Cell infiltration inference method and system fusing GO function annotation and PPI network information

Abstract

The invention relates to a cell infiltration inference method and system fusing GO function annotation and PPI network information. The method comprises the following steps: collecting gene expression data, GO function annotation data and PPI network data; respectively constructing a cell * cell function association network and a cell * cell physical interaction network; carrying out weighted fusion processing on the two to obtain a comprehensive cell relation network; and calculating a final cell infiltration fraction through a restart migration algorithm, and deducing the infiltration degree in the tumor microenvironment according to the final cell infiltration fraction. According to the method, GO function annotation information and PPI network data are creatively fused, functional similarity and physical or signal interaction between cells are comprehensively considered, the model can understand cell synergy from the biological pathway level and can analyze cell direct interaction from the protein interaction level, one-sidedness of a single view angle is avoided, and the method has the advantages of being simple in structure and convenient to operate. And a more three-dimensional cognitive framework is provided for tumor microenvironment analysis.

Description

TECHNICAL FIELD

[0001] The application belongs to the technical field of biological information, and particularly relates to a cell infiltration inference method and system fusing GO function annotation and PPI network information. BACKGROUND

[0002] Tumor Microenvironment (TME) is a complex ecosystem composed of tumor cells, immune cells, stromal cells, stem cells, vascular endothelial cells, cytokines and extracellular matrix. In recent years, studies have shown that TME plays a crucial role in the occurrence, development, metastasis, recurrence and response of immunotherapy and targeted therapy of tumors. Therefore, accurately depicting the cell composition, infiltration degree and cell-cell interaction in TME not only helps to understand the biological mechanism of tumors, but also provides important information for developing more precise treatment strategies.

[0003] At present, the inference of cell composition in TME mainly relies on the computational analysis method of bulk RNA-seq data. Traditional cell infiltration inference methods can be roughly divided into two categories: one is based on the deconvolution model method, such as CIBERSORT, EPIC, quanTIseq and TIMER, etc. These methods construct a reference expression matrix and use a linear mixing model to infer the proportion of different cell types in the sample; the other is based on the enrichment scoring method of marker gene set, such as ssGSEA, xCell and MCP-counter, which calculate the activity of each cell type in the sample by enrichment analysis.

[0004] Although the existing methods reveal the cell composition in TME to some extent, there are still many limitations. First, the description of traditional methods is often limited to immune cells, ignoring the infiltration characteristics of stromal cells, stem cells and their subgroups, and cannot construct a comprehensive cell atlas. Second, these methods often process gene expression characteristics independently, ignoring the functional synergy or regulatory relationship between genes, making it difficult to accurately distinguish cell subtypes with similar functions or co-expression characteristics. In addition, the deconvolution method has strong dependence on reference data sets, and has weak generalization ability in different platforms or tissue sources, making it difficult to adapt to tumor heterogeneity and cell heterogeneity. In addition, the enrichment scoring method based on marker genes is usually a normalized score, which lacks proportional interpretation and is difficult to compare directly between different samples.

[0005] To solve these problems, researchers have tried to introduce functional information to assist cell infiltration inference in recent years. CITMIC is an innovative solution. CITMIC constructs a cell-GO bipartite graph based on Gene Ontology (GO) functional annotations, and calculates the activity of cell types in the sample using a graph propagation algorithm. However, although the CITMIC method has significantly improved accuracy and cell coverage compared to traditional methods, there are still some limitations. First, although the GO functional annotations used by CITMIC can provide functional similarity between cells, they do not consider the real interactions between cells in terms of physical or signal transduction. Second, GO information has certain static and redundant properties and cannot reflect molecular-level changes during tumor progression. In addition, CITMIC only constructs a cell relationship network based on functional module similarity, ignoring potential structural biological information such as protein-protein interaction (PPI) relationships that regulate cell behavior. Therefore, the CITMIC method may have weak biological interpretation and insufficient recognition of local specificity.

[0006] In addition, different cell types in tumors often communicate and coordinate functions through protein-protein interaction (PPI) networks. PPI networks can directly describe the physical and signal connection patterns between cells and are widely used in disease mechanism research and target screening. However, few current studies combine PPI networks with cell infiltration inference. Therefore, how to integrate PPI network information into cell infiltration inference to reveal the real physical connection patterns between cells is still a research problem that needs to be solved.

[0007] In summary, there is currently a lack of a cell infiltration inference method that can simultaneously integrate functional information (such as GO) and structural information (such as PPI). Combining these two types of information, constructing a cell relationship network with more biological interpretation, and accurately depicting cell distribution and interaction in tumor tissues are important challenges in current tumor research and precision medicine. SUMMARY

[0008] To overcome the above-mentioned defects of the prior art, the present application provides a cell infiltration inference method and system that integrates GO functional annotations and PPI network information, to construct a more realistic cell communication map and comprehensively analyze the state and function of multiple cell types in TME, improving the characterization ability and prediction effect of tumor immune characteristics.

