Gene image data correction method, electronic equipment and medium

CN119032399APending Publication Date: 2024-11-26SHENZHEN HUADA SANJIAN QIFA TECHNOLOGY CO LTD
View PDF 4 Cites 0 Cited by

Patent Information

Application Number
CN202280095022.3
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2022-06-29
Publication Date
2024-11-26

AI Technical Summary

Technical Problem

There are errors in gene expression data in existing spatial transcriptome sequencing technology, which affects sequencing accuracy and efficiency.

Method used

By acquiring microscope images and gene images, cell segmentation and image registration are performed, the cell gene expression characteristics are corrected based on the probability distribution model, the probability value of the background gene expression characteristics is determined, and the correction results are output to correct the background gene expression characteristics.

Benefits of technology

It effectively reduces data errors, improves sequencing efficiency and accuracy, and provides reliable data for downstream analysis.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119032399A_ABST
    Figure CN119032399A_ABST
Patent Text Reader

Abstract

The invention discloses a gene image data correction method, electronic equipment and a medium. The method comprises the following steps: acquiring a gene image and a microscope image of a biological sample; performing cell segmentation on the microscope image to obtain a cell segmentation result; based on a cell segmentation result, respectively determining each gene expression feature of the gene image as a cell gene expression feature located in a cell and a background gene expression feature located outside the cell; fitting a probability distribution model for gene expression characteristics of each cell through signal values of spatial positions and gene expression characteristics; based on a probability distribution model, determining a probability value of target background gene expression features in a preset range of a target cell belonging to the target cell; and outputting a correction result according to the probability value so as to correct the background gene expression characteristics. According to the method, the electronic equipment and the medium, the correction accuracy and the correction efficiency of high-throughput space-time group sequencing data such as a Stereo-seq space transcriptome are improved, and the sequencing efficiency is improved.
Need to check novelty before this filing date? Find Prior Art

Description

Gene image data correction method, electronic device and medium Technical Field

[0001] The present application relates to the field of image processing technology, and in particular to a gene image data correction method, electronic device, and medium. Background Art

[0002] Stereo-seq (Spatio-Temporal Enhanced REsolution Omics-sequencing, spatiotemporal enhanced resolution omics sequencing) spatial transcriptome sequencing technology is a high-throughput spatiotemporal group sequencing technology. It captures mRNA in tissues through a chip positioned by mRNA (messenger ribonucleic acid), and restores it to its spatial position through spatial barcodes to achieve the detection of tissue spatial transcriptome information. During the experiment, frozen sections of fresh tissue are loaded onto the chip surface, then fixed and permeabilized, and finally reverse transcribed and amplified, which can achieve spatial positioning and detection of single cells and molecular information. However, there are errors in the gene expression data obtained in the current spatial transcriptome sequencing technology. This will affect the accuracy and efficiency of subsequent sequencing.

[0003] Summary of the Invention

[0004] The main purpose of this application is to provide a gene image data correction method, electronic device and medium to improve the above-mentioned defects in the prior art.

[0005] This application solves the above technical problems through the following technical solutions:

[0006] As a first aspect of the present application, a method for correcting gene image data is provided, comprising:

[0007] Obtain microscopic and genetic images of biological samples;

[0008] performing cell segmentation on the microscope image to obtain a cell segmentation result;

[0009] Based on the cell segmentation result, each gene expression feature of the gene image is determined as a cell gene expression feature located inside the cell and a background gene expression feature located outside the cell;

[0010] For each of the cell gene expression features, a probability distribution model is fitted based on the spatial position and the signal value of the gene expression feature;

[0011] Determining, based on the probability distribution model, a probability value of a target background gene expression feature located within a preset range of a target cell belonging to the target cell; and

[0012] Outputting a correction result according to the probability value to correct the background gene expression characteristics.

[0013] As an optional implementation, cell gene expression information is generated according to the correction result.

[0014] As an optional embodiment, the obtaining of microscope images and gene images includes:

[0015] Obtain ssDNA images and Stereo-seq spatial transcriptome data.

[0016] As an optional embodiment, before performing cell segmentation on the microscope image to obtain a cell segmentation result, the method further includes:

[0017] Perform image registration on the microscope image and the gene image.

