Cell warehousing method and system and storage medium

Abstract

The invention relates to the technical field of cell data detection and analysis, in particular to a cell warehousing method and system and a storage medium. The method comprises the following steps: acquiring a cell original data set; performing data preprocessing on the cell original data set to generate a cell data set; performing multi-dimensional cell feature extraction on the cell data set to obtain cell multi-dimensional feature data; performing cell expression feature recognition on the cell multi-dimensional feature data to generate cell expression feature information; and performing cell type division on the cell expression characteristic information to obtain cell type data. Through a data processing technology, a feature mapping technology, a pattern recognition technology and a deep learning technology, multi-dimensional management of the cell data is realized, so that the process time of cell data storage is shortened, the stored cell data can be traced, and the cell storage efficiency is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of cell data detection and analysis, and in particular to a cell storage method, system and storage medium. Background Art

[0002] Flow cytometry quantitatively analyzes the physical and chemical properties of cells, so that the accuracy and completeness of cell data can be presented, thereby clarifying information such as cell type, characteristics and function; applying single-cell sequencing technology to the field of cell experiments can deeply study the gene expression of cells and obtain gene expression level data; with the increase of cell research data, researchers store cell data in cell databases for subsequent more in-depth cell research; the existing cell storage method is to register the cells to be stored through an artificial interactive interface, determine the storage rules that have a corresponding relationship with the target cell type from the pre-stored storage rules, and then store the cell data according to the storage rules. However, there are many types of cell data stored in the cell database; the existing technology fails to effectively manage cell information, resulting in a long cell data storage process; and it is difficult to trace the stored cell data, making the cell storage efficiency low. Summary of the invention

[0003] Based on this, it is necessary to provide a cell banking method, system and storage medium to solve at least one of the above technical problems.

[0004] To achieve the above object, a cell banking method is provided, the method comprising the following steps:

[0005] Step S1: obtaining an original cell data set; performing data preprocessing on the original cell data set to generate a cell data set; performing multi-dimensional cell feature extraction on the cell data set to obtain multi-dimensional cell feature data;

[0006] Step S2: performing cell expression feature recognition on the cell multi-dimensional feature data to generate cell expression feature information; performing cell type classification on the cell expression feature information to obtain cell type data; performing cell genome detection on the cell multi-dimensional feature data according to the cell type data to generate cell genome data;

[0007] Step S3: performing sequence structure analysis on the cell genome data to obtain gene sequence structure data; performing cell function detection on the gene sequence structure data to obtain cell function data; performing gene-specific expression pattern recognition on the cell function data to generate a gene-specific expression pattern;

[0008] Step S4: Carry out cell correlation mapping of cell type data, cell function data and gene-specific expression patterns to obtain cell correlation data; perform intelligent cell coding identification based on the cell correlation data to generate cell coding identification data; establish a cell database index architecture based on the cell coding identification data to obtain a cell database index architecture; adaptively and parallelly transmit the cell data set to the cell database index architecture to generate a cell storage report.

[0009] The present invention obtains a standardized cell data set by acquiring the original cell data set and performing data preprocessing, which provides accurate and reliable basic data for subsequent analysis; multi-dimensional cell feature extraction further enriches the data set, so that the multi-dimensional feature information of the cell data is displayed; cell expression feature recognition and cell type division provide data support for subsequent genome detection, ensuring the pertinence and accuracy of genome detection. The recognition of cell expression feature information and the division of cell type data make cell genome detection more accurate, ensuring that the generated cell genome data is more representative and scientifically valuable; sequence structure analysis and cell function detection provide important information for understanding the biological functions and mechanisms of cells, while the recognition of gene-specific expression patterns can reveal the role and regulatory mechanism of specific genes in cells. The sequence structure analysis of cell genome data provides a data basis for understanding the physical structure and function of genes, while the acquisition of cell function data reveals the specific role of cells in organisms; the recognition of gene-specific expression patterns further deepens the understanding of gene function and provides key information for subsequent biological research and applications. Cell correlation mapping integrates data on cell types, functions, and gene expression patterns, ensuring that the generated cell correlation data provides an important perspective for a comprehensive understanding of cell-to-cell interactions; the generation of cell intelligent coding identifiers provides an efficient tool for the management and retrieval of cell data, and the establishment of a cell database index architecture based on this provides a structured framework for the storage and rapid access of cell data; the cell data set is adaptively transmitted in parallel to the cell database index architecture, and the cell storage report finally generated ensures the systematic management of the data and the convenience of subsequent research. Therefore, the present invention realizes multi-dimensional management of cell data through data processing technology, feature mapping technology, pattern recognition technology, and deep learning technology, thereby shortening the process time of cell data storage, ensuring that the cell data stored can be traced, and thus improving the efficiency of cell storage.

[0010] Preferably, step S2 comprises the following steps:

[0011] Step S21: performing cell feature labeling on the multi-dimensional cell feature data to obtain cell feature labeling data; performing expression feature selection on the cell feature labeling data to generate expression feature selection data;

[0012] Step S22: extracting cell expression features from the cell multi-dimensional feature data based on the expression feature selection data to generate cell expression feature information; performing cell expression state detection on the cell expression feature information to obtain cell expression state data;

[0013] Step S23: performing expression activity identification on the cell expression state data to generate cell expression activity data; performing cell type classification according to the cell expression activity data to obtain cell type data;

[0014] Step S24: extracting cell gene types from the cell type data to generate cell gene type data; identifying gene enrichment conditions from the cell gene type data to obtain cell gene enrichment conditions;

[0015] Step S25: measuring the expression level of cell gene enrichment to generate gene enrichment expression level data; performing cell genome detection based on the gene enrichment expression level data to obtain cell genome data.

[0016] The present invention performs feature marking on multi-dimensional feature data of cells, providing an accurate reference basis for subsequent expression feature selection; expression feature selection further screens out key features to ensure the pertinence and efficiency of subsequent analysis; cell expression feature extraction based on expression feature selection data makes subsequent cell expression state detection more accurate and can accurately reflect the gene expression of cells in different states; expression activity recognition of cell expression state data enables identification of actively expressed gene regions in cells; cell type division based on these data can accurately classify cells, providing clear cell type data support for subsequent genome analysis; cell gene type extraction of cell type data provides detailed information for identifying specific gene types in cells; identification of gene enrichment can reveal the aggregation trend of genes in cells; expression quantity measurement of cell gene enrichment ensures that quantitative indicators are provided for evaluating the intensity and pattern of gene expression.

[0017] Preferably, step S3 comprises the following steps:

[0018] Step S31: performing sequence sequencing on the cell genome data to generate gene sequence sequencing data; performing sequencing data segmentation on the gene sequence sequencing data to obtain gene sequence segmentation information; performing sequence expression feature recognition on the gene sequence segmentation information to obtain gene sequence expression features;

[0019] Step S32: performing epigenetic modification site location on the gene sequence expression characteristics to generate epigenetic modification sites; performing epigenetic structural feature identification on the epigenetic modification sites to obtain epigenetic structural features; performing sequence structure analysis based on the epigenetic structural features to obtain gene sequence structure data;

[0020] Step S33: performing sequence structure characteristic state recognition on the gene sequence structure data to generate a sequence structure characteristic state; performing cell function domain mapping on the sequence structure characteristic state to obtain cell function domain mapping data;

[0021] Step S34: positioning the function regulation nodes on the cell function domain mapping data to obtain the cell function regulation nodes; identifying the cell function performance of the cell function regulation nodes to obtain the cell function data;

[0022] Step S35: Perform gene-specific expression pattern recognition on the cell function data to generate a gene-specific expression pattern.

