Influenza B virus antigenicity rapid identification method, device, terminal and medium
By extracting the characteristics of influenza B virus and establishing an antigenic prediction model, the problem of long and low efficiency of antigenic identification of influenza B viruses in the prior art is solved, and rapid and accurate antigenic identification and vaccine strain recommendation are achieved. Improved the effectiveness of the flu vaccine.
Patent Information
- Application Number
- CN202410989243.6
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-07-23
- Publication Date
- 2024-11-12
- Estimated Expiration
- 2044-07-23
AI Technical Summary
The existing antigenic identification methods for influenza B viruses are time-consuming and inefficient, and cannot meet the needs of large-scale rapid identification, especially in the assessment of strain antigenicity in Victoria and Yamagata lineages.
By obtaining the HA1 sequence sample data of the Victoria and Yamagata lineages of the influenza B virus, the antigenic epitope, physical and chemical properties, nitrogen glycosylation sites and receptor binding region characteristics were extracted, and antigenic prediction models PREDAC-BV and PREDAC-BY were established. Antigenic prediction and identification are used using machine learning algorithms.
It has achieved rapid identification of antigenicity of influenza B virus, improved efficiency, accurately predicted the antigenicity of the strain, and assisted in the recommendation of vaccine strains, improving the effectiveness and production efficiency of influenza vaccines.
Smart Images

Figure CN118942538A_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the technical field of virus antigen research, and in particular to a method, device, terminal and medium for rapid identification of antigenicity of type B influenza virus. Background Art
[0002] Seasonal influenza is a huge threat to human health. Currently, influenza A and B are the main types prevalent in the population. Among them, influenza B viruses include two lineages, Victoria and Yamagata, accounting for about 1 / 3 of the global influenza disease burden, and usually have higher infection rates and mortality rates in children, posing a huge threat to human health.
[0003] Flu vaccination is currently the most effective way to prevent influenza virus infection and related deaths. However, the influenza virus accumulates mutations in its surface proteins, causing changes in its antigenicity, which reduces the effectiveness of existing vaccines. We need to replace the vaccine with one that matches the antigenicity of the current influenza strains in a timely manner in order to effectively prevent and control the disease.
[0004] Therefore, it is very important to accurately and quickly identify the antigenicity of influenza viruses to improve the effectiveness of influenza vaccines. The gold standard HI test (Hemagglutination Inhibition Assay) for identifying the antigenicity of influenza virus strains is currently used, but this identification method requires huge human, material and financial resources, has technical problems such as long time consumption and low efficiency, and is not suitable for large-scale antigenic identification of influenza strains. Researchers have developed some predictive tools that can quickly and efficiently identify the antigenicity of influenza A viruses, but there are currently no predictive tools for antigenic identification of influenza B viruses.
[0005] Therefore, we urgently need a technology that can accurately and quickly identify the antigenicity of influenza B virus so that we can timely evaluate the antigenicity of the two lineages of influenza B virus strains that are currently prevalent. This is of great significance for improving the effectiveness of influenza vaccines, the efficiency of research and development and production, and influenza prevention and control. Summary of the invention
[0006] The present application provides a method, device, terminal and medium for rapid identification of influenza B virus antigenicity, which is used to solve the technical problems that the existing method for rapid identification of influenza B virus antigenicity is limited by unstable factors such as experimental conditions and technical level, and has the problems of long time consumption and low efficiency.
[0007] In order to solve the above technical problems, the first aspect of the present application provides a method for rapid antigenicity identification of influenza B virus, comprising:
[0008] Obtaining preset HA1 sequence sample data and sample antigenicity data of the Victoria lineage and the Yamagata lineage of influenza B virus, respectively, wherein the sample antigenicity data respectively include antigenic relationships between strains within the Victoria lineage and the Yamagata lineage;
[0009] Extracting virus features from the Victoria lineage and Yamagata lineage HA1 sequence sample data of influenza B virus, respectively, and obtaining virus features related to antigenic changes corresponding to the Victoria lineage and Yamagata lineage sample data sets, respectively, wherein the virus features specifically include: antigen epitope features, physicochemical property features, nitrogen glycosylation sites, and receptor binding region features;
[0010] Using the virus characteristics and the sample antigenicity data as model training data, through model training, antigenicity prediction models PREDAC-BV and PREDAC-BY corresponding to Victoria lineage and Yamagata lineage of influenza B virus are obtained respectively;
[0011] Obtain the HA1 amino acid sequence of the influenza Victoria lineage or Yamagata lineage strain of the influenza B virus to be identified, and input the HA1 amino acid sequence of the influenza B virus strain into the antigenicity prediction model of the corresponding lineage to determine the antigenicity identification result of the influenza B virus strain according to the output result of the antigenicity prediction model.
[0012] Preferably, the method for extracting the antigen epitope characteristic value specifically includes:
[0013] According to the preset amino acid site screening conditions, the amino acid sites that meet the amino acid site screening conditions are determined from the HA1 protein sequences of the influenza B Victoria lineage and the Yamagata lineage virus samples as the antigenic sites of the two lineages respectively;
[0014] Clustering the antigenic sites to divide the antigenic sites into five antigenic epitopes;
[0015] Using the PSI-BLAST algorithm, a PSSM matrix containing each of the antigenic sites is constructed;
[0016] According to a pair of influenza B virus sample data of the same lineage, the sum of the absolute values of the differences between the PSSM scores of the two amino acid residues corresponding to each site on the antigenic epitope is taken as the characteristic value of the antigenic epitope. When the characteristic values of all antigenic epitopes are obtained, the characteristic values of the antigenic epitope are output.