[0018] As an optional implementation manner, the step of performing image registration on the microscope image and the gene image includes:

[0019] angularly rotating and / or scaling the microscope image according to the markings of the microscope image;

[0020] Calculating a preliminary offset by using the center of gravity of the microscope image and the gene image to perform a preliminary offset on the microscope image;

[0021] Performing offset correction on the microscope image by marking the microscope image and the gene image;

[0022] Image registration between the microscope image and the gene image is achieved based on the offset-corrected microscope image.

[0023] As an optional implementation manner, the step of performing offset correction on the microscope image by using the markers of the microscope image and the gene image includes:

[0024] Determining corresponding markers on the microscope image and the gene image respectively according to the calculated preliminary offset;

[0025] Determine the final offset using the determined mark;

[0026] The gene image is subjected to offset correction according to the determined final offset.

[0027] As an optional implementation manner, the step of determining the final offset using the determined mark includes:

[0028] Determine the offset by determining the mark;

[0029] Based on the calculated offset, traverse multiple adjacent periods and calculate the similarity within each period;

[0030] The offset correction is done by taking the period with the highest similarity from the similarities within multiple periods;

[0031] The offset of the corresponding marker is recalculated using the corrected offset as the final offset.

[0032] As an optional embodiment, performing cell segmentation on the microscope image to obtain a cell segmentation result includes:

[0033] performing cell segmentation on the microscope image to obtain a correspondence between spatial positions and cells;

[0034] A cell segmentation result is generated according to the correspondence between the spatial position and the cell.

[0035] As an optional embodiment, performing cell segmentation on the microscope image includes:

[0036] Cell segmentation was performed on the microscope images using a watershed algorithm.

[0037] As an optional implementation, the spatial position includes pixel coordinates.

[0038] As an optional embodiment, for each of the cell gene expression features, fitting a probability distribution model based on the spatial position and the signal value of the gene expression feature includes:

[0039] For each of the cell gene expression features, a Gaussian mixture model is fitted through the spatial position and the signal value of the gene expression feature.

[0040] As an optional embodiment, determining, based on the probability distribution model, a probability value of a target background gene expression feature within a preset range of a target cell belonging to the target cell includes:

[0041] Based on the Gaussian mixture model, a probability value of a target background gene expression feature within a preset pixel point region of a target cell belonging to the target cell is determined.

[0042] As an optional embodiment, outputting a correction result according to the probability value to correct the background gene expression characteristics includes:

[0043] It is determined whether the probability value is greater than or equal to a preset probability value. If so, the target background gene expression feature is used as the cell gene expression feature located in the target cell to correct the background gene expression feature.

[0044] As an optional implementation manner, the method further includes:

[0045] In response to the target background gene expression feature being simultaneously outside of at least two target cells, determining a probability value of belonging to each corresponding target cell;

[0046] The highest probability value is selected from the at least two determined probability values ​​as the probability value for outputting the correction result, and the target cell corresponding to the highest probability value is used as the correction object.

[0047] As a second aspect of the present application, an electronic device is provided, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the above-mentioned gene image data correction method when executing the computer program.

[0048] As a third aspect of the present application, a computer-readable medium is provided, on which computer instructions are stored. When the computer instructions are executed by a processor, the method for correcting genetic image data as described above is implemented.

[0049] Based on the content of this application, those skilled in the art can understand other aspects of the content of this application.

[0050] The positive progress of this application is:

[0051] The gene image data correction method, electronic device and medium provided in this application effectively correct cellular gene expression data based on spatial information and gene expression information through a probability distribution model, can accurately correct cellular expression information, provide reliable data for downstream analysis, and are compatible with local diffusion of mRNA in tissues, thereby improving the correction accuracy and efficiency of high-throughput spatiotemporal sequencing data such as Stereo-seq spatial transcriptomes, effectively reducing data errors and thereby improving sequencing efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0052] The features and advantages of the present invention will be better understood after reading the detailed description of the embodiments of the present invention in conjunction with the following drawings. In the drawings, components are not necessarily drawn to scale, and components with similar related properties or features may have the same or similar reference numerals.

[0053] FIG1 is a flow chart of a gene image data correction method according to an exemplary embodiment of the present application.

[0054] FIG2 is a schematic diagram of a scenario in which cell gene expression information is generated by registering gene images and microscope images.

