Penaeus vannamei improved variety propagation method based on deep learning

Through deep learning-based methods, the prediction model is trained using the genome and trait phenotype data of shrimp, which solves the problem of trait degeneration and weak risk of anti-epidemic diseases in the breeding of shrimp in the South American white shrimp species, and achieves rapid breeding of excellent varieties and improves breeding The efficiency and disease resistance of the industry.

CN119032879AActive Publication Date: 2024-11-29GUANGDONG YUEHAI FEED GROUP

Patent Information

Application Number
CN202411142250.9
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-08-20
Publication Date
2024-11-29
Estimated Expiration
2044-08-20

AI Technical Summary

Technical Problem

The breeding of shrimps in the South American white shrimps has problems of deterioration in traits and weak risk of anti-epidemic diseases, which leads to the need to frequently import shrimps, affecting the profits of the breeding industry. It is difficult for the existing technology to quickly and effectively breed shrimp varieties with disease resistance and excellent traits.

Method used

Using a deep learning-based method, by obtaining the genomic data and trait phenotype data of the first generation population, training the shrimp varieties prediction model, determining the gene sequence set related to excellent traits, and using it to select and expand the excellent shrimps to achieve rapid breeding. .

Benefits of technology

Through deep learning models, the breeding process of excellent traits of shrimp is accelerated, the breeding efficiency is improved, and the gene sequences related to specific traits can be more accurately positioned, and the shrimp varieties with strong disease resistance and rapid growth are selected, reducing the risk of epidemics .

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119032879A_ABST
    Figure CN119032879A_ABST
Patent Text Reader

Abstract

The invention relates to a penaeus vannamei improved variety propagation method based on deep learning. The method comprises the following steps: acquiring genome data of a primary population; obtaining specific character data of the screened primary population; locating a specific gene sequence set according to the specific character data and the genome data; the gene sequence set is a gene number set related to the specific character; and according to the gene number set, determining seed shrimps for fine breed propagation. The method comprises the following steps: breeding prawn groups of different families, obtaining character phenotype data and genome data of prawns of different families, and determining a gene sequence meeting character phenotype requirements according to a correlation degree between the character phenotype data and the genome data, namely, positioning a gene sequence related to specific characters; and next-generation prawn selection is carried out according to the gene sequence set, or seed prawns with stable characters are directly bred.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present application relates to the field of bioinformatics, and in particular to a method for breeding improved varieties of whiteleg shrimp based on deep learning. Background Art

[0002] Whiteleg shrimp is the largest shrimp species farmed in my country and has a very high market value.

[0003] my country relies on imports for high-quality broodstock, which means buying broodstock from abroad for breeding. However, broodstock breeding has the problem of trait degeneration and weak risk of disease resistance. If the broodstock trait degenerates or dies, it needs to be imported again. Especially in recent years, foreign broodstock companies only sell shrimp fry but not broodstock, which has further deprived my country's shrimp farming industry of profits.

[0004] The individual shrimps are very fragile, and the environment in the breeding farms can easily lead to the outbreak of diseases, resulting in large-scale death of shrimps. Therefore, the price of shrimps in the market is generally higher than other meats.

[0005] For example, an outbreak of Vibrio parahaemolyticus infection in 2009 caused large-scale death of shrimp fry due to early mortality syndrome and acute hepatopancreatic necrosis syndrome, resulting in huge economic losses.

[0006] Breeding shrimp varieties with excellent traits such as strong disease resistance and rapid growth is considered to be the fundamental way to solve the disease problem.

[0007] In 2019, the Chinese Academy of Sciences completed the gene sequencing of Penaeus vannamei and published the first reference genome data of Penaeus vannamei, which laid the foundation for the precise molecular breeding of shrimp.

[0008] In the molecular breeding of shrimp, it is necessary to evaluate the degree of association between specific genes and specific traits and determine the genotypes associated with excellent traits for breeding.

[0009] The traits that need to be selected for white shrimp are generally based on growth rate, disease resistance, meat yield and feed consumption. Most of the above traits are quantitative traits controlled by multiple genes. That is, the expression of shrimp traits is the result of the joint action of multiple loci. In addition, the heritability of some shrimp traits is relatively low and is greatly affected by environmental factors.