[0023] The present invention performs sequence sequencing on cell genome data, and the generated gene sequence sequencing data provides raw data for gene sequence analysis; the segmentation of sequencing data further refines the gene sequence, which is helpful for more accurate analysis of gene structure; the recognition of sequence performance characteristics makes it possible to clarify the regulatory mechanism of gene expression; the epigenetic modification sites generated by epigenetic modification site positioning provide molecular markers for studying gene expression regulation; the recognition of epigenetic structural characteristics can reveal the molecular basis of gene expression regulation; the sequence structure analysis based on these characteristics provides data support at the structural level for understanding gene function and regulatory network; the sequence structure feature state obtained by sequence structure feature state recognition provides state information for functional analysis of gene sequence; cell function domain mapping links the structural features of gene sequence with cell function, and provides important clues for revealing how genes play a role in cells; the cell function regulatory nodes obtained by functional regulatory node positioning provide precise positions for identifying key regulatory elements in cells; the cell function data obtained by cell function performance recognition reveals that cell function regulatory nodes affect cell behavior and response; the gene-specific expression pattern obtained by gene-specific expression pattern recognition provides a detailed pattern for studying the expression changes of specific genes under different conditions, and can clarify the role of genes in cell function.

[0024] Preferably, step S35 includes the following steps:

[0025] Step S351: classify the cell function data into functional types to obtain cell function type data; perform cell DNA content parameter detection on the cell function type data to generate a cell DNA content value;

[0026] Step S352: performing DNA content function association on the cell function data according to the cell DNA content value to obtain DNA content function association data; performing cell cycle division according to the DNA content function association data to obtain cell cycle data;

[0027] Step S353: extracting cell time sequence parameters from the cell cycle data to obtain cell time sequence parameters; performing functional sequence expression recognition on the cell function data based on the cell time sequence parameters to generate a cell function sequence expression pattern;

[0028] Step S354: extracting single function expression features from the cell function sequential expression pattern to generate single function expression features; performing cycle interval singularity feature recognition on the single function expression features according to the cell cycle data to obtain cycle interval singularity features;

[0029] Step S355: Perform gene stage-specific detection based on the period interval uniqueness feature to obtain gene stage-specific information; perform gene-specific expression pattern recognition on the gene stage-specific information to generate a gene-specific expression pattern.

[0030] The present invention classifies cell function data into functional types, and can systematically understand and organize cell functions; cell DNA content parameter detection provides quantitative data for the relationship between cell function and DNA content; the generation of DNA content function correlation data can clarify the correlation between cell function and DNA content; by dividing the cell cycle, a time frame is provided for different stages of subsequent cell growth and division, so as to reveal the cell cycle regulation mechanism; the extraction of cell time sequence parameters provides a reference of the time dimension for cell function data, so as to track the changes of cell function over time; the functional sequence expression recognition based on these parameters reveals the expression pattern of cell function at different time points; by extracting single functional expression features, cycle information is provided for identifying the expression features of specific functions in the cell cycle; the expression patterns of these features in the cell cycle are further refined, and accurate data support is provided for studying the functional changes in specific stages of the cell cycle; the gene stage-specific information obtained by gene stage-specific detection reveals the specific expression of genes in different stages of the cell cycle; the gene-specific expression pattern recognition provides a data basis for studying the regulatory mechanism of gene expression and the molecular basis of the cell cycle.

[0031] Preferably, step S4 comprises the following steps:

[0032] Step S41: Perform cell correlation mapping on the cell type data, cell function data and gene-specific expression pattern to obtain cell correlation data;

[0033] Step S42: performing cell correlation analysis on the cell multi-dimensional feature data according to the cell correlation data to obtain cell correlation data; performing cell intelligent coding identification according to the cell correlation data to generate cell coding identification data;

[0034] Step S43: assign cell database index features to the cell coding identification data to obtain database index assignment information; establish a cell database index architecture based on the database index assignment information to obtain a cell database index architecture; adaptively and parallelly transmit the cell data set to the cell database index architecture to generate a cell storage report.

[0035] The present invention maps cell type data, cell function data and gene-specific expression patterns for cell correlation, provides a comprehensive data view for understanding the interactions and functional connections between cells, and can reveal the intrinsic connections between different cell types and functions; performs cell correlation analysis based on cell correlation data, further refines the interactions and dependencies between cells; generates cell intelligent coding identifiers, provides a unique identifier for each cell, which helps to accurately track and identify cells in large-scale data sets, and provides an efficient tool for the management and retrieval of cell data; assigns cell database index features to cell coding identifier data, which provides key information for rapid retrieval and positioning of cell data in the database; the cell database index architecture established based on this information optimizes the data storage structure and improves data retrieval efficiency; the cell data set is adaptively and parallelly transmitted to the cell database index architecture, and the generated cell storage report ensures the systematic management of the data and the convenience of subsequent research.

[0036] Preferably, step S41 includes the following steps:

[0037] Step S411: performing type statistics on the cell type data to obtain the number of cell type types; sorting the number of cell type types to generate cell type number sorting data;

[0038] Step S412: performing function performance state detection on the cell function data to obtain the cell function performance state; performing state type statistics on the cell function performance state to generate cell function state type data;

[0039] Step S413: matching the cell type quantity sorting data with the cell function state category data in terms of cell type function state quantity to generate a cell type function quantity matching value;

[0040] Step S414: performing specific expression genome determination on the gene-specific expression pattern to obtain the specific expression genome; performing specific gene type extraction on the cell type data according to the specific expression genome to generate specific gene type data;

[0041] Step S415: mapping the specific gene type data and the cell type quantity ranking data to the specific expression gene quantity to obtain a specific expression gene quantity mapping value;

[0042] Step S416: Perform cell-related merging of the cell type function quantity matching value and the specific expression gene quantity mapping value to obtain cell-related data.

[0043] The present invention performs type quantity statistics on cell type data, providing quantitative information of cell diversity for research; the cell type quantity ranking data generated by type quantity ranking can identify whether a specific cell type is more common or rare in a sample; the cell function performance state obtained by cell function performance state detection provides direct data for evaluating the activity and functional state of the cell; the cell function state type data generated by state type statistics ensures the identification of the distribution of different cell function states; the cell type quantity ranking data is matched with the cell function state type data, providing a quantitative index for analyzing the relationship between a specific cell type and a functional state, so as to reveal the abundance of a specific cell type in different functional states; the determination of the specific expression gene set provides accurate genome information for identifying genes expressed in a specific cell type, so as to clarify the molecular characteristics of a specific cell type; the acquisition of the specific expression gene quantity mapping value provides data support for quantifying the expression level of specific genes in a specific cell type, which is helpful to identify and quantify genes that play an important role in a specific cell type; the cell type function quantity matching value is merged with the specific expression gene quantity mapping value, providing a comprehensive data set for a comprehensive understanding of the relationship between cell types, functional states and gene expression, which is helpful to reveal the complex relationship between cell types and functional states and gene expression patterns.

[0044] Preferably, step S42 includes the following steps:

[0045] Step S421: performing type function similarity measurement according to the cell correlation data to obtain a type function similarity measurement value; performing cell type function clustering on the cell multi-dimensional feature data based on the type function similarity measurement value to generate cell type function clustering data;

[0046] Step S422: performing specific gene quantity distribution cycle identification according to the cell correlation data to obtain expression gene distribution cycle data; performing specific gene quantity cycle association on the cell multi-dimensional feature data based on the expression gene distribution cycle data to generate specific gene cycle association data;

[0047] Step S423: integrating the cell type function clustering data and the specific gene cycle association data to obtain cell association data; generating cell coding rules based on the cell association data to obtain cell coding rule information;

[0048] Step S424: performing cell type encoding on the cell type data according to the cell encoding rule information to generate cell type encoding data; performing cell function encoding on the cell function data based on the cell encoding rule information to generate cell function encoding data; performing specific expression pattern encoding on the gene specific expression pattern according to the cell encoding rule information to generate specific pattern encoding data;

[0049] Step S425: The cell type coding data, the cell function coding data and the specific pattern coding data are fused into a cell intelligent coding identification to generate cell coding identification data.