[0009] In a first aspect, the present application provides a cell infiltration inference method that integrates GO functional annotations and PPI network information, which comprises: S1: Collect a dataset and perform preprocessing, wherein the dataset includes gene expression data, GO functional annotation data, and PPI network data; S2: constructing a cell-cell functional association network according to the gene expression data and the GO functional annotation data; S3: constructing a cell-cell physical interaction network according to the gene expression data and the PPI network data; S4: performing weighted fusion processing on the cell-cell functional association network and the cell-cell physical interaction network to obtain a comprehensive cell relationship network; S5: calculating a final cell infiltration score based on the comprehensive cell relationship network by using a restart walk algorithm, and inferring the infiltration degree in a tumor microenvironment according to the final cell infiltration score.

[0010] The application innovatively fuses Gene Ontology (GO) functional annotation information and protein-protein interaction (PPI) network data, comprehensively considers the functional similarity and physical or signal interaction between cells by constructing a weighted fusion of a cell-cell functional association network and a cell-cell physical interaction network, and can cover multiple cell types, including immune cells, interstitial cells, stem cells and the like, when constructing the cell relationship network, so that a more comprehensive TME cell atlas is constructed, thereby providing more comprehensive and accurate cell infiltration inference. The application effectively overcomes the limitation of traditional methods which only rely on a single data source, so that the cell infiltration inference is more in line with the real biological characteristics of the tumor microenvironment.

[0011] Preferably, the step S2 of constructing a cell-cell functional association network according to the gene expression data and the GO functional annotation data specifically comprises: S21: calculating a Jaccard coefficient and weighted gene expression data according to the gene expression data and the GO functional annotation data; S22: calculating an association comprehensive weight according to the Jaccard coefficient and the weighted gene expression data; and constructing a GO-cell bipartite network according to the association comprehensive weight; S23: constructing a cell-cell functional association network according to the association comprehensive weight and the bipartite network; Wherein, each element in the cell-cell functional association network represents the association strength between two cell types.

[0012] Preferably, the step S3 of constructing a cell-cell physical interaction network according to the gene expression data and the PPI network data specifically comprises: S31: calculating a gene expression and network weight comprehensive contribution value according to the gene expression data and the PPI network data; S32: calculating the shortest path distance between genes by using a Floyd algorithm; and performing gene distance stability correction on the shortest path distance between genes; S33: constructing a cell-cell physical interaction network according to the result of the comprehensive contribution of gene expression and network weight and the stability correction of the distance between genes.

[0013] The nodes in the comprehensive cell relationship network represent different cell types, and the weight of the edge represents the correlation between the cell types.

[0014] The step S5 is based on the comprehensive cell relationship network, and the final cell infiltration score is calculated by restarting the walk algorithm, specifically including: S51: calculating the node cell infiltration score for each node in the comprehensive cell relationship network by restarting the walk algorithm; S52: logarithmic transformation is performed on the node cell infiltration score; S53: the result of the logarithmic transformation is normalized to obtain the final cell infiltration score.

[0015] In a second aspect, based on the same inventive concept, the present application further provides a cell infiltration inference model integrating GO functional annotation and PPI network information, which comprises the cell-cell functional association network, the cell-cell physical interaction network and the comprehensive cell relationship network in the method of the first aspect.

[0016] The PPI information and the GO functional annotation are integrated to directly reflect the connection mode between cells at the molecular level, wherein the PPI information is from the perspective of protein interaction, and the GO functional annotation is from the perspective of cell function, which complement each other, so that the calculated cell infiltration degree result is more reliable, thereby providing a more valuable basis for precise treatment of tumors.

[0017] In a third aspect, based on the same inventive concept, the present application further provides a system of a cell infiltration inference model integrating GO functional annotation and PPI network information, which comprises: A data acquisition unit for data set data acquisition; wherein the data set comprises gene expression data, GO functional annotation data and PPI network data; A first data processing unit for constructing a cell-cell functional association network according to the gene expression data and the GO functional annotation data; A second data processing unit for constructing a cell-cell physical interaction network according to the gene expression data and the PPI network data; A third data processing unit for weighted fusion processing of the cell-cell functional association network and the cell-cell physical interaction network to obtain a comprehensive cell relationship network; and a fourth data processing unit configured to calculate a final cell infiltration score based on the integrated cell relationship network by restarting the walk algorithm, and to infer the infiltration degree in the tumor microenvironment according to the final cell infiltration score.

[0018] Preferably, the first data processing unit further comprises: a first calculation module configured to calculate a Jaccard coefficient and a weighted gene expression data according to the gene expression data and the GO function annotation data; a second calculation module configured to calculate an integrated correlation weight according to the Jaccard coefficient and the weighted gene expression data, and to construct a GO x cell bipartite network according to the integrated correlation weight; and a first network construction module configured to construct a cell x cell function correlation network according to the integrated correlation weight. Each element in the cell x cell function correlation network represents the correlation strength between two cell types.

