Spatial omics tumor evolution prediction method and system based on graph neural network
Through the method based on graph neural network, multimodal data is integrated and comprehensive spatial map is constructed, which solves the problem of insufficient data fragmentation and model adaptability in tumor research, and accurately predicts the spatial and temporal changes of tumors and the various cancer types. Research has improved the research efficiency and targeted treatment strategies.
Patent Information
- Application Number
- CN202410914627.1
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-07-09
- Publication Date
- 2024-11-15
- Estimated Expiration
- 2044-07-09
AI Technical Summary
The prior art has problems such as fragmentation of data, insufficient multimodal data integration, limited model adaptability and high computational complexity in tumor evolution research, making it difficult to effectively capture the spatial and temporal changes of tumors and the diversity of different cancer types.
Using spatial oscillary tumor evolution prediction method based on graph neural network, the integrated spatial map is constructed, gene expression, spatial location and imaging features are integrated, and the graph neural network model training is used to extract features from the data, identify copy number variations and construct tumor evolution. tree, realizes spatiotemporal inference of tumor cloning.
It improves the prediction accuracy of tumor evolution patterns, enhances the understanding of tumor heterogeneity, has broad application prospects, can be applied to a variety of cancer types, improves research efficiency and supports the formulation of personalized treatment strategies.
Smart Images

Figure CN118969078A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of gene expression analysis, and in particular to a spatial omics tumor evolution prediction method and system based on graph neural network. Background Art
[0002] Tumor evolution is a complex multi-step process with genetic, phenotypic and epigenetic heterogeneity. Traditional pathological methods mainly rely on morphological observation of tissue sections, and make diagnoses by observing the patient's tissue structure and cytopathological characteristics under a microscope. However, simple pathological images cannot provide molecular information of lesions, and comprehensive exploration of diseases usually requires the combination of molecular diagnostic techniques.
[0003] In recent years, the rapid development of multi-omics technologies has surpassed the limitations of traditional pathology. These innovative methods help to better understand tumors by analyzing DNA, RNA and proteins within cancer cells. This not only helps to accurately locate the type and stage of the tumor, but also can identify specific cells and reveal important molecular markers, which is of great significance for the diagnosis and treatment of tumors.
[0004] Existing analytical methods include:
[0005] 1. Spatial omics technology: Spatial omics technology allows gene expression analysis while retaining tissue spatial information. By sequencing gene expression at various locations in a tissue sample, gene expression data with precise spatial location information can be obtained. Such data provides a new opportunity for in-depth study of the spatial structure and function of biological tissues.
[0006] 2. Genetic information inference: Copy number variation (CNV) refers to the difference in the number of copies of certain specific DNA fragments in the genomes of different individuals. These structural differences may be caused by duplications, deletions or other changes. Common gene amplification and deletion in cancer cells have an important impact on the growth, drug sensitivity and resistance of cancer cells. InferCNV is a tool for inferring large-scale chromosome copy number changes from single-cell RNA sequencing data. By comparing the gene expression intensity of tumor cells and normal cells, gene amplification or deletion regions can be identified.
[0007] 3. Pseudo-time-space inference (PSTS): PSTS is a spatial graph-based method for modeling and revealing the relationship between dynamically changing cell transcriptional states across tissues. By combining spatial and temporal information, trajectory mapping can be performed in more detail to study the dynamic changes of cells during development, disease progression, and other processes.
[0008] Although these methods have achieved certain success in tumor research, they still have the following shortcomings:
[0009] 1. Data fragmentation: Most existing methods can only provide static "snapshot" data and cannot capture the dynamic progression of the tumor at each time point. Although existing spatial transcriptome data can provide spatial information, it cannot directly infer information about temporal changes.
[0010] 2. Insufficient integration of multimodal data: Although spatial omics technology can provide gene expression and spatial location information, it is still insufficient in integrating other phenotypic and imaging features. Traditional methods often analyze gene expression, morphological features or imaging data separately, failing to fully utilize the comprehensive advantages of multimodal data.
[0011] 3. Limited adaptability and generalization of the model: Existing models have limited adaptability and generalization when dealing with different cancer types. The diversity of tissue clones in different cancer types varies greatly, and it is necessary to develop a general model that can adapt to multiple cancer types to provide a wider range of application prospects.
[0012] 4. Computational complexity and efficiency: As the scale of data increases, existing methods have bottlenecks in computational complexity and efficiency. Especially when processing high-resolution spatial omics data, the computational speed and resource consumption of existing algorithms have become the main obstacles restricting their application.
[0013] In summary, existing technologies in tumor evolution research still have problems such as data fragmentation, insufficient integration of multimodal data, limited model adaptability and high computational complexity. A new method is urgently needed to overcome these shortcomings. Summary of the invention
[0014] The purpose of the present invention is to provide a spatial omics tumor evolution prediction method and system based on graph neural network, which uses spatial omics data to illustrate the spatial and temporal changes in tumor evolution, conduct spatiotemporal inference of tumor clonal evolution, and improve prediction accuracy.