[0050] The present invention provides an accurate metric for quantifying the similarity between different cell types and functions by acquiring type function similarity metrics; cell type function clustering based on these metrics can identify cell populations with similar functional characteristics, which is of great significance for understanding cell diversity and functional heterogeneity; the dynamic changes of gene expression in the cell cycle are revealed by identifying the expression gene distribution cycle data; the specific gene quantity cycle association based on these data provides important information for studying the relationship between gene expression and cell cycle, which helps to reveal the molecular mechanism of cell cycle regulation; the integration of cell type function clustering data and specific gene cycle association data provides a comprehensive perspective for a comprehensive understanding of the relationship between cell type, function and gene expression; the generation of cell coding rules based on these data provides a rule basis for the standardized coding of cell data, which helps to unify and standardize the representation of cell data; the generation of cell type coding, cell function coding and specific expression pattern coding provides a standardized coding system for the classification, retrieval and management of cell data; the cell type coding data, cell function coding data and specific pattern coding data are fused, and the generated cell coding identification data provides a comprehensive and multi-dimensional identifier for each cell, and this fused coding identification data enhances the traceability and uniqueness of the cell data.

[0051] Preferably, step S43 includes the following steps:

[0052] Step S431: performing cell database index mapping on the cell multi-dimensional feature data to generate database index mapping features; performing cell database index type matching on the database index mapping features to obtain index type matching data;

[0053] Step S432: performing index structure type identification on the index type matching data according to the cell correlation data to obtain index structure type data; performing index feature enhancement on the index structure type mapping data to generate index feature enhancement data;

[0054] Step S433: assigning index features to the index feature enhancement data based on the cell coding identification data to obtain database index assignment information; establishing a cell database index architecture according to the database index assignment information to obtain a cell database index architecture;

[0055] Step S434: performing correlation sharding processing on the cell data set based on the cell correlation data to obtain a cell sharding data set; dividing the cell sharding data set into transmission task nodes to generate transmission task node information; and transmitting the cell sharding data set in parallel to the cell database index architecture based on the transmission task node information to input a cell storage report.

[0056] The present invention uses cell multi-dimensional feature data to perform database index mapping and obtains index type matching data, thereby ensuring the compatibility and consistency between cell data and database index structure, which helps to improve the accuracy and efficiency of data retrieval; the index structure type data obtained by index structure type identification provides guidance for the optimization of database index structure; the index feature enhancement data generated by index feature enhancement enhances the discrimination and retrieval efficiency of the index, enables the database to respond to query requests more quickly, and improves the performance of data management; the index feature assignment based on cell coding identification data provides an accurate index position for each cell data item; this helps to quickly locate and retrieve cell data, and the cell database index architecture thus established provides a basis for systematic storage and efficient retrieval of cell data; the cell data set correlation sharding processing under the guidance of cell correlation data optimizes the data transmission and storage process; the transmission task node information generated by the transmission task node division makes data transmission more efficient and orderly; the parallel transmission based on the transmission task node information improves the speed and reliability of data storage, and ensures the accuracy and timeliness of cell storage reports.

[0057] In this specification, a cell storage system is provided for executing the above-mentioned cell storage method, and the cell storage system comprises:

[0058] The cell data acquisition module is used to obtain the original cell data set; perform data preprocessing on the original cell data set to generate a cell data set; perform multi-dimensional cell feature extraction on the cell data set to obtain multi-dimensional cell feature data;

[0059] The cell genome detection module is used to identify cell expression characteristics of multi-dimensional cell feature data to generate cell expression feature information; classify cell expression feature information into cell types to obtain cell type data; perform cell genome detection on multi-dimensional cell feature data according to cell type data to generate cell genome data;

[0060] The gene-specific expression pattern recognition module is used to perform sequence structure analysis on cell genome data to obtain gene sequence structure data; perform cell function detection on gene sequence structure data to obtain cell function data; perform gene-specific expression pattern recognition on cell function data to generate gene-specific expression patterns;

[0061] The cell data storage module is used to perform cell correlation mapping on cell type data, cell function data and gene-specific expression patterns to obtain cell correlation data; perform intelligent cell coding identification based on the cell correlation data to generate cell coding identification data; establish a cell database index architecture based on the cell coding identification data to obtain a cell database index architecture; adaptively and parallelly transmit the cell data set to the cell database index architecture to generate a cell storage report.

[0062] The present invention obtains the original data set of cells and performs data preprocessing through the cell data acquisition module, thereby obtaining a standardized cell data set, which provides accurate and reliable basic data for subsequent analysis; multidimensional cell feature extraction further enriches the data set, so that the multidimensional feature information of the cell data is displayed; cell expression feature recognition and cell type division provide data support for subsequent genome detection, ensuring the pertinence and accuracy of genome detection. Through the cell genome detection module, the recognition of cell expression feature information and the division of cell type data make the cell genome detection more accurate, ensuring that the generated cell genome data is more representative and scientifically valuable; sequence structure analysis and cell function detection provide important information for understanding the biological functions and mechanisms of cells, and the recognition of gene-specific expression patterns can reveal the role and regulatory mechanism of specific genes in cells. Through the gene-specific expression pattern recognition module, the sequence structure analysis of cell genome data provides a data basis for understanding the physical structure and function of genes, and the acquisition of cell function data reveals the specific role of cells in organisms; the recognition of gene-specific expression patterns further deepens the understanding of gene functions and provides key information for subsequent biological research and application. Through the cell data storage module, the cell correlation mapping integrates the data of cell type, function and gene expression pattern, ensuring that the generated cell correlation data provides an important perspective for a comprehensive understanding of the interaction between cells; the generation of cell intelligent coding identification provides an efficient tool for the management and retrieval of cell data, and the establishment of the cell database index architecture based on this provides a structured framework for the storage and rapid access of cell data; the cell data set is adaptively transmitted in parallel to the cell database index architecture, and the cell storage report finally generated ensures the convenience of systematic management of data and subsequent research. Therefore, the present invention realizes multi-dimensional management of cell data through data processing technology, feature mapping technology, pattern recognition technology and deep learning technology, thereby shortening the process time of cell data storage, ensuring that the cell data stored can be traced, and then improving the efficiency of cell storage.

[0063] A computer-readable storage medium stores a computer program, wherein the computer program is used to execute the cell banking method. BRIEF DESCRIPTION OF THE DRAWINGS

[0064] Figure 1 A schematic diagram of the steps of a cell banking method;

[0065] Figure 2 for Figure 1 Detailed implementation steps of step S3 in FIG.

[0066] Figure 3 for Figure 2 Detailed implementation steps of step S35;

[0067] The realization of the purpose, functional features and advantages of the present invention will be further explained in conjunction with embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0068] The technical method of the present invention is described clearly and completely below in conjunction with the accompanying drawings. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by technicians in this field without creative work are within the scope of protection of the present invention.

[0069] In addition, the accompanying drawings are only schematic illustrations of the present invention and are not necessarily drawn to scale. The same reference numerals in the figures represent the same or similar parts, and their repeated description will be omitted. Some of the block diagrams shown in the accompanying drawings are functional entities and do not necessarily correspond to physically or logically independent entities. The functional entities can be implemented in software form, or implemented in one or more hardware modules or integrated circuits, or implemented in different networks and / or processor methods and / or microcontroller methods.

[0070] It should be understood that, although the terms "first", "second", etc. may be used herein to describe various units, these units should not be limited by these terms. These terms are used only to distinguish one unit from another unit. For example, without departing from the scope of the exemplary embodiments, the first unit may be referred to as the second unit, and similarly the second unit may be referred to as the first unit. The term "and / or" used herein includes any and all combinations of one or more of the listed associated items.

[0071] To achieve this, please refer to Figures 1 to 3 , a cell banking method, the method comprising the following steps:

[0072] Step S1: obtaining an original cell data set; performing data preprocessing on the original cell data set to generate a cell data set; performing multi-dimensional cell feature extraction on the cell data set to obtain multi-dimensional cell feature data;

[0073] Step S2: performing cell expression feature recognition on the cell multi-dimensional feature data to generate cell expression feature information; performing cell type classification on the cell expression feature information to obtain cell type data; performing cell genome detection on the cell multi-dimensional feature data according to the cell type data to generate cell genome data;

[0074] Step S3: performing sequence structure analysis on the cell genome data to obtain gene sequence structure data; performing cell function detection on the gene sequence structure data to obtain cell function data; performing gene-specific expression pattern recognition on the cell function data to generate a gene-specific expression pattern;

[0075] Step S4: Carry out cell correlation mapping of cell type data, cell function data and gene-specific expression patterns to obtain cell correlation data; perform intelligent cell coding identification based on the cell correlation data to generate cell coding identification data; establish a cell database index architecture based on the cell coding identification data to obtain a cell database index architecture; adaptively and parallelly transmit the cell data set to the cell database index architecture to generate a cell storage report.

