Marker gene screening method and device, equipment, storage medium and program product

Abstract

The invention relates to a marker gene screening method and device, computer equipment, a storage medium and a computer program product. The method comprises the following steps: counting the positive rate of each candidate gene in each cell type according to a to-be-analyzed single cell gene expression matrix and cell classification information; performing data conversion on the gene expression quantity in the single cell gene expression matrix and the positive rate of each candidate gene in each cell type to obtain a feature vector of each candidate gene in each cell type; calculating a gene score value of each candidate gene in each cell type on the basis of the feature vectors; and screening each candidate gene according to the gene score value to obtain the high-specificity marker gene of each cell type. By adopting the method, the marker gene with high specific expression can be screened out, and the accuracy of marker gene screening is improved.

Description

Technical Field

[0001] This application relates to the field of biotechnology, and in particular to a method, apparatus, device, storage medium, and program product for screening marker genes. Background Technology

[0002] Marker genes can annotate the cell types present in a sample, enabling further research on genes that are highly specifically expressed in some cells but not expressed or expressed at low levels in others. This is a widely used research method in cell studies. For unknown cell types, identifying their marker genes helps to quickly and accurately annotate their cell type; while for known cell types, similar analyses can be used to discover new marker genes, providing more molecular markers for subsequent research.

[0003] Traditional methods for identifying marker genes do not have high specificity in expression across different cell types, and their expression is evenly distributed across cell types. This results in low accuracy of the obtained marker genes for cell type identification, making it difficult to use these marker genes as specific genes for certain cell types (or populations) for downstream analysis. Summary of the Invention

[0004] Therefore, it is necessary to provide a marker gene screening method, device, equipment, storage medium, and program product to address the above-mentioned technical problems, which can screen for marker genes that are highly specifically expressed in cell types and improve the accuracy of marker gene screening.

[0005] In a first aspect, this application provides a marker gene screening method, the method comprising:

[0006] Based on the single-cell gene expression matrix and cell classification information to be analyzed, the positive rate of each candidate gene in each cell type is calculated.

[0007] The gene expression levels in the single-cell gene expression matrix and the positive rate of each candidate gene in each cell type are converted to obtain the feature vector of each candidate gene in each cell type.

[0008] Based on the feature vector, calculate the gene score value of each candidate gene in each cell type;

[0009] Each candidate gene is screened based on the gene score to obtain highly specific marker genes for each cell type.

[0010] In one embodiment, the method further includes:

[0011] The gene expression levels in the single-cell gene expression matrix are standardized to obtain a standard single-cell gene expression matrix.

[0012] Based on the gene expression levels in the standard single-cell gene expression matrix and the number of cells corresponding to each cell type, the average expression level of each candidate gene in each cell type is determined.

[0013] The data conversion of gene expression levels in the single-cell gene expression matrix and the positivity rate of each candidate gene in each cell type includes:

[0014] The average expression level and positive rate of each candidate gene in each cell type are converted into data.

[0015] In one embodiment, calculating the gene score value of each candidate gene in each cell type based on the feature vector includes:

[0016] Based on the target vector and the feature vector of each candidate gene in each cell type, the distance and angle are determined;

[0017] Based on the distance, the included angle, and the target parameter, calculate the gene score value of each candidate gene in each cell type.

[0018] In one embodiment, the data conversion of gene expression levels in the single-cell gene expression matrix and the positivity rate of each candidate gene in each cell type includes:

[0019] The average expression level of each candidate gene in each cell type is converted into a first expression level percentage and a first expression level residual.

[0020] The positive rate of each candidate gene in each cell type is converted into a second expression level percentage and a second expression level residual.

[0021] The step of using the conversion results of each of the cell types as the feature vectors of each of the candidate genes includes:

[0022] A feature vector for each candidate gene is constructed based on the first expression level percentage, the first expression level residual, the second expression level percentage, and the second expression level residual.