[0055] FIG3 is a schematic diagram showing the correspondence between pixel coordinates and cells obtained by performing cell segmentation on a microscope image.

[0056] FIG4 is a schematic diagram showing the corresponding relationship between DNB (DNA nanoball) and cell membrane (cell mask).

[0057] FIG5 is a schematic diagram showing the correction results of the background DNB correction.

[0058] FIG6 is a schematic diagram showing different clustering results on mouse brain data before correction.

[0059] FIG. 7 is a schematic diagram showing different clustering results on mouse brain data after correction.

[0060] FIG8 is a schematic diagram showing the distribution of the total number of UMIs (unique molecular identifiers) per cell before and after correction.

[0061] FIG9 is a schematic diagram showing the distribution of the total number of genes per cell before and after correction.

[0062] FIG10 is a schematic diagram showing the clustering results before correction on the UMAP (dimensionality reduction algorithm) dimensionality reduction.

[0063] FIG11 is a schematic diagram showing the corrected clustering results on UMAP dimensionality reduction.

[0064] FIG12 is a schematic structural diagram of an electronic device for implementing a gene image data correction method according to another embodiment of the present application. DETAILED DESCRIPTION

[0065] The present application is further described below by way of examples, but the present application is not limited to the scope of the examples.

[0066] It should be noted that references in the specification to "one embodiment," "an alternative embodiment," "another embodiment," etc. indicate that the described embodiment may include a particular feature, structure, or characteristic, but every embodiment may not necessarily include that particular feature, structure, or characteristic. Moreover, such phrases do not necessarily refer to the same embodiment. In addition, when a particular feature, structure, or characteristic is described in conjunction with an embodiment, whether or not explicitly described, it is within the knowledge of those skilled in the relevant art to implement such feature, structure, or characteristic in conjunction with other embodiments.

[0067] In the description of the contents of this application, it should be understood that the terms "center", "lateral", "up", "down", "left", "right", "vertical", "horizontal", "top", "bottom", "inside", "outside", etc., indicating the orientation or positional relationship, are based on the orientation or positional relationship shown in the accompanying drawings, and are only for the convenience of describing the contents of this application and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as limiting the contents of this application. In addition, the terms "first" and "second" are used for descriptive purposes only, and cannot be understood as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Thus, the features defined as "first" and "second" may explicitly or implicitly include one or more of the features. In the description of the contents of this application, unless otherwise specified, "multiple" means two or more. In addition, the term "including" and any variations thereof are intended to cover non-exclusive inclusions.

[0068] In the description of the present application, it should be noted that, unless otherwise expressly specified or limited, the terms "installed," "connected," and "connected" should be understood in a broad sense. For example, they can refer to fixed connections, detachable connections, or integral connections; they can refer to mechanical connections or electrical connections; they can refer to direct connections or indirect connections through an intermediate medium; and they can refer to internal communication between two components. Those skilled in the art will understand the specific meanings of the above terms in the present application in specific contexts.

[0069] The terms used herein are intended only to describe specific embodiments and are not intended to limit exemplary embodiments. Unless the context clearly indicates otherwise, the singular forms "a", "an", "an item" used herein are also intended to include the plural. It should also be understood that the terms "comprise" and / or "include" used herein specify the presence of stated features, integers, steps, operations, units and / or components, and do not preclude the presence or addition of one or more other features, integers, steps, operations, units, components and / or combinations thereof.

[0070] In existing high-throughput sequencing analysis, stereo-seq spatial transcriptome data is aligned with ssDNA (single-stranded DNA) images, and cell segmentation is performed on the ssDNA images. A correspondence is established between pixel coordinates and cells. This correspondence is then used to convert the stereo-seq spatial transcriptome data into cellular gene expression data for downstream analysis.

[0071] However, since the cell size obtained based on ssDNA image segmentation is only the size of the cell nucleus, there is an error compared to the actual cell size. In addition, problems such as mRNA diffusion in sequencing experiments can easily lead to errors in experimental data, resulting in low data accuracy in the entire sequencing process, errors in the obtained gene expression data, and low sequencing efficiency.

