Method for augmenting crop genotype data based on genotype position information and method for constructing training dataset of crop phenotype prediction model by using same

Abstract

Provided are a method for augmenting crop genotype data based on genotype position information and a method for constructing a training dataset of a crop phenotype prediction model by using same. The method for augmenting genotype data, according to an embodiment of the present invention, extracts an embedding vector from genome data including genotype data of crops and positional data of each genotype, and generates, from the extracted embedding vector, new genotype data different from the genotype data of the preprocessed genome data. Accordingly, diverse and sufficient training datasets for the crop phenotype prediction model are constructed, thus solving the problem of insufficient training datasets, and when the genotype data is augmented, SNP positional dependencies may be reflected so that genetic mutations occur only at realistically significant positions, thereby augmenting the genotype data to match actual biological characteristics.

Description

Method for augmenting crop genotype data based on genotype location information and method for constructing a training dataset for a crop phenotype prediction model using the same

[0001] The present invention relates to machine learning application technology in the fields of agriculture and biotechnology, and more specifically, to a method of augmenting crop genotype data and using it to construct a training dataset for a crop phenotype prediction model.

[0002] Machine learning technology is gaining increasing importance in fields such as agriculture and biotechnology. In particular, models that predict crop phenotypes based on genetic characteristics can contribute to accelerating the speed of crop improvement. However, learning genotype data is difficult due to a lack of samples and high-dimensional features, and existing models have limitations in effectively learning the local correlations of genotype data.

[0003] In other words, the collection and analysis of current genotype data are highly complex and costly, and securing large-scale data is difficult due to their high-dimensional nature. In particular, while digital breeding aimed at improving crop traits requires accurate and large amounts of genotype data, there are limitations in collecting only the desired data due to environmental factors and the complexity of gene expression.

[0004] The present invention has been devised to solve the aforementioned problems, and the objective of the present invention is to provide a method for constructing a diverse, realistic, and sufficient training dataset for a crop phenotype prediction model by augmenting crop genotype data using genotype location information and SNP (Single Nucleotide Polymorphism) data.

[0005] A method for constructing a training dataset for a crop phenotype prediction model according to an embodiment of the present invention for achieving the above objective comprises: a step of acquiring genomic data including genotype data for a crop and location data for each genotype; a step of acquiring phenotype data composed of traits for a crop; a step of preprocessing the acquired genomic data and phenotype data; a step of combining the preprocessed genomic data and phenotype data to construct a training dataset for a crop phenotype prediction model, which is a machine learning model that predicts crop phenotype data from crop genomic data; a step of extracting an embedding vector from the preprocessed genomic data; a step of generating new genotype data different from the genotype data of the preprocessed genomic data from the extracted embedding vector; and a step of combining the generated new genotype data with the location data of the preprocessed genomic data and the preprocessed phenotype data to add a new training dataset.

[0006] Genotype data can be SNP (Single Nucleotide Polymorphism) data.

[0007] The preprocessing step may involve acquiring genomic and phenotypic data by classifying them by crop variety.

[0008] The preprocessing step may include a step of converting the base sequence of the genotype data into an integer.

[0009] The integerization step may involve converting the allele combinations of the genotype data into integers by mapping them to their respective integer values.

[0010] The preprocessing step may involve categorizing each characteristic data of the phenotypic data by dividing it into multiple intervals.

[0011] The extraction step may include: a step of extracting an embedding vector from genotype data of genomic data; a step of extracting an embedding vector from location data of genomic data; and a step of combining the extracted embedding vectors into a single embedding vector.

[0012] The generation step may include a step of inputting the combined embedding vector into a convolution layer to extract features; and a step of inputting the extracted features into an FCL to average pool the features to generate new genotype data.

[0013] The extraction step is performed using an embedding network that extracts embedding vectors from preprocessed genomic data, and the generation step is performed using a genotype generation network that generates new genotype data from the extracted embedding vectors; the parameters of the embedding network and the genotype generation network can be updated and trained in a direction that reduces the loss between the new genotype data and the genotype data of the preprocessed genomic data.