[0019] Preferably, the second data processing unit further comprises: a third calculation module configured to calculate a gene expression and network weight integrated contribution value according to the gene expression data and the PPI network data; a shortest path calculation module configured to calculate a shortest path distance between genes by using the Floyd algorithm, and to correct the shortest path distance between genes for gene distance stability; and a second network construction module configured to construct a cell x cell physical interaction network according to the gene expression and network weight integrated contribution value and the result of the gene distance stability correction.

[0020] In a fourth aspect, based on the same inventive concept, the present application further provides a computer device, which comprises a processor and a memory, and the memory stores at least one instruction, which is loaded and executed by the processor to implement the cell infiltration inference method integrating GO function annotation and PPI network information as described in the first aspect.

[0021] Compared with the prior art, the present application has the following advantages: The cell infiltration inference method fusing GO function annotation and PPI network information provided in the application innovatively integrates GO function annotation and PPI network information, and breaks through the dependence of traditional methods on single data. GO function annotation covers the function panorama of cells in biological processes, and PPI network introduces physical connection evidence of molecular interaction, and the two form a "function-structure" double pillar, so that the model can understand cell synergy from the biological pathway level and analyze cell direct interaction from the protein interaction level, avoiding one-sidedness of a single perspective, and providing a more stereoscopic cognitive framework for tumor microenvironment analysis.

[0022] In addition, compared with the traditional method which only focuses on part of immune cells, the GO function annotation based on the application can identify the infiltration characteristics of cell types such as immune cells, interstitial cells and stem cells, and the coverage is more than 3 times. At the same time, through the interaction mode of PPI network to the cell subpopulation (such as different polarized state of macrophages and T cell subtypes), the leap from "general cell type analysis" to "full spectrum of subpopulation analysis" is realized, and the complex cell composition of tumor microenvironment is fully unlocked.

[0023] In summary, the application realizes significant technical breakthrough and application value improvement in the field of tumor microenvironment cell infiltration inference through multi-source data fusion and innovative algorithm design. The bulk RNA-seq data, GO function annotation and PPI network data are innovatively integrated, breaking through the limitation of traditional single data processing, which can not only cover the function characteristics of cell types such as immune cells and interstitial cells based on GO annotation, but also directly depict the physical interaction and signal transduction relationship between cells through PPI network, and construct a more complete and real tumor microenvironment cell relationship map. At the same time, the random walk algorithm combined with the weighted fusion strategy is adopted, which ensures that the calculation efficiency is more than 50% higher than that of the traditional deep learning method, and realizes the self-adaptation of different tumor types and sequencing platform samples. In practical application, the method shows excellent performance in survival analysis, far exceeding the traditional method, and provides a reliable basis for clinical judgment of patient prognosis. In addition, the technology does not require special data or complex equipment, has strong compatibility and high expansibility, and is easy to be clinically transformed, providing a new and efficient computing tool for tumor research and treatment. BRIEF DESCRIPTION OF DRAWINGS

[0024] Figure 1 is the cell infiltration inference method flow chart fusing GO function annotation and PPI network information provided in the embodiment of the application.

[0025] Figure 2 is the verification result of the infiltration score (predicted value) of different methods and flow cytometry (true value) provided in the embodiment of the application.

[0026] Figure 3 This invention illustrates the correlation between the infiltration scores of different cell subpopulations and patient prognosis in its embodiments.

[0027] Figure 4 This is a survival prediction performance analysis shown in an embodiment of the present invention.

[0028] Figure 5 This is a survival prediction performance analysis of the existing method CITMIC as shown in the embodiments of the present invention. Detailed Implementation

[0029] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions will be clearly and completely described below in conjunction with the embodiments of the present invention. Obviously, the described embodiments are only some, not all, of the embodiments of the present invention. All other embodiments obtained by those skilled in the art based on the embodiments of the present invention without creative effort are within the scope of protection of the present invention.

[0030] Example 1: As Figure 1 As shown, this invention proposes a cell invasion inference method that integrates GO functional annotation and PPI network information. By incorporating PPI information and GO functional annotation, the method can directly reflect the connection patterns between cells at the molecular level. PPI information reflects protein-protein interactions, while GO functional annotation reflects cell function. The two complement each other, making the calculated cell invasion level more reliable and providing more valuable evidence for precision tumor treatment. The specific implementation process is shown in steps 1 to 5.

[0031] Step 1: Collect the dataset and preprocess it.

[0032] The dataset includes gene expression data, GO functional annotation data, and PPI network data.

[0033] (1) Collect gene expression data. Optionally, obtain gene expression data from the ImmPort database. Specific gene expression data include SDY311 and SDY420, where SDY311 is data from immune-related healthy individuals and SDY420 is data from patients with immune-related diseases. Gene expression data can be downloaded using the access number provided by the database and saved in a common format, such as CSV, TXT, or TSV, for subsequent processing and analysis.

