A method and device for analyzing intercellular communication based on graph convolutional networks

Abstract

A method and device for analyzing intercellular communication based on a graph convolutional network, which constructs an initial feature matrix of ligands and receptors based on the digital features of ligands and receptors; collects initial ligand-receptor interaction pairs of proteins and constructs a ligand-receptor interaction adjacency matrix; constructs a ligand-receptor interaction prediction network model based on the graph convolutional network, performs prediction processing after training, and obtains predicted ligand-receptor interaction pairs with interactions; identifies and filters single-cell RNA sequencing data to obtain ligand-receptor interaction pairs that meet set requirements; obtains cell-cell communication intensity by cell-cell communication score calculation and three-point estimation method measurement; constructs a cell-cell communication heat map and performs visual analysis based on the cell-cell communication intensity. The present invention can obtain relatively accurate cell-cell communication analysis results while reducing costs and provide multiple visualizations.

Description

Technical Field

[0001] The present invention relates to the field of intercellular communication technology, and in particular to an intercellular communication analysis method and device based on a graph convolutional network. Background Art

[0002] Cell-cell communication is crucial for the development and homeostasis of multicellular organisms and plays a key role in many biological processes. For example, tumor-associated macrophages and carcinogenesis-associated fibroblasts play important roles in disease progression within the tumor microenvironment. Therefore, comprehensive analysis of cell-cell communication during disease development and progression can improve our understanding of disease mechanisms and help identify new therapeutic strategies.

[0003] Cell-cell communication is often facilitated by interactions between different proteins, such as receptor-receptor interactions, extracellular matrix-receptor interactions, and ligand-receptor interactions. Specifically, the communication between two cells can be quantified by examining all the ligand-receptor interactions involved in regulating this process.

[0004] Currently, studying cell-cell communication using traditional experimental methods is time-consuming, labor-intensive, and costly. Advances in single-cell RNA sequencing data have led to the development of various computational approaches. The process of analyzing and inferring cell-cell communication through computational methods consists of two main steps: screening for ligand-receptor interactions and measuring the strength of cell-cell communication mediated by these interactions. By establishing a comprehensive and reliable database of ligand-receptor interactions, LRI resources can be leveraged to measure the strength of cell-cell communication. Extensive research efforts have been devoted to constructing high-quality LRI databases. CellPhoneDB employs a permutation approach to calculate LRI scores based on ligand and receptor expression and uses these scores to assess the specificity of LRIs. iTALK first identifies highly or differentially expressed genes and then uses its ligand-receptor database to match and correlate these genes, thereby detecting significant LRIs. Furthermore, CellDialog takes protein features as input, reduces their dimensionality using feature selection methods based on tree boosting and mixed-effect models, and finally predicts LRIs using the KTBoost algorithm. With the development of these ligand-receptor interaction databases, numerous cell-cell communication inference methods have been developed using these databases. For example, CellPhoneDB identifies cell-cell communication by detecting ligand-receptor interactions that are highly enriched between cell types, and NATMI constructs complex network models to evaluate cell-cell communication mediated by ligand-receptor interactions. Graph convolutional networks, by performing convolution operations within a graph structure, can capture the relationships and features between nodes and their neighbors, identifying ligand-receptor interactions with higher accuracy, thereby building a more comprehensive and reliable ligand-receptor interaction database. This ligand-receptor interaction resource can then be used for cell-cell communication analysis.

[0005] Therefore, how to design a method based on graph convolutional networks to analyze cell-cell communication mediated by ligand-receptor interactions, while reducing costs and realizing visualization of cell-cell communication analysis, has become an urgent problem to be solved. Summary of the Invention

[0006] To this end, the present invention provides a method and device for analyzing intercellular communication based on a graph convolutional network, which can obtain relatively accurate cell-cell communication analysis results while reducing costs and provide multiple visualizations.

[0007] To achieve the above objectives, the present invention provides the following technical solution: a method for analyzing intercellular communication based on a graph convolutional network, comprising:

[0008] Downloading protein ligand and receptor sequence information from a set database; processing the protein ligand and receptor sequence information through iFeature to obtain digital features of the ligand and receptor; constructing an initial ligand and receptor feature matrix based on the digital features of the ligand and receptor; collecting initial ligand-receptor interaction pairs of the protein and constructing a ligand-receptor interaction adjacency matrix;

[0009] Based on a graph convolutional network, a ligand-receptor interaction prediction network model is constructed; the ligand-receptor interaction prediction network model is trained using the ligand and receptor initial feature matrix and the ligand-receptor interaction adjacency matrix to obtain a trained ligand-receptor interaction prediction network model; and prediction processing is performed using the trained ligand-receptor interaction prediction network model to obtain predicted ligand-receptor interaction pairs with interaction;

[0010] Identifying and filtering the collected initial ligand-receptor interaction pairs and the predicted ligand-receptor interaction pairs through single-cell RNA sequencing data to obtain ligand-receptor interaction pairs that meet set requirements;

[0011] performing a cell-cell communication score calculation on the ligand-receptor interaction pairs that meet the set requirements to obtain expression threshold scores, expression product scores, and cell expression scores of cell-cell communication of several ligand-receptors between cell types; adding several corresponding scores of communication between cell types to obtain expression threshold results, expression product results, and cell expression results of cell-cell communication; and measuring the cell-cell communication intensity using a three-point estimation method based on the expression threshold results, expression product results, and cell expression results of cell-cell communication;

[0012] A cell-cell communication heat map is constructed based on the cell-cell communication intensity; the most active ligand-receptor interaction pairs in the communication between two cell types are analyzed through the cell-cell communication heat map to complete the cell-cell communication visualization analysis.

