Breeding character analysis method, device, equipment, medium and computer program product

Abstract

The invention relates to the field of breeding character analysis, and provides a breeding character analysis method, device and equipment, a medium and a computer program product.The method comprises the steps that a target data set is constructed based on genotype data and phenotypic character data of breeding samples; training through the target data set to obtain a character prediction model; analyzing the effect of the gene variation site on the phenotypic character through the character prediction model to obtain an effect matrix; the gene variation site is determined based on the genotype data; carrying out aggregation processing on the effect matrix to obtain a key variation point corresponding to the target character; the target character is selected from the phenotypic character data according to requirements. According to the method, the effect of the gene loci on the characters is mined through the character prediction model, genotype data and phenotype data are fully utilized, and the accuracy of breeding character analysis is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of breeding trait analysis, and in particular to a breeding trait analysis method, device, equipment, medium and computer program product. Background Art

[0002] Existing methods for analyzing breeding traits rely on association analysis between genetic data and traits, requiring a large number of samples to detect significant associations, and the analysis results are mainly additive effects (the sum of independent contributions of multiple gene loci to a phenotype, with each allele affecting the phenotype in a linear manner). There is a lack of exploration of dominant effects (the phenomenon that the dominant and recessive relationship between the same gene loci causes the phenotype to deviate from the additive model) and epistatic effects (the interaction between different gene loci, which causes the phenotypic expression of a gene to depend on the state of other genes), resulting in inaccurate analysis of crop breeding traits. Summary of the invention

[0003] The present invention provides a breeding trait analysis method, device, equipment, medium and computer program product, which are used to solve the defect of inaccurate analysis in existing breeding trait analysis schemes and realize accurate analysis of breeding traits.

[0004] The present invention provides a breeding trait analysis method, comprising the following steps: Construct the target data set based on the genotype data and phenotypic trait data of the breeding samples; Obtaining a trait prediction model through training of the target data set; The effect of the gene variation site on the phenotypic trait is analyzed by the trait prediction model to obtain an effect matrix; the gene variation site is determined based on the genotype data; The effect matrix is ​​aggregated to obtain key variation sites corresponding to the target trait; the target trait is selected from the phenotypic trait data according to demand.

[0005] According to a breeding trait analysis method provided by the present invention, the construction of a target data set based on genotype data and phenotypic trait data of breeding samples comprises: The genotype data of the breeding samples are transformed to obtain a genotype matrix; Encoding the phenotypic trait data of the breeding samples to obtain a trait coding matrix; Based on the numbering of the breeding samples, the genotype matrix and the trait coding matrix are integrated to obtain a target data set.

[0006] According to a breeding trait analysis method provided by the present invention, the trait prediction model includes an encoding module, a sampling module, a decoding module and a prediction module; the trait prediction model obtained by training the target data set includes: Using the genotype matrix as a model input, and calculating the compressed expression matrix of the genotype data through the encoding module; By means of the sampling module and the compressed expression matrix, an expression matrix is ​​calculated and generated; The reconstructed expression matrix is ​​calculated by the decoding module and the generated expression matrix; the gene reconstruction loss is determined based on the genotype matrix and the reconstructed expression matrix; The predicted phenotypic data of the genotype matrix is ​​calculated by the prediction module; the phenotypic prediction loss is determined based on the phenotypic trait data and the predicted phenotypic data; The trait prediction model is back-propagated based on a loss function to update the network parameters of the trait prediction model; the loss function is determined based on the gene reconstruction loss and the phenotype prediction loss.

[0007] According to a breeding trait analysis method provided by the present invention, the genotype data of the breeding sample is converted to obtain a genotype matrix including: Based on the genotype data of the breeding samples, determining the gene locus data of each sample; the gene locus data includes the same homozygous locus, different homozygous locus and heterozygous locus; The gene site data are converted into numerical data to obtain a genotype matrix, wherein the same homozygous sites, the different homozygous sites and the heterozygous sites are converted into different numerical values.

