Plant genome sequencing data analysis method and system based on artificial intelligence
By combining long and short-term memory networks and AI sliding sampling core technology, a genome expression description vector relationship network is constructed and noise analysis is integrated, which solves the problem of noise perturbation recognition in genome sequencing data analysis, improves the depth and accuracy of data analysis, and achieves more Comprehensive noise detection and data quality assessment.
Patent Information
- Application Number
- CN202410961338.7
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-07-17
- Publication Date
- 2024-11-12
- Estimated Expiration
- 2044-07-17
AI Technical Summary
Existing genome sequencing data analysis methods have insufficient data depth and breadth requirements when dealing with complex genome expression volume, transcript structure or epigenetic marker characteristics, and the noise perturbation problem is difficult to effectively identify and process, affecting the accuracy and reliability of the data. .
Using long-term and short-term memory networks based on artificial intelligence and AI sliding sampling core technology, a vector relationship network of genome expression description is constructed, and the sequencing noise perturbation results are determined through vector relationship network bi-unit integration to improve the sensitivity and accuracy of noise detection.
It significantly improves the accuracy and reliability of genome sequencing data analysis, enables more precise identification and processing of noise perturbations, provides a more comprehensive data quality assessment, and supports subsequent data cleaning and experimental design.
Smart Images

Figure CN118942543A_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the field of artificial intelligence technology, and in particular to an artificial intelligence-based plant genome sequencing data analysis method and analysis system. Background Art
[0002] In the field of genome sequencing data analysis, the application of artificial intelligence and neural network models has become increasingly common. These advanced technologies, with their powerful data processing capabilities and efficient algorithm accuracy, are gradually changing the way we understand and mine genome data.
[0003] Artificial intelligence technologies, especially deep learning, have been widely used in the classification, prediction and analysis of genomic data. They can extract useful biological information from massive sequencing data and help researchers reveal the complex relationship between genes and phenotypes. Neural network models, with their excellent pattern recognition and feature extraction capabilities, can discover hidden laws and associations in genomic data that are difficult to capture with traditional methods.
[0004] However, although artificial intelligence and neural network models have shown great potential in genome sequencing data analysis, there are still some challenges and problems. Traditional sequencing data analysis methods, even after combining these advanced technologies, are still limited by data processing capabilities and algorithm accuracy, making it difficult to fully mine the deep information in genomic data. Especially when faced with complex feature sets such as genomic expression, transcript structure, or epigenetic markers, the limitations of these traditional methods become increasingly obvious, and they often cannot meet the needs of modern scientific research for data depth and breadth.
[0005] Even more serious is the widespread noise disturbance problem in sequencing data. This noise not only comes from technical limitations in the sequencing process, but can also be introduced by multiple links such as sample processing and data reading. The presence of noise seriously affects the accuracy and reliability of the data, and is a major problem that researchers must face. Unfortunately, although artificial intelligence and neural network models perform well in data processing and analysis, current noise detection methods still need to be improved in accurately identifying and quantifying noise disturbances in sequencing data. Summary of the invention
[0006] In order to improve the above problems, the present application provides a plant genome sequencing data analysis method and analysis system based on artificial intelligence.
[0007] The present application embodiment provides a plant genome sequencing data analysis method based on artificial intelligence, which is applied to an artificial intelligence analysis system. The method includes:
[0008] Determine a first genome expression description vector relationship network of a first initial genome sequencing data set and a second genome expression description vector relationship network of a second initial genome sequencing data set using a long short-term memory network, wherein the first initial genome sequencing data set and the second initial genome sequencing data set correspond to a target plant object, and the first genome expression description vector relationship network and the second genome expression description vector relationship network are any one of a genome expression feature set, a transcript structure feature set, or an epigenetic marker feature set;
[0009] Determine at least one local description vector relationship network from the first genome expression description vector relationship network and the second genome expression description vector relationship network based on the AI sliding sampling kernel, and determine at least one vector relationship network binary based on the data distribution characteristics of each local description vector relationship network in the corresponding genome expression description vector relationship network, wherein the first local description vector relationship network and the second local description vector relationship network in each vector relationship network binary belong to different genome expression description vector relationship networks and have the same data distribution characteristics in the corresponding genome expression description vector relationship network;
[0010] Integrate the first local description vector relationship network and the second local description vector relationship network in each of the vector relationship network binary groups to obtain a genome sequencing integrated vector set, and determine the sequencing noise perturbation results of the first local description vector relationship network and the second local description vector relationship network in the corresponding vector relationship network binary group based on each of the genome sequencing integrated vector sets;
[0011] Based on the sequencing noise perturbation results of each of the vector relationship network binary groups, the sequencing noise perturbation results of the first initial genome sequencing data set and the second initial genome sequencing data set are determined, and the sequencing noise perturbation results are the presence of sequencing noise perturbation or the absence of sequencing noise perturbation.
[0012] Further, for the first local description vector relationship network and the second local description vector relationship network in each of the vector relationship network tuples, the first local description vector relationship network and the second local description vector relationship network are integrated to obtain a genome sequencing integrated vector set, including:
[0013] Generate a genome sequencing integrated vector set based on the sequencing attention variables of each characteristic element of the first local description vector relationship network and the second local description vector relationship network, wherein each characteristic element of the genome sequencing integrated vector set includes at least one attention dimension, and the sequencing attention variable of each attention dimension is determined by at least one of the sequencing attention variables of the first local description vector relationship network corresponding to the characteristic element or the sequencing attention variables of the second local description vector relationship network corresponding to the characteristic element;
[0014] Among them, the sequencing attention variable of each characteristic element of the genomic expression feature set is the genomic expression mapping parameter, the sequencing attention variable of each characteristic element of the transcript structure feature set is the transcript structure mapping parameter, and each characteristic element of the epigenetic mark feature set corresponds to multiple sequencing attention variables and each sequencing attention variable is an epigenetic mapping parameter of an epigenetic attention dimension.
[0015] Further, the AI sliding sampling kernel is used to determine at least one local description vector relationship network from the first genome expression description vector relationship network and the second genome expression description vector relationship network, respectively, including:
[0016] Determine at least one first target data distribution feature in the first genome expression description vector relationship network, determine the data distribution feature in the second genome expression description vector relationship network that is the same as each of the first target data distribution features as a second target data distribution feature, and each of the first target data distribution features is used to reflect the core sequencing embedding vector of the first genome expression description vector relationship network;
[0017] Based on the AI sliding sampling kernel and the selected sampling strategy, at least one local description vector relationship network is determined from each of the first target data distribution characteristics and each of the second target data distribution characteristics.
[0018] Furthermore, the determining the sequencing noise perturbation results of the first initial genome sequencing data set and the second initial genome sequencing data set based on the sequencing noise perturbation results of each of the vector relationship network binary groups includes:
[0019] Determine at least one target data distribution feature cluster, each of the target data distribution feature clusters including one of the first target data distribution features and a second target data distribution feature corresponding to the first target data distribution feature;
[0020] Determine the first number of vector relationship network tuples corresponding to each of the target data distribution feature clusters, and the second number of vector relationship network tuples in which the sequencing noise disturbance result in the corresponding vector relationship network tuple is that there is no sequencing noise disturbance;
[0021] For each of the target data distribution feature clusters, determining sequencing noise perturbation results of the first target data distribution feature and the second target data distribution feature in the target data distribution feature cluster based on the first number and the second number corresponding to the target data distribution feature cluster;
[0022] Based on the sequencing noise perturbation results of each of the target data distribution feature clusters, the sequencing noise perturbation results of the first initial genome sequencing data set and the second initial genome sequencing data set are determined.
[0023] Further, for each of the target data distribution feature clusters, determining the sequencing noise perturbation results of the first target data distribution feature and the second target data distribution feature in the target data distribution feature cluster based on the first number and the second number corresponding to the target data distribution feature cluster includes:
[0024] Determine a first ratio of a second number corresponding to the target data distribution feature cluster to a first number corresponding to the first number;
[0025] If the first proportion corresponding to the target data distribution feature cluster is less than the first threshold value, determine the noise disturbance analysis weight of the target data distribution feature cluster based on the first proportion corresponding to the target data distribution feature cluster and the second number, and determine the sequencing noise disturbance results of the first target data distribution feature and the second target data distribution feature in the target data distribution feature cluster based on the noise disturbance analysis weight;
[0026] If the first proportion corresponding to the target data distribution feature cluster is not less than the first threshold value, it is determined that the sequencing noise disturbance results of the first target data distribution feature and the second target data distribution feature in the target data distribution feature cluster are that there is no sequencing noise disturbance.
[0027] Furthermore, determining the sequencing noise perturbation results of the first initial genome sequencing data set and the second initial genome sequencing data set based on the sequencing noise perturbation results of each of the target data distribution feature clusters includes:
[0028] If the sequencing noise perturbation result of at least one of the target data distribution feature clusters is that there is no sequencing noise perturbation, determining that the sequencing noise perturbation results of the first initial genome sequencing data set and the second initial genome sequencing data set are that there is no sequencing noise perturbation;
[0029] If the sequencing noise perturbation results of each of the target data distribution feature clusters are that sequencing noise perturbations exist, it is determined that the sequencing noise perturbation results of the first initial genome sequencing data set and the second initial genome sequencing data set are that sequencing noise perturbations exist.