[0034] Also, download gene expression data and clinical data of TCGA-LGG (low-grade glioma) cancer patients through the UCSC Xena platform. Select the TCGA-LGG dataset on the UCSC Xena platform, and download the gene expression data (such as RNA-Seq data) and related clinical data (such as patient clinical information, staging, prognosis, etc.). Extract the required gene expression matrix and save it in a standard format such as TXT or CSV file for subsequent analysis.

[0035] (2) Collect GO function annotation data, and optionally download GO function annotation data from the MSigDB website. Select GO data sets related to gene function and pathways, especially annotations related to biological processes (BP), molecular functions (MF), and cellular components (CC). Download the relevant GO function set file (such as GMT format) and format the data for use in subsequent analysis.

[0036] (3) Collect protein-protein interaction (PPI) network data. Download protein-protein interaction networks and their detailed information from the STRING database. In the STRING database, select the corresponding species (such as humans) and the required PPI data (for example, include interaction relationships with a protein interaction score greater than or equal to 700). When downloading data, select to obtain detailed protein interaction information, such as protein ID, interaction score, and relationship between proteins.

[0037] Further, by calculating the intersection of genes in the gene expression data and the gene symbols in the PPI network, genes that exist in both can be filtered out. Based on these intersection genes, further filter the interaction relationships in the PPI network, and only keep the protein interactions related to the intersection genes, thereby narrowing the scope of the PPI network and focusing on interactions closely related to gene expression data, facilitating subsequent analysis and research.

[0038] In this embodiment, by calculating the intersection of genes in the gene expression data and the gene symbols in the PPI network, specifically including: 1) Load gene expression data: Load the gene expression matrix obtained from the ImmPort database (SDY311 and SDY420) and TCGA-LGG cancer patient data. The data format can be CSV, TXT, etc., and each row represents the expression of a gene.

[0039] 2) Load PPI network data: PPI network data downloaded from the STRING database contains the interaction relationships between proteins. Each record usually includes two protein IDs, their interaction score (such as confidence score), and other relationship information.

[0040] 3) Convert PPI protein IDs to gene symbols: Convert the protein IDs in the PPI network data to gene symbols. This can be done by using Ensembl, NCBI, or other gene annotation databases (e.g. biomart, UniProt). Ensure that all protein IDs are correctly mapped to the corresponding gene symbols.

[0041] 4) Select genes of interest: Extract the genes of interest from the gene expression data. For example, genes related to a disease, or highly differentially expressed genes. Ensure that the symbols of these genes match the gene symbols in the PPI network data.

[0042] 5) Filter gene expression data: Filter the gene expression data based on a threshold of expression level to select genes of interest. For example, genes with expression level greater than a certain value, or significantly differentially expressed genes.

[0043] 6) Calculate intersection: Extract genes from the PPI network that match the gene symbols in the gene expression data. For example, if the PPI network data contains gene A, gene B, gene C, and gene D, and the gene expression data also contains these genes, then these genes are matching genes.

[0044] Calculate the intersection of gene symbols in the gene expression data and gene symbols in the PPI network data. The specific method is: Convert the gene symbol column in the gene expression data and the gene symbol column in the PPI network data into set form.

[0045] Calculate the intersection of the two sets to obtain the set of genes that exist in both the gene expression data and the PPI network data. According to the result of the intersection, further narrow the scope of the PPI network. Only keep the gene pairs that have interaction relationships with the genes in the gene expression data. That is, if a gene in a protein interaction pair is in the intersection gene list, keep the protein interaction relationship; otherwise, delete the relationship. According to the intersection gene and the screening result of the PPI network, construct a sub-network that only contains the interactions between the intersection genes. This will be a smaller PPI network closely related to the gene expression data. Thus, the resulting sub-network has more biological significance and can provide valuable candidate genes for further functional analysis and disease research.

[0046] Step 2: Construct a cell-cell functional association network based on gene expression data and GO functional annotation data; In this embodiment, the cell-cell functional association network is constructed, which specifically includes: S21: Calculate the Jaccard coefficient and weighted gene expression data based on the gene expression data and GO functional annotation data; Preferably, the Jaccard coefficient is used to measure the similarity between two sets, and the Jaccard coefficient is calculated as follows: The calculation formula is as follows: ; In the formula, C represents the genes contained in the GO annotation, and G represents the marker gene set of a specific cell type.

[0047] |C∩G| is the intersection size of the two sets, that is, the number of genes that belong to both the GO annotation and the marker gene set of the specific cell type.

[0048] |C∪G| is the union size of the two sets, that is, the total number of genes that belong to the GO annotation or the marker gene set of the specific cell type.

[0049] For example, if there are two sets as follows: ; It can be obtained that the Jaccard coefficient between the GO annotation gene set and the marker gene set of the specific cell type is 0.33, indicating that the similarity between the two sets is 33%.

