Gene co-expression network establishment method and related device

Abstract

The invention provides a gene co-expression network establishment method and a related device. The gene co-expression network establishment method comprises the following steps: acquiring a target gene expression quantity matrix; performing feature extraction on the target gene expression quantity matrix to obtain a first gene feature matrix; constructing a global gene co-expression network according to the first gene feature matrix, and / or extracting second gene feature matrixes of different cell types according to the first gene feature matrix and the target gene expression quantity matrix, and constructing a cell type specific co-expression network according to the second gene feature matrix of different cell types. The problem of high false positive caused by direct prediction based on high-dimension and high-sparseness single cell transcriptome sequencing data in a traditional single cell gene co-expression method is solved, the accuracy of single cell gene co-expression prediction is improved, and a more remarkably related cell type specific gene module can be predicted.

Description

Technical Field

[0001] The present application relates to the field of artificial intelligence technology, and in particular to a method for establishing a gene co-expression network and related devices. Background Art

[0002] In the biological field, gene co-expression analysis is crucial for understanding complex biological processes. Single-cell sequencing technology can analyze gene expression at single-cell resolution and reveal heterogeneity between cells. However, due to the high dimensionality, high noise, and high sparsity of single-cell sequencing data, the complexity of network construction is increased, making it a huge challenge for researchers to infer gene expression from single-cell data. Summary of the invention

[0003] In view of this, the present application provides a method for establishing a gene co-expression network and related devices to solve at least part of the above-mentioned technical problems.

[0004] On the one hand, the present application provides a method for establishing a gene co-expression network, including: obtaining a target gene expression matrix; the elements in the target gene expression matrix are used to measure the expression level of a certain gene in a certain cell; feature extraction is performed on the target gene expression matrix to obtain a first gene feature matrix; the elements in the first gene feature matrix are used to measure the feature values ​​of the genes in the target gene expression matrix in different dimensions; a corresponding cell type-specific co-expression network is constructed according to the first gene feature matrix and the target gene expression matrix; and / or, a global gene co-expression network is constructed according to the first gene feature matrix.

[0005] In some embodiments, constructing a cell type-specific co-expression network based on the first gene feature matrix and the target gene expression matrix includes: determining a second gene feature matrix for each cell type based on the target gene expression matrix and the first gene feature matrix; each row in the second gene feature matrix is ​​the eigenvalue of genes in the first gene feature matrix in different dimensions, and each column is the eigenvalue of different genes in the same dimension; obtaining a corresponding cell type-specific module based on the second gene feature matrix of each cell type; and performing hierarchical clustering on the genes in each cell type-specific module to obtain a corresponding cell type-specific co-expression network.

[0006] In some embodiments, determining the second gene feature matrix of each cell type based on the target gene expression matrix and the first gene feature matrix includes: obtaining the gene expression matrix of differentially expressed genes contained in each cell type based on the target gene expression matrix; calculating the correlation between the gene expression matrix of differentially expressed genes contained in each cell type and the first gene feature matrix to form a cell-embedded gene correlation matrix for the corresponding cell type; wherein each row in the cell-embedded gene correlation matrix represents the importance of different features in the corresponding cell, and each column represents the importance of the same feature in the corresponding cell; for each cell type, determining the second gene feature matrix for the corresponding cell type based on the cell-embedded gene correlation matrix and the first gene feature matrix for the corresponding cell type.

[0007] In some embodiments, determining the second gene feature matrix of the corresponding cell type based on the cell-embedded gene correlation matrix of the corresponding cell type and the first gene feature matrix includes: extracting features of a set dimension from the first gene feature matrix as features of the corresponding cell type based on the cell-embedded gene correlation matrix; and forming the second gene feature matrix based on the extracted features of the corresponding cell type and the genes contained in the first gene feature matrix.

[0008] In some embodiments, the obtaining of the corresponding cell type-specific module according to the second gene feature matrix of each cell type includes: calculating the cosine similarity between each gene in the second gene feature matrix; clustering the second gene feature matrix according to the cosine similarity between each gene to form a first sub-cell type-specific module and a second sub-cell type-specific module; calculating a first score of the first sub-cell type-specific module and a second score of the second sub-cell type-specific module; comparing the first score and the second score; wherein, in response to the first score being greater than the second score, determining the first sub-cell type-specific module as the corresponding cell type-specific module; in response to the first score being less than the second score, determining the second sub-cell type-specific module as the corresponding cell type-specific module; in response to the first score being equal to the second score, determining the first sub-cell type-specific module or the second sub-cell type-specific module as the corresponding cell type-specific module.

[0009] In some embodiments, the calculating of the first score of the first sub-cell type-specific module and the second score of the second sub-cell type-specific module comprises: calculating a first relative expression level of each gene in the first sub-cell type-specific module in different cells; and calculating the first score according to each of the first relative expression levels and the number of genes included in the first sub-cell type-specific module; and calculating a second relative expression level of each gene in the second sub-cell type-specific module in different cells; and calculating the second score according to each of the second relative expression levels and the number of genes included in the second sub-cell type-specific module.

[0010] In some embodiments, constructing a global gene co-expression network based on the first gene feature matrix includes: calculating the co-expression relationship between each gene based on the first gene feature matrix to obtain a gene co-expression correlation matrix; hierarchically clustering the genes in the gene co-expression correlation matrix to construct the global gene co-expression network; the global gene co-expression network has a tree structure, wherein each branch of the tree structure includes a gene co-expression module; the gene co-expression module includes a group of genes with similar expression patterns.

[0011] In some embodiments, each row of the first gene feature matrix represents the eigenvalue of the same gene in different dimensions, and each column represents the eigenvalues ​​of different genes in the same dimension; the co-expression relationship between each gene is calculated according to the first gene feature matrix to obtain a gene co-expression correlation matrix, including: calculating the cosine similarity between each gene in the first gene feature matrix; the cosine similarity is used to measure the co-expression relationship between genes; and the gene co-expression correlation matrix is ​​obtained according to the obtained cosine similarity between each gene.

[0012] In some embodiments, the hierarchical clustering of genes in the gene co-expression correlation matrix to construct the global gene co-expression network includes: setting the number of genes included in the minimum gene module, and gradually processing the data in the gene co-expression correlation matrix according to the dynamic cutting tree strategy to form at least one gene co-expression module; recording each obtained gene co-expression module to construct the global gene co-expression network.

[0013] In some embodiments, obtaining the target gene expression matrix includes: obtaining a single-cell transcriptome sequencing scRNA-seq dataset of at least one biological sample, and generating a sub-expression matrix of genes contained in the corresponding biological sample according to each scRNA-seq dataset; preprocessing at least one of the sub-expression matrices to obtain the target gene expression matrix.

[0014] In some embodiments, the preprocessing includes at least one of the following: quality control, screening of highly variable genes, and data normalization.

[0015] In some embodiments, the feature extraction of the target gene expression matrix to obtain the first gene feature matrix includes: using a feature extraction unit included in a trained gene clustering model to extract features from the target gene expression matrix to obtain the first gene feature matrix; wherein the feature extraction unit includes an input layer, a convolution layer, an activation function layer, a pooling layer and a fully connected layer, the pooling layer is a spatial pyramid pooling layer, and the output result of the pooling layer is used as the input of the fully connected layer; the convolution layer includes N layers, and the output result of the i-th convolution layer is the input of the i+1-th convolution layer, and the output result of the N-th convolution layer is processed by the activation function layer as the input of the pooling layer, wherein N and i are positive integers, and i is less than N.