[0076] The present invention obtains a standardized cell data set by acquiring the original cell data set and performing data preprocessing, which provides accurate and reliable basic data for subsequent analysis; multi-dimensional cell feature extraction further enriches the data set, so that the multi-dimensional feature information of the cell data is displayed; cell expression feature recognition and cell type division provide data support for subsequent genome detection, ensuring the pertinence and accuracy of genome detection. The recognition of cell expression feature information and the division of cell type data make cell genome detection more accurate, ensuring that the generated cell genome data is more representative and scientifically valuable; sequence structure analysis and cell function detection provide important information for understanding the biological functions and mechanisms of cells, while the recognition of gene-specific expression patterns can reveal the role and regulatory mechanism of specific genes in cells. The sequence structure analysis of cell genome data provides a data basis for understanding the physical structure and function of genes, while the acquisition of cell function data reveals the specific role of cells in organisms; the recognition of gene-specific expression patterns further deepens the understanding of gene function and provides key information for subsequent biological research and applications. Cell correlation mapping integrates data on cell types, functions, and gene expression patterns, ensuring that the generated cell correlation data provides an important perspective for a comprehensive understanding of cell-to-cell interactions; the generation of cell intelligent coding identifiers provides an efficient tool for the management and retrieval of cell data, and the establishment of a cell database index architecture based on this provides a structured framework for the storage and rapid access of cell data; the cell data set is adaptively transmitted in parallel to the cell database index architecture, and the cell storage report finally generated ensures the systematic management of the data and the convenience of subsequent research. Therefore, the present invention realizes multi-dimensional management of cell data through data processing technology, feature mapping technology, pattern recognition technology, and deep learning technology, thereby shortening the process time of cell data storage, ensuring that the cell data stored can be traced, and thus improving the efficiency of cell storage.

[0077] In the embodiment of the present invention, reference Figure 1 FIG. 1 is a schematic diagram of a process flow of a cell storage method of the present invention. In this example, the cell storage method includes the following steps:

[0078] Step S1: obtaining an original cell data set; performing data preprocessing on the original cell data set to generate a cell data set; performing multi-dimensional cell feature extraction on the cell data set to obtain multi-dimensional cell feature data;

[0079] In an embodiment of the present invention, relevant cell raw data, including sequence information of fragments of each cell, are downloaded from a laboratory or a cell data sharing platform through a data interface; the downloaded data is compressed and saved in a fastq file format to form a cell raw data set; data preprocessing is performed on the cell raw data set, specifically, during the quality control process, low-quality reads are removed to reduce the impact of technical noise on the analysis; quality control indicators include the total number of cell reads, the number of detected genes, and the mitochondrial gene expression ratio; for example, low-quality cells or empty droplets usually have only a few genes, while cell doublets or multiplets show abnormally high gene counts; reads are aligned to a reference genome, and the reads of each gene are counted to generate a gene expression matrix; this step is usually processed using software such as CellRanger and STAR; for example, the peripheral blood single cell (PBMC) data set is processed using Cell Ranger software to generate a cell count matrix. At the single-cell level, some reads come from dual cells; filtering processing technology is used to reduce the interference of cells on data analysis; for example, low-quality cells are filtered out by setting a threshold; the gene expression matrix is ​​normalized to eliminate technical bias and facilitate the comparison of gene expression between different cells; commonly used normalization methods include LogNormalize, which performs logarithmic transformation on the gene expression value of each cell and scales it to the same scale; the data is scaled to ensure that the gene expression value of each cell is on the same scale; for example, the ScaleData function in the Seurat package is used to select specific variables for regression; PCA is performed to reduce the dimensionality of the data for visualization and subsequent analysis; specifically, the RunPCA function in the Seurat package is used to perform PCA analysis and obtain multi-dimensional feature data of cells.

[0080] Step S2: performing cell expression feature recognition on the cell multi-dimensional feature data to generate cell expression feature information; performing cell type classification on the cell expression feature information to obtain cell type data; performing cell genome detection on the cell multi-dimensional feature data according to the cell type data to generate cell genome data;

[0081] In the embodiment of the present invention, the FindVariableFeatures function in the Seurat package is used to identify genes with highly variable expression between cells; specifically, the expression levels in different cells vary greatly, indicating differences in cell states or types; for example, when processing PBMC data, 2000 highly variable genes are screened out by the FindVariableFeatures function; cell clustering is performed by the FindNeighbors and FindClusters functions of the Seurat package, and the number of clusters is controlled by the resolution parameter (resolution); for example, the resolution is set to 0.9, and different cell clusters are identified by the FindClusters function; then, R is used to perform clustering. The unTSNE function performs t-SNE dimensionality reduction and visualization to observe the distribution of different cell clusters; based on the cell type data, cell genome detection is performed; the DoHeatmap function of the Seurat package is used to perform heat map visualization of the expression differences of marker genes for each cell cluster to identify the specific expression genes of each cell cluster; in addition, all genes with significant differential expression are found through the FindAllMarkers function; single-cell genome sequencing technology, such as MALBAC technology, is used to amplify and sequence the genome in a single cell; MALBAC technology is used to reduce PCR amplification bias, so that 93% of the genome in a single cell can be sequenced, thereby discovering genetic differences between individual cells and generating cell genome data.

[0082] Step S3: performing sequence structure analysis on the cell genome data to obtain gene sequence structure data; performing cell function detection on the gene sequence structure data to obtain cell function data; performing gene-specific expression pattern recognition on the cell function data to generate a gene-specific expression pattern;

[0083] In an embodiment of the present invention, CRISPR genetic editing technology is used to invert CTCF sites in situ to reveal the construction of three-dimensional genome topology; for example, in the protocadherin gene cluster, the CTCF protein recognizes the directionality of its targeted DNA element and establishes a specific interaction with the gene promoter, thereby forming a spatiotemporal expression pattern; by analyzing the DNA sequence of the CTCF site, chromatin looping and high-level topological domains are formed, and then its regulatory effect on gene expression is analyzed to obtain cell function data; the Seurat process is used to analyze single-cell data and identify gene-specific expression patterns; for example, when processing single-cell data, exogenous genes are first removed, a Seurat object is constructed, and the expression ratio of mitochondrial genes and ribosomal genes is calculated to evaluate the quality of the cells; then, a cleaned expression matrix is ​​obtained by filtering out genes and cells with too low expression levels and cells with too high a proportion of mitochondrial DNA; then, standardization processing, finding variant characteristic genes, scaling data, performing PCA and other steps are performed, and finally, different cell subpopulations are identified through t-SNE dimensionality reduction and visualization, and the specific expression genes of each subpopulation are identified to obtain gene-specific expression patterns.

[0084] Step S4: Carry out cell correlation mapping of cell type data, cell function data and gene-specific expression patterns to obtain cell correlation data; perform intelligent cell coding identification based on the cell correlation data to generate cell coding identification data; establish a cell database index architecture based on the cell coding identification data to obtain a cell database index architecture; adaptively and parallelly transmit the cell data set to the cell database index architecture to generate a cell storage report.

