Tumor infiltration boundary analysis method and device, electronic equipment and storage medium

Abstract

The invention provides a tumor infiltration boundary analysis method and device, electronic equipment and a storage medium, and the method comprises the steps: analyzing space transcriptome data, and determining a tumor region and a non-tumor region; boundary division is carried out on the tumor area and the non-tumor area, and a boundary line between the tumor area and the non-tumor area is determined; dividing the areas on the two sides of the boundary line to obtain a preset number of grid areas; numbering the preset number of grid regions to obtain an infiltration boundary region; and according to the spatial transcriptome data and the infiltration boundary region, analyzing heterogeneity statistical information of the boundary region and enriched gene information of the boundary region. The space transcriptome data is processed, and the boundary line of the tumor area and the non-tumor area is determined; after the areas on the two sides of the boundary line are divided, the divided infiltration boundary areas are analyzed, and quantitative analysis on the tumor infiltration boundary areas can be achieved through space transcriptome data. And the invasion and infiltration process of the tumor can be analyzed.

Description

Technical Field

[0001] The present disclosure relates to the field of data processing technology, and in particular to a method and device, electronic equipment and storage medium for analyzing tumor infiltration boundaries. Background Art

[0002] Cancer, also known as malignant tumor, is a disease caused by excessive proliferation of body cells out of human regulation. The process of tumor growth is accompanied by the invasion and infiltration of tumor tissue into non-tumor tissue. In tumor immunity research, an important issue in the infiltration process is to explain the microenvironment at the infiltration boundary.

[0003] Among the various methods of studying tumors through spatiotemporal omics, spatiotemporal omics can restore the physical location of gene expression in tissues while sequencing, but there is no mature method to model and analyze the process of tumor invasion and infiltration. Summary of the invention

[0004] The present disclosure provides a method and device for analyzing tumor infiltration boundaries, an electronic device and a storage medium, the main purpose of which is to analyze the microenvironment of the tumor infiltration area.

[0005] According to a first aspect of the present disclosure, a method for analyzing tumor invasion boundaries is provided, comprising:

[0006] Spatial transcriptome data were analyzed to identify tumor and non-tumor areas;

[0007] Demarcating the tumor area and the non-tumor area to determine a boundary line between the tumor area and the non-tumor area;

[0008] Dividing the areas on both sides of the boundary line to obtain a preset number of grid areas;

[0009] Numbering the preset number of grid areas to obtain infiltration boundary areas;

[0010] Based on the spatial transcriptome data and the infiltration boundary area, analysis of boundary area heterogeneity statistical information and boundary area enriched gene information is performed.

[0011] Optionally, analyzing the spatial transcriptome data to determine the tumor area and the non-tumor area includes:

[0012] Preprocessing the spatial transcriptome data to obtain preprocessed spatial transcriptome data;

[0013] Performing standardization processing on the pre-processed spatial transcriptome data to obtain standardized spatial transcriptome data;

[0014] Performing dimensionality reduction processing on the spatial transcriptome data after the standardization processing to obtain spatial transcriptome data after dimensionality reduction processing;

[0015] Performing clustering processing on the spatial transcriptome data after the dimensionality reduction processing to obtain clusters corresponding to different genes;

[0016] The tumor area and the non-tumor area are determined according to the preset gene expression levels and the clusters corresponding to the different genes.

[0017] Optionally, preprocessing the spatial transcriptome data to obtain preprocessed spatial transcriptome data includes:

[0018] Based on a first preset length, merging the first grid in the spatial transcriptome chip into a target sampling point;

[0019] The transcripts in each of the target sampling points are integrated to obtain the pre-processed spatial transcriptome data.

[0020] Optionally, dividing the tumor area and the non-tumor area to determine the boundary line between the tumor area and the non-tumor area includes:

[0021] Invoking a first preset image processing algorithm to process the spatial transcriptome data to determine an infiltration boundary between the tumor area and the non-tumor area;

[0022] The infiltration boundary line is fitted to obtain the boundary line.

[0023] Optionally, dividing the areas on both sides of the boundary line to obtain a preset number of grid areas includes:

[0024] Divide the boundary line into equal parts according to preset pixel parameters to determine a first number of equal division points;

[0025] According to a second preset length, creating perpendicular lines of equal length to both sides of each of the equally divided points;

[0026] Based on the vertical line, the boundary line, and at least one first expansion curve, the tumor area on one side of the boundary line is grid-divided to obtain a first preset number of grid areas; wherein the at least one first expansion curve is parallel to the boundary line;

[0027] Based on the vertical line, the boundary line, and at least one second expansion curve, the non-tumor area on the other side of the boundary line is gridded to obtain a second preset number of grid areas; wherein the at least one second expansion curve is parallel to the boundary line.

[0028] Optionally, the step of numbering the preset number of grid areas to obtain the infiltration boundary areas includes:

[0029] Numbering the preset number of grid areas to obtain an area number corresponding to each grid area;

[0030] The region number corresponding to each target sampling point is determined to obtain the infiltration boundary region.

[0031] Optionally, determining the area number corresponding to each target sampling point includes:

[0032] Calculating the vector outer product of each target sampling point and each boundary curve of the grid area respectively; wherein the boundary curve includes the vertical line, the intersection line, the first extended curve or the second extended curve;

[0033] If the vector outer product has opposite signs, it is determined that the target sampling point is located in the grid area;

[0034] Based on the area number of the grid area, the area number corresponding to each of the target sampling points is determined.

[0035] Optionally, the determining the area number corresponding to each target sampling point further includes:

[0036] Based on a second preset image processing algorithm, determining the grid area corresponding to each of the target sampling points;

[0037] Based on the area number of the grid area, the area number corresponding to each of the target sampling points is determined.

[0038] Optionally, the performing of the analysis of the border region heterogeneity statistical information and the border region enriched gene information based on the spatial transcriptome data and the infiltration border region includes:

[0039] Grouping the grid areas according to a preset grouping method;

[0040] Based on the spatial transcriptome data, obtaining heterogeneity statistical information of different groups to obtain the heterogeneity statistical information of the boundary area;

[0041] According to the infiltration boundary area and the spatial transcriptome information, the enriched gene information of the boundary area is determined.

[0042] Optionally, determining the enriched gene information in the border region according to the infiltration border region and the spatial transcriptome information includes:

[0043] Based on the spatial transcriptome information, respectively obtaining the expression levels of different genes in each of the target sampling points;

[0044] Sorting the expression amounts according to the distances between the target sampling points corresponding to the expression amounts and the boundary line;

[0045] Based on a preset test method, the genes corresponding to the sorted expression levels are tested to obtain a cumulative curve;

[0046] Processing the cumulative curve to obtain a target evaluation index;

[0047] The target evaluation indicators of all genes in the infiltration boundary area are processed to obtain the enriched gene information of the boundary area.