[0015] The purpose of the present invention can be achieved by the following technical solutions:
[0016] A spatial omics tumor evolution prediction method based on graph neural network includes the following steps:
[0017] S1, data acquisition and loading: Acquire different types of spatial transcriptome data, including gene expression data and spatial location information;
[0018] S2, data preprocessing: preprocessing and normalizing the acquired spatial transcriptome data;
[0019] S3, Gene Annotation and Grouping: Annotate and sort gene expression count data according to genomic location, and then group genes;
[0020] S4, constructing a spatial neighbor graph and calculating spatial statistics: using the spatial location information and gene expression data in the spatial transcriptome data, constructing an adjacency matrix reflecting the spatial relationship between cells, and calculating spatial statistics, wherein the adjacency matrix represents the connection relationship between each cell and its neighboring cells;
[0021] S5, graph neural network model training: construct a spatial neighbor graph based on the adjacency matrix as the input of the graph neural network model, train the model, and learn features from the spatial neighbor graph;
[0022] S6, copy number estimation and diploid basic unit identification: identify reliable diploid basic units and preliminarily estimate the copy number of each basic unit in spatial omics;
[0023] S7, comprehensive spatial graph construction: add the estimated copy number to the spatial neighbor graph to construct a comprehensive spatial graph representing tumor heterogeneity, retrain the graph neural network model to capture the spatial distribution of genetic variations in tissue samples, and obtain latent embedding;
[0024] S8, breakpoint determination and copy number profile construction: Based on the estimated copy number, the segmentation algorithm is used to determine the breakpoints and obtain the copy number profile of each basic unit and spatial clone;
[0025] S9, downstream task analysis: Use latent embedding to perform downstream task analysis, construct a tumor evolution tree, classify malignant and non-malignant cells, and analyze tumor heterogeneity;
[0026] S10, Cross-sample analysis: extended to different spatial omics samples, comparative analysis of primary tumors and metastases.
[0027] The S2 comprises the following steps:
[0028] S21, drawing a transcript distribution map of each basic unit, filtering low-quality basic units according to a minimum transcript number threshold, and filtering low-expressed genes according to a minimum basic unit number threshold, wherein each basic unit represents an area of a preset size on a tissue section and provides gene expression information of the area;
[0029] S22, filtering mitochondrial genes, HLA genes, and cell cycle genes;
[0030] S23, Gene expression in each basic unit was normalized and log-transformed.
[0031] The S3 comprises the following steps:
[0032] S31, mapping ID to genome position, initializing genome position column;
[0033] S32, filtering discarded gene IDs and null values;
[0034] S33, traverse the filtered genes, fill in the chromosome location information, add annotations to the gene expression count data and sort them according to the genome location;
[0035] S34, sorting the genes according to their chromosomal positions into a plurality of groups, each group comprising a preset number of genes, and the gene expression value of each group is represented by the average expression level of the genes contained in the group;
[0036] S35, calculating the average count value of each group to obtain a count matrix, wherein the count matrix represents the gene expression data of each basic unit.
[0037] The S4 comprises the following steps:
[0038] S41, determine the adjacency relationship between cells through Delaunay triangulation or KNN algorithm to generate a spatial relationship map between cells;
[0039] S42, calculate the centrality score of each cell in the spatial map and calculate the cell co-occurrence probability;
[0040] S43, neighbor enrichment analysis was performed to evaluate the enrichment of a certain type of cell in its neighbors;
[0041] S44, Moran's index was calculated to evaluate spatial autocorrelation and verify the degree of spatial clustering of gene expression.
[0042] The S5 comprises the following steps:
[0043] S51, constructing the spatial transcriptome data into a graph structure based on the adjacency matrix, where the nodes represent each basic unit and the edges represent the neighbor relationship between the basic units, and inputting the graph structure into the graph neural network model for training;
[0044] S52, uses a graph neural network model to extract important features from the spatial neighborhood graph, learns the potential representation of each basic unit through the model's multi-layer convolution operations, and generates a more detailed feature map;
[0045] S53, obtain the potential representation of each basic unit through the graph neural network model, and cluster the potential representation using a clustering method.
[0046] The S6 comprises the following steps:
[0047] S61, calculating the autocorrelation score for each cluster obtained by the cluster potential representation in step S5, and evaluating the stability of the gene expression of the cells in each cluster. The higher the autocorrelation score, the more consistent the gene expression of the cells in the cluster. The autocorrelation score is calculated as follows:
[0048]
[0049] Where: m is the autocorrelation score of cluster m, x i and x j is the expression profile of spot i and j in cluster m, μ m is the mean expression value of cluster m, is the variance of cluster m;
[0050] S62, based on the assumption that diploid cells have less gene expression diversity than tumor cells, the cluster with the highest autocorrelation score was selected as the diploid basic unit;
[0051] S63, aggregating the gene expression data of the identified diploid basic units, calculating the average expression value of each group in the diploid basic unit, and forming a baseline expression profile;
[0052] S64, the count matrix was normalized by the baseline expression profile to obtain a preliminary estimate of the copy number of each group in all basic units as a genetic signature.