[0010] According to the reference genome of shrimp, there are a large number of species-specific genes and a large number of tandemly repeated genes in shrimp, which makes it difficult to analyze the correlation between genes and traits of individual shrimp.

[0011] Identifying genes or gene loci that are closely related to traits is a key point in the selection of improved shrimp. The vannamei shrimp has a total of 2.4 billion base pairs, of which about 24% are simple repetitive base sequences (i.e., microsatellites). Therefore, genotyping for breeding traits also requires a lot of DNA sequencing and analysis of the vannamei shrimp.

[0012] In order to quickly carry out molecular breeding of excellent traits of whiteleg shrimp, the present application provides a method for breeding improved varieties of whiteleg shrimp based on deep learning. Summary of the invention

[0013] In order to overcome the problems existing in the related art, the present application provides a method for breeding improved varieties of white shrimp based on deep learning, comprising:

[0014] Obtaining genome data of a primary population; the genome data includes a gene sequence with a number; the primary population is a population of seed shrimps bred from the same maternal lineage and different paternal lines;

[0015] Obtain phenotypic data of the primary population;

[0016] A gene number set is determined according to the degree of association between the trait phenotypic data and the genome data; the gene number set is a gene sequence set associated with the selected trait; and the seed shrimp for improved breeding is determined according to the gene number set.

[0017] In one embodiment, obtaining genome data of the primary population specifically includes:

[0018] Perform high-throughput whole-genome sequencing on each species of shrimp in the primary population to obtain the full genome sequence of the primary population;

[0019] Obtain a reference map of shrimp genes;

[0020] The whole gene sequence is numbered according to the shrimp gene reference map to obtain the genome data.

[0021] In one embodiment, obtaining the phenotypic data of the primary population specifically includes:

[0022] Cultivating the primary population in different breeding environments;

[0023] The phenotypic data of the primary population are collected and recorded.

[0024] In one embodiment, determining the gene number set according to the degree of association between the trait phenotypic data and the genomic data specifically includes:

[0025] Training a model for predicting improved shrimp species;

[0026] The phenotypic data and genome data of each marked shrimp are input into the shrimp improved breed prediction model to obtain a gene number set related to the specific trait.

[0027] In one embodiment, the training of the shrimp improved breed prediction model specifically includes:

[0028] Acquire a sample data set, where the sample data set is constructed based on reference genome data of shrimp and trait annotation data corresponding to the reference genome data;

[0029] Dividing the sample data set into a training set and a test set;

[0030] Constructing the improved shrimp breed prediction model, wherein the improved shrimp breed prediction model is a neural network model with a P-NET structure;

[0031] The training set is used to iteratively train the improved prawn breed prediction model to obtain the trained improved prawn breed prediction model.

[0032] In one embodiment, the construction of the trait annotation data based on the reference genome data of the shrimp and the reference genome data corresponding to the reference genome data specifically includes:

[0033] Obtain reference genome data for shrimp;

[0034] The reference genome data is labeled to obtain reference genome data with real trait labels.

[0035] In one embodiment, the network structure of the shrimp breeding prediction model includes an input layer, a gene layer, a biological pathway layer, a fully connected layer, and an output layer;

[0036] Each node of the gene layer represents a numbered gene sequence; the output of the gene layer is connected to the biological pathway layer, where each node represents a biological pathway; the biological pathway layer is used to link the expression pattern of the gene with the known biological pathway; the fully connected layer is used to perceive the degree of association between the trait phenotypic data and the gene sequence, and send the gene sequence set with a correlation degree higher than a preset threshold to the output layer.

[0037] In one embodiment, determining the seed shrimp for improved breeding according to the gene number set specifically includes:

[0038] Obtaining each gene number in the gene number set and the gene sequence corresponding to the gene number;

[0039] A gene chip is prepared according to the gene sequence; and the next generation of seed shrimps for breeding or seed shrimps with stable phenotypes are screened out through the gene chip.

