Method, device, equipment and medium for automatic analysis of protein immunoblotting images

Abstract

This invention provides an automated method, apparatus, device, and medium for analyzing protein immunoblot images, relating to the field of image understanding technology. The method includes: acquiring a protein immunoblot image to be analyzed; converting the protein immunoblot image to be analyzed into a grayscale image and performing background noise reduction processing on the grayscale image; generating a grayscale curve based on the grayscale values ​​of pixels in the grayscale image; identifying valleys in the grayscale curve to obtain each valley point; adding segmentation lines to the grayscale image based on the position of the valley points in the grayscale curve to obtain the swimlane division result of the protein immunoblot image to be analyzed; and determining the grayscale value data of each swimlane based on the swimlane division result. This invention can achieve automated swimlane division and grayscale value extraction of protein immunoblot images, improving the analysis efficiency of protein immunoblot images.

Description

Technical Field

[0001] This invention relates to the field of image understanding technology, and in particular to methods, apparatus, equipment and media for automated analysis of protein immunoblot images. Background Technology

[0002] Western blotting (WB) is a commonly used molecular biology experiment in basic research. It is used to detect the presence and relative abundance of specific proteins in a sample. After a Western blotting experiment, an immunoblotting image is generated. Grayscale analysis of this image allows for the determination of the presence and relative abundance of specific proteins in the sample.

[0003] A single Western blot image displays the relative abundance of a specific protein in different samples. Since different lanes in a Western blot image correspond to different samples, lane division is a crucial step in Western blot image analysis. By dividing the image into lanes, relative quantification of specific proteins in different samples can be performed. Currently, lane division is often done manually by visually observing the Western blot image, which is inefficient. Summary of the Invention

[0004] This invention provides an automated method, apparatus, device, and medium for analyzing protein immunoblot images, which addresses the shortcomings of low lane division efficiency in existing technologies and improves the analysis efficiency of protein immunoblot images.

[0005] This invention provides an automated method for analyzing protein immunoblot images, comprising:

[0006] Acquire an immunoblot image of the protein to be analyzed, convert the immunoblot image of the protein to be analyzed into a grayscale image, and perform background noise reduction processing on the grayscale image;

[0007] A grayscale curve is generated based on the grayscale values ​​of the pixels in the grayscale image;

[0008] Valley identification is performed on the grayscale curve to obtain each valley point in the grayscale curve;

[0009] Based on the position of the trough point in the grayscale curve, a dividing line is added to the grayscale image to obtain the lane division result of the immunoblot image of the protein to be analyzed, and the grayscale value data corresponding to each lane is determined based on the lane division result.

[0010] According to the automatic analysis method for protein immunoblotting images provided by the present invention, the step of identifying the valleys of the grayscale curve to obtain each valley point in the grayscale curve includes:

[0011] Based on the points corresponding to each local minimum value in the grayscale curve, a preliminary valley point identification result is obtained, which includes multiple valley candidate points.

[0012] The candidate valley points are selected based on the constraints to obtain the valley points;

[0013] The constraints include a first constraint, which is used to constrain the uniformity of the lateral distance between two adjacent points in the selected trough points.

[0014] According to the automatic analysis method for protein immunoblotting images provided by the present invention, the constraint conditions further include a second constraint condition, which is used to constrain the significance of the peaks between two adjacent points in the selected trough points.

[0015] According to the automatic analysis method for protein immunoblotting images provided by the present invention, the constraint conditions further include a third constraint condition, which is used to constrain the stability of the longitudinal coordinates between two adjacent points in the selected trough points.

[0016] According to the present invention, an automatic analysis method for protein immunoblotting images is provided, wherein generating a grayscale curve based on the grayscale values ​​of pixels in the grayscale image includes:

[0017] Multiple sampling lines are selected along the length direction of the grayscale image at preset intervals;

[0018] The average grayscale value of multiple pixels located on the same sampling line is obtained as the grayscale value corresponding to the sampling line;

[0019] The position of the sampling line along the length of the grayscale image and the grayscale value corresponding to the sampling line are combined to form a pair of two-dimensional coordinates, and a line graph is generated based on each of the two-dimensional coordinates.