[0053] The S8 comprises the following steps:
[0054] S81, based on the obtained copy number estimate, the copy number estimate of each basic unit is segmented using a likelihood-based segmentation algorithm to determine multiple breakpoints, wherein the segments between each breakpoint represent different gene regions, and the copy number estimate of each segment is obtained by calculating the median copy number of all genes in the segment, thereby obtaining the copy number profile of the basic unit; wherein, assuming that the observed data at each position i are independent and identically distributed, the segmentation algorithm determines the breakpoints by calculating the negative maximum log-likelihood function:
[0055]
[0056] in, Represents the position τ a +1 to τ b θ represents the subsequence of data points used to maximize the observed data y i The probability parameter, logP(y i |θ) is the observed data y under given parameters θ i The logarithmic probability, τ a and τ b Indicates two breakpoints;
[0057] S82, aggregate the copy number estimates for each basic unit, calculate the average copy number of all basic units for each breakpoint fragment, and combine the averages to form an overall copy number profile for the spatial clones.
[0058] The S9 comprises the following steps:
[0059] S91, performing cluster analysis using the cell potential embeddings generated in step S7 to identify tumor clones;
[0060] S92, automatic classification of malignant and non-malignant cells: using variational inference methods, cells are automatically classified into malignant and non-malignant cells based on copy number variation;
[0061] S93, constructing a tumor evolution tree for the tumor clones obtained by clustering: according to the clustering results obtained in step S8, the tumor cells are grouped according to the clone structure, and a tumor evolution tree is constructed using the grouped data to show the evolution process of different clones;
[0062] S94, analyze tumor heterogeneity and identify the characteristics and evolution paths of different clones: conduct detailed analysis of tumor heterogeneity in specific samples to identify the unique characteristics and evolution paths of each clone; apply segmentation algorithms and variational inference techniques to refine the copy number variation of each clone and further identify changes in the genomic structure of the tumor.
[0063] The S10 comprises the following steps:
[0064] S101, performing steps S1-S9 on the spatial omics datasets of different tumor types to reveal the clonal diversity of different cancer types;
[0065] S102, comparative analysis of primary tumors and metastases identifies specific and shared genomic alterations and reveals the evolutionary pathways of metastasis.
[0066] A spatial omics tumor evolution prediction system based on graph neural network, used to implement the above method, the system comprising:
[0067] Data acquisition module: obtains different types of spatial transcriptome data, including gene expression data and spatial location information;
[0068] Preprocessing module: preprocess and normalize the acquired spatial transcriptome data;
[0069] Annotation and grouping module: annotate and sort gene expression count data according to genomic location, and then group genes;
[0070] Spatial neighbor graph construction module: using the spatial location information and gene expression data in the spatial transcriptome data, construct an adjacency matrix reflecting the spatial relationship between cells and calculate spatial statistics. The adjacency matrix represents the connection relationship between each cell and its neighboring cells.
[0071] Graph neural network training module: constructs a spatial neighbor graph based on the adjacency matrix as the input of the graph neural network model, trains the model, and learns features from the spatial neighbor graph;
[0072] Copy number estimation module: Identify credible diploid basic units and preliminarily estimate the copy number of each basic unit in spatial omics;
[0073] Comprehensive feature training module: Add estimated copy number to the spatial neighbor graph to construct a comprehensive spatial graph representing tumor heterogeneity, retrain the graph neural network model to capture the spatial distribution of genetic variations in tissue samples, and obtain latent embeddings;
[0074] Breakpoint segmentation module: Based on the estimated copy number, the segmentation algorithm is used to determine the breakpoints and obtain the copy number profile of each basic unit and spatial clone;
[0075] Analysis module: Use potential embeddings to analyze downstream tasks, build tumor evolution trees, classify malignant and non-malignant cells, and analyze tumor heterogeneity;
[0076] Extended Comparative Module: Expanded to different spatial omics samples to conduct comparative analysis of primary tumors and metastases.
[0077] Compared with the prior art, the present invention has the following beneficial effects:
[0078] (1) Improve the prediction accuracy of tumor evolution patterns: The present invention constructs a comprehensive spatial map by integrating multiple features in spatial omics technology, including phenotypic, genetic and imaging features. This multi-feature integration method can fully reflect the complex interactions in the tumor microenvironment, improve the accurate depiction of tumor evolution patterns, and provide more detailed and realistic tumor evolution patterns, which is of great significance for the study of tumor heterogeneity and the understanding of tumor progression.