[0048] According to a second aspect of the present disclosure, a device for analyzing tumor invasion boundaries is provided, comprising:

[0049] A first determination unit is used to analyze the spatial transcriptome data to determine the tumor area and the non-tumor area;

[0050] A second determining unit is used to divide the tumor area and the non-tumor area into boundaries, and determine a boundary line between the tumor area and the non-tumor area;

[0051] A first processing unit, configured to divide the areas on both sides of the boundary line into a predetermined number of grid areas;

[0052] A second processing unit is used to number the preset number of grid areas to obtain infiltration boundary areas;

[0053] An analysis unit is used to perform analysis of boundary region heterogeneity statistical information and boundary region enrichment gene information based on the spatial transcriptome data and the infiltration boundary region.

[0054] Optionally, the first determining unit includes:

[0055] A first processing module, used for preprocessing the spatial transcriptome data to obtain preprocessed spatial transcriptome data;

[0056] A second processing module is used to perform standardization processing on the pre-processed spatial transcriptome data to obtain standardized spatial transcriptome data;

[0057] A third processing module is used to perform dimensionality reduction processing on the spatial transcriptome data after the standardization processing to obtain the spatial transcriptome data after the dimensionality reduction processing;

[0058] A fourth processing module is used to perform clustering processing on the spatial transcriptome data after the dimensionality reduction processing to obtain clusters corresponding to different genes;

[0059] The first determination module is used to determine the tumor area and the non-tumor area according to the preset gene expression levels and the clusters corresponding to the different genes.

[0060] Optionally, the first processing module is further used for:

[0061] Based on a first preset length, merging the first grid in the spatial transcriptome chip into a target sampling point;

[0062] The transcripts in each of the target sampling points are integrated to obtain the pre-processed spatial transcriptome data.

[0063] Optionally, the second determining unit includes:

[0064] a fifth processing module, configured to call a first preset image processing algorithm to process the spatial transcriptome data and determine an infiltration boundary between the tumor area and the non-tumor area;

[0065] A fitting module is used to perform fitting processing on the infiltration boundary line to obtain the boundary line.

[0066] Optionally, the first processing unit includes:

[0067] A second determination module is used to divide the boundary line into equal parts according to a preset pixel parameter to determine a first number of equal division points;

[0068] A creation module, used for creating perpendicular lines of equal length to both sides of each of the equally divided points according to a second preset length;

[0069] A first division module is used to perform grid division on the tumor area on one side of the boundary line based on the vertical line, the boundary line, and at least one first expansion curve to obtain a first preset number of grid areas; wherein the at least one first expansion curve is parallel to the boundary line;

[0070] The second division module is used to grid the non-tumor area on the other side of the junction line based on the vertical line, the junction line, and at least one second extension curve to obtain a second preset number of grid areas; wherein the at least one second extension curve is parallel to the junction line.

[0071] Optionally, the second processing unit includes:

[0072] A sixth processing module, used for numbering the preset number of grid areas to obtain an area number corresponding to each grid area;

[0073] The third determination module is used to determine the area number corresponding to each of the target sampling points to obtain the infiltration boundary area.

[0074] Optionally, the third determining module is used to:

[0075] Calculating the vector outer product of each target sampling point and each boundary curve of the grid area respectively; wherein the boundary curve includes the vertical line, the intersection line, the first extended curve or the second extended curve;

[0076] If the vector outer product has opposite signs, it is determined that the target sampling point is located in the grid area;

[0077] Based on the area number of the grid area, the area number corresponding to each of the target sampling points is determined.

[0078] Optionally, the third determining module is further used to:

[0079] Based on a second preset image processing algorithm, determining the grid area corresponding to each of the target sampling points;

[0080] Based on the area number of the grid area, the area number corresponding to each of the target sampling points is determined.

[0081] Optionally, the analysis unit includes:

[0082] A grouping module, used for grouping the grid areas according to a preset grouping method;

[0083] An acquisition module, used to acquire heterogeneity statistical information of different groups based on the spatial transcriptome data, and obtain the heterogeneity statistical information of the boundary area;

[0084] The fourth determination module is used to determine the enriched gene information of the boundary area according to the infiltration boundary area and the spatial transcriptome information.

[0085] Optionally, the fourth determining module is further used for:

[0086] Based on the spatial transcriptome information, respectively obtaining the expression levels of different genes in each of the target sampling points;

[0087] Sorting the expression amounts according to the distances between the target sampling points corresponding to the expression amounts and the boundary line;

[0088] Based on a preset test method, the genes corresponding to the sorted expression levels are tested to obtain a cumulative curve;

[0089] Processing the cumulative curve to obtain a target evaluation index;

[0090] The target evaluation indicators of all genes in the infiltration boundary area are processed to obtain the enriched gene information of the boundary area.

[0091] According to a third aspect of the present disclosure, there is provided an electronic device, including:

[0092] at least one processor; and

[0093] a memory communicatively connected to the at least one processor; wherein,

[0094] The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the method described in the first aspect.

[0095] According to a fourth aspect of the present disclosure, a non-transitory computer-readable storage medium storing computer instructions is provided, wherein the computer instructions are used to enable the computer to execute the method described in the first aspect.

[0096] According to a fifth aspect of the present disclosure, a computer program product is provided, comprising a computer program, wherein when the computer program is executed by a processor, the computer program implements the method as described in the first aspect above.

[0097] The present disclosure provides a method and device, electronic device and storage medium for analyzing tumor infiltration boundaries, which determine the tumor area and non-tumor area by analyzing spatial transcriptome data; divide the boundaries between the tumor area and the non-tumor area to determine the boundary between the tumor area and the non-tumor area; divide the areas on both sides of the boundary to obtain a preset number of grid areas; number the preset number of grid areas to obtain the infiltration boundary area; and perform analysis of boundary area heterogeneity statistical information and boundary area enrichment gene information based on the spatial transcriptome data and the infiltration boundary area. The present disclosure determines the boundary between the tumor area and the non-tumor area by processing the spatial transcriptome data; after gridding the areas on both sides of the boundary, the gridded infiltration boundary area is analyzed, so as to realize the quantitative analysis of the tumor infiltration boundary area using spatial transcriptome data; and can analyze the invasion and infiltration process of the tumor.

[0098] It should be understood that the content described in this section is not intended to identify the key or important features of the embodiments of the present application, nor is it intended to limit the scope of the present application. Other features of the present application will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0099] The accompanying drawings are used to better understand the present solution and do not constitute a limitation of the present disclosure.

