Classification method and device of three-level lymph structure, electronic equipment and storage medium

Abstract

The invention discloses a three-level lymphatic structure classification method and device, electronic equipment and a storage medium, and relates to the technical field of three-level lymphatic structure classification, and the main technical scheme comprises the following steps: carrying out first principal component analysis on related data information of a three-level lymphatic structure, and screening first principal components based on a preset variance contribution threshold; calculating a gene set enrichment fraction of the three-level lymph structure, performing second principal component analysis on the gene set enrichment fraction and the screened first principal component, and determining a target second principal component; and determining the position of the three-level lymphatic structure in the spatial diagram based on the target second principal component. A first round of feature mapping is performed on each feature of the three-level lymphatic structure, a second round of feature extraction is performed on the integrated features and a gene set enrichment score of the three-level lymphatic structure, a spatial diagram position of the three-level lymphatic structure is determined according to a second principal component of a target, and the three-level lymphatic structure is obtained by combining case cognition and the spatial diagram position of the three-level lymphatic structure. The three-level lymph structure can be effectively classified, and the development state can be effectively identified.

Description

Technical Field

[0001] The present disclosure relates to the technical field of three-level lymphatic structure classification, and in particular to a three-level lymphatic structure classification method, device, electronic device and storage medium. Background Art

[0002] Tertiary lymphatic structures are lymphatic tissues that often occur in chronic inflammatory tissues, especially cancerous tissues. The criteria and methods for their classification have always been based on pathological sections as the gold standard.

[0003] The current classification technology makes it difficult to identify and classify tertiary lymphatic structures that are not obvious or immature. Summary of the invention

[0004] The present disclosure provides a classification method, device, electronic device and storage medium for tertiary lymphatic structures, the main purpose of which is to classify tertiary lymphatic structures and identify their developmental states.

[0005] According to a first aspect of the present disclosure, a method for classifying three-level lymphatic structures is provided, comprising:

[0006] Performing first principal component analysis on the relevant data information of the three-level lymphatic structure respectively, and screening the first principal components based on a preset variance contribution threshold, retaining the first principal components whose variance contribution values ​​are greater than or equal to the preset variance contribution threshold, wherein the relevant data information of the three-level lymphatic structure includes at least one of a cell composition ratio, a characteristic gene positive rate, a cell neighborhood ratio, a characteristic gene expression level, and a characteristic receptor ligand pair expression level;

[0007] Calculating the gene set enrichment score of the tertiary lymphatic structure, performing a second principal component analysis based on the gene set enrichment score of the tertiary lymphatic structure and the screened first principal component, and determining a target second principal component;

[0008] The position of the tertiary lymphatic structure in the spatial map is determined based on the target second principal component.

[0009] Optionally, before performing the first principal component analysis on the data information related to the three-level lymphatic structures respectively, the method includes:

[0010] Performing center normalization processing on at least one of the cell composition ratio, characteristic gene positive rate and cell neighborhood ratio to eliminate order of magnitude differences;

[0011] A cell smoothness factor is calculated, and data is normalized based on at least one of the expression level of a characteristic gene and the expression level of a characteristic receptor ligand pair of cells using the cell smoothness factor.

[0012] Optionally, before determining the position of the tertiary lymphatic structure in the spatial map based on the target second principal component, the method further includes:

[0013] The variance contribution of each second principal component is calculated, and each second principal component is screened according to the variance contribution and a preset quantity threshold to determine a target second principal component.

[0014] Optionally, determining the target second principal component includes:

[0015] The second principal components are ranked from large to small according to their variance contribution, and the top three second principal components are determined as the target second principal components;

[0016] The determining the position of the tertiary lymphatic structure in the spatial map based on a preset number of second principal components comprises:

[0017] According to the ranking order of the target second principal component, the horizontal coordinate, the vertical coordinate and the vertical coordinate of the tertiary lymphatic structure are determined in sequence to determine the position of the tertiary lymphatic structure in the spatial map.

