Method and system for selecting continuous irregular cryoelectron microscope single particles

Abstract

The invention relates to the technical field of image analysis, and discloses a method and system for selecting continuous irregular single particles of a cryoelectron microscope, and the method comprises the steps: obtaining a cryoelectron microscope picture, analyzing the cryoelectron microscope picture, and obtaining a preliminary marking track; performing interpolation correction on the preliminary mark track to obtain a corrected mark track; and generating a plurality of protein particle data according to the correction mark trajectory, and outputting the protein particle data. It can be seen that aiming at the defect that continuous irregular particles with low signal-to-noise ratios cannot be accurately selected in the existing cryoelectron microscope single-particle technology, the method comprises the following steps: preliminarily analyzing a cryoelectron microscope picture to obtain a small number of mark points as a preliminary track, and then performing interpolation correction on the preliminary mark track to obtain a small number of mark points; and finally, generating a protein particle data file, and quickly and accurately completing the selection of the protein particles.

Description

Technical Field

[0001] The present invention relates to the field of image analysis technology, and in particular to a method, system, terminal and computer-readable storage medium for selecting continuous irregular single particles under cryo-electron microscopy. Background Art

[0002] Cryo-electron microscopy single particle technology is currently the most popular structure analysis method in the field of structural biology. This method is based on the central section theorem. Starting from the two-dimensional projection images (particles) of biological macromolecules at different angles, protein particles are selected, and the protein particles are aligned, classified, averaged and reversely projected to obtain their three-dimensional density map. It can be seen that defining and selecting particles from cryo-electron microscopy images is a very important step in this method, and is the key to determining the success of the final reconstruction.

[0003] With the development of technology, since the "resolution revolution", cryo-electron microscopy single-particle technology has undergone more than ten years of rapid development. Currently, semi-automatic template matching and fully automatic particle selection methods developed using machine learning are widely used. However, since biological samples have different conformational changes in their natural state, and in order to reduce electron radiation damage, the signal-to-noise ratio of cryo-electron microscopy images imaged with low electron doses is low, and the two existing methods still cannot achieve better processing.

[0004] Among them, when using the template matching method, it is necessary to manually select some particles required for reconstruction, generate a template, and then determine the position of each particle by calculating the correlation between the original image and the template; this method is highly dependent on the original image with high signal-to-noise ratio and high contrast, and for biological samples with large heterogeneity and continuous irregularity, this method will obviously fail to identify all particles. Due to the above two reasons, the particles selected using the semi-automatic template matching method require users to spend a lot of time and energy on template selection and particle screening, which is easy to introduce human errors.

[0005] The particle selection method of machine learning is based on methods such as convolutional neural networks, regional convolutional neural networks, cross-correlation and image segmentation. It selects particles by distinguishing biological samples from background noise. However, this method still cannot achieve comprehensive and accurate particle selection for low signal-to-noise ratio and continuous irregular samples.

[0006] In summary, the existing technology still lacks an efficient and accurate method for selecting continuous irregular cryo-EM single particles. Summary of the invention

[0007] The purpose of the present invention is to provide a method and system for selecting continuous irregular cryo-electron microscopy single particles, aiming to solve the problem in the prior art of lack of efficient and accurate means for selecting single particles in continuous irregular cryo-electron microscopy images.

[0008] The technical solution adopted by the present invention to solve the technical problem is as follows:

[0009] The present invention provides a method for selecting continuous irregular cryo-electron microscopy single particles, and the method for selecting continuous irregular cryo-electron microscopy single particles specifically comprises:

[0010] Acquire a cryo-electron microscopy image, analyze the cryo-electron microscopy image, and obtain a preliminary marking trajectory;

[0011] Correcting the preliminary marking trajectory to obtain a corrected marking trajectory;

[0012] A plurality of protein particle data are generated according to the calibration mark trajectory, and the protein particle data are output.

[0013] Further, the obtaining of cryo-EM images, analyzing the cryo-EM images, and obtaining preliminary marking trajectories specifically include:

[0014] Acquire a cryo-electron microscopy image, and preprocess the cryo-electron microscopy image to obtain a preprocessed image;

[0015] The pre-processed image is analyzed to obtain the preliminary marking trajectory.