[0079] (2) More subtle feature perception: By introducing genetic information into the construction process of the graph network, the present invention enhances the ability to learn from multi-level spatial omics data. Compared with data analysis methods that only use a single feature, this multi-feature graph network construction method can more accurately capture subtle changes in tumor heterogeneity and evolution.
[0080] (3) Strong generalizability: The method of the present invention is highly generalizable and can be applied to a variety of cancer types. For different types of solid tumors, this method can provide valuable insights and reveal the diversity of tissue clones in different cancers. Therefore, this method has broad application prospects in the field of cancer research and can provide new tools and methods for the evolutionary study of different types of cancer.
[0081] (4) Improved research efficiency: Through automated and efficient data processing and analysis, the method of the present invention significantly improves research efficiency. Researchers can obtain high-quality analysis results in a shorter time, promoting the rapid development of tumor research.
[0082] (5) Promote the formulation of personalized treatment strategies: The method of the present invention can reveal the clonal diversity and evolutionary paths in different cancer types, which provides a scientific basis for the formulation of personalized cancer treatment strategies. By identifying the characteristics and evolutionary paths of different clones, it can assist doctors in designing treatment plans more targeted and improve treatment effects. BRIEF DESCRIPTION OF THE DRAWINGS
[0083] Figure 1 is a flow chart of the method of the present invention;
[0084] Figure 2 is a system structure diagram of the present invention;
[0085] Figure 3 This is a diagram of the model training process of the present invention. DETAILED DESCRIPTION
[0086] The present invention is described in detail below in conjunction with the accompanying drawings and specific embodiments. This embodiment is implemented based on the technical solution of the present invention, and provides a detailed implementation method and specific operation process, but the protection scope of the present invention is not limited to the following embodiments.
[0087] This embodiment provides a spatial omics tumor evolution prediction method based on graph neural network, such as Figure 1 As shown, the following steps are included:
[0088] S1, Data acquisition and loading: Acquire different types of spatial transcriptome data, including gene expression data and spatial location information.
[0089] Specifically, S1 includes the following steps:
[0090] S11, according to the spatial omics type of different platforms, different methods are called in the process to load data and create AnnData objects in Python.
[0091] S12, applicable platforms covered in the method include: 10x Genomics Visium, 10x Genomics Xenium, Vigzen MERSCOPE (MERFISH), Nanostring CosMx, Stereo-seq, 4i (four-dimensional immunofluorescence imaging), Imaging Mass Cytometry, seqFISH, Slide-seqV2, etc.
[0092] The analysis process of data from different platforms is different. This example mainly uses 10x Genomics Visium data as the main example. Among them, "spot" is the basic unit for capturing and analyzing gene expression in 10x Visium technology. Each spot (basic unit) represents a small area on a tissue slice and provides gene expression information for that area.
[0093] In one embodiment, taking 10x Genomics Visium data as an example, the read_10x_h5 function in scanpy is used to read the HDF5 file, load expression data, spatial coordinates and scale factors, process related files and metadata, and load image information as needed.
[0094] S2, data preprocessing: preprocess and normalize the acquired spatial transcriptome data.
[0095] Specifically, S2 includes the following steps:
[0096] S21, draw the transcript distribution map of each spot (basic unit), filter low-quality basic units according to the minimum transcript number threshold, and filter low-expressed genes according to the minimum basic unit number threshold.
[0097] Low-quality cells usually have fewer transcripts. By setting a minimum transcript count threshold, cells with transcript counts below the threshold can be filtered out. In one embodiment, this can be achieved by sc.pp.filter_cells(adata,min_counts=10), with the threshold set to 10. This function filters out cells with a total transcript count of less than 10, and considers these cells to be of low quality.
[0098] Low-expression genes are expressed in a small number of cells. By setting a minimum basic cell number threshold, genes expressed in a small number of cells can be filtered out. In one embodiment, this can be achieved by sc.pp.filter_genes(adata,min_cells=5), with the threshold set to 5. This function filters out genes that are expressed in less than 5 cells, and considers these genes to have low expression levels.
[0099] S22, filter mitochondrial genes (eg, gene names beginning with 'MT-'), HLA genes, and cell cycle genes.
[0100] S23, the gene expression in each basic unit is standardized (the total number of transcripts in each spot is normalized to 1e4) and logarithmically transformed, and the results are visualized.
[0101] S3, Gene Annotation and Grouping: Annotate and sort gene expression count data according to genomic location, and then group genes (binning).
[0102] Specifically, S3 includes the following steps:
[0103] S31, ENSG IDs were mapped to genomic positions using the pyensembl library and the genomic position column was initialized.
[0104] S32, filter out discarded gene IDs and NaN values.
[0105] S33, traverse the filtered genes, fill in the chromosome position information, add annotations to the gene expression count data according to the genome position and sort them; in this embodiment, the genome data is obtained through the pyensembl library, and these data are added to the annotations of the gene expression counts. In this way, each gene is accompanied by the corresponding genome position information, so that it can be sorted according to this information.