[0018] Optionally, the second principal component includes at least two eigenvectors, and after determining the position of the third-level lymphatic structure in the spatial map, the method further includes:

[0019] Calculate the feature proportion of each of the eigenvectors in each of the second principal components of the target;

[0020] The developmental state of the tertiary lymphatic structure is determined according to the feature proportion and the position of the tertiary lymphatic structure in the spatial map.

[0021] Optionally, after determining the position of the tertiary lymphatic structure in the spatial map, the method further includes:

[0022] Calculate the feature proportion of each of the eigenvectors in each of the second principal components of the target;

[0023] The category of the lymphatic structure is determined according to the feature proportion of each lymphatic structure, the position in the spatial map and the preset classification rules.

[0024] According to a second aspect of the present disclosure, a classification device for a three-level lymphatic structure is provided, comprising:

[0025] A first principal component analysis unit, used for performing first principal component analysis on the relevant data information of the three-level lymphatic structures respectively;

[0026] A first screening unit is used to screen the first principal component based on a preset variance contribution threshold, and retain the first principal component whose variance contribution value is greater than or equal to the preset variance contribution threshold, wherein the relevant data information of the three-level lymphatic structure includes at least one of a cell composition ratio, a characteristic gene positive rate, a cell neighborhood ratio, a characteristic gene expression level, and a characteristic receptor ligand pair expression level;

[0027] A calculation unit, used to calculate the gene set enrichment score of the tertiary lymphoid structure;

[0028] A second principal component analysis unit is used to perform a second principal component analysis based on the gene set enrichment score of the tertiary lymphatic structure and the screened first principal component to determine a target second principal component;

[0029] The first determination unit is used to determine the position of the tertiary lymphatic structure in the spatial map based on the target second principal component.

[0030] Optionally, the device comprises:

[0031] A processing unit is used to perform center normalization processing on at least one of the cell composition ratio, the characteristic gene positive rate and the cell neighborhood ratio before the first principal component analysis unit respectively performs the first principal component analysis on the relevant data information of the three-level lymphatic structure to eliminate the order of magnitude difference;

[0032] The first calculation unit is used to calculate a cell smoothness factor, and perform data normalization on at least one of the expression level of a characteristic gene and the expression level of a characteristic receptor ligand pair of cells according to the cell smoothness factor.

[0033] Optionally, the device further comprises:

[0034] The second screening unit is used to calculate the variance contribution of each second principal component before the second principal component analysis unit determines the position of the tertiary lymphatic structure in the spatial map based on the target second principal component, and screen each second principal component according to the variance contribution and a preset quantity threshold to determine the target second principal component.

[0035] Optionally, the second screening unit is further used for:

[0036] The second principal components are ranked from large to small according to their variance contribution, and the top three second principal components are determined as the target second principal components;

[0037] The first determining unit is further configured to:

[0038] According to the ranking order of the target second principal component, the horizontal coordinate, the vertical coordinate and the vertical coordinate of the tertiary lymphatic structure are determined in sequence to determine the position of the tertiary lymphatic structure in the spatial map.

[0039] Optionally, the second principal component includes at least two eigenvectors, and the device further includes:

[0040] A second calculation unit is used to calculate the feature proportion of each of the feature vectors in each of the target second principal components after the first determination unit determines the position of the third-level lymphatic structure in the spatial map;

[0041] The second determining unit is used to determine the developmental state of the tertiary lymphatic structure according to the feature proportion and the position of the tertiary lymphatic structure in the spatial map.

[0042] Optionally, the device further comprises:

[0043] The second calculation unit is further configured to calculate the feature proportion of each of the feature vectors in each of the target second principal components after the first determination unit determines the position of the third-level lymphatic structure in the spatial map;

[0044] The second determination unit is further used to determine the category of the lymphatic structure according to the feature proportion of each lymphatic structure, the position in the spatial map and the preset classification rule.

[0045] According to a third aspect of the present disclosure, there is provided an electronic device, including:

[0046] at least one processor; and

[0047] a memory communicatively connected to the at least one processor; wherein,

[0048] 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.

[0049] 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.

[0050] 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.