[0014] According to another aspect of the present invention, a system for constructing a training dataset for a crop phenotype prediction model is provided, comprising: an acquisition unit for acquiring genomic data including genotype data for a crop and location data for each genotype, and phenotype data composed of traits for a crop; and a processor for preprocessing the acquired genomic data and phenotype data, constructing a training dataset for a crop phenotype prediction model which is a machine learning model that predicts crop phenotype data from crop genomic data by combining the preprocessed genomic data and phenotype data, extracting an embedding vector from the preprocessed genomic data, generating new genotype data different from the genotype data of the preprocessed genomic data from the extracted embedding vector, and adding a new training dataset by combining the generated new genotype data, location data of the preprocessed genomic data, and preprocessed phenotype data.

[0015] According to another aspect of the present invention, a method for augmenting genotype data is provided, comprising: acquiring genomic data including genotype data for a crop and location data for each genotype; preprocessing the acquired genomic data; extracting an embedding vector from the preprocessed genomic data; and generating new genotype data different from the genotype data of the preprocessed genomic data from the extracted embedding vector.

[0016] According to another aspect of the present invention, a genetic data augmentation system is provided, characterized by comprising: an acquisition unit for acquiring genetic data including genetic data for a crop and location data for each genetic type; and a processor for preprocessing the acquired genetic data, extracting an embedding vector from the preprocessed genetic data, and generating new genetic data different from the genetic data of the preprocessed genetic data from the extracted embedding vector.

[0017] As explained above, according to the embodiments of the present invention, by utilizing genotype location information and SNP data to augment crop genomic data and constructing a diverse and sufficient training dataset for a crop phenotype prediction model, the problem of insufficient training dataset can be resolved.

[0018] In addition, according to embodiments of the present invention, when augmenting genotype data, genetic mutations can occur only at realistically significant locations by reflecting SNP location dependency, thereby enabling augmentation into genotype data that corresponds to actual biological characteristics.

[0019] And according to embodiments of the present invention, the reliability and accuracy of a crop phenotype prediction model can be improved using a training dataset constructed through data augmentation having statistical characteristics similar to existing genotype data.

[0020] Furthermore, according to the embodiments of the present invention, crop phenotype prediction models with high reliability and accuracy enable the prediction of crop phenotypes in various environments, thereby ultimately opening the way to more efficiently breed crops with specific traits such as disaster resistance, disease resistance, and high yield, and contributing to the improvement of agricultural productivity and the strengthening of food security by developing varieties resistant to environmental changes.

[0021] FIG. 1 is a flowchart of a method for constructing a training dataset for a crop phenotype prediction model according to an embodiment of the present invention.

[0022] FIGS. 2 and FIGS. 3 are diagrams illustrating the structure of a genotype data augmentation model.

[0023] FIG. 4 is a flowchart of a genetic data augmentation model learning method according to another embodiment of the present invention,

[0024] FIG. 5 is a hardware configuration diagram of a crop phenotype prediction model learning system according to another embodiment of the present invention.

[0025] The present invention will be described in more detail below with reference to the drawings.

[0026] In an embodiment of the present invention, a method for augmenting crop genotype data based on genotype location information and a method for constructing a training dataset for a crop phenotype prediction model using the same are presented. This is a technology that constructs a diverse and sufficient training dataset for a crop phenotype prediction model by augmenting crop genomic data through the combined use of genotype location information and SNP data.

[0027] In particular, when augmenting genotype data, SNP positional dependency is reflected so that gene mutations occur only at realistically significant locations, thereby augmenting the genotype data to match actual biological characteristics.

[0028] FIG. 1 is a diagram illustrating the flow of a method for constructing a training dataset for a crop phenotype prediction model according to an embodiment of the present invention. A crop phenotype prediction model is a machine learning model that predicts phenotype data composed of crop traits from crop genome data.

[0029] To build a training dataset, as described above, genomic data and phenotypic data of the target crop are first obtained (S110).