[0030] Furthermore, the sequencing noise perturbation results of the first local description vector relationship network and the second local description vector relationship network in the corresponding vector relationship network tuple determined based on each genome sequencing integrated vector set are achieved through a long short-term memory network, and the long short-term memory network is debugged by the following steps:
[0031] Determine a plurality of genome expression vector relationship network sample tuples, each of the genome expression vector relationship network sample tuples comprising a first genome expression description vector relationship network sample of a first initial genome sequencing data set sample and a second genome expression description vector relationship network sample of a second initial genome sequencing data set sample, the first initial genome sequencing data set sample and the second initial genome sequencing data set sample correspond to a target plant object, and the first genome expression description vector relationship network sample and the second genome expression description vector relationship network sample are respectively any one of a genome expression feature set, a transcript structure feature set or an epigenetic marker feature set;
[0032] Integrate the first genome expression description vector relationship network sample and the second genome expression description vector relationship network sample in each genome expression vector relationship network sample binary to obtain a genome sequencing integrated vector set sample, input each genome sequencing integrated vector set sample into an initial recurrent neural network to obtain a discriminant viewpoint corresponding to each genome sequencing integrated vector set sample, and determine the sequencing noise perturbation prediction result of the first genome expression description vector relationship network sample and the second genome expression description vector relationship network sample in the genome expression vector relationship network sample binary corresponding to each genome sequencing integrated vector set sample based on the discriminant viewpoint;
[0033] Based on the actual sequencing noise perturbation results and the sequencing noise perturbation prediction results of the first genome expression description vector relationship network sample and the second genome expression description vector relationship network sample in each genome expression vector relationship network sample binary group, a debugging error function is determined, and the initial recurrent neural network is debugged based on the debugging error function and each genome expression vector relationship network sample binary group until the debugging is completed when the debugging error function meets the debugging termination requirements, and the recurrent neural network obtained after the debugging is determined as the long short-term memory network.
[0034] Furthermore, when the sequencing noise disturbance result is that there is sequencing noise disturbance, the method further includes:
[0035] Based on the sequencing noise disturbance result, the first initial genome sequencing data set and the second initial genome sequencing data set are subjected to denoising processing.
[0036] Furthermore, the method further comprises:
[0037] The genome sequencing system of the target plant object is updated.
[0038] An embodiment of the present application provides an artificial intelligence analysis system, comprising at least one processor and a memory; the memory stores computer-executable instructions; the at least one processor executes the computer-executable instructions stored in the memory, so that the at least one processor performs the above method.
[0039] An embodiment of the present application provides a computer-readable storage medium on which a computer program is stored. The computer program implements the above method when running.
[0040] In the embodiment of the present application, firstly, by using the long short-term memory network, a first genome expression description vector relationship network corresponding to the first initial genome sequencing data set and a second genome expression description vector relationship network of the second initial genome sequencing data set corresponding to the target plant object can be accurately constructed. This network model is not only applicable to the genome expression feature set, but also can effectively process the transcript structure feature set or epigenetic marker feature set, showing its wide applicability.
[0041] Secondly, the embodiment of the present application innovatively introduces AI sliding sampling kernel technology. Through this technology, it is possible to accurately extract local description vector relationship networks from complex genome expression description vector relationship networks, and further construct vector relationship network tuples based on the similarity of data distribution characteristics. This process not only improves the precision of data analysis, but also provides strong support for subsequent noise perturbation analysis.
[0042] Furthermore, the embodiment of the present application integrates the local description vector relationship network in the vector relationship network binary to form a genome sequencing integrated vector set. This step enables more accurate determination of the sequencing noise disturbance result, thereby effectively improving the sensitivity and accuracy of noise detection.
[0043] Finally, by synthesizing the sequencing noise perturbation results of each vector relationship network binary, the embodiment of the present application can comprehensively evaluate the sequencing noise perturbation of the first initial genome sequencing data set and the second initial genome sequencing data set. This evaluation result not only provides important information about data quality for researchers, but also helps guide subsequent data cleaning and experimental design work, thereby significantly improving the accuracy and reliability of genome sequencing data analysis.
[0044] In summary, the embodiment of the present application cleverly combines the long short-term memory network with the AI sliding sampling kernel technology, bringing innovation to the analysis of genome sequencing data. Through the long short-term memory network, the genome expression description vector relationship network of the target plant object is accurately constructed, which is suitable for a variety of feature sets. The introduction of AI sliding sampling kernel technology realizes the accurate extraction of local description vector relationship networks from complex data, and constructs vector relationship network tuples based on data distribution characteristics, thereby improving the precision of data analysis. Furthermore, by integrating the vector relationship network tuples, a genome sequencing integrated vector set is formed, thereby improving the sensitivity and accuracy of noise detection. In this way, the noise disturbance of the sequencing data set can be comprehensively evaluated, important data quality information can be provided to scientific researchers, and subsequent data cleaning and experimental design can be assisted, significantly improving the accuracy and reliability of genome sequencing data analysis. BRIEF DESCRIPTION OF THE DRAWINGS
[0045] Figure 1 A flow chart of a plant genome sequencing data analysis method based on artificial intelligence provided in an embodiment of the present application.
[0046] Figure 2 A schematic diagram of the structure of an artificial intelligence analysis system provided in an embodiment of the present application. DETAILED DESCRIPTION
[0047] In order to better understand the above technical scheme, the technical scheme of the present application is described in detail below through the accompanying drawings and specific embodiments. It should be understood that the embodiments of the present application and the specific features in the embodiments are detailed descriptions of the technical scheme of the present application, rather than limitations on the technical scheme of the present application. In the absence of conflict, the embodiments of the present application and the technical features in the embodiments can be combined with each other.
[0048] Figure 1 A plant genome sequencing data analysis method based on artificial intelligence is shown, which is applied to an artificial intelligence analysis system. The method includes the following steps 110-140.
[0049] Step 110: Determine a first genome expression description vector relationship network of the first initial genome sequencing data set and a second genome expression description vector relationship network of the second initial genome sequencing data set using a long short-term memory network.
[0050] Among them, the first initial genome sequencing data set and the second initial genome sequencing data set correspond to target plant objects, and the first genome expression description vector relationship network and the second genome expression description vector relationship network are respectively any one of a genome expression feature set, a transcript structure feature set or an epigenetic marker feature set.
[0051] In the embodiment of the present application, the long short-term memory network (LSTM) is a special recurrent neural network (RNN) that can learn long-term dependencies. In genome sequencing data analysis, LSTM can be trained to recognize complex patterns in sequence data, such as specific structures and functional regions in gene sequences. LSTM can effectively handle long-term dependency problems in sequences through its unique gating mechanism, making it perform well in processing large-scale sequences such as genomic data.
[0052] The first initial genome sequencing dataset refers to the data set obtained from the first round of genome sequencing of the target plant object. These data contain detailed information about the plant genome and are the basis for subsequent analysis and comparison. The quality and integrity of the first initial genome sequencing dataset are crucial for accurately analyzing the structure and function of the plant genome.
[0053] The first genome expression description vector relationship network is a data structure obtained by processing the first initial genome sequencing data set through a specific algorithm (such as LSTM). It converts complex genomic data into vector form, which is convenient for mathematical operations and comparative analysis. This relationship network captures the expression characteristics, transcript structure characteristics or epigenetic marker characteristics in the genome, providing researchers with an intuitive and quantitative way to understand and compare the differences and similarities of genomes.
[0054] Second initial genome sequencing dataset: Similar to the first initial genome sequencing dataset, but can be sequenced at different time points, conditions, or different parts of the plant. By comparing the first and second initial genome sequencing datasets, researchers can explore changes in gene expression in plants under different environments or developmental stages.
[0055] The second genome expression description vector relationship network is a vector relationship network constructed based on the second initial genome sequencing data set. Similar to the first genome expression description vector relationship network, it also captures specific features of the genome, but reflects the information in the second initial genome sequencing data set.
[0056] Target plant objects refer to specific plant species or individuals selected by researchers and are the focus of genome sequencing and analysis. By deeply studying the genome of target plant objects, scientists can reveal their genetic characteristics, physiological functions, and adaptability to the environment.
[0057] Furthermore, the genomic expression feature set is a set of features that describe the expression level of genes under specific conditions. Expression refers to the amount of mRNA transcribed from a gene, which reflects the activity of the gene in the cell. The genomic expression feature set helps to understand which genes are activated or inhibited under specific conditions. The transcript structure feature set focuses on the structural information of gene transcripts, such as the boundaries and lengths of exons and introns. Transcript structure is crucial for understanding the function and regulatory mechanism of genes because it determines the composition and splicing mode of protein coding sequences. The epigenetic mark feature set is a set of features that describe epigenetic modifications (such as DNA methylation, histone modifications, etc.) on the genome. These modifications can affect gene expression without changing the DNA sequence. The epigenetic mark feature set is of great significance for parsing the complex regulatory network of gene expression.
[0058] In some examples, the first genome expression description vector relationship network is a high-dimensional data structure in which each gene or gene expression product is represented as a numerical feature vector. For example, there are 1,000 genes, and the expression level of each gene can be quantified as a specific value, so that a 1,000-dimensional feature vector is obtained. Each element in this vector represents the expression of the corresponding gene, and the magnitude of the value reflects the expression intensity of the gene. The relationship network formed by these vectors in space shows the expression correlation and interaction relationship between genes. Similar to the first genome expression description vector relationship network, the second genome expression description vector relationship network is also composed of numerical feature vectors. However, these vectors are obtained based on the second initial genome sequencing data set. Therefore, although the dimension and structure can be similar to the first relationship network, the values therein will reflect the gene expression under different conditions or time points. By comparing these two relationship networks, the changes in gene expression under different environments or states can be analyzed. The genome expression feature set is a set containing multiple numerical features, each of which represents the expression of a gene. For example, a feature vector can be as follows: [5.6, 3.2, 8.9, ..., 1.2], where each value represents the expression of a specific gene. This feature set can help understand which genes are upregulated or downregulated under different conditions. The transcript structure feature set focuses on the structural characteristics of the transcript, such as exon length, number of introns, etc. These features can also be quantified into values and form a feature vector. For example, a transcript structure feature vector can include: [300, 4, 200, ...], where the values represent the length of the first exon, the number of introns, the length of the second exon, etc. These features help understand the complexity of the transcript and its possible functional impact. The epigenetic mark feature set contains a series of numerical features that describe epigenetic modifications, such as DNA methylation levels, histone modification status, etc. These features can also be represented as numerical feature vectors. For example, a DNA methylation feature vector can be: [0.8, 0.3, 0.9, ...], where the values represent the methylation levels of different gene loci. These features are crucial for understanding epigenetic regulation of gene expression. The above examples provide a powerful tool for quantifying and comparing genomic data, which helps to gain a deeper understanding of the complexity and function of the genome.
