Animal monkey pox virus positioning method based on immunological data analysis

Abstract

The invention relates to an animal monkey pox virus positioning method based on immunological data analysis, and belongs to the technical field of monkey pox virus localization. Virus characteristic data of monkey pox viruses are obtained through a processed monkey pox virus knowledge graph, and the training number of a training set is constructed according to the virus characteristic data of the monkey pox viruses; and determining a final training item of a training set, finally inputting the final training item of the training set into the monkey pox virus positioning model for training, monitoring the prediction precision of the monkey pox virus positioning model, and determining a training state according to the prediction precision of the monkey pox virus positioning model. According to the method, the training speed of the training system is adjusted, the training speed is prevented from being too high or too low during model training, the prediction precision of the model can be improved, the prediction precision of the model is monitored by fusing the Markov model, the prediction precision of the model is updated in time while the requirements are met, and the training amount of the model can be reduced.

Description

Technical Field

[0001] The present invention relates to the technical field of monkeypox virus localization, and in particular to an animal monkeypox virus localization method based on immunological data analysis. Background Art

[0002] Monkeypox is a new infectious disease caused by monkeypox virus (MPXV), with fever, rash, and lymphadenopathy as the main clinical manifestations. Some patients have complications such as bacterial infection, encephalitis, and even death. Monkeypox can be transmitted from person to person, including droplet transmission and contact with patient body fluids and secretions. MPXV has been detected in the air and wastewater around patients. Vertical transmission can cause miscarriage in pregnant women and fetal death. Sexual transmission has not been ruled out. Studies have found that replicable MPXV was isolated from the semen of patients on the 6th day after onset, and MPXV deoxyribonucleic acid was detected in 79% of the samples. According to the WHO report, sexual contact is the most common mode of transmission for men, women, and pregnant women, accounting for 83.6%, and gatherings with sexual contact account for 66.7% of all exposure environments. Genome sequencing is the most effective method for identifying new strains or discovering variant strains, providing a more effective and accurate means for infectious disease prevention and control. A series of commercial monkeypox virus genome sequencing platforms have been established, and the NCBI database has included 6,190 reference sequences of MPXV strain genes. However, when using machine learning technology to detect monkeypox DNA\RNA gene sequences, the training limit of the training system is not considered, resulting in the model training speed being too fast or too slow, affecting the prediction accuracy of the model and being unfavorable for the location and detection of monkeypox DNA\RNA gene sequences. Summary of the invention

[0003] The present invention overcomes the deficiencies of the prior art and provides an animal monkeypox virus localization method based on immunological data analysis.

[0004] To achieve the above object, the technical solution adopted by the present invention is:

[0005] The first aspect of the present invention provides a method for localizing monkeypox virus in animals based on immunological data analysis, comprising:

[0006] Obtaining sample data of monkeypox virus, extracting components from the sample data of monkeypox virus, obtaining immunological data of monkeypox virus, and constructing a monkeypox virus localization model based on a multi-layer perceptron neural network;

[0007] Constructing a monkeypox virus knowledge graph based on the immunological data of the monkeypox virus, and performing data enhancement processing on the virus feature data in the monkeypox virus knowledge graph to obtain a processed monkeypox virus knowledge graph;

[0008] Obtaining virus feature data of the monkeypox virus through the processed monkeypox virus knowledge graph, constructing the number of training items of the training set according to the virus feature data of the monkeypox virus, and determining the final training items of the training set;

[0009] The final training item of the training set is input into the monkeypox virus localization model for training, and the prediction accuracy of the monkeypox virus localization model is monitored, and the training status is determined according to the prediction accuracy of the monkeypox virus localization model.

[0010] Furthermore, in the method for localizing the animal monkeypox virus based on immunological data analysis, sample data of the monkeypox virus is obtained, and components of the sample data of the monkeypox virus are extracted to obtain immunological data of the monkeypox virus, and a monkeypox virus localization model is constructed based on a multi-layer perceptron neural network, specifically:

[0011] Obtaining sample data of monkeypox virus, and extracting the sample data of monkeypox virus to obtain a sample extract, and extracting monkeypox virus genetic material fragments and derivatives related to monkeypox virus from the sample extract by gene detection technology;

[0012] The monkeypox virus genetic material fragments and derivatives related to the monkeypox virus are obtained, and the immunological data of the monkeypox virus is constructed based on the monkeypox virus genetic material fragments and derivatives related to the monkeypox virus, and a monkeypox virus localization model is constructed based on a multi-layer perceptron neural network.