[0016] Furthermore, the pre-processed image is analyzed to obtain the preliminary marking trajectory, specifically:

[0017] A plurality of marking points on the preprocessed image are obtained as the preliminary marking trajectory.

[0018] Further, the step of correcting the preliminary marking trajectory to obtain a corrected marking trajectory specifically includes:

[0019] The preliminary trajectory is interpolated using the Bezier curve interpolation method to obtain multiple interpolation points

[0020] The correction mark trajectory is obtained by fitting according to each of the interpolation points.

[0021] Furthermore, the generating a plurality of protein particle data according to the calibration mark trajectory specifically includes:

[0022] Obtaining a plurality of protein particles according to the calibration marker trajectory;

[0023] The center coordinates of each protein particle are calculated to obtain a plurality of protein particle coordinates as the protein particle data.

[0024] Furthermore, obtaining a plurality of protein particles according to the calibration marker trajectory specifically includes:

[0025] According to the cryo-electron microscopy images, the distances between adjacent subunits constituting the irregular continuous polymers are measured to obtain the distance between protein particles;

[0026] The calibration mark track is evenly divided according to the protein particle distance to obtain a plurality of protein particles.

[0027] Furthermore, the outputting of the protein particle data specifically includes:

[0028] Converting the protein particle data into a cryo-electron microscopy analysis software format to obtain conversion data;

[0029] The converted data is output.

[0030] In addition, to achieve the above-mentioned purpose, the present invention also provides a system for selecting continuous irregular cryo-electron microscopy single particles, the system for selecting continuous irregular cryo-electron microscopy single particles comprising:

[0031] A trajectory acquisition module is used to acquire cryo-electron microscopy images and analyze the cryo-electron microscopy images to acquire preliminary marking trajectories;

[0032] A trajectory correction module, used for correcting the preliminary marking trajectory to obtain a corrected marking trajectory;

[0033] The particle selection module is used to generate a plurality of protein particle data according to the calibration mark trajectory and output the protein particle data.

[0034] In addition, to achieve the above-mentioned purpose, the present invention also provides a terminal, which includes: a memory, a processor, and a program for selecting continuous irregular cryo-electron microscopy single particles stored in the memory and executable on the processor, wherein the program for selecting continuous irregular cryo-electron microscopy single particles, when executed by the processor, controls the terminal to implement the steps of a method for selecting continuous irregular cryo-electron microscopy single particles as described above.

[0035] In addition, to achieve the above-mentioned purpose, the present invention also provides a readable storage medium, which stores a program for selecting continuous irregular cryo-electron microscopy single particles. When the program for selecting continuous irregular cryo-electron microscopy single particles is executed by a processor, the steps of a method for selecting continuous irregular cryo-electron microscopy single particles as described above are implemented.

[0036] The present invention adopts the above technical solution to achieve the following effects:

[0037] The present invention addresses the shortcoming that the current cryo-electron microscopy single particle technology cannot accurately select low signal-to-noise ratio and continuous irregular particles. By preliminarily analyzing the cryo-electron microscopy images, a small number of marking points are obtained as preliminary trajectories, and then the preliminary marking trajectories are interpolated and corrected. Finally, a protein particle data file is generated, so that the protein particles can be selected quickly and accurately. BRIEF DESCRIPTION OF THE DRAWINGS

[0038] Figure 1 This is a flow chart of the steps of a method for selecting continuous irregular cryo-electron microscopy single particles in a preferred embodiment of the present invention;

[0039] Figure 2 is a schematic diagram of a graphical interface at the beginning of a graphical interface in a preferred embodiment of the present invention;

[0040] Figure 3 It is a schematic diagram of a graphical interface for obtaining cryo-electron microscopy images in a preferred embodiment of the present invention;

[0041] Figure 4 is a schematic diagram of an image after preprocessing in a preferred embodiment of the present invention;

[0042] Figure 5 It is a schematic diagram of the process of obtaining a preliminary marking trajectory in a preferred embodiment of the present invention.