[0059] Based on the above, in step 110, the artificial intelligence analysis system begins its complex genome data analysis process. First, the system uses the long short-term memory network (LSTM), a powerful deep learning tool, to process the first initial genome sequencing data set. The LSTM network, through its unique memory unit and gating mechanism, can capture long-term dependencies and complex patterns in the genome sequence, thereby generating a first genome expression description vector relationship network. This relationship network accurately represents the expression quantity characteristics, transcript structure characteristics or epigenetic marker characteristics in the genome in the form of a vector, depending on the purpose and needs of the analysis. Similarly, the artificial intelligence analysis system also performs the same processing on the second initial genome sequencing data set. This data set can come from different tissues, different developmental stages or samples under different environmental conditions of the same plant. Through the processing of the LSTM network, the system generates a second genome expression description vector relationship network, which also captures the specific characteristics of the genome in the form of a vector. These two vector relationship networks provide a basis for subsequent comparison and analysis. Researchers can compare these two relationship networks to explore the changes in gene expression, differences in transcript structure or the distribution of epigenetic markers in plants under different conditions. The accuracy and effectiveness of this step is crucial to the entire genome sequencing data analysis process because it provides high-quality data input and analysis foundation for subsequent steps.
[0060] Step 120: Determine at least one local description vector relationship network from the first genome expression description vector relationship network and the second genome expression description vector relationship network based on the AI sliding sampling kernel, and determine at least one vector relationship network tuple based on the data distribution characteristics of each local description vector relationship network in the corresponding genome expression description vector relationship network.
[0061] The first local description vector relationship network and the second local description vector relationship network in each of the vector relationship network tuples belong to different genome expression description vector relationship networks and have the same data distribution characteristics in the corresponding genome expression description vector relationship networks.
[0062] In the embodiments of the present application, the AI sliding sampling kernel is an advanced data processing technology that can perform sliding sampling in large and complex data sets. In genomic analysis, the AI sliding sampling kernel is used to effectively extract local data fragments, i.e., local description vector relationship networks, from the huge genome expression description vector relationship network. This technology can capture subtle changes and important features in the data set through intelligent sliding and sampling, providing strong support for subsequent data analysis and comparison.
[0063] The local description vector relationship network is a part of the data extracted from the entire genome expression description vector relationship network through the AI sliding sampling kernel. It represents the characteristics and relationships of a specific region or fragment in the original data set. These local description vector relationship networks can more finely reflect the local characteristics and change patterns of the genome, helping researchers to deeply explore the complex structure and function of the genome.
[0064] Data distribution characteristics refer to the distribution and characteristics of data in a specific space or range. In genomic analysis, data distribution characteristics can reveal key information such as the pattern of gene expression, the abundance of transcripts, and the distribution of epigenetic markers. By comparing the data distribution characteristics of different local description vector relationship networks, researchers can discover similarities and differences in the genome, thereby gaining a deeper understanding of the function and regulatory mechanism of genes.
[0065] A vector relationship network tuple is a pair of two local description vector relationship networks from different genome expression description vector relationship networks. Although these two local description vector relationship networks are in different original data sets, their data distribution characteristics in their respective data sets are the same or highly similar. The construction of this tuple helps researchers compare and analyze across data sets and discover the commonalities and differences between different genomes.
[0066] The first local description vector relationship network is a local data segment extracted from the first genome expression description vector relationship network by the AI sliding sampling kernel. It represents the characteristics and relationships of a specific region in the first data set, providing an important data basis for subsequent comparison and analysis. Similar to the first local description vector relationship network, the second local description vector relationship network is a local data segment extracted from the second genome expression description vector relationship network. It reflects the characteristics and relationships of the corresponding region in the second data set, and together with the first local description vector relationship network, it constitutes a vector relationship network tuple for comparison and analysis across data sets.
[0067] In step 120, the artificial intelligence analysis system begins to use its powerful AI sliding sampling kernel technology to conduct in-depth analysis of the previously constructed first genome expression description vector relationship network and the second genome expression description vector relationship network. The goal of this step is to determine at least one local description vector relationship network and find the similarities and differences between the data. First, the system uses the AI sliding sampling kernel to perform sliding sampling in the first genome expression description vector relationship network, intelligently identifies and extracts representative local data fragments, which constitute the first local description vector relationship network. This process can accurately capture the local features and subtle changes in the genome, providing a rich data basis for subsequent comparative analysis. Similarly, the system also performs a similar sliding sampling operation on the second genome expression description vector relationship network to obtain a second local description vector relationship network. These two local description vector relationship networks represent specific regions or features in two different data sets. Next, the system begins to compare the data distribution characteristics of these local description vector relationship networks in their respective original data sets. Through precise data analysis and comparison, the system can identify those local description vector relationship networks that have a high degree of similarity in data distribution and pair them to form vector relationship network tuples. Each vector relationship network binary contains a first local description vector relationship network from the first genome expression description vector relationship network and a second local description vector relationship network from the second genome expression description vector relationship network. The key to this step is to use the intelligence and precision of AI sliding sampling kernel technology to extract valuable local information from complex genomic data and discover the commonalities and differences between different data sets by comparing data distribution characteristics. This lays a solid foundation for subsequent genome sequencing data integration and noise perturbation analysis.
[0068] Step 130: Integrate the first local description vector relationship network and the second local description vector relationship network in each of the vector relationship network tuples to obtain a genome sequencing integrated vector set, and determine the sequencing noise perturbation results of the first local description vector relationship network and the second local description vector relationship network in the corresponding vector relationship network tuple based on each of the genome sequencing integrated vector sets.
[0069] In the present application embodiment, the genome sequencing integrated vector set is a comprehensive data set formed by integrating genome sequencing data from different sources or under different conditions. In this data set, each gene or gene expression product is represented as a numerical feature vector, and these vectors are combined together to form a data set that fully reflects genome characteristics. This integration not only helps scientific researchers obtain more comprehensive gene expression information, but also reveals the dynamic changes and regulatory mechanisms of gene expression by comparing data under different conditions.
[0070] Sequencing noise perturbation results refer to the deviation between sequencing data and the actual situation caused by various factors (such as sequencing instrument errors, sample processing differences, etc.) during the genome sequencing process. This perturbation result can be manifested as abnormal fluctuations in gene expression, misidentification of transcript structure, or inaccurate measurement of epigenetic markers. By analyzing the sequencing noise perturbation results, researchers can evaluate the accuracy and reliability of sequencing data, thereby providing important reference for subsequent data analysis and interpretation.
[0071] In detail, step 130 is a key link in the entire genome sequencing data analysis process, which involves integrating the vector relationship network tuples identified and paired in the previous steps, and determining the sequencing noise disturbance based on the integration results. First, the system traverses each vector relationship network tuple, which is formed by pairing the first local description vector relationship network and the second local description vector relationship network, and their data distribution characteristics in their respective original data sets are the same or highly similar. For each tuple, the system uses specific algorithms and technologies to integrate them. This integration process is not a simple data merger, but takes into account the differences between different data sets, and ensures that the integrated data can truly reflect the characteristics of the original data through weighted averaging, data standardization and other methods. After the integration is completed, the system obtains a genome sequencing integrated vector set. This vector set combines information from different data sets and has a more comprehensive and accurate description of genome features. Next, based on this integrated vector set, the system analyzes the sequencing noise disturbance of the first local description vector relationship network and the second local description vector relationship network in each tuple. When analyzing the sequencing noise disturbance, the system uses statistical methods and machine learning algorithms to compare the differences between the integrated vector set and the original data. These differences can come from various noise factors in the sequencing process, such as instrument errors, sample preparation differences, etc. The system quantifies these differences and generates a sequencing noise disturbance result. This result can not only help researchers understand the accuracy and reliability of sequencing data, but also provide an important reference for subsequent data interpretation and experimental result verification. It can be seen that step 130 is a comprehensive data processing and analysis process. It integrates and compares information from different data sets, reveals the noise disturbance in genome sequencing data, and provides more accurate and comprehensive data support for researchers.
[0072] Step 140: Determine the sequencing noise perturbation results of the first initial genome sequencing data set and the second initial genome sequencing data set based on the sequencing noise perturbation results of each of the vector relationship network binary groups, wherein the sequencing noise perturbation result is the presence of sequencing noise perturbation or the absence of sequencing noise perturbation.
[0073] In an embodiment of the present application, the goal of the system is to comprehensively determine whether there is sequencing noise disturbance in the first initial genome sequencing data set and the second initial genome sequencing data set based on the sequencing noise disturbance results of each vector relationship network binary obtained in the previous step.
[0074] First, the system aggregates and analyzes the sequencing noise perturbation results for all vector relationship network pairs. These results contain detailed information about how the local description vector relationship network differs from the original data during the integration process. The system carefully reviews these perturbation results, especially focusing on those pairs that show significant noise perturbation.
[0075] Next, the system counts and analyzes these noise perturbation results. It calculates the proportion of binary groups with noise perturbations, as well as the size and distribution of these perturbations. This information will help the system comprehensively evaluate the sequencing quality of the entire data set.