[0106] S34, in order to facilitate subsequent analysis and reduce the impact of dropout, genes are sorted into several groups according to their chromosomal positions, each group contains 25 genes (i.e., 25 genes are a bin), and the gene expression value of each group (bin) is represented by the average expression level of the genes contained in the group. Using bins to group genes helps reduce the sparsity and noise of data, improve the significance of statistical analysis, increase computational efficiency, and standardize data from different samples.
[0107] S35, calculate the average count value of each bin, obtain a spot×bin count matrix, and store it in adata.obs. The count matrix represents the gene expression data of each basic unit.
[0108] S4, construct a spatial neighbor graph and calculate spatial statistics: use the spatial location information and gene expression data in the spatial transcriptome data to construct an adjacency matrix reflecting the spatial relationship between cells, and calculate spatial statistics. The adjacency matrix represents the connection relationship between each cell and its neighboring cells.
[0109] Specifically, S4 includes the following steps:
[0110] S41, determining the adjacency relationship between cells by Delaunay triangulation or KNN (k nearest neighbor) algorithm, and generating a spatial relationship diagram between cells; in this embodiment, the parameter k of the KNN algorithm is 6.
[0111] S42, calculate the centrality score of each cell in the spatial map and calculate the cell co-occurrence probability.
[0112] S43, perform neighbor enrichment analysis to evaluate the enrichment of a certain type of cell in its neighbors.
[0113] S44, calculate Moran's I to evaluate spatial autocorrelation and verify the degree of spatial clustering of gene expression.
[0114] S5, graph neural network model training: construct a spatial neighbor graph based on the adjacency matrix as the input of the graph neural network model, train the model, and learn features from the spatial neighbor graph.
[0115] Specifically, S5 includes the following steps:
[0116] S51, based on the adjacency matrix, the spatial transcriptome data is constructed into a graph structure, where the node represents each basic unit spot, and the edge represents the neighbor relationship between the basic units, and the graph structure is input into the graph neural network model for training.
[0117] S52, using a graph neural network (GNN) model (such as the Graph Transformer convolutional layer) to extract important features from the spatial neighbor graph, learn the potential representation of each basic unit through the model's multi-layer convolution operation, and generate a more detailed feature map. During the training process, an appropriate loss function (such as cross entropy loss) and optimization algorithm (such as Adam optimizer, learning rate 0.01) are used to improve the performance of the model. The loss function of self-supervised learning (such as reconstruction error) is selected to measure the model's ability to reconstruct the input data, and an optimization algorithm (such as Adam optimizer) is used to update parameters to improve the training effect and performance of the model.
[0118] S53, obtain the potential representation of each basic unit through the graph neural network model, and cluster the potential representation using a suitable clustering method (such as k-means, mclust clustering).
[0119] S6, copy number estimation and diploid basic unit identification: identify reliable diploid spots (i.e., normal spots) and preliminarily estimate the copy number of each basic unit in spatial omics.
[0120] Specifically, S6 includes the following steps:
[0121] S61, calculating the autocorrelation score for each cluster obtained by the cluster potential representation in step S5, and evaluating the stability of the gene expression of the cells in each cluster. The higher the autocorrelation score, the more consistent the gene expression of the cells in the cluster. The autocorrelation score is calculated as follows:
[0122]
[0123] Where: mis the autocorrelation score of cluster m, x i and x j is the expression profile of spot i and j in cluster m, μ m is the mean expression value of cluster m, is the variance of cluster m.
[0124] S62, based on the assumption that diploid cells (i.e., normal cells) have less gene expression diversity than tumor cells, the cluster with the highest autocorrelation score was selected as the diploid spot, which usually exhibits less gene expression variability.
[0125] S63, aggregating the gene expression data of the identified diploid spots, calculating the average expression value of each bin in the diploid spots, and forming a baseline expression profile.
[0126] S64, normalize the count matrix by the baseline expression profile to obtain a preliminary estimate of the copy number in each bin of all spots as a genetic signature.
[0127] S7, comprehensive spatial graph construction: add the estimated copy number to the spatial neighbor graph, integrate phenotypic, genetic and imaging features, construct a comprehensive spatial graph representing tumor heterogeneity, retrain the graph neural network model to capture the spatial distribution of genetic variation in tissue samples, and learn a more refined estimate of the copy number of each bin in each spot to obtain a latent embedding for downstream tasks. The training process of the graph neural network model is as follows Figure 3 shown.
[0128] S8, breakpoint determination and copy number profile construction: Based on the estimated copy number, the segmentation algorithm is used to determine the breakpoints and obtain the copy number profile of each basic unit and spatial clone.