[0040] The technical solution provided by this application may have the following beneficial effects:

[0041] The present application first cultivates shrimp populations of different families, obtains trait phenotypic data and genomic data of shrimps from different families, determines gene sequences that meet trait phenotypic requirements based on the degree of correlation between the trait phenotypic data and the genomic data, that is, locates gene sequences related to specific traits, and then selects the next generation of shrimps based on the gene sequence set, or directly breeds shrimps with stable traits.

[0042] It should be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] The above and other objects, features and advantages of the present application will become more apparent through a more detailed description of exemplary embodiments of the present application in conjunction with the accompanying drawings, wherein the same reference numerals generally represent the same components in the exemplary embodiments of the present application.

[0044] Figure 1 This is a schematic diagram of the process of the method for expanding the breeding of white shrimp varieties shown in the embodiments of the present application. DETAILED DESCRIPTION

[0045] The preferred embodiments of the present application will be described in more detail below with reference to the accompanying drawings. Although the preferred embodiments of the present application are shown in the accompanying drawings, it should be understood that the present application can be implemented in various forms and should not be limited by the embodiments described herein. On the contrary, these embodiments are provided to make the present application more thorough and complete, and to fully convey the scope of the present application to those skilled in the art.

[0046] The terms used in this application are for the purpose of describing specific embodiments only and are not intended to limit this application. The singular forms of "a", "said" and "the" used in this application and the appended claims are also intended to include plural forms unless the context clearly indicates other meanings. It should also be understood that the term "and / or" used herein refers to and includes any or all possible combinations of one or more associated listed items.

[0047] It should be understood that although the terms "first", "second", "third", etc. may be used in this application to describe various information, this information should not be limited to these terms. These terms are only used to distinguish the same type of information from each other. For example, without departing from the scope of this application, the first information may also be referred to as the second information, and similarly, the second information may also be referred to as the first information. Thus, the features defined as "first" and "second" may explicitly or implicitly include one or more of the features. In the description of this application, the meaning of "multiple" is two or more, unless otherwise clearly and specifically defined.

[0048] Currently in aquaculture, the breeding of South American white shrimp is mainly family selection, that is, constructing shrimp groups of different families for cultivation and selecting shrimp families that meet specific traits.

[0049] The current family breeding methods are all phenotypic breeding, that is, dividing them into different control groups for breeding, statistically analyzing the trait data of each shrimp family, and selecting shrimp that meet the requirements as breeding shrimp generation by generation.

[0050] Phenotypic selection cannot determine the relationship between genes and traits, or between environment and traits. It is common for shrimps of the same family to degenerate in different environments or after several generations of inbreeding.

[0051] Although pedigree breeding can utilize genetic laws and maintain the excellent traits of the population through hybridization and other means, it relies on the work experience of breeders and has low efficiency.

[0052] The embodiment of the present application is based on whole genome selective breeding to select improved shrimp. Whole genome selective breeding requires the construction of a genetic model based on the correlation between the genotype and phenotype on the whole genome of the shrimp population. That is, it is necessary to collect the DNA sequence of the shrimp and perform correlation analysis with the traits, and the data analysis work will consume a lot of time.

[0053] Therefore, the embodiment of the present application proposes a method for expanding the breeding of white shrimp varieties based on deep learning, which can complete the data analysis work through the deep learning model and accelerate the breeding process of improved varieties.

[0054] In the examples of the present application, a breeding population of Penaeus vannamei was first established, and family breeding was performed using 50 paternal Penaeus vannamei introduced and one maternal Penaeus vannamei. The resulting primary population included 50 different paternal breeding populations.

[0055] like Figure 1 As shown, a method for breeding improved varieties of white shrimp based on deep learning in the embodiment of the present application comprises the following steps:

[0056] 101. Obtain the genome data of the primary population;

[0057] The genome data includes a numbered gene sequence; the primary generation population is a population of seed shrimps bred from the same maternal line and different paternal lines.

[0058] 102. Obtain phenotypic data of the primary population;

[0059] 103. Determine a gene number set according to the degree of association between the trait phenotypic data and the genome data; the gene number set is a gene sequence set associated with the selected trait;

[0060] 104. Determine the shrimp species for improved breeding based on the gene number set.