[0050] Preferably, the correlation between the gene expression of a specific GO annotation and a cell type is measured by weighted gene expression data, and the weighted gene expression data is calculated as follows: The calculation formula is as follows: ; Wherein, GEP g is the gene expression value of gene g in a specific cell type. Wg is the weight of gene g in the PPI network, which is calculated by the PageRank algorithm. The PageRank algorithm assigns a weight value according to the interaction relationship between genes, reflecting the importance of the gene in the network, g is the intersection of the GO annotation and the marker gene set of the specific cell type, and W'g is the normalization of the gene expression. S22: Calculate the correlation comprehensive weight according to the Jaccard coefficient and the weighted gene expression data; construct a GOxcell bipartite network according to the correlation comprehensive weight; The comprehensive weight Wc, G is the product of the Jaccard coefficient and wGEP g , and the comprehensive weight reflects the correlation strength between the GO annotation and the specific cell type. The formula is as follows: ; For example: Jaccard(C,G)=0.33; wGEPg1=4.16; wGEPg2=4.56; wGEPg3=3.55; The weighted gene expression data of all genes are summed to obtain: wGEPsum=wGEPg1+wGEPg2+wGEPg3=4.16+4.56+3.55=12.27; The comprehensive weight Wc,G is calculated: Wc,G=Jaccard(C,G) x wGEPsum=0.33 x 12.27=4.05; Based on the calculated comprehensive weight Wc,G, a bipartite network is constructed.

[0051] In this bipartite network, nodes represent different GO annotations and cell types, and the weights of edges are represented by the comprehensive weight Wc,G. The edge weights of the bipartite network reflect the strength of the association between GO annotations and specific cell types. The higher the weight of the edge, the closer the relationship between the GO annotation and the cell type. Through the bipartite network, complex gene expression data and functional annotations can be systematized, avoiding direct calculation of gene similarity in the cell x cell network. Through the GO x cell bipartite network, cell types are connected through the GO functional items they share. For example, if two cell types share multiple GO functional items, their functional similarity is high. The bipartite network makes this functional sharing relationship intuitive, thereby providing the necessary information for constructing a cell x cell functional association network.

[0052] S24: Constructing a cell x cell functional association network according to the association comprehensive weight and the bipartite network; Wherein each element in the association matrix of the cell x cell functional association network represents the association strength between two cell types.

[0053] The association strength R between cell type Ci and cell type Cj Ci,j The association strength R between cell type Ci and cell type Cj C,G can be calculated by the product of the comprehensive weight W Ci and its transpose, as follows: R Cj = W C,G x W T C,G ; Example: Given three cell types C1, C2 and C3, and the comprehensive weights of their association with GO annotations have been calculated: W C1,G =[4.16,4.56,3.55] (for cell type C1).

[0054] W C2,G =[5.00,3.80,4.00] (for cell type C2).

[0055] W C3,G =[3.20,3.60,2.80] (for cell type C3).

[0056] Calculate the strength of association between cell types C1 and C2: RC C1,C2 =W C1,G ×W C2,G T =[4.16,4.56,3.55]×[5.00,3.80,4.00] T The calculation process is as follows: R CC1,C2 =(4.16×5.00)+(4.56×3.80)+(3.55×4.00)=20.80+17.33+14.20=52.33.

[0057] Calculate R CC1,C3 : Calculate the strength of association between cell types C1 and C3: RC C1,C3 =W C1,G ×W C3,GT =[4.16,4.56,3.55]×[3.20,3.60,2.80] T .

[0058] The calculation process is as follows: RC C1,C3 =(4.16×3.20)+(4.56×3.60)+(3.55×2.80)=13.31+16.42+9.94=39.67.

[0059] Calculate RC C2,C3 : Calculate the strength of association between cell types C2 and C3: RC C2,C3 =W C2,G ×W C3,G T =[5.00,3.80,4.00]×[3.20,3.60,2.80] T .

[0060] The calculation process is as follows: RC C2,C3 =(5.00×3.20)+(3.80×3.60)+(4.00×2.80)=16.00+13.68+11.20=40.88.

[0061] Based on the above calculation results, we can construct the association matrix of the cell-cell functional association network: .

[0062] In this embodiment, the cell-cell function correlation matrix is obtained by calculating the product of the comprehensive weight and its transpose. Each element in the matrix represents the correlation strength between two cell types, reflecting their functional correlation in gene expression and PPI network. This provides a basis for further cell function analysis and network research.

[0063] S3: Constructing a cell-cell physical interaction network according to gene expression data and PPI network data; Preferably, the constructing a cell-cell physical interaction network specifically comprises: S31: Calculating the gene expression and network weight comprehensive contribution value according to gene expression data and PPI network data; The formula is: gene expression and network weight comprehensive contribution value = W g1 ·GEP g1 +W g2 ·GEP g2 .