[0016] On the one hand, the present application provides a gene co-expression network establishment device, comprising: An acquisition module is used to acquire a gene expression matrix; the elements of the gene expression matrix are used to measure the expression level of a gene in a single cell; An extraction module is used to perform feature extraction on the target gene expression matrix to obtain a first gene feature matrix; the elements in the first gene feature matrix are used to measure the feature values ​​of genes in the target gene expression matrix in different dimensions; A construction module is used to construct a corresponding cell type-specific co-expression network according to the first gene feature matrix and the gene expression matrix; and / or to construct a global gene co-expression network according to the first gene feature matrix.

[0017] On one hand, the present application provides a device for establishing a gene co-expression network, comprising a processor for calling a program in a memory so that the device executes any of the methods described above.

[0018] On one hand, the present application provides a chip, including a processor, for calling a program from a memory so that a device equipped with the chip executes any of the methods described above.

[0019] On one hand, the present application provides a computer-readable storage medium having a program stored thereon, wherein the program is a computer that actively executes any of the methods described above.

[0020] The embodiment of the present application provides a method for establishing a gene co-expression network and a related device. The method for establishing a co-expression network includes: obtaining a target gene expression matrix; the elements in the target gene expression matrix are used to measure the expression level of a certain gene in a certain cell; extracting features from the target gene expression matrix to obtain a first gene feature matrix; the elements in the first gene feature matrix are used to measure the feature values ​​of genes in the target gene expression matrix in different dimensions; constructing a corresponding cell type-specific co-expression network based on the first gene feature matrix and the target gene expression matrix; and / or constructing a global gene co-expression network based on the first gene feature matrix. The method for establishing a gene co-expression network provided in an embodiment of the present application performs feature extraction on a target gene expression matrix to obtain a first gene feature matrix, and then constructs a global gene co-expression network based on the first gene feature matrix, and / or constructs a corresponding cell type-specific co-expression network based on the first gene feature matrix and the target gene expression matrix. In this way, gene features are used to construct a global gene co-expression network and / or a cell type-specific co-expression network, which can avoid the problem of high false positives caused by directly predicting single-cell gene co-expression based on sparse single-cell sequencing data, and not only improves the accuracy of single-cell gene co-expression prediction, but also can predict more significantly related cell type-specific gene modules. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] Figure 1 The figure is a schematic diagram of a process for establishing a gene co-expression network provided in an embodiment of the present application.

[0022] Figure 2 Shown is an exemplary schematic diagram of the target gene expression matrix provided in the examples of the present application.

[0023] Figure 3 Shown is a schematic diagram of the structure of a feature extraction unit in a gene clustering model provided in an embodiment of the present application.

[0024] Figure 4 Shown is an exemplary schematic diagram of the first gene feature matrix provided in an embodiment of the present application.

[0025] Figure 5 The figure is a schematic flow chart of a method for constructing a cell type-specific co-expression network provided in an embodiment of the present application.

[0026] Figure 6 Shown is a schematic diagram of a process for determining a corresponding cell type specific module provided in an embodiment of the present application.

[0027] Figure 7 Shown is a schematic flow chart of a method for constructing a global gene co-expression network provided in an embodiment of the present application.

[0028] Figure 8 Shown is a schematic diagram of the structure of a gene co-expression network establishment device provided in an embodiment of the present application.

[0029] Fig. 9 The figure shows a device for establishing a gene co-expression network provided in an embodiment of the present application. DETAILED DESCRIPTION

[0030] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0031] As mentioned above, gene co-expression analysis is crucial for understanding complex biological processes. For example, in the study of microarray and conventional transcriptome sequencing (i.e., RNA-seq) data, gene co-expression analysis has shown excellent performance in gene module detection, disease discovery, and detection of biologically relevant genes. In particular, the development of single-cell RNA sequencing (i.e., scRNA-seq) technology has enabled the analysis of gene expression at a single cell resolution, revealing heterogeneity between cells. Currently, a variety of methods or indicators have been proposed for inferring gene co-expression relationships from scRNA-seq data, including but not limited to Pearson correlation coefficient, Spearman correlation coefficient, GENIE3, PIDC, minet, sclink, and glasso. When inferring gene co-expression from scRNA-seq data, these aforementioned indicators or methods consider different association measures. For example, the popular weighted gene co-expression network analysis (WGCNA) uses pearson as a co-expression correlation indicator, which is mainly used to construct conventional transcriptome gene co-expression networks. PIDC and Minet use mutual information (MI) as a co-expression measurement method. GENIE3 uses a tree-based ensemble method to estimate the correlation between genes. sclink modifies the Gaussian graphical model by explicitly modeling in single-cell data to estimate gene co-expression. However, due to the high dimensionality and high sparsity of scRNA-seq data, the aforementioned indicators or methods have low accuracy in constructing gene co-expression networks. In addition, the aforementioned indicators or methods are less effective when dealing with large-scale transcriptome integration data from multiple sources and high heterogeneity, and cannot identify gene modules with high correlation. Moreover, for methods that infer cell type-specific co-expression networks from large data sets, such as sclink and CS-CORE, genes with high cell type expression are directly screened for network construction, but these methods will miss some genes with low cell type expression, making the final constructed network inaccurate. Therefore, it is urgent to develop new computational methods to effectively extract and integrate gene co-expression information from these large scRNA-seq data to improve the accuracy of gene co-expression prediction. And improve the current method of constructing gene co-expression networks for specific cell types based on large samples, infer more accurate cell type-specific networks, and reveal their potential gene co-expression patterns.

[0032] To this end, the present application embodiment provides a method for establishing a coexpression network, by obtaining a target gene expression matrix, and extracting features from the target gene expression matrix, obtaining a first gene feature matrix, and then using the first gene feature matrix to construct a global gene coexpression network, and / or, using the first gene feature matrix and the target gene expression matrix to construct a corresponding cell type-specific coexpression network. In this way, using gene features to construct a global gene coexpression network and / or a cell type-specific coexpression network can avoid the problem of high false positives caused by directly predicting single-cell gene coexpression based on sparse single-cell sequencing data, which not only improves the accuracy of single-cell gene coexpression prediction, but also can predict more significantly related cell type-specific gene modules.

[0033] The embodiments described in this application are described in detail below with reference to the accompanying drawings.

[0034] like Figure 1 As shown, it shows a schematic diagram of a method for establishing a gene co-expression network provided in an embodiment of the present application. Figure 1 In the method for establishing a gene co-expression network, the method may include: Step 101: Obtain a target gene expression matrix; the elements of the target gene expression matrix are used to measure the expression level of a gene in a single cell.

[0035] It should be noted that the so-called gene expression refers to the process of synthesizing genetic information from genes into functional gene products, where gene expression products are usually proteins, and all known life uses gene expression to synthesize macromolecules of life. The gene expression process can include the following three main steps: transcription, RNA processing, and translation. The so-called gene expression matrix can be a core data structure in bioinformatics and transcriptomics research. It can be generated by high-throughput sequencing technology such as scRNA-seq datasets. The rows of this gene expression matrix represent genes and the columns represent cells, where each element (and / or cell) in the gene expression matrix contains the expression level of the response gene in the corresponding cell. An example of a gene expression matrix is Figure 2 shown.

[0036] In some embodiments, step 101 may include: obtaining a scRNA-seq dataset of at least one biological sample, and generating a sub-expression matrix of genes included in the corresponding biological sample according to each scRNA-seq dataset; Preprocessing is performed on at least one of the sub-expression matrixes to obtain the target gene expression matrix.