[0061] In step 101, the step of obtaining genome data of the primary population specifically includes the following steps:

[0062] 1011. Perform high-throughput whole genome sequencing on each species of shrimp in the primary population to obtain the whole genome sequence of the primary population;

[0063] In the examples of the present application, the complete gene sequences of various shrimp species are numbered and stored separately.

[0064] 1012. Obtain a reference map of shrimp genes;

[0065] 1013. Number the whole gene sequence according to the shrimp gene reference map to obtain the genome data.

[0066] The shrimp gene reference map is the publicly available genome series and annotation information of Penaeus vannamei. This application example numbers and annotates the gene sequences of 50 species of shrimp to obtain genome data. For gene sequences that are not annotated in the reference map, they are recorded as sequences to be annotated and numbered.

[0067] In step 102, the phenotypic data of the primary population is obtained, which specifically includes the following steps:

[0068] 1021. Cultivating the primary population in different breeding environments;

[0069] 1022. Collect and record the phenotypic data of the primary population.

[0070] Exemplarily, in a genotype screening culture environment for Vibrio resistance, multiple shrimp individuals from different families are randomly selected, and each family represents a genotype.

[0071] Vibrio parahaemolyticus was used for immersion infection. The Vibrio infection experiment lasted for 8 days, and the first 96 shrimps that died were taken as the sensitive group samples, and the last 96 shrimps that survived were taken as the stress-resistant individuals, and their survival and death times were recorded as the phenotypic data.

[0072] In addition to Vibrio resistance traits, phenotypic data can also be collected separately for growth traits, meat yield traits, or feed conversion rate traits.

[0073] In the examples of the present application, the observed trait phenotype types of shrimps of the same family are encoded to obtain the trait phenotype data.

[0074] In step 103, a gene number set is determined according to the degree of association between the trait phenotype data and the genome data, specifically:

[0075] A gene number set is determined according to the trait phenotypic data, the genome data and a shrimp breeding prediction model.

[0076] Specifically, the following steps are included:

[0077] 1031. Training a model for predicting improved shrimp varieties;

[0078] 1032. Input the trait phenotypic data and the genome data of each marked shrimp into the shrimp improved breed prediction model to obtain a gene number set related to the specific trait.

[0079] In the embodiment of the present application, the pre-trained shrimp breeding prediction model compares the genomic data of the shrimp populations of each paternal line to determine the gene number set related to the Vibrio resistance phenotype.

[0080] The gene number set may include one or more gene numbers, depending on whether the trait phenotype is determined by a single gene or multiple genes.

[0081] Specifically, the process of training the shrimp breeding prediction model is as follows:

[0082] 310. Obtain a sample data set;

[0083] The sample data set is constructed based on reference genome data of shrimp and trait annotation data corresponding to the reference genome data;

[0084] The method for obtaining the sample training set in the embodiment of the present application is:

[0085] Obtain reference genome data and reference trait data of shrimp;

[0086] The reference genome data is labeled to obtain reference genome data with real trait labels.

[0087] 320. Divide the sample data set into a training set and a test set;

[0088] 330. Constructing the shrimp improved breed prediction model;

[0089] Specifically, the shrimp breeding prediction model is a neural network model with a P-NET structure. The P-NET structure is a neural network model with a P-NET structure. e Gene-pathway relationships in the dataset.

[0090] In an embodiment of the present application, the network structure of the shrimp breeding prediction model includes an input layer, a gene layer, a biological pathway layer, a fully connected layer and an output layer.

[0091] Specifically, each node of the gene layer represents a numbered gene sequence; the output of the gene layer is connected to the biological pathway layer, where each node represents a biological pathway. The biological pathway layer is used to connect the expression pattern of the gene with the known biological pathway; the fully connected layer is used to perceive the degree of association between the trait phenotypic data and the gene sequence, and send the gene sequence set with a degree of association higher than a preset threshold to the output layer.

[0092] In the input layer, the genome data and phenotypic data of the primary population are encoded as follows: (x 1 , x 2 …x i , l) n .

[0093] Among them, x i represents the i-th numbered gene sequence, l is the phenotypic data, and n represents the individual shrimp number.