[0064] The gene expression and network weight comprehensive contribution value reflects the comprehensive contribution of the expression level of a gene in a cell type and the importance of the network.

[0065] For example: In cell type i (immune cell), the expression value of gene 1 is GEPg1=2.5; the network weight of gene 1 is Wg1=1.2.

[0066] In cell type j (neuron cell), the expression value of gene 2 is GEPg2=3.0, and the network weight of gene 2 is Wg2=1.5.

[0067] Then, the calculation of the gene expression and network weight comprehensive contribution value is: Wg1⋅GEPg1+Wg2⋅GEPg2=(1.2⋅2.5)+(1.5⋅3.0)=7.5.

[0068] This value reflects the comprehensive contribution of the expression level of gene 1 and gene 2 in immune cells and neuron cells and their importance in the network. Using the calculation method of gene expression and network weight comprehensive contribution, the influence of genes on different cell types can be quantified, revealing the role of genes in the cell network.

[0069] S32: Calculating the shortest path distance between genes by Floyd algorithm; correcting the distance stability between genes for the shortest path distance between genes; The connection strength of genes in the PPI network is measured by the intergenic distance d, which is calculated by the Floyd algorithm. Specifically, the Floyd algorithm is used to calculate the shortest path distance between two genes in the PPI network, thereby reflecting the connection strength between them. In actual calculation, there may be no direct connection between certain genes, which may lead to unstable calculation (for example, the distance is zero). In order to solve this problem, the present application further introduces an intergenic distance stability correction (plus a small correction term ε) to ensure the stability and accuracy of the calculation process.

[0070] S33: According to the results of the gene expression and network weight comprehensive contribution value and the intergenic distance stability correction, a cell-cell physical interaction network is constructed.

[0071] By integrating S31 and S32, the cell-cell physical interaction network can be calculated, and the formula is: ; In the formula, the numerator measures the comprehensive contribution of the gene pair from the expression of the molecule and the importance of the network; the denominator adjusts and normalizes the numerator from the perspective of the actual interaction strength between genes and the calculation stability. The combination of the two enables the comprehensive and accurate construction of the cell-cell physical interaction network, providing strong support for the study of the functional association between cells.

[0072] S4: The cell-cell functional association network and the cell-cell physical interaction network are weighted and fused to obtain a comprehensive cell relationship network.

[0073] The formula used is: .

[0074] β can be adjusted according to different input data. At this point, each sample can construct an F network, in which the nodes represent different cell types and the weights of the edges represent the association relationship between cell types. Thus, the cell infiltration score can be inferred from the perspective of protein interaction and cell function.

[0075] S5: Based on the comprehensive cell relationship network, the final cell infiltration score is calculated by the restart walk algorithm, and the infiltration degree in the tumor microenvironment is inferred according to the final cell infiltration score.

[0076] Specifically, it includes: S51: The node cell infiltration score for each node in the comprehensive cell relationship network is calculated by the restart walk algorithm.

[0077] The weight update formula of the restart walk algorithm is: ; where, a is the restart probability (usually take 0.85), I(g) is the initial weight of cell g, N(g) is the neighbor node set of cell g, and dg' is the out-degree of node g'.

[0078] S52: Log-transforming the node cell infiltration score; By the restart walk algorithm, a Score can be calculated for each node (cell type) in the network, and the non-positive values can be processed by log-transformation, and the formula is: .

[0079] S53: Normalizing the log-transformed result to obtain the final cell infiltration score.

[0080] By normalization processing, the infiltration score is scaled to the range of 0 to 1 for cross-sample comparison, and the final infiltration score is obtained, and the formula is: .

[0081] In order to further verify the cell infiltration inference method of fusing GO function annotation and PPI network information according to the application, the correlation coefficients of the infiltration scores (predicted values) and flow cytometry (true values) of different methods on the adrenal gland data set are compared. Among them, the existing mainstream methods are CIBERSORT, MCP-counter, xCell and CITMIC; the cell infiltration inference method of the application is marked as ours. The Spearman rank correlation coefficient of the predicted infiltration score and the true value (range: [-1.0, 1.0]). As shown in Figure 2 the cell infiltration inference method of the application is significantly better than the prior art on all cell types, which is specifically shown as follows:

[0082] It can be seen that the application comprehensively surpasses the prior art system while maintaining the advantages of CITMIC function annotation, and establishes a new standard for cell infiltration analysis through PPI network weighting and dynamic optimization mechanism.

[0083] Figure 3 Survival analysis of the method of the application. The correlation between the infiltration scores of different cell subgroups and the prognosis of patients is shown, and 65 cell subgroups are significantly related to the prognosis. This shows the potential influence of many cell types in the tumor microenvironment on the prognosis, highlighting the importance of comprehensive consideration of multiple cell types. The method can effectively identify these cell subgroups with prognostic significance, providing key information for the construction of subsequent risk models.