[0043] Figure 6 It is a schematic diagram of the principle of a system for selecting continuous irregular cryo-electron microscopy single particles in a preferred embodiment of the present invention;

[0044] Figure 7 It is a schematic diagram of the operating environment of a preferred embodiment of the terminal of the present invention. DETAILED DESCRIPTION

[0045] In order to make the purpose, technical solution and advantages of the present invention clearer and more specific, the present invention is further described in detail with reference to the accompanying drawings and examples. It should be understood that the described embodiments are only part of the embodiments of the present disclosure, rather than all the embodiments. The specific embodiments described herein are only used to explain the present invention, and are not used to limit the present invention. All other embodiments obtained by those skilled in the art without creative work are within the scope of protection of the present disclosure.

[0046] Embodiment 1

[0047] See also Figure 1, Embodiment 1 of the present application is a method for selecting continuous irregular cryo-electron microscopy single particles, which can be applied to terminals, including mobile devices, user terminals, handheld devices, computing devices, wearable devices, etc. It can also be run in a server or edge unit. The server can be an independent physical server, a server cluster or distributed system composed of multiple physical servers, or a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud storage, big data and artificial intelligence platforms.

[0048] A method for selecting continuous irregular cryo-electron microscopy single particles in this embodiment comprises the following steps:

[0049] S1. Obtain a cryo-electron microscopy image, analyze the cryo-electron microscopy image, and obtain a preliminary marking trajectory.

[0050] Specifically, in this embodiment, programming is performed based on Matlab to form an analysis of cryo-electron microscopy images. The program corresponding to the method of the present invention is opened in Matlab, and the corresponding original image of the frozen image is selected. The original image of the frozen image is then preprocessed, and the preprocessed image is used as the image for subsequent analysis.

[0051] Please refer to Figure 2 , Figure 2 After running the program in Matlab, the particle labeling graphical interface pops up first. Click "load file" in the upper right corner and select the original image in the folder named "Image" to open it. Figure 3 Graphical interface.

[0052] Then pre-process the image by clicking "invert image", "adjust contrast" and "Image filters" on the right in turn to improve the image contrast by inverting the image, adjusting the contrast and performing high-pass or low-pass filtering on the image. Then adjust the image size at the "scale" in the middle of the right side to get the following result: Figure 4 Preprocessed images of standard sizes are shown.

[0053] Afterwards, the preprocessed image is analyzed, and the marking points distributed in a spiral trajectory are obtained as a preliminary marking trajectory. The preliminary marking trajectory can be performed by a deep learning network. The cryo-electron microscopy image is input into the deep learning network, and the deep learning network outputs the preliminary marking trajectory. It can also be marked by manually selecting points.

[0054] Please refer to Figure 5 In this embodiment, manual point selection is specifically adopted to obtain multiple manually selected marking points as the preliminary marking trajectory.

[0055] S2. Perform interpolation correction on the preliminary marking trajectory to obtain a corrected marking trajectory.

[0056] Since the small number of manually selected marker points are relatively sparse and dense, the curve fitting in sparse areas will differ greatly from the actual trajectory, while interpolation will obtain more continuous points, which will match the actual trajectory after fitting.

[0057] To this end, it is necessary to perform interpolation correction on the preliminary marking trajectory obtained in step S1. Specifically, in this embodiment, the Bezier curve interpolation method is used for correction, which fits the Bezier curve according to the marking points and interpolates to obtain multiple interpolation points, and then regenerates the trajectory according to the interpolation points to obtain the corrected marking trajectory.

[0058] S3. Generate a plurality of protein particle data according to the calibration mark trajectory, and output the protein particle data.

[0059] In this embodiment, the correction mark trajectory is divided equally to obtain a plurality of equally divided protein particle data. Specifically, in this embodiment, firstly, measurements are performed based on cryo-electron microscopy images, and the distances between adjacent subunits constituting irregular continuous polymers are measured in the images. The measured distances are defined as the protein particle distances. Based on the protein particle distances, the spiral trajectory is divided equally and calibrated to obtain a plurality of protein particles, and the center coordinates of each protein particle are obtained as protein particle data.

