Multi-omics cancer sample representation method based on graph representation and related device

Abstract

The invention discloses a multi-omics cancer sample representation method based on graph representation and a related device. The representation method comprises the following steps: acquiring gene common library data; processing the gene public library data to obtain gene expression data and methylation data of which the variance of the cancer sample is greater than a threshold value; processing the gene expression data of which the variance of the cancer sample is greater than a threshold value and the methylation data to obtain multi-omics data of the cancer sample, and taking an intersection of the multi-omics data of the cancer sample to obtain a common gene; obtaining a gene interaction network of the corresponding gene through a protein interaction network database on the basis of the common gene, filtering out part of scattered points in the gene interaction network, and integrating to obtain a sample gene interaction network skeleton; and integrating the multi-omics data of the cancer sample and the sample gene interaction network skeleton representation by adopting a sample graph representation algorithm. According to the method, multiple omics data are processed to obtain omics data corresponding to genes highly related to cancer occurrence, so that the influence of experimental deviation in measurement and sequencing data on subsequent conclusions is reduced.

Description

Technical Field

[0001] The present invention belongs to the technical field of bioinformatics, and in particular relates to a multi-omics cancer sample representation method based on graph representation and a related device. Background Art

[0002] Breast cancer, lung cancer, and kidney cancer are common and clinically harmful malignant tumors, posing a serious threat to global health. According to a study on the domestic cancer situation published in JNCC in 2022, breast cancer is one of the most common cancers in women, and lung cancer is one of the cancers causing the most deaths worldwide. The incidence and mortality of kidney cancer are also increasing year by year. The reason is that cancer is a malignant tumor with high genetic heterogeneity. These tumor cells carrying different gene mutation spectra and genetic phenotypes have different biological behaviors and sensitivities to treatment. In addition, the same type of tumor may have genetic variations between different patients, resulting in great differences in the response to therapeutic drugs.

[0003] With the rapid progress of current high-throughput biotechnology and artificial intelligence technology, researchers are paying more and more attention to the integration and analysis of multi-omics data based on multiple cancer datasets. Machine learning methods have been widely used in cancer research, providing many new tools to integrate and analyze various omics data to obtain more accurate prediction results and promote the realization of precision medicine.

[0004] Among the current mainstream multi-omics data fusion methods, there are mainly three technical methods: feature-connected multi-omics data integration methods, model-integrated multi-omics data integration methods, and network-model-based multi-omics methods. The first is the feature-connected multi-omics data integration method. The idea of ​​this method is to directly splice omics data including proteomics, genomics, transcriptomics, etc. to form a sample joint matrix containing multi-omics data, and then use matrix decomposition, supervised, unsupervised and other methods to explore this joint matrix. With the deepening of research, people gradually realized this limitation and began to seek more flexible and effective methods, so a multi-omics data integration method based on model integration was proposed. This method integrates independent models constructed by different single-omics into the final model. The integrated learning method shows obvious advantages in improving the generalization ability, stability and flexibility of the model. Finally, the multi-omics method based on the network model combines multi-omics data into a network to model biological laws. This method can accurately reflect the interaction between omics data, and also show the biological process of mutual influence between nodes in a single omics.

[0005] Among them, the more active scheme is the multi-omics method based on network model, which mainly has two main ideas. The first method uses genes as nodes, the interaction relationship between genes as edges, and various omics data of genes as node features. Graph neural network is used for node-level prediction, such as predicting cancer genes, or edge-level tasks, such as predicting the interaction relationship between unknown genes. The first method uses genes as nodes and the interaction relationship between genes as edges. The overall graph modeled lacks practical significance and can only be used for node-level prediction, but cannot be inferred for a single sample. The second method is sample-based, using cancer samples as nodes, compressing and splicing the high-dimensional omics data of samples into matrices as node features, and the similarity between samples constitutes the edges between nodes. Subsequently, graph neural network is used for node-level prediction, such as predicting the survival period or typing of samples. The second method uses samples as nodes, cancer samples as nodes, and the similarity between samples constitutes the edges between nodes. This approach cannot model the network topological relationship between multiple genes well. At present, the multi-omics fusion method based on network model has limitations.