[0023] In one embodiment, the distance includes Euclidean distance; determining the distance and angle based on the target vector and the feature vector of each candidate gene in each cell type includes:

[0024] Calculate the Euclidean distance between the target vector and the feature vector of each candidate gene in each cell type;

[0025] Calculate the angle between the feature vector and the target vector.

[0026] In one embodiment, calculating the gene score value of each candidate gene in each cell type based on the distance, the included angle, and the target parameter includes:

[0027] Calculate the product between the included angle and the target parameter;

[0028] The sum of the distance and the product is used as the gene score of the candidate gene in each cell type.

[0029] Secondly, this application also provides a marker gene screening device, the device comprising:

[0030] The statistics module is used to calculate the positive rate of each candidate gene in each cell type based on the gene expression matrix of the single cell to be analyzed and the cell classification information.

[0031] The processing module is used to perform data conversion on the gene expression level in the single-cell gene expression matrix and the positive rate of each candidate gene in each cell type to obtain the feature vector of each candidate gene in each cell type.

[0032] The scoring module is used to calculate the gene score value of each candidate gene in each cell type based on the feature vector.

[0033] The screening module is used to screen each candidate gene according to the gene score to obtain highly specific marker genes for each cell type.

[0034] In one embodiment, the device further includes:

[0035] The standardization module is used to standardize the gene expression levels in the single-cell gene expression matrix to obtain a standard single-cell gene expression matrix.

[0036] The determination module is used to determine the average expression level of each candidate gene in each cell type based on the gene expression levels in the standard single-cell gene expression matrix and the number of cells corresponding to each cell type.

[0037] The processing module is also used to perform data conversion on the average expression level and positive rate of each candidate gene in each cell type.

[0038] In one embodiment, the scoring module is further configured to determine the distance and angle based on the target vector and the feature vector of each candidate gene in each cell type; and to calculate the gene score value of each candidate gene in each cell type based on the distance, the angle and the target parameter.

[0039] In one embodiment, the processing module is further configured to convert the average expression level of each candidate gene in each cell type into a first expression level percentage and a first expression level residual; convert the positive rate of each candidate gene in each cell type into a second expression level percentage and a second expression level residual; and construct a feature vector of each candidate gene based on the first expression level percentage, the first expression level residual, the second expression level percentage, and the second expression level residual.

[0040] In one embodiment, the distance includes Euclidean distance;

[0041] The scoring module is also used to calculate the Euclidean distance between the target vector and the feature vector of each candidate gene in each cell type; and to calculate the angle between the feature vector and the target vector.

[0042] In one embodiment, the scoring module is further configured to calculate the product between the included angle and the target parameter; and to use the sum of the distance and the product as the gene score of the candidate gene in each cell type.

[0043] Thirdly, this application also provides a computer device, which includes a memory and a processor. The memory stores a computer program, and the processor executes the computer program to implement the steps of the marker gene screening method.

[0044] Fourthly, this application also provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of the marker gene screening method.

[0045] Fifthly, this application also provides a computer program product, which includes a computer program that, when executed by a processor, implements the steps of the marker gene screening method.

[0046] The aforementioned marker gene screening method, apparatus, computer equipment, storage medium, and computer program product first calculate the positive rate of each candidate gene in each cell type based on the gene expression matrix to be analyzed and cell classification information. Then, by converting the gene expression level in the single-cell gene expression matrix and the positive rate of each candidate gene in each cell type, a feature vector of each candidate gene in each cell type is obtained. The candidate gene is then scored using this feature vector, and marker genes with more specific expression are screened from the candidate genes based on the gene score value. This improves the accuracy of marker gene screening and is beneficial for using these genes as characteristic genes of certain cell types for downstream analysis. Attached Figure Description

[0047] Figure 1 This is a diagram illustrating the application environment of a marker gene screening method in one embodiment;

[0048] Figure 2 This is a flowchart illustrating a marker gene screening method in one embodiment;

[0049] Figure 3 This is a schematic diagram illustrating the distribution of marker genes in one embodiment;

[0050] Figure 4 This is a schematic diagram of the distribution of nTPM values ​​in the HPA database in one embodiment;

[0051] Figure 5 This is a structural block diagram of a marker gene screening device in one embodiment;

[0052] Figure 6 This is a structural block diagram of the marker gene screening device in another embodiment;

[0053] Figure 7 This is an internal structural diagram of a computer device in one embodiment. Detailed Implementation

[0054] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application.

