Method, device and equipment for analyzing genetic basis of cotton plant type and storage medium
By acquiring three-dimensional information of cotton plants, optimizing plant type data using machine learning models, and combining this with genome-wide association analysis, the efficiency and accuracy issues of analyzing the genetic basis of cotton plant type were resolved, achieving efficient and precise progress in cotton breeding.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- INST OF COTTON RES CHINESE ACAD OF AGRI SCI
- Filing Date
- 2026-03-12
- Publication Date
- 2026-06-05
AI Technical Summary
Existing technologies are insufficient to efficiently and accurately analyze the genetic basis of cotton plant type. Traditional measurement methods are time-consuming, labor-intensive, subjective, and have low accuracy. The lack of a dedicated three-dimensional phenotypic analysis platform has led to slow progress in cotton breeding.
By acquiring three-dimensional information of cotton plants, optimizing initial plant type data using machine learning models, and combining genome-wide association analysis, candidate genes related to plant type were located, and a complete process of three-dimensional phenotype acquisition, phenotype optimization, gene localization, and functional verification was established.
This study enabled precise and efficient genetic analysis of cotton plant architecture, provided important molecular targets, and helped to breed new varieties adapted to high-density planting and mechanical harvesting, overcoming the false positive problem of single-trait association analysis.
Smart Images
Figure CN122157761A_ABST
Abstract
Description
Technical Field
[0001] This application relates to the field of plant type genetic analysis technology, and more specifically, to a method, apparatus, equipment, and storage medium for analyzing the genetic basis of cotton plant type. Background Technology
[0002] Currently, cotton ( Gossypium Cotton (spp.) is a globally important economic crop. Plant architecture, as a core agronomic trait, directly affects cotton yield, fiber quality, and adaptability, making it a key target trait in cotton breeding. Traditional cotton plant architecture research relies on manual measurement of traits such as plant height, fruiting branch length, and fruiting branch angle, which is time-consuming, labor-intensive, subjective, and lacks precision, making it difficult to meet the needs of large-scale germplasm resource screening and genetic analysis.
[0003] In recent years, 3D reconstruction technology has provided a new approach for high-throughput acquisition of plant phenotypes. Among them, structured light motion recovery (SfM)-multi-view stereo vision (MVS) technology has been applied in crops such as rice and maize due to its low cost and non-invasiveness. However, cotton has a unique plant architecture with a complex canopy, and there is currently a lack of a dedicated 3D phenotype analysis platform for cotton. At the same time, existing research has not yet established a complete process of "3D phenotype acquisition - phenotype optimization - gene localization - functional verification," resulting in slow progress in the analysis of the genetic basis of cotton plant architecture and insufficient discovery of key regulatory genes.
[0004] Therefore, developing a high-throughput, high-precision three-dimensional phenotypic acquisition method for cotton plant architecture is of great significance for accelerating the process of cotton molecular breeding. Summary of the Invention
[0005] The purpose of this application is to provide a method, apparatus, device, and storage medium for analyzing the genetic basis of cotton plant type, so as to solve the above-mentioned problems existing in the prior art and improve the efficiency and accuracy of genetic basis analysis of cotton plant type.
[0006] Firstly, a method for analyzing the genetic basis of cotton plant architecture is provided, which may include: Obtain three-dimensional information of cotton plants; Based on the three-dimensional information, the initial plant type data of the cotton plant is extracted; The initial plant type data is optimized using a machine learning model to obtain plant type phenotypic data; The plant type phenotypic data are combined with the genotype data corresponding to the cotton plant to perform genome-wide association analysis to locate candidate genes related to plant type; wherein, the candidate genes are the genetic basis associated with the traits of the cotton plant type.
[0007] Secondly, a genetic basis analysis device for cotton plant type is provided, which may include: The acquisition module is used to acquire three-dimensional information of cotton plants; An extraction module is used to extract the initial plant type data of the cotton plant based on the three-dimensional information; The optimization module is used to optimize the initial plant type data using a machine learning model to obtain plant type phenotypic data; The analysis module is used to combine the plant type phenotypic data with the genotype data corresponding to the cotton plant to perform genome-wide association analysis and locate candidate genes related to plant type; wherein, the candidate genes are the genetic basis associated with the traits of the cotton plant type.
[0008] Thirdly, an electronic device is provided, which includes a processor, a communication interface, a memory, and a communication bus, wherein the processor, the communication interface, and the memory communicate with each other through the communication bus; Memory, used to store computer programs; When a processor executes a program stored in memory, it implements any of the steps described in the first aspect above.