[0008] According to a breeding trait analysis method provided by the present invention, the effect of gene variation sites on phenotypic traits is analyzed by the trait prediction model to obtain an effect matrix including: Determine the target variant site, the total set of variant sites, and the subset of variant sites based on the gene variant sites; Determine a first prediction result corresponding to the subset of variant sites by using the trait prediction model; Determining a second prediction result corresponding to a target union by the trait prediction model; the target union is determined based on the target variant site and the variant site subset; Based on the total set of variant sites, the subset of variant sites, the first prediction result and the second prediction result, an effect matrix of the target variant site is determined.

[0009] According to a breeding trait analysis method provided by the present invention, the aggregation processing of the effect matrix to obtain the key variation sites corresponding to the target trait includes: Slice and extract the effect matrix according to the target trait to obtain a target matrix; Performing sample aggregation processing on the target matrix to obtain a first matrix; Performing phenotypic aggregation processing on the first matrix to obtain a second matrix; The gene variation sites are screened based on the second matrix to obtain key variation sites corresponding to the target trait.

[0010] The present invention also provides a breeding trait analysis device, comprising the following modules: A target data set construction module is used to construct a target data set based on the genotype data and phenotypic trait data of breeding samples; A model training module, used to obtain a trait prediction model through training of the target data set; An effect matrix construction module, used to analyze the effect of gene variation sites on phenotypic traits through the trait prediction model to obtain an effect matrix; the gene variation sites are determined based on the genotype data; The trait analysis module is used to aggregate the effect matrix to obtain key variation sites corresponding to the target trait; the target trait is selected from the phenotypic trait data according to demand.

[0011] The present invention also provides an electronic device, comprising a memory, a processor, and a computer program stored in the memory and running on the processor, wherein when the processor executes the computer program, any of the breeding trait analysis methods described above is implemented.

[0012] The present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon, and when the computer program is executed by a processor, the breeding trait analysis method as described in any one of the above is implemented.

[0013] The present invention also provides a computer program product, comprising a computer program, wherein when the computer program is executed by a processor, the breeding trait analysis method as described above is implemented.

[0014] The breeding trait analysis method, device, equipment, medium and computer program product provided by the present invention construct a target data set for training a trait prediction model through the genotype data and phenotypic trait data of the breeding sample, and then analyze the effect of the gene variation site on the phenotypic trait through the trait prediction model, mine the effect of the gene site on the trait, and finally aggregate the effect to obtain the key variation site corresponding to the target trait. The present application mines the effect of the gene site on the trait through the trait prediction model, makes full use of the genotype data and the phenotypic data, and improves the accuracy of the breeding trait analysis. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] In order to more clearly illustrate the technical solutions in the present invention or the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0016] Figure 1 It is one of the flow charts of the breeding trait analysis method provided by the present invention.

[0017] Figure 2 This is the second flow chart of the breeding trait analysis method provided by the present invention.

[0018] Figure 3 It is a schematic diagram of the structure of the breeding trait analysis device provided by the present invention.

[0019] Figure 4 It is a structural schematic diagram of the electronic device provided by the present invention. DETAILED DESCRIPTION

[0020] In order to make the purpose, technical solution and advantages of the present invention clearer, the technical solution of the present invention will be clearly and completely described below in conjunction with the drawings of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0021] Combine the following Figure 1-Figure 4 The breeding trait analysis method, device, equipment, medium and computer program product of the present invention are described.

[0022] Figure 1 is one of the flow charts of the breeding trait analysis method provided by the present invention, such as Figure 1 As shown, the method includes the following: Step 100: construct a target data set based on the genotype data and phenotypic trait data of the breeding samples; First, the genotype data and phenotypic trait data of the breeding materials are collected, and the genotype data and phenotypic trait data are preprocessed in units of crop numbers to construct a "genotype-phenotype" data set, i.e., the target data set in this embodiment. The specific construction process of the target data set is described in detail in the subsequent embodiments.

[0023] Step 200, obtaining a trait prediction model through training of the target data set; Specifically, the breeding trait analysis method provided by the present invention can use a multi-task variational autoencoder to establish a trait prediction model based on the target data set. The multi-task variational autoencoder includes four components: an encoding module, a sampling module, a decoding module, and a prediction module.