[0055] It should be noted that in the following description, the terms "first and second" are used only to distinguish similar objects and do not represent a specific ordering of objects. It is understood that "first and second" can be interchanged in a specific order or sequence where permitted, so that the embodiments of this application described herein can be implemented in an order other than that illustrated or described herein.

[0056] The marker gene screening method provided in this application can be applied to, for example... Figure 1 In the application environment shown, this environment may include terminal 102 and server 104. In other application environments, it may only include terminal 102 or server 104. Terminal 102 communicates with server 104 via a network. A data storage system can store the data that server 104 needs to process. The data storage system can be integrated on server 104 or located in the cloud or on another network server. When performing marker gene screening, screening can be performed using terminal 102 or server 104.

[0057] The terminal 102 can be a smartphone, tablet, laptop, or desktop computer, or it can be a testing device used in the medical or medical research fields.

[0058] Server 104 can be a standalone physical server or a service node in a blockchain system. These service nodes form a peer-to-peer (P2P) network, where the P2P protocol is an application layer protocol running on top of the Transmission Control Protocol (TCP). Furthermore, server 104 can also be a server cluster composed of multiple physical servers, and can be a cloud server providing basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communication, middleware services, domain name services, security services, content delivery networks (CDNs), and big data and artificial intelligence platforms.

[0059] In one embodiment, such as Figure 2 As shown, a marker gene screening method is provided, which can be performed by... Figure 1 The method is executed by a server or terminal, or by a server and terminal working together. Figure 1 Taking the terminal execution in the example, the following steps are included:

[0060] S202, based on the single-cell gene expression matrix and cell classification information to be analyzed, calculate the positive rate of each candidate gene in each cell type.

[0061] The term "cell type" can refer to a specific type of cell, including: cytotrophoblasts (CTBs), endothelial cells (ECs), extravillous trophoblasts (EVTs), fibroblasts (FBCs), Hofbauer cells (HBCs), mixed immune cells (MICs), smooth muscle cells (SMCs), and syncytiotrophoblasts (SCTs), among others. In this application, "cell type" can also refer more broadly to the collection of all cells within that type.

[0062] Candidate genes can include at least two marker genes to be selected. Marker genes can be the result of labeling genes in a cell, such as labeling a gene in a cell as a marker gene. Then the marker gene is a gene. .

[0063] Elements in a single-cell gene expression matrix can include the gene expression level in each cell. Cell classification information can be the category information of each cell to be analyzed, such as the cell type.

[0064] Gene expression levels in a single-cell gene expression matrix can represent the content of a specific gene product (such as mRNA, protein, or other substances) within an organism. Correspondingly, the average expression level refers to the average expression level of a candidate gene across different cell types.

[0065] The positivity rate can be the proportion of a gene appearing in each cell type (e.g., the gene appearing in all cells of each cell type). For example, a gene... The positive rate in all cell types was ,in, , used to represent the i-th gene among N genes; , used to represent the j-th cell type among K cell types; For genes In cell type The percentage of cells with gene expression levels greater than 0. For example, if there are 100 smooth muscle cells, the gene expression level is... If it appears in 98 of the smooth muscle cells, the positive rate is 98%.

[0066] In one embodiment, the terminal can determine the cell type of each cell to be analyzed based on cell classification information, divide cells belonging to the same cell type into the same group, obtain a group of cells of the same cell type, and then calculate the gene expression level of each cell in each cell type based on the single-cell gene expression matrix, and calculate the positive rate of candidate genes in each cell type based on cell classification information.