[0017] Preferably, the method for extracting the characteristic value of the physical and chemical property specifically includes:
[0018] According to the amino acid index database, the physical and chemical property indicators corresponding to the Victoria lineage and the Yamagata lineage are determined, wherein the physical and chemical property indicators include: hydrophobicity, volume, charge, polarity and accessible surface area;
[0019] According to a pair of influenza B virus sample data of the same lineage and any selected physicochemical property index, the average value of the corresponding physicochemical property score difference at all amino acid sites of the pair of strains is calculated as the characteristic value of the physicochemical property. When a pair of strains has more than three different amino acid sites, the average value of the first three sites with the largest corresponding physicochemical property score difference at all amino acid sites is taken as the characteristic value of the physicochemical property. After the characteristic values of all physicochemical property indexes are obtained, the characteristic value of the physicochemical property is output.
[0020] Preferably, the method for extracting the receptor binding region features specifically includes:
[0021] According to a pair of influenza B virus sample data of the same lineage, the average value of the shortest Euclidean distance from the sites with different amino acids on the HA1 protein sequences of the pair of strains to the receptor binding region characteristics is calculated as the receptor binding region characteristics.
[0022] Preferably, the training method of the antigenicity prediction model includes:
[0023] Based on the influenza B Victoria lineage and Yamagata lineage virus sample HA1 sequence data and the sample antigenicity data, combined with a plurality of preset initial algorithm models, the Victoria lineage and Yamagata lineage sample HA1 sequence data and the sample antigenicity data are used as inputs of each initial algorithm model, each initial algorithm model is trained, and a five-fold cross validation is performed;
[0024] Based on the cross-validation results obtained, the optimal initial algorithm model corresponding to each lineage is determined to obtain the best antigenicity prediction model for different lineages.
[0025] Preferably, the types of the initial algorithm models include: XGBoost, LightGBM, RF and SVM.
[0026] Preferably, after determining the antigenic identification result of the influenza B virus strain, the method further comprises:
[0027] Based on the constructed prediction model, the antigenic relationship between all known sequences of Victoria lineage strains or Yamagata lineage strains is predicted, and an antigenic similarity network between strains is constructed. The Markov clustering method is used to cluster the antigenic similarity network of strains of the same lineage to identify different antigenic classes. The recommendation of vaccine strains is assisted by analyzing the antigenic similarity between the same lineage strains prevalent in the current epidemic season and the same lineage antigen cluster that dominated the epidemic in the past. When the antigenic similarity is low, it is recommended that the vaccine strain of the same lineage should be replaced, otherwise the vaccine strain should not be replaced.
[0028] At the same time, the second aspect of the present application provides a device for rapid identification of influenza B virus antigenicity, comprising:
[0029] A sample data acquisition unit, used to respectively acquire HA1 sequence sample data and sample antigenicity data of the preset Victoria lineage and Yamagata lineage of influenza B virus, wherein the sample antigenicity data respectively include the antigenic relationship between strains within the Victoria lineage and the Yamagata lineage;
[0030] An antigen feature extraction unit is used to extract virus features from the Victoria lineage and Yamagata lineage HA1 sequence sample data of the influenza B virus, respectively, to obtain virus features related to antigenic changes corresponding to the Victoria lineage and Yamagata lineage sample data sets, respectively, wherein the virus features specifically include: antigen epitope features, physicochemical property features, nitrogen glycosylation sites, and receptor binding region features;
[0031] An antigenicity prediction model training unit, used to obtain antigenicity prediction models PREDAC-BV and PREDAC-BY corresponding to the Victoria lineage and the Yamagata lineage of influenza B virus respectively through model training based on the virus characteristics and the sample antigenicity data as model training data;
[0032] The antigenicity identification unit is used to obtain the HA1 amino acid sequence of the influenza Victoria lineage or Yamagata lineage strain of the influenza B virus to be identified, and input the HA1 amino acid sequence of the influenza B virus strain into the antigenicity prediction model of the corresponding lineage to determine the antigenicity identification result of the influenza B virus strain according to the output result of the antigenicity prediction model.
[0033] The third aspect of the present application provides a terminal for rapid antigenicity identification of influenza B virus, comprising: a memory and a processor;
[0034] The memory is used to store program codes corresponding to a rapid antigenic identification of type B influenza virus as provided in the first aspect of the present application;
[0035] The processor is used for reading and executing the program code.
[0036] The fourth aspect of the present application provides a computer-readable storage medium, in which a program code corresponding to the rapid antigenicity identification of type B influenza virus provided in the first aspect of the present application is stored.