[0013] As a preferred embodiment of a method for analyzing intercellular communication based on a graph convolutional network, the ligand-receptor interaction prediction network model comprises two graph convolutional layers and three fully connected layers, and skip connections are provided in the convolutional layers;

[0014] The output expression of the convolutional layer with skip connection is:

[0015]

[0016] Where X is the initial feature matrix of the ligand and receptor; A′ is the ligand-receptor interaction adjacency matrix; D is the degree matrix of the interaction adjacency matrix A′; θ, b, b′, W are all learnable parameters; ReLU is the activation function commonly used in deep learning.

[0017] As a preferred embodiment of a method for analyzing intercellular communication based on graph convolutional networks, the calculation formulas for the expression threshold score, expression product score, and cell expression score of the cell-cell communication of the ligand receptor are:

[0018]

[0019] Where, scoring expression thresholds for cell-cell communication; score expression products of cell-cell communication; Cell expression scores for cell-cell communication; A and B are cell types; a is ligand; b is receptor; M a,A is the average expression level of a in cell type A; M b,B is the average expression level of b in cell type B; M a and M b are the average expression levels of ligand a and receptor b in all cells respectively; σ a and σ b are the standard deviations of the expression levels of ligand a and receptor b in all cells, respectively. The result is 1 when both inequalities are satisfied, otherwise it is 0; N a,A is the number of cells in cell type A whose expression value of ligand a is greater than 0; N b,B is the number of cells in cell type B whose expression value of receptor b is greater than 0; N A and N B are the number of cells in cell type A and cell type B, respectively.

[0020] As a preferred embodiment of a method for analyzing intercellular communication based on graph convolutional networks, the expression threshold results, expression product results, and cell expression results of the cell-cell communication are expressed as follows:

[0021]

[0022] Where n is the number of ligand-receptor interaction pairs involved in mediating cell-cell communication.

[0023] As a preferred solution of a method for analyzing intercellular communication based on graph convolutional networks, the expression of the cell-cell communication intensity is:

[0024]

[0025] Where R max 、Rmin and R med They are the maximum, minimum and median values ​​of the standard cell-cell communication results after normalizing the expression threshold results of cell-cell communication, expression product results and cell expression results, respectively.

[0026] The present invention also provides a graph convolutional network-based intercellular communication analysis device, based on the above graph convolutional network-based intercellular communication analysis method, comprising:

[0027] The ligand and receptor initial feature matrix and ligand-receptor interaction adjacency matrix construction module is used to download the protein ligand and receptor sequence information from a set database; process the protein ligand and receptor sequence information through iFeature to obtain the digital features of the ligand and receptor; construct the ligand and receptor initial feature matrix based on the digital features of the ligand and receptor; collect the initial ligand-receptor interaction pairs of the protein and construct the ligand-receptor interaction adjacency matrix;

[0028] A ligand-receptor interaction prediction network model construction and processing module is used to construct a ligand-receptor interaction prediction network model based on a graph convolutional network; the ligand-receptor interaction prediction network model is trained using the ligand and receptor initial feature matrix and the ligand-receptor interaction adjacency matrix to obtain a trained ligand-receptor interaction prediction network model; and prediction processing is performed using the trained ligand-receptor interaction prediction network model to obtain predicted ligand-receptor interaction pairs with interactions.

[0029] A ligand-receptor interaction pair identification and filtering module is used to identify and filter the collected initial ligand-receptor interaction pairs and the predicted ligand-receptor interaction pairs through single-cell RNA sequencing data to obtain ligand-receptor interaction pairs that meet the set requirements;

[0030] a cell-cell communication strength acquisition module, configured to calculate a cell-cell communication score for the ligand-receptor interaction pairs that meet set requirements, and obtain expression threshold scores, expression product scores, and cell expression scores for cell-cell communication of several ligand-receptors between cell types; summing up several corresponding scores for communication between cell types to obtain expression threshold results, expression product results, and cell expression results for cell-cell communication; and obtaining the cell-cell communication strength by measuring the expression threshold results, expression product results, and cell expression results of cell-cell communication using a three-point estimation method;

[0031] The cell-cell communication heat map construction and analysis module is used to construct a cell-cell communication heat map based on the cell-cell communication intensity; analyze the most active ligand-receptor interaction pairs in the communication between two cell types through the cell-cell communication heat map, and complete the cell-cell communication visualization analysis.

[0032] As a preferred embodiment of a cell-to-cell communication analysis device based on a graph convolutional network, in the ligand-receptor interaction prediction network model construction and processing module, the ligand-receptor interaction prediction network model comprises two graph convolutional layers and three fully connected layers, and skip connections are provided in the convolutional layers;

[0033] The output expression of the convolutional layer with skip connection is:

[0034]

[0035] Where X is the initial feature matrix of the ligand and receptor; A′ is the ligand-receptor interaction adjacency matrix; D is the degree matrix of the interaction adjacency matrix A′; θ, b, b′, W are all learnable parameters; ReLU is the activation function commonly used in deep learning.