[0067] S204 transforms the gene expression levels and the positive rate of each candidate gene in each cell type in the single-cell gene expression matrix to obtain the feature vector of each candidate gene in each cell type.

[0068] In one embodiment, the gene expression levels in the single-cell gene expression matrix and the positive rate of each candidate gene in each cell type are converted into data, and the conversion results of each cell type are used as feature point information of each cell type. Then, the feature vector of each candidate gene can be determined based on the origin and the feature point information.

[0069] The feature point information can be the result of data transformation of gene expression levels and positive rates, or it can be a coordinate point in a Euclidean coordinate system. It should be noted that each candidate gene corresponds to one feature point within each cell type.

[0070] In one embodiment, the terminal can first convert the average expression level of each candidate gene in each cell type into a first expression level percentage and a first expression level residual; convert the positive rate of each candidate gene in each cell type into a second expression level percentage and a second expression level residual; and then construct a feature vector for each candidate gene based on the first expression level percentage, the first expression level residual, the second expression level percentage, and the second expression level residual.

[0071] In another embodiment, the terminal may first convert the gene expression levels of the single-cell gene expression matrix into average expression levels, and then perform data conversion on the average expression levels and positive rates of each cell type. Specifically, the data conversion process for average expression levels and positive rates may include: the terminal converting the average expression level of each candidate gene in each cell type into a first expression level percentage and a first expression level residual; converting the positive rate of each candidate gene in each cell type into a second expression level percentage and a second expression level residual; and finally, constructing a feature vector for each candidate gene based on the first expression level percentage, the first expression level residual, the second expression level percentage, and the second expression level residual.

[0072] Here, average expression level can be the average expression level of a gene across different cell types. For example, gene... Average expression levels in N cell types ,in, , used to represent the i-th gene among N genes, , used to represent the i-th cell type among K cell types, For genes In cell type The average expression level in [the sample / sample].

[0073] Furthermore, the conversion of gene expression levels can include the following process: the terminal standardizes the gene expression levels in the single-cell gene expression matrix to obtain a standard single-cell gene expression matrix; based on the gene expression levels in the standard single-cell gene expression matrix and the number of cells corresponding to each cell type, the average expression level of each candidate gene in each cell type is determined. After obtaining the average expression level in each cell type, the terminal can perform data conversion on the average expression level and positive rate in each cell type.

[0074] The standardization process for single-cell gene expression matrices can include: the terminal determining a first difference based on the maximum and minimum expression levels in the single-cell gene expression matrix; for each gene expression level in the single-cell gene expression matrix, determining the difference between each gene expression level and the minimum expression level to obtain a second difference corresponding to each gene expression level; and based on the first difference and the second difference corresponding to each gene expression level, determining the standard gene expression levels corresponding to each gene expression level sequentially to obtain a standard single-cell gene expression matrix composed of the standard gene expression levels corresponding to each gene expression level.

[0075] As an example, to better illustrate the standardization, gene expression level averaging, and data transformation processes described above, a specific example is provided below:

[0076] First, based on the maximum value in the single-cell gene expression matrix and minimum value Standardizing the expression matrix involves representing the gene expression levels in cells. Convert to ;in, , represents the m-th cell in M ​​cells. , representing the nth gene among N marker genes; the conversion formula is: Then, calculate the genes. In cell type Average expression level in all cells , Cell type The total number of cells contained, where l represents the cell type. The lth cell in and In this context, 'i' represents the i-th gene among N marker genes;

[0077] Finally, the genes In cell type Average expression level in and positive rate Convert them to residuals and percentages respectively, and then average expression levels. The corresponding residuals and percentages, and the positive rate By combining the corresponding residuals and proportions, we obtain ,in:

[0078]

[0079]

[0080]

[0081]

[0082] S206 calculates the gene score of each candidate gene in each cell type based on the feature vector.

[0083] In one embodiment, the terminal can calculate the gene score of each candidate gene in each cell type based on the target vector and the feature vector of each candidate gene in each cell type, and based on the distance, angle and target parameters.