[0013] Furthermore, in the method for localizing animal monkeypox virus based on immunological data analysis, a monkeypox virus knowledge graph is constructed according to the immunological data of the monkeypox virus, and the virus feature data in the monkeypox virus knowledge graph is subjected to data enhancement processing to obtain the processed monkeypox virus knowledge graph, specifically including:

[0014] Construct a monkeypox virus knowledge graph and introduce a recurrent spatial attention mechanism to obtain the immunological data of the monkeypox virus, and extract the monkeypox virus genetic material fragments and related derivatives from the immunological data of the monkeypox virus;

[0015] Taking the monkeypox virus genetic material fragments and related derivatives as nodes, and inputting the nodes into the cyclic spatial attention mechanism, processing the nodes, and obtaining a normalized feature map with spatial attention;

[0016] Performing an inner product operation on the normalized feature map with spatial attention and the node, focusing the attention on the node, generating an attention feature map, and using the attention feature map as the virus feature data after data enhancement;

[0017] The virus feature data after data enhancement is input into the storage space of the monkeypox virus knowledge graph for storage, and a query address is configured to regularly update the monkeypox virus knowledge graph.

[0018] Furthermore, in the method for localizing the animal monkeypox virus based on immunological data analysis, the virus feature data of the monkeypox virus is obtained through the processed monkeypox virus knowledge graph, and the number of training sets of training is constructed according to the virus feature data of the monkeypox virus, and the final training items of the training set are determined, specifically including:

[0019] Setting a quantity threshold, and obtaining virus feature data of the monkeypox virus of the quantity threshold from the processed monkeypox virus knowledge graph, and initializing the training quantity of the training set according to the virus feature data of the monkeypox virus of the quantity threshold;

[0020] Obtaining the training speed of each training quantity for the current training system, and obtaining the training speed corresponding to the training quantity of the current training set according to the training speed of each training quantity for the current training system and the training quantity of the training set;

[0021] Setting a training speed threshold, when the training speed corresponding to the training quantity of the current training set is greater than the training speed threshold, outputting the training quantity of the training set, and determining the final training items of the training set according to the training quantity of the training set;

[0022] When the training speed corresponding to the training quantity of the current training set is not greater than the training speed threshold, the training quantity of the training set is adjusted until the training speed corresponding to the training quantity of the current training set is greater than the training speed threshold.

[0023] Furthermore, in the method for localizing the animal monkeypox virus based on immunological data analysis, the final training item of the training set is input into the monkeypox virus localization model for training, and the prediction accuracy of the monkeypox virus localization model is monitored, specifically including:

[0024] Inputting the final training item of the training set into the monkeypox virus localization model for training, and introducing a Markov chain to obtain prediction accuracy change characteristic data of the monkeypox virus localization model within a preset time;

[0025] Taking the prediction accuracy characteristic data of each timestamp in the prediction accuracy change characteristic data of the monkeypox virus positioning model within a preset time as a state vector, and constructing a state vector transfer matrix based on the state vector;

[0026] Input the state vector transfer matrix into the Markov chain for calculation, calculate the state transfer probability value of the state vector transferring to another state vector in each timestamp, and set the state transfer probability threshold;

[0027] When the state transition probability value is greater than the state transition probability threshold, the state vector in the corresponding timestamp is updated to another state vector; when the state transition probability value is not greater than the state transition probability threshold, the state vector in the corresponding timestamp is maintained unchanged.

[0028] Further, in the method for localizing the monkeypox virus in animals based on immunological data analysis, the state of training is determined according to the prediction accuracy of the monkeypox virus localization model, specifically including:

[0029] Obtaining prediction accuracy characteristic data of the monkeypox virus positioning model at the current timestamp, and setting a prediction accuracy characteristic data threshold, and determining whether the prediction accuracy characteristic data of the monkeypox virus positioning model at the current timestamp is greater than the prediction accuracy characteristic data threshold;

[0030] When the prediction accuracy feature data of the monkeypox virus positioning model at the current timestamp is greater than the prediction accuracy feature data threshold, the training of the monkeypox virus positioning model is completed, and the model parameters of the monkeypox virus positioning model are saved;

[0031] When the prediction accuracy feature data of the monkeypox virus localization model at the current timestamp is not greater than the prediction accuracy feature data threshold, the monkeypox virus localization model is continuously trained.