[0009] Fourthly, a computer-readable storage medium is provided, wherein a computer program is stored therein, and when executed by a processor, the computer program implements the steps of any of the methods described in the first aspect above.
[0010] This application provides a method, apparatus, device, and storage medium for analyzing the genetic basis of cotton plant type, acquiring three-dimensional information of cotton plants. Based on the three-dimensional information, initial plant type data of cotton plants is extracted. The initial plant type data is optimized using a machine learning model to obtain plant type phenotypic data. The plant type phenotypic data is combined with the corresponding genotype data of cotton plants to perform genome-wide association analysis (GWAS) to locate candidate genes related to plant type. In this scheme, the genetic basis of cotton plant type is analyzed through genome-wide association analysis (GWAS), accurately identifying candidate genes related to cotton plant type. The obtained candidate genes provide important molecular targets for cotton plant type improvement, which helps to breed new cotton varieties adapted to high-density planting and mechanical harvesting. Therefore, this application overcomes the false positive problem of single-trait association analysis, achieves accurate and efficient acquisition of cotton plant type phenotype, realizes a systematic plant type genetic analysis process, and can improve the efficiency and accuracy of genetic basis analysis of cotton plant type. Attached Figure Description
[0011] To more clearly illustrate the technical solutions of the embodiments of this application, the accompanying drawings used in the embodiments of this application will be briefly introduced below. It should be understood that the following drawings only show some embodiments of this application and should not be regarded as a limitation of the scope. For those skilled in the art, other related drawings can be obtained based on these drawings without creative effort.
[0012] Figure 1 A flowchart illustrating a method for analyzing the genetic basis of cotton plant type provided in this application embodiment; Figure 2 A flowchart illustrating a method for analyzing the genetic basis of cotton plant type provided in this application embodiment; Figure 3 A schematic diagram illustrating a method for analyzing the genetic basis of cotton plant type provided in an embodiment of this application; Figure 4 A schematic diagram of the structure of a genetic basis analysis device for cotton plant type provided in an embodiment of this application; Figure 5 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application. Detailed Implementation
[0013] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of this application, and not all of the embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application. Unless otherwise defined, the technical or scientific terms used in this application should have the ordinary meaning understood by those skilled in the art. The words "first," "second," and similar terms used in this application do not indicate any order, quantity, or importance, but are only used to distinguish different components. The words "comprising" or "including," etc., mean that the element or object preceding the word covers the element or object listed after the word and its equivalents, but do not exclude other elements or objects. The words "connected," "coupled," or "connected," etc., are not limited to physical or mechanical connections, but can include electrical connections, whether direct or indirect. "Up," "down," "left," "right," etc., are only used to indicate relative positional relationships. When the absolute position of the described object changes, the relative positional relationship may also change accordingly.
[0014] The method for analyzing the genetic basis of cotton plant type provided in this application embodiment can be applied to electronic devices, terminal devices, devices or equipment for analyzing the genetic basis of cotton plant type, or other devices or equipment capable of executing this embodiment, and there are no limitations on this application. In this embodiment, the execution subject is described as an electronic device.
[0015] The terminal can be a user equipment (UE) such as a mobile phone, smartphone, laptop computer, digital broadcast receiver, personal digital assistant (PDA), or tablet computer (PAD), handheld device, in-vehicle device, wearable device, computing device, or other processing device connected to a wireless modem, mobile station (MS), or mobile terminal. This terminal has the ability to communicate with one or more core networks via a radio access network (RAN).
[0016] The preferred embodiments of this application are described below with reference to the accompanying drawings. It should be understood that the preferred embodiments described herein are for illustration and explanation only and are not intended to limit this application. Furthermore, the embodiments and features in the embodiments of this application can be combined with each other without conflict.
[0017] Figure 1 This is a flowchart illustrating a method for analyzing the genetic basis of cotton plant type, as provided in an embodiment of this application. Figure 1 As shown, the method may include: Step S101: Obtain the three-dimensional information of the cotton plant.
[0018] For example, three-dimensional information of a cotton plant can be obtained. This can be achieved through multi-view image reconstruction, LiDAR scanning, depth cameras, or 3D laser scanners.
[0019] Step S102: Based on the three-dimensional information, extract the initial plant type data of the cotton plant.
