Track line reconstruction method and device, computer equipment and storage medium

Abstract

The invention relates to a trajectory reconstruction method and device, computer equipment, a computer readable storage medium and a computer program product. The method comprises the steps that a first image, a second image and a third image which are successfully registered are obtained, a fourth image which fails to be registered is obtained, the relative position of a first camera and the relative position of a second camera are kept constant, the four images are obtained by conducting two-round photographing on a biological chip through two cameras respectively, a plurality of trajectory lines are distributed on the biological chip, and the trajectory lines are matched with the first camera and the second camera; the registration is used for identifying a trajectory in the image; transforming the third trajectory equation according to the first trajectory equation and the second trajectory equation to obtain a fourth trajectory equation; and reconstructing a trajectory on the fourth image according to the fourth trajectory equation. On the basis of the other three images which are successfully registered in the two rounds of photographing, the trajectory is reconstructed in the image which fails to be registered, so that the situation that the subsequent sequencing process cannot be carried out due to the fact that the trajectory cannot be identified is avoided, and the gene sequencing efficiency is improved.

Description

Technical Field

[0001] This application relates to the field of gene sequencing image analysis, specifically to a trajectory line reconstruction method, apparatus, computer equipment, computer-readable storage medium, and computer program product. Background Technology

[0002] This section is intended to provide background or context for implementing the embodiments of the invention as set forth in the claims and detailed description. The description herein is not intended to imply that it is prior art simply because it is included in this section.

[0003] The research and application of gene sequencing technology covers almost all areas of human society, including health, agriculture, energy, and national defense and security. It has played a huge role in promoting life sciences, biomedicine and related industries, and has a more profound impact than the information economy era.

[0004] Current next-generation sequencing (NGS) technologies employ high-resolution microscopic imaging systems to capture fluorescent molecular images of DNA nanoballs (DNBs) on biochips, enabling gene sequencing based on these images. This sequencing method first requires image registration to identify the tracks within the image. Following image registration, subsequent processing (such as noise reduction, grayscale extraction, and correction) can be performed, ultimately allowing for base identification.

[0005] However, in some cases, image registration fails, making it impossible to identify the track lines, which in turn affects the efficiency of gene sequencing. Summary of the Invention

[0006] Therefore, it is necessary to provide a trajectory reconstruction method, apparatus, computer equipment, computer-readable storage medium, and computer program product that can improve the efficiency of gene sequencing in order to address the above-mentioned technical problems.

[0007] This application provides a trajectory line reconstruction method, including:

[0008] The first, second, and third images of successfully registered data are acquired, and the fourth image of unregistered data is acquired. The first and second images are obtained by the first camera taking two rounds of pictures of the biochip, and the third and fourth images are obtained by the second camera taking two rounds of pictures of the biochip. There are multiple trajectory lines distributed on the biochip. Registration includes identifying multiple trajectory lines from the images. The successfully registered image contains multiple trajectory lines, and the unregistered image does not contain multiple trajectory lines.

[0009] Obtain the first trajectory equation in the first image, the second trajectory equation in the second image, and the third trajectory equation in the third image;

[0010] The third trajectory equation is obtained by transforming the first and second trajectory equations;

[0011] The trajectory line is reconstructed on the fourth image based on the fourth trajectory equation.

[0012] This application also provides a trajectory line reconstruction device, comprising:

[0013] The image acquisition module is used to acquire a first image, a second image, and a third image that have been successfully registered, and to acquire a fourth image that has failed to register. The first and second images are obtained by the first camera taking two rounds of pictures of the biochip, and the third and fourth images are obtained by the second camera taking two rounds of pictures of the biochip. The biochip has multiple trajectory lines distributed on it. Registration includes identifying multiple trajectory lines from the images. The successfully registered images contain multiple trajectory lines, while the images that have failed to register do not contain multiple trajectory lines.

[0014] The equation acquisition module is used to acquire the first trajectory equation of the trajectory line in the first image, the second trajectory equation in the second image, and the third trajectory equation in the third image.

[0015] The equation transformation module is used to transform the third trajectory equation based on the first and second trajectory equations to obtain the fourth trajectory equation.

[0016] The trajectory reconstruction module is used to reconstruct the trajectory line on the fourth image based on the fourth trajectory equation.

[0017] A computer device includes a memory and a processor, the memory storing a computer program, and the processor executing the computer program to implement the steps of the above-described trajectory reconstruction method.

[0018] A computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of the above-described trajectory reconstruction method.

[0019] A computer program product includes a computer program that, when executed by a processor, implements the steps of the above-described trajectory reconstruction method.

[0020] The aforementioned trajectory line reconstruction method, apparatus, computer equipment, computer-readable storage medium, and computer program product acquire a first image, a second image, and a third image that have been successfully registered, and acquire a fourth image that has failed to register. The first and second images are obtained by a first camera photographing the biochip, and the third and fourth images are obtained by a second camera photographing the biochip. The first and third images are obtained in the same round of photography, and the second and fourth images are obtained in the same round of photography. The relative positions of the first and second cameras remain constant. Multiple trajectory lines are distributed on the biochip. Registration is used to identify the trajectory lines in the images. The method acquires a first trajectory equation in the first image, a second trajectory equation in the second image, and a third trajectory equation in the third image. The method transforms the third trajectory equation based on the first and second trajectory equations to obtain a fourth trajectory equation. The method reconstructs the trajectory line on the fourth image based on the fourth trajectory equation. In this way, the trajectory equation of the trajectory line in the failed registration image can be inferred from the trajectory equation of the trajectory line in the successfully registered image, based on the other three successfully registered images. Then, the trajectory line can be reconstructed in the failed registration image, avoiding the inability to identify the trajectory line and thus preventing the subsequent sequencing process from being impossible, thereby improving the efficiency of gene sequencing. Attached Figure Description

[0021] Figure 1 This is a flowchart illustrating a trajectory reconstruction method in one embodiment;

[0022] Figure 2 This is a schematic diagram of the registration result in one embodiment;

[0023] Figure 3 This is a schematic diagram of DNA nanosphere coordinate reconstruction in one embodiment;

[0024] Figure 4 This is a flowchart illustrating a real-world application scenario in one embodiment;

[0025] Figure 5 This is a schematic diagram of the experimental results in one embodiment;

[0026] Figure 6 This is a schematic diagram of the experimental results in another embodiment;

[0027] Figure 7 This is a structural block diagram of a trajectory line reconstruction device in one embodiment;

[0028] Figure 8 This is another structural block diagram of the trajectory line reconstruction device in one embodiment;

[0029] Figure 9 This is an internal structural diagram of a computer device in one embodiment;

[0030] Figure 10 This is a diagram of the internal structure of a computer device in another embodiment. Detailed Implementation

[0031] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of this application and are not intended to be used in the overall description of this application. The use of terms like "first" and "second" is merely for distinguishing technical features and should not be construed as indicating or implying relative importance, the number of indicated technical features, or the sequential relationship between indicated technical features.