[0051] The classification method, device, electronic device and storage medium of the tertiary lymphatic structure provided by the present disclosure, the main technical scheme includes: first, respectively perform a first principal component analysis on the relevant data information of the tertiary lymphatic structure, and screen the first principal component based on a preset variance contribution threshold, retaining the first principal component whose variance contribution value is greater than or equal to the preset variance contribution threshold; second, calculate the gene set enrichment score of the tertiary lymphatic structure, perform a second principal component analysis based on the gene set enrichment score of the tertiary lymphatic structure and the screened first principal component, and determine the target second principal component; finally, determine the position of the tertiary lymphatic structure in the spatial map based on the target second principal component. Compared with the related art, the embodiment of the present application performs a first round of feature mapping on each feature of the tertiary lymphatic structure, performs a second round of feature extraction on the gene set enrichment score of the tertiary lymphatic structure after integration of each feature, and determines the spatial map position of the tertiary lymphatic structure according to the target second principal component, and by combining case cognition with the spatial map position of the tertiary lymphatic structure, the tertiary lymphatic structure can be effectively classified and the developmental state can be identified.

[0052] 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

[0053] The accompanying drawings are used to better understand the present solution and do not constitute a limitation of the present disclosure.

[0054] Figure 1 A schematic diagram of a flow chart of a method for classifying three-level lymphatic structures provided in an embodiment of the present disclosure;

[0055] Figure 2 A schematic flow chart of a method for processing data information related to a three-level lymphatic structure provided in an embodiment of the present disclosure;

[0056] Figure 3 A schematic diagram of the spatial position of a three-level lymphatic structure provided in an embodiment of the present disclosure;

[0057] Figure 4 A schematic diagram of the structure of a three-level lymphatic structure classification device provided in an embodiment of the present disclosure;

[0058] Figure 5 A schematic diagram of the structure of another three-level lymphatic structure classification device provided in an embodiment of the present disclosure;

[0059] Figure 6 A schematic block diagram of an exemplary electronic device provided for an embodiment of the present disclosure. DETAILED DESCRIPTION

[0060] 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.

[0061] The following describes the classification method, device, electronic device and storage medium of the three-level lymphatic structure according to the embodiments of the present disclosure with reference to the accompanying drawings.

[0062] Figure 1 A schematic flow chart of a method for classifying three-level lymphatic structures provided in an embodiment of the present disclosure.

[0063] like Figure 1 As shown, the method comprises the following steps:

[0064] Step 101, performing first principal component analysis on the relevant data information of the three-level lymphatic structure respectively, and screening the first principal component based on a preset variance contribution threshold, retaining the first principal component whose variance contribution value is greater than or equal to the preset variance contribution threshold, the relevant data information of the three-level lymphatic structure includes at least one of cell composition ratio, characteristic gene positivity rate, cell neighborhood ratio, characteristic gene expression level and characteristic receptor ligand pair expression level.

[0065] Tertiary lymphoid structures (TLS) are lymphoid tissue structures found in non-lymphoid tissues. They are common in a variety of tissues in an inflamed state and can drive the activation of immune cells. Their formation is related to a variety of chronic diseases such as chronic inflammatory diseases, autoimmune diseases and cancer.

[0066] The first principal component analysis is performed on the cell composition ratio, the characteristic gene positivity rate, the cell neighborhood ratio, the characteristic gene expression level, and the characteristic receptor ligand pair expression level, and the relevant data information of each tertiary lymphatic structure is feature extracted to obtain the first principal component, and the variance contribution of the first principal component is calculated respectively, and the first principal component is screened based on a preset variance contribution threshold, and the first principal component whose variance contribution is greater than or equal to the preset variance contribution threshold is retained; the preset variance contribution threshold is an empirical value, which can be set to any value between 5% and 10%. The embodiment of the present application takes the preset variance contribution threshold of 5% as an example for explanation, but this description method is not a limitation on the specific preset variance contribution threshold, and the embodiment of the present application does not limit the preset variance contribution threshold.