[0076] Then, based on these detailed noise perturbation analyses, the system makes a comprehensive judgment. If most of the vector relationship network tuples show significant noise perturbation, or the tuples in certain key areas have serious noise problems, then the system may determine that the entire first initial genome sequencing data set or the second initial genome sequencing data set has sequencing noise perturbation. Conversely, if only a few tuples show slight noise perturbation, and most of the data remain stable and consistent, then the system may determine that the data set does not have significant sequencing noise perturbation.
[0077] Finally, the system generates a detailed report that includes the analysis results of sequencing noise disturbance and the system's comprehensive judgment. This report will provide valuable information for researchers to help them understand the quality and reliability of sequencing data, thereby guiding subsequent experimental design and data analysis.
[0078] It can be seen that step 140 is a key step to comprehensively evaluate the noise disturbance of sequencing data. It provides researchers with an accurate judgment on the quality of the entire sequencing data set by analyzing the noise disturbance results of each vector relationship network binary, which helps to ensure the accuracy and reliability of subsequent research.
[0079] In summary, in a complete plant genome research case, the artificial intelligence analysis system was used to deeply analyze and process two sets of genome sequencing data to detect potential sequencing noise disturbances. First, the artificial intelligence analysis system obtained the first initial genome sequencing data set and the second initial genome sequencing data set of the target plant object. These data sets can come from different tissue samples of the same plant, or the sequencing results of the same tissue at different time points or conditions. The system uses the long short-term memory network (LSTM), a powerful deep learning model, to construct the first genome expression description vector relationship network and the second genome expression description vector relationship network respectively. These relationship networks can capture genome expression quantity characteristics, transcript structure characteristics, or epigenetic mark characteristics, depending on the needs and purposes of the analysis. Next, the artificial intelligence analysis system uses AI sliding sampling kernel technology to perform local sampling in these two genome expression description vector relationship networks. The purpose of this step is to identify and extract local description vector relationship networks with similar data distribution characteristics to form vector relationship network tuples. The two local description vector relationship networks in each tuple come from different initial genome sequencing data sets, but they show the same data distribution characteristics in their respective data sets. Subsequently, the system integrates the local description vector relationship networks in each vector relationship network binary to generate a genome sequencing integrated vector set. This process helps to comprehensively compare the corresponding parts in the two initial data sets, thereby more accurately identifying sequencing noise. By comparing and analyzing these integrated vector sets, the artificial intelligence analysis system is able to determine the sequencing noise perturbation results in each vector relationship network binary. Finally, based on the sequencing noise perturbation analysis results of all vector relationship network binary groups, the artificial intelligence analysis system draws a conclusion about the overall sequencing noise perturbation of the first initial genome sequencing data set and the second initial genome sequencing data set. This conclusion clearly indicates whether there is sequencing noise perturbation in the data set, providing researchers with valuable information to help them evaluate data quality and guide subsequent experimental design and data analysis. In this way, the artificial intelligence analysis system not only improves the efficiency and accuracy of genome sequencing data processing, but also assists in the in-depth understanding and exploration of the complexity and dynamics of plant genomes.
[0080] The embodiment of the present application provides an accurate and efficient analysis method for the genome sequencing data of the target plant object by innovatively combining the long short-term memory network with the AI sliding sampling kernel technology. Specifically, through the long short-term memory network, the first genome expression description vector relationship network of the first initial genome sequencing data set and the second genome expression description vector relationship network of the second initial genome sequencing data set can be accurately constructed, whether it is a genome expression feature set, a transcript structure feature set or an epigenetic marker feature set, all can be effectively expressed. Furthermore, with the help of AI sliding sampling kernel technology, it is possible to accurately extract local description vector relationship networks from complex vector relationship networks, and construct vector relationship network binaries based on the similarity of data distribution characteristics. This step not only improves the meticulousness of data analysis, but also lays a solid foundation for subsequent noise disturbance analysis.
[0081] In addition, another significant advantage of the embodiment of the present application is that, by integrating the local description vector relationship network in the vector relationship network binary, a genome sequencing integrated vector set is formed, so that the sequencing noise disturbance result can be determined more accurately. This method not only improves the sensitivity of noise detection, but also provides a comprehensive assessment of the quality of sequencing data. Finally, by combining the sequencing noise disturbance results of each vector relationship network binary, it is possible to accurately determine whether the first initial genome sequencing data set and the second initial genome sequencing data set have sequencing noise disturbances, providing powerful data support for scientific researchers, which helps to improve the accuracy and reliability of genome sequencing data.
[0082] In some optional embodiments, for the first local description vector relationship network and the second local description vector relationship network in each of the vector relationship network binary groups, the first local description vector relationship network and the second local description vector relationship network are integrated to obtain a genome sequencing integrated vector set, including: generating a genome sequencing integrated vector set based on the sequencing attention variables of each characteristic element of the first local description vector relationship network and the second local description vector relationship network, wherein each characteristic element of the genome sequencing integrated vector set includes at least one attention dimension, and the sequencing attention variable of each attention dimension is determined by at least one of the sequencing attention variables of the first local description vector relationship network corresponding to the characteristic element or the sequencing attention variables of the second local description vector relationship network corresponding to the characteristic element; wherein the sequencing attention variable of each characteristic element of the genome expression feature set is a genome expression mapping parameter, the sequencing attention variable of each characteristic element of the transcript structure feature set is a transcript structure mapping parameter, and each characteristic element of the epigenetic mark feature set corresponds to multiple sequencing attention variables and each sequencing attention variable is an epigenetic mapping parameter of an epigenetic attention dimension.
[0083] Based on this embodiment, the artificial intelligence analysis system adopts a special method to integrate the first local description vector relationship network and the second local description vector relationship network in each vector relationship network binary, thereby obtaining a genome sequencing integrated vector set. The key to this process is to use the sequencing attention variable, which is an indicator to measure the importance of each feature element in the genome sequencing process.
[0084] First, the system examines each characteristic element in the first local description vector relationship network and the second local description vector relationship network. These characteristic elements can represent the expression of the genome, the structure of the transcript, or epigenetic markers, which are important parts of biological genetic information.
[0085] Next, the system calculates one or more sequencing attention variables for each feature element. These variables are essentially a mapping parameter that can reflect which feature elements are more concerned and which are relatively less important during the sequencing process. Specifically, if it is a genomic expression feature set, the sequencing attention variable of each feature element is the genomic expression mapping parameter; if it is a transcript structure feature set, then the sequencing attention variable of each feature element is the transcript structure mapping parameter; and for the epigenetic mark feature set, due to its complexity, each feature element will correspond to multiple sequencing attention variables, and each variable represents a mapping parameter for an epigenetic attention dimension.
[0086] After determining these sequencing attention variables, the artificial intelligence analysis system generates a genome sequencing integrated vector set based on them. Each feature element of this integrated vector set contains at least one attention dimension, and the sequencing attention variable of each attention dimension is determined by the sequencing attention variable of the corresponding feature element in the first local description vector relationship network or the second local description vector relationship network. This processing method not only retains the richness of the original data, but also introduces the attention mechanism, allowing the system to focus more on those important feature elements when processing genome sequencing data.
[0087] In this way, the artificial intelligence analysis system can more effectively mine the deep information in the genome sequencing data and improve the processing ability of complex genome feature sets. At the same time, due to the introduction of the attention mechanism, the system can also show stronger robustness in the face of noise disturbances, because it can more accurately identify and focus on those characteristic elements that have a greater impact on the analysis results. In this way, not only the accuracy and efficiency of the artificial intelligence analysis system in processing genome sequencing data are improved, but also the stability and reliability of the system in the face of complex data and noise disturbances are enhanced. This is an important technological breakthrough in the field of artificial intelligence in the field of genome sequencing data analysis, which is expected to provide researchers with more accurate and efficient data analysis tools and promote the in-depth development of genomic research.
[0088] Under some other preferred design ideas, the AI sliding sampling kernel is used to determine at least one local description vector relationship network from the first genome expression description vector relationship network and the second genome expression description vector relationship network, including: determining at least one first target data distribution feature in the first genome expression description vector relationship network, and determining the data distribution feature in the second genome expression description vector relationship network that is the same as each of the first target data distribution features as a second target data distribution feature, and each of the first target data distribution features is used to reflect the core sequencing embedding vector of the first genome expression description vector relationship network; based on the AI sliding sampling kernel and the selected sampling strategy, at least one local description vector relationship network is determined from each of the first target data distribution features and each of the second target data distribution features.
[0089] Under this design concept, the artificial intelligence analysis system uses a refined method to determine at least one local description vector relationship network from the first genome expression description vector relationship network and the second genome expression description vector relationship network. This process involves the identification and matching of data distribution features and the extraction of local descriptions based on AI sliding sampling kernels.
[0090] First, the system deeply analyzes the first genome expression description vector relationship network to determine at least one first target data distribution feature. These data distribution features can reflect the core information and key patterns in the genome sequencing data, similar to the "fingerprint" or "marker" in the data. The system identifies these features through complex algorithms, which can represent the core sequencing embedded vectors in the vector relationship network and are an important basis for subsequent analysis.
[0091] Next, the system searches for data distribution features that match the first target data distribution features in the second genome expression description vector relationship network and determines them as the second target data distribution features. This process is similar to finding common "markers" or "fingerprints" in two sets of data to ensure that the local description vector relationship networks extracted from the two vector relationship networks have similar or identical data characteristics, so that effective comparison and analysis can be performed.
[0092] After determining these target data distribution characteristics, the artificial intelligence analysis system uses the AI sliding sampling kernel and the selected sampling strategy to extract the local description vector relationship network from these characteristics. The AI sliding sampling kernel is an advanced data processing technology that can slide across the entire data set to capture the local characteristics of the data according to the selected sampling strategy. In this way, the system can accurately extract the local description vector relationship network that matches the target data distribution characteristics, providing an accurate data basis for subsequent noise detection and data analysis.