[0032] In the description of this application, unless otherwise expressly defined, terms such as "setup," "installation," and "connection" should be interpreted broadly, and those skilled in the art can reasonably determine the specific meaning of the above terms in this application in conjunction with the specific content of the technical solution.

[0033] DNA sequencing technologies include first-generation DNA sequencing, represented by Sanger sequencing, and second-generation DNA sequencing technologies, represented by Illumina Hiseq 2500, Roche 454, ABI Solid, and BGISEQ-500. In 1977, Sanger invented the dideoxy terminator sequencing method, becoming a representative of first-generation sequencing technology. In 2001, based on first-generation sequencing technology, the draft human genome was completed. Sanger sequencing is characterized by its simple experimental operation, intuitive and accurate results, and short experimental cycle, and has wide applications in clinical gene mutation detection and genotyping, where the timeliness of test results is crucial. However, the disadvantages of Sanger sequencing are low throughput and high cost, which limits its application in large-scale gene sequencing. To overcome the shortcomings of Sanger sequencing, second-generation sequencing technology emerged. Compared with first-generation DNA sequencing technology, second-generation DNA sequencing technology features high sequencing throughput, low cost, high automation, and single-molecule sequencing capabilities. Taking the HiSeq 2500V2 sequencing technology as an example, one experimental procedure can generate approximately 10-200G of data. The average sequencing cost per base is less than 1 / 1000 of the cost of Sanger sequencing, and the obtained sequencing results can be directly processed and analyzed by computer. Therefore, second-generation DNA sequencing technology is very suitable for large-scale sequencing.

[0034] Over the past decade, second-generation DNA sequencing technology has gradually grown from an emerging technology to a mainstream sequencing method and has become an important detection tool in the clinical field, playing an increasingly important role in the prevention and control of infectious diseases, the diagnosis of genetic diseases, and non-invasive prenatal screening.

[0035] Microscopic imaging systems are widely used in second-generation DNA sequencing technology. During gene sequencing, fluorescence imaging of four bases on a biochip is required: adenine (A), thymine (T), cytosine (C), and guanine (G). Multi-channel imaging (such as four-channel or two-channel imaging) is typically used, and then the images obtained from each channel are registered using algorithms to match the base positions in different images, thereby enabling the determination of the DNA base sequence. To distinguish the four bases (i.e., the four fluorescence bands), gene sequencing optical systems need to use multi-channel imaging, commonly four-channel or two-channel imaging systems, with each channel consisting of a lens, filter, and camera.

[0036] Taking the representative CollMPS sequencing technology as an example, its basic principle is as follows: During the sequencing process, dNTPs with cleavable groups (called Cold dNTPs) are added to the sequencing strand under the action of DNA polymerase; fluorescently labeled antibodies can specifically recognize the four bases of Cold dNTPs and bind specifically to them; then a high-resolution imaging system collects the light signal, and the sequence to be tested can be obtained after the light signal is digitally processed.

[0037] Depending on the combination method, the pairing of imaging and optical systems can generate various application scenarios, including: 2C2I (2 cameras - 2 images); 4C4I (4 cameras - 4 images); and 2C4I (2 cameras - 4 images, requiring two rounds of shooting each time). The 2C4I mode can further improve the sequencing performance of the 2C2I system and reduce the cost and maintenance difficulty of the 4C4I system. In this mode, two cameras obtain four images through two rounds of shooting, meaning each camera captures two images.

[0038] Image-based base recognition algorithms first need to locate the position coordinates of each DNB on the image; this process is called "registration." Registration relies on pattern features or template features. The registration process is based on track line template features, where track lines appear as low-grayscale values ​​and are close to straight lines on the image. Each type of biochip corresponds to a track line template definition. Taking a single field of view (FOV, where each image corresponds to one shot) as an example, the distribution (distance interval) of track line positions in both the horizontal and vertical directions follows a uniform rule.

[0039] The registration process involves first identifying all track lines in the image along two directions, such as horizontal and vertical, and then comparing them with a template. Assuming there are 9 track lines in each direction, after finding all track lines, the center pixel coordinates of all DNBs in the current FOV image are derived based on 9×9=81 intersection points and the arrangement rules of DNBs (DNB distance interval, i.e., pitch, and distribution shape, such as square or triangular distribution). Due to distortion caused by the optical imaging system, a distortion matrix needs to be calculated based on the coordinates of the 81 intersection points to make more accurate corrections to the DNB coordinate calculations.

[0040] Image-based base identification algorithms first need to locate the coordinates of each dnb (digital noun) on the image. Determining the dnb coordinates requires identifying all track lines. Track line identification is based on grayscale contrast; that is, the grayscale of the track region is lower than that of the sequencing region (the region outside the track lines on the field of view; the sequencing region has a high density of dnbs).

[0041] In certain scenarios, such as when the proportion of a certain base in the sequence is almost zero, almost no dnb (digital nuclei) will appear to glow in the corresponding image taken at a certain moment. This is reflected in the image as a very low grayscale of the entire field of view (FOV), making it impossible to distinguish between the track region and the sequencing region. In other words, the track line cannot be identified, the coordinates of the dnb pixels on the FOV cannot be correctly located, and the brightness or intensity of each dnb cannot be extracted. As a result, base identification and classification cannot be completed.

[0042] According to the current process and algorithm, the FOV in the above scenarios is directly discarded (output result is NaN). In severe cases, the NaN ratio is so high that even a single sequencing result cannot be used.

[0043] Currently, there is no suitable solution to handle this situation. For FOV images where track lines cannot be identified, the FOV directly outputs NaN, rendering the current data invalid. For results with a high proportion of NaN, the sequencing output data may even become unusable, severely impacting sequencing efficiency.