[0067] For the detailed implementation method of the first principal component analysis and the variance contribution of the first principal component, please refer to any implementation method in the prior art, and the embodiments of the present application will not be described one by one here.

[0068] Step 102, calculating the gene set enrichment score of the tertiary lymphatic structure, performing a second principal component analysis based on the gene set enrichment score of the tertiary lymphatic structure and the screened first principal component, and determining a target second principal component.

[0069] The gene set enrichment scores of the tertiary lymphoid structures provide the classification criteria for the tertiary lymphoid structures, and the first principal component is used to consider the developmental status of the tertiary lymphoid structures.

[0070] For the specific calculation process of the gene set enrichment score (GSVA) ​​of the tertiary lymphoid structure, please refer to any implementation process in the prior art, and the present embodiment will not be described one by one here.

[0071] Step 103: determining the position of the tertiary lymphatic structure in the spatial map based on the target second principal component.

[0072] The coordinate positions of the tertiary lymphatic structures in the spatial map are determined according to the determined target second principal components, and then the positions of the tertiary lymphatic structures in the spatial map are determined.

[0073] The classification method of the tertiary lymphatic structure provided by the present disclosure mainly includes the following technical solutions: first, respectively perform a first principal component analysis on the relevant data information of the tertiary lymphatic structure, and screen the first principal component based on a preset variance contribution threshold, and retain the first principal component whose variance contribution value is greater than or equal to the preset variance contribution threshold; second, calculate the gene set enrichment score of the tertiary lymphatic structure, perform a second principal component analysis based on the gene set enrichment score of the tertiary lymphatic structure and the screened first principal component, and determine the target second principal component; finally, determine the position of the tertiary lymphatic structure in the spatial map based on the target second principal component. Compared with the related art, the embodiment of the present application performs a first round of feature mapping on each feature of the tertiary lymphatic structure, performs a second round of feature extraction on the gene set enrichment score of the tertiary lymphatic structure after integration of each feature, and determines the spatial map position of the tertiary lymphatic structure according to the target second principal component. By combining case cognition with the spatial map position of the tertiary lymphatic structure, the tertiary lymphatic structure can be effectively classified and the developmental state can be identified.

[0074] The metrics between different categories of data are different, and the dispersion between data is large. Therefore, before performing the first principal component analysis, the relevant data information of the three-level lymphatic structure needs to be preprocessed; please refer to Figure 2 , Figure 2A flowchart of a method for processing data information related to a three-level lymphatic structure provided in an embodiment of the present application includes:

[0075] Step 201, performing center normalization processing on at least one of the cell composition ratio, characteristic gene positive rate and cell neighborhood ratio to eliminate order of magnitude differences.

[0076] For data such as cell composition ratio, characteristic gene positive rate, cell neighborhood ratio, etc., which are based on the third-level lymphatic structure, central normalization is directly performed:

[0077]

[0078] Make each data form a cluster with the origin as the center to reduce the degree of dispersion between data.

[0079] Step 202, calculating a cell smoothness factor, and performing data normalization on at least one of the expression level of a characteristic gene and the expression level of a characteristic receptor ligand pair of the cell according to the cell smoothness factor.

[0080] For the spatial group data of characteristic gene expression levels, characteristic receptor ligand expression levels, etc. in cells, smoothing is performed to reduce the differences caused by sequencing bias. The calculation formula of cell smoothing factor is as follows:

[0081]

[0082] After the cell smoothing privacy calculation is completed, the Monocle3 algorithm can be used to standardize each cell separately, that is, the expression level is divided by the corresponding smoothing factor.

[0083] In one implementable manner of the embodiment of the present application, when determining the target second principal component, the variance contribution of each second principal component is calculated, and each second principal component is screened according to the variance contribution and a preset quantity threshold to determine the target second principal component.

[0084] When determining the target second principal component, firstly rank the second principal components from large to small according to variance contribution, and determine the top three second principal components as the target second principal components;

[0085] The larger the variance contribution, the stronger the ability of the second principal component to integrate the information of the original variable. The target second principal components with the top three variance contribution values ​​are determined. According to the ranking order of the target second principal components, the horizontal coordinate, vertical coordinate and vertical coordinate of the tertiary lymphatic structure are determined in sequence to determine the position of the tertiary lymphatic structure in the spatial map.