[0085] In an embodiment of the present invention, the FindAllMarkers function in the Seurat package is used to identify marker genes in different cell types; the identified genes whose expression levels in specific cell types are significantly higher than those of other types are mapped to form cell correlation data; for example, in a cell data set, the FindAllMarkers function is used to find the specific highly expressed genes of each cell cluster, thereby obtaining the correlation between cells; based on the cell correlation data, the autoencoder neural network is used to encode and identify the cells; specifically, the high-dimensional cell expression data is mapped to a low-dimensional space while retaining the correlation between cells; for example, a deep autoencoder model is trained by integrating cell type data, cell function data and gene-specific expression patterns, and the feature vector of each cell is encoded into a unique cell coding identifier; a cell database index architecture is established using database technology (such as MySQL); specifically, a unique index is created for each cell coding identifier, and the cell type data, cell function data and gene-specific expression patterns are stored as fields in the database; such an architecture quickly retrieves and compares data from different cells, facilitating subsequent data analysis and query; parallel computing technology is used, such as Apache Spark performs distributed processing and transmission of cell data sets; for example, it divides the cell data set into multiple small blocks, and then processes them in parallel on multiple computing nodes. Finally, the processing results are summarized and stored in the cell database, and a cell storage report is generated.

[0086] Preferably, step S2 comprises the following steps:

[0087] Step S21: performing cell feature labeling on the multi-dimensional cell feature data to obtain cell feature labeling data; performing expression feature selection on the cell feature labeling data to generate expression feature selection data;

[0088] Step S22: extracting cell expression features from the cell multi-dimensional feature data based on the expression feature selection data to generate cell expression feature information; performing cell expression state detection on the cell expression feature information to obtain cell expression state data;

[0089] Step S23: performing expression activity identification on the cell expression state data to generate cell expression activity data; performing cell type classification according to the cell expression activity data to obtain cell type data;

[0090] Step S24: extracting cell gene types from the cell type data to generate cell gene type data; identifying gene enrichment conditions from the cell gene type data to obtain cell gene enrichment conditions;

[0091] Step S25: measuring the expression level of cell gene enrichment to generate gene enrichment expression level data; performing cell genome detection based on the gene enrichment expression level data to obtain cell genome data.

[0092] In an embodiment of the present invention, the FindVariableFeatures function in the Seurat package is used to perform cell feature labeling on the multi-dimensional feature data of cells; specifically, by calculating the expression variability of each gene, the gene with the largest expression difference between cells is identified; the SelectFeatures function is used to perform expression feature selection on the cell feature labeling data, specifically based on the set threshold (such as average expression level and variability), the most representative gene is selected, and expression feature selection data is generated; based on the expression feature selection data, the ScaleData function in the Seurat package is used to extract cell expression features from the multi-dimensional feature data of cells, and the cell expression features are extracted by centering and scaling the gene expression data; the FindMarkers function is used to detect the cell expression state of the cell expression feature information, and by comparing the gene expression differences of different cell populations, the differentially expressed genes are identified to obtain the cell expression state data; the ScoreFeatures function is used to perform expression active analysis on the cell expression state data The method uses feature recognition technology to specifically identify the expression characteristics of each gene in each cell to obtain the active gene expression pattern; according to the cell expression activity data, the FindClusters function is used to divide the cell types, and the cells with similar expression patterns are divided into the same type through clustering technology; the cell gene type data is extracted, and the gene expression matrix of the specific cell type is extracted through the GetAssayData function to analyze the gene expression pattern; the EnrichmentTest function is used to identify the gene enrichment of the cell gene type data, and the enriched gene set is identified by comparing the expression difference between the specific gene set and the background gene set; the expression of the cell gene enrichment is measured through the AverageExpression function to generate gene enrichment expression data; based on the gene enrichment expression data, the DoHeatmap function is used to detect the cell genome, and the gene expression pattern is displayed through a heat map to show the expression difference of genes in different cell types.

[0093] As an example of the present invention, refer to Figure 2 As shown, in this example, step S3 includes:

[0094] Step S31: performing sequence sequencing on the cell genome data to generate gene sequence sequencing data; performing sequencing data segmentation on the gene sequence sequencing data to obtain gene sequence segmentation information; performing sequence expression feature recognition on the gene sequence segmentation information to obtain gene sequence expression features;

[0095] Step S32: performing epigenetic modification site location on the gene sequence expression characteristics to generate epigenetic modification sites; performing epigenetic structural feature identification on the epigenetic modification sites to obtain epigenetic structural features; performing sequence structure analysis based on the epigenetic structural features to obtain gene sequence structure data;

[0096] Step S33: performing sequence structure characteristic state recognition on the gene sequence structure data to generate a sequence structure characteristic state; performing cell function domain mapping on the sequence structure characteristic state to obtain cell function domain mapping data;

[0097] Step S34: positioning the function regulation nodes on the cell function domain mapping data to obtain the cell function regulation nodes; identifying the cell function performance of the cell function regulation nodes to obtain the cell function data;

[0098] Step S35: Perform gene-specific expression pattern recognition on the cell function data to generate a gene-specific expression pattern.

[0099] In the embodiment of the present invention, a high-throughput sequencing technology (such as the Illumina platform) is used to sequence the cell genome data to generate gene sequence sequencing data; the data generated by the specific sequencing platform includes the base sequence information of the cell genome; the BWA technology is used to compare the gene sequence sequencing data, and the short sequences obtained by sequencing are accurately mapped to the reference genome to generate a file in the SAM / BAM format; the sequencing data is segmented by GATK to obtain gene sequence segmentation information; this step includes sorting, deduplication, local realignment and basic quality score correction of the BAM file; The feature recognition technology is used to identify the sequence performance characteristics of the gene sequence segmentation information, specifically identifying the transcription factor binding sites and chromatin accessible regions; the ChIP-seq technology is used to sequence specific epigenetic modifications (such as H3K27ac), and the peak area of ​​epigenetic modification is identified by comparing the ChIP-seq data to the reference genome; the HOMER software package is used to identify the epigenetic structural characteristics of the epigenetic modification sites; the sequence structure analysis is performed according to the epigenetic structural characteristics, by analyzing the distribution of open chromatin regions and transcription factor binding sites; using 3C technology (such as Hi- C) Identify the sequence structure feature state of gene sequence structure data to specifically reveal the interaction between chromatin; compare the sequence structure feature state with known gene expression data and epigenetic data, and perform cell function domain mapping to obtain cell function domain mapping data; use CRISPR-Cas9 technology to locate the functional regulatory nodes of the cell function domain mapping data, specifically by knocking out or knocking in specific genomic regions to study their effects on cell function; identify the cell function performance of cell function regulatory nodes, and identify the key genomic regions that regulate specific cell functions by monitoring the phenotypic changes of cells after CRISPR-Cas9 editing; use single-cell RNA sequencing technology to identify gene-specific expression patterns of cell function data, and identify gene expression characteristics in specific cell types or states by analyzing gene expression changes at the single-cell level; use the AverageExpression function in the Seurat package to measure the expression level of gene-specific expression patterns to obtain the average expression level of each gene in different cell types or states; perform cell genome detection based on gene enrichment expression data, and obtain gene-specific expression patterns by analyzing changes in gene expression levels.

[0100] As an example of the present invention, refer to Figure 3 As shown, in this example, step S35 includes:

[0101] Step S351: classify the cell function data into functional types to obtain cell function type data; perform cell DNA content parameter detection on the cell function type data to generate a cell DNA content value;

[0102] Step S352: performing DNA content function association on the cell function data according to the cell DNA content value to obtain DNA content function association data; performing cell cycle division according to the DNA content function association data to obtain cell cycle data;

[0103] Step S353: extracting cell time sequence parameters from the cell cycle data to obtain cell time sequence parameters; performing functional sequence expression recognition on the cell function data based on the cell time sequence parameters to generate a cell function sequence expression pattern;

[0104] Step S354: extracting single function expression features from the cell function sequential expression pattern to generate single function expression features; performing cycle interval singularity feature recognition on the single function expression features according to the cell cycle data to obtain cycle interval singularity features;

[0105] Step S355: Perform gene stage-specific detection based on the period interval uniqueness feature to obtain gene stage-specific information; perform gene-specific expression pattern recognition on the gene stage-specific information to generate a gene-specific expression pattern.