[0037] It should be noted that the target gene expression matrix mentioned in the present application can be a matrix composed of multiple gene expressions extracted from at least one biological sample. In other words, the genes or cells in the target gene expression matrix can come from at least one biological sample. The biological sample can be any organism with genetic genes, such as mice, certain human tissues (e.g., cortical tissue, peripheral blood mononuclear cells, etc.). Among them, after scRNA-seq, each biological sample will obtain an scRNA-seq data set; each scRNA-seq data set will generate a corresponding sub-expression matrix.

[0038] After obtaining each sub-expression matrix, preprocessing is performed on at least one sub-expression matrix to obtain the target gene expression matrix, wherein the preprocessing may include at least one of the following: quality control, screening of highly variable genes, and data normalization.

[0039] It should be noted that the so-called quality control may refer to the fact that the sequencing quality of the scRNA-seq data set obtained after scRNA-seq will seriously affect the subsequent analysis. Therefore, the obtained scRNA-seq data set can be quality controlled to filter out genes or cells that do not meet the conditions. For example, in some embodiments, the purpose of this quality control is mainly to remove low-quality cells and genes. Therefore, scanpy in the python package can be used to perform quality control on each obtained scRNA-seq data set. Among them, scanpy is a python package specifically used to process single-cell data. That is, the filter_cells function and filter_genes function of the scanpy package remove cells and genes with low expression levels in each scRNA-seq data set to obtain filtered expression data.

[0040] Here, the so-called screening of highly variable genes may refer to selecting genes with large expression differences between different cells from the scRNA-seq data set after the aforementioned quality control for research. For example, in the present application, 1000 highly variable genes may be screened out from the quality-controlled scRNA-seq data set for analysis.

[0041] Here, the so-called normalization can mean that in order to avoid gradient disappearance or explosion in neural network training, the data of screening highly variable genes can be normalized to limit the data of screening highly variable genes to a suitable range. For example, the min-max normalization method can be used to map the data of screening highly variable genes to between 0 and 1, so that the training speed of the gene clustering model can be accelerated and the training efficiency can be improved.

[0042] After the above preprocessing, the subsequent gene expression matrix is ​​obtained. Figure 2 FIG. 1 shows an exemplary gene expression matrix, in which each column represents all genes corresponding to a cell, and each row represents all cells corresponding to a gene. For example, Figure 2 The gene expression data in includes a total of n cells, each cell includes m genes, and n and m are both positive integers. Each element represents the expression level of a gene in a cell, and the value of each element is between 0 and 1.

[0043] Step 102: extracting features from the target gene expression matrix to obtain a first gene feature matrix; the elements in the first gene feature matrix are used to measure the feature values ​​of genes in the target gene expression matrix in different dimensions.

[0044] In some embodiments, step 102 may include: performing feature extraction on the target gene expression matrix using a feature extraction unit included in a trained gene clustering model to obtain the first gene feature matrix; wherein the feature extraction unit includes an input layer, a convolution layer, an activation function layer, a pooling layer and a fully connected layer, the pooling layer is a spatial pyramid pooling layer, and the output result of the pooling layer is used as the input of the fully connected layer; the convolution layer includes N layers, and the output result of the i-th convolution layer is the input of the i+1-th convolution layer, and the output result of the N-th convolution layer is processed by the activation function layer as the input of the pooling layer, wherein N and i are positive integers, and i is less than N.

[0045] That is to say, the feature extraction unit can be implemented by a deep neural network. In an exemplary embodiment, the feature extraction unit can be a convolutional neural network (CNN), for example, the feature extraction unit can be an AlexNet network.

[0046] For example, Figure 3 As shown, the feature extraction unit may include an input layer (input), a convolution layer (Cnov), an activation function layer (Relu), a pooling layer (Pool) and a fully connected layer (FC). In which, exemplarily, the feature extraction unit (such as the convolution layer in the feature extraction unit) may satisfy one or more of the following: the number of convolution kernels 2 n, the size of the convolution kernel is 3*1, the step size (that is, the step size of the convolution) is set to 1, and the padding is set to 1; where n is a positive integer. Here, the convolution kernel (also known as a filter or feature detector) is a small matrix that slides (or convolves) on the input data (such as an image) and calculates the sum of the element products of the convolution kernel and the input data at each position. This process generates a new two-dimensional array, usually called a feature map or activation map, which represents the intensity and position of certain features in the input data. Among them, the step size can refer to the interval at which the convolution kernel moves on the input data, that is, the convolution kernel matrix itself. Padding can refer to adding additional values ​​to the edges of the input data so that the input and output sizes remain consistent. It should be noted that in the embodiments of the present application, the number of convolution kernels, the size of the convolution kernel, the step size of the convolution, the padding, the number of convolution layers, etc. in the feature extraction unit can also be changed according to actual needs.

[0047] In some embodiments, the pooling layer in the feature extraction unit may be a spatial pyramid pooling layer (SPPNet). Exemplarily, the output of the pooling layer may be used as the input of the fully connected layer. In this way, by converting gene expression matrices of different sizes into feature vectors of fixed size, data of different sizes may be processed without changing the gene clustering model, thereby improving the adaptability and generalization of the gene clustering model. In other words, the trained gene clustering model may be applicable to gene expression matrices of different sizes.

[0048] For example, the dimension of the output result of SPPNet can be set to 44 dimensions, so that the dimension of the output result of gene expression matrices of different sizes after being processed by SPPNet is 44 dimensions, and then the output result of SPPNet is input into the fully connected layer for processing to obtain the gene feature matrix. In this way, the feature extraction ability of the gene clustering model under different sample sizes can be improved, thereby improving the adaptability and generalization of the gene clustering model.

[0049] In some embodiments, except for the last convolution layer in the feature extraction unit, there may be no pooling layer behind other convolution layers. For example, the feature extraction unit may include N convolution layers, the output result of the i-th convolution layer may be the input of the i+1-th convolution layer, and the output result of the N-th convolution layer may be the input of the pooling layer after being processed by the activation function layer, wherein N and i are positive integers, and i is less than N. In this way, the amount of calculation of the gene clustering model can be effectively reduced.

[0050] The feature extraction unit in the above-mentioned trained gene clustering model performs feature extraction on the target gene expression matrix to obtain a first gene feature matrix. The elements in the first gene feature matrix represent the expression intensity of a specific dimension of the gene in the target gene expression matrix, that is, the elements in the first gene feature matrix are used to measure the characteristic values ​​of a gene in the target gene expression matrix in different dimensions.

[0051] The first gene feature matrix obtained in step 102 can be Figure 4 As shown. Figure 4 In , each row is the feature value of the same gene in different dimensions, and each column is the feature value of different genes in the same dimension. For example, Figure 4 The first gene feature matrix in the total includes p dimensions, that is, each gene contains feature values ​​in p dimensions, there are m genes in each dimension, and each gene corresponds to one feature value. p and m are both positive integers. In some embodiments, p is less than n (n is the number of cells).

[0052] Step 103: constructing a corresponding cell type-specific co-expression network according to the first gene feature matrix and the target gene expression matrix; and / or constructing a global gene co-expression network according to the first gene feature matrix.

[0053] It should be noted that after obtaining the first gene feature matrix, a global gene co-expression network and / or a corresponding cell type-specific co-expression network can be obtained according to demand.