[0086] In one implementable manner of the embodiment of the present application, the second principal component contains at least two eigenvectors. After determining the position of the tertiary lymphoid structure in the spatial map, the feature proportion of each eigenvector in each target second principal component is calculated; based on the feature proportion and the position of the tertiary lymphoid structure in the spatial map, the developmental state of the tertiary lymphoid structure is determined, such as a mature tertiary lymphoid structure, early lymphoid aggregates and myeloid cell aggregates, etc. Specifically, the embodiment of the present application is not limited to this.

[0087] In one possible implementation of the embodiment of the present application, after calculating the feature proportion of each feature vector in each target second principal component, the following steps may also be performed: determining the category of the lymphatic structure according to the feature proportion of each lymphatic structure, the position in the spatial map and the preset classification rules. In one possible implementation of the embodiment of the present application, please continue to refer to Figure 3 ,Depend on Figure 3 It can be seen that the position of the lymphatic structure in the spatial map is roughly distributed in three directions, which correspond to different categories of lymphatic structures. Therefore, the preset classification rules of different lymph node structures can be determined according to the position of the lymphatic structure in the spatial map combined with the feature proportion, and the lymphatic structure can be classified according to the preset classification rules.

[0088] To clearly illustrate the classification method of the tertiary lymphatic structure provided in this application, an example is used as an example to illustrate the following; the spatial transcription data of 20 samples of human liver cancer are used as data input, among which there are 461 immune cell aggregates, and the proportion of immune cells and the proportion of immune cell neighborhood relationships are calculated in units of tertiary lymphatic structures, and the positive rate of 74 reported immune aggregate characteristic genes is calculated; in units of cells, the intercellular receptor ligand pairs are calculated using the SPATEO spatial component package, and the joint expression of 283 pairs of receptor ligand pairs is obtained, and the average is taken as the score of each tertiary lymphatic structure. Finally, the GSVA algorithm is used to obtain the enrichment score of the germinal center characteristic gene set of each tertiary lymphatic structure.

[0089] Two principal component analyses were performed based on the above data, and after the second principal component analysis, the first three-dimensional principal components with a total variance contribution of 48% were obtained, please refer to Table 1, which contains: the eigenvectors and characteristic proportions of the first three-dimensional principal components PC1, PC2 and PC3. It should be noted that Table 1 is only an illustrative example, and the embodiments of the present application are not limited to this.

[0090] Table 1

[0091]

[0092]

[0093] Further analysis of the feature vectors with the highest feature ratio in Table 1 reveals the following three-level lymphatic structure features with biological functions:

[0094] 1. In the first dimension PC1, the positive rate of characteristic genes in PC1, lymphocyte induction factor LTB has a higher characteristic ratio.

[0095] 2. In the second dimension PC2 and the third dimension PC3, the characteristic gene positivity PC3 and the receptor ligand pair PC2 both include CCL19, CCL21, CXCL13 and CCR7, CXCR5 with a higher characteristic ratio. The first three will guide the functional expression of the latter two genes in lymphocyte aggregates.

[0096] Use the plotly package to make spatial graphs, such as Figure 3 As shown, Figure 3 A schematic diagram of the spatial position of a tertiary lymphatic structure provided in an embodiment of the present application, wherein the tertiary lymphatic structure can be classified by combining the principal component characteristics of different dimensions found in the Ben-Li analysis and the occurrence characteristics of the tertiary lymphatic structure:

[0097] 1. Mature tertiary lymphoid structures (TLS+) identified by staining.

[0098] 2. Mature lymphoid aggregates (LTi+_LR+) with both lymphocyte aggregation and functional interaction.

[0099] 3. Developing lymphoid aggregates with only one of the lymphocyte aggregation or functional interactions (LTi+_LR- and LTi-_LR+).