[0044] This application provides a method, apparatus, computer device, computer-readable storage medium, and computer program product for reconstructing track lines, which can reconstruct track lines in images, avoiding the inability to identify track lines and thus preventing subsequent sequencing processes from being impossible, thereby improving the efficiency of gene sequencing.

[0045] Please see Figure 1 , Figure 1 This is a flowchart illustrating a trajectory reconstruction method in one embodiment. In one embodiment, such as... Figure 1As shown, a trajectory line reconstruction method is provided. It is understood that this method can be applied to a terminal, a server, or a system including both a terminal and a server, and is implemented through interaction between the terminal and the server. In this embodiment, the method includes the following steps:

[0046] Step S102: Obtain the first, second, and third images that were successfully registered, and obtain the fourth image that failed to be registered.

[0047] The first and second images are obtained by the first camera taking pictures of the biochip, and the third and fourth images are obtained by the second camera taking pictures of the biochip. The first and third images are obtained in the same round of shooting, and the second and fourth images are obtained in the same round of shooting. The relative positions of the first and second cameras remain constant. Multiple trajectory lines are distributed on the biochip, and registration is used to identify the trajectory lines in the images.

[0048] Optionally, the biochip is an array of chips carrying multiple DNA nanospheres. Before sequencing, the DNA fragment to be sequenced is circularized into single-stranded circular DNA. Using rolling circle amplification (RCA) technology, the circular single-stranded DNA is converted into multiple copies of single-stranded DNA linked end-to-end, which then fold freely into nanosphere structures in solution, i.e., DNA nanospheres (DNBs). Due to the mutual repulsion of their own negative charges, DNBs reduce the interactions between individual DNBs, making them independent. Each array site contains at least several hundred copies of DNB; these copies aggregate to generate a strong signal, thereby allowing identification of the base classes of the DNB.

[0049] DNA nanospheres are precisely and individually loaded onto array sites on a biochip. The biochip can be of any version. Taking version V1 as an example, the biochip size is approximately 75mm x 25mm. The total number of fields of view (FOV, the range that can be observed in a single operation by the objective lens of the micro-imaging optical system) included in the biochip is the total number of FOVs, for example, 576 FOVs. This is for illustrative purposes only and should not be construed as a limitation of this application.

[0050] Then, the sequencing template and sequencing reagents are pumped in. The pumped-in sequencing template hybridizes complementaryly with the DNB adapters on the biochip. Catalyzed by DNA polymerase, the sequencing template binds to fluorescently labeled probes in the sequencing reagents, achieving DNB labeling. Introducing substrate excites the labeled molecules to emit light. The light signals emitted by different labeled molecules are collected by the instrument's camera, processed, and converted into digital signals, which are then transmitted to a computer for further processing, ultimately achieving base recognition and gene sequencing. The fundamental advantages of low error accumulation from rolling circle replication amplification and high signal density from the arrayed chip significantly improve sequencing accuracy.

[0051] In one embodiment, the biochip has track lines distributed parallel to each other in different directions. The track lines in different directions intersect to form multiple blocks, and the shape of each block can be rectangular, triangular, etc. Each block has several array spots evenly distributed on it. The array spots can adsorb DNA nanospheres. For example, one DNA nanosphere can be loaded on one spot. The DNA nanospheres can be amplification products including DNA fragments.

[0052] Because biochips have trajectory lines distributed on them, an image containing these trajectory lines can be obtained by photographing the biochip. Since the sequencing regions in the field of view (FOV) other than the trajectory lines contain a high density of DNA nanospheres, which react and emit light upon the introduction of substrate, while the trajectory lines do not contain DNA nanospheres and do not emit light upon substrate introduction, the trajectory lines in the image can be identified during image registration by extracting the brightness of each pixel. For example, the brightness of a pixel can be represented by its grayscale value. For instance, based on grayscale contrast, locations in the image with significantly lower grayscale values ​​than other areas can be identified as trajectory lines.

[0053] However, in some scenarios, such as when the proportion of a certain base in the sequence is almost zero, almost no DNA nanospheres will show a luminescent state in the corresponding image taken at a certain moment. This is reflected in the image as a very low grayscale value for the entire FOV, making it impossible to distinguish the trajectory line from the sequencing region, i.e., the trajectory line cannot be identified, and therefore the pixel coordinates of the DNA nanospheres on that FOV cannot be correctly located, and the brightness or intensity of each DNA nanosphere cannot be extracted.

[0054] In one embodiment, the first and second cameras are microscope cameras, and the first, second, third, and fourth images can be fluorescence images obtained by continuously photographing the biochip using the microscope cameras. During sequencing, fluorescence images are obtained by photographing the biochip using microscope cameras. One microscope camera can photograph a single field of view to obtain fluorescence images of the same field of view, while different microscope cameras can photograph different fields of view to obtain fluorescence images of different fields of view. The field of view of a microscope camera is relatively small, and hundreds of field-of-view images can be captured for a single biochip. The first, second, third, and fourth images can be consecutive fluorescence images selected from the image queues of the first and second cameras, respectively. For example, the first and second images are fluorescence images obtained by continuously photographing the same field of view using the first camera, and the third and fourth images are fluorescence images obtained by continuously photographing the same field of view using the second camera.

[0055] For example, the first, second, and third images are successfully registered images, where the trajectory lines are clearly visible, such as... Figure 2 As shown in (a); while the fourth image is a registration failure image, in which the trajectory lines are blurred and invisible, as shown in (a). Figure 2 As shown in (b). In this embodiment of the application, the first, second and third images that were successfully registered are used to reconstruct the trajectory lines of the fourth image that failed to be registered, so that the trajectory lines can also be clearly seen in the fourth image, avoiding the difficulty of continuing the subsequent sequencing process due to the inability to identify the trajectory lines.

[0056] It should be noted that the first, second, third, and fourth images in this application are merely for distinguishing four images and do not constitute a limitation on the shooting rounds or source cameras of the first, second, third, and fourth images. They can be four images acquired by two cameras in 2C4I dual-channel mode. Furthermore, there are no restrictions on images that failed to register. Those skilled in the art will understand that using the fourth image as an example of failed registration is merely for illustrative purposes, and the failed registration image can be any of these images. Image a can be used as the fourth image for trajectory line reconstruction in this application if it satisfies the following conditions: image b (successfully registered) from the same camera as image a, image c (successfully registered) from another camera acquired in the same shooting round as image b from the same camera, and image d (successfully registered) from the other camera acquired in the same shooting round as image a. In other words, when the other three images are successfully registered, any one of the first, second, third, and fourth images can be used as the fourth image for trajectory line reconstruction in this application.