[0054] In some embodiments, for the step 103, the corresponding cell type-specific co-expression network is constructed according to the first gene feature matrix and the target gene expression matrix, such as Figure 5 As shown, it may include: Step 501: determining a second gene feature matrix for each cell type according to the target gene expression matrix and the first gene feature matrix; each row in the second gene feature matrix is ​​a feature value of a gene in the first gene feature matrix in different dimensions, and each column is a feature value of different genes in the same dimension; Step 502: Obtain a corresponding cell type specific module according to the second gene feature matrix of each cell type; Step 503: hierarchical clustering is performed on the genes in each cell type-specific module to obtain the corresponding cell type-specific co-expression network.

[0055] In some embodiments, step 501 may include: obtaining a gene expression matrix of differentially expressed genes contained in each cell type according to the target gene expression matrix; calculating the correlation between the gene expression matrix of differentially expressed genes contained in each cell type and the first gene feature matrix to form a cell-embedded gene correlation matrix of the corresponding cell type; wherein each row in the cell-embedded gene correlation matrix represents the importance of different features in the corresponding cell, and each column represents the importance of the same feature in the corresponding cell; for each cell type, determining the second gene feature matrix of the corresponding cell type according to the cell-embedded gene correlation matrix of the corresponding cell type and the first gene feature matrix.

[0056] Here, the cell type mentioned here may refer to a cell group classified based on specific morphology, function, structure and molecular markers. In biology, the diversity of cell types is the basis of the complexity of organisms. Among them, there are different cell types according to different classification methods. For example, according to morphological structure classification, epithelial cell groups, muscle cell groups, nerve cell groups, etc. can be included. For example, according to functional classification, it can include: photoreceptor cell groups, olfactory cell groups, taste cell groups, etc. The differentially expressed genes (Differential Gene Expression) may refer to genes whose gene expression levels change significantly under different conditions (such as different tissue types, different developmental stages, different environmental pressures or different pathological states, etc.), that is, genes with relatively large expression differences. In some embodiments, a threshold can be set to screen differentially expressed genes. For example, when the gene expression similarity is less than a certain threshold, it is defined as a differentially expressed gene; for example, if the gene expression similarity is greater than a certain threshold, it is defined as an expression-similar gene, and the rest are differentially expressed genes, etc.

[0057] That is to say, for step 501, the gene expression matrix of the differentially expressed genes corresponding to each cell type is first obtained from the target gene expression matrix; then, the correlation between the gene expression matrix of the differentially expressed genes corresponding to each cell type and the first gene feature matrix calculated above is calculated to obtain the cell-embedding gene correlation matrix corresponding to each cell type. Each row in the cell-embedding gene correlation matrix represents the importance of different features in the corresponding cell, and each column represents the importance of the same feature in the corresponding cell; then, for each cell type, the second gene feature matrix of the corresponding cell type is determined according to the cell-embedding gene correlation matrix of the corresponding cell type and the first gene feature matrix.

[0058] Among them, in some embodiments, the gene expression matrix of differentially expressed genes contained in each cell type obtained according to the target gene expression matrix may refer to screening out the gene expression matrix of differentially expressed genes contained in each cell type from the target gene expression matrix.

[0059] In some embodiments, the calculation of the correlation between the gene expression matrix of the differentially expressed genes contained in each cell type and the first gene feature matrix to form a cell-embedded gene correlation matrix for the corresponding cell type may refer to calculating the correlation coefficient (such as the Pearson correlation coefficient) between the gene pairs contained in the corresponding cell type through the gene expression matrix of the differentially expressed genes contained in the cell type and the first gene feature matrix to evaluate the correlation between them, and then combining the gene expression matrix of the differentially expressed genes contained in each cell type with the correlation matrix of the co-expression network based on the correlation to obtain the cell-embedded gene correlation matrix.

[0060] Among them, in some embodiments, for each cell type, determining the second gene feature matrix of the corresponding cell type based on the cell-embedded gene correlation matrix of the corresponding cell type and the first gene feature matrix may include: extracting features of a set dimension from the first gene feature matrix as features of the corresponding cell type based on the cell-embedded gene correlation matrix; and forming the second gene feature matrix based on the extracted features of the corresponding cell type and the genes contained in the first gene feature matrix.

[0061] That is, after obtaining the cell-embedded gene correlation matrix, the second gene feature matrix is ​​determined in combination with the first gene feature matrix. Specifically, the features of the set dimension are extracted from the first gene feature matrix as the features of the corresponding cell type according to the cell-embedded gene correlation matrix. For example, 100 dimensions are extracted as the features of the corresponding cell type; then, the second gene feature matrix is ​​formed according to the extracted features of the corresponding cell type and the genes contained in the first gene feature matrix. For example, the first gene feature matrix contains 1000 genes, so the dimension of the second gene feature matrix is ​​(1000, 100), where 1000 is the number of genes and 100 is the feature dimension.

[0062] Then, in some embodiments, for step 502, as Figure 6 As shown, it may include: Step 601: Calculate the cosine similarity between each gene in the second gene feature matrix; Step 602: performing clustering processing on the second gene feature matrix according to the cosine similarity between the genes to form a first sub-cell type specific module and a second sub-cell type specific module; Step 603: Calculate a first score of the first sub-cell type-specific module and a second score of the second sub-cell type-specific module; Step 604: Compare the first score and the second score; wherein, in response to the first score being greater than the second score, determine the first sub-cell type-specific module as the corresponding cell type-specific module; in response to the first score being less than the second score, determine the second sub-cell type-specific module as the corresponding cell type-specific module; in response to the first score being equal to the second score, determine the first sub-cell type-specific module or the second sub-cell type-specific module as the corresponding cell type-specific module.

[0063] It should be noted that the first two steps in step 502: the manner of obtaining the first sub-cell type specific module and the second sub-cell type specific module is similar to the steps of steps 701 and 702 described later, and the details are not repeated here. Only one point needs to be explained, the number of clusters here is set to 2, that is, the first sub-cell type specific module and the second sub-cell type specific module are formed by clustering.

[0064] In some embodiments, the calculation of the first score of the first sub-cell type-specific module and the second score of the second sub-cell type-specific module in step 502 may include: calculating a first relative expression level of each differentially expressed gene in the first sub-cell type-specific module in different cells; and calculating the first score based on each of the first relative expression levels and the number of genes included in the first sub-cell type-specific module; and calculating a second relative expression level of each differentially expressed gene in the second sub-cell type-specific module in different cells; and calculating the second score based on each of the second relative expression levels and the number of genes included in the second sub-cell type-specific module.

[0065] It should be noted that the so-called cell type specificity refers to the differences in gene expression levels between different cell types, which reflect the functions and characteristics of different cell types. Cell type-specific gene expression patterns are of great significance for understanding cell development, tissue function and disease mechanisms.

[0066] This embodiment of the application defines a new cell type specific score to screen the cell type specific module, and the specific steps are as follows: The first step is to calculate the relative expression levels of genes in different cells. For example, the relative expression level of gene g is the expression level of gene g in cell c divided by the sum of the expression levels of gene g in all cells of this cell type. The calculation formula is as follows: (1) in, represents the expression level of gene g in cell c, and C represents the total number of cells contained in a certain cell type. Represents the relative expression level of gene g in cell c.