[0100] 4. Early lymphoid aggregates without any signal for lymphocyte aggregation or functional interaction (LTi-_LR-).

[0101] 5. Myeloid cell aggregates (MA) without obvious B cells and T cells.

[0102] Please continue reading Figure 3 It can be found that the tertiary lymphoid structure forms three directions, corresponding to the mature tertiary lymphoid structure (TLS+), early lymphoid aggregates and myeloid cell aggregates (LTi-_LR-, MA). As the intermediate state of development, the developing lymphoid aggregates and the maturing lymphoid aggregates (LTi+_LR- and LTi-_LR+, LTi+_LR+) gradually approach the mature tertiary lymphoid structure or myeloid cell aggregates in space.

[0103] The embodiments of the present application also include the following advantages: based on spatial group data, combined with the composition ratio of multiple immune cells, the spatial structure of immune cells, and the expression pattern of key immune-related genes, to assist in supervised classification of pathological sections.

[0104] Corresponding to the above-mentioned three-level lymphatic structure classification method, the present invention also provides a three-level lymphatic structure classification device. Since the device embodiment of the present invention corresponds to the above-mentioned method embodiment, the details not disclosed in the device embodiment can be referred to the above-mentioned method embodiment, and will not be repeated in the present invention.

[0105] Figure 4 A schematic diagram of a three-level lymphatic structure classification device provided in an embodiment of the present disclosure is shown in FIG. Figure 4 As shown, including:

[0106] A first principal component analysis unit 31 is used to perform a first principal component analysis on the relevant data information of the three-level lymphatic structures respectively;

[0107] A first screening unit 32 is used to screen the first principal component based on a preset variance contribution threshold, and retain the first principal component whose variance contribution value is greater than or equal to the preset variance contribution threshold, wherein the relevant data information of the three-level lymphatic structure includes at least one of a cell composition ratio, a characteristic gene positive rate, a cell neighborhood ratio, a characteristic gene expression level, and a characteristic receptor ligand pair expression level;

[0108] A calculation unit 33 is used to calculate the gene set enrichment score of the tertiary lymphoid structure;

[0109] A second principal component analysis unit 34 is used to perform a second principal component analysis based on the gene set enrichment score of the tertiary lymphatic structure and the screened first principal component to determine a target second principal component;

[0110] The first determining unit 35 is used to determine the position of the tertiary lymphatic structure in the spatial map based on the target second principal component.

[0111] The classification device of the tertiary lymphatic structure provided by the present disclosure has the following main technical solutions: first, respectively perform a first principal component analysis on the relevant data information of the tertiary lymphatic structure, and screen the first principal component based on a preset variance contribution threshold, and retain the first principal component whose variance contribution value is greater than or equal to the preset variance contribution threshold; second, calculate the gene set enrichment score of the tertiary lymphatic structure, perform a second principal component analysis based on the gene set enrichment score of the tertiary lymphatic structure and the screened first principal component, and determine the target second principal component; finally, determine the position of the tertiary lymphatic structure in the spatial map based on the target second principal component. Compared with the related art, the embodiment of the present application performs a first round of feature mapping on each feature of the tertiary lymphatic structure, performs a second round of feature extraction on each feature after integration and the gene set enrichment score of the tertiary lymphatic structure, and determines the spatial map position of the tertiary lymphatic structure according to the target second principal component. By combining case cognition with the spatial map position of the tertiary lymphatic structure, the tertiary lymphatic structure can be effectively classified and the developmental state can be identified.

[0112] Furthermore, in a possible implementation of this embodiment, as Figure 5 As shown, the device comprises:

[0113] The processing unit 36 ​​is used to perform center normalization processing on at least one of the cell composition ratio, the characteristic gene positive rate and the cell neighborhood ratio before the first principal component analysis unit 31 performs the first principal component analysis on the relevant data information of the three-level lymphatic structure respectively, so as to eliminate the order of magnitude difference;

[0114] The first calculation unit 37 is used to calculate a cell smoothness factor, and perform data normalization on at least one of the expression level of a characteristic gene and the expression level of a characteristic receptor ligand pair of the cell according to the cell smoothness factor.