[0106] In an embodiment of the present invention, the AverageExpression function in the Seurat package is used to classify the cell function data into functional types, and the average expression value of each cell type is specifically calculated to distinguish different cell function types; by flow cytometry technology, a nucleic acid dye (such as PI) is used to label DNA, and the DNA content of each stage of the cell cycle is analyzed to generate a cell DNA content value; according to the cell DNA content value, the FindAllMarkers function in the Seurat package is used to associate the cell function data with the DNA content function, and identify the gene expression changes associated with the DNA content change; by analyzing the DNA content function association data, combined with the cell cycle theory (G0 / G1 phase, S phase, G2 phase and M phase), the cell cycle is divided to obtain the cell cycle data; the cell cycle data is analyzed to extract the cell time sequence parameters, such as the duration and conversion rate of each stage of the cell cycle, to obtain the cell time sequence parameters; based on the cell time sequence parameters, the DoHeatmap function in the Seurat package is used to identify the function sequence expression of the cell function data, and the basic expression is displayed by a heat map. The expression pattern changes with the cell cycle; analyze the sequential expression pattern of cell functions, extract single function expression features, such as the expression peak of a specific gene in the cell cycle, and generate a single function expression feature; according to the cell cycle data, use the FindMarkers function in the Seurat package to identify the cycle interval uniqueness of the single function expression feature, and obtain the cycle interval uniqueness; based on the cycle interval uniqueness, use gene editing technology (such as CRISPR-Cas9) to perform gene stage-specific detection to obtain gene stage-specific information; by editing specific genes and observing cell cycle changes, determine the specific role of genes in the cell cycle; analyze the gene stage-specific information, use the FindAllMarkers function in the Seurat package to perform gene-specific expression pattern recognition, and specifically identify genes with significant expression differences under specific cell states.

[0107] Preferably, step S4 comprises the following steps:

[0108] Step S41: Perform cell correlation mapping on the cell type data, cell function data and gene-specific expression pattern to obtain cell correlation data;

[0109] Step S42: performing cell correlation analysis on the cell multi-dimensional feature data according to the cell correlation data to obtain cell correlation data; performing cell intelligent coding identification according to the cell correlation data to generate cell coding identification data;

[0110] Step S43: assign cell database index features to the cell coding identification data to obtain database index assignment information; establish a cell database index architecture based on the database index assignment information to obtain a cell database index architecture; adaptively and parallelly transmit the cell data set to the cell database index architecture to generate a cell storage report.

[0111] In the embodiment of the present invention, the FindAllMarkers function in the Seurat package is used to calculate the ratio of gene expression in different cell populations and the average logarithmic fold change (logFC) to identify the characteristic genes of each cell type, and the cell type data, cell function data and gene-specific expression patterns are comprehensively analyzed to identify genes with significant expression differences in different cell types, thereby obtaining cell correlation data; based on the cell correlation data, the FindNeighbors and FindClusters functions in the Seurat package are used to perform cell correlation analysis on the multi-dimensional feature data of the cells, and by constructing a cell adjacency graph based on expression similarity, the correlation between cells is identified and cluster analysis is performed; based on the cell correlation data, the ScaleData and RunPCA functions in the Seurat package are used to perform cluster analysis on the cell correlation data. Perform intelligent cell coding and identification, map the high-dimensional expression data of cells to low-dimensional space through dimensionality reduction technology, and provide a unique coding identifier for each cell; assign cell database index features to the cell coding identification data, and use the index creation technology of the database management system (such as MySQL) to assign a unique index key to each cell coding identifier; establish a cell database index architecture based on the database index assignment information; use the table creation and index creation functions provided by the database management system to build an index architecture to store and manage cell coding identification data and its related features; adaptively transmit the cell data set in parallel to the cell database index architecture, use a parallel computing framework (such as Apache Spark) to split the data into multiple small blocks, and process them in parallel on multiple computing nodes, then summarize and store the processing results in the cell database, and generate a cell storage report.

[0112] Preferably, step S41 includes the following steps:

[0113] Step S411: performing type statistics on the cell type data to obtain the number of cell type types; sorting the number of cell type types to generate cell type number sorting data;

[0114] Step S412: performing function performance state detection on the cell function data to obtain the cell function performance state; performing state type statistics on the cell function performance state to generate cell function state type data;

[0115] Step S413: matching the cell type quantity sorting data with the cell function state category data in terms of cell type function state quantity to generate a cell type function quantity matching value;

[0116] Step S414: performing specific expression genome determination on the gene-specific expression pattern to obtain the specific expression genome; performing specific gene type extraction on the cell type data according to the specific expression genome to generate specific gene type data;

[0117] Step S415: mapping the specific gene type data and the cell type quantity ranking data to the specific expression gene quantity to obtain a specific expression gene quantity mapping value;

[0118] Step S416: Perform cell-related merging of the cell type function quantity matching value and the specific expression gene quantity mapping value to obtain cell-related data.

[0119] In the embodiment of the present invention, the table function in the Seurat package is used to perform type statistics on the cell type data, specifically the statistics of the seurat_clusters metadata, to obtain the frequency distribution of different cell types; the sort function in the R language is used to sort the number of cell type types, and generate cell type number sorting data; the ScoreFeatures function in the Seurat package is used to detect the functional performance state of the cell function data, specifically by detecting the state of each cell on a specific gene set, thereby evaluating the functional state of the cell; the table function in the R language is used to perform state type statistics on the cell function performance state, and identify cell types with different functional states; the cell type number sorting data is matched with the cell function state type data, and the merge function in the R language is used to generate the cell type function quantity matching value; use the FindAllMarkers function in the Seurat package to determine the specific expression gene set for the gene-specific expression pattern, specifically by screening differentially expressed genes to determine the genes that are specifically highly expressed in specific cell types; according to the specific expression gene set, use the GetAssayData function in the Seurat package to extract specific gene types from the cell type data and perform cell type specific gene labeling; map the specific gene type data with the cell type quantity sorting data to the specific expression gene quantity, and use the merge function in the R language to obtain the specific expression gene quantity mapping value; merge the cell type function quantity matching value with the specific expression gene quantity mapping value for cell correlation, and use the Reduce function and merge function in the R language to obtain the cell correlation data.

[0120] Preferably, step S42 includes the following steps:

[0121] Step S421: performing type function similarity measurement according to the cell correlation data to obtain a type function similarity measurement value; performing cell type function clustering on the cell multi-dimensional feature data based on the type function similarity measurement value to generate cell type function clustering data;

[0122] Step S422: performing specific gene quantity distribution cycle identification according to the cell correlation data to obtain expression gene distribution cycle data; performing specific gene quantity cycle association on the cell multi-dimensional feature data based on the expression gene distribution cycle data to generate specific gene cycle association data;

[0123] Step S423: integrating the cell type function clustering data and the specific gene cycle association data to obtain cell association data; generating cell coding rules based on the cell association data to obtain cell coding rule information;

[0124] Step S424: performing cell type encoding on the cell type data according to the cell encoding rule information to generate cell type encoding data; performing cell function encoding on the cell function data based on the cell encoding rule information to generate cell function encoding data; performing specific expression pattern encoding on the gene specific expression pattern according to the cell encoding rule information to generate specific pattern encoding data;

[0125] Step S425: The cell type coding data, the cell function coding data and the specific pattern coding data are fused into a cell intelligent coding identification to generate cell coding identification data.

[0126] In an embodiment of the present invention, the FindAllMarkers function in the Seurat package is used to measure the type functional similarity of cell correlation data, and the differentially expressed genes between different cell types are detected to quantify the functional similarity of the cell types; based on the type functional similarity measurement value, the FindNeighbors and FindClusters functions in the Seurat package are used to perform cell type functional clustering on the multidimensional feature data of the cells, and the correlation between cells is identified by constructing a cell adjacency graph based on expression similarity, and cluster analysis is performed; using single-cell transcriptome data, by analyzing the expression of cell cycle-related genes, the expression gene distribution cycle data is identified; and by analyzing the expression of marker genes in cell cycle stages such as G1 / S and G2 / M, the cycle stage of the cell is annotated; based on the expression gene distribution cycle data, the DoHeatmap function in the Seurat package is used to perform specific gene quantity cycle association on the multidimensional feature data of the cells, and the pattern of gene expression changing with the cell cycle is displayed through a heat map; the cell type Functional clustering data and specific gene cycle association data were integrated, and the merge function in R language was used to obtain cell association data; based on the cell association data, the DimPlot and ClusterTree functions in the Seurat package were used to generate cell coding rules, and the high-dimensional expression data of the cells were mapped to the low-dimensional space through dimensionality reduction technology to construct a hierarchical structure of cell clustering; according to the cell coding rule information, the factor function in R language was used to encode the cell type data; based on the cell coding rule information, the ScaleData and RunPCA functions in the Seurat package were used to encode the cell function data; through the cell coding rule information, the FindAllMarkers function in the Seurat package was used to encode the gene-specific expression pattern; the cell type coding data, cell function coding data and specific pattern coding data were fused for cell intelligent coding identification, and the Reduce function and merge function in R language were used to generate cell coding identification data.