[0093] This not only improves the accuracy of data analysis, but also enables the system to process complex genome sequencing data more efficiently. It ensures that the local description vector relationship network extracted from two different genome expression description vector relationship networks has a high degree of similarity and comparability, thereby greatly improving the accuracy and reliability of subsequent noise detection and data analysis. Through this method, the artificial intelligence analysis system can more deeply explore the hidden information and association rules in genome sequencing data, and provide researchers with more comprehensive and accurate data analysis results.
[0094] In the next step, the sequencing noise perturbation results of the first initial genome sequencing data set and the second initial genome sequencing data set are determined based on the sequencing noise perturbation results of each of the vector relationship network binary groups, including: determining at least one target data distribution feature cluster, each of the target data distribution feature clusters including one of the first target data distribution features and a second target data distribution feature corresponding to the first target data distribution feature; determining the first number of the vector relationship network binary groups corresponding to each of the target data distribution feature clusters, and the second number of the vector relationship network binary groups in which the sequencing noise perturbation results in the corresponding vector relationship network binary groups are the ones without sequencing noise perturbation; for each of the target data distribution feature clusters, based on the first number and the second number corresponding to the target data distribution feature cluster, determining the sequencing noise perturbation results of the first target data distribution feature and the second target data distribution feature in the target data distribution feature cluster; based on the sequencing noise perturbation results of each of the target data distribution feature clusters, determining the sequencing noise perturbation results of the first initial genome sequencing data set and the second initial genome sequencing data set.
[0095] Based on this embodiment, the artificial intelligence analysis system takes a series of sophisticated operations to determine the sequencing noise perturbation results of the first initial genome sequencing data set and the second initial genome sequencing data set. This process involves the determination of the target data distribution feature clusters, the statistics of the vector relationship network binary groups, and the determination of the sequencing noise perturbation results based on these data.
[0096] First, the system determines at least one target data distribution feature cluster. These feature clusters are composed of the first target data distribution features and their corresponding second target data distribution features. In simple terms, each feature cluster contains similar or matching data distribution features from two initial genome sequencing data sets, which provides a basis for subsequent comparison and analysis.
[0097] Next, the system counts the number of vector network bigrams corresponding to each target data distribution feature cluster, which is the first number. At the same time, the system also counts the number of vector network bigrams whose sequencing noise perturbation results are that there is no sequencing noise perturbation among these vector network bigrams, which is the second number. The statistics of these two numbers are crucial for the subsequent judgment of the sequencing noise perturbation situation.
[0098] Then, for each target data distribution feature cluster, the system determines the sequencing noise perturbation results of the first target data distribution feature and the second target data distribution feature in the feature cluster based on the corresponding first number and second number. Specifically, if the ratio of the second number to the first number is high, it means that in the feature cluster, most of the vector relationship network tuples are not perturbed by sequencing noise, so it can be judged that the sequencing noise perturbation result of the feature cluster is good. On the contrary, if the ratio is low, it means that the sequencing noise perturbation is more serious.
[0099] Finally, based on the sequencing noise perturbation results of each target data distribution feature cluster, the system comprehensively judges the sequencing noise perturbation results of the first initial genome sequencing data set and the second initial genome sequencing data set. This process is similar to "summary scoring". The system comprehensively considers the situation of each feature cluster and gives an overall sequencing noise perturbation evaluation result.
[0100] Through this method, the artificial intelligence analysis system can comprehensively and accurately evaluate the sequencing noise disturbance of the two initial genome sequencing data sets. This not only helps researchers understand the quality and reliability of the data, but also provides an important reference for subsequent data cleaning, experimental design, and data analysis. At the same time, this evaluation method based on target data distribution feature clusters and vector relationship network tuples is also highly versatile and flexible, and can be widely used in noise detection and quality control scenarios for various genome sequencing data. In other words, through this series of refined operations and analyses, not only the accuracy and sensitivity of sequencing noise disturbance detection are improved, but also a new solution is provided for the quality control of genome sequencing data.
[0101] In some exemplary embodiments, for each of the target data distribution feature clusters, determining the sequencing noise perturbation results of the first target data distribution feature and the second target data distribution feature in the target data distribution feature cluster based on the first number and the second number corresponding to the target data distribution feature cluster includes: determining a first ratio of the second number corresponding to the target data distribution feature cluster to the corresponding first number; if the first ratio corresponding to the target data distribution feature cluster is less than a first threshold value, determining the noise perturbation analysis weight of the target data distribution feature cluster based on the first ratio and the second number corresponding to the target data distribution feature cluster, and determining the sequencing noise perturbation results of the first target data distribution feature and the second target data distribution feature in the target data distribution feature cluster based on the noise perturbation analysis weight; if the first ratio corresponding to the target data distribution feature cluster is not less than the first threshold value, determining the sequencing noise perturbation results of the first target data distribution feature and the second target data distribution feature in the target data distribution feature cluster as the absence of sequencing noise perturbation.
[0102] Based on this embodiment, the artificial intelligence analysis system uses a specific method to determine the sequencing noise perturbation results of the first target data distribution feature and the second target data distribution feature in each target data distribution feature cluster. This process combines statistical data and preset threshold values to ensure the accuracy and reliability of the results.
[0103] First, the system determines the ratio of the second number corresponding to each target data distribution feature cluster to the corresponding first number. This ratio is called the first proportion. This ratio reflects the proportion of vector relationship network tuples in the feature cluster that are not disturbed by sequencing noise, and is an important indicator for evaluating the disturbance of sequencing noise.
[0104] Next, the system determines whether the first proportion is less than a preset first threshold value. The threshold value is set based on experience or actual needs and is a critical value used to distinguish whether sequencing noise disturbance exists.
[0105] If the first proportion is less than the first threshold value, it means that there are many vector relationship network tuples in the target data distribution feature cluster that are disturbed by sequencing noise, and it cannot be simply assumed that there is no sequencing noise disturbance. At this time, the system determines a noise disturbance analysis weight based on the first proportion and the second number. This weight reflects the degree to which the feature cluster is disturbed by sequencing noise. The larger the weight, the more serious the disturbance. Then, the system uses this weight to determine the sequencing noise disturbance results of the first target data distribution feature and the second target data distribution feature in the feature cluster. This result will comprehensively consider the weight and other relevant factors to give a quantitative evaluation index.
[0106] If the first proportion is not less than the first threshold value, it means that most of the vector relationship network tuples in the target data distribution feature cluster are not disturbed by sequencing noise. Therefore, the system can determine that the sequencing noise disturbance results of the first target data distribution feature and the second target data distribution feature in the feature cluster are that there is no sequencing noise disturbance.
[0107] Through this method, the artificial intelligence analysis system can give different sequencing noise disturbance assessment results for different situations, which is more in line with the actual situation. At the same time, this method also has certain flexibility and scalability, and can be adjusted and optimized according to different needs. It can be seen that this sequencing noise disturbance assessment method based on the first proportion and noise disturbance analysis weight improves the accuracy and reliability of the assessment, helps scientific researchers better understand the quality and reliability of genome sequencing data, and provides strong support for subsequent data analysis and research.
[0108] In some possible embodiments, the sequencing noise perturbation results of the first initial genome sequencing data set and the second initial genome sequencing data set are determined based on the sequencing noise perturbation results of each of the target data distribution feature clusters, including: if the sequencing noise perturbation result of at least one of the target data distribution feature clusters is that there is no sequencing noise perturbation, determining that the sequencing noise perturbation results of the first initial genome sequencing data set and the second initial genome sequencing data set are that there is no sequencing noise perturbation; if the sequencing noise perturbation results of each of the target data distribution feature clusters are that there is sequencing noise perturbation, determining that the sequencing noise perturbation results of the first initial genome sequencing data set and the second initial genome sequencing data set are that there is sequencing noise perturbation.
[0109] In this embodiment, the artificial intelligence analysis system comprehensively judges the sequencing noise disturbance of the first initial genome sequencing data set and the second initial genome sequencing data set based on the sequencing noise disturbance results of each target data distribution feature cluster. This process is based on a comprehensive and detailed evaluation method to ensure the accuracy and reliability of the final conclusion.
[0110] First, the system checks the sequencing noise perturbation results of all target data distribution feature clusters. These feature clusters were previously obtained through a series of complex analyses, and each feature cluster represents a specific data distribution pattern in the data set. Therefore, the noise perturbation analysis of these feature clusters can directly reflect the noise situation of the entire data set.
[0111] If the system finds that the sequencing noise perturbation result of at least one target data distribution feature cluster is that there is no sequencing noise perturbation, then it will determine that the sequencing noise perturbation results of the first initial genome sequencing data set and the second initial genome sequencing data set are that there is no sequencing noise perturbation. This is because as long as there is a feature cluster that is not affected by noise, it means that at least part of the data in the entire data set is reliable and not disturbed by noise.
[0112] On the other hand, if the sequencing noise perturbation results of all target data distribution feature clusters show the presence of sequencing noise perturbation, then the system determines that the sequencing noise perturbation results of the first initial genome sequencing data set and the second initial genome sequencing data set are the presence of sequencing noise perturbation. This means that the entire data set is widely affected by noise, and no part is completely reliable.
[0113] Through this comprehensive evaluation method, the AI analysis system is able to provide a clear conclusion about the sequencing noise perturbation of the entire data set. This conclusion not only takes into account the various parts of the data set, but is also based on a detailed feature cluster analysis, so it has a high degree of accuracy and credibility.