[0006] It can be seen that the existing sample characterization methods are not yet able to construct a special data structure that can both model the topological relationship of multi-gene networks and perform downstream predictions on individual samples. Summary of the invention

[0007] In order to overcome the technical problem that the prior art cannot understand the network topological relationship between multiple genes and thus cannot make downstream predictions, the present invention aims to propose a multi-omics cancer sample representation method and related devices based on graph representation. The sample representation method can comprehensively understand the multi-gene network topological relationship and realize fine-grained representation of single samples, so that more accurate graph classification can be obtained by using this sample representation method, and functions such as molecular subtype prediction and drug effect prediction of cancer samples can be realized.

[0008] To achieve the above purpose, the technical solution adopted by the present invention is as follows:

[0009] A first aspect of the present invention provides a multi-omics cancer sample representation method based on graph representation, comprising the following steps:

[0010] Obtain gene public library data;

[0011] The gene public library data was processed to obtain gene expression data and methylation data of cancer samples with variance greater than the threshold;

[0012] After processing the gene expression data and methylation data of cancer samples with variance greater than a threshold, multi-omics data of cancer samples are obtained, and the multi-omics data of cancer samples are intersected to obtain common genes;

[0013] Based on public genes, the gene interaction network of the corresponding gene is obtained through the protein interaction network database. After filtering out some scattered points in the gene interaction network and integrating them, the skeleton of the sample gene interaction network is obtained.

[0014] The multi-omics data of cancer samples and the skeleton representation of the sample gene interaction network are integrated using a sample graph representation algorithm to obtain a multi-omics cancer sample representation based on graph representation.

[0015] Furthermore, the methylation level of the methylation data is calculated by the following formula:

[0016]

[0017] In the formula, represents the methylation level of methylation data, Indicates the methylation level of the gene body region, Gene body represents the gene body region, i represents the gene number, and Median represents the median.

[0018] Furthermore, the common genes are obtained by the following formula:

[0019] G=G Rk(Var(pro_meth))＜301 ∩G Rk(Var(body_meth))＜301 ∩G Rk(Var(Exp))＜301 (3)

[0020] In the formula, G is a common gene, Rk is the variance ranking of genomic data, Var is the variance, pro_meth is the methylation level of the promoter region, body_meth is the methylation level of the gene body region, Exp is the gene expression level, G Rk(Var(pro_meth))＜301 The top 300 genes with the largest variance in the promoter region are G Rk(Var(body_meth))＜301 G is the top 300 genes with the highest variance in the genome region. Rk(Var(Exp))＜301 The top 300 genes in terms of gene expression level variance.

[0021] Furthermore, the gene expression data and methylation data of cancer samples with variance greater than the threshold were processed using R scripts.

[0022] Furthermore, the edges with gene interaction confidence greater than 0.4 were selected as the skeleton of the sample gene interaction network.

[0023] Furthermore, the multi-omics cancer sample representation S based on graph representation is:

[0024] S={(G1,y1),(G2,y2),(G3,y3)...(G N ,y N )}

[0025] Among them, S represents a certain cancer type graph data set, Gi represents the i-th sample in the data set, y i Represents the cancer subtype label corresponding to the i-th sample.

[0026] Furthermore, the multi-omics data of cancer samples and the sample gene interaction network skeleton representation are integrated using a sample graph representation algorithm to obtain a multi-omics cancer sample representation based on graph representation, including the following steps:

[0027] The skeleton of the sample gene interaction network was reconstructed and represented as a two-dimensional list, where rows represent source nodes, columns represent target nodes, and the values ​​in the list represent whether there is an edge. Using the skeleton of the sample gene interaction network, it can be determined whether there is an edge between two genes; if there is an edge, the adjacent node number of the corresponding node is used as the feature of this node; otherwise, the search will continue until the entire two-dimensional list is traversed;

[0028] Then, for each node, the corresponding three genomics data are integrated, and the integration result is used as the feature of this node to obtain a multi-omics cancer sample representation based on graph representation.

[0029] A second aspect of the present invention provides a multi-omics cancer sample representation system based on graph representation, comprising:

[0030] A data acquisition module is used to acquire gene public library data;

[0031] A data processing module is used to process the gene public library data to obtain gene expression data and methylation data of cancer samples with variance greater than a threshold;

[0032] A common gene acquisition module is used to process the gene expression data and methylation data of cancer samples with variance greater than a threshold to obtain multi-omics data of cancer samples, and to obtain common genes by taking the intersection of the multi-omics data of cancer samples;

[0033] The sample gene interaction network skeleton acquisition module is used to obtain the gene interaction network of the corresponding gene based on the public gene through the protein interaction network database, filter out some scattered points in the gene interaction network and integrate them to obtain the sample gene interaction network skeleton;

[0034] The integration module is used to integrate the multi-omics data of cancer samples with the sample gene interaction network skeleton representation using a sample graph representation algorithm to obtain a multi-omics cancer sample representation based on graph representation.