[0020] For example, initial plant type data of cotton plants are extracted based on three-dimensional information. The initial plant type data includes any one or more of the following: plant height, fruiting branch length, and fruiting branch angle.
[0021] Step S103: Optimize the initial plant type data using a machine learning model to obtain plant type phenotypic data.
[0022] For example, if 3D information is obtained through multi-view image reconstruction, due to factors such as point cloud noise during the 3D reconstruction process, limitations of plant structure recognition algorithms, and occlusion, there will be a deviation between the automatically extracted plant type parameters (such as plant height, fruit branch length, and angle) and the actual values measured manually in the field using tools such as measuring tapes and protractors. This deviation will affect the accuracy of subsequent genetic association analysis. Therefore, machine learning models are used to optimize the initial plant type data to obtain plant type phenotypic data.
[0023] Specifically, the model training process includes: Input features (X): Original plant type parameters extracted from the 3D model (e.g., the plant height calculated by the algorithm is 125.3 cm). Output labels (y): Actual plant type parameters obtained by precise manual measurement of the same plant (e.g., the measured plant height is 128.1 cm).
[0024] Model training: Using multiple sets of such (X, y) paired data, train machine learning models (such as BDT, RF, XGBoost models, etc.) to teach the model the mapping relationship between "incorrect automatic measurements" and "true values".
[0025] The specific output of optimization: After being processed by the best machine learning model that has been trained (such as the selected BDT model), the output is the optimized plant phenotypic data with higher accuracy.
[0026] Therefore, by using machine learning models to correct the automatically extracted, coarse initial plant type data, the numerical values are made closer to the true values measured manually, thereby improving the reliability of the data and the accuracy of the analysis.
[0027] Step S104: Combine the plant type phenotypic data with the corresponding genotype data of cotton plants to perform genome-wide association analysis and locate candidate genes related to plant type; among them, candidate genes are the genetic basis for the trait association with cotton plant type.
[0028] For example, genotype data is a set of information characterizing an individual's genetic variation (such as an SNP matrix). Genotype data can be pre-stored, remotely accessed, or generated in real time; there are no restrictions on this.
[0029] For example, the optimized plant type phenotypic data can be compared with the pre-obtained population genotype SNP data corresponding to cotton plants to perform genome-wide association analysis and locate candidate genes related to plant type.
[0030] The method provided in this application obtains three-dimensional information of cotton plants. Based on the three-dimensional information, initial plant type data of the cotton plants is extracted. The initial plant type data is optimized using a machine learning model to obtain plant type phenotypic data. The plant type phenotypic data is combined with the genotype data corresponding to the cotton plants to perform genome-wide association analysis (GWAS) to locate candidate genes related to plant type; wherein, candidate genes are the genetic basis associated with the trait of cotton plant type. In this scheme, the genetic basis of cotton plant type is analyzed through genome-wide association analysis (GWAS), and candidate genes related to cotton plant type are accurately identified. The obtained candidate genes provide important molecular targets for cotton plant type improvement, which helps to breed new cotton varieties adapted to high-density planting and mechanical harvesting. Therefore, this application overcomes the false positive problem of single trait association analysis, realizes accurate and efficient acquisition of cotton plant type phenotype, realizes a systematic plant type genetic analysis process, and can improve the efficiency and accuracy of genetic basis analysis of cotton plant type.
[0031] Figure 2 A flowchart illustrating a method for the genetic basis of cotton plant type provided in this application is shown below. Figure 2 As shown, in this embodiment... Figure 1 Based on the embodiments, the method is described in detail below, and the method includes: Step S201: Obtain the three-dimensional information of the cotton plant.
[0032] In one example, S201 includes: acquiring multi-view images of cotton plants to obtain multi-view images; constructing a three-dimensional point cloud model of cotton plants based on the multi-view images using motion reconstruction structure and multi-view stereo vision technology; and determining the three-dimensional information of cotton plants based on the three-dimensional point cloud model.
[0033] In one example, multi-view images are acquired through an image acquisition system, which includes a lifting platform, a camera, a controller, an electrically controlled rotating platform, a backdrop, and supplementary lighting equipment. The controller controls the electrically controlled rotating platform and the lifting platform to work together to acquire multi-view images at different heights and angles.
[0034] For example, multi-view images of cotton plants are acquired to obtain multi-view images; based on the multi-view images, a three-dimensional point cloud model of the cotton plant is constructed using Structure from Motion (SfM) and Multi-View Stereo (MVS) techniques. The three-dimensional information of the cotton plant is then determined based on the three-dimensional point cloud model.