[0036] As a preferred embodiment of a cell-to-cell communication analysis device based on a graph convolutional network, in the cell-to-cell communication intensity acquisition module, the calculation formulas for the expression threshold score, expression product score, and cell expression score of the ligand receptor cell-to-cell communication are respectively:

[0037]

[0038] Where, scoring expression thresholds for cell-cell communication; score expression products of cell-cell communication; Cell expression scores for cell-cell communication; A and B are cell types; a is ligand; b is receptor; M a,A is the average expression level of a in cell type A; M b,B is the average expression level of b in cell type B; M a and M b are the average expression levels of ligand a and receptor b in all cells respectively; σ a and σ b are the standard deviations of the expression levels of ligand a and receptor b in all cells, respectively. The result is 1 when both inequalities are satisfied, otherwise it is 0; N a,A is the number of cells in cell type A whose expression value of ligand a is greater than 0; N b,B is the number of cells in cell type B whose expression value of receptor b is greater than 0; N A and N Bare the number of cells in cell type A and cell type B, respectively.

[0039] As a preferred embodiment of a cell-to-cell communication analysis device based on a graph convolutional network, in the cell-to-cell communication intensity acquisition module, the expression threshold result, expression product result, and cell expression result of the cell-to-cell communication are respectively:

[0040]

[0041] Where n is the number of ligand-receptor interaction pairs involved in mediating cell-cell communication.

[0042] As a preferred solution of the intercellular communication analysis device based on graph convolutional network, in the cell-cell communication strength acquisition module, the expression of the cell-cell communication strength is:

[0043]

[0044] Where R max 、R min and R med They are the maximum, minimum and median values ​​of the standard cell-cell communication results after normalizing the expression threshold results of cell-cell communication, expression product results and cell expression results, respectively.

[0045] The present invention has the following advantages: downloading protein ligand and receptor sequence information from a set database; processing the protein ligand and receptor sequence information through iFeature to obtain digital features of ligands and receptors; constructing ligand and receptor initial feature matrices based on the digital features of ligands and receptors; collecting initial ligand-receptor interaction pairs of proteins, and constructing a ligand-receptor interaction adjacency matrix; constructing a ligand-receptor interaction prediction network model based on a graph convolutional network; training the ligand-receptor interaction prediction network model through the ligand and receptor initial feature matrix and the ligand-receptor interaction adjacency matrix to obtain the trained ligand-receptor interaction prediction network model; performing prediction processing on the trained ligand-receptor interaction prediction network model to obtain predicted ligand-receptor interaction pairs with interactions; and collecting the ligand-receptor interaction pairs through single-cell RNA sequencing data. The initial ligand-receptor interaction pair and the predicted ligand-receptor interaction pair are identified and filtered to obtain the ligand-receptor interaction pair that meets the set requirements; the ligand-receptor interaction pair that meets the set requirements is subjected to cell-cell communication score calculation to obtain the expression threshold score, expression product score and cell expression score of the cell-cell communication of several ligand receptors between cell types; several corresponding scores of communication between cell types are added to obtain the expression threshold result, expression product result and cell expression result of cell-cell communication; according to the expression threshold result, the expression product result and the cell expression result of cell-cell communication, the cell-cell communication intensity is measured by the three-point estimation method; according to the cell-cell communication intensity, a cell-cell communication heat map is constructed; the most active ligand-receptor interaction pair in the communication between two cell types is analyzed by the cell-cell communication heat map, and cell-cell communication visualization analysis is completed. The present invention measures the cell-cell communication intensity mediated by these ligand-receptor interactions by the identified high-confidence ligand-receptor interaction pairs and single-cell RNA sequencing data, and further performs cell-cell communication analysis. This paper first uses graph convolutional networks, leveraging the multidimensional features of ligands and receptors as initial embeddings, to obtain a more complete, reliable, and well-organized ligand-receptor interaction database for single-cell RNA sequencing data. By filtering the ligand-receptor interaction resource and calculating the cell-cell communication strength using a three-point evaluation method, the paper obtains relatively accurate cell-cell communication analysis results compared to other popular tools and provides multiple visualizations. BRIEF DESCRIPTION OF THE DRAWINGS

[0046] To more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for the embodiments or the description of the prior art. Obviously, the drawings described below are merely exemplary, and those skilled in the art can, without inventive effort, derive other implementation drawings based on the provided drawings.

[0047] The structures, proportions, sizes, etc. illustrated in this specification are intended solely to complement the contents disclosed herein and to facilitate understanding and reading by persons skilled in the art. They are not intended to limit the conditions under which the present invention may be implemented and therefore have no substantive technical significance. Any structural modifications, changes in proportions, or adjustments in sizes, without affecting the efficacy and objectives of the present invention, shall remain within the scope of the technical contents disclosed herein.

[0048] Figure 1 This is a schematic diagram of the flow of a method for analyzing intercellular communication based on a graph convolutional network provided in Example 1 of the present invention;

[0049] Figure 2 This is a schematic diagram of a specific implementation process of a method for analyzing intercellular communication based on a graph convolutional network provided in Example 1 of the present invention;

[0050] Figure 3 This is a schematic diagram of the communication intensity between cell types in human melanoma tissue in a method for analyzing intercellular communication based on a graph convolutional network provided in Example 1 of the present invention;

[0051] Figure 4 Schematic diagram of the three most active ligand-receptor pairs mediating communication between melanoma cancer cells and other cell types in a graph convolutional network-based intercellular communication analysis method provided in Example 1 of the present invention;

[0052] Figure 5 Schematic diagram of the architecture of an intercellular communication analysis device based on a graph convolutional network provided in Example 2 of the present invention. DETAILED DESCRIPTION

[0053] The following describes the implementation of the present invention using specific embodiments. Those skilled in the art will readily understand the other advantages and benefits of the present invention from the disclosure herein. Obviously, the embodiments described are only a portion of the present invention, not all of it. All other embodiments derived by persons of ordinary skill in the art based on the embodiments of the present invention without inventive effort are intended to fall within the scope of protection of the present invention.

