILES codes of chemicals in the GyrA and GyrB training sets were used as input to the multi-task graph neural network model.

[0084] The task-specific input layer can extract the data of GyrA and GyrB respectively and input them into the shared network of the model (molecular graph embedding layer, molecular fragment embedding layer, molecular graph neural network encoder, molecular fragment graph neural network encoder and dual-pathway combiner) for training.

[0085] RDKit is used in the molecular graph embedding layer to extract an a×46 atomic feature matrix, an adjacency matrix of length b (used to represent the atomic numbers of bonding atom pairs in molecules), and a b×10 chemical bond feature matrix from the molecular graph, where a is the number of atoms in the chemical, b is twice the number of chemical bonds in the chemical, 46 is the number of atomic features, and 10 is the number of chemical bond features.

[0086] RDKit is used in the molecular fragment embedding layer to extract molecular fragment features from the molecular graph. The extracted molecular fragment features include: an a×46 atomic feature matrix with a length of b f The molecular fragment adjacency matrix, b f ×10 chemical bond feature matrix of molecular fragments and a molecular fragment index list of length a (indicating the index of the molecular fragment where each atom in the chemical is located), where b f It is twice the number of chemical bonds remaining after the molecule is broken into molecular fragments.

[0087] The feature vectors extracted from the molecular graph embedding layer and the molecular fragment embedding layer are first transformed into a length of d h The feature vectors are then input into the molecular graph neural network encoder and the molecular fragment graph neural network encoder to obtain the molecular graph feature sequence and the molecular fragment feature sequence, respectively. hThe length of is the same as the size of the hidden layer. The molecular graph neural network encoder and the molecular fragment graph neural network encoder are respectively composed of a neighborhood attention module, an information aggregation module, a gating mechanism to update the node feature module and a feature attention module. In the molecular graph neural network encoder and the molecular fragment graph neural network encoder, the node features of the molecular graph and the molecular fragment graph are updated through the neighborhood attention module and the information aggregation module, and then the node feature module is updated through the gating mechanism to balance between retaining the original information and using the new information. In the feature attention module, the global features of the graph are extracted through the maximum pooling layer and the sum pooling layer, and the attention weights are generated by the multi-layer perceptron. The features of the nodes are weighted and adjusted. Finally, the features of all nodes are aggregated into a global feature vector through the global pooling layer and the activation function, thereby obtaining the molecular graph feature sequence and the molecular fragment feature sequence.

[0088] The dual-path combiner first uses an interactive attention strategy to capture the intrinsic connection between molecules and molecular fragments. It uses a graph attention convolution layer to learn the relationship between the molecular graph feature sequence and the molecular fragment feature sequence, calculates the attention weights of different molecular fragments, and obtains the molecule-molecular fragment interactive feature sequence through nonlinear transformation through the ReLU activation function. The graph attention convolution layer uses 4 attention heads to perform independent calculations, which can better capture the characteristics of molecular fragments. The above molecular graph feature sequence and molecule-molecular fragment interactive feature sequence are then concatenated and input into the task-specific predictor.

[0089] The task-specific predictor consists of two prediction heads, each of which includes a fully connected layer and outputs the IC of the chemical for GyrA and GyrB respectively. 50 The predicted value of the scaled value s out_a and out_b .

[0090] During training, the adaptive momentum optimizer Adam is used to update the neural network parameters based on the gradient, and the learning rate lr is 0.000525. In addition, in order to control the progress of convergence to the local minimum, batchsize_a and batchsize_b are added to the model, and the parameters set the batch size to 32 and 32 respectively. In order to improve the generalization ability of the model and prevent the model from overfitting, the weight decay parameter weight-decay and the random loss regularization parameter dropout are set. The weight decay parameter weight-decay is set to 0.00001, and the random loss regularization parameter dropout is set to 0.0. In addition, the number of layers of the encoder depth, the size of the hidden layer feature-dimension, the number of slices n-slices, and the decay rate r are used to adjust the model complexity. The depth, feature-dimension, n-slices, and r are 4, 64, 2, and 1 respectively. A 10-fold cross validation is used, and the training is repeated 10 times. Each time, the validation set and the training set are randomly selected according to a certain ratio for training. Each training is performed for a maximum of 500 iterations. When the validation set R of the current iteration is 2 Less than the optimal validation set R 2 And the current number of iterations is greater than the optimal validation set R 2 The training is terminated when the number of iterations is greater than 50. The prediction ability of the model when different hyperparameters are selected is evaluated based on the average value of the statistical parameters of the model on the validation set during 10 trainings. Finally, the model is retrained on the entire training set based on the optimal hyperparameter combination, and the test set R is calculated. 2 , RMSE, MSE, and MAE statistical parameters are used to characterize the prediction ability of the model.