[0032] The second aspect of the present invention provides an animal monkeypox virus localization system based on immunological data analysis, comprising a memory and a processor, wherein the memory comprises an animal monkeypox virus localization method program based on immunological data analysis, and when the animal monkeypox virus localization method program based on immunological data analysis is executed by the processor, any step of the animal monkeypox virus localization method based on immunological data analysis is implemented.

[0033] The third aspect of the present invention provides a computer-readable storage medium, which includes a program for a method for locating animal monkeypox virus based on immunological data analysis. When the program for the method for locating animal monkeypox virus based on immunological data analysis is executed by a processor, the steps of any one of the methods for locating animal monkeypox virus based on immunological data analysis are implemented.

[0034] The present invention solves the defects existing in the background technology and has the following beneficial effects:

[0035] The present invention obtains sample data of monkeypox virus, extracts components of the sample data of monkeypox virus, obtains immunological data of monkeypox virus, constructs a monkeypox virus localization model based on a multi-layer perceptron neural network, and then constructs a monkeypox virus knowledge graph according to the immunological data of monkeypox virus, and performs data enhancement processing on virus feature data in the monkeypox virus knowledge graph to obtain the processed monkeypox virus knowledge graph, thereby obtaining virus feature data of monkeypox virus through the processed monkeypox virus knowledge graph, and constructs the training quantity of a training set according to the virus feature data of monkeypox virus, determines the final training items of the training set, and finally inputs the final training items of the training set into the monkeypox virus localization model for training, monitors the prediction accuracy of the monkeypox virus localization model, and determines the state of training according to the prediction accuracy of the monkeypox virus localization model. The present invention can improve the prediction accuracy of the model by adjusting the training speed of the training system to avoid the training speed being too fast or too slow during model training. The prediction accuracy of the model is monitored by fusing the Markov model. The prediction accuracy of the model is updated in time while meeting the requirements, thereby reducing the amount of model training. BRIEF DESCRIPTION OF THE DRAWINGS

[0036] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, drawings of other embodiments can be obtained based on these drawings without paying creative work.

[0037] Figure 1 The overall flow chart of the method for localizing the animal monkeypox virus based on immunological data analysis is shown;

[0038] Figure 2 A partial method flow chart of a method for localizing monkeypox virus in animals based on immunological data analysis is shown;

[0039] Figure 3 A system block diagram of the animal monkeypox virus localization system based on immunological data analysis is shown. DETAILED DESCRIPTION

[0040] In order to more clearly understand the above-mentioned purpose, features and advantages of the present invention, the present invention is further described in detail below in conjunction with the accompanying drawings and specific embodiments. It should be noted that the embodiments of the present application and the features in the embodiments can be combined with each other without conflict.

[0041] In the following description, many specific details are set forth to facilitate a full understanding of the present invention. However, the present invention may also be implemented in other ways different from those described herein. Therefore, the protection scope of the present invention is not limited to the specific embodiments disclosed below.

[0042] Example 1

[0043] like Figure 1 As shown, the first aspect of the present invention provides an animal monkeypox virus localization method based on immunological data analysis, comprising:

[0044] S102: Obtaining sample data of monkeypox virus, extracting components from the sample data of monkeypox virus, obtaining immunological data of monkeypox virus, and constructing a monkeypox virus localization model based on a multi-layer perceptron neural network;

[0045] S104: constructing a monkeypox virus knowledge graph based on the immunological data of the monkeypox virus, and performing data enhancement processing on the virus feature data in the monkeypox virus knowledge graph to obtain a processed monkeypox virus knowledge graph;

[0046] S106: Obtaining virus feature data of the monkeypox virus through the processed monkeypox virus knowledge graph, constructing the training quantity of the training set according to the virus feature data of the monkeypox virus, and determining the final training items of the training set;

[0047] S108: Inputting the final training item of the training set into the monkeypox virus localization model for training, monitoring the prediction accuracy of the monkeypox virus localization model, and determining the training status according to the prediction accuracy of the monkeypox virus localization model.

[0048] It should be noted that the present invention can improve the prediction accuracy of the model by adjusting the training speed of the training system to avoid too fast or too slow training speed during model training. Moreover, by integrating the Markov model to monitor the prediction accuracy of the model, the prediction accuracy of the model can be updated in time while meeting the requirements, thereby reducing the amount of model training.