[0020] The line graph is smoothed to obtain the grayscale curve.

[0021] According to the present invention, an automatic analysis method for protein immunoblotting images, after obtaining the lane division result of the immunoblotting image of the protein to be analyzed, includes:

[0022] Based on the lane division results, the grayscale data of each lane in the immunoblot image of the protein to be analyzed are statistically analyzed to obtain statistical results, and the statistical results are stored in a preset file.

[0023] The next image that meets the preset format requirements is retrieved from the preset database as the new immunoblot image of the protein to be analyzed. The step of converting the immunoblot image of the protein to be analyzed into a grayscale image is repeated until there is no image that meets the preset format requirements in the preset database.

[0024] The present invention also provides an automated protein immunoblotting image analysis device, comprising:

[0025] The image reading module is used to acquire the immunoblot image of the protein to be analyzed, convert the immunoblot image of the protein to be analyzed into a grayscale image, and perform background noise reduction processing on the grayscale image.

[0026] The grayscale curve generation module is used to generate a grayscale curve based on the grayscale values ​​of the pixels in the grayscale image.

[0027] The valley identification module is used to identify the valleys of the grayscale curve and obtain each valley point in the grayscale curve.

[0028] The analysis result determination module is used to add segmentation lines to the grayscale image based on the position of the valley point in the grayscale curve, to obtain the lane division result of the immunoblot image of the protein to be analyzed, and to determine the grayscale value data corresponding to each lane based on the lane division result.

[0029] The present invention also provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement any of the above-described automatic protein immunoblotting image analysis methods.

[0030] The present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements any of the above-described automatic protein immunoblotting image analysis methods.

[0031] The present invention also provides a computer program product, including a computer program that, when executed by a processor, implements any of the above-described methods for automatic analysis of protein immunoblotting images.

[0032] The automatic analysis method, apparatus, device, and medium for protein immunoblot images provided by this invention automatically divides lanes by converting the gray values ​​of each pixel in the protein immunoblot image to be analyzed into gray-scale curves and then identifying the troughs in the gray-scale curves. Since the gray values ​​in the gray-scale curves can correspond to the pixels, the accuracy of the lane division results can be improved. Compared with manual visual division, this method can effectively improve the analysis efficiency of protein immunoblot images while ensuring the reliability of the lane division results. Attached Figure Description

[0033] To more clearly illustrate the technical solutions in this invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of this invention. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.

[0034] Figure 1 This is a flowchart illustrating the automated protein immunoblotting image analysis method provided by the present invention.

[0035] Figure 2 This is a schematic diagram of a grayscale image in the automatic analysis method for protein immunoblotting images provided by the present invention.

[0036] Figure 3 This is a schematic diagram of the grayscale curve in the automatic analysis method for protein immunoblotting images provided by the present invention.

[0037] Figure 4 This is a schematic diagram of the lane division results in the automatic analysis method for protein immunoblotting images provided by this invention.

[0038] Figure 5 This is a verification of the effectiveness of the automated protein immunoblotting image analysis method provided by the present invention. Figure 1 .

[0039] Figure 6 This is a verification of the effectiveness of the automated protein immunoblotting image analysis method provided by the present invention. Figure 2 .

[0040] Figure 7 This is a schematic diagram of the structure of the automated protein immunoblotting image analysis device provided by the present invention.

[0041] Figure 8 This is a schematic diagram of the structure of the electronic device provided by the present invention. Detailed Implementation

[0042] To make the objectives, technical solutions, and advantages of this invention clearer, the technical solutions of this invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of this invention. All other embodiments obtained by those skilled in the art based on the embodiments of this invention without creative effort are within the scope of protection of this invention.

[0043] The following is combined with Figures 1-6 The automatic analysis method for protein immunoblotting images provided by this invention is described below. Figure 1 As shown, the method includes the following steps:

[0044] S110. Obtain the immunoblot image of the protein to be analyzed, convert the immunoblot image of the protein to be analyzed into a grayscale image, and perform background noise reduction processing on the grayscale image.