[0091] In order to further avoid overfitting of the model and improve the generalization ability of the model, the hyperparameters used are searched and optimized within a certain range and a certain step size:

[0092] Select the learning rate parameter lr to get R corresponding to different learning rates 2 , lr is selected as 0.000525;

[0093] Select the weight decay parameter weight-decay and get the R corresponding to different weight decay parameters 2 , select λ as 0.00001;

[0094] Select batch size batchsize_a and batchsize_b to get R corresponding to different batch sizes 2 , batchsize_a and batchsize_b are selected as 32 and 32 respectively;

[0095] Select the random loss regularization term parameter dropout, and get the R corresponding to different random loss regularization term parameters 2 , select dropout as 0.0;

[0096] Select the number of encoder layers depth, and get the R corresponding to the number of encoder layers 2 , select depth as 4;

[0097] Select the feature-dimension of the hidden layer and get the R corresponding to the size of different hidden layers. 2 , select feature-dimension as 64;

[0098] Select the number of slices n-slices and get the R corresponding to different numbers of slices 2 , select n-slices as 2;

[0099] Select the attenuation rate r and get the R corresponding to different attenuation rates 2 , select r as 1.

[0100] (3) Prediction of DNA gyrase inhibitory activity of the chemical to be evaluated.

[0101] BDBM50423645 was selected from the test set as the chemical to be evaluated to predict its inhibitory activity on DNA gyrase. The chemical structure of BDBM50423645 is shown in the following formula:

[0102]

[0103] BDBM50423645 is a fluorinated organic compound that is widely present in the environment. As the chemical to be tested in this embodiment, the SMILES code of BDBM50423645 is queried through the PubChem molecular database, specifically "CO[C@@H]1[C@@H](OC(N)=O)[C@H](O)[C@@H](Oc2ccc3c(=O)c(NC(=O)c4ccc(O)c(CC=C(C)C)c4)c(O)oc3c2C)OC1(C)C", and standardization; desolvation; charge correction; deionization and other chemical molecular structure cleaning operations are performed to avoid interference in subsequent calculations. These SMILES code cleaning operations can perform molecular structure inspection processing to ensure that the structure of the molecule is chemically reasonable; correct common drawing errors and standardize functional groups; hide hydrogen atoms; recalculate stereochemistry; remove covalently bonded impurities; ensure that the strongest acid group is ionized first; produce neutral molecules as much as possible; standardize tautomers; and remove salts and covalently bound metals contained in the compound. The processed SMILES code was used as the input information of the model to calculate the p(IC 50 ) are predicted to be 6.23 and 6.85 respectively.

[0104] The p(IC 50 ) are 7.00 and 6.70 respectively, and the predicted results are basically consistent with the facts.

[0105] In summary, the present invention, through the established multi-task graph neural network model, can predict the inhibitory activity of chemicals on DNA gyrase based only on the SMILES codes of the chemicals.

[0106] The above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit the same. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features may be replaced by equivalents. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for predicting the inhibitory activity of a chemical on DNA gyrase, characterized in that: The DNA gyrase comprises GyrA and GyrB, and the method comprises the following steps: S1. Obtain chemical structures and inhibitory activity data of chemicals on GyrA and GyrB, perform structural cleaning operations on chemical structures, perform scaling operations on inhibitory activity data of GyrA and GyrB to construct a data set, and randomly divide the data set into a training set and a test set in proportion; S2. Construct a multi-task graph neural network model with chemical SMILES codes as input, and its output is the predicted value of the scaled value of the inhibitory activity data of chemicals on GyrA and GyrB; S3. Use cross-validation to determine the optimal hyperparameters of the multi-task graph neural network model, and use the training set to train it to obtain the trained optimal multi-task graph neural network model, which is used as a DNA gyrase inhibitory activity prediction model to predict the inhibitory activity data scaling values ​​of chemicals on GyrA and GyrB; S4. Input the SMILES code of the chemical to be tested in the test set or the SMILES code of the chemical to be evaluated into the DNA gyrase inhibitory activity prediction model to obtain the predicted value of the inhibitory activity data scaling value of the chemical on GyrA and GyrB.

2. The method for predicting the inhibitory activity of a chemical on DNA gyrase according to claim 1, characterized in that: The step S1 comprises the following sub-steps: S1.