[0100] Figure 1 A schematic diagram of a flow chart of a method for analyzing tumor infiltration boundaries provided in an embodiment of the present disclosure;

[0101] Figure 2 A schematic flow chart of a method for determining a boundary line between a tumor area and a non-tumor area provided in an embodiment of the present disclosure;

[0102] Figure 3 A schematic diagram of an infiltration boundary area;

[0103] Figure 4 A schematic flow chart of a method for dividing an infiltration boundary area provided in an embodiment of the present disclosure;

[0104] Figure 5 A schematic flow chart of another method for analyzing tumor infiltration boundaries provided in an embodiment of the present disclosure;

[0105] Figure 6 A schematic diagram of the enrichment scores of different pathways on both sides of a junction;

[0106] Figure 7 A schematic flow chart of another method for analyzing tumor infiltration boundaries provided in an embodiment of the present disclosure;

[0107] Figure 8 A schematic diagram of the structure of a device for analyzing tumor infiltration boundaries provided in an embodiment of the present disclosure;

[0108] Fig. 9 A schematic diagram of the structure of another device for analyzing tumor infiltration boundaries provided in an embodiment of the present disclosure;

[0109] Fig.10 A schematic block diagram of an exemplary electronic device provided for an embodiment of the present disclosure. DETAILED DESCRIPTION

[0110] The following is a description of exemplary embodiments of the present disclosure in conjunction with the accompanying drawings, including various details of the embodiments of the present disclosure to facilitate understanding, which should be considered as merely exemplary. Therefore, it should be recognized by those of ordinary skill in the art that various changes and modifications may be made to the embodiments described herein without departing from the scope and spirit of the present disclosure. Similarly, for the sake of clarity and conciseness, descriptions of well-known functions and structures are omitted in the following description.

[0111] The following describes the method and apparatus, electronic device, and storage medium for analyzing tumor infiltration boundaries according to the embodiments of the present disclosure with reference to the accompanying drawings.

[0112] Figure 1 A schematic flow chart of a method for analyzing tumor infiltration boundaries provided in an embodiment of the present disclosure.

[0113] like Figure 1 As shown, the method comprises the following steps:

[0114] Step 101, analyzing the spatial transcriptome data to determine the tumor area and the non-tumor area.

[0115] In the disclosed embodiments, spatiotemporal omics technology is used to sequence and analyze the infiltration area of ​​the tumor to obtain spatial transcriptome data; the spatial transcriptome data can accurately reflect the gene expression map of the tumor infiltration area, and the tumor area and non-tumor area can be determined according to the annotation information in the spatial transcriptome data. The tumor area is an area where tumor cells are enriched in lesions; the non-tumor area is a normal human tissue cell area. It should be noted that the disclosed embodiments do not limit the specific cell types of the tumor area and the non-tumor area.

[0116] Compared with the method of determining tumor areas and non-tumor areas by relying on medical imaging and other means, the method of determining tumor areas and non-tumor areas by analyzing spatial transcriptome data can improve the accuracy of identification.

[0117] Step 102: dividing the tumor area and the non-tumor area into boundaries to determine a boundary line between the tumor area and the non-tumor area.

[0118] In the disclosed embodiment, the boundary line is the boundary line between tumor cells and normal tissue cells during the process of tumor cells invading surrounding tissue cells. After determining the tumor area and the non-tumor area, the boundary line is determined according to the biochemical characteristics of the tumor infiltration area.

[0119] Based on the boundary line between the tumor area and the non-tumor area, it is possible to analyze the characteristics of gene expression from the tumor area to the non-tumor area, and then obtain the differences between the tumor area and the non-tumor area.

[0120] Step 103, dividing the areas on both sides of the boundary line to obtain a preset number of grid areas.

[0121] In the embodiment of the present disclosure, the two side areas are tumor infiltration areas adjacent to the boundary line; when dividing the two side areas of the boundary line, the boundary line and other lines can be used for division; the other lines can be, for example, vertical lines perpendicular to the boundary line, or extended lines parallel to the boundary line. It should be noted that the embodiment of the present disclosure does not constitute a limitation on how to divide the two side areas of the boundary line.

[0122] Dividing the areas on both sides of the boundary line into a preset number of grid areas can facilitate the research and analysis of the spatial transcriptome data corresponding to the tumor infiltration area; and obtain the differences in genetic gradients from tumor to normal tissue.

[0123] Step 104: numbering the preset number of grid areas to obtain infiltration boundary areas.

[0124] In the embodiment of the present disclosure, the areas on both sides of the boundary line are divided into a preset number of grid areas, and after the grid areas are numbered, the set of the preset number of grid areas obtained is the infiltration boundary area. The infiltration boundary area can be a tumor infiltration area, or a part of a tumor infiltration area, or the whole tumor infiltration area, a part of a tumor area, and a part of a non-tumor area, which is not limited in the present disclosure.

[0125] After the preset number of grid areas are numbered, a mapping relationship can be established between the preset number of divided grid areas and the spatial transcriptome data, so as to facilitate the analysis and processing of different areas of the tumor infiltration region.

[0126] Step 105: Based on the spatial transcriptome data and the infiltration boundary region, analyze the boundary region heterogeneity statistical information and the boundary region enrichment gene information.

[0127] In the disclosed embodiment, the border region heterogeneity statistical information may include but is not limited to information such as cell type ratios and gene expression levels of different genes; the border region heterogeneity statistical information may reflect the heterogeneity between tumor cells and normal tissue cells in the infiltrating border region. The border region enriched gene information is the enriched genes in the infiltrating border region; by analyzing the spatial transcriptome data, obtaining the expression level of any gene in the infiltrating border region, and analyzing and processing the expression level of any gene, the enriched genes in the infiltrating border region can be obtained.

[0128] The present disclosure provides a method for analyzing tumor infiltration boundaries, which determines the tumor area and the non-tumor area by analyzing the spatial transcriptome data; divides the boundary between the tumor area and the non-tumor area to determine the boundary between the tumor area and the non-tumor area; divides the areas on both sides of the boundary to obtain a preset number of grid areas; numbers the preset number of grid areas to obtain the infiltration boundary area; and performs analysis of the boundary area heterogeneity statistical information and the boundary area enrichment gene information based on the spatial transcriptome data and the infiltration boundary area. The present disclosure determines the boundary between the tumor area and the non-tumor area by processing the spatial transcriptome data; after gridding the areas on both sides of the boundary, the grid-divided infiltration boundary area is analyzed, so as to realize the quantitative analysis of the tumor infiltration boundary area using the spatial transcriptome data; and can analyze the invasion and infiltration process of the tumor.