[0057] In one embodiment, the relative positions of the first camera and the second camera remain constant during the image capture process. For example, the first camera and the second camera can be two cameras fixed on the same gene sequencer.

[0058] Step S104: Obtain the first trajectory equation in the first image, the second trajectory equation in the second image, and the third trajectory equation in the third image.

[0059] By establishing an image coordinate system within the acquired images, each trajectory line in the image will have its corresponding trajectory equation. The trajectory equation reflects the position of the trajectory line in the image. For each successfully registered first, second, and third image, the trajectory lines in the images have been successfully identified, and the first trajectory equation in the first image, the second trajectory equation in the second image, and the third trajectory equation in the third image can be obtained.

[0060] In the coordinate system of a biochip, or in an image coordinate system free from camera distortion, the trajectory equation of a line is a linear equation. Taking a coordinate system containing x and y axes as an example, the trajectory equation of a line in a certain direction in a biochip can be expressed as a linear equation in two variables: y = k1x + c1, where k1 and c1 are constants, and k1 and c1 are different for different trajectory lines. If the trajectory lines are distributed parallel to each other along the x-axis, the trajectory equation can be further expressed as a linear equation in one variable: y = k2, where k2 is a constant, and k2 is different for different trajectory lines.

[0061] When camera distortion is considered, the trajectory lines in the captured image are slightly curved parabolic in shape, and the equation of the trajectory line can be a quadratic equation or a cubic equation in two variables. For example, assuming the image coordinate system includes x-axis and y-axis, the equation of the trajectory line in a certain direction in the image can be expressed as a quadratic equation in two variables: y = k³x. 2 +k4x+c2, where k3, k4, and c2 are constants, and k3, k4, and c2 are different for different trajectories; the trajectory equation of the trajectory in the other direction can be expressed as a quadratic equation in two variables: x=k5y 2 +k6y+c3, where k5, k6, and c3 are constants, and k5, k6, and c3 are different for different trajectories. For example, the equation of a trajectory line in a certain direction in an image can be expressed as a cubic equation in two variables: y = k7x 3 +k8x 2 +k9x+c4, where k7, k8, k9, and c4 are constants, and k7, k8, k9, and c4 are different for different trajectories; the trajectory equation for the trajectory in the other direction can be expressed as a cubic equation in two variables x= k 10 y 3 +k 11 y 2 +k 12y+c5, where k 10 k 11 k 12 c5 is a constant, and k represents different trajectories. 10 k 11 k 12 C5 is different.

[0062] The trajectory equation of the trajectory line in the first image is the first trajectory equation, the trajectory equation of the trajectory line in the second image is the second trajectory equation, and the trajectory equation of the trajectory line in the third image is the third trajectory equation.

[0063] Optionally, all the first trajectory equations in the first image can form a first trajectory equation set, all the second trajectory equations in the second image can form a second trajectory equation set, all the third trajectory equations in the third image can form a third trajectory equation set, and all the fourth trajectory equations in the fourth image can form a fourth trajectory equation set. When obtaining the trajectory equation of a trajectory line in a certain image, one can first obtain the set of trajectory equations in that image, and then obtain the trajectory equation of the trajectory line from it.

[0064] It should be noted that because the trajectory lines on the biochip are arranged in parallel, the equations of the trajectory lines in the same direction in different images have only minor differences, such as only the constant term is different. For the first, second, and third images that were successfully registered, the trajectory equations of the trajectory lines can be directly obtained. However, for the fourth image that was successfully registered, the trajectory lines are blurry, and the trajectory equations cannot be directly obtained.

[0065] Step S106: Transform the third trajectory equation according to the first trajectory equation and the second trajectory equation to obtain the fourth trajectory equation.

[0066] Using the fourth trajectory equation in the fourth image as the object of calculation, the third trajectory equation is transformed based on the first and second trajectory equations to obtain the fourth trajectory equation.

[0067] In this embodiment, the first and second images are obtained by the first camera taking pictures of the biochip, and the third and fourth images are obtained by the second camera taking pictures of the biochip. The first and third images are obtained in the same round of shooting, and the second and fourth images are obtained in the same round of shooting. The relative positions of the first and second cameras remain constant.

[0068] It can be seen that the third and fourth images were acquired by the same camera, and the lens distortion of the third and fourth images is the same. Therefore, the curvature of the same trajectory line is the same in the third and fourth images. The fourth trajectory line in the fourth image can be obtained by transforming the third trajectory equation of the trajectory line in the third image.

[0069] Furthermore, during the sequence of taking the first and third images, followed by the second and fourth images, the biochip may experience slight movement, resulting in a minor shift in the image capture position. Since the relative positions of the first and second cameras remain constant, the transformation from the first image to the second image is directly correlated with the transformation from the third image to the fourth image. Therefore, by referring to the changes in the first trajectory equation to the second trajectory equation, the third trajectory equation can be transformed to obtain the fourth trajectory equation.

[0070] Optionally, the difference between the second trajectory equation and the first trajectory equation can be obtained, and this difference can be added to the third trajectory equation to obtain the fourth trajectory equation, so that the difference between the fourth trajectory equation and the third trajectory equation is equal to the difference between the second trajectory equation and the first trajectory equation, ensuring that the transformation from the third trajectory equation to the fourth trajectory equation is the same as the transformation from the first trajectory equation to the second trajectory equation.

[0071] Optionally, different cameras can take pictures for different fields of view (FOVs). For example, the first and second images are obtained by the first camera taking pictures for the first FOV, and the third and fourth images are obtained by the second camera taking pictures for the second FOV. During two rounds of taking pictures of the same field of view with the same camera, various reasons may cause slight movements of the camera or biochip, resulting in a slight shift in the image position and changing the trajectory equation of the trajectory line in different images. For example, from acquiring the first image to acquiring the second image, the trajectory equation changes from the first trajectory equation of the first image to the second trajectory equation of the second image. Since the relative positions of the first and second cameras remain constant, the image position of the second camera also shifts slightly from acquiring the third image to acquiring the fourth image. When transforming the third trajectory equation based on the first and second trajectory equations to obtain the fourth trajectory equation, the positional offset of the second image relative to the first image can be obtained. The third trajectory equation can then be transformed based on this positional offset to obtain the fourth trajectory equation. For example, adding this positional offset to the third trajectory equation yields the fourth trajectory equation.