[0084] The target vector can be a vector formed between a pre-set reference point (such as 1, 1, 1, 1) and the origin.

[0085] The target parameter can be a pre-set parameter, such as 0.1 by default; in addition, the target parameter can be dynamically adjusted according to the actual situation.

[0086] Gene scores can be scores for marker genes belonging to the same cell type, with each cell type having a corresponding score for its marker genes.

[0087] This distance can include Euclidean distance. Therefore, the calculation of distance and angle can specifically include: the terminal can first calculate the Euclidean distance between the target vector and the feature vector of each candidate gene in each cell type; and then calculate the angle between the feature vector and the target vector.

[0088] In one embodiment, the distance includes Euclidean distance, so the terminal can also calculate the Euclidean distance between the target vector and the feature vector of each candidate gene in each cell type, and then calculate the angle between the feature vector and the target vector. For example, first calculate the candidate gene... The Euclidean distance between the feature vector and the target vector in cell type j is calculated, and then the angle between the feature vector and the target vector is calculated.

[0089] In one embodiment, after calculating the included angle and distance, the terminal can determine the product between the included angle and the target parameter; the sum of the distance and the product is used as the gene score value of the candidate gene score.

[0090] For example, calculating genes based on a scoring formula. In cell type The score is calculated using the following formula:

[0091]

[0092] in, and It can be feature vectors and target vectors, or location information and target location information. express and The Euclidean distance between them , It can be the angle between the feature vector and the target vector, or it can be the angle from the origin to the target vector. and The angle between them This is an adjustable target parameter, with a default value of 0.1.

[0093] S208 screens each candidate gene based on gene score to obtain highly specific marker genes for each cell type.

[0094] In one embodiment, the terminal can sort the candidate genes belonging to the same cell type according to the score of the marker genes belonging to the same cell type, and then select multiple marker genes that meet the preset conditions to obtain the highly specific marker genes for that cell type.

[0095] For each cell type, the marker genes can be sorted and selected using the above scheme to obtain all highly specific marker genes.

[0096] The above sorting can be in ascending or descending order. If it is in ascending order, the corresponding preset condition can be multiple marker genes arranged at the beginning (such as the first 5 marker genes); if it is in descending order, the corresponding preset condition can be multiple marker genes arranged at the end (such as the last 5 marker genes).

[0097] In one embodiment, after obtaining highly specific marker genes for each cell type, the terminal can generate a corresponding dotplot for display. For example, after selecting the five marker genes with the lowest scores for each cell type, a dotplot can be generated for display.

[0098] In the above embodiments, firstly, based on the gene expression matrix to be analyzed and cell classification information, the positive rate of each candidate gene in each cell type is calculated. Then, the gene expression level in the single-cell gene expression matrix and the positive rate of each candidate gene in each cell type are converted to obtain the feature vector of each candidate gene in each cell type. The candidate gene is then scored using the feature vector. Based on the gene score, marker genes with more specific expression are screened from the candidate genes, which improves the accuracy of marker gene screening and is beneficial for using these genes as characteristic genes of certain cell types for downstream analysis.

[0099] As an example, to better understand the technical solution of this application, an example is described below:

[0100] First, human placental embryo data from E-MTAB-6701 were downloaded from the ArrayExpress database, containing the expression levels of 20,072 genes in 25,615 cells. These cells were annotated into nine cell types: CTBs, ECs, EVTs, FBCs, HBCs, MICs, SMCs, SCTs, and t-cells.

[0101] Next, each of the 20,072 genes was scored. The specific scoring process is as follows:

[0102] 1) Based on the gene expression matrix and cell classification information, statistically analyze the genes. The positive rate;

[0103] Among them, genes The positive rate in all cell types was , , For genes In cell type The percentage of cells with expression levels greater than 0;

[0104] 2) Calculate genes Average expression level across all cell types , The specific calculation process is as follows:

[0105] Based on the maximum value of the expression matrix and minimum value The expression matrix is ​​standardized to obtain the standard expression matrix, which represents the expression levels of genes in cells. Convert to ;in, , represents the m-th cell in M ​​cells. , representing the nth gene among N marker genes; the conversion formula is: .