[0037] It can be seen from the above technical solutions that this application has the following advantages:
[0038] The technical solution provided by the present application is based on feature extraction of HA1 protein sequence sample data and antigenic sample data of Victoria lineage and Yamagata lineage of influenza B virus, to obtain virus features corresponding to the sample data sets of the two lineages of influenza B virus, and use the virus features and sample antigenic data as model training data, through model training, to obtain antigenic prediction models PREDAC-BV and PREDAC-BY corresponding to the two lineages of influenza B virus, respectively, and then the Victoria lineage or Yamagata lineage of influenza B virus to be identified is input into the above-mentioned antigenic prediction model to determine the identification result of the strain according to the output result of the antigenic prediction model. The present application establishes antigenic prediction models for the two lineages of Victoria and Yamagata in influenza B virus based on a machine learning algorithm, and then realizes rapid prediction of the antigenicity of the two lineages of influenza B virus based on the constructed antigenic prediction model, thereby improving the efficiency of antigenic identification of influenza B virus. At the same time, this application clusters all Victoria lineage strains of influenza B virus based on the constructed prediction model to obtain different antigenic classes, and assists in vaccine strain recommendation by calculating the antigenic similarity between the strains of the current epidemic season and the antigenic clusters that dominated the epidemic in the past, which helps to improve the effectiveness of influenza vaccines in preventing Victoria lineage infections. BRIEF DESCRIPTION OF THE DRAWINGS
[0039] In order to more clearly illustrate the embodiments of the present application 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 application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative labor.
[0040] Figure 1 This is a schematic diagram of a process for an embodiment of a method for rapid antigenicity identification of type B influenza virus provided in the present application.
[0041] Figure 2 This is an overall logic block diagram of a method for rapid antigenic identification of type B influenza virus provided in this application.
[0042] Figure 3 The present invention provides a flow chart for determining antigenic epitopes of Victoria lineage and Yamagata lineage of influenza B virus.
[0043] Figure 4 This is a diagram showing the results of the antigen prediction model used in this application to assist in recommending Victoria lineage vaccine strains.
[0044] Figure 5 This is a schematic diagram of the structure of an embodiment of a device for rapid identification of influenza B virus antigenicity provided in the present application.
[0045] Figure 6 This is a schematic diagram of the structure of an embodiment of a terminal for rapid antigenic identification of type B influenza virus provided in the present application. DETAILED DESCRIPTION
[0046] The embodiments of the present application provide a method, device, terminal and medium for rapid identification of influenza B virus antigenicity, which are used to solve the technical problems that the existing influenza B virus identification method is limited by unstable factors such as experimental conditions and technical level, and has the disadvantages of being time-consuming and inefficient.
[0047] In order to make the purpose, features, and advantages of the invention of this application more obvious and easy to understand, the technical solutions in the embodiments of this application will be clearly and completely described below in conjunction with the drawings in the embodiments of this application. Obviously, the embodiments described below are only part of the embodiments of this application, not all of them. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.
[0048] First, a detailed description of an embodiment of a method for rapid antigenic identification of influenza B virus provided by the present application is as follows:
[0049] See also Figure 1 The present embodiment provides a method for rapid identification of influenza B virus antigenicity, comprising:
[0050] Step 101: respectively obtain HA1 sequence sample data and sample antigenicity data on HA (Haemagglutinin) proteins of the Victoria lineage and the Yamagata lineage of the preset influenza B virus.
[0051] Among them, the sample antigenicity data include the antigenic relationship between each strain within the Victoria lineage and the Yamagata lineage.
[0052] It should be noted that the solution provided in this example first obtains the HA1 protein sequence sample data of two preset B influenza virus lineages Victoria and Yamagata, as well as the antigenic data of these B influenza virus sample data. The sample antigenic data can be obtained by collecting existing hemagglutination inhibition test data on the Victoria lineage and the Yamagata lineage to determine the antigenic relationship between some strains. The specific implementation method can refer to the following example:
[0053] Data collection and processing of virus samples: Download the amino acid sequences of HA proteins of Victoria lineage and Yamagata lineage from the global influenza data, and then perform the following processing on the downloaded sequence data:
[0054] 1) First, the sequences were quality controlled and the sequences that met the following criteria were excluded: the sequences whose names did not start with B and whose length was within the box-type Figure 4 Sequences outside the quantile interval of 1.5 times and sequences with lineage mismatches.
[0055] 2) Then, MAFFT (Multiple Alignment using Fast Fourier Transform) was used to align the HA sequences by multiple sequence alignment method. After multiple sequence alignment, the HA1 sequence was extracted from the aligned sequences.
[0056] 3) Finally, the missing and abnormal amino acids (i.e., "-", "X") at the beginning (first 40 amino acids) and end (last 40 amino acids) of the sequence were filled with the mode amino acid of the 10 most similar sequences measured by Hamming distance at the same site, because mutations rarely occur at these positions.
[0057] HI test data collection and processing: Download the Victoria and Yamagata lineage HI test data from the World Influenza Center Laboratory (WIC), and then perform the following processing on the downloaded HI data:
[0058] 1) Based on the results of the HI test, the antigenic relationship between strains A and B was determined using the following formula:
[0059] H aβ =log 2 T aβ -log 2 T aβ (1)
[0060] Among them, H aβ represents the HI titer of strain a produced by titrating the antiserum against reference strain b, T aβIt indicates the maximum dilution of antiserum β against strain b that can effectively prevent cell agglutination caused by strain a. aβ When the absolute value is equal to or greater than 2, the two are defined as antigenically dissimilar, otherwise, they are defined as antigenically similar.
[0061] 2) In order to obtain a more reliable data set, this application only includes strain pairs with two or more HI test results. For strain pairs with two HI test results, only strain pairs with consistent antigenic relationships determined by formula 1 are retained; for strain pairs with more than two HI test results, their antigenic relationships are determined as the mode of the antigenic relationships determined by formula 1.