[0024] The functional structure of each component is as follows: The encoding module includes M encoding components, each of which includes a linear layer, a normalization layer, an activation layer, and a dropout layer. Each encoding component can transform an a-dimensional vector into a b-dimensional vector. The input of the first encoding component is the genotype data in the target dataset, with a dimension of ; The output dimension of the mth encoding component is the input dimension of the m+1th encoding component, that is, L(m). This embodiment can use 2 encoding components with an output dimension of [2048, 512]; the normalization layer can use batch normalization, and the activation layer can use LeakyReLU (an improved ReLU activation function); the essence of the dropout layer is to achieve regularization by randomly shielding neurons to prevent overfitting of the neural network.

[0025] The sampling module consists of a generator and two sampling components. The sampling components are linear layers, denoted as and , the input dimension is L(M), and the output dimension is the preset generation dimension , the generation dimension in this embodiment It can be 32, and the generator can use a Gaussian generator with a mean of 0 and a variance of 1.

[0026] The decoding module includes M decoding components and 1 output layer. Each decoding component includes a linear layer, a normalization layer, an activation layer, and a dropout layer. Each decoding component is a mirror component corresponding to the encoding component, which can convert a b-dimensional vector into an a-dimensional vector. The input of the first decoding component is the generated dimension ; The output dimension of the mth decoding component is the input dimension of the m+1th decoding component, that is, L(M-m+1); The input dimension of the output layer is the output dimension of the Mth decoding component, that is, L(1), and the output dimension is the genotype data dimension In this embodiment, two decoding components can be used, and the output dimension is [512, 2048]; the normalization layer can use batch normalization; and the activation layer can use LeakyReLU.

[0027] The prediction module includes Y prediction components, where Y is the dimension of the phenotypic trait data in the target dataset. Each prediction component includes a linear layer, a normalization layer, an activation layer, and an output layer. Each prediction component can The generating vector of dimension is enlarged to After conversion to dimensional output. For quantitative traits, =1, when the phenotypic trait For categorical traits, is the number of categories, that is, the dimension corresponding to the one-hot encoding. In this embodiment, the normalization layer can use batch normalization; the activation layer can use LeakyReLU; the enlargement dimension is 128.

[0028] Step 300, analyzing the effect of gene variation sites on phenotypic traits through the trait prediction model to obtain an effect matrix; the gene variation sites are determined based on the genotype data; Gene mutation sites are screened out from the genotype data of the target data set, and the present invention provides a Shapley method (a mathematical method for fairly distributing cooperative benefits in game theory) to calculate the effect value of each gene mutation site on each phenotypic trait in the trait prediction model.

[0029] Step 400: Aggregate the effect matrix to obtain key variation sites corresponding to the target trait; the target trait is selected from the phenotypic trait data according to demand.

[0030] From the phenotypic trait data of the target data set, one or more phenotypic traits are selected as target traits according to the requirements. First, the effect matrix is ​​sliced ​​and extracted according to the target trait to obtain the target effect matrix, and then the target effect matrix is ​​aggregated according to the sample to obtain the first matrix. The first matrix is ​​then aggregated according to the phenotypic trait to obtain the second matrix. The second matrix is ​​sorted in descending order, and the gene variant sites with the top effect values ​​after descending sorting are selected as the key variant sites corresponding to the target trait.

[0031] This embodiment uses the genotype data and phenotypic trait data of the breeding samples to construct a target data set for training the trait prediction model, and then uses the trait prediction model to analyze the effect of the gene variation site on the phenotypic trait, mine the effect of the gene site on the trait, and finally aggregate the effect to obtain the key variation site corresponding to the target trait. This application mines the effect of the gene site on the trait through the trait prediction model, makes full use of the genotype data and phenotypic data, and improves the accuracy of breeding trait analysis.

[0032] Figure 2 FIG. 2 is a flow chart of the breeding trait analysis method provided by the present invention. Figure 2 As shown, the method may also include: Step 110, converting the genotype data of the breeding sample to obtain a genotype matrix; Step 120, encoding the phenotypic trait data of the breeding sample to obtain a trait encoding matrix; Step 130: Based on the number of the breeding samples, the genotype matrix and the trait coding matrix are integrated to obtain a target data set.