[0049] Furthermore, in the method for localizing the animal monkeypox virus based on immunological data analysis, sample data of the monkeypox virus is obtained, and components of the sample data of the monkeypox virus are extracted to obtain immunological data of the monkeypox virus, and a monkeypox virus localization model is constructed based on a multi-layer perceptron neural network, specifically:

[0050] Obtaining sample data of monkeypox virus, and extracting the sample data of monkeypox virus to obtain sample extract, and extracting monkeypox virus genetic material fragments and derivatives related to monkeypox virus from the sample extract by genetic detection technology;

[0051] Obtain monkeypox virus genetic material fragments and derivatives related to monkeypox virus, construct the immunological data of monkeypox virus based on the monkeypox virus genetic material fragments and derivatives related to monkeypox virus, and construct a monkeypox virus localization model based on a multi-layer perceptron neural network.

[0052] It should be noted that the monkeypox virus genetic material fragments and derivatives related to the monkeypox virus include monkeypox DNA fragment sequences, monkeypox RNA fragment sequences and related derived DNA fragment sequences. The sample data of the monkeypox virus includes serum samples, fecal samples and other data.

[0053] like Figure 2 As shown, further, in the animal monkeypox virus positioning method based on immunological data analysis, a monkeypox virus knowledge graph is constructed according to the immunological data of the monkeypox virus, and the virus feature data in the monkeypox virus knowledge graph is enhanced to obtain the processed monkeypox virus knowledge graph, which specifically includes:

[0054] S202: constructing a monkeypox virus knowledge graph and introducing a recurrent spatial attention mechanism to obtain the immunological data of the monkeypox virus, and extracting monkeypox virus genetic material fragments and related derivatives from the immunological data of the monkeypox virus;

[0055] S204: taking the monkeypox virus genetic material fragments and related derivatives as nodes, and inputting the nodes into the cyclic spatial attention mechanism, processing the nodes, and obtaining a normalized feature map with spatial attention;

[0056] S206: performing inner product operation on the normalized feature map with spatial attention and the nodes, focusing the attention on the nodes, generating an attention feature map, and using the attention feature map as the virus feature data after data enhancement;

[0057] S208: Input the enhanced virus feature data into the storage space of the monkeypox virus knowledge graph for storage, configure the query address, and regularly update the monkeypox virus knowledge graph.

[0058] It should be noted that this method can construct a monkeypox virus knowledge graph and process it through a cyclic spatial attention mechanism, which can focus attention on the nodes, generate an attention feature graph, and improve the query speed for related sequence fragments.

[0059] Furthermore, in the animal monkeypox virus localization method based on immunological data analysis, the virus feature data of the monkeypox virus is obtained through the processed monkeypox virus knowledge graph, and the number of training sets of training is constructed according to the virus feature data of the monkeypox virus, and the final training items of the training set are determined, including:

[0060] Setting a quantity threshold, and obtaining virus feature data of the monkeypox virus with the quantity threshold from the processed monkeypox virus knowledge graph, and initializing the training quantity of the training set according to the virus feature data of the monkeypox virus with the quantity threshold;

[0061] Obtain the training speed of each training quantity for the current training system, and obtain the training speed corresponding to the training quantity of the current training set according to the training speed of each training quantity for the current training system and the training quantity of the training set;

[0062] A training speed threshold is set. When the training speed corresponding to the training quantity of the current training set is greater than the training speed threshold, the training quantity of the training set is output, and the final training items of the training set are determined according to the training quantity of the training set.

[0063] When the training speed corresponding to the training quantity of the current training set is not greater than the training speed threshold, the training quantity of the training set is adjusted until the training speed corresponding to the training quantity of the current training set is greater than the training speed threshold.

[0064] It should be noted that since the training system and data processing device (such as a central processing unit) have a certain data processing upper limit, this method can continuously optimize the number of training sets in the training set, so that the training speed is kept within a certain threshold range, thereby improving the prediction accuracy of the model and more accurately locating the monkeypox DNA sequence, RNA sequence, etc.

[0065] Furthermore, in the animal monkeypox virus localization method based on immunological data analysis, the final training items of the training set are input into the monkeypox virus localization model for training, and the prediction accuracy of the monkeypox virus localization model is monitored, specifically including:

[0066] The final training items of the training set are input into the monkeypox virus localization model for training, and the Markov chain is introduced to obtain the prediction accuracy change characteristic data of the monkeypox virus localization model within a preset time;

[0067] The prediction accuracy characteristic data of each timestamp in the prediction accuracy change characteristic data of the monkeypox virus positioning model within a preset time is used as a state vector, and a state vector transfer matrix is ​​constructed based on the state vector;

[0068] The state vector transfer matrix is ​​input into the Markov chain for calculation, the state transfer probability value of the state vector transferring to another state vector in each timestamp is calculated, and the state transfer probability threshold is set;

[0069] When the state transition probability value is greater than the state transition probability threshold, the state vector in the corresponding timestamp is updated to another state vector. When the state transition probability value is not greater than the state transition probability threshold, the state vector in the corresponding timestamp is maintained unchanged.