[0106] Calculate genes using standard expression matrix In cell type Average expression level in in Cell type The total number of cells contained;

[0107] 3) Genes In cell type Average expression level in and positive rate Convert them into residuals and proportions respectively, and obtain ,in:

[0108]

[0109]

[0110]

[0111]

[0112] Then, calculate the genes. In cell type Scores ,in It can represent and The Euclidean distance between them , It can be from the origin to and The angle between them This is an adjustable target parameter, with a default value of 0.1.

[0113] Finally, the five marker genes with the lowest scores were selected from the marker genes corresponding to each cell type, and the selected marker genes were displayed using a Dotplot.

[0114] like Figure 3 As shown, the vertical axis (Y-axis) represents cell classification, the horizontal axis (X-axis) represents gene names, the size of the circles indicates the proportion of cells, and the intensity of the color indicates the level of gene expression. Figure 3 It can be seen that the marker genes screened in this application show higher specificity in terms of gene expression level and the number of cells expressing the gene.

[0115] Based on the nTPM values ​​of each gene in the corresponding cell type from the database - The Human Protein Atlas (https: / / www.proteinatlas.org / ), the distribution of nTPM values ​​of the top 10 marker genes in the cell type EVTs was statistically analyzed. Figure 4 As shown, the nTPM values ​​of this application are higher, indicating that the marker genes identified in this application are more reliable. Among them, Figure 4 The Y-axis represents the percentage of nTPM values, and the X-axis represents different marker gene methods, where conep is the method used in this application.

[0116] It should be understood that although the steps in the flowcharts of the embodiments described above are shown sequentially according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some steps in the flowcharts of the embodiments described above may include multiple steps or multiple stages. These steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these steps or stages is not necessarily sequential, but can be performed alternately or in turn with other steps or at least some of the steps or stages of other steps.

[0117] Based on the same inventive concept, this application also provides a marker gene screening device for implementing the marker gene screening method described above. The solution provided by this device is similar to the solution described in the above method; therefore, the specific limitations in one or more of the marker gene screening device embodiments provided below can be found in the limitations of the marker gene screening method described above, and will not be repeated here.

[0118] In one embodiment, such as Figure 5 As shown, a marker gene screening device is provided, including: a statistical module 502, a processing module 504, a scoring module 506, and a screening module 508, wherein:

[0119] The statistics module 502 is used to calculate the positive rate of each candidate gene in each cell type based on the gene expression matrix of the single cell to be analyzed and the cell classification information.

[0120] The processing module 504 is used to perform data conversion on the gene expression level in the single-cell gene expression matrix and the positive rate of each candidate gene in each cell type to obtain the feature vector of each candidate gene in each cell type.

[0121] The scoring module 506 is used to calculate the gene score value of each candidate gene in each cell type based on the feature vector.

[0122] The screening module 508 is used to screen each candidate gene according to the gene score to obtain highly specific marker genes for each cell type.

[0123] In one embodiment, such as Figure 6 As shown, the device also includes:

[0124] Standardization module 510 is used to standardize the gene expression levels in the single-cell gene expression matrix to obtain a standard single-cell gene expression matrix;

[0125] The determination module 512 is also used to determine the average expression level of each candidate gene in each cell type based on the gene expression level in the standard single-cell gene expression matrix and the number of cells corresponding to each cell type.

[0126] The processing module 504 is also used to perform data conversion on the average expression level and positive rate of each candidate gene in each cell type.

[0127] In one embodiment, the scoring module 506 is further configured to determine the distance and angle based on the target vector and the feature vector of each candidate gene in each cell type; and to calculate the gene score value of each candidate gene in each cell type based on the distance, angle and target parameters.