[0129] In order to analyze the microenvironment of the tumor infiltration boundary area and to quantitatively analyze the heterogeneity of the tumor boundary area, it is necessary to determine the boundary between the tumor area and the non-tumor area based on the spatial transcriptome data. The present disclosure embodiment provides a flow chart of a method for determining the boundary between the tumor area and the non-tumor area.

[0130] like Figure 2 As shown, the method comprises the following steps:

[0131] Step 201 : preprocessing the spatial transcriptome data to obtain preprocessed spatial transcriptome data.

[0132] As a refinement of an embodiment of the present disclosure, preprocessing the spatial transcriptome data to obtain preprocessed spatial transcriptome data includes: merging the first grids in the spatial transcriptome chip into target sampling points based on a first preset length; integrating the transcripts in each of the target sampling points to obtain the preprocessed spatial transcriptome data.

[0133] Specifically, in the presently disclosed embodiment, in the spatiotemporal omics technology, the resolution of the spatial transcriptome chip can achieve nanometer-level resolution; each spatial transcriptome chip includes a grid-shaped field of view. The spatiotemporal omics technology can achieve ultra-high throughput and ultra-high precision detection.

[0134] See also Figure 3 , the first grid is a grid-like field of view in the spatial transcriptome data, such as the corresponding small grid in the solid square in the figure. The spatial transcriptome data is gridded according to the first preset length, and the transcripts in each first grid are merged and integrated into a target sample point. The target sampling point corresponds to the solid square in the figure. Exemplarily, the grid is divided according to the first preset length of 25 microns, and each unit cell on the grid is a square area with a side length of 25 microns; the transcripts in each first grid are integrated into a sample point to obtain an analyzable data matrix. It should be noted that the present disclosure does not limit the size of the first preset length.

[0135] By preprocessing the spatial transcriptome data, the needs of tumor infiltration boundary analysis can still be met; at the same time, the preprocessed spatial transcriptome data can facilitate subsequent analysis and research.

[0136] Step 202: performing standardization processing on the pre-processed spatial transcriptome data to obtain standardized spatial transcriptome data.

[0137] Specifically, in the disclosed embodiment, the pre-processed spatial transcriptome data is subjected to standardization processing, which can reduce the difference in sequencing depth between spatial transcriptome data, and avoid the influence on tumor infiltration boundary analysis due to the difference in sequencing depth.

[0138] Step 203, performing dimensionality reduction processing on the spatial transcriptome data after the standardization processing to obtain the spatial transcriptome data after the dimensionality reduction processing.

[0139] Step 204: performing clustering processing on the spatial transcriptome data after the dimensionality reduction processing to obtain clusters corresponding to different genes.

[0140] Specifically in the disclosed embodiment, the spatial transcriptome data after dimensionality reduction presents most of the transcriptional features in a low-dimensional space. The spatial transcriptome data includes information such as the expression levels of different genes; by clustering the spatial transcriptome data after dimensionality reduction, clusters corresponding to different genes can be obtained.

[0141] As an implementable method of an embodiment of the present disclosure, when performing clustering processing, a clustering method that considers spatial location information is used, such as SpaGCN.

[0142] Step 205 , determining the tumor area and the non-tumor area according to the preset gene expression levels and the clusters corresponding to the different genes.

[0143] Specifically in the embodiments of the present disclosure, the preset gene expression level may be, for example, the expression level of tumor-related genes, or the gene expression level of normal tissue in a non-tumor region. Exemplarily, based on the expression level of tumor-related genes, the cluster corresponding to the tumor region and the location thereof are determined in the clusters corresponding to various genes in the spatial transcriptome data.

[0144] Step 206 , calling a first preset image processing algorithm to process the spatial transcriptome data and determine the infiltration boundary between the tumor area and the non-tumor area.

[0145] Specifically in the embodiments of the present disclosure, the first preset image processing algorithm may be, for example, a computer vision algorithm; the computer vision algorithm may be a method using the OpenCV library to determine the tumor area and the non-tumor area. The infiltration boundary line may be understood as the boundary line between the tumor area and the non-tumor area determined by the first preset image processing algorithm; it is understandable that the infiltration boundary line differs from the actual boundary line. After determining the tumor area and the non-tumor area, the spatial transcriptome data is processed to obtain the infiltration boundary line between the tumor area and the non-tumor area.

[0146] Step 207, performing fitting processing on the infiltration boundary line to obtain the boundary line.

[0147] Specifically, in the embodiment of the present disclosure, since the pixel-level boundary line found by computer vision has large noise, the obtained infiltration boundary line is further fitted to obtain the boundary line between the tumor area and the non-tumor area. The interference of the noise of the fuzzy boundary on the determination of the boundary line can be solved by the fitting process.

[0148] In summary, the disclosed embodiment performs standardization, dimensionality reduction, and clustering on the pre-processed spatial transcriptome data, thereby identifying the tumor area and the non-tumor area; and uses the first preset image processing algorithm to determine the boundary between the tumor area and the non-tumor area.

[0149] After determining the boundary between the tumor region and the non-tumor region, in order to facilitate quantitative analysis of the spatial transcriptome data, the regions on both sides of the boundary may be divided. The present disclosure provides a flow chart of a method for dividing an infiltration boundary region.

[0150] like Figure 4 As shown, the method comprises the following steps:

[0151] Step 301: divide the boundary line into equal parts according to preset pixel parameters, and determine a first number of equal division points.

[0152] Specifically in the embodiment of the present disclosure, the preset pixel parameter can be understood as a preset number of pixels; the lamps are divided at intervals of the preset pixel parameter on the boundary line to obtain a first number of equally divided points. The first number is related to the length of the boundary line and the preset pixel parameter.

[0153] Step 302: Create perpendicular lines of equal length on both sides of each of the equally divided points according to a second preset length.

[0154] Specifically, in the disclosed embodiment, at each equally divided point, perpendicular lines of equal length are created on both sides of the junction line according to the second preset length. The created perpendicular lines can be used to extend the junction line to the two side areas to achieve grid division of the tumor infiltration area.

[0155] Step 303, based on the vertical line, the boundary line, and at least one first expansion curve, gridding the tumor area on one side of the boundary line to obtain a first preset number of grid areas; wherein the at least one first expansion curve is parallel to the boundary line.

[0156] Specifically, in the disclosed embodiment, the first expansion curve can be understood as a curve extending along the vertical line toward the tumor area side of the junction line and parallel to the junction line. If there are two or more first expansion curves, each first expansion curve can be but is not limited to being distributed at the same interval. The tumor area on one side of the junction line is grid-divided by the vertical line, the junction line, and at least one first expansion curve. The size of the first preset number is related to the preset pixel parameter.

[0157] Step 304, based on the vertical line, the boundary line, and at least one second extension curve, gridding the non-tumor area on the other side of the boundary line to obtain a second preset number of grid areas; wherein the at least one second extension curve is parallel to the boundary line.