[0129] Specifically, S8 includes the following steps:
[0130] S81, based on the obtained copy number estimate, use a likelihood-based segmentation algorithm to segment the copy number estimate of each basic unit, determine multiple breakpoints, and the segments between each breakpoint represent different gene regions. By calculating the median copy number of all genes in the segment, the copy number estimate of each segment is obtained, and the copy number profile of the basic unit is obtained.
[0131] Assuming that the observations at each position i are independent and identically distributed, the segmentation algorithm determines the breakpoints by calculating the negative maximum log-likelihood function:
[0132]
[0133] in, Represents the position τ a+1 to τ b θ represents the subsequence of data points used to maximize the observed data y i The probability parameter, logP(y i |θ) is the observed data y under given parameters θ i The logarithmic probability, τ a and τ b Indicates two breakpoints.
[0134] S82, aggregate the copy number estimates for each basic unit, calculate the average copy number of all basic units for each breakpoint fragment, and combine the averages to form an overall copy number profile for the spatial clones.
[0135] S9, Downstream Task Analysis: Use latent embeddings for downstream task analysis, construct a tumor evolution tree, classify malignant and non-malignant cells, and analyze tumor heterogeneity.
[0136] Specifically, S9 includes the following steps:
[0137] S91, using the cell potential embedding generated in step S7 to perform cluster analysis (such as Leiden, Mclust, Louvain method) to identify tumor clones; downstream analysis and visualization can be customized according to user needs, such as pathway analysis, differential expression analysis, functional annotation, etc. for different clones.
[0138] S92, Automatic Classification of Malignant and Non-malignant Cells: Using variational inference methods, cells are automatically classified into malignant and non-malignant cells based on copy number variation.
[0139] S93, constructing a tumor evolution tree for the tumor clones obtained by clustering: according to the clustering results obtained in step S8, the tumor cells are grouped according to the clone structure, and the grouped data are used to construct a tumor evolution tree to show the evolution process of different clones.
[0140] S94, analyze tumor heterogeneity and identify the characteristics and evolution paths of different clones: conduct detailed analysis of tumor heterogeneity in specific samples to identify the unique characteristics and evolution paths of each clone; apply segmentation algorithms and variational inference techniques to refine the copy number variation of each clone and further identify changes in the genomic structure of the tumor.
[0141] S10, Cross-sample analysis: extended to different spatial omics samples, comparative analysis of primary tumors and metastases.
[0142] Specifically, S10 includes the following steps:
[0143] S101, executing steps S1-S9 on the spatial omics datasets of different tumor types to reveal the clonal diversity of different cancer types.
[0144] S102, comparative analysis of primary tumors and metastases identifies specific and shared genomic alterations and reveals the evolutionary pathways of metastasis.
[0145] This embodiment also provides a spatial omics tumor evolution prediction system based on graph neural network, which is used to implement the above method, such as Figure 2 As shown, the system includes:
[0146] Data acquisition module: obtains different types of spatial transcriptome data, including gene expression data and spatial location information;
[0147] Preprocessing module: preprocess and normalize the acquired spatial transcriptome data;
[0148] Annotation and grouping module: annotate and sort gene expression count data according to genomic location, and then group genes;
[0149] Spatial neighbor graph construction module: using the spatial location information and gene expression data in the spatial transcriptome data, construct an adjacency matrix reflecting the spatial relationship between cells and calculate spatial statistics. The adjacency matrix represents the connection relationship between each cell and its neighboring cells.
[0150] Graph neural network training module: constructs a spatial neighbor graph based on the adjacency matrix as the input of the graph neural network model, trains the model, and learns features from the spatial neighbor graph;
[0151] Copy number estimation module: Identify credible diploid basic units and preliminarily estimate the copy number of each basic unit in spatial omics;
[0152] Comprehensive feature training module: Add estimated copy number to the spatial neighbor graph to construct a comprehensive spatial graph representing tumor heterogeneity, retrain the graph neural network model to capture the spatial distribution of genetic variations in tissue samples, and obtain latent embeddings;
[0153] Breakpoint segmentation module: Based on the estimated copy number, the segmentation algorithm is used to determine the breakpoints and obtain the copy number profile of each basic unit and spatial clone;
[0154] Analysis module: Use potential embeddings to analyze downstream tasks, build tumor evolution trees, classify malignant and non-malignant cells, and analyze tumor heterogeneity;
[0155] Extended Comparative Module: Expanded to different spatial omics samples to conduct comparative analysis of primary tumors and metastases.
[0156] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working process of the described module can refer to the corresponding process in the aforementioned method embodiment, and will not be repeated here.
[0157] The preferred specific embodiments of the present invention are described in detail above. It should be understood that a person skilled in the art can make many modifications and changes based on the concept of the present invention without creative work. Therefore, any technical solution that can be obtained by a person skilled in the art through logical analysis, reasoning, or limited experiments based on the concept of the present invention on the basis of the prior art should be within the scope of protection determined by the claims.