[0045] S120. Generate a grayscale curve based on the grayscale values ​​of pixels in the grayscale image;

[0046] S130. Perform valley identification on the grayscale curve to obtain each valley point in the grayscale curve;

[0047] S140. Based on the position of the trough point in the grayscale curve, add segmentation lines to the grayscale image to obtain the lane division result of the immunoblot image of the protein to be analyzed, and determine the grayscale value data corresponding to each lane based on the lane division result.

[0048] The automatic analysis method for protein immunoblot images provided by this invention automatically divides lanes by converting the gray values ​​of each pixel in the protein immunoblot image to be analyzed into gray-scale curves and then identifying the troughs in the gray-scale curves. Since the gray values ​​in the gray-scale curves can correspond to the pixels, the accuracy of the lane division results can be improved. Compared with manual visual division, this method can effectively improve the analysis efficiency of protein immunoblot images while ensuring the reliability of the lane division results.

[0049] In one possible implementation of the automatic protein immunoblot image analysis method provided by this invention, a database can be pre-set, for example, a folder can be set up as the database. This database stores the protein immunoblot images to be analyzed. Obtaining the protein immunoblot image to be analyzed can be achieved by automatically reading images that meet preset format requirements (e.g., TIFF, JPG, PNG, etc.) from this database. Further, in another possible implementation of the method provided by this invention, all images that meet the preset format requirements in the database can be traversed and pre-sorted, for example, by the time they were stored in the database or by the image filename. The sorting result is stored, and each time a new protein immunoblot image is retrieved from the database as the protein immunoblot image to be analyzed, the selection is based on the sorting result.

[0050] By setting up a database and reading images conforming to a preset format from the database as the protein immunoblot images to be analyzed, batch automatic analysis of protein immunoblot images can be achieved, improving the analysis efficiency of protein immunoblot images.

[0051] After obtaining the immunoblot image of the protein to be analyzed, it is converted into a grayscale image, such as... Figure 2As shown. For grayscale images, a uniform size and format can be set, such as 8-bit or JPG format. In one possible implementation, the grayscale image can be further processed to remove background noise, thereby improving data quality and the accuracy of subsequent analysis to obtain swimlane division results. This can be achieved using existing denoising methods.

[0052] After obtaining the grayscale image, a grayscale curve is generated based on the grayscale values ​​of the pixels in the grayscale image, specifically including:

[0053] Multiple sampling lines are selected along the length of the grayscale image at preset intervals;

[0054] The average gray value of multiple pixels located on the same sampling line is obtained as the gray value corresponding to the sampling line;

[0055] The position of the sampling line along the length of the grayscale image and the grayscale value corresponding to the sampling line are combined to form a pair of two-dimensional coordinates, and a line chart is generated based on each two-dimensional coordinate.

[0056] Smooth the line chart to obtain a grayscale curve.

[0057] The immunoblot image of the protein to be analyzed is a strip image with obvious differences in length and width. After converting the immunoblot image of the protein to be analyzed into a grayscale image, multiple sampling lines can be selected along the length direction of the grayscale image at a preset interval. The preset interval can be n pixels. It can be understood that the larger the preset interval, the lower the sampling accuracy, and the smaller the preset interval, the higher the sampling accuracy. The size of the preset interval affects the sampling accuracy and thus the accuracy of the lane division result. An appropriate preset interval can be selected based on the accuracy requirements of the actual scenario.

[0058] Multiple pixels are selected along each sampling line. In Western blot images, only the darker detection lines reflect the protein response. To improve the accuracy of analysis results for Western blot images, pixels with gray values ​​greater than a threshold are selected along each sampling line. This eliminates interference from pixels not on the detection lines. For pixels selected along a sampling line, the average gray value is taken as the corresponding gray value for that sampling line.

[0059] The position of the sampling line along the length of the grayscale image and the grayscale value corresponding to the sampling line are combined to form a pair of two-dimensional coordinates. Specifically, the position of the sampling line along the length of the grayscale image is taken as the x-axis coordinate in the two-dimensional coordinate system, and the grayscale value corresponding to the sampling line is taken as the y-axis coordinate in the two-dimensional coordinate system. Then, each sampling line can correspond to a point in the two-dimensional coordinate system. Connecting these points will produce a line graph.