[0084] Figures 4-5 As shown in Figure 4 is the survival prediction performance analysis of the method of the application. Figure 5To compare the survival prediction performance of the existing method CITMIC, the ROC curves of the present method and the CITMIC method at different time points (1 year, 3 years, 5 years, and 7 years) are shown, reflecting the performance difference of the two methods in the survival prediction task, and indicating that the present method has higher AUC values at all time points, i.e., better survival prediction ability.

[0085] In summary, the present application innovatively integrates Gene Ontology (GO) functional annotation information and protein-protein interaction (PPI) network data, comprehensively considers the functional similarity and physical or signal interaction between cells by constructing a weighted fusion of cell-cell functional association network and cell-cell physical interaction network, and can cover multiple cell types, including immune cells, interstitial cells, stem cells, etc., when constructing the intercellular relationship network, thus providing a more comprehensive and accurate cell infiltration inference. The present application effectively overcomes the limitations of traditional methods that rely on a single data source, making the cell infiltration inference more consistent with the true biological characteristics of the tumor microenvironment.

[0086] In Example Two, the present application further provides a cell infiltration inference model integrating GO functional annotation and PPI network information, which includes the cell-cell functional association network, the cell-cell physical interaction network, and the comprehensive cell relationship network as described in Example One.

[0087] By integrating PPI network and GO functional annotation information, the cell infiltration inference model proposed by the present application can comprehensively reflect the connection mode between cells at the molecular level, and accurately infer the infiltration degree of immune cells in tumor tissue. This model not only improves the accuracy of cell infiltration inference, but also provides an important basis for precise treatment of tumors. The popularization and application of this method can provide more reliable data support for personalized treatment plans for tumor immunotherapy.

[0088] In Example Three, the present application further provides a system for a cell infiltration inference model integrating GO functional annotation and PPI network information, which includes: a data acquisition unit for acquiring a data set; wherein the data set includes gene expression data, GO functional annotation data, and PPI network data; a first data processing unit for constructing a cell-cell functional association network based on gene expression data and GO functional annotation data; a second data processing unit for constructing a cell-cell physical interaction network based on gene expression data and PPI network data; a third data processing unit configured to perform weighted fusion processing on the cell-cell functional association network and the cell-cell physical interaction network to obtain a comprehensive cell relationship network; and a fourth data processing unit configured to calculate a final cell infiltration score by restarting a walk algorithm based on the comprehensive cell relationship network, and infer the infiltration degree in a tumor microenvironment according to the final cell infiltration score.

[0089] Preferably, the first data processing unit further comprises: a first calculation module configured to calculate a Jaccard coefficient and weighted gene expression data according to gene expression data and GO function annotation data; a second calculation module configured to calculate an association comprehensive weight according to the Jaccard coefficient and the weighted gene expression data, and construct a GOxcell bipartite network according to the association comprehensive weight; and a first network construction module configured to construct the cell-cell functional association network according to the association comprehensive weight. Each element in the cell-cell functional association network represents the association strength between two cell types.

[0090] Preferably, the second data processing unit further comprises: a third calculation module configured to calculate a gene expression and network weight comprehensive contribution value according to gene expression data and PPI network data; a shortest path calculation module configured to calculate a shortest path distance between genes by a Floyd algorithm, and perform gene distance stability correction on the shortest path distance between genes; and a second network construction module configured to construct the cell-cell physical interaction network according to the gene expression and network weight comprehensive contribution value and the result of the gene distance stability correction.

[0091] In embodiment four, the present application further provides a computer device comprising a processor and a memory, wherein the memory stores at least one instruction, and the at least one instruction is loaded and executed by the processor to implement the cell infiltration inference method of fusing GO function annotation and PPI network information as described in embodiment one.

[0092] Although the example embodiments have been described herein with reference to the accompanying drawings, it is to be understood that the above-described example embodiments are merely exemplary and are not intended to limit the scope of the present application thereto. Various changes and modifications can be made thereto by those of ordinary skill in the art without departing from the scope and spirit of the present application. All such changes and modifications are intended to be included within the scope of the present application as claimed in the appended claims.

[0093] It is to be understood that the terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting; it is not intended to exclude myriad other embodiments of the present application that other inventors can develop based on the description contained herein. That is, although the present application is described in terms of particular embodiments and illustrative figures, it should be apparent that the disclosure is not limited to these embodiments. Rather, the present application is directed to whatever can be made, used and or worked by anyone skilled in the art using the disclosure herein including the best mode for carrying out the present application. Various modifications and changes can be made thereto by those skilled in the art which freely exercise their skill and knowledge, with the frame- work being merely for the purposes of illustration and not limitation of the present application. It is therefore desired that applicable statutes not be construed as limiting the scope of the present application but rather as broad as the statutes permit. It is intended that all such modifications, changes and improvements fall within the spirit and scope of the present application as claimed.

[0094] While the present application has been described with reference to the above specific embodiments, it is apparent that many alternatives, modifications and variations will be apparent to those skilled in the art in light of the above description. Accordingly, it is intended to embrace all such alternatives, modifications and variations as can come within the spirit and scope of the present application.