[0054] Example 1

[0055] See also Figure 1and Figure 2 Embodiment 1 of the present invention provides a method for analyzing intercellular communication based on a graph convolutional network, comprising the following steps:

[0056] S1. Download the protein ligand and receptor sequence information from a set database; process the protein ligand and receptor sequence information through iFeature to obtain the digital features of the ligand and receptor; construct the ligand and receptor initial feature matrix based on the digital features of the ligand and receptor; collect the initial ligand-receptor interaction pairs of the protein and construct the ligand-receptor interaction adjacency matrix;

[0057] S2. Constructing a ligand-receptor interaction prediction network model based on a graph convolutional network; training the ligand-receptor interaction prediction network model using the initial feature matrix of the ligand and receptor and the ligand-receptor interaction adjacency matrix to obtain a trained ligand-receptor interaction prediction network model; performing prediction processing on the trained ligand-receptor interaction prediction network model to obtain predicted ligand-receptor interaction pairs with interaction;

[0058] S3. Identifying and filtering the collected initial ligand-receptor interaction pairs and the predicted ligand-receptor interaction pairs through single-cell RNA sequencing data to obtain ligand-receptor interaction pairs that meet the set requirements;

[0059] S4. Calculating a cell-cell communication score for the ligand-receptor interaction pairs that meet the set requirements to obtain expression threshold scores, expression product scores, and cell expression scores for cell-cell communication of several ligand-receptors between cell types; adding several corresponding scores for communication between cell types to obtain an expression threshold result, an expression product result, and a cell expression result for cell-cell communication; and measuring the cell-cell communication intensity using a three-point estimation method based on the expression threshold result, the expression product result, and the cell expression result of cell-cell communication;

[0060] S5. Construct a cell-cell communication heat map based on the cell-cell communication intensity; analyze the most active ligand-receptor interaction pairs in the communication between two cell types through the cell-cell communication heat map to complete the cell-cell communication visualization analysis.

[0061] In this embodiment, in step S1, the ligand and receptor sequence information of the protein is downloaded from a set database; the ligand and receptor sequence information of the protein is processed by iFeature to obtain the digital features of the ligand and receptor; based on the digital features of the ligand and receptor, an initial ligand and receptor feature matrix is ​​constructed; the initial ligand-receptor interaction pairs of the protein are collected, and a ligand-receptor interaction adjacency matrix is ​​constructed;

[0062] Specifically, the sequence information of proteins (ligands and receptors) was downloaded from the UniProt database; then, the sequence information of ligands and receptors was processed using iFeature to obtain the digital features of ligands and receptors and construct the initial feature matrix of ligands and receptors; the collected ligand-receptor interaction pairs were organized into the form of a ligand-receptor interaction matrix.

[0063] In this embodiment, in step S2, a ligand-receptor interaction prediction network model is constructed based on a graph convolutional network; the ligand-receptor interaction prediction network model is trained using the ligand and receptor initial feature matrix and the ligand-receptor interaction adjacency matrix to obtain a trained ligand-receptor interaction prediction network model; and prediction processing is performed using the trained ligand-receptor interaction prediction network model to obtain predicted ligand-receptor interaction pairs with interaction.

[0064] Specifically, the ligand-receptor interaction prediction network model includes a network with two graph convolutional layers and three fully connected layers (ReLU is used as the activation function except for the last fully connected layer), and skip connections are added in the convolutional layers to avoid problems such as gradient disappearance.

[0065] The initial feature matrix X of ligand and receptor and the ligand-receptor interaction adjacency matrix A are used as inputs of the network for training and prediction.

[0066] The output expression of each convolutional layer with skip connection is:

[0067]

[0068] Where X is the initial feature matrix of the ligand and receptor; A′ is the ligand-receptor interaction adjacency matrix; D is the degree matrix of the interaction adjacency matrix A′; θ, b, b′, W are all learnable parameters; ReLU is the activation function commonly used in deep learning.

[0069] The Sigmoid activation function is used after the last fully connected layer so that the output is a number between (0, 1). When the value is greater than 0.55, we believe that the corresponding ligand-receptor interaction exists, otherwise it is considered that there is no interaction. The expression of the fully connected layer is the same as the skip connection expression, and the Sigmoid expression is:

[0070]

[0071] Where e is the base of the natural logarithm function.

[0072] In this embodiment, in step S3, the collected initial ligand-receptor interaction pairs and the predicted ligand-receptor interaction pairs are identified and filtered through single-cell RNA sequencing data to obtain ligand-receptor interaction pairs that meet the set requirements;

[0073] Specifically, the collected initial ligand-receptor interaction pairs and the predicted ligand-receptor interaction pairs are identified and filtered through single-cell RNA sequencing data. When the ligand or receptor in the ligand-receptor interaction pair is not expressed in a certain cell or the expression value is lower than the average level, it is considered that the ligand-receptor pair does not mediate communication between the corresponding cells and is filtered.