[0072] Optionally, when transforming the third trajectory equation according to the first and second trajectory equations to obtain the fourth trajectory equation, the photographing displacement of the two rounds of photography can also be determined according to the first and second trajectory equations. The photographing displacement is the displacement of the photographing position in the two photographs, such as determining the photographing displacement of the second image relative to the photographing position of the first image according to the first and second trajectory equations. When transforming the third trajectory equation, this photographing displacement is added to the third trajectory equation, and the sum of the third trajectory equation and the photographing displacement is used as the fourth trajectory equation.

[0073] Step S108: Reconstruct the trajectory line on the fourth image according to the fourth trajectory equation.

[0074] Since the fourth trajectory equation describes the position of the trajectory line in the image coordinate system of the fourth image, the trajectory line can be reconstructed on the fourth image based on the fourth trajectory equation. This reconstruction may include labeling or drawing each trajectory line in the fourth image. For example, please refer to... Figure 2 The fourth image after reconstructing the trajectory line will be generated by Figure 2 (b) The blurred trajectory line becomes Figure 2 (a) shows the clear outline of the trajectory line.

[0075] Computer equipment can successfully identify the trajectory line from the fourth image after reconstruction, which allows for subsequent denoising, grayscale extraction and correction processing, facilitating gene sequencing.

[0076] The aforementioned trajectory reconstruction method acquires three successfully registered images (first, second, and third) and one unregistered image (fourth). The first and second images are obtained by photographing the biochip with a first camera, while the third and fourth images are obtained by photographing the biochip with a second camera. The first and third images are acquired in the same round of photography, as are the second and fourth images. The relative positions of the first and second cameras remain constant. Multiple trajectory lines are distributed on the biochip, and registration is used to identify these trajectory lines in the images. Thus, based on the other three successfully registered images from the two rounds of photography, the trajectory equations of the trajectory lines in the successfully registered images can be inferred to deduce the trajectory equations in the unregistered images. This allows for the reconstruction of the trajectory lines in the unregistered images, avoiding the inability to identify trajectory lines and preventing subsequent sequencing processes from being impossible, thereby improving the efficiency of gene sequencing.

[0077] In one embodiment, transforming the third trajectory equation based on the first and second trajectory equations to obtain the fourth trajectory equation includes:

[0078] The photographic displacement is determined based on the first and second trajectory equations; the third trajectory equation is then transformed based on the photographic displacement to obtain the fourth trajectory equation.

[0079] Among them, the shooting displacement is the offset of the shooting position when taking two rounds of shots.

[0080] Since the third and fourth images were acquired by the same camera, the lens distortion in the third and fourth images is the same. Therefore, the curvature of the same trajectory line is the same in the third and fourth images. The fourth trajectory line in the fourth image can be obtained by transforming the third trajectory equation of the trajectory line in the third image.

[0081] Furthermore, between the rounds of capturing the first and third images and the rounds of capturing the second and fourth images, the biochip may experience slight movement, resulting in a minor shift in the image capture position. Since the relative positions of the first and second cameras remain constant, the same position shift occurs between acquiring the third and fourth images as the position shift occurs between acquiring the first and second images. Therefore, the image capture displacement can be determined based on the first and second trajectory equations. This displacement can then be transferred to the two rounds of capturing images from the other camera, and the third trajectory equation can be transformed based on this displacement to obtain the fourth trajectory equation.

[0082] Here, the image displacement is an n-dimensional vector with magnitude and direction, where n is a positive integer. The magnitude of the image displacement represents the overall offset of the image position between the two rounds of shooting. The magnitude of each element in the image displacement represents the offset of the image position along each coordinate axis during the two rounds of shooting. The sign of each element in the image displacement indicates the direction of the offset of the image position along each coordinate axis during the two rounds of shooting. Specifically, n can be 2.

[0083] For example, when the first image is obtained by performing the first round of photography and the second image is obtained by performing the second round of photography, the difference between the second trajectory equation and the first trajectory equation can be used as the photography displacement between the two rounds of photography; when the second image is obtained by performing the first round of photography and the first image is obtained by performing the second round of photography, the difference between the first trajectory equation and the second trajectory equation can be used as the photography displacement between the two rounds of photography.

[0084] In one embodiment, the third trajectory equation is transformed based on the photographed displacement to obtain a fourth trajectory equation, including:

[0085] The third trajectory equation of the second trajectory line is transformed based on the first displacement to obtain the fourth trajectory equation of the second trajectory line; the third trajectory equation of the first trajectory line is transformed based on the second displacement to obtain the fourth trajectory equation of the first trajectory line.

[0086] Optionally, the multiple trajectory lines include multiple first trajectory lines parallel to each other in a first direction and multiple second trajectory lines parallel to each other in a second direction. The first direction can be horizontal, and the second direction can be vertical. The first trajectory lines can be parallel to each other in the horizontal direction, and the second trajectory lines can be parallel to each other in the vertical direction. Adjacent parallel trajectory lines in the first direction and parallel trajectory lines in the second direction form a block. Several array spots are uniformly distributed on the block, and each spot can hold a DNA nanosphere.

[0087] With the horizontal direction as the x-axis and the vertical direction as the y-axis, both the biochip coordinate system and the image coordinate system are xy coordinate systems.

[0088] For example, the image displacement can be a first displacement in the first direction. For instance, first displacement + l1 represents a movement of l1 along the positive x-axis. Then, the difference between the second trajectory equation and the first trajectory equation of the second trajectory line distributed parallel to the y-axis is a constant l1. Based on the first displacement l1, the third trajectory equation of the second trajectory line is transformed to x = k5y. 2 Adding +k6y+c3 to the first displacement + l1, we obtain the fourth trajectory equation of the second trajectory line: x=k5y 2 +k6y+c3+ l1.