[0067] The second step is to calculate the cell type specificity scores in different sub-cell type specificity modules, that is, the first score or the second score. Specifically, the sum of the cell type specificity scores of all genes in the sub-cell type specificity module is divided by the number of genes in the sub-cell type specificity module to obtain the cell type specificity score of the sub-cell type specificity module. The calculation formula is as follows: (2) in, represents the expression level of gene g in cell type t, That is, the sum of the relative expression levels of the genes calculated previously in different cells. m | represents the total number of genes in module m. The cell type specificity score of the sub-cell type specificity module is represented, that is, the first score or the second score. That is, the first score and the second score are calculated according to the above two steps.

[0068] After obtaining the first score of the first sub-cell type-specific module and the second score of the second sub-cell type-specific module, the first score and the second score are compared. When the first score is greater than the second score, the first sub-cell type-specific module is determined to be the corresponding cell type-specific module; if the first score is less than the second score, the second sub-cell type-specific module is determined to be the corresponding cell type-specific module. If the first score is equal to the second score, the first sub-cell type-specific module or the second sub-cell type-specific module is determined to be the corresponding cell type-specific module. That is, the cell type-specific scores of different sub-cell type-specific modules are compared, and the sub-cell type-specific module with a higher score is selected as the specific module of the cell type.

[0069] Afterwards, hierarchical clustering is performed on the screened cell type-specific modules to obtain the corresponding cell type-specific co-expression network. Among them, the cell type-specific co-expression network refers to the network formed by gene sets with similar gene expression patterns in a specific cell type. This network can help understand the uniqueness and function of different cell types at the gene expression level.

[0070] In other embodiments, the so-called global gene co-expression network (Global Gene Co-expression Network) can be a bioinformatics analysis method for studying the interaction and coordinated expression patterns between genes. This method can help us understand the function and regulatory network of genes in different biological processes. In the global gene co-expression network, each gene is represented as a node in the network, and the edge (connecting line) between the nodes represents the co-expression relationship between genes. These relationships are usually determined by calculating the correlation coefficient of gene expression data, such as Pearson correlation coefficient or Spearman correlation coefficient. The weight of the edge in the network can reflect the intensity of the co-expression relationship, and the higher the weight, the more similar the expression patterns of two genes are. That is, the co-expression network between each gene in the gene expression matrix is ​​obtained according to the first gene feature matrix.

[0071] In some embodiments, for the step 103 of constructing a global gene co-expression network according to the first gene feature matrix, Figure 7 As shown, it may include: Step 701: Calculate the co-expression relationship between genes according to the first gene feature matrix to obtain a gene co-expression correlation matrix; Step 702: hierarchically clustering the genes in the gene co-expression correlation matrix to construct the global gene co-expression network; the global gene co-expression network has a tree structure, wherein each branch of the tree structure includes a gene co-expression module; the gene co-expression module includes a group of genes with similar expression patterns.

[0072] That is, constructing the global gene co-expression network based on the first gene feature may include the following two steps: calculating the co-expression relationship between the genes in the aforementioned target gene co-expression matrix according to the first gene feature matrix obtained previously, and obtaining the gene co-expression correlation matrix, that is, step 701; then, hierarchical clustering is performed on the genes in the gene co-expression correlation matrix to obtain the global gene co-expression network, that is, step 702. Hierarchical clustering is a commonly used clustering analysis method, which does not require the number of clusters to be specified in advance, but constructs a clustering tree (called a dendrogram or dendrogram) composed of levels by stepwise merging or splitting. That is to say, the global gene co-expression network has a tree structure, and each branch of the tree structure includes a gene co-expression module; the gene co-expression module includes a group of genes with relatively high similar expression patterns. In implementation, a group of genes with relatively high similar expression patterns can be determined by a threshold.

[0073] Here, each row of the first gene feature matrix represents the eigenvalue of the same gene in different dimensions, and each column represents the eigenvalues ​​of different genes in the same dimension; step 701 may include: calculating the cosine similarity between genes in the first gene feature matrix; the cosine similarity is used to measure the co-expression relationship between genes; and obtaining the gene co-expression correlation matrix according to the obtained cosine similarity between each gene.

[0074] That is, the co-expression relationship between genes is calculated using cosine similarity to obtain the gene co-expression correlation matrix. The so-called cosine similarity is a similarity measurement method for measuring the angle between two vectors. It is determined by calculating the ratio of the dot product of the two vectors and the product of their modules. The range of cosine similarity is from -1 to 1, where 1 represents the exact same direction of the vectors, -1 represents the exact opposite direction, and 0 represents that the vectors are orthogonal, i.e., there is no correlation. In the present application, two vectors can refer to any two rows in the first gene feature matrix.

[0075] Among them, the calculation formula of cosine similarity is as follows: Cosine Similarity = (A⋅B) / (||A||*||B||).

[0076] Where: A⋅B is the dot product of vectors A and B; ||A|| is the modulus (or norm) of vector A; ||B|| is the modulus (or norm) of vector B.

[0077] In some embodiments, step 602 may include: setting the number of genes included in the minimum gene module, gradually processing the data in the gene co-expression correlation matrix according to the dynamic cutting tree strategy to form at least one gene co-expression module; and recording each obtained gene co-expression module to construct the global gene co-expression network.

[0078] Here, the number of genes contained in the set minimum gene module can be the minimum unit of the specified gene module. For example, if the number of genes contained in the set minimum gene module is 10, then the clustered gene module contains at least 10 genes. The dynamic cutting tree strategy is a method for identifying gene modules in weighted gene co-expression network analysis (WGCNA). Therefore, for step 602, a global gene co-expression network can be constructed according to the dynamic cutting tree strategy.

[0079] The gene co-expression network establishment method provided in the embodiment of the present application, by converting a high-dimensional and sparse single-cell gene expression matrix into a low-dimensional gene feature matrix, to construct a global gene co-expression network or a cell type-specific co-expression network, realizes matrix decoupling, so as to avoid directly constructing a network based on sparse single-cell data, and improve the accuracy of co-expression calculation. That is, the embodiment of the present application provides a decoupled feature learning framework (DeepCSCN) to construct a cell type-specific gene co-expression network (that is, the aforementioned cell type-specific co-expression network). Among them, DeepCSCN can infer a cell type-specific co-expression network from a large-scale sample by decoupling cell type features (that is, separating feature dimensions related to different cell types). DeepCSCN has the following innovations and advantages: (1) Effective feature extraction: DeepCSCN uses a deep clustering model (that is, GeneCluster, that is, the aforementioned trained gene clustering model) to extract gene features, solves the sparsity problem of scRNA-seq data, and improves the accuracy of gene correlation calculation. (2) Higher accuracy: Compared with existing methods, DeepCSCN has higher co-expression prediction accuracy and can identify more cell type-specific gene modules. (3) Global to local network construction: DeepCSCN first uses the embedding features of all genes to construct a global gene co-expression network; then decouples the embedding of specific cell types to construct a co-expression network for specific cell types.

[0080] In order to understand the present application, examples are provided below for illustration.

[0081] Among them, the gene co-expression network establishment method process can be as follows: (1) Data collection and preprocessing In this application, we obtained a total of 8 single-cell datasets from Single Cell Protal, including 4 mouse cortical data and 4 human peripheral blood mononuclear data (PBMC). In the following description, we mainly take the human PBMC1drop-seq dataset as an example, which includes 9 cell types, a total of 10,802 cells and 22,792 genes. The dataset was first preliminarily filtered by the python package scanpy to filter genes and cells, and then 1,000 highly variable genes were screened, and the original count matrix was normalized to obtain the gene expression matrix. The data in the gene expression matrix was then input into GeneCluster for training to obtain the first gene feature matrix.