[0062] The processed HA1 amino acid sequences and the strain pairs whose antigenic relationships were determined by the HI test were matched according to the strain names as the data sets for constructing the antigenic relationship prediction model. Among them, there were 895 pairs in the Victoria lineage (301 pairs were antigenically similar and 594 pairs were antigenically dissimilar) and 751 pairs in the Yamagata lineage (322 pairs were antigenically similar and 429 pairs were antigenically dissimilar).
[0063] In addition, in addition to the above-mentioned method of obtaining data from a public database, sample antigenicity data of the influenza B virus sample data may also be obtained by performing a hemagglutination inhibition test on the influenza B virus sample data and recording the test results.
[0064] Step 102: extract virus features from the HA1 sequence sample data of the Victoria lineage and the Yamagata lineage of influenza B virus, respectively, and obtain virus features related to antigenic changes corresponding to the Victoria lineage and the Yamagata lineage sample data sets, respectively.
[0065] Among them, the virus characteristics specifically include: antigenic epitope characteristics, physical and chemical property characteristics, nitrogen glycosylation sites and receptor binding region characteristics.
[0066] It should be noted that based on the HA1 amino acid sequence data of the influenza B virus Victoria lineage and the Yamagata lineage virus samples obtained in the previous step, the sample data of the two lineages are respectively subjected to virus feature extraction to obtain the virus features of the two lineages. The virus features mentioned in this embodiment are generally features that can affect the antigenicity of the influenza virus HA protein, specifically including: antigen epitope features, physicochemical properties, nitrogen glycosylation sites, and receptor binding region features.
[0067] Among them, the methods for extracting antigen epitope characteristics include:
[0068] 1) According to the preset amino acid site screening conditions, the amino acid sites that meet the amino acid site screening conditions are determined from the HA1 protein sequences of the Victoria lineage and Yamagata lineage virus samples of influenza B virus as the antigenic sites of the two lineages respectively;
[0069] It should be noted that the screening targets corresponding to the amino acid site screening conditions mentioned in this example are: a) selecting surface-exposed amino acid residues; b) selecting potential antigenic sites predicted by ScanNet; c) selecting amino acid residues located in the head domain of the HA protein.
[0070] More specifically, for screening target (a), this embodiment is based on B / Victoria's B / Brisbane / 60 / 2008 crystal structure (pdb 4FQM) and B / Yamagata's B / Yamanashi / 166 / 1998 crystal structure (pdb 4M40), using FreeSASA software to calculate the relative solvent accessibility (RSA) of each residue to determine whether the residue is exposed. Residues (exposed sites) with RSA greater than threshold A are selected as preliminary candidate antigenic sites, and the reference value of threshold A is 15%.
[0071] For screening target (b), this embodiment uses the ScanNet prediction algorithm to predict the probability of each residue being an antigenic site. Based on the output probability results, the top N residues with the highest probability are selected as potential antigenic sites, and the reference value of N is 150.
[0072] For screening target (c), in this example, the head domain of the HA protein of the virus sample (sites 52-281 for B / Victoria and 52-279 for B / Yamagata) is considered to be the main antigenic region of influenza, and therefore the residues located in the head domain are spatially marked.
[0073] In summary, when the amino acid residue at a certain site simultaneously satisfies the conditions that RSA is greater than the threshold A, the probability result output by the ScanNet algorithm ranks among the top 150 with the highest probability, and the site is located in the head domain of the corresponding lineage, it means that the amino acid residue corresponding to the site can be used as an antigenic site. Then, according to the same screening criteria, the union of the A, C, and E chain amino acid sites that meet the above three conditions is selected as the final antigenic site.
[0074] 2) Clustering the antigenic sites into five antigenic epitopes;
[0075] It should be noted that, e) the antigen sites were clustered using the K-Means method to obtain the antigen epitope region. According to the spatial position of the chain A residues, the above-determined antigen sites were divided into five epitopes using K-means. The epitopes of B / Victoria and B / Yamagata were aligned in spatial position by TM-align. The final determined epitopes are shown in Table 1.
[0076] Table 1 Distribution of antigenic epitopes and antigenic sites of influenza B virus Victroia lineage Yamagata lineage
[0077]
[0078] 3) Using the PSI-BLAST algorithm, a PSSM matrix (Position-Specific Scoring Matrix) containing each antigenic site is constructed;
[0079] 4) Taking Victoria pedigree as an example, based on a pair of selected influenza B virus Victoria pedigree sample data, the absolute sum of the difference between the PSSM scores of the two amino acid residues corresponding to each site position on the antigen epitope is used as the characteristic value of the antigen epitope. When the characteristic values of all antigen epitopes are obtained, the characteristic value of the antigen epitope is output. The method of Yamagata to calculate the characteristics of antigen epitopes is the same.
[0080] It should be noted that after the definition of the antigen epitope is completed, the characteristic values related to the epitope are calculated. According to the HA1 sequence of the Victoria lineage and the Yamagata lineage, PSI-BLAST is used to generate 346×20 site-specific scoring matrices (PSSM) of the two lineages to reflect the distribution of 20 amino acids at 346 sites. The PSSM matrix scores the 20 amino acids at each residue position according to the distribution frequency of different amino acids at that position.