[0060] The protein particle data is then output. In this embodiment, a folder called "Result" is automatically generated at the same level as the folder called "Picking-result", and the newly generated particle coordinates are saved in the folder in the ".mat" format.

[0061] It is worth explaining that the ".mat" format is the generation of protein particle files of Matlab program files, but the Matlab program files are only responsible for the selection of protein particles in cryo-electron microscopy images. The subsequent protein particles need to be imported into the existing cryo-electron microscopy analysis software Relion for subsequent three-dimensional reconstruction. Therefore, the ".mat" file must be converted into a ".star" file that can be recognized by Relion. After the ".mat" coordinate file generated in the previous step is input into the file conversion program, because the coordinate system definitions of Matlab and Relion are different, each protein particle coordinate in the ".mat" is first converted, and then all the protein particle coordinates on the same image are integrated together to output a ".star" file. At the same time, a "STAR" folder is automatically created at the same level as the "Result" folder to store the final coordinate file.

[0062] Embodiment 2

[0063] See also Figure 6 Based on the above method, the present invention also provides a system for selecting continuous irregular cryo-electron microscopy single particles, the system for selecting continuous irregular cryo-electron microscopy single particles comprising:

[0064] A trajectory acquisition module 51 is used to acquire a cryo-electron microscopy image and analyze the cryo-electron microscopy image to acquire a preliminary marking trajectory;

[0065] Further, the obtaining of cryo-EM images, analyzing the cryo-EM images, and obtaining preliminary marking trajectories specifically include:

[0066] Acquire a cryo-electron microscopy image, and preprocess the cryo-electron microscopy image to obtain a preprocessed image;

[0067] The pre-processed image is analyzed to obtain the preliminary marking trajectory.

[0068] Further, the analyzing the pre-processed image to obtain the preliminary marking trajectory specifically includes:

[0069] Acquire a plurality of marking points on the preprocessed image;

[0070] Fitting is performed on each of the marking points to obtain the preliminary marking trajectory.

[0071] A trajectory correction module 52, used for correcting the preliminary marking trajectory to obtain a corrected marking trajectory;

[0072] Furthermore, the pre-processed image is analyzed to obtain the preliminary marking trajectory, specifically:

[0073] A plurality of marking points on the preprocessed image are obtained as the preliminary marking trajectory.

[0074] Further, the step of correcting the preliminary marking trajectory to obtain a corrected marking trajectory specifically includes:

[0075] The preliminary trajectory is interpolated using the Bezier curve interpolation method to obtain multiple interpolation points

[0076] The correction mark trajectory is obtained by fitting according to each of the interpolation points.

[0077] The particle selection module 53 is used to generate a plurality of protein particle data according to the calibration mark trajectory and output the protein particle data.

[0078] Furthermore, the generating a plurality of protein particle data according to the calibration mark trajectory specifically includes:

[0079] Obtaining a plurality of protein particles according to the calibration marker trajectory;

[0080] The center coordinates of each protein particle are calculated to obtain a plurality of protein particle coordinates as the protein particle data.

[0081] Furthermore, obtaining a plurality of protein particles according to the calibration marker trajectory specifically includes:

[0082] According to the cryo-electron microscopy images, the distances between adjacent subunits constituting the irregular continuous polymers are measured to obtain the distance between protein particles;

[0083] The calibration mark track is evenly divided according to the protein particle distance to obtain a plurality of protein particles.

[0084] Furthermore, the outputting of the protein particle data specifically includes:

[0085] Converting the protein particle data into a cryo-electron microscopy analysis software format to obtain conversion data;

[0086] The converted data is output.

[0087] Embodiment 3

[0088] See also Figure 7 Based on the above method, the present invention also provides a terminal, which includes a processor 10, a memory 20 and a display 30. Figure 7 Only some components of the terminal are shown, but it should be understood that it is not required to implement all of the components shown, and more or fewer components may be implemented instead.