[0035] Optionally, a 3D model can be constructed based on SfM-MVS technology. Specifically, ① the SIFT algorithm is used to extract image feature points, including scale space extremum detection, key point localization, orientation determination, and feature description; ② feature point matching is performed using the FLANN algorithm, combined with the RANSAC algorithm to remove erroneous matching points and optimize matching accuracy; ③ the PnP algorithm is used to estimate camera pose, and sparse point clouds are generated through triangulation, which are then optimized using bundle adjustment (BA) to reduce reprojection errors; ④ a dense point cloud is generated based on the MVS algorithm, and statistical outlier removal (SOR) filtering is applied to finally construct a high-fidelity cotton 3D model.
[0036] Optional, Figure 3 This is a schematic diagram illustrating a method for analyzing the genetic basis of cotton plant type provided in an embodiment of this application. Figure 3 As shown, the multi-view image acquisition system consists of a lifting platform, a high-resolution RGB camera, a PLC controller, an electrically controlled rotating platform, a black background board, and supplementary lighting equipment. The cotton plant is fixed in the center of the rotating platform, which is controlled by the PLC to rotate counterclockwise at a rate of 3 degrees per second. The camera acquires one RGB image per second. For plants whose height exceeds the camera's field of view, the camera height is adjusted via the lifting platform, and images are acquired in two segments, up and down, for a total of 240 images. For plants of standard height, 120 images are acquired.
[0037] Step S202: Based on the three-dimensional information, extract the initial plant type data of the cotton plant.
[0038] In one example, the initial plant type data includes any one or more of the following: plant height, fruit branch length, and fruit branch angle.
[0039] For example, initial plant architecture data of cotton plants are extracted based on three-dimensional information. The initial plant architecture data is trait data, which includes any one or more of the following: plant height, fruiting branch length, and fruiting branch angle.
[0040] Optionally, in one implementation, a three-dimensional point cloud model of cotton can be used to identify the main stem nodes, the highest point at the top, and the ends of fruiting branches of the cotton plant, thereby automatically extracting five trait data: ① Plant height (PH): the straight-line distance from the cotyledon node to the top of the main stem; ② Length of the third fruiting branch (FBL_F3): the length of the third fruiting branch counted downwards from the top; ③ Angle between the third fruiting branches (FBA_F3): the angle between the third fruiting branch and the main stem; ④ Length of the third fruiting branch from the bottom (FBL_R3): the length of the third fruiting branch counted upwards from the cotyledon node; ⑤ Angle between the third fruiting branch from the bottom (FBA_R3): the angle between the third fruiting branch from the bottom and the main stem. Simultaneously, the above traits are manually measured using a precision measurement tool as the true values for model verification.
[0041] Therefore, for the first time, three-dimensional reconstruction was carried out on a large amount of cotton material, and the core phenotypic data of five traits were extracted in high throughput, breaking through the limitations of traditional manual measurement and realizing the accurate and efficient acquisition of cotton plant type phenotype.
[0042] Step S203: Optimize the initial plant type data using a machine learning model to obtain plant type phenotypic data.
[0043] In one example, S203 includes: constructing multiple machine learning models, including linear models, Bagging ensemble models, and Boosting ensemble models; training and evaluating the performance of multiple machine learning models using initial plant type data as input and manually measured standard plant type parameters as expected output; selecting machine learning models whose performance meets preset optimization conditions from multiple machine learning models for optimizing the initial plant type data to obtain plant type phenotypic data.
[0044] For example, machine learning models are constructed, including: ① linear models: Linear Regression (LR), Ridge Regression (RR), Lasso Regression (Lasso); ② Bagging ensemble models: Bagged Decision Tree (BDT), Random Forest (RF), Extremely Random Tree (ET); ③ Boosting ensemble models: Category Boosting (CatBoost), Extreme Gradient Boosting Tree (XGBoost), Lightweight Gradient Boosting Machine (LightGBM), etc., with no specific limitations on the models. Using the extracted initial plant type data as input and manually measured standard plant type parameters as the expected output, various machine learning models are trained, validated, and their performance evaluated. For example, R² (coefficient of determination), MAE (mean absolute error), and / or RMSE (root mean square error) can be used to evaluate model performance. Finally, machine learning models whose performance meets the preset optimization conditions are selected from the various models. The optimal machine learning model, BDT, is ultimately selected to optimize the phenotypic data of the five traits, obtaining plant type phenotypic data to ensure the accuracy of subsequent genetic analysis. For example, by comparing the performance of various machine learning models on the training and test sets, the bagged decision tree (BDT) is selected as the optimal model, and the initial plant type data is optimized based on the bagged decision tree (BDT) to obtain plant type phenotypic data.