[0070] It should be noted that when the state transition probability value is greater than the state transition probability threshold, the state vector in the corresponding timestamp is updated to another state vector. When the state transition probability value is not greater than the state transition probability threshold, the state vector in the corresponding timestamp is maintained unchanged, the state can be updated in time to stop training, and finally reduce the amount of model training.

[0071] Furthermore, in the method for localizing the monkeypox virus in animals based on immunological data analysis, the state of training is determined according to the prediction accuracy of the monkeypox virus localization model, specifically including:

[0072] Obtain prediction accuracy feature data of the monkeypox virus positioning model at the current timestamp, set a prediction accuracy feature data threshold, and determine whether the prediction accuracy feature data of the monkeypox virus positioning model at the current timestamp is greater than the prediction accuracy feature data threshold;

[0073] When the prediction accuracy feature data of the monkeypox virus positioning model at the current timestamp is greater than the prediction accuracy feature data threshold, the training of the monkeypox virus positioning model is completed, and the model parameters of the monkeypox virus positioning model are saved;

[0074] When the prediction accuracy feature data of the monkeypox virus positioning model at the current timestamp is not greater than the prediction accuracy feature data threshold, the monkeypox virus positioning model is continuously trained.

[0075] In addition, the method further comprises:

[0076] The working temperature conditions and the training speed of the training system under various training amounts are obtained through big data, and a training speed prediction model of the training system is built based on a deep neural network, introducing a graph neural network.

[0077] Input each operating temperature condition and the training speed of the training system under each training amount into the graph neural network, with the operating temperature as the first node, the training amount as the second node, and the training speed as the third node;

[0078] Constructing a directed description relationship, connecting the first node, the second node, and the third node based on the directed description relationship, constructing a topological structure graph, and obtaining a related adjacency matrix based on the topological structure graph;

[0079] Inputting the relevant adjacency matrix into the training speed prediction model of the training system for training, obtaining the training speed prediction model of the training system after training, and obtaining the operating temperature information of the current training system and the training amount of the training data;

[0080] Input the working temperature information of the current training system and the training amount of the training data into the training speed prediction model of the training system after training to make a prediction, and obtain the training speed of the training system under the working temperature information of the current training system and the training amount of the training data;

[0081] The real-time training speed is updated according to the working temperature information of the current training system and the training speed of the training system under the training amount of training data.

[0082] It should be noted that different operating temperatures will affect the data processing capacity of the training system and the data processing system, thereby affecting the training speed of the model. This method can optimize the training amount of training data, thereby making the model training more reasonable.

[0083] Example 2

[0084] like Figure 3 As shown, the second aspect of the present invention provides an animal monkeypox virus localization system 4 based on immunological data analysis, including a memory 41 and a processor 42. The memory 41 includes an animal monkeypox virus localization method program based on immunological data analysis. When the animal monkeypox virus localization method program based on immunological data analysis is executed by the processor 42, the solution of Example 1 is implemented, including:

[0085] Obtain sample data of monkeypox virus, extract components from the sample data of monkeypox virus, obtain immunological data of monkeypox virus, and build a monkeypox virus localization model based on a multi-layer perceptron neural network;

[0086] Constructing a monkeypox virus knowledge graph based on the immunological data of the monkeypox virus, and performing data enhancement processing on the virus feature data in the monkeypox virus knowledge graph to obtain a processed monkeypox virus knowledge graph;

[0087] Obtaining virus feature data of the monkeypox virus through the processed monkeypox virus knowledge graph, constructing the number of training sets for training according to the virus feature data of the monkeypox virus, and determining the final training items of the training set;

[0088] The final training items of the training set are input into the monkeypox virus localization model for training, and the prediction accuracy of the monkeypox virus localization model is monitored, and the status of the training is determined according to the prediction accuracy of the monkeypox virus localization model.

[0089] Furthermore, in the animal monkeypox virus localization system based on immunological data analysis, sample data of the monkeypox virus is obtained, and components of the sample data of the monkeypox virus are extracted to obtain immunological data of the monkeypox virus, and a monkeypox virus localization model is constructed based on a multi-layer perceptron neural network, specifically:

[0090] Obtaining sample data of monkeypox virus, and extracting the sample data of monkeypox virus to obtain sample extract, and extracting monkeypox virus genetic material fragments and derivatives related to monkeypox virus from the sample extract by genetic detection technology;

[0091] Obtain monkeypox virus genetic material fragments and derivatives related to monkeypox virus, construct the immunological data of monkeypox virus based on the monkeypox virus genetic material fragments and derivatives related to monkeypox virus, and construct a monkeypox virus localization model based on a multi-layer perceptron neural network.