[0081] For a pair of strains, the antigenicity score (eigenvalue) of each epitope is calculated based on the sum of the absolute values of the difference between the PSSM matrix scores of the two comparison residues at each residue position on the epitope. If a position involves a deletion or insertion, the PSSM matrix score difference at that position is defined as the maximum value of all absolute differences between the target residue and all 20 amino acids. For strains A and B, the t eigenvalue of epitope e is calculated using the following formula 2:
[0082] pssm(A,B,e)=∑|m(p,e,A p )-m(p,e,B p )| (2)
[0083] In the formula, m(p,e,A p ) represents amino acid A at position p belonging to epitope e p PSSM matrix score. m(p,e,B p ) represents amino acid B at position p belonging to epitope e p The PSSM matrix score.
[0084] The methods for extracting characteristic values of physical and chemical properties include:
[0085] 1) According to the amino acid index database, determine the physical and chemical property indicators corresponding to the Victoria lineage and the Yamagata lineage, where the physical and chemical property indicators include: hydrophobicity, volume, charge, polarity and accessible surface area;
[0086] 2) Taking Victoria pedigree as an example, based on a selected pair of influenza B virus Victoria pedigree sample data and any selected physical and chemical property index, calculate the average value of the physical and chemical property score difference at all amino acid sites of a pair of strains as the characteristic value of the physical and chemical property. When a pair of strains has more than three different amino acid sites, take the average value of the first three sites with the largest physical and chemical property score difference at all amino acid sites as the characteristic value of the physical and chemical property. After obtaining the characteristic values of all physical and chemical property indicators, output the physical and chemical property characteristic value. Yamagata calculates the physical and chemical property characteristics in the same way.
[0087] It should be noted that the present application collected 56 amino acid indices reported to affect the antigenicity of influenza viruses from the amino acid index database (AAindex), which represent five physicochemical properties, including hydrophobicity, volume, charge, polarity and accessible surface area. Each time, one amino acid index is selected from each group of physicochemical properties to form a combination (composed of 5 amino acid indices) for antigenic relationship prediction, and the combination with the highest AUC (Area Under Curve, the area under the ROC curve and the coordinate axis) value is selected for model construction. Finally, five amino acid indices with IDs FAUJ880109, FAUJ8880103, ZIMJ680104, ZIMJ680103, and CHOC760101 were used to construct the antigen prediction model for the Victoria lineage, and five amino acid indices with IDs FAUJ880109, PONJ960101, ZIMJ680104, CHAM820101, and CHOC760102 were used to construct the antigen prediction model for the Yamagata lineage.
[0088] The extraction method of nitrogen glycosylation sites is as follows:
[0089] NetNGlyc was used to predict the nitrogen glycosylation sites of each HA1 sequence. For a pair of strains, the characteristic value of the nitrogen glycosylation site is the number of different nitrogen glycosylation sites in the HA1 sequences of the two strains.
[0090] The methods for extracting receptor binding region features include:
[0091] For a pair of strains, the characteristic value of the receptor binding region is the average of the shortest Euclidean distances from the sites where the amino acids of the HA1 proteins of the two strains are different to the receptor binding region (140-loop, 190-helix, 240-loop). The Euclidean distance between two residues is calculated based on their C-α atoms. Using the pdb structure as a template (Victoria: pdb 4FQM, Yamagata: pdb4M40), the shortest Euclidean distance from a residue to the receptor binding region is the shortest Euclidean distance from the residue to all residues in the receptor binding region. If there are changes in the amino acids at more than three sites, only the shortest three Euclidean distances are considered in the calculation.
[0092] At this point, the data sets for constructing antigenicity prediction models for the Victoria and Yamagata lineages of influenza B virus have been prepared, including 12 features and 1 model prediction target—the antigenic relationship between two strains. The features specifically include 5 features related to epitopes, 5 features related to the physicochemical properties of amino acids, 1 feature related to nitrogen glycosylation, and 1 feature related to the receptor binding region.
[0093] Step 103: Using the virus characteristics and sample antigenicity data as model training data, through model training, antigenicity prediction models PREDAC-BV and PREDAC-BY corresponding to the Victoria lineage and Yamagata lineage of influenza B virus are obtained respectively.
[0094] More specifically, the antigenicity prediction model is trained by:
[0095] Based on the sample data sets and sample antigenicity data of Victoria lineage and Yamagata lineage of influenza B virus, combined with multiple preset initial algorithm models, the Victoria lineage and Yamagata lineage sample HA1 sequence data and sample antigenicity data were used as the input of each initial algorithm model, and each initial algorithm model was trained and subjected to five-fold cross-validation.
[0096] Based on the cross-validation results obtained, the optimal initial algorithm model corresponding to each lineage is determined so that it can be used to train the best antigenicity prediction models for different lineages.
[0097] It should be noted that, based on the above-mentioned 4 groups of 12 features related to antigenic changes, this application tests the performance of four machine learning methods in predicting the antigenic relationship defined by the HI test between the strain pairs within the Victoria lineage and the Yamagata lineage of influenza B virus, including: XGBoost (eXtreme Gradient Boosting, an optimized distributed gradient boosting (Gradient Boosting) framework), LightGBM (Light Gradient Boosting Machine, an optimized distributed gradient boosting (Gradient Boosting) framework), RF (Random Forest) and SVM (Support Vector Machine). Among them, when building the model, SMOTE (Synthetic Minority Over-sampling Technique) is used to balance positive and negative samples, and then the data set is randomly divided into a training set and a test set at a ratio of 4:1. The model is evaluated by cross-validation and independent testing, using accuracy, precision, recall, AUC and F1 scores as evaluation indicators, and the calculation formula is as follows:
[0098]
[0099] Among them, TP represents true positive samples, TN represents true negative samples, FP represents false positive samples, and FN represents false negative samples.