Claims
1. A spatial omics tumor evolution prediction method based on graph neural network, characterized in that: The following steps are involved: S1, data acquisition and loading: Acquire different types of spatial transcriptome data, including gene expression data and spatial location information; S2, data preprocessing: preprocessing and normalizing the acquired spatial transcriptome data; S3, Gene Annotation and Grouping: Annotate and sort gene expression count data according to genomic location, and then group genes; S4, constructing a spatial neighbor graph and calculating spatial statistics: using the spatial location information and gene expression data in the spatial transcriptome data, constructing an adjacency matrix reflecting the spatial relationship between cells, and calculating spatial statistics, wherein the adjacency matrix represents the connection relationship between each cell and its neighboring cells; S5, graph neural network model training: construct a spatial neighbor graph based on the adjacency matrix as the input of the graph neural network model, train the model, and learn features from the spatial neighbor graph; S6, copy number estimation and diploid basic unit identification: identify reliable diploid basic units and preliminarily estimate the copy number of each basic unit in spatial omics; S7, comprehensive spatial graph construction: add the estimated copy number to the spatial neighbor graph to construct a comprehensive spatial graph representing tumor heterogeneity, retrain the graph neural network model to capture the spatial distribution of genetic variations in tissue samples, and obtain latent embedding; S8, breakpoint determination and copy number profile construction: Based on the estimated copy number, the segmentation algorithm is used to determine the breakpoints and obtain the copy number profile of each basic unit and spatial clone; S9, downstream task analysis: Use latent embedding to perform downstream task analysis, construct a tumor evolution tree, classify malignant and non-malignant cells, and analyze tumor heterogeneity; S10, Cross-sample analysis: extended to different spatial omics samples, comparative analysis of primary tumors and metastases.
2. The spatial omics tumor evolution prediction method based on graph neural network according to claim 1, characterized in that: The S2 comprises the following steps: S21, drawing a transcript distribution map of each basic unit, filtering low-quality basic units according to a minimum transcript number threshold, and filtering low-expressed genes according to a minimum basic unit number threshold, wherein each basic unit represents an area of a preset size on a tissue section and provides gene expression information of the area; S22, filtering mitochondrial genes, HLA genes, and cell cycle genes; S23, Gene expression in each basic unit was normalized and log-transformed.
3. The spatial omics tumor evolution prediction method based on graph neural network according to claim 1, characterized in that: The S3 comprises the following steps: S31, mapping ID to genome position, initializing genome position column; S32, filtering discarded gene IDs and null values; S33, traverse the filtered genes, fill in the chromosome location information, add annotations to the gene expression count data and sort them according to the genome location; S34, sorting the genes according to their chromosomal positions into a plurality of groups, each group comprising a preset number of genes, and the gene expression value of each group is represented by the average expression level of the genes contained in the group; S35, calculating the average count value of each group to obtain a count matrix, wherein the count matrix represents the gene expression data of each basic unit.
4. The spatial omics tumor evolution prediction method based on graph neural network according to claim 1, characterized in that: The S4 comprises the following steps: S41, determine the adjacency relationship between cells through Delaunay triangulation or KNN algorithm to generate a spatial relationship map between cells; S42, calculate the centrality score of each cell in the spatial map and calculate the cell co-occurrence probability; S43, neighbor enrichment analysis was performed to evaluate the enrichment of a certain type of cell in its neighbors; S44, Moran's index was calculated to evaluate spatial autocorrelation and verify the degree of spatial clustering of gene expression.
5. The spatial omics tumor evolution prediction method based on graph neural network according to claim 1, characterized in that: The S5 comprises the following steps: S51, constructing the spatial transcriptome data into a graph structure based on the adjacency matrix, where the nodes represent each basic unit and the edges represent the neighbor relationship between the basic units, and inputting the graph structure into the graph neural network model for training; S52, uses a graph neural network model to extract important features from the spatial neighborhood graph, learns the potential representation of each basic unit through the model's multi-layer convolution operations, and generates a more detailed feature map; S53, obtain the potential representation of each basic unit through the graph neural network model, and cluster the potential representation using a clustering method.
6. The method for predicting tumor evolution based on spatial omics of graph neural network according to claim 5, characterized in that: The S6 comprises the following steps: S61, calculating the autocorrelation score for each cluster obtained by the cluster potential representation in step S5, and evaluating the stability of the gene expression of the cells in each cluster. The higher the autocorrelation score, the more consistent the gene expression of the cells in the cluster. The autocorrelation score is calculated as follows: Where: m is the autocorrelation score of cluster m, x i and x j is the expression profile of spot i and j in cluster m, μ m is the mean expression value of cluster m, is the variance of cluster m; S62, based on the assumption that diploid cells have less gene expression diversity than tumor cells, the cluster with the highest autocorrelation score was selected as the diploid basic unit; S63, aggregating the gene expression data of the identified diploid basic units, calculating the average expression value of each group in the diploid basic unit, and forming a baseline expression profile; S64, the count matrix was normalized by the baseline expression profile to obtain a preliminary estimate of the copy number of each group in all basic units as a genetic signature.