[0035] A third aspect of the present invention provides an electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the multi-omics cancer sample representation method based on graph representation.

[0036] A fourth aspect of the present invention provides a computer-readable storage medium storing a computer program, wherein the computer program, when executed by a processor, implements a multi-omics cancer sample representation method based on graph representation.

[0037] Compared with the prior art, the present invention has the following technical effects:

[0038] First, in the present invention, by processing the gene public library data, the gene expression data and methylation data of the cancer sample with a variance greater than a threshold are obtained; after processing the gene expression data and methylation data of the cancer sample with a variance greater than a threshold, the multi-omics data of the cancer sample are obtained, and the multi-omics data of the cancer sample are intersected to obtain common genes. The multi-omics data can be processed using a new high-dimensional multi-omics data processing scheme for cancer samples to obtain the omics data corresponding to genes that are highly related to cancer occurrence, thereby reducing the impact of experimental biases in measurement and sequencing data on subsequent conclusions. Based on the new high-dimensional multi-omics data processing scheme for cancer samples, the present invention represents the high-dimensional multi-omics data of cancer as the features of the nodes in the graph, effectively achieving dimensionality reduction of the multi-omics data. Secondly, verification was carried out based on this sample representation method, proving that the cancer sample representation method proposed by the present invention can effectively perform downstream analysis and become an effective tool for scientific researchers to analyze cancer sample data. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] Figure 1 Provide an overall flow chart for cancer omics data processing;

[0040] Figure 2 Build module (I) for sample graph model;

[0041] Figure 3 Building modules for sample graph models (II);

[0042] Figure 4 It is an example of the application of cancer omics data based on graph representation;

[0043] Figure 5 Figure 1 shows the prediction results of molecular subtypes of breast cancer using this framework.

[0044] Figure 6 Schematic diagram of the graph-based multi-omics cancer sample representation system. DETAILED DESCRIPTION

[0045] In order to facilitate the understanding of the present invention, the present invention will be described more fully below with reference to the relevant drawings. The preferred embodiments of the present invention are given in the drawings. However, the present invention can be implemented in many different forms and is not limited to the embodiments described herein. On the contrary, the purpose of providing these embodiments is to make the disclosure of the present invention more thoroughly and comprehensively understood.

[0046] See also Figure 1 The multi-omics cancer sample representation method based on graph representation of the present invention comprises the following steps:

[0047] 1) Process the high-variance (high variance means variance greater than a threshold, the threshold is determined according to actual needs) gene expression data and methylation data of cancer samples obtained from public library data (here the UCSC Xena database is used as an example). After processing by R scripts, three types of genomic data (i.e., sample expression matrix, promoter region methylation matrix, and gene body region methylation matrix) are obtained, i.e., multi-omics data of cancer samples.

[0048] Current studies have shown that the methylation of different regions of DNA has different effects on gene expression. The effects of methylation of different parts of the DNA molecule on the gene expression mechanism are very complex. Studies have shown that DNA methylation in promoters and promoter regions will inhibit gene expression, while DNA methylation on the gene body may promote gene expression. Further studies have found that the relationship between DNA methylation on the gene body and gene expression is related to whether it is located in a CpG island (CGI). In the normal human genome, CpG in CpG islands is usually unmethylated, while CpG outside CpG islands is usually methylated. In addition, studies have also shown that DNA methylation is closely related to the occurrence of cancer. After tumor development, CpG islands are usually highly methylated locally, while the genome presents DNA hypomethylation. Hypermethylation can lead to a decrease in the expression of tumor suppressor genes, thereby increasing the formation and survival efficiency of cancer cells, while hypomethylation can lead to a decrease in the methylation level of oncogenes and their activation, as well as the activation of some transposons, which in turn leads to a decrease in chromosome stability and ultimately promotes the formation of malignant tumors. Therefore, for the methylated regions that inhibit gene expression, represented by the promoter region, the methylation status of the gene in these parts is obtained according to formula (1):

[0049]

[0050] in, It indicates the methylation level of the DNA methylation region that inhibits the expression of gene i, that is, the methylation level of the promoter region. Indicates the methylation status of the upstream region from the transcription start site of the gene. Indicates the methylation status of the first exon region of the gene. Indicates the methylation status of the 5' untranslated region of the gene. The methylation status of the upstream region of the transcription start site of the gene. The reason for taking the median is that methylation data often presents an asymmetric distribution or contains outliers, so taking the median can often better represent the central trend of the data and reflect the true methylation level of the sample.