[0158] Specifically, in the embodiment of the present disclosure, the second extended curve can be understood as a curve extending along the vertical line toward the non-tumor area side of the junction line and parallel to the junction line. If there are two or more second extended curves, each second extended curve can be but is not limited to being distributed at the same interval. The non-tumor area on one side of the junction line is grid-divided by the vertical line, the junction line, and at least one second extended curve. The size of the second preset number is related to the preset pixel parameter.

[0159] Step 305: numbering the preset number of grid areas to obtain an area number corresponding to each grid area.

[0160] Specifically in the disclosed embodiment, the preset number is the sum of the first preset number and the second preset number. All grid areas are numbered, and a mapping relationship can be established between the preset number of grid areas and the spatial transcriptome data, so as to facilitate the analysis and processing of different areas of the tumor infiltration area.

[0161] Step 306: determine the region number corresponding to each target sampling point to obtain the infiltration boundary region.

[0162] As a refinement of an embodiment of the present disclosure, the determining the area number corresponding to each of the target sampling points includes: respectively calculating the vector outer product of each of the target sampling points and each boundary curve of the grid area; wherein the boundary curve includes the vertical line, the boundary line, the first extended curve, or the second extended curve; if the vector outer products have opposite signs, it is determined that the target sampling point is located in the grid area; based on the area number of the grid area, determining the area number corresponding to each of the target sampling points.

[0163] Specifically, in the embodiment of the present disclosure, to determine the region number corresponding to each target sampling point, it is necessary to first confirm which grid region the target sampling point is located in. By calculating the vector outer product of the target sampling point and the boundary curve of the grid region, it is determined which grid region each target sampling point is located in. After determining the grid region in which the target sampling point is located, each target sampling point will obtain a corresponding region number.

[0164] In another achievable manner of the embodiment of the present disclosure, the determining the area number corresponding to each of the target sampling points further includes: determining the grid area corresponding to each of the target sampling points based on a second preset image processing algorithm; and determining the area number corresponding to each of the target sampling points based on the area number of the grid area.

[0165] Specifically, the second preset image processing algorithm may be, for example, a flood fill method, and the second preset image processing algorithm is used to obtain the grid area corresponding to each target sample point. After determining the grid area where the target sampling point is located, each target sample point will obtain a corresponding area number. It should be noted that the embodiments of the present disclosure do not constitute a limitation on the second preset image processing algorithm.

[0166] In order to clearly illustrate the embodiment of the present disclosure, the embodiment of the present disclosure provides a flowchart of another method for analyzing tumor infiltration boundaries.

[0167] like Figure 5 As shown, the method comprises the following steps:

[0168] Step 401: group the grid areas according to a preset grouping method.

[0169] Specifically in the embodiments of the present disclosure, the preset grouping method may be, for example, grouping according to rows and columns of grid areas, or grouping according to specific areas, which is not limited in the present disclosure.

[0170] Step 402: Based on the spatial transcriptome data, obtain the heterogeneity statistical information of different groups to obtain the boundary region heterogeneity statistical information.

[0171] Specifically, in the embodiments of the present disclosure, the heterogeneity statistical information can be understood as statistical information reflecting the heterogeneity of the tumor infiltration area, such as cell type ratio, gene expression, enrichment score difference of tumor-related pathways, etc., which is not limited in the present disclosure. The heterogeneity statistical information of all different groups reflects the heterogeneity statistical information of the boundary area of ​​the entire tumor infiltration area.

[0172] Step 403: Determine the enriched gene information of the boundary region according to the infiltration boundary region and the spatial transcriptome information.

[0173] Step 4031: Based on the spatial transcriptome information, the expression levels of different genes in each of the target sampling points are obtained respectively.

[0174] Step 4032: sort the expression quantities according to the distance between the target sampling point corresponding to the expression quantity and the boundary line.

[0175] Specifically in the disclosed embodiment, for each gene in the tumor infiltration area, the expression level of each gene at all target sampling points is obtained from the spatial transcriptome data, and the distances from the target sampling points to the boundary line corresponding to the expression level of each gene are sorted.

[0176] Step 4033: Based on a preset testing method, the genes corresponding to the sorted expression levels are tested to obtain a cumulative curve.

[0177] Specifically, in the embodiment of the present disclosure, the preset test method may be, for example, the Kolmogorov–Smirnov test (KS test), which is not limited in the present disclosure; the preset test method is used to detect whether the expression level of any gene obeys a preset probability distribution or a random distribution. The expression levels after sorting are tested to obtain a cumulative curve.

[0178] Step 4034, processing the cumulative curve to obtain a target evaluation index.

[0179] Specifically in the embodiment of the present disclosure, the target evaluation index may be the AUC value and the Delta D value of the cumulative curve, which is not limited in the present disclosure. The AUC value and the Delta D value of the cumulative curve corresponding to each gene calculated are used as the target evaluation index.

[0180] Step 4035, processing the target evaluation indicators of all genes in the infiltration boundary region to obtain the enriched gene information of the boundary region.

[0181] Specifically, in the embodiment of the present disclosure, by sorting the AUC values ​​in descending order, the genes whose AUC values ​​exceed the preset threshold are the boundary region enriched genes. Figure 6 , Figure 6 The figure shows that after dividing the tumor infiltration area, the enrichment scores of different pathways on both sides of the boundary line were calculated, and the gradual difference in gene expression from tumor to normal tissue was successfully observed.

[0182] In summary, the present disclosure provides a method for calculating the enriched genes in the border region, which can accurately identify the enriched gene information in the border region of the tumor infiltration region, and can further quantitatively analyze the microenvironment of the tumor infiltration region, providing more reliable data support for the field of tumor research.

[0183] In order to clearly illustrate the embodiment of the present disclosure, the embodiment of the present disclosure provides a flowchart of another method for analyzing tumor infiltration boundaries.

[0184] like Figure 7 As shown, the method comprises the following steps:

[0185] Step 501 : preprocess the spatial transcriptome data to obtain preprocessed spatial transcriptome data.

[0186] Step 502: performing standardization processing on the pre-processed spatial transcriptome data to obtain standardized spatial transcriptome data.

[0187] Step 503: Perform dimensionality reduction processing on the spatial transcriptome data after the standardization processing to obtain the spatial transcriptome data after the dimensionality reduction processing.

[0188] Step 504: perform clustering processing on the spatial transcriptome data after the dimension reduction processing to obtain clusters corresponding to different genes.

[0189] Step 505 , determining the tumor area and the non-tumor area according to the preset gene expression levels and the clusters corresponding to the different genes.