[0089] In some embodiments, the memory 20 may be an internal storage unit of the terminal, such as a hard disk or memory of the terminal. In other embodiments, the memory 20 may also be an external storage device of the terminal, such as a plug-in hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (SecureDigital, SD) card, a flash card (Flash Card), etc. equipped on the terminal. Furthermore, the memory 20 may also include both an internal storage unit of the terminal and an external storage device. The memory 20 is used to store application software and various types of data installed in the terminal, such as the program code of the installation terminal. The memory 20 may also be used to temporarily store data that has been output or is to be output. In one embodiment, a continuous irregular cryo-electron microscopy single particle selection program 40 is stored on the memory 20, and the continuous irregular cryo-electron microscopy single particle selection program 40 can be executed by the processor 10.

[0090] In some embodiments, the processor 10 can be a central processing unit (CPU), a microprocessor or other data processing chip, which is used to run the program code or process data stored in the memory 20, such as executing related programs of the method for selecting continuous irregular cryo-electron microscopy single particles.

[0091] In some embodiments, the display 30 may be an LED display, a liquid crystal display, a touch-sensitive liquid crystal display, an OLED (Organic Light-Emitting Diode) touch device, etc. The display 30 is used to display information on the terminal and to display a visual user interface. The components of the terminal communicate with each other via a system bus.

[0092] In one embodiment, when the processor 10 executes the continuous irregular cryo-electron microscopy single particle selection program 40 in the memory 20, the steps of a method for selecting continuous irregular cryo-electron microscopy single particles as described above are implemented.

[0093] In some embodiments, the memory 20 may be an internal storage unit of the terminal, such as a hard disk or memory of the terminal. In other embodiments, the memory 20 may also be an external storage device of the terminal, such as a plug-in hard disk, a smart memory card (SmartMediaCard, SMC), a secure digital (SecureDigital, SD) card, a flash card (FlashCard), etc. equipped on the terminal. Further, the memory 20 may also include both an internal storage unit of the terminal and an external storage device. The memory 20 is used to store application software and various types of data installed in the terminal, such as the program code of the installation terminal. The memory 20 may also be used to temporarily store data that has been output or is to be output. In one embodiment, a program for selecting continuous irregular cryo-electron microscopy single particles is stored on the memory 20, and the program for selecting continuous irregular cryo-electron microscopy single particles can be executed by the processor 10, thereby realizing the method for selecting continuous irregular cryo-electron microscopy single particles in the present application.

[0094] In some embodiments, the processor 10 may be a central processing unit (CPU), a microprocessor or other data processing chip, used to run the program code or process data stored in the memory 20, such as executing the method for selecting continuous irregular cryo-electron microscopy single particles.

[0095] Embodiment 4

[0096] This embodiment provides a storage medium, wherein the readable storage medium stores a program for selecting continuous irregular cryo-electron microscopy single particles. When the program for selecting continuous irregular cryo-electron microscopy single particles is executed by a processor, the steps of the method for selecting continuous irregular cryo-electron microscopy single particles as described above are implemented.

[0097] In summary, the present invention addresses the shortcoming of the current cryo-electron microscopy single particle technology that is unable to accurately select low signal-to-noise ratio and continuous irregular particles. By preliminarily analyzing the cryo-electron microscopy images, a small number of marking points are obtained as preliminary trajectories, and then the preliminary marking trajectories are interpolated and corrected. Finally, a protein particle data file is generated, so that the protein particles can be selected quickly and accurately.

[0098] It should be noted that, in this article, the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, article or terminal including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or terminal. In the absence of further restrictions, an element defined by the sentence "comprises a ..." does not exclude the presence of other identical elements in the process, method, article or terminal including the element.

[0099] Of course, those skilled in the art can understand that all or part of the processes in the above-mentioned embodiments can be implemented by instructing related hardware (such as a processor, a controller, etc.) through a computer program, and the program can be stored in a computer-readable storage medium, and the program can include the processes of the above-mentioned method embodiments when executed. The storage medium can be a memory, a disk, an optical disk, etc.