[0127] Preferably, step S43 includes the following steps:

[0128] Step S431: performing cell database index mapping on the cell multi-dimensional feature data to generate database index mapping features; performing cell database index type matching on the database index mapping features to obtain index type matching data;

[0129] Step S432: performing index structure type identification on the index type matching data according to the cell correlation data to obtain index structure type data; performing index feature enhancement on the index structure type mapping data to generate index feature enhancement data;

[0130] Step S433: assigning index features to the index feature enhancement data based on the cell coding identification data to obtain database index assignment information; establishing a cell database index architecture according to the database index assignment information to obtain a cell database index architecture;

[0131] Step S434: performing correlation sharding processing on the cell data set based on the cell correlation data to obtain a cell sharding data set; dividing the cell sharding data set into transmission task nodes to generate transmission task node information; and transmitting the cell sharding data set in parallel to the cell database index architecture based on the transmission task node information to input a cell storage report.

[0132] In the embodiment of the present invention, the FindAllMarkers function in the Seurat package is used to map the multi-dimensional feature data of cells to a cell database index. Specifically, by comparing the gene expression levels of different cell populations, the differentially expressed genes in each cell population are identified, and these genes will be used as the features of the database index; the Reduce and merge functions of the R language are used to match the database index mapping features to the cell database index type, and by merging multiple data frames, the correspondence between the cell type and the gene expression data is ensured; according to the cell correlation data, the FindAllMarkers function in the Seurat package is used to identify the index structure type of the index type matching data, and by analyzing the distribution of differentially expressed genes, the specific gene markers of the cell type are identified; the index structure type Map data to enhance index features, use the Reduce function of R language to generate index feature enhancement data, and enhance the correlation between cell types and gene expression features through cumulative merging operations; based on cell coding identification data, use the factor function of R language to assign index features to index feature enhancement data, and assign a unique coding identification to each cell type; according to the database index assignment information, use the table creation and index functions of database technology (such as MySQL) to establish the cell database index architecture; based on cell correlation data, use the split function of R language to perform correlation sharding on the cell data set, and divide the large data set into smaller and manageable data blocks; divide the cell sharding data set into transmission task nodes, and use a parallel computing framework (such as Apache Spark); assign data transmission tasks to multiple computing nodes to achieve parallel transmission; based on the transmission task node information, transmit the cell sharding data set in parallel to the cell database index architecture, and use the batch insert function of the database management system to input the cell storage report.

[0133] In this specification, a cell storage system is provided for executing the above-mentioned cell storage method, and the cell storage system comprises:

[0134] The cell data acquisition module is used to obtain the original cell data set; perform data preprocessing on the original cell data set to generate a cell data set; perform multi-dimensional cell feature extraction on the cell data set to obtain multi-dimensional cell feature data;

[0135] The cell genome detection module is used to identify cell expression characteristics of multi-dimensional cell feature data to generate cell expression feature information; classify cell expression feature information into cell types to obtain cell type data; perform cell genome detection on multi-dimensional cell feature data according to cell type data to generate cell genome data;

[0136] The gene-specific expression pattern recognition module is used to perform sequence structure analysis on cell genome data to obtain gene sequence structure data; perform cell function detection on gene sequence structure data to obtain cell function data; perform gene-specific expression pattern recognition on cell function data to generate gene-specific expression patterns;

[0137] The cell data storage module is used to perform cell correlation mapping on cell type data, cell function data and gene-specific expression patterns to obtain cell correlation data; perform intelligent cell coding identification based on the cell correlation data to generate cell coding identification data; establish a cell database index architecture based on the cell coding identification data to obtain a cell database index architecture; adaptively and parallelly transmit the cell data set to the cell database index architecture to generate a cell storage report.

[0138] The present invention obtains the original data set of cells and performs data preprocessing through the cell data acquisition module, thereby obtaining a standardized cell data set, which provides accurate and reliable basic data for subsequent analysis; multidimensional cell feature extraction further enriches the data set, so that the multidimensional feature information of the cell data is displayed; cell expression feature recognition and cell type division provide data support for subsequent genome detection, ensuring the pertinence and accuracy of genome detection. Through the cell genome detection module, the recognition of cell expression feature information and the division of cell type data make the cell genome detection more accurate, ensuring that the generated cell genome data is more representative and scientifically valuable; sequence structure analysis and cell function detection provide important information for understanding the biological functions and mechanisms of cells, and the recognition of gene-specific expression patterns can reveal the role and regulatory mechanism of specific genes in cells. Through the gene-specific expression pattern recognition module, the sequence structure analysis of cell genome data provides a data basis for understanding the physical structure and function of genes, and the acquisition of cell function data reveals the specific role of cells in organisms; the recognition of gene-specific expression patterns further deepens the understanding of gene functions and provides key information for subsequent biological research and application. Through the cell data storage module, the cell correlation mapping integrates the data of cell type, function and gene expression pattern, ensuring that the generated cell correlation data provides an important perspective for a comprehensive understanding of the interaction between cells; the generation of cell intelligent coding identification provides an efficient tool for the management and retrieval of cell data, and the establishment of the cell database index architecture based on this provides a structured framework for the storage and rapid access of cell data; the cell data set is adaptively transmitted in parallel to the cell database index architecture, and the cell storage report finally generated ensures the convenience of systematic management of data and subsequent research. Therefore, the present invention realizes multi-dimensional management of cell data through data processing technology, feature mapping technology, pattern recognition technology and deep learning technology, thereby shortening the process time of cell data storage, ensuring that the cell data stored can be traced, and then improving the efficiency of cell storage.

[0139] A computer-readable storage medium stores a computer program, wherein the computer program is used to execute the cell banking method.

[0140] Therefore, the embodiments should be regarded as illustrative and non-restrictive from all points, and the scope of the present invention is limited by the appended claims rather than the above description, and it is therefore intended that all changes falling within the meaning and range of equivalent elements of the application documents are included in the present invention.

[0141] The above description is only a specific embodiment of the present invention, so that those skilled in the art can understand or implement the present invention. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention will not be limited to the embodiments shown herein, but should conform to the widest scope consistent with the principles and novel features invented herein.

Claims

1. A cell banking method, characterized in that: The following steps are involved: Step S1: obtaining an original cell data set; performing data preprocessing on the original cell data set to generate a cell data set; performing multi-dimensional cell feature extraction on the cell data set to obtain multi-dimensional cell feature data; Step S2: performing cell expression feature recognition on the cell multi-dimensional feature data to generate cell expression feature information; performing cell type classification on the cell expression feature information to obtain cell type data; performing cell genome detection on the cell multi-dimensional feature data according to the cell type data to generate cell genome data; Step S3: performing sequence structure analysis on the cell genome data to obtain gene sequence structure data; performing cell function detection on the gene sequence structure data to obtain cell function data; performing gene-specific expression pattern recognition on the cell function data to generate a gene-specific expression pattern; Step S4: Perform cell correlation mapping on the cell type data, cell function data and gene-specific expression pattern to obtain cell correlation data; perform cell intelligent coding identification according to the cell correlation data to generate cell coding identification data; establish a cell database index architecture based on the cell coding identification data to obtain a cell database index architecture; The cell data set is adaptively and parallelly transferred to the cell database index architecture to generate a cell entry report.