[0051] For the methylated regions that promote gene expression, represented by the gene body region, the present invention processes them according to formula (2), wherein Indicates the methylation level of the DNA methylation region that promotes the expression of gene i, that is, the methylation level of the gene body region body_meth.

[0052]

[0053] In the formula, represents the methylation level of methylation data, Indicates the methylation level of the gene body region, Gene body represents the gene body region, i represents the gene number, and Median represents the median.

[0054] See also Figure 2 The molecular omics data of samples obtained from the public cancer sample database TCGA (The Cancer Genome Atlas) were used as the data source. The omics data pre-processed in the UCSC Xena database were used to extract the sample gene expression data files and methylation data files HM450 files. The sample gene expression data files were subjected to variance filtering to obtain the sample expression matrix. The methylation data files HM450 files and the CHAMP probe-gene name package in the R language were subjected to variance filtering to obtain the promoter region methylation matrix and the gene body region methylation matrix. The columns of the sample expression matrix, promoter region methylation matrix and gene body region methylation matrix represent one gene, and the rows represent one sample. Then, according to formula (3), the top 300 genes with the largest variance in the three matrices were selected.

[0055] G=G Rk(Var(pro_meth))＜301 ∩G Rk(Var(body_meth))＜301 ∩G Rk(Var(Exp))＜301 (3)

[0056] Where G is a common gene, Rk is the variance ranking of genomic data, Var is the variance, pro_meth is the methylation level of the promoter region, body_meth is the methylation level of the gene body region, and Exp is the gene expression level. Rk(Var(pro_meth))＜301 The top 300 genes with the largest variance in the promoter region are G Rk(Var(body_meth))＜301 G is the top 300 genes with the highest variance in the genome region. Rk(Var(Exp))＜301 The top 300 genes in terms of gene expression level variance.

[0057] 2) The obtained public gene G is initially saved, and the gene interaction network of the corresponding gene is found through the protein interaction network database (here taking the STRING database as an example), and some scattered points in the gene interaction network are filtered out using a graph processing tool (here taking the tool cytoscape as an example), and then after integrating the omics data, a multi-omics graph data representation of various cancer samples is obtained;

[0058] For details, see Figure 3 , search the public gene G obtained in step 1) in the STRING database to obtain the gene interaction network of the corresponding gene.

[0059] Furthermore, after preliminary processing by the omics data processing method proposed in the present invention, i.e., step 1), three genomic data are obtained, and the gene interaction network is integrated according to the three genomic data to generate a graph representation of each sample, thereby obtaining multi-omics graph data of various cancer samples. Here, the edges with gene interaction confidence medium_Confidence greater than 0.4 are screened, and a preliminary sample gene interaction network skeleton can be obtained. Then, according to the sample gene interaction network skeleton and the three genomic data obtained in step 1), the sample graph representation algorithm is used to integrate them to obtain a multi-omics graph data representation S of various cancer samples, that is, a multi-omics cancer sample representation based on graph representation, S = {(G1, y1), (G2, y2), (G3, y3)...(G N ,y N )}, where S represents a certain cancer type graph data representation set, and a certain cancer type graph data representation set S includes Sample1, Sample2, ..., SampleN, G i represents the i-th sample in the dataset, and yi represents the cancer subtype label corresponding to the i-th sample.

[0060] Among them, see Table 1, the specific process of the sample graph representation algorithm is:

[0061] The skeleton of the sample gene interaction network was reconstructed and represented as a two-dimensional list, where rows represent source nodes and columns represent target nodes. The values ​​in the list represent whether there is an edge. Using the skeleton of the sample gene interaction network, it is possible to determine whether there is an edge between two genes. If there is an edge, the adjacent node number of the corresponding node is used as the feature of this node; otherwise, the search will continue until the entire two-dimensional list is traversed.

[0062] Then, for each node, the corresponding three genomic data are integrated and the integration result is used as the feature of this node. In this way, a graph data representation that integrates the gene interaction network skeleton and omics information is obtained, that is, a multi-omics cancer sample representation based on graph representation.