[0114] In some alternative embodiments, the sequencing noise perturbation results of the first local description vector relationship network and the second local description vector relationship network in the corresponding vector relationship network binary group determined based on each of the genome sequencing integrated vector sets are achieved through a long short-term memory network, and the long short-term memory network is debugged by the following steps: determining multiple genome expression vector relationship network sample binary groups, each of the genome expression vector relationship network sample binary groups includes a first genome expression description vector relationship network sample of a first initial genome sequencing data set sample and a second genome expression description vector relationship network sample of a second initial genome sequencing data set sample, the first initial genome sequencing data set sample and the second initial genome sequencing data set sample correspond to a target plant object, and the first genome expression description vector relationship network sample and the second genome expression description vector relationship network sample are respectively any one of a genome expression feature set, a transcript structure feature set or an epigenetic mark feature set; converting the first genome expression description vector relationship network sample in each of the genome expression vector relationship network sample binary groups into a first genome expression description vector relationship network sample; The first genome expression description vector relationship network sample and the second genome expression description vector relationship network sample are integrated to obtain a genome sequencing integrated vector set sample, each of the genome sequencing integrated vector set samples is input into the initial recurrent neural network to obtain a discriminant viewpoint corresponding to each of the genome sequencing integrated vector set samples, and the sequencing noise perturbation prediction results of the first genome expression description vector relationship network sample and the second genome expression description vector relationship network sample in the genome expression vector relationship network sample binary corresponding to each of the genome sequencing integrated vector set samples are determined based on the discriminant viewpoint; based on the actual sequencing noise perturbation results and the sequencing noise perturbation prediction results of the first genome expression description vector relationship network sample and the second genome expression description vector relationship network sample in each of the genome expression vector relationship network sample binary, a debugging error function is determined, and the initial recurrent neural network is debugged based on the debugging error function and each of the genome expression vector relationship network sample binary until the debugging is completed when the debugging error function meets the debugging termination requirement, and the recurrent neural network obtained after the debugging is determined as the long short-term memory network.
[0115] Based on this embodiment, the artificial intelligence analysis system uses a long short-term memory network (LSTM) to determine the sequencing noise perturbation results of the corresponding vector relationship network tuple (i.e., the first local description vector relationship network and the second local description vector relationship network) in the genome sequencing integrated vector set. The long short-term memory network is a special recurrent neural network (RNN) that can effectively process sequence data and remember long-term dependencies, so it has significant advantages in processing genome sequencing data.
[0116] In order to train this long short-term memory network, the system first determines multiple genome expression vector relationship network sample tuples. These sample tuples are extracted from the genome sequencing data of the target plant object, and each sample tuple includes a first genome expression description vector relationship network sample of the first initial genome sequencing data set sample and a second genome expression description vector relationship network sample of the second initial genome sequencing data set sample. These samples can be any of the genome expression feature sets, transcript structure feature sets, or epigenetic mark feature sets, representing different levels and characteristics of the genome.
[0117] Next, the system integrates the first and second genome expression description vector relationship network samples in these sample binary groups to obtain genome sequencing integrated vector set samples. These integrated vector set samples are then input into an initial recurrent neural network to obtain the discriminant opinions corresponding to each sample. These discriminant opinions are the network's preliminary judgment on whether each sample has sequencing noise disturbance.
[0118] Based on these discriminant viewpoints, the system further determines the sequencing noise perturbation prediction results of the first and second genome expression description vector relationship network samples in the genome expression vector relationship network sample tuple corresponding to each genome sequencing integrated vector set sample. These prediction results are the network's specific predictions for sequencing noise perturbations, which will be compared with the actual results.
[0119] To train and optimize the network, the system determines a debugging error function based on the actual sequencing noise perturbation results and prediction results of the first and second genome expression description vector relationship network samples in each sample binary. This function measures the difference between the network prediction and the actual results and is a key indicator for optimizing network performance.
[0120] By continuously using these sample binary pairs and the debugging error function to debug and optimize the initial recurrent neural network until the debugging error function meets the preset debugging termination requirements (such as the error rate is lower than a certain threshold or the maximum number of iterations is reached), the system will eventually determine the recurrent neural network that has completed debugging as the required long short-term memory network.
[0121] This not only improves the accuracy and efficiency of the analysis, but also enables the system to process complex genome sequencing data and effectively identify and predict sequencing noise disturbances, which is of great significance for subsequent data cleaning, experimental design, and data analysis.
[0122] In some exemplary embodiments, when the sequencing noise disturbance result indicates that there is sequencing noise disturbance, the method further includes: performing denoising processing on the first initial genome sequencing data set and the second initial genome sequencing data set based on the sequencing noise disturbance result.
[0123] In this embodiment, the artificial intelligence analysis system demonstrates its powerful intelligent analysis capabilities when processing genome sequencing data. When the system detects that the sequencing noise disturbance result is the presence of sequencing noise disturbance, the system takes a series of precise measures to perform noise reduction processing on the first initial genome sequencing data set and the second initial genome sequencing data set.
[0124] First, the AI analysis system carefully analyzes the source and nature of sequencing noise. This noise may come from errors in the sequencing instrument itself, contamination during sample processing, or interference when reading data. The system uses advanced algorithms, such as deep learning models, to identify and distinguish this noise from real genome sequencing signals.
[0125] Next, the system uses complex statistical methods and machine learning techniques to clean the data. This may include using filters to remove high-frequency noise, or predicting and correcting sequencing errors through modeling. During the denoising process, the artificial intelligence analysis system pays special attention to protecting the integrity and accuracy of the genomic data, ensuring that the denoised data can truly reflect the genomic information of the sample.
[0126] For example, if the system detects an abnormal gene sequence reading, it will compare it with the known genome database to confirm whether the reading is due to sequencing noise. If it is confirmed to be noise, the system will remove it from the data set; if it is not noise, the system will retain the reading to ensure the integrity of the data.
[0127] After denoising the first and second initial genome sequencing datasets, the artificial intelligence analysis system generates a more accurate and reliable genome sequencing dataset. This optimized dataset can be used for subsequent genomics research, such as gene variation analysis, disease risk assessment, etc.
[0128] Through this noise removal process, the artificial intelligence analysis system not only improves the accuracy of genome sequencing data, but also provides researchers with a higher quality data foundation, further promoting the research and application of genomics. This precise data processing method is of great significance for improving the accuracy of medical diagnosis, the efficiency of drug development, and the realization of personalized medicine.
[0129] In some independent embodiments, the denoising of the first initial genome sequencing dataset and the second initial genome sequencing dataset includes: combining the sequencing noise disturbance result, the first initial genome sequencing dataset and the second initial genome sequencing dataset to obtain a sequencing technology noise detection vector and a sequencing biological noise detection vector of the target plant object, wherein the sequencing technology noise detection vector is used to characterize the sequencing technology noise factor in the target plant object, and the sequencing biological noise detection vector is used to characterize the sequencing biological noise factor in the target plant object; for the sequencing technology noise detection vector, based on a noise detection vector in the sequencing biological noise detection vector that is related to the sequencing technology noise detection vector, obtaining a first linkage noise positioning vector, The first linkage noise localization vector is used to characterize a sequencing technology noise detection vector that integrates a sequencing biological noise detection vector; for the sequencing biological noise detection vector, based on a noise detection vector in the sequencing technology noise detection vector that is related to the sequencing biological noise detection vector, a second linkage noise localization vector is obtained, and the second linkage noise localization vector is used to characterize a sequencing biological noise detection vector that integrates a sequencing technology noise detection vector; the first linkage noise localization vector is merged with the second linkage noise localization vector to obtain a global noise localization vector; based on the global noise localization vector, a noise removal viewpoint for the target plant object is determined; and the first initial genome sequencing data set and the second initial genome sequencing data set are subjected to noise removal processing according to the noise removal viewpoint.
[0130] In this embodiment, the process of the artificial intelligence analysis system performing noise removal on the first initial genome sequencing data set and the second initial genome sequencing data set is a highly sophisticated and technically demanding operation. This process involves complex vector operations and noise identification technology to ensure the accuracy and effectiveness of noise removal.
[0131] First, the system needs to combine the sequencing noise perturbation results, the first initial genome sequencing data set, and the second initial genome sequencing data set to obtain the sequencing technology noise detection vector and sequencing biological noise detection vector of the target plant object. These two vectors are the basis of the noise removal process and are used to characterize the sequencing technology noise factors and sequencing biological noise factors in the target plant object, respectively. In simple terms, sequencing technology noise may come from errors or improper operation of the sequencing instrument, while sequencing biological noise may be related to biological processes such as sample collection and preservation.
[0132] Next, the system performs linkage noise positioning. For the sequencing technology noise detection vector, the system obtains the first linkage noise positioning vector based on the relevant part of the sequencing biological noise detection vector. This vector is actually a comprehensive reflection of the sequencing technology noise taking into account the sequencing biological noise factor. Similarly, for the sequencing biological noise detection vector, the system will also obtain the second linkage noise positioning vector based on the relevant part of the sequencing technology noise detection vector.
[0133] After obtaining these two linked noise localization vectors, the system merges them to obtain a global noise localization vector. This global noise localization vector comprehensively considers the noise factors of both sequencing technology and biology, providing precise guidance for subsequent noise removal processing.
[0134] Based on this global noise localization vector, the system determines the noise removal viewpoint for the target plant object. This noise removal viewpoint is actually a comprehensive noise removal strategy that takes into account the source, nature and impact of various noises to ensure the pertinence and effectiveness of noise removal.
[0135] Finally, the system performs denoising on the first initial genome sequencing data set and the second initial genome sequencing data set based on the denoising viewpoint. This process may include steps such as data cleaning, correction, and reconstruction to ensure that the denoised data set can more accurately reflect the genome information of the target plant object.