[0115] Furthermore, in a possible implementation of this embodiment, as Figure 5 As shown, the device also includes:

[0116] The second screening unit 38 is used to calculate the variance contribution of each second principal component before the second principal component analysis unit 34 determines the position of the tertiary lymphatic structure in the spatial map based on the target second principal component, and screen each second principal component according to the variance contribution and a preset quantity threshold to determine the target second principal component.

[0117] Furthermore, in a possible implementation of this embodiment, the second screening unit 38 is further configured to:

[0118] The second principal components are ranked from large to small according to their variance contribution, and the top three second principal components are determined as the target second principal components;

[0119] The first determining unit 35 is further configured to:

[0120] According to the ranking order of the target second principal component, the horizontal coordinate, the vertical coordinate and the vertical coordinate of the tertiary lymphatic structure are determined in sequence to determine the position of the tertiary lymphatic structure in the spatial map.

[0121] Furthermore, in a possible implementation of this embodiment, as Figure 5 As shown, the second principal component includes at least two eigenvectors, and the device further includes:

[0122] A second calculation unit 39 is used to calculate the feature proportion of each of the feature vectors in each of the target second principal components after the first determination unit 35 determines the position of the third-level lymphatic structure in the spatial map;

[0123] The second determining unit 310 is used to determine the development state of the tertiary lymphatic structure according to the feature proportion and the position of the tertiary lymphatic structure in the spatial map.

[0124] Optionally, the device further comprises:

[0125] The second calculation unit 39 is further configured to calculate the feature proportion of each of the feature vectors in each of the target second principal components after the first determination unit determines the position of the third-level lymphatic structure in the spatial map;

[0126] The second determination unit 310 is further configured to determine the category of the lymphatic structure according to the feature proportion of each lymphatic structure, the position in the spatial map and a preset classification rule.

[0127] 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 not limited in this embodiment.

[0128] 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.

[0129] Figure 6 A schematic block diagram of an example electronic device 600 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.

[0130] like Figure 6 As shown, the device 400 includes a computing unit 401, which can perform various appropriate actions and processes according to a computer program stored in a ROM (Read-Only Memory) 402 or a computer program loaded from a storage unit 408 to a RAM (Random Access Memory) 403. In the RAM 403, various programs and data required for the operation of the device 400 can also be stored. The computing unit 401, the ROM 402, and the RAM 403 are connected to each other via a bus 404. An I / O (Input / Output) interface 405 is also connected to the bus 404.

[0131] A number of components in the device 400 are connected to the I / O interface 405, including: an input unit 406, such as a keyboard, a mouse, etc.; an output unit 407, such as various types of displays, speakers, etc.; a storage unit 408, such as a disk, an optical disk, etc.; and a communication unit 409, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 409 allows the device 400 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.

[0132] The computing unit 401 may be a variety of general and / or special processing components with processing and computing capabilities. Some examples of the computing unit 401 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, DSP (Digital Signal Processor), and any appropriate processor, controller, microcontroller, etc. The computing unit 401 performs the various methods and processes described above, such as a classification method for three-level lymphatic structures. For example, in some embodiments, the classification method for three-level lymphatic structures may be implemented as a computer software program, which is tangibly contained in a machine-readable medium, such as a storage unit 408. In some embodiments, part or all of the computer program may be loaded and / or installed on the device 400 via the ROM 402 and / or the communication unit 409. When the computer program is loaded into the RAM 403 and executed by the computing unit 401, one or more steps of the method described above may be performed. Alternatively, in other embodiments, the computing unit 401 may be configured to execute the aforementioned three-level lymphatic structure classification method in any other appropriate manner (eg, by means of firmware).

[0133] 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 dedicated 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.

[0134] 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.

[0135] 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 electrical connections based on one or more lines, portable computer disks, hard disks, RAM, ROM, EPROM (Electrically Programmable Read-Only-Memory) or flash memory, optical fiber, CD-ROM (Compact Disc Read-Only Memory), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.