[0074] In this embodiment, in step S4, a cell-cell communication score is calculated for the ligand-receptor interaction pairs that meet the set requirements to obtain expression threshold scores, expression product scores, and cell expression scores of cell-cell communication of several ligand-receptors between cell types; several corresponding scores of communication between cell types are added together to obtain expression threshold results, expression product results, and cell expression results of cell-cell communication; based on the expression threshold results, expression product results, and cell expression results of cell-cell communication, the cell-cell communication intensity is measured by a three-point estimation method;

[0075] Specifically, the calculation formulas for the expression threshold score, expression product score and cell expression score of the ligand receptor cell-cell communication are:

[0076]

[0077] Where, scoring expression thresholds for cell-cell communication; score expression products of cell-cell communication; Cell expression scores for cell-cell communication; A and B are cell types; a is ligand; b is receptor; M a,A is the average expression level of a in cell type A; M b,B is the average expression level of b in cell type B; M a and M b are the average expression levels of ligand a and receptor b in all cells respectively; σ a and σ b are the standard deviations of the expression levels of ligand a and receptor b in all cells, respectively. The result is 1 when both inequalities are satisfied, otherwise it is 0; N a,A is the number of cells in cell type A whose expression value of ligand a is greater than 0; N b,B is the number of cells in cell type B whose expression value of receptor b is greater than 0; N A and N Bare the number of cells in cell type A and cell type B, respectively.

[0078] After calculating the expression threshold score, expression product score, and cell expression score for all ligand-receptor cell-cell communication between all cell types, all corresponding scores for communication between cell types are added together to obtain the final expression threshold result, expression product result, and cell expression result. Specifically, assuming that for cell type A and cell type B, the expressions of the above three results are as follows:

[0079]

[0080] Where n is the number of ligand-receptor interaction pairs involved in mediating cell-cell communication.

[0081] The three results obtained above were normalized by applying the minimum-maximum scaling method to obtain the standardized cell-cell communication results R1, R2, and R3; the final cell-cell communication strength was measured using the three-point estimation method:

[0082]

[0083] Where R max 、R min and R med are the maximum, minimum and median scores in R1, R2 and R3 respectively.

[0084] In this embodiment, in step S5, a cell-cell communication heat map is constructed based on the cell-cell communication intensity; the most active ligand-receptor interaction pairs in the communication between two cell types are analyzed through the cell-cell communication heat map to complete the cell-cell communication visualization analysis.

[0085] Specifically, a cell-cell communication heat map was constructed using the final cell-cell communication intensities obtained in step S4, and the most active ligand-receptor interaction pairs in pairwise cell type communication were analyzed.

[0086] like Figure 3 As shown, the communication intensity between cell types in human melanoma tissue is displayed, and the darker the color, the higher the communication intensity between the corresponding cell types.

[0087] like Figure 4 The figure shows the three most active ligand-receptor pairs mediating communication between melanoma cancer cells and other cell types, with darker colors representing higher activity. For example, for Melanoma-T, when melanoma cancer cells act as efferent cells and T cells act as afferent cells, the three most active ligand-receptor pairs mediating communication between the two are LGALS1_PTPRC, B2M_HLA-F, and B2M_CD3G, with the underlined characters representing the ligand and receptor, respectively.

[0088] In summary, the present invention downloads the ligand and receptor sequence information of the protein from a set database; processes the ligand and receptor sequence information of the protein through iFeature to obtain the digital features of the ligand and receptor; constructs the ligand and receptor initial feature matrix according to the digital features of the ligand and receptor; collects the initial ligand-receptor interaction pairs of the protein, and constructs the ligand-receptor interaction adjacency matrix; constructs a ligand-receptor interaction prediction network model based on a graph convolutional network; trains the ligand-receptor interaction prediction network model through the ligand and receptor initial feature matrix and the ligand-receptor interaction adjacency matrix to obtain the trained ligand-receptor interaction prediction network model; performs prediction processing on the trained ligand-receptor interaction prediction network model to obtain predicted ligand-receptor interaction pairs with interaction; collects the ligand-receptor interaction pairs through single-cell RNA sequencing data. The initial ligand-receptor interaction pair and the predicted ligand-receptor interaction pair are identified and filtered to obtain a ligand-receptor interaction pair that meets the set requirements; the ligand-receptor interaction pair that meets the set requirements is subjected to cell-cell communication score calculation to obtain the expression threshold score, expression product score and cell expression score of the cell-cell communication of several ligand receptors between cell types; several corresponding scores of communication between cell types are added to obtain the expression threshold result, expression product result and cell expression result of cell-cell communication; according to the expression threshold result, the expression product result and the cell expression result of cell-cell communication, the cell-cell communication intensity is measured by the three-point estimation method; according to the cell-cell communication intensity, a cell-cell communication heat map is constructed; the most active ligand-receptor interaction pair in the communication between two cell types is analyzed by the cell-cell communication heat map to complete the cell-cell communication visualization analysis. The present invention measures the cell-cell communication intensity mediated by these ligand-receptor interactions by the identified high-confidence ligand-receptor interaction pairs and single-cell RNA sequencing data, and further performs cell-cell communication analysis. This paper first uses graph convolutional networks, leveraging the multidimensional features of ligands and receptors as initial embeddings, to obtain a more complete, reliable, and well-organized ligand-receptor interaction database for single-cell RNA sequencing data. By filtering the ligand-receptor interaction resource and calculating the cell-cell communication strength using a three-point evaluation method, the paper obtains relatively accurate cell-cell communication analysis results compared to other popular tools and provides multiple visualizations.