[0045] Therefore, by optimizing the phenotypic extraction accuracy through three types of nine machine learning models, the optimal model BDT was selected, which significantly improved the reliability of phenotypic data and provided a high-quality data foundation for genetic analysis.
[0046] Step S204: Combine the plant type phenotypic data with the corresponding genotype data of cotton plants to perform genome-wide association analysis and locate candidate genes related to plant type; among them, candidate genes are the genetic basis for the trait association with cotton plant type.
[0047] For example, the optimized plant type phenotypic data, together with the genotype data (SNP data) corresponding to the cotton plant, are input into the genome-wide association analysis software to find genetic loci that are significantly associated with plant type traits.
[0048] Optionally, GWAS analysis was performed on the plant phenotypic and genotypic data generated by bagged decision tree (BDT) to identify the candidate gene GhPA1. Specifically, genome-wide association analysis (GWAS) was performed using genome-wide association analysis software, linking the optimized phenotypic data of the five traits with high-quality SNP data. For example, the association results were visualized using a Manhattan plot, and intersection analysis was performed on the significant association intervals for each trait, identifying a candidate gene in the 99.89–99.95 Mb interval on chromosome A10. GhPA1 (GhA10G2109). This gene belongs to the CYP45090A1 family and is involved in the biosynthesis of brassinolides (BRs), and is a key candidate gene for plant architecture regulation.
[0049] Therefore, a gene mapping strategy based on "three-dimensional phenotype, GWAS, and co-localization" was established to accurately identify genes regulating plant type. GhPA1 This overcomes the false positive problem in single-trait association analysis; and verifies the results through overexpression and RNA interference experiments. GhPA1 The study of gene function has formed a complete technical process of "phenotype acquisition, data optimization, gene localization, and functional verification." This process is universal and can be extended to the genetic analysis of complex plant architectures in other crops such as maize and rice. The three-dimensional reconstruction platform and technical process provided in this application offer new technical tools for cotton molecular breeding, enabling the identification of... GhPA1 Genes provide important molecular targets for improving cotton plant architecture, which helps to breed new cotton varieties adapted to high-density planting and mechanical harvesting.
[0050] Step S205: Verify the regulatory function of candidate genes on cotton plant architecture through molecular experiments.
[0051] In one example, S205 includes: constructing a genetic transformation vector for a candidate gene; transforming the genetic transformation vector into cotton plants to obtain transgenic cotton plants; comparing the plant type phenotype differences between transgenic cotton plants and wild-type plants, and verifying the regulatory function of the candidate gene based on the plant type phenotype differences.
[0052] For example, a genetic transformation vector is a "gene delivery tool" that is artificially designed and constructed.
[0053] Genetic transformation vectors are used to efficiently and stably deliver a foreign target gene (or DNA fragment) into the cells of a recipient organism (such as cotton), enabling it to be expressed or exert a regulatory effect. Genetic transformation vectors include overexpression vectors and RNA interference vectors. Overexpression vectors are designed to produce plants with significantly increased expression levels of the candidate gene; RNA interference vectors are designed to produce plants with specifically suppressed expression levels of the candidate gene.
[0054] In this step, genetic transformation vectors for the candidate genes are constructed, including overexpression vectors and RNA interference vectors. The overexpression vectors and RNA interference vectors are then transformed into cotton plants to obtain transgenic cotton plants, including overexpression plants and RNA interference plants. By comparing the plant morphology differences between the overexpression plants and RNA interference plants and the wild-type (WT) plants, it is confirmed that the candidate genes positively or negatively regulate cotton plant height, fruiting branch length, and fruiting branch angle.