7. The spatial omics tumor evolution prediction method based on graph neural network according to claim 1, characterized in that: The S8 comprises the following steps: S81, based on the obtained copy number estimate, the copy number estimate of each basic unit is segmented using a likelihood-based segmentation algorithm to determine multiple breakpoints, wherein the segments between each breakpoint represent different gene regions, and the copy number estimate of each segment is obtained by calculating the median copy number of all genes in the segment, thereby obtaining the copy number profile of the basic unit; wherein, assuming that the observed data at each position i are independent and identically distributed, the segmentation algorithm determines the breakpoints by calculating the negative maximum log-likelihood function: in, Represents the position τ a +1 to τ b θ represents the subsequence of data points used to maximize the observed data y i The probability parameter, logP(y i |θ) is the observed data y under given parameters θ i The logarithmic probability, τ a and τ b Indicates two breakpoints; S82, aggregate the copy number estimates for each basic unit, calculate the average copy number of all basic units for each breakpoint fragment, and combine the averages to form an overall copy number profile for the spatial clones.
8. The spatial omics tumor evolution prediction method based on graph neural network according to claim 1, characterized in that: The S9 comprises the following steps: S91, performing cluster analysis using the cell potential embeddings generated in step S7 to identify tumor clones; S92, automatic classification of malignant and non-malignant cells: using variational inference methods, cells are automatically classified into malignant and non-malignant cells based on copy number variation; S93, constructing a tumor evolution tree for the tumor clones obtained by clustering: according to the clustering results obtained in step S8, the tumor cells are grouped according to the clone structure, and a tumor evolution tree is constructed using the grouped data to show the evolution process of different clones; S94, analyze tumor heterogeneity and identify the characteristics and evolution paths of different clones: conduct detailed analysis of tumor heterogeneity in specific samples to identify the unique characteristics and evolution paths of each clone; apply segmentation algorithms and variational inference techniques to refine the copy number variation of each clone and further identify changes in the genomic structure of the tumor.
9. The spatial omics tumor evolution prediction method based on graph neural network according to claim 1, characterized in that: The S10 comprises the following steps: S101, performing steps S1-S9 on the spatial omics datasets of different tumor types to reveal the clonal diversity of different cancer types; S102, comparative analysis of primary tumors and metastases identifies specific and shared genomic alterations and reveals the evolutionary pathways of metastasis.
10. A spatial omics tumor evolution prediction system based on graph neural network, characterized in that: For implementing the method according to any one of claims 1 to 9, the system comprises: Data acquisition module: obtains different types of spatial transcriptome data, including gene expression data and spatial location information; Preprocessing module: preprocess and normalize the acquired spatial transcriptome data; Annotation and grouping module: annotate and sort gene expression count data according to genomic location, and then group genes; Spatial neighbor graph construction module: using the spatial location information and gene expression data in the spatial transcriptome data, construct an adjacency matrix reflecting the spatial relationship between cells and calculate spatial statistics. The adjacency matrix represents the connection relationship between each cell and its neighboring cells. Graph neural network training module: constructs a spatial neighbor graph based on the adjacency matrix as the input of the graph neural network model, trains the model, and learns features from the spatial neighbor graph; Copy number estimation module: Identify credible diploid basic units and preliminarily estimate the copy number of each basic unit in spatial omics; Comprehensive feature training module: Add estimated copy number to the spatial neighbor graph to construct a comprehensive spatial graph representing tumor heterogeneity, retrain the graph neural network model to capture the spatial distribution of genetic variations in tissue samples, and obtain latent embeddings; Breakpoint segmentation module: Based on the estimated copy number, the segmentation algorithm is used to determine the breakpoints and obtain the copy number profile of each basic unit and spatial clone; Analysis module: Use potential embeddings to analyze downstream tasks, build tumor evolution trees, classify malignant and non-malignant cells, and analyze tumor heterogeneity; Extended Comparative Module: Expanded to different spatial omics samples to conduct comparative analysis of primary tumors and metastases.
Citation Information
Patent Citations
Copy number variation prediction method and device, computer equipment and storage medium
CN111402951A
Method for analyzing active pathway in single cell multi-omics based on graph neural network
CN115240772A
Method and system for identifying spatial transcriptome cell expression pattern
CN115732034A
ScRNA-seq data dimension reduction method based on graph neural network
CN116386729A
Prediction model for simultaneously detecting multiple tumors and performing tissue traceability and training method and application thereof
CN116665771A
Cited By
Method and device for deconvolution of spatial transcriptome data
CN119649912A
Heterogeneity non-invasive typing method in hepatoma based on multiple omics and application
CN119672022A