[0094] In the biological pathway layer, each node unit calculates the degree of association between the trait phenotype data and the i-th numbered gene sequence, extracts the gene sequences with a high degree of association, and excludes the gene sequences that have no relationship with the current trait phenotype.

[0095] The biological pathway layer of the embodiment of the present application screens out the gene numbers or gene sequences associated with the target trait and excludes data of other gene sequences.

[0096] In the fully connected layer, the confidence of each gene number is calculated to determine the degree of association between the trait phenotypic data and the gene sequence, and the output layer outputs the gene number set.

[0097] Among them, the activation function between the fully connected layer and the output layer is:

[0098]

[0099] Among them, x inis the probability distribution value of the i-th gene sequence of the n-th numbered shrimp individual.

[0100] The embodiment of the present application calculates the probability distribution between each gene sequence and the trait phenotype in each shrimp individual, classifies each gene sequence, and thus obtains a gene number set.

[0101] 340. Iteratively train the improved shrimp breed prediction model using the training set to obtain the trained improved shrimp breed prediction model.

[0102] After obtaining individual shrimps with stable traits, the embodiment of the present application designs a gene chip based on the gene sequence set of the individual as a probe to select shrimps before the next iteration, which specifically includes the following steps:

[0103] Obtaining each gene number in the gene number set and the gene sequence corresponding to the gene number;

[0104] A gene chip is prepared according to the gene sequence; and the next generation of seed shrimps for breeding or seed shrimps with stable phenotypes are screened out through the gene chip.

[0105] The present application first cultivates shrimp populations of different families, obtains trait phenotypic data and genomic data of shrimps from different families, determines gene sequences that meet trait phenotypic requirements based on the degree of correlation between the trait phenotypic data and the genomic data, that is, locates gene sequences related to specific traits, and then selects the next generation of shrimps based on the gene sequence set, or directly breeds shrimps with stable traits.

[0106] Regarding the device in the above embodiment, the specific way in which each module performs the operation has been described in detail in the embodiment of the method, and will not be elaborated here.

[0107] The scheme of the present application has been described in detail above with reference to the accompanying drawings. In the above embodiments, the description of each embodiment has its own emphasis. For the part that is not described in detail in a certain embodiment, refer to the relevant description of other embodiments. Those skilled in the art should also know that the actions and modules involved in the description are not necessarily required for the present application. In addition, it can be understood that the steps in the method of the embodiment of the present application can be adjusted in order, merged and deleted according to actual needs, and the modules in the device of the embodiment of the present application can be merged, divided and deleted according to actual needs.

[0108] In addition, the method according to the present application may also be implemented as a computer program or a computer program product, which includes computer program code instructions for executing some or all of the steps in the above method of the present application.

[0109] Alternatively, the present application can also be implemented as a non-temporary machine-readable storage medium (or computer-readable storage medium, or machine-readable storage medium) on which executable code (or computer program, or computer instruction code) is stored. When the executable code (or computer program, or computer instruction code) is executed by a processor of an electronic device (or electronic device, server, etc.), the processor executes part or all of the steps of the above-mentioned method according to the present application.

[0110] Those skilled in the art will further appreciate that the various illustrative logical blocks, modules, circuits, and algorithm steps described in connection with the application herein may be implemented as electronic hardware, computer software, or combinations of both.

[0111] The flow chart and block diagram in the accompanying drawings show the possible architecture, function and operation of the system and method according to multiple embodiments of the present application. In this regard, each square box in the flow chart or block diagram can represent a part of a module, a program segment or a code, and the part of the module, the program segment or the code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the square box can also occur in a sequence different from that marked in the accompanying drawings. For example, two continuous square boxes can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each square box in the block diagram and / or the flow chart, and the combination of the square boxes in the block diagram and / or the flow chart can be implemented with a dedicated hardware-based system that performs the specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0112] The embodiments of the present application have been described above, and the above description is exemplary, not exhaustive, and is not limited to the disclosed embodiments. Many modifications and changes will be apparent to those of ordinary skill in the art without departing from the scope and spirit of the described embodiments. The selection of terms used herein is intended to best explain the principles of the embodiments, practical applications, or improvements to the technology in the market, or to enable other persons of ordinary skill in the art to understand the embodiments disclosed herein.