[0100] Then, the machine learning method with the best performance (in the order of AUC, accuracy, precision, recall, and F1 score) in the cross-validation was selected to establish the final antigenicity models PREDAC-BV and PREDAC-BY. The independent set test performance of the model is shown in Table 2.
[0101] Table 2 Independent set test performance of antigen prediction model
[0102]
[0103] Step 104: Obtain the HA1 amino acid sequence of the influenza B virus Victoria lineage or Yamagata lineage strain to be identified, and input the HA1 amino acid sequence of the influenza B virus strain into the antigenicity prediction model of the corresponding lineage to determine the antigenicity identification result of the influenza B virus strain based on the output result of the antigenicity prediction model.
[0104] In addition, the constructed influenza B virus Victoria lineage and Yamagata lineage antigenicity prediction models PREDAC-BV and PREDAC-BY have the following functions:
[0105] 1) Construct an antigenic relationship network. Use PREDAC-BV and PREDAC-BY to predict the antigenic relationship between all pairs of strains in the Victoria Yamagata lineage. Then, select all strain pairs predicted to be antigenically similar, and use Cytoscape to construct the antigenic relationship networks ACnet-BV and ACnet-BY for the Victoria lineage and the Yamagata lineage, respectively. The nodes of the network are strains, and the edges are antigenic similarities. Antigenic similarity is the logarithmic ratio of the probability that two strains are predicted to be antigenically similar to the probability that they are antigenically dissimilar. This network can visually display the antigenic relationship between all influenza strains in the Victoria lineage and the Yamagata lineage, making it easier to study the antigenic similarity of influenza strains at the network level.
[0106] 2) Antigen cluster division. Use MCL to cluster the strains in the above-mentioned antigen relationship network to determine different antigen clusters, wherein the inflation parameter of MCL is selected according to the highest modularity of the network. In the present application, a total of 7 antigen clusters are identified in the Victoria pedigree, namely BJ87, HK01, BR08, CO17, WT19, New, and AU21, wherein the antigen cluster New is an antigen cluster that does not contain vaccine strains identified in the present application, and the remaining 6 antigen clusters all contain vaccine strains that have been used in influenza vaccines, and are named after the abbreviations of the earliest vaccine strains used therein. It can be considered that the antigenic relationship between strains within the same antigen cluster is relatively similar, while the antigenic relationship between strains belonging to different antigen clusters is relatively dissimilar. Through antigen cluster division, the antigenic evolution of the Victoria pedigree and the Yamagta pedigree can be revealed at the network level.
[0107] 3) Analyze the antigenic evolution of the Victoria and Yamagata lineages of influenza B virus. The antigenic evolution of the two lineages of influenza B virus is a process in which new antigenic clusters continuously replace old antigenic clusters. Combined with the antigenic cluster division, regional and temporal distribution of strains, we can trace the evolutionary history of the Victoria and Yamagata lineages of influenza B virus in the northern and southern hemispheres, different continents and even different countries, and draw antigenic evolution maps of the two lineages.
[0108] 4) Recommendation of adjuvant vaccine strains. Based on the antigenic relationship between strains predicted by the antigen prediction model, we can calculate the proportion of antigenically similar strain pairs between all strains in each epidemic season in the northern and southern hemisphere and the antigenic clusters that were previously prevalent. When this proportion is low, it indicates that there has been a significant antigenic change between the strains prevalent in the current epidemic season and the antigenic clusters that were previously prevalent, suggesting that the vaccine strain should be replaced at this time to improve the protective effect of the influenza vaccine. Figure 4 The antigenic similarity ratio between the Victoria pedigree strains in each epidemic season in the northern and southern hemispheres calculated based on the above antigen prediction model PREDAC-BV and the previous major epidemic antigen clusters can be compared with the vaccine strains recommended by the World Health Organization (WHO), so that antigenic changes can be monitored earlier and the replacement of influenza vaccine strains can be prompted earlier. Since the Yamagata pedigree is no longer prevalent in the population since March 2020, the present invention does not recommend adjuvant vaccines for this pedigree.
[0109] The above is a detailed description of an embodiment of a method for rapid antigenicity identification of influenza B virus provided by the present application. The following is a detailed description of an apparatus for rapid antigenicity identification of influenza B virus provided by the present application.
[0110] See also Figure 5 This embodiment provides a device for rapid identification of influenza B virus antigenicity, comprising:
[0111] The sample data acquisition unit 201 is used to respectively acquire HA1 sequence sample data and sample antigenicity data of the preset Victoria lineage and Yamagata lineage of influenza B virus, wherein the sample antigenicity data respectively includes the antigenic relationship between strains within the Victoria lineage and the Yamagata lineage;
[0112] The antigen feature extraction unit 202 is used to extract virus features from the HA1 sequence sample data of the Victoria lineage and the Yamagata lineage of influenza B virus, respectively, to obtain virus features related to antigenic changes corresponding to the Victoria lineage and the Yamagata lineage sample data sets, respectively. The virus features specifically include: antigen epitope features, physical and chemical property features, nitrogen glycosylation sites and receptor binding region features;
[0113] Antigenicity prediction model training unit 203, used to obtain antigenicity prediction models PREDAC-BV and PREDAC-BY corresponding to Victoria lineage and Yamagata lineage of influenza B virus respectively through model training based on virus characteristics and sample antigenicity data as model training data;
[0114] The antigenicity identification unit 204 is used to obtain the HA1 amino acid sequence of the influenza B virus Victoria lineage or Yamagata lineage strain to be identified, and input the HA1 amino acid sequence of the influenza B virus strain into the antigenicity prediction model of the corresponding lineage to determine the antigenicity identification result of the influenza B virus strain according to the output result of the antigenicity prediction model.