[0072] To overcome the above-mentioned existing defects, this embodiment provides a gene image data correction method, including: obtaining a microscope image and a gene image of a biological sample; performing cell segmentation on the microscope image to obtain a cell segmentation result; based on the cell segmentation result, determining each gene expression feature of the gene image as a cellular gene expression feature located within the cell and a background gene expression feature located outside the cell; for each cellular gene expression feature, fitting a probability distribution model based on the spatial position and signal value of the gene expression feature; based on the probability distribution model, determining a probability value of a target background gene expression feature located within a preset range of a target cell belonging to the target cell; and outputting a correction result based on the probability value to correct the background gene expression feature.

[0073] In this embodiment, the gene image data correction method is preferably applied to the correction of Stereo-seq spatial transcriptome data, but its application scenario is not specifically limited and can be adjusted and selected accordingly according to actual needs or possible needs.

[0074] In this embodiment, based on spatial information and gene expression information, the cell gene expression data is effectively corrected through a probability distribution model, which can accurately correct the cell expression information and provide reliable data for downstream analysis, thereby effectively reducing data errors and improving sequencing efficiency.

[0075] Specifically, as an optional embodiment, as shown in FIG1 , the gene image data correction method provided in this embodiment mainly includes the following steps:

[0076] Step 101: Acquire a microscope image and a gene image of a biological sample.

[0077] In this step, the microscope image can be an image obtained by photographing the biological sample using a microscope, and can include spatial information of the biological sample. Prior to photographing, the cells of the biological sample or the DNA (single-stranded or double-stranded) therein can be stained, and then photographed using a microscope to obtain the microscope image of the biological sample. The biological sample can include tissues, cells, and / or cell suspensions. The genetic image can include both spatial information and genetic data of the biological sample.

[0078] Alternatively, the microscope image can be an image obtained by photographing a biological sample on a chip using a microscope, and the gene image is an image based on the same biological sample and generated using a gene matrix. There are regularly arranged sites on the chip for collecting biological sample genes, each site can capture the gene sequence of the biological sample, and the gene sequence or number of bases at the site can be obtained through gene sequencing. The gene sequence or number of bases at the site can then be used as the value of an element in the gene matrix, so that the elements of the gene matrix correspond to the sites of the chip (for example, one element corresponds to one site, and the elements of the first row and first column of the gene matrix correspond to the sites in the upper left corner of the chip). By analogy, the gene matrix can be obtained, and then the gene image can be drawn according to the gene matrix. Among them, the pixels in the gene image correspond to the elements of the gene matrix, and the pixel values ​​of the pixels correspond to the values ​​of the elements, so the gene image can include spatial information of the same biological sample. The chip can include spatiotemporal chips, sequencing chips, etc.

[0079] In this embodiment, the microscope image can be represented as an ssDNA image, but the type of microscope image is not limited and can be adjusted and selected according to actual needs. The gene image can be represented as stereo-seq spatial transcriptome data, spatial transcriptome data, or gene expression data, etc.

[0080] Step 102: perform image registration between the microscope image and the gene image.

[0081] It should be noted that the intermediate calculations of image registration are not necessarily processed on the microscope image, but can be processed on a temporary image of the microscope image, and the microscope image is processed after the final calculations are completed.

[0082] In this step, with reference to Figure 2, ssDNA image (microscope image) and Stereo-seq spatial transcriptome data (gene image) are image registered to generate cell gene expression information. In the process of image registration, according to the mark of the microscope image, the microscope image is rotated and / or scaled, and a preliminary offset is calculated by the center of gravity of the microscope image and the gene image to perform a preliminary offset on the microscope image. The microscope image is offset corrected by the mark of the microscope image and the gene image, and according to the microscope image after offset correction, image registration of the microscope image and the gene image is achieved. Wherein, the mark in the microscope image can be represented by a point (the point can be connected by a line), or by a line. The biological sample is on the chip, and the chip is provided with a regularly arranged mark, which is displayed in the microscope image obtained by shooting, and can also be displayed when drawing the gene image.

[0083] As a specific embodiment, the image registration process of the microscope image and the gene image includes the following steps:

[0084] Step 1021 : performing angular rotation and / or scaling on the microscope image according to the mark of the microscope image.