[0082] (2) Model training, obtaining the first gene feature matrix The data in the preprocessed gene expression matrix is ​​input into the GeneCluster model for feature extraction to obtain a first gene feature matrix, wherein the dimension of the first gene feature matrix is ​​(1000, 2048).

[0083] (3) Construction of global gene co-expression network The gene feature matrix of the PBMC1 drop-seq dataset extracted by the GeneCluster model was used to calculate the correlation matrix between genes based on cosine similarity, and hierarchical clustering was performed on the correlation matrix to obtain the global gene co-expression module of the PBMC1 drop-seq dataset. Finally, after experiments, a total of 25 global gene co-expression modules were identified in this dataset. Then we associated different gene modules with cell types and found that module 1 was significantly associated with CD16+ monocytes and dendritic cells, module 2 was significantly associated with megakaryocytes, module 3 was significantly associated with cytotoxic T cells, dendritic cells and natural killer cells, module 5 was significantly associated with plasmacytoid dendritic cells, and module 8 was significantly associated with B cells.

[0084] (4) Construction of cell type-specific co-expression networks Although the global gene co-expression network can associate gene modules with cell types, it is impossible to accurately assign each module to a specific cell type. The construction of the cell type-specific network of the PBMC1 drop-seq dataset is mainly divided into three steps. In the first step, we first generate a correlation matrix to quantify the importance of gene representation in identifying different cell types. This is done by first extracting the differentially expressed genes in different cell types of the dataset, calculating the correlation between the gene expression matrix of these differentially expressed genes and the gene feature matrix, and obtaining the cell-embedding correlation matrix with a dimension of (10802, 2048); in the second step, the top 100-dimensional features of a specific cell type (such as B cells, with a cell number of 477) are extracted as the features of B cells with a dimension of (477, 100). Based on the gene features (1000, 100) of all genes in the specific cell type B cells, the cosine similarity is calculated and clustered, and the B cell-specific module is screened using the cell type-specific score. Finally, the B cell-specific module we screened contains a total of 182 genes. The genes of the module were then clustered again (182, 100), and finally a total of 4 specific B cell co-expression modules were identified. GO enrichment analysis was run on each module, and it was found that module 1 was mainly enriched in "MHC protein complex binding", module 2 was mainly enriched in "B cell activation", and module 3 was mainly enriched in "immunoglobulin receptor binding functions". The same data set was applied to sclink and CS-CORE for comparison. In the identification of B cell gene co-expression modules, CS-CORE identified a total of 4 B cell functional modules, but only one module was related to B cells; sclink did not identify B cell-related functional modules. Therefore, compared with other cell type-specific network construction methods, DeepCSCN can identify more and more relevant functional pathways.

[0085] (5) Comparison of different gene co-expression methods We compared different gene co-expression methods, including pearson, spearman, GENIE3, minet, PIDC, sclink, glasso, and CS-CORE. Taking the PBMC1 drop-seq dataset as an example, we used AUPRC and AUROC as evaluation indicators for different co-expression methods. AUROC is a curve plot of false positive rate (FDR) and true positive rate (TPR), and AUPRC is the area under the curve surrounded by recall and precision. We first screened 400 highly variable genes for comparison, calculated the gene correlation matrix of different co-expression methods, and calculated the AUPRC and AUROC scores of different methods based on this matrix. We found that in the PBMC1 drop-seq dataset, the AUPRC scores of pearson, spearman, GENIE3, minet, PIDC, sclink, glasso, CS-CORE and DeepCSCN were 0.50, 0.48, 0.40, 0.07, 0.48, 0.51, 0.18, 0.20, and 0.60, respectively. Their AUROC scores were 0.89, 0.89, 0.74, 0.30, 0.88, 0.89, 0.54, 0.59, and 0.91, respectively. Therefore, when DeepCSCN is compared with other methods, DeepCSCN has the highest AUPRC and AUROC scores, which effectively improves the accuracy of co-expression prediction.

[0086] like Figure 8 As shown, the present application embodiment provides a schematic diagram of the structure of a gene co-expression network establishment device. Figure 8 In the embodiment, the co-expression network establishing device 800 may include: The acquisition module 801 is used to acquire a target gene expression matrix; the elements in the target gene expression matrix are used to measure the expression level of a certain gene in a certain cell; An extraction module 802 is used to perform feature extraction on the target gene expression matrix to obtain a first gene feature matrix; the elements in the first gene feature matrix are used to measure the feature values ​​of genes in the target gene expression matrix in different dimensions; Construction module 803 is used to construct a corresponding cell type-specific co-expression network according to the first gene feature matrix and the target gene expression matrix; and / or to construct a global gene co-expression network according to the first gene feature matrix.

[0087] In some embodiments, the construction module 803 is also used to: determine a second gene feature matrix for each cell type based on the target gene expression matrix and the first gene feature matrix; each row in the second gene feature matrix is ​​the eigenvalue of the genes in the first gene feature matrix in different dimensions, and each column is the eigenvalue of different genes in the same dimension; obtain the corresponding cell type-specific module based on the second gene feature matrix of each cell type; perform hierarchical clustering on the genes in each cell type-specific module to obtain the corresponding cell type-specific co-expression network.

[0088] In some embodiments, the construction module 803 is also used to: obtain a gene expression matrix of differentially expressed genes contained in each cell type according to the target gene expression matrix; calculate the correlation between the gene expression matrix of differentially expressed genes contained in each cell type and the first gene feature matrix to form a cell-embedded gene correlation matrix of the corresponding cell type; wherein each row in the cell-embedded gene correlation matrix represents the importance of different features in the corresponding cell, and each column represents the importance of the same feature in the corresponding cell; for each cell type, determine the second gene feature matrix of the corresponding cell type according to the cell-embedded gene correlation matrix of the corresponding cell type and the first gene feature matrix.

[0089] In some embodiments, the construction module 803 is further used to: extract features of a set dimension from the first gene feature matrix as features of the corresponding cell type according to the cell-embedded gene correlation matrix; and form the second gene feature matrix according to the extracted features of the corresponding cell type and the genes included in the first gene feature matrix.

[0090] In some embodiments, the construction module 803 is also used to: calculate the cosine similarity between each gene in the second gene feature matrix; cluster the second gene feature matrix according to the cosine similarity between each gene to form a first sub-cell type-specific module and a second sub-cell type-specific module; calculate a first score of the first sub-cell type-specific module and a second score of the second sub-cell type-specific module; compare the first score and the second score; wherein, in response to the first score being greater than the second score, determining the first sub-cell type-specific module as the corresponding cell type-specific module; in response to the first score being less than the second score, determining the second sub-cell type-specific module as the corresponding cell type-specific module; in response to the first score being equal to the second score, determining the first sub-cell type-specific module or the second sub-cell type-specific module as the corresponding cell type-specific module.

[0091] In some embodiments, the construction module 803 is also used to: calculate the first relative expression level of each gene in the first sub-cell type-specific module in different cells; and calculate the first score based on each of the first relative expression levels and the number of genes included in the first sub-cell type-specific module; and calculate the second relative expression level of each gene in the second sub-cell type-specific module in different cells; and calculate the second score based on each of the second relative expression levels and the number of genes included in the second sub-cell type-specific module.

[0092] In some embodiments, the construction module 803 is also used to: calculate the co-expression relationship between each gene based on the first gene feature matrix to obtain a gene co-expression correlation matrix; hierarchically cluster the genes in the gene co-expression correlation matrix to construct the global gene co-expression network; the global gene co-expression network has a tree structure, wherein each branch of the tree structure includes a gene co-expression module; the gene co-expression module includes a group of genes with similar expression patterns.