[0060] In practice, the color of the detection line produced by the protein reaction changes smoothly. In the method provided by this invention, the obtained line graph is smoothed to obtain a grayscale curve, such as... Figure 3 As shown, by smoothing the line graph to obtain a grayscale curve, it is equivalent to interpolating based on some existing grayscale values ​​along the length of the grayscale image, thus obtaining the grayscale values ​​at all positions along the length of the grayscale image. This can effectively improve the accuracy of the analysis results of the immunoblot images of the proteins to be analyzed.

[0061] After obtaining the grayscale curve, the valleys of the grayscale curve are identified to obtain each valley point in the grayscale curve, including:

[0062] Based on the points corresponding to each local minimum in the grayscale curve, the preliminary identification results of the valley points are obtained, which include multiple valley candidate points.

[0063] Based on the constraints, candidate trough points are selected to obtain trough points;

[0064] The constraints include a first constraint, which is used to constrain the uniformity of the lateral distance between two adjacent points in the selected trough points.

[0065] Since different lanes in the immunoblot image of the protein to be analyzed correspond to different protein reactions, there will be a process of grayscale decrease followed by an increase between lanes. The method provided by this invention identifies the troughs in the grayscale curve, thereby accurately identifying the dividing lines between adjacent lanes.

[0066] First, the points corresponding to the local minima in the grayscale curve are used as candidate troughs. The local minima can be determined by the slope of the points in the curve. These candidate troughs are indeed troughs in the local part of the curve, but they may be due to local abrupt changes in the depth of the detection line in a single lane caused by instability during the experiment. Therefore, further screening of the candidate troughs is required.

[0067] Based on constraints, candidate trough points are screened. The first constraint is that different lanes should have a consistent width, that is, the distance between two adjacent trough points should be uniform. According to this constraint, some candidate trough points can be deleted.

[0068] Furthermore, in another possible implementation of the method provided by the present invention, the constraint condition may also include a second constraint condition, which is used to constrain the significance of the peaks between two adjacent points in the selected trough points.

[0069] The peak between two adjacent points refers to the point with the largest gray value between two adjacent points. Since different lanes correspond to different protein detection lines, there must be a unique point with the largest gray value in the same protein detection line. There is a large difference in gray value between this point and the start and end points of the detection line. Therefore, by using the second constraint condition, the candidate points of the valleys can be identified by further eliminating local gray value fluctuations.

[0070] Furthermore, in another possible implementation of the method provided by the present invention, the constraint conditions may also include a third constraint condition, which is used to constrain the longitudinal coordinate stability between two adjacent points in the selected trough points.

[0071] The stability of the longitudinal coordinate between two adjacent troughs refers to the existence of only one peak between two adjacent troughs. That is, in the interval between two adjacent troughs in the grayscale curve, there is only one point where the longitudinal coordinate to the left of the point gradually increases and the longitudinal coordinate to the right of the point gradually decreases.

[0072] By constructing a triple trough identification and correction mechanism that includes the first constraint, the second constraint, and the third constraint, the influence of local gray value fluctuations or background interference caused by unstable factors in the experiment on the trough identification results can be effectively eliminated, thereby improving the accuracy of the trough points and ensuring the accuracy and robustness of the lane division results. This solves the key pain points of lane fusion, drifting, or misclassification when dividing lanes by eye.

[0073] Based on the position of the trough points in the grayscale curve, segmentation lines are added to the grayscale image. Specifically, based on the x-axis coordinate of the trough point in the grayscale curve, the corresponding position of the trough point along the length of the grayscale image can be determined. A line segment perpendicular to the length of the grayscale image is then generated at this corresponding position as the segmentation line. Figure 4 As shown.

[0074] After obtaining the lane division results of the immunoblot image of the protein to be analyzed, the following is included:

[0075] Based on the lane division results, the grayscale data of each lane in the immunoblot image of the protein to be analyzed are determined and statistically analyzed to obtain the statistical results, which are then stored in a preset file.

[0076] The system retrieves the next image that meets the preset format requirements from the preset database as a new immunoblot image of the protein to be analyzed. The process of converting the immunoblot image of the protein to be analyzed into a grayscale image is repeated until there are no images that meet the preset format requirements in the preset database.