[0033] Specifically, the breeding samples are numbered, and then the genotype data and phenotypic trait data are preprocessed. The preprocessing of genotype data includes quality control, gene comparison, variation detection and conversion processing; the preprocessing of phenotypic trait data includes missing value supplementation, normalization processing and coding processing.

[0034] Phenotypic trait data include quantitative traits and categorical traits. Quantitative traits are filled with missing values ​​and normalized; categorical traits are filled with missing values ​​and coded. As shown in Table 1, Table 1 is the phenotypic trait data before preprocessing.

[0035] Table 1

[0036] For missing value filling of quantitative traits, the trait average value can be used for filling. For all quantitative traits after filling, the Min-Max normalization method can be used to put the data of quantitative traits into the interval [0, 1]. For missing value filling of categorical traits, the type with the most traits can be used for filling. Each categorical trait after filling can be converted into a one-hot encoding matrix using one-hot encoding. The number of columns of the one-hot encoding matrix is ​​equal to the number of categories of the trait, and the number of rows is equal to the number of samples in the data set. In the one-hot encoding vector of each sample, the column position corresponding to the classification value is 1, and the rest of the positions are 0. Take the quantitative traits "plant height" and "yield per mu" and the categorical trait "resistance to large leaf spot disease" as examples for illustration. The phenotypic trait data after preprocessing is shown in Table 2.

[0037] Table 2

[0038] Using the sample number as an anchor, the preprocessed genotype data and phenotypic trait data are integrated to construct a "genotype-phenotype" data set, which is the target data set in this embodiment.

[0039] This embodiment constructs a data set that can be used for a trait prediction model by processing the collected genotype data and phenotypic trait data of breeding samples.

[0040] In one embodiment, the breeding trait analysis method provided by the embodiment of the present invention may further include: Step 210, using the genotype matrix as a model input, and calculating the compressed expression matrix of the genotype data through the encoding module; Step 220: Calculate and generate an expression matrix through the sampling module and the compressed expression matrix; Step 230, calculating and reconstructing an expression matrix through the decoding module and the generated expression matrix; the gene reconstruction loss is determined based on the genotype matrix and the reconstructed expression matrix; Step 240, calculating predicted phenotypic data of the genotype matrix by the prediction module; the phenotypic prediction loss is determined based on the phenotypic trait data and the predicted phenotypic data; Step 250: back-propagate the trait prediction model based on a loss function to update the network parameters of the trait prediction model; the loss function is determined based on the gene reconstruction loss and the phenotype prediction loss.

[0041] Specifically, the main contents of establishing a trait prediction model based on the target data set include: Preset the parameters of the multi-task variational autoencoder; initialize the parameters of each component of the multi-task variational autoencoder. In this embodiment, the Xavier method can be used to initialize the parameters (by adjusting the variance of the weight initialization to keep the variance of the activation values ​​of each layer consistent, thereby promoting the stability of forward / backward propagation).

[0042] The genotype matrix As the model input, it is input into the task variational autoencoder, and the genotype data compression expression is calculated through the encoding module. ; The generation module uses the generator to generate randomly , and calculate the generated expression , is calculated as shown in Formula 1.

[0043] ; (1) Computing reconstructed expression of genotype data through the decoding module ; Calculate the predicted phenotypic data through the prediction module ; The calculation of the loss function is shown in formula 2, where is the preset multi-task loss balance parameter; is the loss of the genotype data reconstruction task, which is calculated as shown in Formula 3; is the loss of phenotypic data prediction, which is calculated as shown in Formula 4.

[0044] ; (2) ; (3) ; (4) in, for and The error can be calculated using the mean square error (MSE); is the KL divergence (Kullback-Leibler divergence) between the original genomic data and the generated expression; For the The prediction loss of a phenotypic trait can be calculated using the root mean square error (MSE) when the trait is predicted as a regression problem, and the cross entropy (CE) when the trait is predicted as a classification problem; express Distribution and KL divergence of the distribution; Indicates the mean , the standard deviation is Normal distribution of represents the first phenotypic traits; Represents the first phenotypic traits; For the The model prediction data of phenotypic traits corresponds to a slice of For the Real data on phenotypic traits.