[0100] It should be understood that the application of the present invention is not limited to the above examples. For ordinary technicians in this field, improvements or changes can be made based on the above description. All these improvements and changes should fall within the scope of protection of the claims attached to the present invention.

Claims

1. A method for selecting continuous irregular single particles for cryo-electron microscopy, characterized in that: The method for selecting continuous irregular cryo-electron microscopy single particles specifically comprises: Acquire a cryo-electron microscopy image, analyze the cryo-electron microscopy image, and obtain a preliminary marking trajectory; Performing interpolation correction on the preliminary marking trajectory to obtain a corrected marking trajectory; A plurality of protein particle data are generated according to the calibration mark trajectory, and the protein particle data are output.

2. A method for selecting continuous irregular cryo-electron microscopy single particles according to claim 1, characterized in that: The step of obtaining a cryo-electron microscopy image and analyzing the cryo-electron microscopy image to obtain a preliminary marking trajectory specifically includes: Acquire a cryo-electron microscopy image, and preprocess the cryo-electron microscopy image to obtain a preprocessed image; The preprocessed image is analyzed to obtain the preliminary marking trajectory.

3. A method for selecting continuous irregular cryo-electron microscopy single particles according to claim 2, characterized in that: The analyzing the pre-processed image to obtain the preliminary marking trajectory specifically includes: A plurality of marking points on the preprocessed image are obtained as the preliminary marking trajectory.

4. A method for selecting continuous irregular cryo-electron microscopy single particles according to claim 3, characterized in that: The correcting the preliminary marking trajectory to obtain a corrected marking trajectory specifically includes: interpolating the preliminary trajectory using a Bezier curve interpolation method to obtain a plurality of interpolation points; The correction mark trajectory is obtained by fitting according to each of the interpolation points.

5. The method for selecting continuous irregular cryo-electron microscopy single particles according to claim 1, characterized in that: Generating a plurality of protein particle data according to the calibration mark trajectory specifically includes: Obtaining a plurality of protein particles according to the calibration marker trajectory; The center coordinates of each protein particle are calculated to obtain a plurality of protein particle coordinates as the protein particle data.

6. A method for selecting continuous irregular cryo-electron microscopy single particles according to claim 5, characterized in that: The step of obtaining a plurality of protein particles according to the calibration marker trajectory specifically comprises: According to the cryo-electron microscopy images, the distances between adjacent subunits constituting the irregular continuous polymers are measured to obtain the distance between protein particles; The calibration mark track is evenly divided according to the protein particle distance to obtain a plurality of protein particles.

7. A method for selecting continuous irregular cryo-electron microscopy single particles according to claim 1, characterized in that: Outputting the protein particle data specifically includes: Converting the protein particle data into a cryo-electron microscopy analysis software format to obtain conversion data; The converted data is output.

8. A system for selecting continuous irregular single particles for cryo-electron microscopy, characterized in that: The system for selecting continuous irregular cryo-electron microscopy single particles comprises: A trajectory acquisition module is used to acquire cryo-electron microscopy images and analyze the cryo-electron microscopy images to acquire preliminary marking trajectories; A trajectory correction module, used for performing interpolation correction on the preliminary marking trajectory to obtain a corrected marking trajectory; The particle selection module is used to generate a plurality of protein particle data according to the calibration mark trajectory and output the protein particle data.

9. A terminal, characterized in that: The terminal includes: a memory, a processor, and a program for selecting continuous irregular cryo-electron microscopy single particles stored in the memory and executable on the processor. When the program for selecting continuous irregular cryo-electron microscopy single particles is executed by the processor, the terminal is controlled to implement the steps of the method for selecting continuous irregular cryo-electron microscopy single particles as described in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a program for selecting continuous irregular cryo-electron microscopy single particles, and when the program for selecting continuous irregular cryo-electron microscopy single particles is executed by a processor, the steps of the method for selecting continuous irregular cryo-electron microscopy single particles as described in any one of claims 1 to 7 are implemented.

Images