[0190] Step 506 , calling a first preset image processing algorithm to process the spatial transcriptome data and determine the infiltration boundary between the tumor area and the non-tumor area.

[0191] Step 507: Fitting the infiltration boundary line to obtain the boundary line.

[0192] Step 508: divide the boundary line into equal parts according to preset pixel parameters, and determine a first number of equal division points.

[0193] Step 509: Create perpendicular lines of equal length on both sides of each of the equally divided points according to the second preset length.

[0194] Step 510, based on the vertical line, the boundary line, and at least one first expansion curve, gridding the tumor area on one side of the boundary line to obtain a first preset number of grid areas; wherein the at least one first expansion curve is parallel to the boundary line.

[0195] Step 511, based on the vertical line, the boundary line, and at least one second extension curve, gridding the non-tumor area on the other side of the boundary line to obtain a second preset number of grid areas; wherein the at least one second extension curve is parallel to the boundary line.

[0196] Step 512: numbering the preset number of grid areas to obtain an area number corresponding to each grid area.

[0197] Step 513: determine the region number corresponding to each target sampling point to obtain the infiltration boundary region.

[0198] Step 514: group the grid areas according to a preset grouping method.

[0199] Step 515: Based on the spatial transcriptome data, obtain the heterogeneity statistical information of different groups to obtain the boundary area heterogeneity statistical information.

[0200] Step 516: Determine the enriched gene information of the boundary region according to the infiltration boundary region and the spatial transcriptome information.

[0201] For details about steps 501 to 516, please refer to the above embodiment, and the embodiments of the present disclosure will not be described in detail one by one.

[0202] It should be noted that the embodiments of the present disclosure may include multiple steps. For the convenience of description, these steps are numbered, but these numbers do not limit the execution time slots or execution order between the steps; these steps can be implemented in any order, and the embodiments of the present disclosure do not limit this.

[0203] Corresponding to the above-mentioned method for analyzing tumor invasion boundaries, the present invention also provides a device for analyzing tumor invasion boundaries. Since the device embodiment of the present invention corresponds to the above-mentioned method embodiment, details not disclosed in the device embodiment can be referred to the above-mentioned method embodiment, and will not be described in detail in the present invention.

[0204] Figure 8 A schematic diagram of a device for analyzing tumor invasion boundaries provided in an embodiment of the present disclosure is shown in FIG. Figure 8 As shown, including:

[0205] A first determination unit 61 is used to analyze the spatial transcriptome data to determine the tumor area and the non-tumor area;

[0206] A second determining unit 62 is used to divide the tumor area and the non-tumor area into boundaries, and determine a boundary line between the tumor area and the non-tumor area;

[0207] A first processing unit 63 is used to divide the areas on both sides of the boundary line to obtain a preset number of grid areas;

[0208] A second processing unit 64 is used to number the preset number of grid areas to obtain infiltration boundary areas;

[0209] The analyzing unit 65 is used to perform analysis on the boundary region heterogeneity statistical information and the boundary region enriched gene information based on the spatial transcriptome data and the infiltration boundary region.

[0210] The present disclosure provides a device for analyzing tumor infiltration boundaries, which determines the tumor area and the non-tumor area by analyzing the spatial transcriptome data; divides the boundary between the tumor area and the non-tumor area to determine the boundary between the tumor area and the non-tumor area; divides the areas on both sides of the boundary to obtain a preset number of grid areas; numbers the preset number of grid areas to obtain the infiltration boundary area; and performs analysis of the boundary area heterogeneity statistical information and the boundary area enrichment gene information based on the spatial transcriptome data and the infiltration boundary area. The present disclosure determines the boundary between the tumor area and the non-tumor area by processing the spatial transcriptome data; after gridding the areas on both sides of the boundary, the gridded infiltration boundary area is analyzed, so as to realize the quantitative analysis of the tumor infiltration boundary area using the spatial transcriptome data; and can explain and analyze the invasion and infiltration process of the tumor.

[0211] Furthermore, in a possible implementation of this embodiment, as Fig. 9 As shown, the first determining unit 61 includes:

[0212] A first processing module 611 is used to preprocess the spatial transcriptome data to obtain preprocessed spatial transcriptome data;

[0213] A second processing module 612 is used to perform standardization processing on the pre-processed spatial transcriptome data to obtain standardized spatial transcriptome data;

[0214] The third processing module 613 is used to perform dimensionality reduction processing on the spatial transcriptome data after the standardization processing to obtain the spatial transcriptome data after the dimensionality reduction processing;

[0215] The fourth processing module 614 is used to perform clustering processing on the spatial transcriptome data after the dimensionality reduction processing to obtain clusters corresponding to different genes;

[0216] The first determination module 615 is used to determine the tumor area and the non-tumor area according to the preset gene expression levels and the clusters corresponding to the different genes.

[0217] Furthermore, in a possible implementation of this embodiment, the first processing module 611 is further configured to:

[0218] Based on a first preset length, merging the first grid in the spatial transcriptome chip into a target sampling point;

[0219] The transcripts in each of the target sampling points are integrated to obtain the pre-processed spatial transcriptome data.

[0220] Furthermore, in a possible implementation of this embodiment, as Fig. 9 As shown, the second determining unit 62 includes:

[0221] A fifth processing module 621 is used to call a first preset image processing algorithm to process the spatial transcriptome data to determine an infiltration boundary between the tumor area and the non-tumor area;

[0222] The fitting module 622 is used to perform fitting processing on the infiltration boundary line to obtain the boundary line.

[0223] Furthermore, in a possible implementation of this embodiment, as Fig. 9 As shown, the first processing unit 63 includes:

[0224] A second determination module 631 is used to divide the boundary line into equal parts according to a preset pixel parameter to determine a first number of equal division points;

[0225] A creation module 632, configured to create perpendicular lines of equal length to both sides of each of the equally divided points according to a second preset length;

[0226] A first division module 633 is used to perform grid division on the tumor area on one side of the boundary line based on the vertical line, the boundary line, and at least one first expansion curve to obtain a first preset number of grid areas; wherein the at least one first expansion curve is parallel to the boundary line;

[0227] The second division module 634 is used to grid the non-tumor area on the other side of the junction line based on the vertical line, the junction line, and at least one second extension curve to obtain a second preset number of grid areas; wherein the at least one second extension curve is parallel to the junction line.

[0228] Furthermore, in a possible implementation of this embodiment, as Fig. 9 As shown, the second processing unit 64 includes:

[0229] A sixth processing module 641 is used to number the preset number of grid areas to obtain an area number corresponding to each grid area;

[0230] The third determination module 642 is used to determine the region number corresponding to each target sampling point to obtain the infiltration boundary region.