Claims

1. A method for breeding improved varieties of white shrimp based on deep learning. It is characterized in that include: Obtaining genome data of a primary population; the genome data includes a gene sequence with a number; the primary population is a population of seed shrimps bred from the same maternal lineage and different paternal lines; Obtain phenotypic data of the primary population; Determining a gene number set according to the degree of association between the trait phenotypic data and the genome data; the gene number set is a gene sequence set associated with the selected trait; The seed shrimp for improved breeding is determined according to the gene number set.

2. According to claim 1, a method for expanding the breeding of white shrimp based on deep learning, It is characterized in that The obtaining of genome data of the primary population specifically includes: Perform high-throughput whole-genome sequencing on each species of shrimp in the primary population to obtain the full genome sequence of the primary population; Obtain a reference map of shrimp genes; The whole gene sequence is numbered according to the shrimp gene reference map to obtain the genome data.

3. According to claim 1, a method for breeding improved varieties of Penaeus vannamei based on deep learning, It is characterized in that The obtaining of the phenotypic data of the primary population specifically includes: Cultivating the primary population in different breeding environments; The phenotypic data of the primary population are collected and recorded.

4. According to claim 1, a method for breeding improved varieties of Penaeus vannamei based on deep learning, It is characterized in that Determining the gene number set according to the degree of association between the trait phenotype data and the genome data specifically includes: Training a model for predicting improved shrimp species; The phenotypic data and genome data of each marked shrimp are input into the shrimp improved breed prediction model to obtain a gene number set related to the specific trait.

5. According to claim 1, a method for breeding improved varieties of Penaeus vannamei based on deep learning, It is characterized in that The training of the improved shrimp breed prediction model specifically includes: Acquire a sample data set, where the sample data set is constructed based on reference genome data of shrimp and trait annotation data corresponding to the reference genome data; Dividing the sample data set into a training set and a test set; Constructing the improved shrimp breed prediction model, wherein the improved shrimp breed prediction model is a neural network model with a P-NET structure; The training set is used to iteratively train the improved prawn breed prediction model to obtain the trained improved prawn breed prediction model.

6. A method for breeding improved varieties of Penaeus vannamei based on deep learning according to claim 5, It is characterized in that The construction of the trait annotation data based on the reference genome data of the shrimp and the reference genome data corresponding to the reference genome data specifically includes: Obtain reference genome data for shrimp; The reference genome data is labeled to obtain reference genome data with real trait labels.

7. A method for breeding improved varieties of Penaeus vannamei based on deep learning according to claim 6, It is characterized in that The network structure of the shrimp breeding prediction model includes an input layer, a gene layer, a biological pathway layer, a fully connected layer and an output layer; Each node of the gene layer represents a numbered gene sequence; the output of the gene layer is connected to the biological pathway layer, where each node represents a biological pathway; the biological pathway layer is used to link the expression pattern of the gene with a known biological pathway; The fully connected layer is used to sense the degree of association between the trait phenotype data and the gene sequence, and send the gene sequence set with a degree of association higher than a preset threshold to the output layer.

8. According to claim 4, a method for breeding improved varieties of Penaeus vannamei based on deep learning, It is characterized in that The step of determining the seed shrimp for improved breeding according to the gene number set specifically includes: Obtaining each gene number in the gene number set and the gene sequence corresponding to the gene number; A gene chip is prepared according to the gene sequence; and the next generation of seed shrimps for breeding or seed shrimps with stable phenotypes are screened out through the gene chip.

Citation Information

Patent Citations

  • Nucleic acid assembly system

    CN103975063A

  • Statistical method suitable for high-quality rice variety screening technology in shrimp and rice co-cropping mode

    CN111903513A

  • Breeding method for disease resistance characters of prawns

    CN113678767A

  • Excavation method of excellent sorghum genes

    CN116130006A

  • SNP chip suitable for litopenaeus vannamei whole genome breeding application and application

    CN116287296A

Cited By

  • Digital breeding method and system for shrimp culture

    CN120409941A