[0055] Optionally, if the candidate gene is GhPA1 The coding sequence of the GhPA1 gene was cloned from a ZM24 cotton cDNA library, and a 35S promoter-driven overexpression vector was constructed. A 289 bp specific fragment was designed to construct an RNA interference vector. The overexpression vector and the RNA interference vector were introduced into Agrobacterium EHA105, respectively, and ZM24 cotton was transformed using the shoot tip meristem transformation method: seeds were delinted with sulfuric acid, disinfected with 75% ethanol, treated with 10% H2O2, and then soaked at 28℃ for germination. Transgenic cotton plants were obtained by Agrobacterium infection of the shoot tip meristem. The transgenic cotton plants included overexpression plants (GhPA1-OE) and RNA interference plants (GhPA1-RNAi). The T3 generation homozygous transgenic plants were verified by qRT-PCR. GhPA1 The gene was significantly upregulated in overexpressing plants and significantly downregulated in RNA interference plants. Statistical analysis of plant type traits showed that, compared to the wild type, overexpressing plants (GhPA1-OE) exhibited significantly increased plant height, fruit branch length, fruit branch angle, maximum lateral length, and canopy area; while RNA interference plants (GhPA1-RNAi) showed the opposite phenotype, confirming... GhPA1 Genes positively regulate cotton plant architecture.
[0056] The method provided in this application obtains three-dimensional information of cotton plants. Based on the three-dimensional information, initial plant type data of cotton plants is extracted. The initial plant type data is optimized using a machine learning model to obtain plant type phenotypic data. The plant type phenotypic data is combined with the genotype data corresponding to the cotton plants to perform genome-wide association analysis (GWAS) to locate candidate genes related to plant type; wherein, candidate genes are the genetic basis associated with cotton plant type traits. The regulatory function of candidate genes on cotton plant type is verified through molecular experiments. In this scheme, the genetic basis of cotton plant type is analyzed through genome-wide association analysis (GWAS), and candidate genes related to cotton plant type are accurately identified. The obtained candidate genes provide important molecular targets for cotton plant type improvement, which helps to breed new cotton varieties adapted to high-density planting and mechanical harvesting. Therefore, this application overcomes the false positive problem of single trait association analysis, achieves accurate and efficient acquisition of cotton plant type phenotype, realizes a systematic plant type genetic analysis process, and can improve the efficiency and accuracy of cotton plant type genetic basis analysis.
[0057] Corresponding to the above method, embodiments of this application also provide a genetic basis device for cotton plant type, such as... Figure 4 As shown, the device includes: The acquisition module 41 is used to acquire the three-dimensional information of the cotton plant; Extraction module 42 is used to extract the initial plant type data of the cotton plant based on the three-dimensional information; Optimization module 43 is used to optimize the initial plant type data using a machine learning model to obtain plant type phenotypic data; Analysis module 44 is used to combine the plant type phenotypic data with the genotype data corresponding to the cotton plant to perform genome-wide association analysis and locate candidate genes related to plant type; wherein, the candidate genes are the genetic basis associated with the traits of the cotton plant type.
[0058] The functions of each functional unit of the genetic basis device for cotton plant type provided in the above embodiments of this application can be realized through the above methods and steps. Therefore, the specific working process and beneficial effects of each unit in the genetic basis device for cotton plant type provided in the embodiments of this application will not be repeated here.
[0059] This application also provides an electronic device, such as... Figure 5 As shown, it includes 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.
[0060] Memory 530 is used to store computer programs; The processor 510 performs the above steps when executing the program stored in the memory 530.
[0061] The communication bus mentioned above can be a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus, etc. This communication bus can be divided into address bus, data bus, control bus, etc. For ease of illustration, only one thick line is used to represent it in the diagram, but this does not mean that there is only one bus or one type of bus.
[0062] The communication interface is used for communication between the aforementioned electronic devices and other devices.
[0063] The memory may include random access memory (RAM) or non-volatile memory (NVM), such as at least one disk storage device. Optionally, the memory may also be at least one storage device located remotely from the aforementioned processor.
[0064] The processors mentioned above can be general-purpose processors, including central processing units (CPUs), network processors (NPs), etc.; they can also be digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components.
[0065] The implementation methods and beneficial effects of the various components of the electronic device in the above embodiments for solving the problem can be found in [reference needed]. Figure 1 The steps in the illustrated embodiments are used to implement the electronic device. Therefore, the specific working process and beneficial effects of the electronic device provided in this application will not be repeated here.
[0066] In another embodiment provided in this application, a computer-readable storage medium is also provided, which stores instructions that, when executed on a computer, cause the computer to perform the genetic basis method for cotton plant type as described in any of the above embodiments.
[0067] In another embodiment provided in this application, a computer program product containing instructions is also provided, which, when run on a computer, causes the computer to execute the genetic basis method of cotton plant type as described in any of the above embodiments.