[0077] Adding dividing lines to a grayscale image allows for the output of swimlane-divided images. Furthermore, the grayscale values ​​of the swimlanes can be statistically analyzed and output. Specifically, based on the swimlane division results, portions of each swimlane are extracted, and the statistical results of the grayscale values ​​of each swimlane are automatically output, as shown in Table 1.

[0078] Table 1

[0079]

[0080] Furthermore, statistical results can be stored in a preset file, which users can copy and download. The preset file can be in CSV format for easy downloading. This preset file records the protein immunoblotting analysis data of all images in the preset database, facilitating downstream statistical analysis or report generation.

[0081] Specifically, a preset file can be created for the preset database. When performing automatic batch analysis on the protein immunoblot images in the preset database, the analysis results of each protein immunoblot image are stored in the preset file. This allows users to import multiple protein immunoblot image files at once, automatically complete the analysis tasks of each image in sequence, and generate corresponding result files, which significantly improves data processing efficiency and consistency.

[0082] Furthermore, if issues such as swimlane recognition failure, insufficient image resolution, or extremely uneven background occur during processing, the system can automatically record the image's number or filename and prompt the user for manual review, ensuring the stability and controllability of the batch processing process.

[0083] The automated protein immunoblot image analysis method provided by this invention can effectively improve the efficiency of protein immunoblot image analysis. Traditionally, analyzing a single protein immunoblot image requires 10-20 minutes after visually dividing the lanes. However, the automated method provided by this invention can complete the analysis of a protein immunoblot image within 1-2 seconds. Furthermore, manually dividing lanes is easily influenced by the subjectivity of different operators, and even different analyses by the same analyst may yield different results. This is especially true when the protein differences between adjacent lanes are small, leading to low reliability of manually divided lanes. The method provided by this invention, based on automated data analysis, provides stable, reliable, highly consistent, and reproducible results. Additionally, the method provided in this application can simultaneously output a visual image of the lane division, facilitating user monitoring of the reliability of the results.

[0084] The method provided by this invention can be integrated into platform software or web tools, facilitating cross-laboratory sharing and promotion. Batch processing functionality utilizes the `os` module in Python for directory traversal and image reading, and iterates through the `analyze_wb_image()` function in a loop. Output results are automatically named and saved, supporting both image visualization (.png) and data table (.csv) formats. The front-end interface simplifies user operation through web applications (such as Streamlit) or desktop GUIs (such as PyQt). The method provided by this invention can be published as a web version in conjunction with Shiny or Streamlit, enabling zero-installation online analysis.

[0085] To verify the reliability of the automated protein immunoblotting image analysis method provided by this invention, a comparative experiment was conducted using both the method provided by this invention and manual lane division analysis on the same protein immunoblotting images. The comparison results are as follows: Figure 5 As shown.

[0086] The Blond-Altman analysis method was further used to analyze the results of multiple protein immunoblot images analyzed using the method provided in this invention and the manual lane division analysis method, such as... Figure 6 As shown, the average difference between the two is close to 0, and all data points fall within the 95% consistency limit (±1.96SD), indicating that the method provided in this application has a high degree of accuracy and reliability in swimlane integral calculation that is consistent with traditional manual methods.

[0087] It is worth noting that, for the results of the manual lane division analysis method used in the comparative experiment, multiple groups of people can analyze the same protein immunoblot image, and the average or the most reliable value can be taken as the analysis result of the manual lane division analysis method for that protein immunoblot image.

[0088] The automatic protein immunoblotting image analysis device provided by the present invention is described below. The automatic protein immunoblotting image analysis device described below can be referred to in correspondence with the automatic protein immunoblotting image analysis method described above. For example... Figure 7 As shown, the automated protein immunoblotting image analysis device provided by the present invention includes:

[0089] The image reading module 710 is used to acquire the immunoblot image of the protein to be analyzed, convert the immunoblot image of the protein to be analyzed into a grayscale image, and perform background noise reduction processing on the grayscale image.

[0090] The grayscale curve generation module 720 is used to generate a grayscale curve based on the grayscale values ​​of pixels in a grayscale image.