[0085] As an optional embodiment, the rotation angle and scaling ratio between the microscope image and the gene image are calculated based on the difference between the markers in the microscope image and the markers in the standard marker template or the gene image, so as to adjust the microscope image or the gene image;

[0086] As an optional embodiment, the rotation angle can also be directly turned to horizontal or vertical without relying on the difference. The rotation angle can be, but is not limited to, 0°, 90°, 180°, 270°, etc.

[0087] After the rotation angle and scaling ratio are adjusted, the microscope image matches the angle and size of the gene image.

[0088] Step 1022: Calculate a preliminary offset based on the center of gravity of the microscope image and the gene image to perform a preliminary offset on the microscope image.

[0089] Step 1023: performing offset correction on the microscope image by marking the microscope image and the gene image;

[0090] Step 1024: perform image registration between the microscope image and the gene image based on the offset-corrected microscope image.

[0091] As an optional embodiment, in step 1023, the step of performing offset correction on the microscope image by marking the microscope image and the gene image further includes the following steps:

[0092] Step 10231: Determine corresponding markers within a distance threshold on the microscope image and the gene image respectively using the preliminary offset calculated in step 1022;

[0093] The distance threshold can be set according to actual conditions.

[0094] Step 10232: Determine the precise offset using the determined mark;

[0095] For example, for each marker on the microscope image, all markers with the same index in the spatial transcriptome data are traversed and the Euclidean distance of the coordinates is calculated. The one with the smallest distance is considered to be the corresponding marker, and the minimum distance is a pending offset; outliers exceeding the distance threshold are excluded, and the median of all pending offsets is taken as the precise offset.

[0096] Regarding periods and indices, an image of a period on a chip (a sub-image of a complete chip) is represented by multiple regularly arranged periods. The spacing between the markers or lines within a period is a preset value and generally varies; however, the arrangement remains the same within each period. In other words, the arrangement within a period is irregular, but the intervals remain the same. Each period has different indices, such as (1, 1) to (9, 9); different periods can have the same index, such as (1, 1) in every period.

[0097] Step 10233: Since the marking cycles in a certain period, in order to eliminate periodic deviation, based on the offset determined in step 10232, traverse multiple adjacent periods and calculate the similarity within each period. From the similarities within multiple periods, the period with the highest similarity is selected to correct the offset.

[0098] After calculating the precise offset and moving the microscope image or its temporary image to the corresponding position based on the precise offset, the microscope image or its temporary image may still differ from the gene image by one or more periods. Therefore, we traverse the target period where the microscope image or its temporary image is moved to the target position and multiple periods adjacent to the target period, and calculate the similarity for each period.

[0099] Step 10234: recalculate the offset corresponding to the manual mark using the corrected offset as the final offset.

[0100] The specific implementation process of calculating the final offset in step 10234 is the same as that in steps 10231 and 10232, and will not be repeated here.

[0101] As an optional embodiment, in step 1021, the microscope image is rotated and / or scaled. If the microscope image is rectangular, it can also be rotated by angles such as 0°, 90°, 180°, and 270°, so the rotation angle of the microscope image must also be determined. Before step 1022, each period of each rotation angle is traversed, and steps 1022 and 1023 are executed. The rotation angle and target period (maximum similarity, minimum offset) are determined using the similarity, the corrected offset, or the first final offset. The second final offset is calculated based on the position determined by the rotation angle and the target period.

[0102] As an optional implementation, the offset may be calculated using Euclidean distance or pixel distance.

[0103] Step 103: Perform cell segmentation on the microscope image to obtain a cell segmentation result.

[0104] In this step, cell segmentation is performed on the microscope image to obtain the correspondence between spatial positions and cells, and a cell segmentation result is generated based on the correspondence between spatial positions and cells.

[0105] As a preferred embodiment, in this step, referring to FIG3 , the ssDNA image is segmented into cells using a watershed algorithm to obtain the correspondence between pixel coordinates and cells. FIG3 shows a schematic diagram of the correspondence between pixel coordinates and cells obtained by performing cell segmentation on the ssDNA image, wherein x and y are pixel coordinates, respectively, and label represents the cell identifier.

[0106] Step 104: Determine gene expression characteristics inside and outside the cell.

[0107] In this step, based on the cell segmentation result, each gene expression feature of the gene image is determined as a cellular gene expression feature located inside the cell and a background gene expression feature located outside the cell.