[0030] Genomic data includes genotype data for crops and location data on the genomes of each genotype. Genomic data can be configured to include only SNP (Single Nucleotide Polymorphism) data, that is, genotype data in which a single base is found to be mutable, rather than all genotype data of the crop. More specifically, it can be composed of SNP data in which the proportion of missing data is less than a certain percentage (e.g., 20%) and the minimum allele frequency is greater than a certain percentage (e.g., 5%).

[0031] Phenotype data is data that represents the traits of a crop. In the case of fruit and vegetable crops, phenotype data can be composed of traits such as fruit weight, fruit width, fruit length, hardness, and sugar content.

[0032] Meanwhile, in step S110, genomic and phenotypic data are acquired separately for each crop variety.

[0033] The genomic data and phenotypic data obtained in the next step S110 are preprocessed (S120). The preprocessing process includes mapping the genomic data and phenotypic data into integer values.

[0034] Since positional data among genomic data is acquired in a numerical state, it is required to convert the nucleotide sequences of genotype data in genomic data into integers. Meanwhile, since genotype data consists of SNP data, allele combinations (AA, AT, TT or GG, GC, CC) are converted into integers by mapping them to their respective integer values. For example, genotype AA can be converted to 0, AT to 1, TT to 2, ..., and so on to convert them into integers.

[0035] The trait data constituting the phenotype data consists of numerical values, and since they are continuous data, they may contain outliers that can affect prediction accuracy. To address this, the preprocessing in step S120 categorizes each trait data into multiple intervals. For example, in the case of overweight data, ~20 is categorized as 0, 20~40 as 1, 40~60 as 2, 60~80 as 3, and 80~ as 4.

[0036] Then, the genomic data and phenotypic data preprocessed in step S120 are combined to form a training dataset for a crop phenotypic prediction model (S130).

[0037] Then, an embedding vector for the genomic data preprocessed in step S120 is extracted (S140), and new genotype data different from the genotype data of the genomic data obtained in step S110 is generated from the extracted embedding vector (S150).

[0038] In the next step S150, new genotype data is combined with location data acquired in step S110 to form genomic data, and the genomic data is combined with phenotype data acquired / preprocessed in steps S110 / S120 to add a new training dataset (S160). This augments the training dataset.

[0039] In step S160, only the genotype data from the existing genomic data is replaced with the new genotype data generated in step S150. The newly generated genomic data is genomic data in which the genotype data has been modified at practically significant locations; while it is genomic data in which genetic mutations have occurred, it possesses characteristics similar to the genotype structure of the actual genomic data.

[0040] Meanwhile, the embedding vector extraction step (S140) and the new genotype data generation step (S150) are performed based on machine learning. The structure of the genotype data augmentation model, which is a machine learning model for performing steps S140 and S150, is shown in FIGS. 2 and 3.

[0041] As illustrated in FIGS. 2 and 3, the genotype data augmentation model is configured to include an embedding network (210) and a genotype generation network (220), and the genotype generation network (220) is configured to include a 1D convolution layer (221) and an FC (Fully Connected) layer (222).

[0042] The embedding network (210) is configured to extract embedding vectors of preprocessed genomic data. Genomic data is input into the embedding network (210) separated by species (BP1150, BP1151, BP1152, BP1155).

[0043] Genome data consists of location data and genotype data, so the embedding network (210) extracts an embedding vector from the location data and extracts an embedding vector from the genotype data, and concatenates the two extracted embedding vectors into one embedding vector and outputs it.

[0044] The genotype generation network (220) generates new genotype data from the embedding vectors extracted and output from the embedding network (210). To this end, the 1D convolution layer (221) of the genotype generation network (220) extracts high-dimensional features from the embedding vectors extracted from the embedding network (210), and the FC layer (222) generates new genotype data by mean pooling the high-dimensional features extracted by the 1D convolution layer (221).

[0045] The genotype generation network (220) is a structure in which a 1D convolution layer (221) learns local patterns and an FC layer (222) learns global features to reduce model complexity and prevent overfitting, thereby strengthening the patterns of the entire data.