2. The cell banking method according to claim 1, characterized in that: Step S2 includes the following steps: Step S21: performing cell feature labeling on the cell multi-dimensional feature data to obtain cell feature labeling data; performing expression feature selection on the cell feature labeling data to generate expression feature selection data; Step S22: extracting cell expression features from the cell multi-dimensional feature data based on the expression feature selection data to generate cell expression feature information; performing cell expression state detection on the cell expression feature information to obtain cell expression state data; Step S23: performing expression activity identification on the cell expression state data to generate cell expression activity data; performing cell type classification according to the cell expression activity data to obtain cell type data; Step S24: extracting cell gene types from the cell type data to generate cell gene type data; identifying gene enrichment conditions from the cell gene type data to obtain cell gene enrichment conditions; Step S25: measuring the expression level of cell gene enrichment to generate gene enrichment expression level data; performing cell genome detection based on the gene enrichment expression level data to obtain cell genome data.

3. The cell banking method according to claim 1, characterized in that: Step S3 includes the following steps: Step S31: performing sequence sequencing on the cell genome data to generate gene sequence sequencing data; performing sequencing data segmentation on the gene sequence sequencing data to obtain gene sequence segmentation information; performing sequence expression feature recognition on the gene sequence segmentation information to obtain gene sequence expression features; Step S32: performing epigenetic modification site location on the gene sequence expression characteristics to generate epigenetic modification sites; performing epigenetic structural feature identification on the epigenetic modification sites to obtain epigenetic structural features; performing sequence structure analysis based on the epigenetic structural features to obtain gene sequence structure data; Step S33: performing sequence structure characteristic state recognition on the gene sequence structure data to generate a sequence structure characteristic state; performing cell function domain mapping on the sequence structure characteristic state to obtain cell function domain mapping data; Step S34: positioning the function regulation nodes on the cell function domain mapping data to obtain the cell function regulation nodes; identifying the cell function performance of the cell function regulation nodes to obtain the cell function data; Step S35: Perform gene-specific expression pattern recognition on the cell function data to generate a gene-specific expression pattern.

4. The cell banking method according to claim 3, characterized in that: Step S35 includes the following steps: Step S351: classify the cell function data into functional types to obtain cell function type data; perform cell DNA content parameter detection on the cell function type data to generate a cell DNA content value; Step S352: performing DNA content function association on the cell function data according to the cell DNA content value to obtain DNA content function association data; performing cell cycle division according to the DNA content function association data to obtain cell cycle data; Step S353: extracting cell time sequence parameters from the cell cycle data to obtain cell time sequence parameters; performing functional sequence expression recognition on the cell function data based on the cell time sequence parameters to generate a cell function sequence expression pattern; Step S354: extracting single function expression features from the cell function sequential expression pattern to generate single function expression features; performing cycle interval singularity feature recognition on the single function expression features according to the cell cycle data to obtain cycle interval singularity features; Step S355: Perform gene stage-specific detection based on the period interval uniqueness feature to obtain gene stage-specific information; perform gene-specific expression pattern recognition on the gene stage-specific information to generate a gene-specific expression pattern.

5. The cell banking method according to claim 1, characterized in that: Step S4 includes the following steps: Step S41: Perform cell correlation mapping on the cell type data, cell function data and gene-specific expression pattern to obtain cell correlation data; Step S42: performing cell correlation analysis on the cell multi-dimensional feature data according to the cell correlation data to obtain cell correlation data; performing cell intelligent coding identification according to the cell correlation data to generate cell coding identification data; Step S43: assign cell database index features to the cell coding identification data to obtain database index assignment information; establish a cell database index architecture based on the database index assignment information to obtain a cell database index architecture; adaptively and parallelly transmit the cell data set to the cell database index architecture to generate a cell storage report.

6. The cell banking method according to claim 5, characterized in that: Step S41 includes the following steps: Step S411: performing type statistics on the cell type data to obtain the number of cell type types; sorting the number of cell type types to generate cell type number sorting data; Step S412: performing function performance state detection on the cell function data to obtain the cell function performance state; performing state type statistics on the cell function performance state to generate cell function state type data; Step S413: matching the cell type quantity sorting data with the cell function state category data in terms of cell type function state quantity to generate a cell type function quantity matching value; Step S414: performing specific expression genome determination on the gene-specific expression pattern to obtain the specific expression genome; performing specific gene type extraction on the cell type data according to the specific expression genome to generate specific gene type data; Step S415: mapping the specific gene type data and the cell type quantity ranking data to the specific expression gene quantity to obtain a specific expression gene quantity mapping value; Step S416: Perform cell-related merging of the cell type function quantity matching value and the specific expression gene quantity mapping value to obtain cell-related data.

7. The cell banking method according to claim 5, characterized in that: Step S42 includes the following steps: Step S421: performing type function similarity measurement according to the cell correlation data to obtain a type function similarity measurement value; performing cell type function clustering on the cell multi-dimensional feature data based on the type function similarity measurement value to generate cell type function clustering data; Step S422: performing specific gene quantity distribution cycle identification according to the cell correlation data to obtain expression gene distribution cycle data; performing specific gene quantity cycle association on the cell multi-dimensional feature data based on the expression gene distribution cycle data to generate specific gene cycle association data; Step S423: integrating the cell type function clustering data and the specific gene cycle association data to obtain cell association data; generating cell coding rules based on the cell association data to obtain cell coding rule information; Step S424: performing cell type encoding on the cell type data according to the cell encoding rule information to generate cell type encoding data; performing cell function encoding on the cell function data based on the cell encoding rule information to generate cell function encoding data; performing specific expression pattern encoding on the gene specific expression pattern according to the cell encoding rule information to generate specific pattern encoding data; Step S425: The cell type coding data, the cell function coding data and the specific pattern coding data are fused into a cell intelligent coding identification to generate cell coding identification data.

8. The cell banking method according to claim 5, characterized in that: Step S43 includes the following steps: Step S431: performing cell database index mapping on the cell multi-dimensional feature data to generate database index mapping features; performing cell database index type matching on the database index mapping features to obtain index type matching data; Step S432: performing index structure type identification on the index type matching data according to the cell correlation data to obtain index structure type data; performing index feature enhancement on the index structure type mapping data to generate index feature enhancement data; Step S433: assigning index features to the index feature enhancement data based on the cell coding identification data to obtain database index assignment information; establishing a cell database index architecture according to the database index assignment information to obtain a cell database index architecture; Step S434: performing correlation sharding processing on the cell data set based on the cell correlation data to obtain a cell sharding data set; dividing the cell sharding data set into transmission task nodes to generate transmission task node information; and transmitting the cell sharding data set in parallel to the cell database index architecture based on the transmission task node information to input a cell storage report.

9. A cell storage system, characterized in that: Used to perform the cell banking method according to claim 1, the cell banking system comprises: The cell data acquisition module is used to obtain the original cell data set; perform data preprocessing on the original cell data set to generate a cell data set; perform multi-dimensional cell feature extraction on the cell data set to obtain multi-dimensional cell feature data; The cell genome detection module is used to identify cell expression characteristics of multi-dimensional cell feature data to generate cell expression feature information; classify cell expression feature information into cell types to obtain cell type data; perform cell genome detection on multi-dimensional cell feature data according to cell type data to generate cell genome data; The gene-specific expression pattern recognition module is used to perform sequence structure analysis on cell genome data to obtain gene sequence structure data; perform cell function detection on gene sequence structure data to obtain cell function data; perform gene-specific expression pattern recognition on cell function data to generate gene-specific expression patterns; The cell data storage module is used to perform cell correlation mapping on cell type data, cell function data and gene-specific expression patterns to obtain cell correlation data; perform intelligent cell coding identification based on the cell correlation data to generate cell coding identification data; establish a cell database index architecture based on the cell coding identification data to obtain a cell database index architecture; adaptively and parallelly transmit the cell data set to the cell database index architecture to generate a cell storage report.

10. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed, the cell banking method according to any one of claims 1 to 8 is implemented.

Images