[0108] In this embodiment, the gene expression feature is DNB. Referring to Figure 4, Figure 4 shows a schematic diagram of the correspondence between DNBs and cell membranes, where x and y are the DNB coordinates, geneID and MIDCount represent the gene information, and label represents the cell identity. Each DNB in ​​the stereo-seq spatial transcriptome data is mapped to the cell information to which the DNB belongs. The remaining DNBs not in the cell are treated as background DNBs.

[0109] Step 105: Fit a probability distribution model using the spatial position and the signal value of the gene expression feature.

[0110] In this step, for each of the cell gene expression features, a probability distribution model is fitted through the spatial position and the signal value of the gene expression feature.

[0111] As a preferred implementation, in this embodiment, the probability distribution model can be a Gaussian mixture model, but different probability distribution models can be used, and in the judgment of the cells to which the background signal belongs, the Bayesian model can be used to judge the cells to which it belongs, and corresponding selection and adjustment can be made according to actual needs.

[0112] In this step, a Gaussian mixture model is fitted for the DNB in ​​each cell using the coordinates (x, y) and the DNB signal value.

[0113] Step 106: Calculate the probability value of the background gene expression feature based on the probability distribution model.

[0114] In this step, based on the probability distribution model, the probability value of the target background gene expression feature within a preset range of a target cell belonging to the cell is determined. The target cell can be all cells in the biological sample or a portion of the cells in the biological sample.

[0115] Specifically, as an optional implementation, in this step, taking the target cell as cell a as an example, for cell a, the Gaussian mixture model is used to calculate the probability value of the background DNB within the central range of 50x50 pixels of cell a belonging to cell a.

[0116] Step 107: Perform correction based on the probability value.

[0117] In this step, background gene expression characteristics are corrected based on the probability values.

[0118] Specifically, in this step, it is determined whether the probability value is greater than or equal to the preset probability value. If so, the target background gene expression feature is used as the cell gene expression feature located in the target cell to correct the background gene expression feature. If not, the target background gene expression feature continues to be used as the background gene expression feature.

[0119] Referring to FIG5 , FIG5 is a schematic diagram of correction results of background DNB correction. For background DNBs, those smaller than a preset probability value are regarded as background DNBs, and those greater than or equal to the preset probability value are regarded as cell DNBs.

[0120] In this embodiment, the preset probability value is not specifically limited and can be selected and adjusted accordingly according to actual needs.

[0121] As an optional embodiment, in this step, in response to the target background gene expression feature being simultaneously located outside at least two target cells, a probability value belonging to each corresponding target cell is determined respectively; the highest probability value is selected from the at least two determined probability values ​​as the probability value for outputting the correction result, and the target cell corresponding to the highest probability value is used as the cell to which the target background gene expression feature belongs.

[0122] Taking the target cells as cells a and b as an example, assuming that the background gene expression feature A is within the central range of 50x50 pixels of both cells a and b, the probability value of the background gene expression feature A belonging to cell a is calculated to be x1, and the probability value of the background gene expression feature A belonging to cell b is x2. If x1 is greater than x2, then the background gene expression feature A is determined to be the gene expression feature of cell a.

[0123] Step 108: Output the correction result.

[0124] In this step, the corrected genes are output.

[0125] As an optional embodiment, the method further includes: generating cell gene expression information according to the correction result.

[0126] In this example, this method was applied to Stereo-seq spatial transcriptome data correction. Figures 6 and 7 show the different clustering results for mouse brain data before and after correction, respectively. Referring to Figures 6 and 7, the four graphs in Figure 6 show the clustering results for the uncorrected mouse brain data, while the four graphs in Figure 7 show the clustering results after data correction using the method provided in this example. As can be clearly seen from Figures 6 and 7, the clustering results after correction show clearer biological outlines than before correction.

[0127] 8 , which is a schematic diagram showing the distribution of the total number of UMIs per cell before and after correction, clearly shows that the total number of cell UMIs after correction is greater than before correction.

[0128] Referring to FIG9 , which is a schematic diagram showing the distribution of the total number of genes in each cell before and after correction, it can be clearly seen that the number of genes in the cell after correction is greater than that before correction.