[0089] It should be noted that the method of the embodiments of the present disclosure can be performed by a single device, such as a computer or server. The method of the embodiments of the present disclosure can also be applied in a distributed scenario, where multiple devices cooperate to perform the method. In such a distributed scenario, one of the multiple devices may only perform one or more steps of the method of the embodiments of the present disclosure, and the multiple devices will interact with each other to complete the method.

[0090] It should be noted that the above description is limited to some embodiments of the present disclosure. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recited in the claims may be performed in an order different from that described in the above embodiments and still achieve the desired results. Furthermore, the processes depicted in the accompanying drawings do not necessarily require the specific order or sequential order shown to achieve the desired results. In certain embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0091] Example 2

[0092] See also Figure 5 , Embodiment 2 of the present invention further provides an intercellular communication analysis device based on a graph convolutional network, comprising:

[0093] The ligand and receptor initial feature matrix and ligand-receptor interaction adjacency matrix construction module 001 is used to download the protein ligand and receptor sequence information from a set database; process the protein ligand and receptor sequence information through iFeature to obtain the digital features of the ligand and receptor; construct the ligand and receptor initial feature matrix based on the digital features of the ligand and receptor; collect the initial ligand-receptor interaction pairs of the protein and construct the ligand-receptor interaction adjacency matrix;

[0094] The ligand-receptor interaction prediction network model construction and processing module 002 is used to construct a ligand-receptor interaction prediction network model based on a graph convolutional network; train the ligand-receptor interaction prediction network model using the ligand and receptor initial feature matrix and the ligand-receptor interaction adjacency matrix to obtain a trained ligand-receptor interaction prediction network model; perform prediction processing on the trained ligand-receptor interaction prediction network model to obtain predicted ligand-receptor interaction pairs with interaction;

[0095] The ligand-receptor interaction pair identification and filtering module 003 is used to identify and filter the collected initial ligand-receptor interaction pairs and the predicted ligand-receptor interaction pairs through single-cell RNA sequencing data to obtain ligand-receptor interaction pairs that meet the set requirements;

[0096] The cell-cell communication strength acquisition module 004 is configured to calculate a cell-cell communication score for the ligand-receptor interaction pairs that meet the set requirements, and obtain expression threshold scores, expression product scores, and cell expression scores for cell-cell communication of several ligand-receptors between cell types; add several corresponding scores for communication between cell types to obtain expression threshold results, expression product results, and cell expression results for cell-cell communication; and obtain the cell-cell communication strength by measuring the expression threshold results, expression product results, and cell expression results of cell-cell communication using a three-point estimation method.

[0097] The cell-cell communication heat map construction and analysis module 005 is used to construct a cell-cell communication heat map based on the cell-cell communication intensity; analyze the most active ligand-receptor interaction pairs in the communication between two cell types through the cell-cell communication heat map, and complete the cell-cell communication visualization analysis.

[0098] In this embodiment, in the ligand-receptor interaction prediction network model construction and processing module 002, the ligand-receptor interaction prediction network model includes two graph convolution layers and three fully connected layers, and the convolution layers are provided with skip connections;

[0099] The output expression of the convolutional layer with skip connection is:

[0100]

[0101] Where X is the initial feature matrix of the ligand and receptor; A′ is the ligand-receptor interaction adjacency matrix; D is the degree matrix of the interaction adjacency matrix A′; θ, b, b′, W are all learnable parameters; ReLU is the activation function commonly used in deep learning.

[0102] In this embodiment, in the cell-cell communication intensity acquisition module 004, the calculation formulas for the expression threshold score, expression product score and cell expression score of the ligand receptor cell-cell communication are respectively:

[0103]

[0104] Where, scoring expression thresholds for cell-cell communication; score expression products of cell-cell communication; Cell expression scores for cell-cell communication; A and B are cell types; a is ligand; b is receptor; M a,A is the average expression level of a in cell type A; M b,B is the average expression level of b in cell type B; M a and M bare the average expression levels of ligand a and receptor b in all cells respectively; σ a and σ b are the standard deviations of the expression levels of ligand a and receptor b in all cells, respectively. The result is 1 when both inequalities are satisfied, otherwise it is 0; N a,A is the number of cells in cell type A whose expression value of ligand a is greater than 0; N b,B is the number of cells in cell type B whose expression value of receptor b is greater than 0; N A and N B are the number of cells in cell type A and cell type B, respectively.

[0105] In this embodiment, in the cell-to-cell communication intensity acquisition module 004, the expression threshold result, expression product result, and cell expression result of the cell-to-cell communication are expressed as follows:

[0106]

[0107] Where n is the number of ligand-receptor interaction pairs involved in mediating cell-cell communication.

[0108] In this embodiment, in the cell-to-cell communication strength acquisition module 004, the expression of the cell-to-cell communication strength is:

[0109]

[0110] Where R max 、R min and R med They are the maximum, minimum and median values ​​of the standard cell-cell communication results after normalizing the expression threshold results of cell-cell communication, expression product results and cell expression results, respectively.