[0093] In some embodiments, each row of the first gene feature matrix represents the feature value of the same gene in different dimensions, and each column represents the feature values ​​of different genes in the same dimension; the construction module 803 is also used to: calculate the cosine similarity between genes in the first gene feature matrix; the cosine similarity is used to measure the co-expression relationship between genes; and obtain the gene co-expression correlation matrix based on the cosine similarity between the genes obtained.

[0094] In some embodiments, the construction module 803 is also used to: set the number of genes included in the minimum gene module, gradually process the data in the gene co-expression correlation matrix according to the dynamic cutting tree strategy to form at least one gene co-expression module; record each obtained gene co-expression module to construct the global gene co-expression network.

[0095] In some embodiments, the acquisition module 801 is specifically used to: acquire a single-cell transcriptome sequencing (scRNA-seq) dataset of at least one biological sample, and generate a sub-expression matrix of genes contained in the corresponding biological sample according to each scRNA-seq dataset; pre-process at least one of the sub-expression matrices to obtain the target gene expression matrix.

[0096] In some embodiments, the extraction module 802 is specifically used to: use the feature extraction unit included in the trained gene clustering model to perform feature extraction on the target gene expression matrix to obtain the first gene feature matrix; wherein the feature extraction unit includes an input layer, a convolution layer, an activation function layer, a pooling layer and a fully connected layer, the pooling layer is a spatial pyramid pooling layer, and the output result of the pooling layer is used as the input of the fully connected layer; the convolution layer includes N layers, and the output result of the i-th convolution layer is the input of the i+1-th convolution layer, and the output result of the N-th convolution layer is processed by the activation function layer as the input of the pooling layer, wherein N and i are positive integers, and i is less than N.

[0097] It should be noted that the gene co-expression network establishment device provided in the embodiment of the present application is a device for implementing the aforementioned co-expression network establishment method. Therefore, the technical features appearing here have been described in detail in the above description of the co-expression network establishment method. Please refer to the previous description for understanding. In order to save space, it is meaningless to repeat them here.

[0098] On one hand, the present application provides a device for establishing a gene co-expression network, comprising a processor for calling a program in a memory so that the device executes any of the methods described above.

[0099] On one hand, the present application provides a chip, including a processor, for calling a program from a memory so that a device equipped with the chip executes any of the methods described above.

[0100] On one hand, the present application provides a computer-readable storage medium having a program stored thereon, wherein the program is a computer that actively executes any of the methods described above.

[0101] Fig. 9 It is a schematic block diagram of a device 900 according to an embodiment of the present application. Fig. 9 The device 900 shown includes a memory 901 , a processor 902 , a communication interface 903 and a bus 904 . The memory 901 , the processor 902 , and the communication interface 903 are connected to each other through the bus 904 .

[0102] The memory 901 may be a graphics processing unit (GPU) storage system, a read-only memory (ROM), a static storage device, a dynamic storage device and / or a random access memory (RAM). The memory 901 may store programs. When the programs stored in the memory 901 are executed by the processor 902, the processor 902 is used to execute the various steps of the method of the embodiment of the present application. For example, the aforementioned Figure 1 , Figure 5 , Figure 6 , Figure 7 The various steps of the embodiments shown in the figure.

[0103] The processor 902 can adopt a graphics processing unit (GPU), a neural network processing unit (NPU), a microprocessor, an application specific integrated circuit (ASIC), and / or one or more integrated circuits to execute relevant programs to implement the method of the method embodiment of the present application.

[0104] The processor 902 may also be an integrated circuit chip with signal processing capability. In the implementation process, each step of the method of the embodiment of the present application may be completed by hardware integrated logic circuits in the processor 902 and / or software instructions.

[0105] The processor 902 may also be a general purpose processor, a digital signal processor (DSP), a dedicated integrated circuit, a field programmable gate array (FPGA), and / or other programmable logic devices, discrete gates and / or transistor logic devices, and discrete hardware components. The methods, steps, and logic block diagrams disclosed in the embodiments of the present application may be implemented and / or executed. The general purpose processor may be a microprocessor and / or the processor may also be any conventional processor, etc.

[0106] The steps of the method disclosed in the embodiments of the present application can be directly embodied as being executed by a hardware decoding processor, and / or being executed by a combination of hardware and software modules in the decoding processor. The software module can be located in a storage medium mature in the art, such as a random access memory, a flash memory, a read-only memory, a programmable read-only memory and / or an electrically erasable programmable memory, a register, etc. The storage medium is located in the memory 901, and the processor 902 reads the information in the memory 901, and combines its hardware to complete the functions required to be executed by the units included in the embodiments of the present application, and / or execute the methods of the various method embodiments in the present application, for example, it can execute Figure 1 , Figure 5 , Figure 6 and Figure 7 etc. The various steps / functions of the embodiments shown.

[0107] The communication interface 903 may use, but is not limited to, a transceiver or other transceiver device to implement communication between the device 900 and other devices or a communication network.

[0108] The bus 904 may include a path for transmitting information between various components of the device 900 (eg, the memory 901 , the processor 902 , and the communication interface 903 ).

[0109] It should be understood that the device 900 shown in the embodiment of the present application may be a processor or a chip for executing the method described in the embodiment of the present application.

[0110] It should be understood that in the embodiment of the present application, the processor may be a graphics processing unit (GPU), and the processor may also be a digital signal processor (DSP), an application specific integrated circuit (ASIC), a field programmable gate array (FPGA) and / or other programmable logic devices, discrete component gate circuits and / or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor and / or the processor may also be any conventional processor, etc.

[0111] It should be understood that in the embodiment of the present application, "B corresponding to A" means that B is associated with A, and B can be determined according to A. However, it should also be understood that determining B according to A does not mean determining B only according to A, and B can also be determined according to A and / or other information.

[0112] It should be understood that the term "and / or" in this article is only a description of the association relationship of the associated objects, indicating that there can be three relationships. For example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone. In addition, the character " / " in this article generally indicates that the associated objects before and after are in an "or" relationship.

[0113] It should be understood that in the various embodiments of the present application, the size of the serial numbers of the above-mentioned processes does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0114] In the several embodiments provided in the present application, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined and / or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0115] The units described as separate components may and / or may not be physically separated, and the components shown as units may and / or may not be physical units, that is, they may be located in one place and / or may be distributed on multiple network units. Some and / or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0116] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0117] In the above embodiments, it can be implemented in whole or in part by software, hardware, firmware and / or any combination thereof. When implemented using software, it can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, the process or function described in the embodiment of the present application is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, and / or other programmable devices. The computer instructions may be stored in a computer-readable storage medium and / or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions may be transmitted from one website, computer, server or data center to another website, computer, server or data center via wired (e.g., coaxial cable, optical fiber, digital subscriber line (DSL, Digital Subscriber Line)) or wireless (e.g., infrared, wireless, microwave, etc.) means. The computer-readable storage medium may be any available medium that can be read by a computer and / or a data storage device such as a server or data center that includes one or more available media integrated therein. The available medium may be a magnetic medium (e.g., a floppy disk, a hard disk, a magnetic tape), an optical medium (e.g., a digital versatile disc (DVD, Digital Video Disk)) and / or a semiconductor medium (e.g., a solid state drive (SSD, Solid State Disk), etc.

[0118] The above description is only a preferred embodiment of the present application and is not intended to limit the present application. Any modifications, equivalent substitutions, etc. made within the spirit and principles of the present application shall be included in the protection scope of the present application.