[0136] Through the above-mentioned noise removal process, the artificial intelligence analysis system not only improves the accuracy and reliability of genome sequencing data, but also provides a higher quality data foundation for subsequent genomic research and applications. The implementation of this noise removal technology is of great significance in promoting the research progress in the field of genomics, improving the accuracy of medical diagnosis, and promoting the development of personalized medicine.
[0137] In some other possible embodiments, the method further includes: updating the genome sequencing system of the target plant object.
[0138] In some other possible embodiments, the artificial intelligence analysis system not only focuses on denoising the genome sequencing data, but also further updates the genome sequencing system of the target plant object. This step is a key step to ensure that the sequencing system continues to maintain optimal performance and accuracy.
[0139] When the system completes the denoising process for the first initial genome sequencing data set and the second initial genome sequencing data set, it will accumulate a lot of processing experience and data insights. These experiences and insights are crucial for optimizing the genome sequencing system. Therefore, the artificial intelligence analysis system uses this information to update and improve the sequencing system.
[0140] Specifically, the system first analyzes the various noise types and sources identified during the noise removal process. These noises may include instrument noise, environmental noise, reagent noise, etc. By deeply understanding the characteristics of these noises, the system can identify possible problems and deficiencies in the sequencing system.
[0141] Next, the AI analysis system proposes specific optimization suggestions and improvement measures for these problems and deficiencies. For example, if instrument noise is found to be the main source of noise, the system may recommend calibration or upgrading the sequencing instrument to reduce instrument errors. If the impact of environmental noise is large, the system may propose suggestions for improving the sequencing environment, such as reducing external interference and optimizing temperature control.
[0142] In addition, the system will optimize the algorithms and parameters of the sequencing system based on the data insights obtained during the noise removal process. For example, by adjusting parameters such as sequencing depth and read length, the coverage and accuracy of sequencing can be improved. At the same time, the system can also use advanced machine learning algorithms to improve the analysis methods and processing procedures of sequencing data, thereby further improving the accuracy and reliability of the data.
[0143] Finally, the AI analysis system integrates these optimization suggestions and improvement measures into the genome sequencing system of the target plant object. This update process may involve multiple aspects such as software upgrades, hardware adjustments, or algorithm optimization. Through this series of update operations, the sequencing system will be able to better adapt to various complex sequencing environments and requirements, and provide more accurate and reliable genome sequencing data.
[0144] In summary, by updating the genome sequencing system of the target plant object, the artificial intelligence analysis system can not only improve the accuracy and reliability of the sequencing data, but also improve the overall performance and adaptability of the sequencing system. This will provide more powerful data support and technical guarantee for subsequent genomic research, medical diagnosis, and drug development.
[0145] It is worth mentioning that the genome sequencing system of the target plant object is updated, including: using an artificial intelligence analysis system to deeply analyze the first initial genome sequencing data set and the second initial genome sequencing data set that have been denoised, and identifying systematic errors and random errors in the sequencing process; based on the error analysis results, adjusting the optical detection system of the sequencing system, optimizing the parameters of laser excitation and fluorescence signal capture, so as to reduce the influence of light signal attenuation and background noise; at the same time, improving the fluid control module of the sequencing system to ensure the precise delivery and mixing of reaction reagents and reduce the noise introduced by reagent concentration fluctuations; further, updating the base recognition algorithm of the sequencing system, introducing a deep learning model, improving the accuracy of base reading, and updating the algorithm model in real time through the cloud platform to adapt to the ever-changing sequencing needs; finally, comprehensively upgrading the hardware and software of the sequencing system to ensure the stability and efficiency of the system, thereby realizing comprehensive optimization and updating of the genome sequencing system of the target plant object.
[0146] Specifically, the AI analysis system plays a vital role in updating the genome sequencing system of the target plant object. This update process is not only complex but also highly sophisticated, requiring the system to have the ability of in-depth analysis and precise adjustment.
[0147] First, the artificial intelligence analysis system deeply analyzes the first initial genome sequencing data set and the second initial genome sequencing data set that have been denoised. The purpose of this step is to identify systematic errors and random errors that may exist in the sequencing process. Systematic errors are usually caused by inherent biases or improper operation of the sequencing system, while random errors may come from various unpredictable external factors. By deeply analyzing these data sets, the system can more accurately locate the source of errors and provide strong support for subsequent optimization work.
[0148] Next, based on the results of the error analysis, the AI analysis system proceeded to adjust the optical detection system of the sequencing system. This includes optimizing the parameters of laser excitation and fluorescence signal capture. Laser excitation is a key step in the sequencing process, which is responsible for stimulating fluorescent-labeled nucleotides to emit fluorescent signals. By adjusting parameters such as laser intensity, wavelength, and excitation time, the system can more effectively stimulate fluorescent signals while reducing the effects of light signal attenuation and background noise. This helps to improve the clarity and accuracy of sequencing signals.
[0149] At the same time, the system will also improve the fluid control module of the sequencing system. The fluid control module is responsible for the precise control and delivery of reagents in the sequencing reaction, such as nucleotides, enzymes, and buffers. By optimizing fluid control parameters such as flow rate, concentration, and mixing ratio, the system can ensure the precise delivery and mixing of reaction reagents. This can not only reduce the noise introduced by reagent concentration fluctuations, but also improve the stability and repeatability of sequencing reactions.
[0150] In order to further improve sequencing accuracy, the artificial intelligence analysis system will also update the base recognition algorithm of the sequencing system. Traditional base recognition algorithms may be limited by fixed patterns and parameters, and it is difficult to adapt to the ever-changing sequencing needs. Therefore, the system introduces a deep learning model to improve the base recognition process. The deep learning model has powerful feature extraction and classification capabilities, and can more accurately identify and interpret the base information in the sequencing signal. In addition, by updating the algorithm model in real time through the cloud platform, the system can continuously learn and adapt to new sequencing data and environmental changes, thereby maintaining the best recognition performance.
[0151] Finally, to ensure the overall performance and stability of the sequencing system, the artificial intelligence analysis system comprehensively upgrades the hardware and software of the sequencing system. Hardware upgrades may include replacing more advanced sequencing instruments, improving computer processing power and storage capacity, etc.; software upgrades may involve optimizing the operating system, updating data analysis software, and introducing new sequencing algorithms. These upgrade measures can ensure that the sequencing system performs well in the face of large-scale, high-complexity genome sequencing tasks, and provide researchers with high-quality and efficient sequencing services.
[0152] In summary, by comprehensively optimizing and updating the genome sequencing system of the target plant objects, the artificial intelligence analysis system can significantly improve the accuracy and reliability of the sequencing data.
[0153] Further, Figure 2 Schematic diagram of the structure of an artificial intelligence analysis system 200 provided in an embodiment of the present application. Figure 2 The artificial intelligence analysis system 200 shown includes a processor 210, which can call and run a computer program from a memory to implement the method in the embodiment of the present application.
[0154] Alternatively, if Figure 2 As shown, the artificial intelligence analysis system 200 may further include a memory 230. The processor 210 may call and run a computer program from the memory 230 to implement the method in the embodiment of the present application.
[0155] The memory 230 may be a separate device independent of the processor 210 , or may be integrated into the processor 210 .
[0156] Alternatively, if Figure 2 As shown, the artificial intelligence analysis system 200 may also include a transceiver 220, and the processor 210 may control the transceiver 220 to interact with other devices. Specifically, it may send information or data to other devices, or receive information or data sent by other devices.
[0157] Optionally, the artificial intelligence analysis system 200 can implement the corresponding processes corresponding to the storage engine or components in the storage engine (such as a processing module) or a device deployed with a storage engine in each method of the embodiments of the present application. For the sake of brevity, they are not repeated here.
[0158] It should be understood that the processor of the embodiment of the present application may be an integrated circuit chip with signal processing capabilities. In the implementation process, each step of the above method embodiment can be completed by the hardware integrated logic circuit or software instructions in the processor. The above processor can be a general processor, a digital signal processor (Digital Signal Processor, DSP), an application-specific integrated circuit (Application Specific Integrated Circuit, ASIC), a field programmable gate array (Field Programmable Gate Array, FPGA) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components. The methods, steps and logic block diagrams disclosed in the embodiments of the present application can be implemented or executed. The general processor can be a microprocessor or the processor can also be any conventional processor. The steps of the method disclosed in the embodiment of the present application can be directly embodied as a hardware decoding processor to perform, or the hardware and software modules in the decoding processor are combined and performed. The software module can be located in a random access memory, a flash memory, a read-only memory, a programmable read-only memory or an electrically erasable programmable memory, a register, and other mature storage media in the art. The storage medium is located in the memory, and the processor reads the information in the memory and completes the steps of the above method in combination with its hardware.
[0159] It can be understood that the memory in the embodiments of the present application can be a volatile memory or a non-volatile memory, or can include both volatile and non-volatile memories. Among them, the non-volatile memory can be a read-only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electrically erasable programmable read-only memory (EEPROM), or a flash memory. The volatile memory can be a random access memory (RAM), which is used as an external cache. By way of example and not limitation, many forms of RAM are available, such as static random access memory (SRAM), dynamic random access memory (DRAM), synchronous dynamic random access memory (SDRAM), double data rate synchronous dynamic random access memory (DDR SDRAM), enhanced synchronous dynamic random access memory (ESDRAM), synchronous link dynamic random access memory (SLDRAM), and direct RAM bus random access memory (DR RAM). It should be noted that the memory of the systems and methods described herein is intended to include, but is not limited to, these and any other suitable types of memory.