[0092] Furthermore, in the animal monkeypox virus localization system based on immunological data analysis, a monkeypox virus knowledge graph is constructed according to the immunological data of the monkeypox virus, and the virus feature data in the monkeypox virus knowledge graph is enhanced to obtain the processed monkeypox virus knowledge graph, which specifically includes:

[0093] Construct a knowledge graph of monkeypox virus and introduce a recurrent spatial attention mechanism to obtain the immunological data of monkeypox virus and extract the genetic material fragments and related derivatives of monkeypox virus from the immunological data of monkeypox virus;

[0094] The monkeypox virus genetic material fragments and related derivatives are used as nodes, and the nodes are input into the recurrent spatial attention mechanism to process the nodes and obtain a normalized feature map with spatial attention;

[0095] Perform inner product operations on the normalized feature graph with spatial attention and nodes, focus attention on the nodes, generate an attention feature graph, and use the attention feature graph as the virus feature data after data enhancement;

[0096] The enhanced virus feature data is input into the storage space of the monkeypox virus knowledge graph for storage, and the query address is configured to regularly update the monkeypox virus knowledge graph.

[0097] Furthermore, in the animal monkeypox virus localization system based on immunological data analysis, the virus feature data of the monkeypox virus is obtained through the processed monkeypox virus knowledge graph, and the number of training sets of training is constructed according to the virus feature data of the monkeypox virus, and the final training items of the training set are determined, including:

[0098] Setting a quantity threshold, and obtaining virus feature data of the monkeypox virus with the quantity threshold from the processed monkeypox virus knowledge graph, and initializing the training quantity of the training set according to the virus feature data of the monkeypox virus with the quantity threshold;

[0099] Obtain the training speed of each training quantity for the current training system, and obtain the training speed corresponding to the training quantity of the current training set according to the training speed of each training quantity for the current training system and the training quantity of the training set;

[0100] A training speed threshold is set. When the training speed corresponding to the training quantity of the current training set is greater than the training speed threshold, the training quantity of the training set is output, and the final training items of the training set are determined according to the training quantity of the training set.

[0101] When the training speed corresponding to the training quantity of the current training set is not greater than the training speed threshold, the training quantity of the training set is adjusted until the training speed corresponding to the training quantity of the current training set is greater than the training speed threshold.

[0102] Furthermore, in the animal monkeypox virus localization system based on immunological data analysis, the final training items of the training set are input into the monkeypox virus localization model for training, and the prediction accuracy of the monkeypox virus localization model is monitored, specifically including:

[0103] The final training items of the training set are input into the monkeypox virus localization model for training, and the Markov chain is introduced to obtain the prediction accuracy change characteristic data of the monkeypox virus localization model within a preset time;

[0104] The prediction accuracy characteristic data of each timestamp in the prediction accuracy change characteristic data of the monkeypox virus positioning model within a preset time is used as a state vector, and a state vector transfer matrix is ​​constructed based on the state vector;

[0105] The state vector transfer matrix is ​​input into the Markov chain for calculation, the state transfer probability value of the state vector transferring to another state vector in each timestamp is calculated, and the state transfer probability threshold is set;

[0106] When the state transition probability value is greater than the state transition probability threshold, the state vector in the corresponding timestamp is updated to another state vector. When the state transition probability value is not greater than the state transition probability threshold, the state vector in the corresponding timestamp is maintained unchanged.

[0107] Furthermore, in the animal monkeypox virus localization system based on immunological data analysis, the training status is determined according to the prediction accuracy of the monkeypox virus localization model, specifically including:

[0108] Obtain prediction accuracy feature data of the monkeypox virus positioning model at the current timestamp, set a prediction accuracy feature data threshold, and determine whether the prediction accuracy feature data of the monkeypox virus positioning model at the current timestamp is greater than the prediction accuracy feature data threshold;

[0109] When the prediction accuracy feature data of the monkeypox virus positioning model at the current timestamp is greater than the prediction accuracy feature data threshold, the training of the monkeypox virus positioning model is completed, and the model parameters of the monkeypox virus positioning model are saved;

[0110] When the prediction accuracy feature data of the monkeypox virus positioning model at the current timestamp is not greater than the prediction accuracy feature data threshold, the monkeypox virus positioning model is continuously trained.