[0089] For example, the image displacement can be a second displacement in the second direction. For instance, second displacement + l2 represents a movement of l2 along the positive y-axis. Then, the difference between the second trajectory equation and the first trajectory equation of the first trajectory line distributed along the x-direction is a constant l2. The third trajectory equation of the first trajectory line is transformed according to the second displacement l2, resulting in the third trajectory equation y = k3x. 2 Adding +k4x+c2 to the second displacement +l2, we obtain the fourth trajectory equation of the first trajectory line: y=k3x 2 +k4x+c2+l2.

[0090] In one embodiment, the image displacement is a two-dimensional vector (+l1, +l2), which includes both the first displacement +l1 in the first direction and the second displacement +l2 in the second direction. Then, the third trajectory equation of the second trajectory line is transformed based on the first displacement l1, resulting in the third trajectory equation x=k5y. 2 Adding +k6y+c3 to the first displacement + l1, we obtain the fourth trajectory equation of the second trajectory line: x=k5y 2 +k6y+c3+ l1, based on the second displacement l2, transform the third trajectory equation of the first trajectory line to y=k3x 2Adding +k4x+c2 to the second displacement +l2, we obtain the fourth trajectory equation of the first trajectory line: y=k3x 2 +k4x+c2+ l2.

[0091] In the above embodiments, the transformation from the third trajectory equation to the fourth trajectory equation is achieved based on the offset of the shooting position during the two rounds of shooting, cleverly utilizing the characteristic that the relative positions of the two cameras remain constant. The dual-channel four-image method itself can reconstruct images that have failed registration, without requiring the input of other complex data. This reduces the amount of data processing, alleviates the processing pressure on computer equipment, and speeds up the processing of registration failures. This is particularly significant for current gene sequencers with two or more fixed microscope cameras.

[0092] In one embodiment, multiple first trajectory lines and multiple second trajectory lines intersect to form multiple trajectory intersection points.

[0093] In one embodiment, obtaining the third trajectory equation of the trajectory line in the third image includes:

[0094] Determine the pixel coordinates of multiple trajectory intersection points on the third image; for each first trajectory line, determine all trajectory intersection points on the first trajectory line, and fit the third trajectory equation of the first trajectory line on the third image based on the pixel coordinates of all trajectory intersection points on the first trajectory line on the third image; for each second trajectory line, determine all trajectory intersection points on the second trajectory line, and fit the third trajectory equation of the second trajectory line on the third image based on the pixel coordinates of all trajectory intersection points on the second trajectory line on the third image.

[0095] When obtaining the trajectory equation of a trajectory line in the third image, the third trajectory equation of a certain trajectory line can be determined based on the trajectory coordinates of the intersection points formed by the intersection of trajectory lines distributed in different directions in the third image. It is understandable that each trajectory intersection point is formed by the intersection of trajectory lines; therefore, each trajectory line contains multiple trajectory intersection points, and which trajectory intersection points are contained in each trajectory line is known. Based on the pixel coordinates of the trajectory intersection points contained in the trajectory line in the third image, the third trajectory equation of that trajectory line can be fitted.

[0096] Furthermore, for a first trajectory line distributed along the first direction, all trajectory intersection points on the first trajectory line can be determined, and a third trajectory equation for the first trajectory line on the third image can be fitted based on the pixel coordinates of all trajectory intersection points on the first trajectory line in the third image; for a second trajectory line distributed along the second direction, all trajectory intersection points on the second trajectory line can be determined, and a third trajectory equation for the second trajectory line on the third image can be fitted based on the pixel coordinates of all trajectory intersection points on the second trajectory line in the third image.

[0097] It should be noted that the method for obtaining the third trajectory equation of a trajectory line in a third image provided in this application embodiment is also applicable to obtaining the first trajectory equation of a trajectory line in a first image and the second trajectory equation in a second image. Related methods can be transferred and applied to related images, and will not be elaborated further here.

[0098] In the above embodiments, the trajectory equation is fitted using the intersection points of the trajectories. Since the trajectory intersection points are formed by the intersection of each trajectory line, the trajectory intersection points can ensure that the intersection points are on the trajectory lines. Fitting the trajectory equation of the trajectory line based on the trajectory intersection points on each trajectory line can ensure that the fitted trajectory equation is accurate enough.

[0099] In one embodiment, after multiple DNA nanospheres are supported on a biochip and the trajectory lines are reconstructed on a fourth image according to a fourth trajectory equation, the method further includes:

[0100] The coordinates of the DNA nanospheres on the fourth image are determined based on multiple trajectory lines.

[0101] Because the sites on the biochip are arranged in an array, the DNA nanospheres carried on the biochip are uniformly distributed. The DNA nanospheres in the image can also be considered to be approximately uniformly distributed. Furthermore, the coordinates of the DNA nanospheres in the fourth image can be reconstructed based on multiple trajectory lines on the fourth image.

[0102] For example, the DNA nanospheres on the biochip are arranged in a grid-like array. Coordinate reconstruction is performed on the DNA nanospheres in a certain block of the fourth image to determine the coordinates of each DNA nanosphere on the fourth image. The positions of each DNA nanosphere in the block are then marked according to these coordinates. Figure 3 As shown.

[0103] Optionally, determining the coordinates of the DNA nanospheres on the fourth image based on multiple trajectory lines may include: determining multiple blocks on the biochip based on two adjacent first trajectory lines and two adjacent second trajectory lines; determining the target block where the DNA nanospheres are located based on the location of the DNA nanospheres, and determining the intersection point of the target trajectories surrounding the target block; obtaining the coordinates of the intersection point of the target trajectories on the fourth image; and determining the coordinates of the DNA nanospheres on the fourth image based on the coordinates of the intersection point of the target trajectories on the fourth image.

[0104] For example, the block is small enough relative to the biochip, and the DNA nanospheres within it can be considered uniformly distributed. The arrangement data of the DNA nanospheres in the target block is determined based on the biochip. This arrangement data could include, for example, the number of rows and columns of DNA nanospheres in the horizontal and vertical directions. Based on this arrangement data, the distribution intervals of the DNA nanospheres in the horizontal and vertical directions of the target block are determined. The intersection point of the target trajectory can be the intersection point of the starting trajectory, such as using the intersection point in the upper left corner as the starting trajectory intersection point. The row and column number of each DNA nanosphere is determined based on its number. Combining the horizontal and vertical distribution intervals with the coordinates of the starting trajectory intersection point, the coordinates of the DNA nanosphere are obtained.