[0115] In addition, in addition to the detailed description of the above-mentioned embodiment of the apparatus for rapid antigenicity identification of influenza B virus, the present application also provides a detailed description of an embodiment of a terminal for rapid antigenicity identification of influenza B virus and a computer-readable storage medium.
[0116] See also Figure 6 , This embodiment provides a terminal for rapid identification of influenza B virus antigenicity, the types of which include but are not limited to: personal computers, industrial computers, servers and embedded intelligent devices, and the main components of the terminal include: a memory 33 and a processor 31, and the memory 33 and the processor 31 can be connected via a communication bus 34;
[0117] The memory 33 is used to store program codes corresponding to the rapid antigenicity identification of type B influenza virus provided in the above embodiment;
[0118] The processor 31 is used to read and execute program codes.
[0119] This embodiment provides a computer-readable storage medium, in which a program code corresponding to a rapid antigenic identification of type B influenza virus according to the above embodiment is stored.
[0120] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the terminals, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.
[0121] In the several embodiments provided in the present application, it should be understood that the disclosed terminals, devices and methods can be implemented in other ways. For example, 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 integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be an indirect coupling or communication connection through some interfaces, devices or units, which can be electrical, mechanical or other forms.
[0122] The terms "first", "second", "third", "fourth", etc. (if any) in the specification of the present application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present application described herein can, for example, be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.
[0123] It should be understood that in the present application, "at least one (item)" means one or more, and "plurality" means two or more. "And / or" is used to describe the association relationship of associated objects, indicating that three relationships may exist. For example, "A and / or B" can mean: only A exists, only B exists, and A and B exist at the same time, where A and B can be singular or plural. The character " / " generally indicates that the objects associated before and after are in an "or" relationship. "At least one of the following" or similar expressions refers to any combination of these items, including any combination of single or plural items. For example, at least one of a, b or c can mean: a, b, c, "a and b", "a and c", "b and c", or "a and b and c", where a, b, c can be single or multiple.
[0124] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, 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 solution of this embodiment.
[0125] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.
[0126] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention is essentially or part of the contribution to the prior art or all or part of the technical solution can be embodied in the form of a software product, which is stored in a storage medium and includes several instructions to enable a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk and other media that can store program code. As described above, the above embodiments are only used to illustrate the technical solution of the present application, not to limit it; although the present application is described in detail with reference to the aforementioned embodiments, ordinary technicians in the field should understand that: it can still modify the technical solutions recorded in the aforementioned embodiments, or replace some of the technical features therein with equivalents; and these modifications or replacements do not make the essence of the corresponding technical solution deviate from the spirit and scope of the technical solutions of the embodiments of the present application.
Claims
1. A method for rapid identification of influenza B virus antigenicity, characterized in that: include: Obtaining preset HA1 sequence sample data and sample antigenicity data of the Victoria lineage and the Yamagata lineage of influenza B virus, respectively, wherein the sample antigenicity data respectively include antigenic relationships between strains within the Victoria lineage and the Yamagata lineage; Extracting virus features from the Victoria lineage and Yamagata lineage HA1 sequence sample data of influenza B virus, respectively, and obtaining virus features related to antigenic changes corresponding to the Victoria lineage and Yamagata lineage sample data sets, respectively, wherein the virus features specifically include: antigen epitope features, physicochemical property features, nitrogen glycosylation sites, and receptor binding region features; Using the virus characteristics and the sample antigenicity data as model training data, through model training, antigenicity prediction models PREDAC-BV and PREDAC-BY corresponding to Victoria lineage and Yamagata lineage of influenza B virus are obtained respectively; Obtain the HA1 amino acid sequence of the influenza Victoria lineage or Yamagata lineage strain of the influenza B virus to be identified, and input the HA1 amino acid sequence of the influenza B virus strain into the antigenicity prediction model of the corresponding lineage to determine the antigenicity identification result of the influenza B virus strain according to the output result of the antigenicity prediction model.
2. A method for rapid identification of influenza B virus antigenicity according to claim 1, characterized in that: The method for extracting the antigen epitope characteristic value specifically includes: According to the preset amino acid site screening conditions, the amino acid sites that meet the amino acid site screening conditions are determined from the HA1 protein sequences of the influenza B Victoria lineage and the Yamagata lineage virus samples as the antigenic sites of the two lineages respectively; Clustering the antigenic sites to divide the antigenic sites into five antigenic epitopes; Using the PSI-BLAST algorithm, a PSSM matrix containing each of the antigenic sites is constructed; According to a pair of influenza B virus sample data of the same lineage, the sum of the absolute values of the differences between the PSSM scores of the two amino acid residues corresponding to each site on the antigenic epitope is taken as the characteristic value of the antigenic epitope. When the characteristic values of all antigenic epitopes are obtained, the characteristic values of the antigenic epitope are output.