[0046] Hereinafter, a method for training a genotype data augmentation model composed of an embedding network (210) and a genotype generation network (220) will be described in detail with reference to FIG. 4. FIG. 4 is a flowchart of a method for training a genotype data augmentation model according to another embodiment of the present invention.

[0047] To train a genotype data augmentation model, first, genomic data of the target crop is acquired (S310), and the acquired genomic data is preprocessed (S320). The preprocessing includes a process of mapping the genomic data to integer values.

[0048] In the next step S320, the preprocessed genomic data is input into the embedding network (210) of the genotype data augmentation model to extract the embedding vector of the preprocessed genomic data (S330).

[0049] Then, the embedding vector extracted in step S330 is input into a genotype generation network (220) to generate new genotype data (S340).

[0050] Subsequently, the parameters of the embedding network (210) and the genotype generation network (220) are updated in a way that reduces the loss between the new genotype data generated in step S340 and the genotype data of the preprocessed genome data in step S320 (S350).

[0051] The cross-entropy loss function can be utilized as an applicable loss function in the S350 stage, and the specific loss function can be configured as follows.

[0052]

[0053] Here, is the genotype data of the genome data preprocessed in step S320, and is new genotype data generated in step S340. The above loss function enables the reliability and accuracy of a crop phenotype prediction model trained on a training dataset constructed from genotype data by augmenting it with genotype data that has statistical characteristics similar to the existing genotype data.

[0054] FIG. 5 is a diagram illustrating the hardware configuration of a crop phenotype prediction model learning system according to another embodiment of the present invention. The crop phenotype prediction model learning system according to an embodiment of the present invention can be implemented as a computing system comprising a communication unit (410), an output unit (420), a processor (430), an input unit (440), and a storage unit (450) as illustrated.

[0055] The communication unit (410) is a communication interface for connecting to an external network or external device, and is configured to acquire genomic data and phenotypic data of a target crop required for building a learning dataset in relation to an embodiment of the present invention.

[0056] The output unit (420) is an output means for displaying the result of an operation performed by the processor (430), and the input unit (440) is a user interface that receives user commands and transmits them to the processor (430).

[0057] The processor (430) trains a genotype data augmentation model according to the procedure shown in FIG. 4 described above, and uses the trained genotype data augmentation model to build a training dataset for a crop phenotype prediction model according to the procedure shown in FIG. 1 described above.

[0058] The storage unit (450) provides storage space necessary for the processor (430) to function and operate. In relation to an embodiment of the present invention, the storage unit (450) may store a learning dataset, a genotype data augmentation model, a crop phenotype prediction model, etc.

[0059] Up to now, a method for augmenting crop genotype data based on genotype location information and a method for constructing a training dataset for a crop phenotype prediction model using the same have been described in detail with reference to preferred embodiments.

[0060] In the above embodiment, the problem of insufficient training datasets is resolved by utilizing genotype location information and SNP data to augment crop genome data and construct a diverse and sufficient training dataset for crop phenotype prediction models. Furthermore, by reflecting SNP location dependency when augmenting genotype data so that gene mutations occur only at realistically significant locations, it is possible to augment with genotype data that corresponds to actual biological characteristics, thereby increasing the reliability and accuracy of crop phenotype prediction models through training datasets constructed via data augmentation that have statistical characteristics similar to existing genotype data.

[0061] Meanwhile, it goes without saying that the technical concept of the present invention may also be applied to a computer-readable recording medium containing a computer program that enables the device and method according to the present embodiment to perform their functions. Furthermore, the technical concept according to various embodiments of the present invention may be implemented in the form of computer-readable code recorded on a computer-readable recording medium. A computer-readable recording medium may be any data storage device that can be read by a computer and store data. For example, a computer-readable recording medium may be a ROM, RAM, CD-ROM, magnetic tape, floppy disk, optical disk, hard disk drive, etc. Additionally, computer-readable code or a program stored on a computer-readable recording medium may be transmitted through a network connected between computers.

[0062] Furthermore, although preferred embodiments of the present invention have been illustrated and described above, the present invention is not limited to the specific embodiments described above. Various modifications are possible by those skilled in the art without departing from the essence of the invention as claimed in the claims, and such modifications should not be understood individually from the technical spirit or perspective of the present invention.