[0129] Referring to FIG10 and FIG11 , FIG10 and FIG11 respectively show schematic diagrams of clustering results before and after correction on UMAP dimensionality reduction, where different shapes represent different classes. It can be clearly seen that after correction, the distinction between classes is more obvious.

[0130] The gene image data correction method provided in this embodiment effectively corrects cellular gene expression data using a probability distribution model based on spatial and gene expression information. This method accurately corrects cellular expression information, provides reliable data for downstream analysis, and is compatible with local diffusion of mRNA within tissues. This improves the accuracy and efficiency of correction for high-throughput spatiotemporal sequencing data such as Stereo-seq spatial transcriptomes, effectively reducing data errors and thereby improving sequencing efficiency. This embodiment also allows for effective adjustment of thresholds and setting of correction ranges, thereby enhancing flexibility and applicability.

[0131] Figure 12 is a schematic diagram of the structure of an electronic device provided according to this embodiment. The electronic device includes a memory, a processor, and a computer program stored in the memory and executable by the processor. When the processor executes the program, it implements the genetic image data correction method described in the above embodiment. The electronic device 30 shown in Figure 12 is merely an example and should not limit the functionality or scope of use of the embodiments of this application.

[0132] As shown in FIG12 , the electronic device 30 may be a general-purpose computing device, such as a server device. Components of the electronic device 30 may include, but are not limited to, the at least one processor 31, the at least one memory 32, and a bus 33 connecting various system components (including the memory 32 and the processor 31).

[0133] The bus 33 includes a data bus, an address bus, and a control bus.

[0134] The memory 32 may include a volatile memory, such as a random access memory (RAM) 321 and / or a cache memory 322 , and may further include a read-only memory (ROM) 323 .

[0135] The memory 32 may also include a program / utility 325 having a set (at least one) of program modules 324, such program modules 324 including but not limited to: an operating system, one or more application programs, other program modules, and program data, each of which or some combination may include an implementation of a network environment.

[0136] The processor 31 executes computer programs stored in the memory 32 to perform various functional applications and data processing, such as the gene image data correction method in the above embodiment of the present application.

[0137] The electronic device 30 can also communicate with one or more external devices 34 (e.g., a keyboard, pointing device, etc.). This communication can occur via an input / output (I / O) interface 35. Furthermore, the model-generating device 30 can also communicate with one or more networks (e.g., a local area network (LAN), a wide area network (WAN), and / or a public network, such as the Internet) via a network adapter 36. As shown in FIG12 , the network adapter 36 communicates with other modules of the model-generating device 30 via a bus 33. It should be understood that, although not shown in the figures, other hardware and / or software modules can be used in conjunction with the model-generating device 30, including but not limited to microcode, device drivers, redundant processors, external disk drive arrays, RAID (RAID) systems, tape drives, and data backup storage systems.

[0138] It should be noted that although several units / modules or sub-units / modules of the electronic device are mentioned in the above detailed description, this division is merely exemplary and not mandatory. In fact, depending on the embodiment of the present application, the features and functions of two or more units / modules described above can be embodied in one unit / module. Conversely, the features and functions of one unit / module described above can be further divided and embodied by multiple units / modules.

[0139] This embodiment further provides a computer-readable storage medium having a computer program stored thereon. When the program is executed by a processor, the steps in the gene image data correction method in the above embodiment are implemented.

[0140] Specifically, the readable storage medium may include but is not limited to: a portable disk, a hard disk, a random access memory, a read-only memory, an erasable programmable read-only memory, an optical storage device, a magnetic storage device, or any suitable combination thereof.

[0141] In a possible implementation, the present application can also be implemented in the form of a program product, which includes program code. When the program product is executed on a terminal device, the program code is used to enable the terminal device to execute the steps in the gene image data correction method in the above embodiment.

[0142] The program code for executing the present application may be written in any combination of one or more programming languages, and the program code may be executed entirely on the user device, partially on the user device, as an independent software package, partially on the user device and partially on a remote device, or entirely on the remote device.

[0143] Although the above describes specific embodiments of the present application, those skilled in the art will understand that these are merely illustrative and that the scope of protection of the present application is defined by the appended claims. Those skilled in the art may make various changes or modifications to these embodiments without departing from the principles and essence of the present application, and such changes and modifications shall fall within the scope of protection of the present application.