[0091] Valley recognition module 730 is used to identify valleys in grayscale curves to obtain each valley point in the grayscale curve;

[0092] The analysis result determination module 740 is used to add segmentation lines to the grayscale image based on the position of the trough point in the grayscale curve, obtain the lane division result of the immunoblot image of the protein to be analyzed, and determine the grayscale value data corresponding to each lane based on the lane division result.

[0093] The automatic analysis device for protein immunoblot images provided by this invention automatically divides lanes by converting the gray values ​​of each pixel in the protein immunoblot image to be analyzed into gray-scale curves and then identifying the troughs in the gray-scale curves. Since the gray values ​​in the gray-scale curves can correspond to the pixels, the accuracy of the lane division results can be improved. Compared with manual eye division, it can effectively improve the efficiency of lane division while ensuring the reliability of the lane division results for protein immunoblot images.

[0094] Figure 8 An example is a schematic diagram of the physical structure of an electronic device, such as... Figure 8 As shown, the electronic device may include a processor 810, a communication interface 820, a memory 830, and a communication bus 840. The processor 810, communication interface 820, and memory 830 communicate with each other via the communication bus 840. The processor 810 can call logical instructions in the memory 830 to execute an automatic protein immunoblot image analysis method. This automatic protein immunoblot image analysis method includes: acquiring a protein immunoblot image to be analyzed; converting the protein immunoblot image to be analyzed into a grayscale image and performing background noise reduction processing on the grayscale image; generating a grayscale curve based on the grayscale values ​​of pixels in the grayscale image; identifying valleys in the grayscale curve to obtain each valley point; adding segmentation lines to the grayscale image based on the position of the valley points in the grayscale curve to obtain the swimlane division result of the protein immunoblot image to be analyzed; and determining the grayscale value data corresponding to each swimlane based on the swimlane division result.

[0095] Furthermore, the logical instructions in the aforementioned memory 830 can be implemented as software functional units and, when sold or used as independent products, can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, or a part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0096] On the other hand, the present invention also provides a computer program product, which includes a computer program that can be stored on a non-transitory computer-readable storage medium. When the computer program is executed by a processor, the computer can execute the automatic protein immunoblot image analysis method provided by the above methods. The automatic protein immunoblot image analysis method includes: acquiring a protein immunoblot image to be analyzed; converting the protein immunoblot image to be analyzed into a grayscale image and performing background noise reduction processing on the grayscale image; generating a grayscale curve based on the grayscale values ​​of the pixels in the grayscale image; identifying the valleys of the grayscale curve to obtain each valley point in the grayscale curve; adding dividing lines to the grayscale image based on the position of the valley points in the grayscale curve to obtain the lane division result of the protein immunoblot image to be analyzed; and determining the grayscale value data corresponding to each lane based on the lane division result.

[0097] In another aspect, the present invention also provides a non-transitory computer-readable storage medium storing a computer program thereon. When executed by a processor, the computer program implements the automatic protein immunoblot image analysis method provided by the above methods. The automatic protein immunoblot image analysis method includes: acquiring a protein immunoblot image to be analyzed; converting the protein immunoblot image to be analyzed into a grayscale image and performing background noise reduction processing on the grayscale image; generating a grayscale curve based on the grayscale values ​​of pixels in the grayscale image; identifying valleys in the grayscale curve to obtain each valley point in the grayscale curve; adding segmentation lines to the grayscale image based on the position of the valley points in the grayscale curve to obtain the swimlane division result of the protein immunoblot image to be analyzed; and determining the grayscale value data corresponding to each swimlane based on the swimlane division result.

[0098] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs. Those skilled in the art can understand and implement this without any creative effort.

[0099] Through the above description of the embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by means of software plus necessary general-purpose hardware platforms, and of course, it can also be implemented by hardware. Based on this understanding, the above technical solutions, in essence or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute the methods described in the various embodiments or some parts of the embodiments.