[0111] Example 3

[0112] The third aspect of the present invention provides a computer-readable storage medium, which includes an animal monkeypox virus localization method program based on immunological data analysis. When the animal monkeypox virus localization method program based on immunological data analysis is executed by a processor, the scheme of Example 1 is implemented.

[0113] In the several embodiments provided in the present application, it should be understood that the disclosed devices and methods can be implemented in other ways. The device embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation, such as: multiple units or components can be combined, or can be integrated into another system, or some features can be ignored or not executed. In addition, the coupling, direct coupling, or communication connection between the components shown or discussed can be through some interfaces, and the indirect coupling or communication connection of the devices or units can be electrical, mechanical or other forms.

[0114] The units described above as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units; they may be located in one place or distributed on multiple network units; some or all of the units may be selected according to actual needs to achieve the purpose of the present embodiment.

[0115] In addition, all functional units in the embodiments of the present invention may be integrated into one processing unit, or each unit may be separately used as a unit, or two or more units may be integrated into one unit; the above-mentioned integrated units may be implemented in the form of hardware or in the form of hardware plus software functional units.

[0116] A person of ordinary skill in the art can understand that: all or part of the steps of implementing the above method embodiments can be completed by hardware related to program instructions, and the aforementioned program can be stored in a computer-readable storage medium. When the program is executed, it executes the steps of the above method embodiments; and the aforementioned storage medium includes: mobile storage devices, read-only memories (ROM, Read-Only Memory), random access memories (RAM, Random Access Memory), magnetic disks or optical disks, and other media that can store program codes.

[0117] Alternatively, if the above-mentioned integrated unit of the present invention is implemented in the form of a software function module and sold or used as an independent product, it can also be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the embodiment of the present invention can be essentially or partly reflected in the form of a software product that contributes to the prior art. The computer software product is stored in a storage medium and includes several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the methods of each embodiment of the present invention. The aforementioned storage medium includes: various media that can store program codes, such as mobile storage devices, ROM, RAM, magnetic disks or optical disks.

[0118] The above are only specific embodiments of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art who is familiar with the technical field can easily think of changes or substitutions within the technical scope disclosed by the present invention, which should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention should be based on the protection scope of the claims.

Claims

1. A method for localizing monkeypox virus in animals based on immunological data analysis, characterized in that: include: Obtaining sample data of monkeypox virus, extracting components from the sample data of monkeypox virus, obtaining immunological data of monkeypox virus, and constructing a monkeypox virus localization model based on a multi-layer perceptron neural network; Constructing a monkeypox virus knowledge graph based on the immunological data of the monkeypox virus, and performing data enhancement processing on the virus feature data in the monkeypox virus knowledge graph to obtain a processed monkeypox virus knowledge graph; Obtaining virus feature data of the monkeypox virus through the processed monkeypox virus knowledge graph, constructing the number of training items of the training set according to the virus feature data of the monkeypox virus, and determining the final training items of the training set; The final training item of the training set is input into the monkeypox virus localization model for training, and the prediction accuracy of the monkeypox virus localization model is monitored, and the training status is determined according to the prediction accuracy of the monkeypox virus localization model.

2. The method for locating animal monkeypox virus based on immunological data analysis according to claim 1, characterized in that: Obtain sample data of monkeypox virus, extract components from the sample data of monkeypox virus, obtain immunological data of monkeypox virus, and construct a monkeypox virus localization model based on a multi-layer perceptron neural network, specifically: Obtaining sample data of monkeypox virus, and extracting the sample data of monkeypox virus to obtain a sample extract, and extracting monkeypox virus genetic material fragments and derivatives related to monkeypox virus from the sample extract by gene detection technology; The monkeypox virus genetic material fragments and derivatives related to the monkeypox virus are obtained, and the immunological data of the monkeypox virus is constructed based on the monkeypox virus genetic material fragments and derivatives related to the monkeypox virus, and a monkeypox virus localization model is constructed based on a multi-layer perceptron neural network.