Claims

1. A step of acquiring genomic data including genotype data for crops and location data for each genotype; A step of acquiring phenotypic data consisting of traits for crops; A step of preprocessing acquired genomic data and phenotypic data; A step of constructing a training dataset for a crop phenotype prediction model, which is a machine learning model that predicts crop phenotype data from crop genomic data, by combining preprocessed genomic data and phenotype data; A step of extracting an embedding vector from preprocessed genomic data; A step of generating new genotype data different from the genotype data of the preprocessed genome data from the extracted embedding vector; A method for constructing a training dataset for a crop phenotype prediction model, characterized by including the step of adding a new training dataset by combining newly generated genotype data with location data and preprocessed genomic data and preprocessed phenotype data.

2. In Claim 1, Genotype data, A method for constructing a training dataset for a crop phenotype prediction model characterized by being SNP (Single Nucleotide Polymorphism) data.

3. In Claim 1, The preprocessing step is, A method for constructing a training dataset for a crop phenotype prediction model, characterized by acquiring genomic data and phenotypic data by classifying them by crop variety.

4. In Claim 1, The preprocessing step is, A method for constructing a training dataset for a crop phenotype prediction model, characterized by including the step of converting the base sequence of genotype data into an integer.

5. In Claim 4, The integerization step is, A method for constructing a training dataset for a crop phenotype prediction model, characterized by mapping allele combinations of genotype data to individual integer values ​​to convert them into integers.

6. In Claim 1, The preprocessing step is, A method for constructing a training dataset for a crop phenotype prediction model, characterized by dividing each trait data of the phenotype data into multiple intervals and categorizing them.

7. In Claim 1, The extraction step is, A step of extracting an embedding vector from genotype data of genomic data; A step of extracting an embedding vector from location data of genomic data; A method for constructing a training dataset for a crop phenotype prediction model, characterized by including the step of combining extracted embedding vectors into a single embedding vector.

8. In Claim 7, The generation step is, A step of inputting the combined embedding vector into a convolution layer to extract features; A method for constructing a training dataset for a crop phenotype prediction model, characterized by including the step of inputting extracted features into an FCL and generating new genotype data by mean pooling the features.

9. In Claim 8, The extraction step is, It is performed using an embedding network that extracts embedding vectors from preprocessed genomic data, and The generation step is, It is performed using a genotype generation network that generates new genotype data from extracted embedding vectors, and Embedding networks and genotype generation networks are, A method for constructing a training dataset for a crop phenotype prediction model, characterized in that parameters are updated and learned in a direction that reduces the loss between the new genotype data and the preprocessed genomic data.

10. An acquisition unit that acquires genomic data including genotype data for crops and position data for each genotype, and phenotypic data composed of traits for crops; A system for constructing a training dataset for a crop phenotype prediction model, characterized by comprising: a processor that preprocesses acquired genomic data and phenotype data, constructs a training dataset for a crop phenotype prediction model, which is a machine learning model that predicts crop phenotype data from crop genomic data by combining the preprocessed genomic data and phenotype data, extracts an embedding vector from the preprocessed genomic data, generates new genotype data different from the genotype data of the preprocessed genomic data from the extracted embedding vector, and adds a new training dataset by combining the generated new genotype data, location data of the preprocessed genomic data, and the preprocessed phenotype data.

11. A step of acquiring genomic data including genotype data for crops and location data for each genotype; A step of preprocessing acquired genomic data; A step of extracting an embedding vector from preprocessed genomic data; A genotype data augmentation method characterized by including the step of generating new genotype data different from the genotype data of preprocessed genomic data from an extracted embedding vector.

12. An acquisition unit for acquiring genomic data including genotype data for crops and location data for each genotype; A genotype data augmentation system characterized by including a processor that preprocesses acquired genomic data, extracts an embedding vector from the preprocessed genomic data, and generates new genotype data different from the genotype data of the preprocessed genomic data from the extracted embedding vector.

Images