[0111] It should be noted that the information interaction, execution process, etc. between the modules of the above-mentioned system are based on the same concept as the method embodiment in Example 1 of the present application, and the technical effects they bring are the same as those of the method embodiment of the present application. For specific contents, please refer to the description in the method embodiment shown above in the present application, and no further details will be given here.

[0112] Example 3

[0113] Embodiment 3 of the present invention provides a non-transitory computer-readable storage medium, in which a program code for a cell-to-cell communication analysis method based on a graph convolutional network is stored. The program code includes instructions for executing embodiment 1 or any possible implementation thereof.

[0114] Computer-readable storage media can be any available medium that can be accessed by a computer or a data storage device such as a server or data center that includes one or more available media. The available media can be magnetic media (e.g., floppy disks, hard disks, magnetic tapes), optical media (e.g., DVDs), or semiconductor media (e.g., solid-state drives (SSDs)).

[0115] Example 4

[0116] Embodiment 4 of the present invention provides an electronic device, including: a memory and a processor;

[0117] The processor and the memory communicate with each other through a bus; the memory stores program instructions that can be executed by the processor, and the processor calls the program instructions to execute an intercellular communication analysis method based on a graph convolutional network of Example 1 or any possible implementation thereof.

[0118] Specifically, the processor can be implemented by hardware or by software. When implemented by hardware, the processor can be a logic circuit, an integrated circuit, etc.; when implemented by software, the processor can be a general-purpose processor, which is implemented by reading software code stored in a memory. The memory can be integrated into the processor or located outside the processor and exist independently.

[0119] In the above embodiments, it can be implemented in whole or in part by software, hardware, firmware 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 invention is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable systems. The computer instructions can be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions can be transmitted from a website, computer, server or data center to another website, computer, server or data center via a wired (e.g., coaxial cable, optical fiber, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) mode.

[0120] Obviously, those skilled in the art will appreciate that the various modules or steps of the present invention described above can be implemented using a general-purpose computing system. They can be centralized on a single computing system or distributed across a network of multiple computing systems. Alternatively, they can be implemented using program code executable by a computing system, and thus, they can be stored in a storage system and executed by the computing system. In some cases, the steps shown or described herein can be performed in a different order than that shown, or they can be fabricated into separate integrated circuit modules, or multiple modules or steps can be fabricated into a single integrated circuit module. Thus, the present invention is not limited to any particular combination of hardware and software.

[0121] Although the present invention has been described in detail above using general descriptions and specific embodiments, it will be apparent to those skilled in the art that modifications and improvements may be made thereto. Therefore, such modifications and improvements, without departing from the spirit of the present invention, are intended to be within the scope of protection claimed herein.

Claims

1. A method for analyzing intercellular communication based on graph convolutional networks, characterized in that: include: Download protein ligand and receptor sequence information from the set database; Processing the ligand and receptor sequence information of the protein through iFeature to obtain digital features of the ligand and receptor; constructing the ligand and receptor initial feature matrix based on the digital features of the ligand and receptor; Collect initial ligand-receptor interaction pairs of proteins and construct a ligand-receptor interaction adjacency matrix; Based on a graph convolutional network, a ligand-receptor interaction prediction network model is constructed; the ligand-receptor interaction prediction network model is trained using the ligand and receptor initial feature matrix and the ligand-receptor interaction adjacency matrix to obtain a trained ligand-receptor interaction prediction network model; and prediction processing is performed using the trained ligand-receptor interaction prediction network model to obtain predicted ligand-receptor interaction pairs with interaction; Identifying and filtering the collected initial ligand-receptor interaction pairs and the predicted ligand-receptor interaction pairs through single-cell RNA sequencing data to obtain ligand-receptor interaction pairs that meet set requirements; performing a cell-cell communication score calculation on the ligand-receptor interaction pairs that meet the set requirements to obtain expression threshold scores, expression product scores, and cell expression scores of cell-cell communication of several ligand-receptors between cell types; adding several corresponding scores of communication between cell types to obtain expression threshold results, expression product results, and cell expression results of cell-cell communication; and measuring the cell-cell communication intensity using a three-point estimation method based on the expression threshold results, expression product results, and cell expression results of cell-cell communication; constructing a cell-cell communication heat map based on the cell-cell communication intensity; analyzing the most active ligand-receptor interaction pairs in the communication between two cell types through the cell-cell communication heat map to complete the cell-cell communication visualization analysis; The calculation formulas for the expression threshold score, expression product score and cell expression score of the cell-cell communication of the ligand receptor are: Where, scoring expression thresholds for cell-cell communication; score expression products of cell-cell communication; Cell expression scores for cell-cell communication; A and B are cell types; a is ligand; b is receptor; M a,A is the average expression level of a in cell type A; M b,B is the average expression level of b in cell type B; M a and M b are the average expression levels of ligand a and receptor b in all cells respectively; σ a and σ b are the standard deviations of the expression levels of ligand a and receptor b in all cells, respectively. The result is 1 when both inequalities are satisfied, otherwise it is 0; N a,A is the number of cells in cell type A whose expression value of ligand a is greater than 0; N b,B is the number of cells in cell type B whose expression value of receptor b is greater than 0; N A and N B are the number of cells in cell type A and cell type B, respectively.