[0100] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, and not to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features; and these modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. An automated method for analyzing protein immunoblot images, characterized in that, include: Acquire an immunoblot image of the protein to be analyzed, convert the immunoblot image of the protein to be analyzed into a grayscale image, and perform background noise reduction processing on the grayscale image; A grayscale curve is generated based on the grayscale values ​​of the pixels in the grayscale image; Valley identification is performed on the grayscale curve to obtain each valley point in the grayscale curve; Based on the position of the valley point in the grayscale curve, a segmentation line is added to the grayscale image to obtain the lane division result of the immunoblot image of the protein to be analyzed, and the grayscale value data corresponding to each lane is determined based on the lane division result. The step of identifying the valleys of the grayscale curve to obtain each valley point in the grayscale curve includes: Based on the points corresponding to each local minimum value in the grayscale curve, a preliminary valley point identification result is obtained, which includes multiple valley candidate points. The candidate valley points are selected based on the constraints to obtain the valley points; The constraints include a first constraint, which constrains the uniformity of the lateral distance between two adjacent points in the selected troughs; and a second constraint, which constrains the significance of the peaks between two adjacent points in the selected troughs. The constraint conditions also include a third constraint condition, which is used to constrain the longitudinal coordinate stability between two adjacent points in the selected trough points. The longitudinal coordinate stability between two adjacent trough points means that there is only one peak between two adjacent trough points.

2. The automatic analysis method for protein immunoblotting images according to claim 1, characterized in that, The step of generating a grayscale curve based on the grayscale values ​​of pixels in the grayscale image includes: Multiple sampling lines are selected along the length direction of the grayscale image at preset intervals; The average grayscale value of multiple pixels located on the same sampling line is obtained as the grayscale value corresponding to the sampling line; The position of the sampling line along the length of the grayscale image and the grayscale value corresponding to the sampling line are combined to form a pair of two-dimensional coordinates, and a line graph is generated based on each of the two-dimensional coordinates. The line graph is smoothed to obtain the grayscale curve.

3. The automatic analysis method for protein immunoblotting images according to claim 1, characterized in that, After obtaining the lane division results of the immunoblot image of the protein to be analyzed, the process includes: Based on the lane division results, the grayscale data of each lane in the immunoblot image of the protein to be analyzed are statistically analyzed to obtain statistical results, and the statistical results are stored in a preset file. The next image that meets the preset format requirements is retrieved from the preset database as the new immunoblot image of the protein to be analyzed. The step of converting the immunoblot image of the protein to be analyzed into a grayscale image is repeated until there is no image that meets the preset format requirements in the preset database.

4. An automated protein immunoblotting image analysis device, characterized in that, The device includes: The image reading module is used to acquire the immunoblot image of the protein to be analyzed, convert the immunoblot image of the protein to be analyzed into a grayscale image, and perform background noise reduction processing on the grayscale image. The grayscale curve generation module is used to generate a grayscale curve based on the grayscale values ​​of the pixels in the grayscale image. The valley identification module is used to identify the valleys of the grayscale curve and obtain each valley point in the grayscale curve. The analysis result determination module is used to add a dividing line to the grayscale image based on the position of the valley point in the grayscale curve, to obtain the lane division result of the immunoblot image of the protein to be analyzed, and to determine the grayscale value data corresponding to each lane based on the lane division result. The step of identifying the valleys of the grayscale curve to obtain each valley point in the grayscale curve includes: Based on the points corresponding to each local minimum value in the grayscale curve, a preliminary valley point identification result is obtained, which includes multiple valley candidate points. The candidate valley points are selected based on the constraints to obtain the valley points; The constraints include a first constraint, which constrains the uniformity of the lateral distance between two adjacent points in the selected troughs; and a second constraint, which constrains the significance of the peaks between two adjacent points in the selected troughs. The constraint conditions also include a third constraint condition, which is used to constrain the longitudinal coordinate stability between two adjacent points in the selected trough points. The longitudinal coordinate stability between two adjacent trough points means that there is only one peak between two adjacent trough points.

5. An electronic device comprising a memory, a processor, and a computer program stored in the memory and running on the processor, characterized in that, When the processor executes the computer program, it implements the automatic analysis method for protein immunoblotting images as described in any one of claims 1 to 3.

6. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the automatic analysis method for protein immunoblotting images as described in any one of claims 1 to 3.

7. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by the processor, it implements the automatic analysis method for protein immunoblotting images as described in any one of claims 1 to 3.

Images