[0136] 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 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).

[0137] 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.

[0138] 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.

[0139] 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.

[0140] 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.

[0141] 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 classifying tertiary lymphatic structures, characterized in that: include: Performing first principal component analysis on the relevant data information of the three-level lymphatic structure respectively, and screening the first principal components based on a preset variance contribution threshold, retaining the first principal components whose variance contribution values ​​are greater than or equal to the preset variance contribution threshold, wherein the relevant data information of the three-level lymphatic structure includes at least one of a cell composition ratio, a characteristic gene positive rate, a cell neighborhood ratio, a characteristic gene expression level, and a characteristic receptor ligand pair expression level; Calculating the gene set enrichment score of the tertiary lymphatic structure, performing a second principal component analysis based on the gene set enrichment score of the tertiary lymphatic structure and the screened first principal component, and determining a target second principal component; The position of the tertiary lymphatic structure in the spatial map is determined based on the target second principal component.

2. The method according to claim 1, characterized in that Before performing the first principal component analysis on the data information related to the three-level lymphatic structures respectively, the method includes: Performing center normalization processing on at least one of the cell composition ratio, characteristic gene positive rate and cell neighborhood ratio to eliminate order of magnitude differences; A cell smoothness factor is calculated, and data is normalized based on at least one of the expression level of a characteristic gene and the expression level of a characteristic receptor ligand pair of cells using the cell smoothness factor.

3. The method according to claim 1, characterized in that Before determining the position of the tertiary lymphatic structure in the spatial map based on the target second principal component, the method further includes: The variance contribution of each second principal component is calculated, and each second principal component is screened according to the variance contribution and a preset quantity threshold to determine a target second principal component.

4. The method according to claim 3, characterized in that Determining the target second principal component includes: The second principal components are ranked from large to small according to their variance contribution, and the top three second principal components are determined as the target second principal components; The determining the position of the tertiary lymphatic structure in the spatial map based on a preset number of second principal components comprises: According to the ranking order of the target second principal component, the horizontal coordinate, the vertical coordinate and the vertical coordinate of the tertiary lymphatic structure are determined in sequence to determine the position of the tertiary lymphatic structure in the spatial map.

5. The method according to any one of claims 1 to 4, characterized in that The second principal component includes at least two eigenvectors. After determining the position of the third-level lymphatic structure in the spatial map, the method further includes: Calculate the feature proportion of each of the eigenvectors in each of the second principal components of the target; The developmental state of the tertiary lymphatic structure is determined according to the feature proportion and the position of the tertiary lymphatic structure in the spatial map.

6. The method according to any one of claims 1 to 4, characterized in that After determining the position of the tertiary lymphatic structure in the spatial map, the method further includes: Calculate the feature proportion of each of the eigenvectors in each of the second principal components of the target; The category of the lymphatic structure is determined according to the feature proportion of each lymphatic structure, the position in the spatial map and the preset classification rules.

7. A classification device for three-level lymphatic structures, characterized in that: include: A first principal component analysis unit, used for performing first principal component analysis on the relevant data information of the three-level lymphatic structures respectively; A first screening unit is used to screen the first principal component based on a preset variance contribution threshold, and retain the first principal component whose variance contribution value is greater than or equal to the preset variance contribution threshold, wherein the relevant data information of the three-level lymphatic structure includes at least one of a cell composition ratio, a characteristic gene positive rate, a cell neighborhood ratio, a characteristic gene expression level, and a characteristic receptor ligand pair expression level; A calculation unit, used to calculate the gene set enrichment score of the tertiary lymphoid structure; A second principal component analysis unit is used to perform a second principal component analysis based on the gene set enrichment score of the tertiary lymphatic structure and the screened first principal component to determine a target second principal component; The first determination unit is used to determine the position of the tertiary lymphatic structure in the spatial map based on the target second principal component.

8. 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 6.

9. 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 1-6.

10. A computer program product, characterized in that The invention comprises a computer program which, when executed by a processor, implements the method according to any one of claims 1 to 6.

Images