Claims

1. A method for establishing a gene co-expression network, characterized in that: include: Obtain the target gene expression matrix; The elements in the target gene expression matrix are used to measure the expression level of a gene in a cell; Performing feature extraction on the target gene expression matrix to obtain a first gene feature matrix; the elements in the first gene feature matrix are used to measure the feature values ​​of genes in the target gene expression matrix in different dimensions; A corresponding cell type-specific co-expression network is constructed according to the first gene feature matrix and the target gene expression matrix; and / or a global gene co-expression network is constructed according to the first gene feature matrix.

2. The method according to claim 1, characterized in that The step of constructing a cell type-specific co-expression network according to the first gene feature matrix and the target gene expression matrix comprises: Determine a second gene feature matrix for each cell type according to the target gene expression matrix and the first gene feature matrix; each row in the second gene feature matrix is ​​a feature value of a gene in the first gene feature matrix in different dimensions, and each column is a feature value of different genes in the same dimension; Obtaining a corresponding cell type-specific module according to the second gene feature matrix of each cell type; The genes in each cell type-specific module were hierarchically clustered to obtain the corresponding cell type-specific co-expression network.

3. The method according to claim 2, characterized in that The step of determining a second gene feature matrix for each cell type according to the target gene expression matrix and the first gene feature matrix includes: Obtaining a gene expression matrix of differentially expressed genes contained in each cell type according to the target gene expression matrix; Calculating the correlation between the gene expression matrix of the differentially expressed genes contained in each cell type and the first gene feature matrix to form a cell-embedded gene correlation matrix of the corresponding cell type; wherein each row in the cell-embedded gene correlation matrix represents the importance of different features in the corresponding cell, and each column represents the importance of the same feature in the corresponding cell; For each cell type, the second gene feature matrix of the corresponding cell type is determined according to the cell-embedded gene correlation matrix of the corresponding cell type and the first gene feature matrix.

4. The method according to claim 3, characterized in that The determining the second gene feature matrix of the corresponding cell type according to the cell-embedded gene correlation matrix of the corresponding cell type and the first gene feature matrix comprises: Extracting features of a set dimension from the first gene feature matrix as features of the corresponding cell type according to the cell-embedded gene correlation matrix; The second gene feature matrix is ​​formed according to the extracted features of the corresponding cell type and the genes included in the first gene feature matrix.

5. The method according to claim 2, characterized in that: The step of obtaining a corresponding cell type specific module according to the second gene feature matrix of each cell type comprises: Calculating the cosine similarity between each gene in the second gene feature matrix; Performing clustering processing on the second gene feature matrix according to the cosine similarity between the genes to form a first sub-cell type specific module and a second sub-cell type specific module; calculating a first score for the first sub-cell type-specific module and a second score for the second sub-cell type-specific module; Compare the first score and the second score; wherein, in response to the first score being greater than the second score, determine the first sub-cell type-specific module as the corresponding cell type-specific module; in response to the first score being less than the second score, determine the second sub-cell type-specific module as the corresponding cell type-specific module; in response to the first score being equal to the second score, determine the first sub-cell type-specific module or the second sub-cell type-specific module as the corresponding cell type-specific module.

6. The method according to claim 5, characterized in that The calculating a first score of the first sub-cell type-specific module and a second score of the second sub-cell type-specific module comprises: Calculating a first relative expression level of each gene in the first sub-cell type-specific module in different cells; and calculating the first score according to each of the first relative expression levels and the number of genes included in the first sub-cell type-specific module; and calculating a second relative expression level of each gene in the second sub-cell type-specific module in different cells; and calculating the second score according to each of the second relative expression levels and the number of genes included in the second sub-cell type-specific module.

7. The method according to claim 1, characterized in that The constructing a global gene co-expression network according to the first gene feature matrix comprises: Calculate the co-expression relationship between each gene according to the first gene feature matrix to obtain a gene co-expression correlation matrix; The genes in the gene co-expression correlation matrix are hierarchically clustered to construct the global gene co-expression network; the global gene co-expression network has a tree structure, wherein each branch of the tree structure includes a gene co-expression module; the gene co-expression module includes a group of genes with similar expression patterns.

8. The method according to claim 7, characterized in that Each row of the first gene feature matrix represents the feature value of the same gene in different dimensions, and each column represents the feature values ​​of different genes in the same dimension; The step of calculating the co-expression relationship between the genes according to the first gene feature matrix to obtain a gene co-expression correlation matrix includes: Calculating the cosine similarity between genes in the first gene feature matrix; the cosine similarity is used to measure the co-expression relationship between genes; The gene co-expression correlation matrix is ​​obtained according to the cosine similarity between the obtained genes.

9. The method according to claim 7, characterized in that: The step of performing hierarchical clustering on the genes in the gene co-expression correlation matrix to construct the global gene co-expression network comprises: The number of genes included in the minimum gene module is set, and the data in the gene co-expression correlation matrix is ​​gradually processed according to the dynamic cutting tree strategy to form at least one gene co-expression module; each obtained gene co-expression module is recorded to construct the global gene co-expression network.

10. The method according to claim 1, characterized in that The step of obtaining the target gene expression matrix comprises: Obtaining a single-cell transcriptome sequencing scRNA-seq dataset of at least one biological sample, and generating a sub-expression matrix of genes included in the corresponding biological sample according to each scRNA-seq dataset; Preprocessing is performed on at least one of the sub-expression matrixes to obtain the target gene expression matrix.

11. The method according to claim 10, characterized in that The preprocessing includes at least one of the following: quality control, screening of highly variable genes, and data normalization.

12. The method according to claim 1, characterized in that The step of extracting features from the target gene expression matrix to obtain a first gene feature matrix includes: The feature extraction unit included in the trained gene clustering model is used to extract features from the target gene expression matrix to obtain the first gene feature matrix; wherein the feature extraction unit includes an input layer, a convolution layer, an activation function layer, a pooling layer and a fully connected layer, the pooling layer is a spatial pyramid pooling layer, and the output result of the pooling layer is used as the input of the fully connected layer; the convolution layer includes N layers, and the output result of the i-th convolution layer is the input of the i+1-th convolution layer, and the output result of the N-th convolution layer is processed by the activation function layer as the input of the pooling layer, wherein N and i are positive integers, and i is less than N.

13. A gene co-expression network establishment device, characterized in that: include: An acquisition module is used to obtain the target gene expression matrix; The elements of the target gene expression matrix are used to measure the expression level of a gene in a cell; An extraction module is used to extract features from the target gene expression matrix to obtain a first gene feature matrix; The elements in the first gene feature matrix are used to measure the characteristic values ​​of genes in the target gene expression matrix in different dimensions; A construction module is used to construct a corresponding cell type-specific co-expression network according to the first gene feature matrix and the gene expression matrix; and / or to construct a global gene co-expression network according to the first gene feature matrix.

14. A gene co-expression network establishment device, characterized in that: The device comprises a processor, configured to call a program from a memory so as to enable the device to execute the method according to any one of claims 1 to 12.

15. A chip, characterized in that: The device comprises a processor, which is used to call a program from a memory, so that a device equipped with the chip executes the method according to any one of claims 1 to 12.

16. A computer-readable storage medium, characterized in that: A program is stored thereon, and the program enables a computer to execute the method according to any one of claims 1 to 12.

17. A computer program product, characterized in that The method comprises a program which causes a computer to execute the method according to any one of claims 1 to 12.

Images