Claims

1. A method of inferring cell infiltration by fusing GO functional annotations with PPI network information, characterized in that, The method comprises the following steps: S1: collecting a data set and performing preprocessing, wherein the data set comprises gene expression data, GO function annotation data, and PPI network data; S2: constructing a cell-cell function correlation network according to the gene expression data and the GO function annotation data; S3: constructing a cell-cell physical interaction network according to the gene expression data and the PPI network data; S4: performing weighted fusion processing on the cell-cell function correlation network and the cell-cell physical interaction network to obtain a comprehensive cell relationship network; S5: calculating a final cell infiltration score based on the comprehensive cell relationship network by using a restart walk algorithm, and inferring the infiltration degree in a tumor microenvironment according to the final cell infiltration score.

2. The method of claim 1, wherein the method is characterized by: The step S2 comprises the following steps: S21: calculating a Jaccard coefficient and weighted gene expression data according to the gene expression data and the GO function annotation data; S22: calculating a correlation comprehensive weight according to the Jaccard coefficient and the weighted gene expression data; and constructing a GO-cell bipartite network according to the correlation comprehensive weight; S23: constructing a cell-cell function correlation network according to the correlation comprehensive weight and the bipartite network; Each element in the cell-cell function correlation network represents the correlation strength between two cell types.

3. The method of claim 2, wherein the method further comprises: The step S3 comprises the following steps: S31: calculating a gene expression and network weight comprehensive contribution value according to the gene expression data and the PPI network data; S32: calculating an intergenic shortest path distance by using a Floyd algorithm; and performing intergenic distance stability correction on the intergenic shortest path distance; S33: constructing a cell-cell physical interaction network according to the gene expression and network weight comprehensive contribution value and the result of the intergenic distance stability correction.

4. The method of claim 3, wherein the method further comprises: The nodes in the comprehensive cell relationship network represent different cell types, and the weights of the edges represent the correlation between the cell types.

5. The method of claim 4, wherein the GO function annotation and PPI network information are fused to infer cell infiltration. The step S5 comprises the following steps: S51: calculating a node cell infiltration score for each node in the comprehensive cell relationship network by using a restart walk algorithm; S52: performing logarithmic conversion on the node cell infiltration score; S53: performing normalization processing on the result of the logarithmic conversion to obtain a final cell infiltration score.

6. A cell infiltration inference model that fuses GO functional annotations with PPI network information, characterized in that, The model comprises the cell-cell function correlation network, the cell-cell physical interaction network, and the comprehensive cell relationship network in the method according to any one of claims 1-5.

7. A system for cell infiltration inference model using fusion of GO functional annotation and PPI network information as claimed in claim 6, wherein, The system comprises: a data acquisition unit for acquiring a data set; wherein the data set comprises gene expression data, GO function annotation data, and PPI network data; a first data processing unit for constructing a cell-cell function correlation network according to the gene expression data and the GO function annotation data; a second data processing unit for constructing a cell-cell physical interaction network according to the gene expression data and the PPI network data; a third data processing unit for performing weighted fusion processing on the cell-cell function correlation network and the cell-cell physical interaction network to obtain a comprehensive cell relationship network; and a fourth data processing unit for calculating a final cell infiltration score based on the comprehensive cell relationship network by using a restart walk algorithm, and inferring the infiltration degree in a tumor microenvironment according to the final cell infiltration score. And a fourth data processing unit configured to calculate a final cell infiltration score based on the integrated cell relationship network by restarting a walk algorithm, and infer an infiltration level in a tumor microenvironment according to the final cell infiltration score.

8. The system of claim 7, wherein, The first data processing unit further comprises: a first calculation module configured to calculate a Jaccard coefficient and weighted gene expression data according to gene expression data and GO function annotation data; a second calculation module configured to calculate an integrated correlation weight according to the Jaccard coefficient and the weighted gene expression data, and construct a GO x cell bipartite network according to the integrated correlation weight; and a first network construction module configured to construct a cell x cell function correlation network according to the integrated correlation weight. Each element in the cell x cell function correlation network represents the correlation strength between two cell types.

9. The system of claim 7, wherein, The second data processing unit further comprises: a third calculation module configured to calculate an integrated contribution value of gene expression and network weight according to gene expression data and PPI network data; a shortest path calculation module configured to calculate a shortest path distance between genes by a Floyd algorithm, and perform a gene distance stability correction on the shortest path distance between genes; and a second network construction module configured to construct a cell x cell physical interaction network according to the integrated contribution value of gene expression and network weight and the result of the gene distance stability correction.

10. A computer device, comprising: The computer device comprises a processor and a memory, and the memory stores at least one instruction, which is loaded and executed by the processor to implement the cell infiltration inference method integrating GO function annotation and PPI network information according to any one of claims 1 to 5.

Images