[0105] Optionally, when determining the coordinates of the DNA nanospheres on the fourth image based on the coordinates of the intersection point of the target trajectory on the fourth image, the arrangement spacing of the DNA nanospheres on the biochip can be obtained, including a first spacing in the first direction and a second spacing in the second direction; the coordinates of the DNA nanospheres on the fourth image are determined based on the first spacing, the second spacing and the coordinates of the intersection point of the target trajectory on the fourth image.

[0106] In one embodiment, determining the coordinates of the DNA nanospheres on the fourth image based on multiple trajectory lines includes:

[0107] Multiple blocks on the biochip are determined based on every two adjacent first trajectory lines and every two adjacent second trajectory lines; the target block where the DNA nanosphere is located is determined based on the location of the DNA nanosphere, as well as the two first trajectory lines and two second trajectory lines corresponding to the target block; the coordinates of the DNA nanosphere on the fourth image are determined based on the fourth trajectory equations of the two first trajectory lines and the two second trajectory lines, and the distances from the DNA nanosphere to the two first trajectory lines and the two second trajectory lines.

[0108] Taking a biochip containing first trajectory lines parallel to a first direction and second trajectory lines parallel to a second direction as an example, each pair of adjacent first trajectory lines and each pair of adjacent second trajectory lines forms a block. During coordinate reconstruction, coordinate reconstruction can be performed block by block. When reconstructing the coordinates of DNA nanospheres in a certain block, that block is designated as the target block, and the two adjacent first trajectory lines and two adjacent second trajectory lines enclosing the target block are taken as the two first trajectory lines and two second trajectory lines corresponding to the target block.

[0109] In one embodiment, determining the coordinates of the DNA nanosphere on the fourth image based on the fourth trajectory equations of the two first trajectory lines and the two second trajectory lines, and the distances from the DNA nanosphere to the two first trajectory lines and the two second trajectory lines, includes: determining the first weights corresponding to the two first trajectory lines based on the distances from the DNA nanosphere to the two first trajectory lines; performing a weighted summation of the fourth trajectory equations of the two first trajectory lines based on their respective first weights to obtain a first positioning equation for the DNA nanosphere in a first direction; determining the second weights corresponding to the two second trajectory lines based on the distances from the DNA nanosphere to the two second trajectory lines; performing a weighted summation of the fourth trajectory equations of the two second trajectory lines based on their respective second weights to obtain a second positioning equation for the DNA nanosphere in a second direction; and combining the first positioning equation and the second positioning equation to solve for the coordinates of the DNA nanosphere.

[0110] Taking the first direction as the horizontal direction (x-direction) and the second direction as the vertical direction (y-direction) as an example, the first positioning equation is the fitting equation for the lines formed by all DNA nanospheres extending along the x-direction in the fourth image, and the second positioning equation is the fitting equation for the lines formed by all DNA nanospheres extending along the y-direction in the fourth image. The combined solution of the first and second positioning equations is the intersection of the two lines, which is also the location of the DNA nanosphere.

[0111] For example, in the target block, a DNA nanosphere is located at a distance d1 from the first trajectory line 1, d2 from the first trajectory line 2, d3 from the second trajectory line 1, and d4 from the second trajectory line 2 on the biochip. The fourth trajectory equation of the first trajectory line 1 is y1, the fourth trajectory equation of the first trajectory line 2 is y2, the fourth trajectory equation of the second trajectory line 1 is x1, and the fourth trajectory equation of the second trajectory line 2 is x2. Then, the first positioning equation can be obtained as follows: The first positioning equation is obtained as follows: .

[0112] That is, the first weight corresponding to the first trajectory line is inversely proportional to the distance from the DNA nanosphere to the first trajectory line. The closer the DNA nanosphere is to the first trajectory line, the higher the first weight assigned to the first trajectory line in the weighted calculation, and vice versa. Similarly, the second weight corresponding to the second trajectory line is inversely proportional to the distance from the DNA nanosphere to the second trajectory line. The closer the DNA nanosphere is to the second trajectory line, the higher the second weight assigned to the second trajectory line in the weighted calculation, and vice versa.

[0113] In the above embodiments, weights are assigned based on the distance from the DNA to each trajectory line. The assigned weights are inversely proportional to the distance, ensuring that closer trajectory lines are assigned higher weights. Thus, during weighted calculations, the lines represented by the corresponding location equations (where the DNA nanospheres are located) are closer to trajectory lines with higher weights and have more similar shapes, while they are closer to trajectory lines with lower weights and have less similar shapes. This achieves a gradual decrease in the similarity of the distortion degree between the lines in the block that are closer to each trajectory line and the trajectory line itself, which conforms to the actual situation of the image under lens distortion and ensures the accuracy of DNA nanosphere coordinate reconstruction.

[0114] This application also provides an application scenario; please refer to [link / reference]. Figure 4 The trajectory line reconstruction method described above can be applied to this gene sequencing scenario. An example of this trajectory line reconstruction method in this application scenario is as follows:

[0115] In one cycle (one biochemical cycle of base synthesis), a dual-channel mode was used, with two microscope cameras acquiring two rounds of fluorescence images. In the first round of imaging, camera 1 and camera 2 acquired image 1 and image 3, respectively. In the second round of imaging, camera 1 and camera 2 acquired image 2 and image 4, respectively. Images 1, 2, 3, and 4 were then entered into the image queue.

[0116] The registration thread retrieves images 1, 2, 3, and 4 from the image queue and registers each image separately. After registration, the results are obtained, including successful and unsuccessful registrations. Specifically, image 1 is successfully registered, and registration data X is output; image 2 is successfully registered, and registration data Y is output; image 3 is successfully registered, and registration data Z is output; image 4 fails to register. For successfully registered images, the registration thread outputs the registration data for each image, including the trajectory equations of the trajectory lines in the image and the coordinate data of the DNA nanospheres. For image 4, which failed to register, the current original image of image 4 is directly cached, and the registration data remains blank.