[0045] Use the preset learning rate (LR) and loss function Loss to back-propagate the multi-task variational autoencoder and update the network parameters. Repeat the above content for multiple iterations of training according to the preset number of training steps and convergence requirements to obtain the trait prediction model.

[0046] This embodiment establishes a trait prediction model based on the target data set by using a multi-task variational autoencoder.

[0047] In one embodiment, the breeding trait analysis method provided by the embodiment of the present invention may further include: Step 111: determining gene locus data of each sample based on the genotype data of the breeding samples; the gene locus data includes identical homozygous loci, different homozygous loci and heterozygous loci; Step 112: convert the gene site data into numerical data to obtain a genotype matrix, wherein the same homozygous sites, the different homozygous sites and the heterozygous sites are converted into different numerical values.

[0048] Specifically, the preprocessing process of genotype data mainly includes the following contents: quality control of genotype data to obtain quality-controlled gene sequencing data; select reference genome and compare the quality-controlled sequencing data; detect genetic variation sites from the comparison results, and the genotype data after variation detection are shown in Table 3. Among them, each row represents the single nucleotide polymorphism (SNP) information of a gene site; the column represents the sample number, and the genotype data exists in four forms: A, T, C, and G, and the missing data is marked by NN.

[0049] Table 3

[0050] Table 4

[0051] The base data in Table 3 are converted into numerical data to form encoded genotype data. Specifically, the gene variation sites are compared with the reference genome, the homozygous sites identical to the reference genome are converted to 0, the different homozygous sites are converted to 2, the heterozygous sites are converted to 1, and the missing values ​​are converted to -1, to obtain the encoded genotype data shown in Table 4, and the genotype matrix in this embodiment can be obtained based on the encoded genotype data.

[0052] This embodiment converts the genotype data into a data format that is convenient for model training by performing preprocessing such as conversion processing on the genotype data.

[0053] In one embodiment, the breeding trait analysis method provided by the embodiment of the present invention may further include: Step 310: determining a target variation site, a total variation site set, and a variation site subset based on the gene variation site; Step 320: Determine a first prediction result corresponding to the subset of variant sites by using the trait prediction model; Step 330: Determine a second prediction result corresponding to a target union by using the trait prediction model; the target union is determined based on the target variant site and the variant site subset; Step 340: Determine the effect matrix of the target variant site based on the total set of variant sites, the subset of variant sites, the first prediction result, and the second prediction result.

[0054] Specifically, the breeding trait analysis method provided in this embodiment uses the Shapley method to calculate the effect value of each gene variation node on each trait in the above trait prediction model.

[0055] Targeting gene mutation sites , i.e., the target variant site in this embodiment, is calculated by the trait prediction model using Formula 5 Effect size for each trait .in, is the set of all gene variation sites in the genotype data, that is, the total set of variation sites in this embodiment; yes Any subset of , i.e., the variable site subset in this embodiment; yes The number of gene variant sites in yes Eliminate variant sites The collection after Is a collection Gene mutation sites The union of , that is, the target union in this embodiment; is the prediction function of the trait prediction model; That is, the second prediction result corresponding to the target union in this embodiment; is the genotype matrix according to Make slices; is the currently input prediction result, that is, the first prediction result corresponding to the variant site subset in this embodiment.

[0056] ; (5) What you get is an N×K dimensional matrix, where N is the number of phenotypic traits and K is the number of samples in the target data set. is the gene variation site of the Kth sample For traits The effect value of .

[0057] The effect values ​​of all gene mutation sites are traversed, and these effect values ​​are transposed and integrated into the effect matrix (SHAP matrix) of the gene mutation sites, that is, the utility matrix in this embodiment, where: , as shown in the table.

[0058] Table 5

[0059] This embodiment analyzes the effect of each gene variation site on each phenotypic trait through a fair contribution allocation method based on cooperative game theory, makes full use of genotypic data and phenotypic data, and improves the accuracy of breeding trait analysis.

[0060] In one embodiment, the breeding trait analysis method provided by the embodiment of the present invention may further include: Step 410, slicing and extracting the effect matrix according to the target trait to obtain a target matrix; Step 420: Perform sample aggregation processing on the target matrix to obtain a first matrix; Step 430: Perform phenotype aggregation processing on the first matrix to obtain a second matrix; Step 440: Screen the gene variation sites based on the second matrix to obtain key variation sites corresponding to the target trait.