[0231] Further, in a possible implementation of this embodiment, the third determining module 642 is used to:

[0232] Calculating the vector outer product of each target sampling point and each boundary curve of the grid area respectively; wherein the boundary curve includes the vertical line, the intersection line, the first extended curve or the second extended curve;

[0233] If the vector outer product has opposite signs, it is determined that the target sampling point is located in the grid area;

[0234] Based on the area number of the grid area, the area number corresponding to each of the target sampling points is determined.

[0235] Furthermore, in a possible implementation of this embodiment, the third determining module 642 is further configured to:

[0236] Based on a second preset image processing algorithm, determining the grid area corresponding to each of the target sampling points;

[0237] Based on the area number of the grid area, the area number corresponding to each of the target sampling points is determined.

[0238] Furthermore, in a possible implementation of this embodiment, as Fig. 9 As shown, the analysis unit 65 includes:

[0239] A grouping module 651 is used to group the grid areas according to a preset grouping method;

[0240] An acquisition module 652 is used to acquire heterogeneity statistical information of different groups based on the spatial transcriptome data to obtain the heterogeneity statistical information of the boundary area;

[0241] The fourth determination module 653 is used to determine the enriched gene information of the boundary area according to the infiltration boundary area and the spatial transcriptome information.

[0242] Furthermore, in a possible implementation of this embodiment, the fourth determining module 653 is further configured to:

[0243] Based on the spatial transcriptome information, respectively obtaining the expression levels of different genes in each of the target sampling points;

[0244] Sorting the expression amounts according to the distances between the target sampling points corresponding to the expression amounts and the boundary line;

[0245] Based on a preset test method, the genes corresponding to the sorted expression levels are tested to obtain a cumulative curve;

[0246] Processing the cumulative curve to obtain a target evaluation index;

[0247] The target evaluation indicators of all genes in the infiltration boundary area are processed to obtain the enriched gene information of the boundary area.

[0248] It should be noted that the above explanation of the method embodiment is also applicable to the device of this embodiment, and the principle is the same, which is no longer limited in this embodiment.

[0249] According to an embodiment of the present disclosure, the present disclosure also provides an electronic device, a readable storage medium and a computer program product.

[0250] Fig.10 A schematic block diagram of an example electronic device 700 that can be used to implement an embodiment of the present disclosure is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present disclosure described and / or required herein.

[0251] like Fig.10 As shown, the device 700 includes a computing unit 701, which can perform various appropriate actions and processes according to a computer program stored in a ROM (Read-Only Memory) 702 or a computer program loaded from a storage unit 708 to a RAM (Random Access Memory) 703. In the RAM 703, various programs and data required for the operation of the device 700 can also be stored. The computing unit 701, the ROM 702, and the RAM 703 are connected to each other via a bus 704. An I / O (Input / Output) interface 705 is also connected to the bus 704.

[0252] A number of components in the device 700 are connected to the I / O interface 705, including: an input unit 706, such as a keyboard, a mouse, etc.; an output unit 707, such as various types of displays, speakers, etc.; a storage unit 708, such as a disk, an optical disk, etc.; and a communication unit 709, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 709 allows the device 700 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.

[0253] The computing unit 701 may be a variety of general and / or special processing components with processing and computing capabilities. Some examples of the computing unit 701 include, but are not limited to, a CPU (Central Processing Unit), a GPU (Graphic Processing Units), various dedicated AI (Artificial Intelligence) computing chips, various computing units running machine learning model algorithms, a DSP (Digital Signal Processor), and any appropriate processor, controller, microcontroller, etc. The computing unit 701 performs the various methods and processes described above, such as a method for tumor infiltration boundary analysis. For example, in some embodiments, the method for tumor infiltration boundary analysis may be implemented as a computer software program, which is tangibly contained in a machine-readable medium, such as a storage unit 708. In some embodiments, part or all of the computer program may be loaded and / or installed on the device 700 via the ROM 702 and / or the communication unit 709. When the computer program is loaded into the RAM 703 and executed by the computing unit 701, one or more steps of the method described above may be performed. Alternatively, in other embodiments, the computing unit 701 may be configured to perform the aforementioned tumor invasion boundary analysis method in any other appropriate manner (eg, by means of firmware).

[0254] Various embodiments of the systems and techniques described above herein may be implemented in digital electronic circuit systems, integrated circuit systems, FPGAs (Field Programmable Gate Arrays), ASICs (Application-Specific Integrated Circuits), ASSPs (Application Specific Standard Products), SOCs (System On Chips), CPLDs (Complex Programmable Logic Devices), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include: being implemented in one or more computer programs that may be executed and / or interpreted on a programmable system including at least one programmable processor that may be a special purpose or general purpose programmable processor that may receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0255] The program code for implementing the method of the present disclosure may be written in any combination of one or more programming languages. These program codes may be provided to a processor or controller of a general-purpose computer, a special-purpose computer, or other programmable data processing device, so that the program code, when executed by the processor or controller, enables the functions / operations specified in the flow chart and / or block diagram to be implemented. The program code may be executed entirely on the machine, partially on the machine, partially on the machine and partially on a remote machine as a stand-alone software package, or entirely on a remote machine or server.

[0256] In the context of the present disclosure, a machine-readable medium may be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, device, or equipment. A machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or device, or any suitable combination of the foregoing. More specific examples of machine-readable storage media may include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a RAM, a ROM, an EPROM (Electrically Programmable Read-Only-Memory) or a flash memory, an optical fiber, a CD-ROM (Compact Dis sc Read-Only Memory), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0257] To provide interaction with a user, the systems and techniques described herein can be implemented on a computer having: a display device (e.g., a CRT (Cathode-Ray Tube) or LCD (Liquid Crystal Display) monitor) for displaying information to the user; and a keyboard and a pointing device (e.g., a mouse or trackball), through which the user can provide input to the computer. Other types of devices can also be used to provide interaction with the user; for example, the feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including acoustic input, voice input, or tactile input).

[0258] The systems and techniques described herein may be implemented in a computing system that includes backend components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes frontend components (e.g., a user computer with a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such backend components, middleware components, or frontend components. The components of the system may be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: LAN (Local Area Network), WAN (Wide Area Network), the Internet, and blockchain networks.

[0259] A computer system may include a client and a server. The client and the server are generally remote from each other and usually interact through a communication network. The relationship between the client and the server is generated by computer programs running on the corresponding computers and having a client-server relationship with each other. The server may be a cloud server, also known as a cloud computing server or cloud host, which is a host product in the cloud computing service system to solve the defects of difficult management and weak business scalability in traditional physical hosts and VPS services ("Virtual Private Server", or "VPS" for short). The server may also be a server of a distributed system, or a server combined with a blockchain.