3. The method for localizing animal monkeypox virus based on immunological data analysis according to claim 1, characterized in that: Constructing a monkeypox virus knowledge graph according to the immunological data of the monkeypox virus, and performing data enhancement processing on the virus feature data in the monkeypox virus knowledge graph to obtain the processed monkeypox virus knowledge graph, specifically including: Construct a monkeypox virus knowledge graph and introduce a recurrent spatial attention mechanism to obtain the immunological data of the monkeypox virus, and extract the monkeypox virus genetic material fragments and related derivatives from the immunological data of the monkeypox virus; Taking the monkeypox virus genetic material fragments and related derivatives as nodes, and inputting the nodes into the cyclic spatial attention mechanism, processing the nodes, and obtaining a normalized feature map with spatial attention; Performing an inner product operation on the normalized feature map with spatial attention and the node, focusing the attention on the node, generating an attention feature map, and using the attention feature map as the virus feature data after data enhancement; The virus feature data after data enhancement is input into the storage space of the monkeypox virus knowledge graph for storage, and a query address is configured to regularly update the monkeypox virus knowledge graph.

4. The method for locating animal monkeypox virus based on immunological data analysis according to claim 1, characterized in that: Obtaining virus feature data of the monkeypox virus through the processed monkeypox virus knowledge graph, and constructing the training quantity of the training set according to the virus feature data of the monkeypox virus, and determining the final training items of the training set, specifically including: Setting a quantity threshold, and obtaining virus feature data of the monkeypox virus of the quantity threshold from the processed monkeypox virus knowledge graph, and initializing the training quantity of the training set according to the virus feature data of the monkeypox virus of the quantity threshold; Obtaining the training speed of each training quantity for the current training system, and obtaining the training speed corresponding to the training quantity of the current training set according to the training speed of each training quantity for the current training system and the training quantity of the training set; Setting a training speed threshold, when the training speed corresponding to the training quantity of the current training set is greater than the training speed threshold, outputting the training quantity of the training set, and determining the final training items of the training set according to the training quantity of the training set; When the training speed corresponding to the training quantity of the current training set is not greater than the training speed threshold, the training quantity of the training set is adjusted until the training speed corresponding to the training quantity of the current training set is greater than the training speed threshold.

5. The method for locating animal monkeypox virus based on immunological data analysis according to claim 1, characterized in that: Inputting the final training item of the training set into the monkeypox virus localization model for training, and monitoring the prediction accuracy of the monkeypox virus localization model, specifically comprising: Inputting the final training item of the training set into the monkeypox virus localization model for training, and introducing a Markov chain to obtain prediction accuracy change characteristic data of the monkeypox virus localization model within a preset time; Taking the prediction accuracy characteristic data of each timestamp in the prediction accuracy change characteristic data of the monkeypox virus positioning model within a preset time as a state vector, and constructing a state vector transfer matrix based on the state vector; Input the state vector transfer matrix into the Markov chain for calculation, calculate the state transfer probability value of the state vector transferring to another state vector in each timestamp, and set the state transfer probability threshold; When the state transition probability value is greater than the state transition probability threshold, the state vector in the corresponding timestamp is updated to another state vector; when the state transition probability value is not greater than the state transition probability threshold, the state vector in the corresponding timestamp is maintained unchanged.

6. The method for locating animal monkeypox virus based on immunological data analysis according to claim 1, characterized in that: The training status is determined according to the prediction accuracy of the monkeypox virus localization model, specifically including: Obtaining prediction accuracy characteristic data of the monkeypox virus positioning model at the current timestamp, and setting a prediction accuracy characteristic data threshold, and determining whether the prediction accuracy characteristic data of the monkeypox virus positioning model at the current timestamp is greater than the prediction accuracy characteristic data threshold; When the prediction accuracy feature data of the monkeypox virus positioning model at the current timestamp is greater than the prediction accuracy feature data threshold, the training of the monkeypox virus positioning model is completed, and the model parameters of the monkeypox virus positioning model are saved; When the prediction accuracy feature data of the monkeypox virus localization model at the current timestamp is not greater than the prediction accuracy feature data threshold, the monkeypox virus localization model is continuously trained.

7. An animal monkeypox virus localization system based on immunological data analysis, characterized in that: It comprises a memory and a processor, wherein the memory comprises a program of a method for locating animal monkeypox virus based on immunological data analysis, and when the program of the method for locating animal monkeypox virus based on immunological data analysis is executed by the processor, the steps of the method for locating animal monkeypox virus based on immunological data analysis as described in any one of claims 1 to 6 are implemented.

8. A computer-readable storage medium, characterized in that: The computer-readable storage medium includes a program for a method for locating animal monkeypox virus based on immunological data analysis. When the program for locating animal monkeypox virus based on immunological data analysis is executed by a processor, the steps of the method for locating animal monkeypox virus based on immunological data analysis as described in any one of claims 1 to 6 are implemented.

Images