[0068] Those skilled in the art will understand that the embodiments in this application can be provided as methods, systems, or computer program products. Therefore, the embodiments in this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the embodiments in this application can take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.
[0069] This application describes embodiments of methods, apparatus (systems), and computer program products according to embodiments of this application with reference to flowchart illustrations and / or block diagrams. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart illustrations. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.
[0070] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.
[0071] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.
[0072] Although preferred embodiments have been described in this application, those skilled in the art, upon learning the basic inventive concept, can make other changes and modifications to these embodiments. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments as well as all changes and modifications falling within the scope of the embodiments of this application.
[0073] Obviously, those skilled in the art can make various modifications and variations to the embodiments of this application without departing from the spirit and scope of the embodiments of this application. Therefore, if these modifications and variations to the embodiments of this application fall within the scope of the claims in this application and their equivalents, then this application also intends to include these modifications and variations.
Claims
1. A method for analyzing the genetic basis of cotton plant type, characterized in that, The method includes: Obtain three-dimensional information of cotton plants; Based on the three-dimensional information, the initial plant type data of the cotton plant is extracted; The initial plant type data is optimized using a machine learning model to obtain plant type phenotypic data; The plant type phenotypic data are combined with the genotype data corresponding to the cotton plant to perform genome-wide association analysis to locate candidate genes related to plant type; wherein, the candidate genes are the genetic basis associated with the traits of the cotton plant type.
2. The method as described in claim 1, characterized in that, The acquisition of three-dimensional information of cotton plants includes: Multi-view images were acquired of the cotton plants to obtain multi-view images; Based on the multi-view images, a three-dimensional point cloud model of the cotton plant is constructed using motion reconstruction structure and multi-view stereo vision technology. Based on the aforementioned three-dimensional point cloud model, the three-dimensional information of the cotton plant is determined.
3. The method as described in claim 2, characterized in that, The multi-view images are acquired through an image acquisition system, which includes a lifting platform, a camera, a controller, an electrically controlled rotating platform, a backdrop, and a lighting device. The controller controls the electrically controlled rotating platform and the lifting platform to work together to acquire multi-view images at different heights and angles.
4. The method as described in claim 1, characterized in that, The optimization of the initial plant type data using a machine learning model to obtain plant type phenotypic data includes: Construct various machine learning models, including linear models, Bagging ensemble models, and Boosting ensemble models; Using the initial plant type data as input and the standard plant type parameters measured manually as the expected output, the various machine learning models are trained and their performance is evaluated. The machine learning model whose performance meets the preset optimization conditions is selected from the various machine learning models and used to optimize the initial plant type data to obtain plant type phenotypic data.
5. The method as described in claim 1, characterized in that, The initial plant type data includes any one or more of the following: plant height, fruit branch length, and fruit branch angle.
6. The method according to any one of claims 1-5, characterized in that, After locating the candidate genes, the method further includes: The regulatory function of the candidate genes on cotton plant architecture was verified through molecular experiments.
7. The method as described in claim 6, characterized in that, The regulatory function of the candidate genes on cotton plant architecture was verified through molecular experiments, including: Construct the genetic transformation vector for the candidate gene; The genetic transformation vector was transformed into cotton plants to obtain transgenic cotton plants; The plant type phenotype differences between the transgenic cotton plants and wild-type plants were compared, and the regulatory function of the candidate genes was verified based on the plant type phenotype differences.
8. A device for analyzing the genetic basis of cotton plant type, characterized in that, The device includes: The acquisition module is used to acquire three-dimensional information of cotton plants; An extraction module is used to extract the initial plant type data of the cotton plant based on the three-dimensional information; The optimization module is used to optimize the initial plant type data using a machine learning model to obtain plant type phenotypic data; The analysis module is used to combine the plant type phenotypic data with the genotype data corresponding to the cotton plant to perform genome-wide association analysis and locate candidate genes related to plant type; wherein, the candidate genes are the genetic basis associated with the traits of the cotton plant type.
9. An electronic device, characterized in that, The electronic device includes a processor, a communication interface, a memory, and a communication bus, wherein the processor, the communication interface, and the memory communicate with each other through the communication bus; Memory, used to store computer programs; A processor, when executing a program stored in memory, implements the method of any one of claims 1-7.
10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program that, when executed by a processor, implements the method described in any one of claims 1-7.