3. A method for rapid identification of influenza B virus antigenicity according to claim 1, characterized in that: The method for extracting the characteristic value of the physical and chemical properties specifically includes: The method for extracting the characteristic value of the physical and chemical properties specifically includes: According to the amino acid index database, the physical and chemical property indicators corresponding to the Victoria lineage and the Yamagata lineage are determined, wherein the physical and chemical property indicators include: hydrophobicity, volume, charge, polarity and accessible surface area; According to a pair of influenza B virus sample data of the same lineage selected and any selected physicochemical property index, the average value of the corresponding physicochemical property score difference at all amino acid sites of the pair of strains is calculated as the characteristic value of the physicochemical property. When a pair of strains has more than three different amino acid sites, the average value of the first three sites with the largest corresponding physicochemical property score difference at all amino acid sites is taken as the characteristic value of the physicochemical property. After the characteristic values of all physicochemical property indicators are obtained, the characteristic value of the physicochemical property is output.
4. A method for rapid identification of influenza B virus antigenicity according to claim 1, characterized in that: The method for extracting the receptor binding region features specifically includes: According to a pair of influenza B virus sample data of the same lineage, the average value of the shortest Euclidean distance from the sites with different amino acids on the HA1 protein sequences of the pair of strains to the receptor binding region characteristics is calculated as the receptor binding region characteristics.
5. A method for rapid identification of influenza B virus antigenicity according to claim 1, characterized in that: The training method of the antigenicity prediction model includes: Based on the influenza B Victoria lineage and Yamagata lineage virus sample HA1 sequence data and the sample antigenicity data, combined with a plurality of preset initial algorithm models, the Victoria lineage and Yamagata lineage sample HA1 sequence data and the sample antigenicity data are used as inputs of each initial algorithm model, each initial algorithm model is trained, and a five-fold cross validation is performed; Based on the cross-validation results obtained, the optimal initial algorithm model corresponding to each lineage is determined to obtain the best antigenicity prediction model for different lineages.
6. A method for rapid identification of influenza B virus antigenicity according to claim 5, characterized in that: The types of initial algorithm models include: XGBoost, LightGBM, RF and SVM.
7. A method for rapid identification of influenza B virus antigenicity according to claim 1, characterized in that: After determining the antigenicity identification result of the influenza B virus strain, the method further comprises: Based on the constructed Victoria lineage antigenicity prediction model, the antigenic relationship between all Victoria lineage strains of known sequences is predicted, and an antigenic similarity network between strains is constructed; the Victoria lineage strain antigenic similarity network is clustered using the Markov clustering method to identify different antigenic classes; the vaccine strain recommendation is assisted by analyzing the antigenic similarity between the Victoria lineage strains prevalent in the current epidemic season and the Victoria lineage antigen clusters that dominated the epidemic in the past. When the antigenic similarity is low, it is recommended to replace the Victoria lineage vaccine strain, otherwise the vaccine strain should not be replaced.
8. A device for rapid identification of influenza B virus antigenicity, characterized in that: include: A sample data acquisition unit, used to respectively acquire HA1 sequence sample data and sample antigenicity data of the preset Victoria lineage and Yamagata lineage of influenza B virus, wherein the sample antigenicity data respectively include the antigenic relationship between strains within the Victoria lineage and the Yamagata lineage; An antigen feature extraction unit is used to extract virus features from the Victoria lineage and Yamagata lineage HA1 sequence sample data of the influenza B virus, respectively, to obtain virus features related to antigenic changes corresponding to the Victoria lineage and Yamagata lineage sample data sets, respectively, wherein the virus features specifically include: antigen epitope features, physicochemical property features, nitrogen glycosylation sites, and receptor binding region features; An antigenicity prediction model training unit, used to obtain antigenicity prediction models PREDAC-BV and PREDAC-BY corresponding to the Victoria lineage and the Yamagata lineage of influenza B virus respectively through model training based on the virus characteristics and the sample antigenicity data as model training data; The antigenicity identification unit is used to obtain the HA1 amino acid sequence of the influenza Victoria lineage or Yamagata lineage strain of the influenza B virus to be identified, and input the HA1 amino acid sequence of the influenza B virus strain into the antigenicity prediction model of the corresponding lineage to determine the antigenicity identification result of the influenza B virus strain according to the output result of the antigenicity prediction model.
9. A terminal for rapid antigenicity identification of influenza B virus, characterized in that: include: Memory and processor; The memory is used to store a program code corresponding to a rapid antigenic identification of a type B influenza virus according to any one of claims 1 to 7; The processor is used for reading and executing the program code.
10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores program codes corresponding to the rapid antigenic identification of type B influenza virus according to any one of claims 1 to 7.
Citation Information
Patent Citations
Method for predicting flu antigen through model and application thereof
CN101847179A
Method for identifying genetic evolution lineages of H1N1 subtype influenza virus
CN111004869A
Method for merging and recombining multiple antigen epitopes based on computer molecular simulation technology
CN115985383A
Receptor sequence generation method and device, equipment, storage medium and program product
CN116978459A
Prediction method for future mutation of influenza virus
CN117352053A
Cited By
H3N2 influenza virus antigenicity dynamic evolution analysis method and device
CN119832993A