[0160] It should be understood that the above-mentioned memory is exemplary but not restrictive. For example, the memory in the embodiments of the present application may also be static random access memory (static RAM, SRAM), dynamic random access memory (dynamic RAM, DRAM), synchronous dynamic random access memory (synchronous DRAM, SDRAM), double data rate synchronous dynamic random access memory (double data rate SDRAM, DDR SDRAM), enhanced synchronous dynamic random access memory (enhanced SDRAM, ESDRAM), synchronous link dynamic random access memory (synch link DRAM, SLDRAM) and direct memory bus random access memory (Direct Rambus RAM, DRRAM), etc. That is to say, the memory in the embodiments of the present application is intended to include but not limited to these and any other suitable types of memory.
[0161] Based on the above, a computer-readable storage medium is provided, on which a computer program is stored, and the computer program implements the above method when running.
[0162] The above are only embodiments of the present application and are not intended to limit the present application. For those skilled in the art, the present application may have various modifications and variations.
Claims
1. A plant genome sequencing data analysis method based on artificial intelligence, characterized in that: Applied to an artificial intelligence analysis system, the method comprises: Determine a first genome expression description vector relationship network of a first initial genome sequencing data set and a second genome expression description vector relationship network of a second initial genome sequencing data set using a long short-term memory network, wherein the first initial genome sequencing data set and the second initial genome sequencing data set correspond to a target plant object, and the first genome expression description vector relationship network and the second genome expression description vector relationship network are any one of a genome expression feature set, a transcript structure feature set, or an epigenetic marker feature set; Determine at least one local description vector relationship network from the first genome expression description vector relationship network and the second genome expression description vector relationship network based on the AI sliding sampling kernel, and determine at least one vector relationship network binary based on the data distribution characteristics of each local description vector relationship network in the corresponding genome expression description vector relationship network, wherein the first local description vector relationship network and the second local description vector relationship network in each vector relationship network binary belong to different genome expression description vector relationship networks and have the same data distribution characteristics in the corresponding genome expression description vector relationship network; Integrate the first local description vector relationship network and the second local description vector relationship network in each of the vector relationship network binary groups to obtain a genome sequencing integrated vector set, and determine the sequencing noise perturbation results of the first local description vector relationship network and the second local description vector relationship network in the corresponding vector relationship network binary group based on each of the genome sequencing integrated vector sets; Based on the sequencing noise perturbation results of each of the vector relationship network binary groups, the sequencing noise perturbation results of the first initial genome sequencing data set and the second initial genome sequencing data set are determined, and the sequencing noise perturbation results are the presence of sequencing noise perturbation or the absence of sequencing noise perturbation.
2. The method according to claim 1, characterized in that: For the first local description vector relationship network and the second local description vector relationship network in each of the vector relationship network tuples, the first local description vector relationship network and the second local description vector relationship network are integrated to obtain a genome sequencing integrated vector set, including: Generate a genome sequencing integrated vector set based on the sequencing attention variables of each characteristic element of the first local description vector relationship network and the second local description vector relationship network, wherein each characteristic element of the genome sequencing integrated vector set includes at least one attention dimension, and the sequencing attention variable of each attention dimension is determined by at least one of the sequencing attention variables of the first local description vector relationship network corresponding to the characteristic element or the sequencing attention variables of the second local description vector relationship network corresponding to the characteristic element; Among them, the sequencing attention variable of each characteristic element of the genomic expression feature set is the genomic expression mapping parameter, the sequencing attention variable of each characteristic element of the transcript structure feature set is the transcript structure mapping parameter, and each characteristic element of the epigenetic mark feature set corresponds to multiple sequencing attention variables and each sequencing attention variable is an epigenetic mapping parameter of an epigenetic attention dimension.
3. The method according to claim 1, characterized in that The AI sliding sampling kernel is used to determine at least one local description vector relationship network from the first genome expression description vector relationship network and the second genome expression description vector relationship network, respectively, including: Determine at least one first target data distribution feature in the first genome expression description vector relationship network, determine the data distribution feature in the second genome expression description vector relationship network that is the same as each of the first target data distribution features as a second target data distribution feature, and each of the first target data distribution features is used to reflect the core sequencing embedding vector of the first genome expression description vector relationship network; Based on the AI sliding sampling kernel and the selected sampling strategy, at least one local description vector relationship network is determined from each of the first target data distribution characteristics and each of the second target data distribution characteristics.
4. The method according to claim 3, characterized in that The determining the sequencing noise perturbation results of the first initial genome sequencing data set and the second initial genome sequencing data set based on the sequencing noise perturbation results of each of the vector relationship network binary groups includes: Determine at least one target data distribution feature cluster, each of the target data distribution feature clusters including one of the first target data distribution features and a second target data distribution feature corresponding to the first target data distribution feature; Determine the first number of vector relationship network tuples corresponding to each of the target data distribution feature clusters, and the second number of vector relationship network tuples in which the sequencing noise disturbance result in the corresponding vector relationship network tuple is that there is no sequencing noise disturbance; For each of the target data distribution feature clusters, determining sequencing noise perturbation results of the first target data distribution feature and the second target data distribution feature in the target data distribution feature cluster based on the first number and the second number corresponding to the target data distribution feature cluster; Based on the sequencing noise perturbation results of each of the target data distribution feature clusters, the sequencing noise perturbation results of the first initial genome sequencing data set and the second initial genome sequencing data set are determined.
5. The method according to claim 4, characterized in that For each of the target data distribution feature clusters, determining the sequencing noise perturbation results of the first target data distribution feature and the second target data distribution feature in the target data distribution feature cluster based on the first number and the second number corresponding to the target data distribution feature cluster, comprises: Determine a first ratio of a second number corresponding to the target data distribution feature cluster to a first number corresponding to the first number; If the first proportion corresponding to the target data distribution feature cluster is less than the first threshold value, determine the noise disturbance analysis weight of the target data distribution feature cluster based on the first proportion corresponding to the target data distribution feature cluster and the second number, and determine the sequencing noise disturbance results of the first target data distribution feature and the second target data distribution feature in the target data distribution feature cluster based on the noise disturbance analysis weight; If the first proportion corresponding to the target data distribution feature cluster is not less than the first threshold value, it is determined that the sequencing noise disturbance results of the first target data distribution feature and the second target data distribution feature in the target data distribution feature cluster are that there is no sequencing noise disturbance.
6. The method according to claim 4, characterized in that The step of determining the sequencing noise perturbation results of the first initial genome sequencing data set and the second initial genome sequencing data set based on the sequencing noise perturbation results of each of the target data distribution feature clusters comprises: If the sequencing noise perturbation result of at least one of the target data distribution feature clusters is that there is no sequencing noise perturbation, determining that the sequencing noise perturbation results of the first initial genome sequencing data set and the second initial genome sequencing data set are that there is no sequencing noise perturbation; If the sequencing noise perturbation results of each of the target data distribution feature clusters are that sequencing noise perturbations exist, it is determined that the sequencing noise perturbation results of the first initial genome sequencing data set and the second initial genome sequencing data set are that sequencing noise perturbations exist.
7. The method according to claim 1, characterized in that The sequencing noise perturbation results of the first local description vector relationship network and the second local description vector relationship network in the corresponding vector relationship network tuple determined based on each genome sequencing integrated vector set are achieved through a long short-term memory network, and the long short-term memory network is debugged by the following steps: Determine a plurality of genome expression vector relationship network sample tuples, each of the genome expression vector relationship network sample tuples comprising a first genome expression description vector relationship network sample of a first initial genome sequencing data set sample and a second genome expression description vector relationship network sample of a second initial genome sequencing data set sample, the first initial genome sequencing data set sample and the second initial genome sequencing data set sample correspond to a target plant object, and the first genome expression description vector relationship network sample and the second genome expression description vector relationship network sample are respectively any one of a genome expression feature set, a transcript structure feature set or an epigenetic marker feature set; Integrate the first genome expression description vector relationship network sample and the second genome expression description vector relationship network sample in each genome expression vector relationship network sample binary to obtain a genome sequencing integrated vector set sample, input each genome sequencing integrated vector set sample into an initial recurrent neural network to obtain a discriminant viewpoint corresponding to each genome sequencing integrated vector set sample, and determine the sequencing noise perturbation prediction result of the first genome expression description vector relationship network sample and the second genome expression description vector relationship network sample in the genome expression vector relationship network sample binary corresponding to each genome sequencing integrated vector set sample based on the discriminant viewpoint; Based on the actual sequencing noise perturbation results and the sequencing noise perturbation prediction results of the first genome expression description vector relationship network sample and the second genome expression description vector relationship network sample in each genome expression vector relationship network sample binary group, a debugging error function is determined, and the initial recurrent neural network is debugged based on the debugging error function and each genome expression vector relationship network sample binary group until the debugging is completed when the debugging error function meets the debugging termination requirements, and the recurrent neural network obtained after the debugging is determined as the long short-term memory network.
8. The method according to claim 1, characterized in that When the sequencing noise disturbance result is that sequencing noise disturbance exists, the method further includes: Based on the sequencing noise disturbance result, the first initial genome sequencing data set and the second initial genome sequencing data set are subjected to denoising processing.
9. The method according to claim 8, characterized in that The method further comprises: The genome sequencing system of the target plant object is updated.
10. An artificial intelligence analysis system, characterized in that: The method comprises at least one processor and a memory; the memory stores computer-executable instructions; the at least one processor executes the computer-executable instructions stored in the memory, so that the at least one processor executes the method according to any one of claims 1 to 9.
Citation Information
Patent Citations
Gene expression prediction method based on LSTM loop neural network
CN109063416A
Gene mining method and system based on transcriptome and DNA methylation group
CN117577179A
Generalized computational framework and system for integrative prediction of biomarkers
US20180166170A1
Machine-learning model for generating confidence classifications for genomic coordinates
US20220415443A1
Predicting gene expression alterations caused by perturbations of transcription factors
WO2024025950A1