[0260] It should be noted that artificial intelligence is a discipline that studies how computers can simulate certain human thought processes and intelligent behaviors (such as learning, reasoning, thinking, planning, etc.), and includes both hardware-level and software-level technologies. Artificial intelligence hardware technologies generally include technologies such as sensors, dedicated artificial intelligence chips, cloud computing, distributed storage, and big data processing; artificial intelligence software technologies mainly include computer vision technology, speech recognition technology, natural language processing technology, as well as machine learning / deep learning, big data processing technology, knowledge graph technology, and other major directions.

[0261] It should be understood that the various forms of processes shown above can be used to reorder, add or delete steps. For example, the steps recorded in this disclosure can be executed in parallel, sequentially or in different orders, as long as the desired results of the technical solutions disclosed in this disclosure can be achieved, and this document does not limit this.

[0262] The above specific implementations do not constitute a limitation on the protection scope of the present disclosure. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modification, equivalent substitution and improvement made within the spirit and principle of the present disclosure shall be included in the protection scope of the present disclosure.

Claims

1. A method for analyzing tumor invasion boundaries, characterized in that: include: Spatial transcriptome data were analyzed to identify tumor and non-tumor areas; Demarcating the tumor area and the non-tumor area to determine a boundary line between the tumor area and the non-tumor area; Dividing the areas on both sides of the boundary line to obtain a preset number of grid areas; Numbering the preset number of grid areas to obtain infiltration boundary areas; Based on the spatial transcriptome data and the infiltration boundary area, analysis of boundary area heterogeneity statistical information and boundary area enriched gene information is performed.

2. The method according to claim 1, characterized in that: The analysis of the spatial transcriptome data to determine the tumor area and the non-tumor area includes: Preprocessing the spatial transcriptome data to obtain preprocessed spatial transcriptome data; Performing standardization processing on the pre-processed spatial transcriptome data to obtain standardized spatial transcriptome data; Performing dimensionality reduction processing on the spatial transcriptome data after the standardization processing to obtain spatial transcriptome data after dimensionality reduction processing; Performing clustering processing on the spatial transcriptome data after the dimensionality reduction processing to obtain clusters corresponding to different genes; The tumor area and the non-tumor area are determined according to the preset gene expression levels and the clusters corresponding to the different genes.

3. The method according to claim 2, characterized in that The preprocessing of the spatial transcriptome data to obtain the preprocessed spatial transcriptome data comprises: Based on a first preset length, merging the first grid in the spatial transcriptome chip into a target sampling point; The transcripts in each of the target sampling points are integrated to obtain the pre-processed spatial transcriptome data.

4. The method according to claim 1, characterized in that: The dividing the boundary between the tumor area and the non-tumor area to determine the boundary line between the tumor area and the non-tumor area comprises: Invoking a first preset image processing algorithm to process the spatial transcriptome data to determine an infiltration boundary between the tumor area and the non-tumor area; The infiltration boundary line is fitted to obtain the boundary line.

5. The method according to claim 1, characterized in that The dividing process of the areas on both sides of the boundary line to obtain a preset number of grid areas includes: Divide the boundary line into equal parts according to preset pixel parameters to determine a first number of equal division points; According to a second preset length, creating perpendicular lines of equal length to both sides of each of the equally divided points; Based on the vertical line, the boundary line, and at least one first expansion curve, the tumor area on one side of the boundary line is grid-divided to obtain a first preset number of grid areas; wherein the at least one first expansion curve is parallel to the boundary line; Based on the vertical line, the boundary line, and at least one second expansion curve, the non-tumor area on the other side of the boundary line is gridded to obtain a second preset number of grid areas; wherein the at least one second expansion curve is parallel to the boundary line.

6. The method according to claim 3 or 5, characterized in that: The step of numbering the preset number of grid areas to obtain the infiltration boundary area comprises: Numbering the preset number of grid areas to obtain an area number corresponding to each grid area; The region number corresponding to each target sampling point is determined to obtain the infiltration boundary region.

7. The method according to claim 6, characterized in that Determining the area number corresponding to each target sampling point includes: Calculating the vector outer product of each target sampling point and each boundary curve of the grid area respectively; wherein the boundary curve includes the vertical line, the intersection line, the first extended curve or the second extended curve; If the vector outer product has opposite signs, it is determined that the target sampling point is located in the grid area; Based on the area number of the grid area, the area number corresponding to each of the target sampling points is determined.

8. The method according to claim 6, characterized in that The determining the area number corresponding to each target sampling point further includes: Based on a second preset image processing algorithm, determining the grid area corresponding to each of the target sampling points; Based on the area number of the grid area, the area number corresponding to each of the target sampling points is determined.

9. The method according to claim 6, characterized in that: The performing of the analysis of the boundary region heterogeneity statistical information and the boundary region enriched gene information based on the spatial transcriptome data and the infiltration boundary region comprises: Grouping the grid areas according to a preset grouping method; Based on the spatial transcriptome data, obtaining heterogeneity statistical information of different groups to obtain the heterogeneity statistical information of the boundary area; According to the infiltration boundary area and the spatial transcriptome information, the enriched gene information of the boundary area is determined.

10. The method according to claim 9, characterized in that Determining the enriched gene information in the border region according to the infiltration border region and the spatial transcriptome information includes: Based on the spatial transcriptome information, respectively obtaining the expression levels of different genes in each of the target sampling points; Sorting the expression quantities according to the distance between the target sampling point corresponding to the expression quantity and the boundary line; Based on a preset test method, the genes corresponding to the sorted expression levels are tested to obtain a cumulative curve; Processing the cumulative curve to obtain a target evaluation index; The target evaluation indicators of all genes in the infiltration boundary area are processed to obtain the enriched gene information of the boundary area.

11. A device for analyzing tumor invasion boundaries, characterized in that: include: A first determination unit is used to analyze the spatial transcriptome data to determine the tumor area and the non-tumor area; A second determining unit is used to divide the tumor area and the non-tumor area into boundaries, and determine a boundary line between the tumor area and the non-tumor area; A first processing unit is used to divide the areas on both sides of the boundary line to obtain a preset number of grid areas; A second processing unit is used to number the preset number of grid areas to obtain infiltration boundary areas; An analysis unit is used to perform analysis of boundary region heterogeneity statistical information and boundary region enrichment gene information based on the spatial transcriptome data and the infiltration boundary region.

12. An electronic device, characterized in that: include: at least one processor; as well as a memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the method according to any one of claims 1 to 10.

13. A non-transitory computer-readable storage medium storing computer instructions, characterized in that: The computer instructions are used to cause the computer to execute the method according to any one of claims 1-10.

14. A computer program product, characterized in that A computer program is included which, when executed by a processor, implements the method according to any one of claims 1 to 10.

Images