2. A method for analyzing intercellular communication based on graph convolutional networks according to claim 1, characterized in that: The ligand-receptor interaction prediction network model includes two graph convolution layers and three fully connected layers, and the convolution layers are provided with skip connections; The output expression of the convolutional layer with skip connection is: Where X is the initial characteristic matrix of ligand and receptor; A′ is the ligand-receptor interaction adjacency matrix; D is the degree matrix of the interaction adjacency matrix A′; θ, b, b′, W are all learnable parameters; ReLU is an activation function commonly used in deep learning.

3. The method for analyzing intercellular communication based on graph convolutional networks according to claim 1, characterized in that: The expression threshold results, expression product results and cell expression results of the cell-cell communication are respectively: Where n is the number of ligand-receptor interaction pairs involved in mediating cell-cell communication.

4. The method for analyzing intercellular communication based on graph convolutional networks according to claim 3, characterized in that: The expression of the cell-cell communication intensity is: Where R max 、R min and R med They are the maximum, minimum and median values ​​of the standard cell-cell communication results after normalizing the expression threshold results of cell-cell communication, expression product results and cell expression results, respectively.

5. A cell-to-cell communication analysis device based on a graph convolutional network, using the cell-to-cell communication analysis method based on a graph convolutional network according to any one of claims 1 to 4, characterized in that: include: The ligand and receptor initial feature matrix and ligand-receptor interaction adjacency matrix construction module are used to download the ligand and receptor sequence information of proteins from the set database; Processing the ligand and receptor sequence information of the protein through iFeature to obtain digital features of the ligand and receptor; constructing the ligand and receptor initial feature matrix based on the digital features of the ligand and receptor; Collect initial ligand-receptor interaction pairs of proteins and construct a ligand-receptor interaction adjacency matrix; A ligand-receptor interaction prediction network model construction and processing module is used to construct a ligand-receptor interaction prediction network model based on a graph convolutional network; the ligand-receptor interaction prediction network model is trained using the ligand and receptor initial feature matrix and the ligand-receptor interaction adjacency matrix to obtain a trained ligand-receptor interaction prediction network model; and prediction processing is performed using the trained ligand-receptor interaction prediction network model to obtain predicted ligand-receptor interaction pairs with interactions. A ligand-receptor interaction pair identification and filtering module is used to identify and filter the collected initial ligand-receptor interaction pairs and the predicted ligand-receptor interaction pairs through single-cell RNA sequencing data to obtain ligand-receptor interaction pairs that meet the set requirements; a cell-cell communication strength acquisition module, configured to calculate a cell-cell communication score for the ligand-receptor interaction pairs that meet set requirements, and obtain expression threshold scores, expression product scores, and cell expression scores for cell-cell communication of several ligand-receptors between cell types; summing up several corresponding scores for communication between cell types to obtain expression threshold results, expression product results, and cell expression results for cell-cell communication; and obtaining the cell-cell communication strength by measuring the expression threshold results, expression product results, and cell expression results of cell-cell communication using a three-point estimation method; a cell-cell communication heat map construction and analysis module, configured to construct a cell-cell communication heat map based on the cell-cell communication intensity; and to analyze the most active ligand-receptor interaction pairs in the communication between two cell types through the cell-cell communication heat map, thereby completing a cell-cell communication visualization analysis; In the cell-cell communication intensity acquisition module, the calculation formulas for the expression threshold score, expression product score and cell expression score of the cell-cell communication of the ligand receptor are respectively: Where, scoring expression thresholds for cell-cell communication; score expression products of cell-cell communication; Cell expression scores for cell-cell communication; A and B are cell types; a is ligand; b is receptor; M a,A is the average expression level of a in cell type A; M b,B is the average expression level of b in cell type B; M a and M b are the average expression levels of ligand a and receptor b in all cells respectively; σ a and σ b are the standard deviations of the expression levels of ligand a and receptor b in all cells, respectively. The result is 1 when both inequalities are satisfied, otherwise it is 0; N a,A is the number of cells in cell type A whose expression value of ligand a is greater than 0; N b,B is the number of cells in cell type B whose expression value of receptor b is greater than 0; N A and N B are the number of cells in cell type A and cell type B, respectively.

6. The intercellular communication analysis device based on graph convolutional network according to claim 5, characterized in that: In the ligand-receptor interaction prediction network model construction and processing module, the ligand-receptor interaction prediction network model includes two graph convolution layers and three fully connected layers, and the convolution layers are provided with skip connections; The output expression of the convolutional layer with skip connection is: Where X is the initial characteristic matrix of ligand and receptor; A′ is the ligand-receptor interaction adjacency matrix; D is the degree matrix of the interaction adjacency matrix A′; θ, b, b′, W are all learnable parameters; ReLU is an activation function commonly used in deep learning.

7. The intercellular communication analysis device based on graph convolutional network according to claim 5, characterized in that: In the cell-cell communication intensity acquisition module, the expression threshold result, expression product result and cell expression result of the cell-cell communication are respectively expressed as: Where n is the number of ligand-receptor interaction pairs involved in mediating cell-cell communication.

8. The intercellular communication analysis device based on graph convolutional network according to claim 7, characterized in that: In the cell-to-cell communication strength acquisition module, the expression of the cell-to-cell communication strength is: Where R max 、R min and R med They are the maximum, minimum and median values ​​of the standard cell-cell communication results after normalizing the expression threshold results of cell-cell communication, expression product results and cell expression results, respectively.

Images