1. Obtain chemical structures and inhibitory activity data of chemicals against GyrA and GyrB from public databases; the chemical structures are chemical SMILES codes, and the inhibitory activity data are used to indicate the inhibitory activity of chemicals against GyrA and GyrB; S1.

2. Performing structure cleaning operations on chemical structures, specifically including: standardizing, removing solvents, charge correction, and deionizing chemical molecular structure cleaning operations on chemical SMILES codes to standardize and unify the form of chemical SMILES codes; wherein, the above-mentioned structure cleaning operations can perform molecular structure inspection processing to ensure that the structure of the molecule is chemically reasonable; correct drawing errors and standardize functional groups; hide hydrogen atoms; recalculate stereochemistry; remove covalently bonded impurities; ensure that the strongest acid group is ionized first; produce neutral molecules; standardize tautomers; remove salts and covalently bound metals contained in the compound; S1.3, performing a scaling operation on the numerical range of the inhibitory activity data of the chemical on GyrA and GyrB by taking the negative logarithm of the original numerical value of the inhibitory activity data of the chemical on GyrA and GyrB; S1.4, constructing GyrA and GyrB data sets according to the chemical SMILES codes after the structure cleaning operation in step S1.2 and the inhibitory activity data of GyrA and GyrB after the scaling operation in step S1.3; S1.

5. Randomly divide the GyrA and GyrB datasets into training and test sets in proportion.

3. The method for predicting the inhibitory activity of a chemical on DNA gyrase according to claim 1, characterized in that: The multi-task graph neural network model includes a task-specific input layer, a molecular graph embedding layer, a molecular fragment graph embedding layer, multiple molecular graph neural network encoders, multiple molecular fragment graph neural network encoders, a dual-path combiner and a task-specific predictor, wherein the task-specific input layer includes a parallel GyrA task input layer and a GyrB task input layer, the molecular graph neural network encoder and the molecular fragment graph neural network encoder are both composed of a neighborhood attention module, an information aggregation module, a gating mechanism update node feature module and a feature attention module, and the feature attention module includes a maximum pooling layer, a sum pooling layer, a multi-layer perceptron global pooling layer and an activation function; the dual-path combiner selects a graph convolutional attention layer, and the graph convolutional attention layer includes multiple attention heads and a ReLU activation function; the task-specific predictor includes 2 prediction heads, each of which includes n prediction heads. l Fully connected layer.

4. The method for predicting the inhibitory activity of a chemical on DNA gyrase according to claim 3, characterized in that: The task-specific input layer extracts the data of GyrA and GyrB respectively through the parallel GyrA task input layer and the GyrB task input layer and inputs them into the shared network of the multi-task graph neural network model for subsequent reasoning, wherein the shared network of the multi-task graph neural network model includes a molecular graph embedding layer, a molecular fragment graph embedding layer, a plurality of molecular graph neural network encoders, a plurality of molecular fragment graph neural network encoders and a dual-pathway combiner; The molecular graph embedding layer calculates the molecular graph of the chemical according to the chemical SMILES code by using RDKit to extract the molecular graph features from the molecular graph; wherein the molecular graph features include a×d at The atomic feature matrix, the adjacency matrix of length b, and the b×d bt The chemical bond characteristic matrix is: a is the number of atoms in the chemical, b is twice the number of chemical bonds in the chemical, and d is at is the number of atomic features, d bt is the number of chemical bond features, and the adjacency matrix is ​​used to represent the atomic numbers of the bonding atom pairs in the molecular graph; The molecular fragment graph embedding layer calculates the molecular graph of the chemical according to the SMILES code of the chemical by using RDKit, and extracts the molecular fragment features from the molecular graph based on the BRICS principle; wherein the molecular fragment features include a×d at The atomic feature matrix of length b f The molecular fragment adjacency matrix, b f ×d bt The chemical bond feature matrix of the molecular fragments and the molecular fragment index list of length a, where b f It is twice the number of chemical bonds remaining after the molecule is broken into molecular fragments. The molecular fragment index list is used to indicate the index of the molecular fragment where each atom in the chemical is located; The various molecular graph features and molecular fragment features extracted from the molecular graph embedding layer and the molecular fragment graph embedding layer are first transformed into a length of d h Then, each type of feature vector is input into the molecular graph neural network encoder and the molecular fragment graph neural network encoder to obtain the molecular graph feature sequence and the molecular fragment feature sequence, respectively. h The length of is the same as the size of the hidden layer; wherein, in the molecular graph neural network encoder and the molecular fragment graph neural network encoder, the molecular graph neural network encoder and the molecular fragment graph neural network encoder update the node features of the molecular graph and the molecular fragment graph through their respective neighborhood attention modules and information aggregation modules, and then update the node feature module through a gating mechanism to balance between retaining the original information and using the new information, and in the feature attention module, the global features of the molecular graph are extracted through the maximum pooling layer and the sum pooling layer, and the attention weights are generated by the multi-layer perceptron, and the features of the nodes are weighted and adjusted, and finally the features of all nodes are aggregated into a global feature vector through the global pooling layer and the activation function, so as to obtain the molecular graph feature sequence and the molecular fragment feature sequence; The molecular graph feature sequence and the molecular fragment feature sequence are input into the dual-path combiner. The dual-path combiner uses the graph convolution attention layer to learn the relationship between the molecular graph feature sequence and the molecular fragment feature sequence. Specifically, it adopts n h Each attention head independently calculates the attention weights of different molecular fragments, and performs nonlinear transformation through the ReLU activation function to obtain the molecule-molecular fragment interaction feature sequence; Then, the molecule-molecule fragment interaction feature sequence and the molecular graph feature sequence output by the molecular graph neural network encoder are concatenated and input into the task-specific predictor, respectively, after passing through the n prediction heads of the two prediction heads. l After the fully connected layers, the predicted values ​​of the inhibitory activity data scaling values ​​of the chemicals on GyrA and GyrB are output respectively.