[0063] 3) Using the common gene G obtained in step 1) and the sample gene interaction network skeleton obtained in step 2), the cancer sample omics data of multiple samples can be integrated into one file so that subsequent researchers can use them end-to-end (here taking typing prediction as an example) and reduce the overall coupling degree of the algorithm.

[0064] Example 1

[0065] In order to verify the effectiveness of the data processing method proposed in the present invention, the present invention provides a cancer subtype classification method based on the cancer sample representation, and its framework is as follows: Figure 3 As shown in the figure. The data source is multi-omics data of real cancer samples, and the network comes from the STRING database. The constructed graph model is input into the graph neural network module. After the convolution kernel graph pooling module, prediction is performed to carry out downstream analysis, such as exploring tumor markers and biological function enrichment, which proves the effectiveness of this representation method.

[0066] Table 1 Sample graph representation algorithm

[0067]

[0068]

[0069] In order to verify the accuracy of the method proposed in the present invention, the present invention used breast cancer data in the TCGA public library database to verify the conclusion.

[0070] The verification process is as follows Figure 4As shown in the figure, first, the cancer omics data in the database is extracted, and then the STRING database is used to obtain the cancer gene interaction network skeleton, and the sample graph model construction method proposed in the present invention is used to construct a graph of breast cancer samples, and then a suitable graph neural network module is designed, which specifically includes a graph convolution module and a graph pooling module. The cancer sample graph is input to train it, and finally the cancer subtype is predicted through the prediction generation layer, and some intermediate results in the network can be used to perform downstream analysis such as tumor marker prediction and biological function enrichment.

[0071] The present invention uses this framework to predict the molecular subtypes of breast cancer, and the prediction results are as follows: Figure 5 As shown, after 1000 training rounds, the accuracy of the network in predicting breast cancer subtypes can exceed 80%, which exceeds most of the existing baseline models.

[0072] The present invention provides a processing flow for high-dimensional cancer multi-omics data, so that multi-omics data related to cancer occurrence can be better screened. In the processing of methylation data, the present invention divides it into two groups of data according to its different gene expression for processing and application. Due to the limitation of model establishment, the previous cancer sample characterization method cannot realize cancer sample typing based on biological network modeling. The new cancer sample representation method proposed by the present invention realizes the modeling of each sample into a graph representation under the premise of using biological network modeling.

[0073] Another embodiment of the present invention provides a multi-omics cancer sample representation system based on graph representation, comprising:

[0074] A data acquisition module is used to acquire gene public library data;

[0075] A data processing module is used to process the gene public library data to obtain gene expression data and methylation data of cancer samples with variance greater than a threshold;

[0076] A common gene acquisition module is used to process the gene expression data and methylation data of cancer samples with variance greater than a threshold to obtain multi-omics data of cancer samples, and to obtain common genes by taking the intersection of the multi-omics data of cancer samples;

[0077] The sample gene interaction network skeleton acquisition module is used to obtain the gene interaction network of the corresponding gene based on the public gene through the protein interaction network database, filter out some scattered points in the gene interaction network and integrate them to obtain the sample gene interaction network skeleton;

[0078] The integration module is used to integrate the multi-omics data of cancer samples with the sample gene interaction network skeleton representation using a sample graph representation algorithm to obtain a multi-omics cancer sample representation based on graph representation.

[0079] Another embodiment of the present invention provides an electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the multi-omics cancer sample representation method based on graph representation.

[0080] Another embodiment of the present invention provides a computer-readable storage medium storing a computer program, wherein the computer program, when executed by a processor, implements a multi-omics cancer sample representation method based on graph representation.

[0081] The above description is only for the best embodiment of the present invention, but it should not be understood as limiting the claims. The present invention is not limited to the above embodiments, and its specific structure is allowed to be changed. However, all changes made within the protection scope of the independent claims of the present invention are within the protection scope of the present invention.

[0082] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by those skilled in the art of the present invention. The terms used herein in the specification of the present invention are only for the purpose of describing specific embodiments and are not intended to limit the present invention. The term "and / or" used herein includes any and all combinations of one or more related listed items.