[0128] In one embodiment, the processing module 504 is further configured to convert the average expression level of each candidate gene in each cell type into a first expression level percentage and a first expression level residual; convert the positive rate of each candidate gene in each cell type into a second expression level percentage and a second expression level residual; and construct a feature vector of each candidate gene based on the first expression level percentage, the first expression level residual, the second expression level percentage, and the second expression level residual.

[0129] In one embodiment, the distance includes Euclidean distance;

[0130] The determination module 512 is also used to calculate the Euclidean distance between the target vector and the feature vector of each candidate gene in each cell type; and to calculate the angle between the feature vector and the target vector.

[0131] In one embodiment, the scoring module 506 is further configured to calculate the product between the included angle and the target parameter; and to use the sum of the distance and the product as the gene score of the candidate gene in each cell type.

[0132] In the above embodiments, firstly, based on the gene expression matrix to be analyzed and cell classification information, the positive rate of each candidate gene in each cell type is calculated. Then, the gene expression level in the single-cell gene expression matrix and the positive rate of each candidate gene in each cell type are converted to obtain the feature vector of each candidate gene in each cell type. The candidate gene is then scored using the feature vector. Based on the gene score, marker genes with more specific expression are screened from the candidate genes, which improves the accuracy of marker gene screening and is beneficial for using these genes as characteristic genes of certain cell types for downstream analysis.

[0133] Each module in the aforementioned marker gene screening device can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in or independent of the processor in a computer device, or stored in the memory of a computer device as software, so that the processor can call and execute the operations corresponding to each module.

[0134] In one embodiment, a computer device is provided, which may be a terminal, and its internal structure diagram may be as follows: Figure 7 As shown, the computer device includes a processor, memory, input / output interface, communication interface, display unit, and input device. The processor, memory, and input / output interface are connected via a system bus, and the communication interface, display unit, and input device are also connected to the system bus via the input / output interface. The processor provides computational and control capabilities. The memory includes a non-volatile storage medium and internal memory. The non-volatile storage medium stores the operating system and computer programs. The internal memory provides an environment for the operation of the operating system and computer programs stored in the non-volatile storage medium. The input / output interface is used for exchanging information between the processor and external devices. The communication interface is used for wired or wireless communication with external terminals; wireless communication can be achieved through Wi-Fi, mobile cellular networks, NFC (Near Field Communication), or other technologies. When the computer program is executed by the processor, it implements a marker gene screening method. The display unit of the computer device is used to form a visually visible image. It can be a display screen, a projection device, or a virtual reality imaging device. The display screen can be an LCD screen or an e-ink screen. The input device of the computer device can be a touch layer covering the display screen, or buttons, trackballs, or touchpads set on the casing of the computer device, or external keyboards, touchpads, or mice, etc.

[0135] In another embodiment, a computer device is provided, which may also be a server. The computer device includes a processor, memory, input / output interfaces (I / O), and a communication interface. The processor, memory, and I / O interfaces are connected via a system bus, and the communication interface is connected to the system bus via the I / O interfaces. The processor of the computer device provides computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and internal memory. The non-volatile storage medium stores an operating system, computer programs, and a database. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage medium. The database of the computer device can be used to store human placental embryo data. The I / O interfaces of the computer device are used for exchanging information between the processor and external devices. The communication interface of the computer device is used for communicating with external terminals via a network connection. When the computer program is executed by the processor, it implements a marker gene screening method.

[0136] Those skilled in the art will understand that Figure 7 The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the computer device to which the present application is applied. Specific computer devices may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0137] In one embodiment, a computer device is provided, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the steps of the marker gene screening method described above.

[0138] In one embodiment, a computer-readable storage medium is provided having a computer program stored thereon, which, when executed by a processor, implements the steps of the marker gene screening method described above.

[0139] In one embodiment, a computer program product is provided, including a computer program that, when executed by a processor, implements the steps of the marker gene screening method described above.

[0140] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, data stored, data displayed, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of related data must comply with the relevant laws, regulations and standards of the relevant countries and regions.