[0061] One or more traits are selected from the phenotypic traits as the target traits in this embodiment, and are represented as a target trait set T in the form of a set; the effect matrix is ​​sliced ​​and extracted according to the target traits to obtain the target effect matrix , which is the target matrix in this embodiment; the target effect matrix is ​​aggregated based on the samples, and the aggregated effect matrix is , i.e., the first matrix in this embodiment, the aggregation method is shown in Formula 6, where, is the absolute value function.

[0062] ; (6) ; (7) According to phenotypic traits After aggregation, the effect matrix is , i.e., the second matrix in this embodiment, the aggregation method is shown in Formula 7, where, is the maximum aggregation function. is: [0.000140, 0.000042, 0.000046, 0.000105, 0.000158].

[0063] right Arrange in descending order, and select the first V gene mutation sites with the largest effect values ​​as key mutation sites. In the example of this embodiment, when V is 10, select The top 10 gene variant sites with the largest effect values ​​are as follows: [X2_837053_C, X2_892379_T, X9_104863109_A, X8_3684564_A, X2_2067198_T, X2_1333237_C, X2_1427131_A, X9_108613741_A, X1_299312468_G, X5_209091560_T].

[0064] When there is only one target trait, the key variant sites screened out can be used as an auxiliary tool for genome-wide association analysis of the trait; when there are multiple target traits, the key variant sites screened out do not need to define individual trait weights, and are the analysis of the synergistic effects of multiple phenotypic traits by deep learning models.

[0065] This embodiment aggregates gene variation sites through the selected target traits to screen key variation sites with larger effect values, thereby providing support for different breeding goals.

[0066] The breeding trait analysis device provided by the present invention is described below. The breeding trait analysis device described below and the breeding trait analysis method described above can be referenced to each other.

[0067] Please refer to Figure 3 The present invention also provides a breeding trait analysis device, comprising: A target data set construction module 301 is used to construct a target data set based on the genotype data and phenotypic trait data of the breeding samples; A model training module 302 is used to obtain a trait prediction model through training of the target data set; An effect matrix construction module 303 is used to analyze the effect of gene variation sites on phenotypic traits through the trait prediction model to obtain an effect matrix; the gene variation sites are determined based on the genotype data; The trait analysis module 304 is used to aggregate the effect matrix to obtain key variation sites corresponding to the target trait; the target trait is selected from the phenotypic trait data according to the demand.

[0068] Optionally, the target data set construction module includes: A data conversion unit is used to convert the genotype data of the breeding samples to obtain a genotype matrix; A data encoding unit is used to encode the phenotypic trait data of the breeding sample to obtain a trait encoding matrix; The target data set construction unit is used to integrate the genotype matrix and the trait coding matrix based on the number of the breeding samples to obtain the target data set.

[0069] Optionally, the trait prediction model includes an encoding module, a sampling module, a decoding module and a prediction module; and the model training module includes: A compressed expression matrix calculation unit, used for taking the genotype matrix as a model input and calculating the compressed expression matrix of the genotype data through the encoding module; An expression matrix generation calculation unit is used to calculate and generate an expression matrix through the sampling module and the compressed expression matrix; A reconstructed expression matrix calculation unit, used to calculate the reconstructed expression matrix through the decoding module and the generated expression matrix; the gene reconstruction loss is determined based on the genotype matrix and the reconstructed expression matrix; A predicted phenotypic data calculation unit, used to calculate the predicted phenotypic data of the genotype matrix through the prediction module; the phenotypic prediction loss is determined based on the phenotypic trait data and the predicted phenotypic data; A parameter updating unit is used to perform back propagation on the trait prediction model based on a loss function to update the network parameters of the trait prediction model; the loss function is determined based on the gene reconstruction loss and the phenotype prediction loss.