Claims

1. A multi-omics cancer sample representation method based on graph representation, characterized in that: The following steps are involved: Obtain gene public library data; Process the public gene library data to obtain gene expression data and methylation data of cancer samples with variance greater than the threshold; After processing the gene expression data and methylation data of cancer samples with variance greater than a threshold, multi-omics data of cancer samples are obtained, and the multi-omics data of cancer samples are intersected to obtain common genes; Based on public genes, the gene interaction network of the corresponding gene is obtained through the protein interaction network database. After filtering out some scattered points in the gene interaction network and integrating them, the skeleton of the sample gene interaction network is obtained. The multi-omics data of cancer samples and the skeleton representation of the sample gene interaction network are integrated using a sample graph representation algorithm to obtain a multi-omics cancer sample representation based on graph representation.

2. The multi-omics cancer sample representation method based on graph representation according to claim 1, characterized in that: The methylation level of the methylation data was calculated by the following formula: In the formula, represents the methylation level of methylation data, Indicates the methylation level of the gene body region, Gene body represents the gene body region, i represents the gene number, and Median represents the median.

3. The multi-omics cancer sample representation method based on graph representation according to claim 1, characterized in that: The common genes are obtained by the following formula: G=G Rk(Var(pro_meth))＜301 ∩G Rk(Var(body_meth))＜301 ∩G Rk(Var(Exp))＜301 (3) In the formula, G is a common gene, Rk is the variance ranking of genomic data, Var is the variance, pro_meth is the methylation level of the promoter region, body_meth is the methylation level of the gene body region, Exp is the gene expression level, G Rk(Var(pro_meth))＜301 The top 300 genes with the largest variance in the promoter region are G Rk(Var(body_meth))＜301 G is the top 300 genes with the highest variance in the genome region. Rk(Var(Exp))＜301 The top 300 genes in terms of gene expression level variance.

4. The multi-omics cancer sample representation method based on graph representation according to claim 1, characterized in that: Gene expression data of cancer samples with variance greater than a threshold and methylation data were processed using R scripts.

5. The multi-omics cancer sample representation method based on graph representation according to claim 1, characterized in that: The edges with gene interaction confidence greater than 0.4 were selected as the skeleton of the sample gene interaction network.

6. The multi-omics cancer sample representation method based on graph representation according to claim 1, characterized in that: The multi-omics cancer sample representation S based on graph representation is: S={(G1,y1),(G2,y2),(G3,y3)...(G N ,y N )} Among them, S represents a certain cancer type graph data set, G i represents the i-th sample in the data set, y i Represents the cancer subtype label corresponding to the i-th sample.

7. The multi-omics cancer sample representation method based on graph representation according to claim 1, characterized in that: The multi-omics data of cancer samples and the skeleton representation of the sample gene interaction network are integrated using a sample graph representation algorithm to obtain a multi-omics cancer sample representation based on graph representation, including the following steps: The skeleton of the sample gene interaction network was reconstructed and represented as a two-dimensional list, where rows represent source nodes, columns represent target nodes, and the values ​​in the list represent whether there is an edge. Using the skeleton of the sample gene interaction network, it can be determined whether there is an edge between two genes; if there is an edge, the adjacent node number of the corresponding node is used as the feature of this node; otherwise, the search will continue until the entire two-dimensional list is traversed; Then, for each node, the corresponding three genomics data are integrated, and the integration result is used as the feature of this node to obtain a multi-omics cancer sample representation based on graph representation.

8. A multi-omics cancer sample representation system based on graph representation, characterized in that: include: A data acquisition module is used to acquire gene public library data; A data processing module is used to process the gene public library data to obtain gene expression data and methylation data of cancer samples with variance greater than a threshold; A common gene acquisition module is used to process the gene expression data and methylation data of cancer samples with variance greater than a threshold to obtain multi-omics data of cancer samples, and to obtain common genes by taking the intersection of the multi-omics data of cancer samples; The sample gene interaction network skeleton acquisition module is used to obtain the gene interaction network of the corresponding gene based on the public gene through the protein interaction network database, filter out some scattered points in the gene interaction network and integrate them to obtain the sample gene interaction network skeleton; The integration module is used to integrate the multi-omics data of cancer samples with the sample gene interaction network skeleton representation using a sample graph representation algorithm to obtain a multi-omics cancer sample representation based on graph representation.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the multi-omics cancer sample representation method based on graph representation as described in any one of claims 1 to 7 is implemented.

10. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the method for representing multi-omics cancer samples based on graph representation according to any one of claims 1 to 7 is implemented.

Images