Claims

1. A gene image data correction method, characterized in that: include: Obtain microscopic and genetic images of biological samples; performing cell segmentation on the microscope image to obtain a cell segmentation result; Based on the cell segmentation result, each gene expression feature of the gene image is determined as a cell gene expression feature located inside the cell and a background gene expression feature located outside the cell; For each of the cell gene expression features, a probability distribution model is fitted based on the spatial position and the signal value of the gene expression feature; Determining, based on the probability distribution model, a probability value of a target background gene expression feature located within a preset range of a target cell belonging to the target cell; and Outputting a correction result according to the probability value to correct the background gene expression characteristics.

2. The method according to claim 1, wherein Also includes: Generate cell gene expression information based on the correction results.

3. The method according to claim 1, wherein Before performing cell segmentation on the microscope image to obtain a cell segmentation result, the method further includes: Perform image registration on the microscope image and the gene image.

4. The method according to claim 3, wherein The step of performing image registration on the microscope image and the gene image comprises: angularly rotating and / or scaling the microscope image according to the markings of the microscope image; Calculating a preliminary offset by using the center of gravity of the microscope image and the gene image to perform a preliminary offset on the microscope image; Performing offset correction on the microscope image by marking the microscope image and the gene image; Image registration between the microscope image and the gene image is achieved based on the offset-corrected microscope image.

5. The method according to claim 4, wherein The step of performing offset correction on the microscope image by using the markers of the microscope image and the gene image comprises: Determining corresponding markers on the microscope image and the gene image respectively according to the preliminary offset; Determine the final offset using the determined mark; The gene image is subjected to offset correction according to the determined final offset.

6. The method according to claim 5, wherein The step of determining the final offset by using the determined mark includes: Determine the offset by determining the mark; Based on the calculated offset, traverse multiple adjacent periods and calculate the similarity within each period; The offset correction is done by taking the period with the highest similarity from the similarities within multiple periods; The offset of the corresponding marker is recalculated using the corrected offset as the final offset.

7. The method according to claim 1, wherein The performing cell segmentation on the microscope image to obtain a cell segmentation result comprises: performing cell segmentation on the microscope image to obtain a correspondence between spatial positions and cells; A cell segmentation result is generated according to the correspondence between the spatial position and the cell.

8. The method according to claim 7, wherein The step of performing cell segmentation on the microscope image comprises: Cell segmentation was performed on the microscope images using a watershed algorithm.

9. The method according to claim 1, wherein For each of the cell gene expression features, fitting a probability distribution model based on the spatial position and the signal value of the gene expression feature comprises: For each of the cell gene expression features, a Gaussian mixture model is fitted through the spatial position and the signal value of the gene expression feature.

10. The method according to claim 9, wherein Determining, based on the probability distribution model, a probability value of a target background gene expression feature within a preset range of a target cell belonging to the target cell includes: Based on the Gaussian mixture model, a probability value of a target background gene expression feature within a preset pixel point region of a target cell belonging to the target cell is determined.

11. The method according to claim 1, wherein Outputting a correction result according to the probability value to correct the background gene expression feature includes: It is determined whether the probability value is greater than or equal to a preset probability value. If so, the target background gene expression feature is used as the cell gene expression feature located in the target cell to correct the background gene expression feature.

12. The method according to claim 1, wherein The method further comprises: In response to the target background gene expression feature being simultaneously outside of at least two target cells, determining a probability value of belonging to each corresponding target cell; The highest probability value is selected from the at least two determined probability values ​​as the probability value for outputting the correction result, and the target cell corresponding to the highest probability value is used as the correction object.

13. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the computer program, the gene image data correction method according to any one of claims 1 to 12 is implemented.

14. A computer-readable medium having computer instructions stored thereon, characterized in that: When the computer instructions are executed by a processor, the gene image data correction method according to any one of claims 1 to 12 is implemented.

Citation Information

Patent Citations

  • Detection method suitable for high-throughput transcriptome spatial position information and application of detection method

    CN112592962A

  • Deep learning and alignment of spatially-resolved whole transcriptomes of single cells

    US20220068438A1

  • Method for cell image segmentation using scribble labels, recording medium and device for performing the method

    US20220101522A1

  • Image processing method and device

    WO2018068300A1