[0070] Optionally, the data conversion unit includes: A gene locus data determination unit, used to determine the gene locus data of each sample based on the genotype data of the breeding sample; the gene locus data includes the same homozygous locus, different homozygous locus and heterozygous locus; The genotype matrix determination unit is used to convert the gene site data into numerical data to obtain a genotype matrix, wherein the same homozygous sites, the different homozygous sites and the heterozygous sites are converted into different numerical values.

[0071] Optionally, the effect matrix building module includes: A variant site determination unit, used to determine a target variant site, a total set of variant sites, and a subset of variant sites based on the gene variant site; A first prediction result determining unit, configured to determine a first prediction result corresponding to the variant site subset by using the trait prediction model; A second prediction result determination unit, configured to determine a second prediction result corresponding to a target union by using the trait prediction model; the target union is determined based on the target variant site and the variant site subset; An effect matrix determination unit is used to determine the effect matrix of the target variant site based on the total set of variant sites, the subset of variant sites, the first prediction result and the second prediction result.

[0072] Optionally, the trait analysis module includes: A target matrix obtaining unit, used for slicing and extracting the effect matrix according to the target trait to obtain a target matrix; A first matrix obtaining unit, used for performing sample aggregation processing on the target matrix to obtain a first matrix; A second matrix obtaining unit, used for performing phenotype aggregation processing on the first matrix to obtain a second matrix; The key variation site obtaining unit is used to screen the gene variation sites based on the second matrix to obtain the key variation sites corresponding to the target trait.

[0073] Figure 4 An example of a physical structure diagram of an electronic device is shown in FIG. Figure 4 As shown, the electronic device may include: a processor 510, a communication interface 520, a memory 530 and a communication bus 540, wherein the processor 510, the communication interface 520 and the memory 530 communicate with each other through the communication bus 540. The processor 510 may call the logic instructions in the memory 530 to execute the breeding trait analysis method, which includes: constructing a target data set based on the genotype data and phenotypic trait data of the breeding sample; obtaining a trait prediction model through training the target data set; analyzing the effect of the gene variation site on the phenotypic trait through the trait prediction model to obtain an effect matrix; the gene variation site is determined based on the genotype data; the effect matrix is ​​aggregated to obtain the key variation site corresponding to the target trait; the target trait is selected from the phenotypic trait data according to the demand.

[0074] In addition, the logic instructions in the above-mentioned memory 530 can be implemented in the form of a software functional unit and can be stored in a computer-readable storage medium when it is sold or used as an independent product. Based on such an understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions for 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, etc. Various media that can store program codes.

[0075] On the other hand, the present invention also provides a computer program product, which includes a computer program, and the computer program can be stored on a non-transitory computer-readable storage medium. When the computer program is executed by a processor, the computer can execute the breeding trait analysis method provided by the above-mentioned methods, and the method includes: constructing a target data set based on the genotype data and phenotypic trait data of the breeding sample; obtaining a trait prediction model through training the target data set; analyzing the effect of gene variation sites on phenotypic traits through the trait prediction model to obtain an effect matrix; the gene variation sites are determined based on the genotype data; the effect matrix is ​​aggregated to obtain key variation sites corresponding to the target trait; the target trait is selected from the phenotypic trait data according to demand.

[0076] On the other hand, the present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, is implemented to execute the breeding trait analysis method provided by the above-mentioned methods, the method comprising: constructing a target data set based on the genotype data and phenotypic trait data of the breeding samples; obtaining a trait prediction model by training the target data set; analyzing the effect of gene variation sites on phenotypic traits by the trait prediction model to obtain an effect matrix; the gene variation sites are determined based on the genotype data; the effect matrix is ​​aggregated to obtain key variation sites corresponding to the target trait; the target trait is selected from the phenotypic trait data according to demand.

[0077] The device embodiments described above are merely illustrative, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. Ordinary technicians in this field can understand and implement it without paying creative labor.

[0078] Through the description of the above implementation methods, those skilled in the art can clearly understand that each implementation method can be implemented by means of software plus a necessary general hardware platform, and of course, can also be implemented by hardware. Based on this understanding, the above technical solution is essentially or the part that contributes to the prior art can be embodied in the form of a software product, and the computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a disk, an optical disk, etc., including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or some parts of the embodiments.