[0141] Those skilled in the art will understand that all or part of the processes in the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium. When executed, the computer program can include the processes of the embodiments described above. Any references to memory, databases, or other media used in the embodiments provided in this application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM). The databases involved in the embodiments provided in this application may include at least one type of relational database and non-relational database. Non-relational databases may include, but are not limited to, blockchain-based distributed databases. The processors involved in the embodiments provided in this application may be general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic devices, quantum computing-based data processing logic devices, etc., and are not limited to these.

[0142] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0143] The embodiments described above are merely illustrative of several implementation methods of this application, and while the descriptions are specific and detailed, they should not be construed as limiting the scope of this patent application. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the protection scope of this application. Therefore, the protection scope of this application should be determined by the appended claims.

Claims

1. A marker gene screening method, characterized in that, The method includes: Based on the single-cell gene expression matrix and cell classification information to be analyzed, the positive rate of each candidate gene in each cell type is calculated. The gene expression levels in the single-cell gene expression matrix and the positive rate of each candidate gene in each cell type are converted to obtain the feature vector of each candidate gene in each cell type. Based on the feature vector, calculate the gene score value of each candidate gene in each cell type; Each candidate gene is screened based on the gene score to obtain highly specific marker genes for each cell type.

2. The method according to claim 1, characterized in that, The method further includes: The gene expression levels in the single-cell gene expression matrix are standardized to obtain a standard single-cell gene expression matrix. Based on the gene expression levels in the standard single-cell gene expression matrix and the number of cells corresponding to each cell type, the average expression level of each candidate gene in each cell type is determined. The data conversion of gene expression levels in the single-cell gene expression matrix and the positivity rate of each candidate gene in each cell type includes: The average expression level and positive rate of each candidate gene in each cell type are converted into data.

3. The method according to claim 1, characterized in that, The calculation of the gene score value of each candidate gene in each cell type based on the feature vector includes: Based on the target vector and the feature vector of each candidate gene in each cell type, the distance and angle are determined; Based on the distance, the included angle, and the target parameter, calculate the gene score value of each candidate gene in each cell type.

4. The method according to claim 2, characterized in that, The data transformation of the average expression level and positive rate of each candidate gene in each cell type includes: The average expression level of each candidate gene in each of the cell types is converted into a first expression level percentage and a first expression level residual; The positive rate of each candidate gene in each cell type is converted into a second expression level percentage and a second expression level residual. The step of using the conversion results of each of the cell types as the feature vectors of each of the candidate genes includes: A feature vector for each candidate gene is constructed based on the first expression level percentage, the first expression level residual, the second expression level percentage, and the second expression level residual.

5. The method according to claim 3, characterized in that, The distance includes Euclidean distance; determining the distance and angle based on the target vector and the feature vector of each candidate gene in each cell type includes: Calculate the Euclidean distance between the target vector and the feature vector of each candidate gene in each cell type; Calculate the angle between the feature vector and the target vector.

6. The method according to claim 3, characterized in that, The calculation of the gene score value for each candidate gene in each cell type based on the distance, the included angle, and the target parameter includes: Calculate the product between the included angle and the target parameter; The sum of the distance and the product is used as the gene score of the candidate gene in each cell type.

7. A marker gene screening device, characterized in that, The device includes: The statistics module is used to calculate the positive rate of each candidate gene in each cell type based on the gene expression matrix of the single cell to be analyzed and the cell classification information. The processing module is used to perform data conversion on the gene expression level in the single-cell gene expression matrix and the positive rate of each candidate gene in each cell type to obtain the feature vector of each candidate gene in each cell type. The scoring module is used to calculate the gene score value of each candidate gene in each cell type based on the feature vector. The screening module is used to screen each candidate gene according to the gene score to obtain highly specific marker genes for each cell type.

8. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that, When the processor executes the computer program, it implements the steps of the method according to any one of claims 1 to 6.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 6.

10. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 6.

Images