5. The method for predicting the inhibitory activity of a chemical on DNA gyrase according to claim 1, characterized in that: The step S3 comprises the following sub-steps: S3.

1. Preset multiple sets of different model hyperparameters as {lr, weight-decay, batchsize_a, batchsize_b, dropout, depth, feature-dimension, n-slices, r}, where lr is the learning rate, weight-decay is the weight decay parameter, batchsize_a and batchsize_b are the number of samples of GyrA and GyrB selected for one training, dropout is the random dropout regularization parameter, depth is the number of encoder layers, feature-dimension is the size of the hidden layer, n-slices is the number of slices, r is the decay rate, lr is used to control the progress of convergence to the local minimum, weight-decay and dropout are used to prevent model overfitting, depth, feature-dimension, n-slices and r are used to adjust the model complexity, and the size of batchsize_a and batchsize_b affects the optimization degree and speed of the model; S3.

2. For each set of model hyperparameters, use the GyrA and GyrB data in the training set to train a multi-task graph neural network model. f The multi-task graph neural network model corresponding to the set of model hyperparameters was evaluated by fold cross-validation based on statistical parameters to determine the optimal model hyperparameters, and the trained multi-task graph neural network model corresponding to the optimal model hyperparameters was obtained, which was used as a DNA gyrase inhibitory activity prediction model to predict the inhibitory activity data scaling values ​​of chemicals on GyrA and GyrB.

6. The method for predicting the inhibitory activity of a chemical on DNA gyrase according to claim 5, characterized in that: The statistical parameter is one of a coefficient of determination, a root mean square error, a mean square error, and a mean absolute error.

7. The method for predicting the inhibitory activity of a chemical on DNA gyrase according to claim 5, characterized in that: For each set of model hyperparameters, the multi-task graph neural network model is trained using the data in the training set. f The fold cross validation evaluates the multi-task graph neural network model corresponding to the set of model hyperparameters based on statistical parameters to determine the optimal model hyperparameters, including: S3.2.

1. Train the multi-task graph neural network model based on a set of preset model hyperparameters, using n f The data in the training set is randomly divided into n f subsets, each time one of the subsets is used as the validation set, and the remaining n f -1 subsets to train the multi-task graph neural network model. During the training process, the statistical parameters are calculated based on the predicted values ​​of the inhibitory activity data scaling values ​​of the chemicals on GyrA and GyrB output by the multi-task graph neural network model and the corresponding true values ​​in the training set. The parameters of the multi-task graph neural network model are adjusted with the optimal statistical parameters as the optimization goal, and then the multi-task graph neural network model is verified using the data in the validation set to calculate the corresponding statistical parameters. The above process is repeated for training n f times, and finally get n f Statistical parameters and calculate n f The average value of the statistical parameters; S3.2.

2. Repeat step S3.2.1 to obtain the statistical parameter averages corresponding to all groups of model hyperparameters, and select a group of model hyperparameters corresponding to the optimal statistical parameter averages as the optimal model hyperparameters.

Images