[0079] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A breeding trait analysis method, characterized in that: include: Construct the target data set based on the genotype data and phenotypic trait data of the breeding samples; Obtaining a trait prediction model through training of the target data set; The effect of the gene variation site on the phenotypic trait is analyzed by the trait prediction model to obtain an effect matrix; the gene variation site is determined based on the genotype data; Aggregating the effect matrix to obtain key variation sites corresponding to the target trait; The target trait is selected from the phenotypic trait data according to demand.

2. The breeding trait analysis method according to claim 1, characterized in that: The target data set is constructed based on the genotype data and phenotypic trait data of the breeding samples, including: The genotype data of the breeding samples are transformed to obtain a genotype matrix; Encoding the phenotypic trait data of the breeding samples to obtain a trait coding matrix; Based on the numbering of the breeding samples, the genotype matrix and the trait coding matrix are integrated to obtain a target data set.

3. The breeding trait analysis method according to claim 2, characterized in that: The trait prediction model includes an encoding module, a sampling module, a decoding module and a prediction module; The trait prediction model obtained by training the target data set comprises: Using the genotype matrix as a model input, and calculating the compressed expression matrix of the genotype data through the encoding module; By means of the sampling module and the compressed expression matrix, an expression matrix is ​​calculated and generated; The reconstructed expression matrix is ​​calculated by the decoding module and the generated expression matrix; the gene reconstruction loss is determined based on the genotype matrix and the reconstructed expression matrix; The predicted phenotypic data of the genotype matrix is ​​calculated by the prediction module; the phenotypic prediction loss is determined based on the phenotypic trait data and the predicted phenotypic data; The trait prediction model is back-propagated based on a loss function to update the network parameters of the trait prediction model; the loss function is determined based on the gene reconstruction loss and the phenotype prediction loss.

4. The breeding trait analysis method according to claim 2, characterized in that: The genotype data of the breeding samples are converted to obtain a genotype matrix including: Based on the genotype data of the breeding samples, determining the gene locus data of each sample; the gene locus data includes the same homozygous locus, different homozygous locus and heterozygous locus; The gene site data are converted into numerical data to obtain a genotype matrix, wherein the same homozygous sites, the different homozygous sites and the heterozygous sites are converted into different numerical values.

5. The breeding trait analysis method according to claim 1, characterized in that: The effect matrix obtained by analyzing the effect of gene variation sites on phenotypic traits through the trait prediction model includes: Determine the target variant site, the total set of variant sites, and the subset of variant sites based on the gene variant sites; Determine a first prediction result corresponding to the subset of variant sites by using the trait prediction model; Determining a second prediction result corresponding to a target union by the trait prediction model; the target union is determined based on the target variant site and the variant site subset; Based on the total set of variant sites, the subset of variant sites, the first prediction result and the second prediction result, an effect matrix of the target variant site is determined.

6. The breeding trait analysis method according to claim 1, characterized in that: The key variation sites corresponding to the target trait obtained by aggregating the effect matrix include: Slice and extract the effect matrix according to the target trait to obtain a target matrix; Performing sample aggregation processing on the target matrix to obtain a first matrix; Performing phenotypic aggregation processing on the first matrix to obtain a second matrix; The gene variation sites are screened based on the second matrix to obtain key variation sites corresponding to the target trait.

7. A breeding trait analysis device, characterized in that: include: A target data set construction module is used to construct a target data set based on the genotype data and phenotypic trait data of breeding samples; A model training module, used to obtain a trait prediction model through training of the target data set; An effect matrix construction module, used to analyze the effect of gene variation sites on phenotypic traits through the trait prediction model to obtain an effect matrix; the gene variation sites are determined based on the genotype data; A trait analysis module is used to aggregate the effect matrix to obtain key variation sites corresponding to the target trait; The target trait is determined based on the phenotypic trait data.

8. An electronic device comprising a memory, a processor, and a computer program stored in the memory and running on the processor, characterized in that: When the processor executes the computer program, the breeding trait analysis method according to any one of claims 1 to 6 is implemented.

9. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the breeding trait analysis method according to any one of claims 1 to 6 is implemented.

10. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the breeding trait analysis method according to any one of claims 1 to 6 is implemented.

Images