[0117] For successfully registered images 1-3, the image data X of image 1 and the obtained registration data X are input together into the brightness extraction thread X. A brightness extraction operation is performed using the original image of image 1 and the coordinates of each DNA nanosphere in image 1, outputting the original light intensity data of each DNA nanosphere in image 1. Similarly, the image data Y of image 2 and the obtained registration data Y are input together into the brightness extraction thread Y. A brightness extraction operation is performed using the original image of image 2 and the coordinates of each DNA nanosphere in image 2, outputting the original light intensity data of each DNA nanosphere in image 2. Finally, the image data Z of image 3 and the obtained registration data Z are input together into the brightness extraction thread Z. A brightness extraction operation is performed using the original image of image 3 and the coordinates of each DNA nanosphere in image 3, outputting the original light intensity data of each DNA nanosphere in image 3.

[0118] For image 4, which failed to register, the registration data X of image 1, the registration data Y of image 2, and the registration data Z of image 3 are input into the dynamic reconstruction thread. The dynamic reconstruction thread executes the trajectory line reconstruction method of this application to obtain the reconstructed registration data of image 4 based on image 1 and the registration data X, the registration data Y of image 2, and the registration data Z of image 3. The reconstructed registration data of image 4 includes the trajectory equation of the trajectory line in image 4 and the coordinates of the further reconstructed DNA nanospheres. The reconstructed registration data and the image data of image 4 are input together into the dynamic brightness extraction thread to obtain the original light intensity data of each DNA nanosphere in image 4. Based on the original light intensity data of images 1-4, subsequent processing such as brightness correction and base classification can be performed.

[0119] In one embodiment, the experimental results for base recognition without trajectory reconstruction are as follows: Figure 5 As shown in Table 1, the data quality for base identification is as follows.

[0120] Table 1

[0121]

[0122] like Figure 5 As shown, around 150 cycles, the base identification results became inconsistent, and it was impossible to successfully identify each type of base. In Table 1, the quality scores for each category corresponding to read2 were significantly lower, indicating a decrease in the accuracy of base identification.

[0123] In one embodiment, for the same set of original images, after trajectory line reconstruction using the trajectory line reconstruction method of this application, the experimental results of base recognition are as follows: Figure 6 As shown in Table 2, the data quality for base identification is as follows.

[0124] Table 2

[0125]

[0126] like Figure 5 As shown, after trajectory reconstruction using the trajectory reconstruction method of this application, a large amount of invalid data was recovered around cycle 150, and the base identification results returned to correctness, no longer chaotic and disordered. In Table 2, the quality scores corresponding to the read2 category no longer decreased, and even showed a significant improvement. This indicates that the accuracy of base identification was improved after trajectory reconstruction using the trajectory reconstruction method of this application.

[0127] In the above embodiments, images that failed to register are dynamically reconstructed, and brightness is extracted from successfully registered images simultaneously. These two processes can be performed concurrently. Once brightness extraction is complete for successfully registered images, only a short waiting time is required before brightness extraction can be performed on images that failed to register, based on the reconstructed registration data. Compared to performing brightness extraction normally on all successfully registered images, this process takes only a small amount of time, improving gene sequencing accuracy while saving time.

[0128] It should be understood that although the steps in the flowcharts of the above embodiments are shown sequentially according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some steps in the flowcharts of the above embodiments may include multiple steps or multiple stages. These steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these steps or stages is not necessarily sequential, but can be performed alternately or in turn with other steps or at least some of the steps or stages of other steps.

[0129] In one embodiment, such as Figure 7 As shown, a trajectory line reconstruction device is provided. This device can be a software module, a hardware module, or a combination of both integrated into a computer device. Specifically, the device includes: an image acquisition module 701, an equation acquisition module 702, an equation transformation module 703, and a trajectory reconstruction module 704, wherein:

[0130] The image acquisition module 701 is used to acquire a first image, a second image, and a third image that have been successfully registered, and to acquire a fourth image that has failed to be registered. The first and second images are obtained by the first camera taking pictures of the biochip, and the third and fourth images are obtained by the second camera taking pictures of the biochip. The first and third images are obtained in the same round of shooting, and the second and fourth images are obtained in the same round of shooting. The relative positions of the first camera and the second camera remain constant. There are multiple trajectory lines distributed on the biochip, and the registration is used to identify the trajectory lines in the image.

[0131] The equation acquisition module 702 is used to acquire the first trajectory equation of the trajectory line in the first image, the second trajectory equation in the second image, and the third trajectory equation in the third image.

[0132] The equation transformation module 703 is used to transform the third trajectory equation based on the first trajectory equation and the second trajectory equation to obtain the fourth trajectory equation;

[0133] The trajectory reconstruction module 704 is used to reconstruct the trajectory line on the fourth image based on the fourth trajectory equation.

[0134] In one embodiment, when transforming the third trajectory equation according to the first trajectory equation and the second trajectory equation to obtain the fourth trajectory equation, the equation transformation module 703 is further configured to:

[0135] The photographing displacement is determined based on the first trajectory equation and the second trajectory equation. The photographing displacement is the offset of the photographing position during the two rounds of photography.

[0136] The third trajectory equation is transformed based on the photographic displacement to obtain the fourth trajectory equation.

[0137] In one embodiment, the multiple trajectory lines include multiple first trajectory lines parallel to each other in a first direction and multiple second trajectory lines parallel to each other in a second direction. The image displacement includes a first displacement in the first direction and a second displacement in the second direction. When transforming the third trajectory equation based on the image displacement to obtain the fourth trajectory equation, the equation transformation module 703 is further configured to:

[0138] The third trajectory equation of the second trajectory line is transformed based on the first displacement to obtain the fourth trajectory equation of the second trajectory line;

[0139] The third trajectory equation of the first trajectory line is transformed based on the second displacement to obtain the fourth trajectory equation of the first trajectory line.

[0140] In one embodiment, the multiple trajectory lines include multiple first trajectory lines distributed parallel to each other in a first direction and multiple second trajectory lines distributed parallel to each other in a second direction. The multiple first trajectory lines and multiple second trajectory lines intersect to form multiple trajectory intersection points. When obtaining the third trajectory equation of the trajectory lines in the third image, the equation acquisition module 702 is further used for:

[0141] Determine the pixel coordinates of multiple trajectory intersection points on the third image;

[0142] For each first trajectory line, determine all trajectory intersection points on the first trajectory line, and fit the third trajectory equation of the first trajectory line on the third image based on the pixel coordinates of all trajectory intersection points on the first trajectory line in the third image.

[0143] For each second trajectory line, determine all trajectory intersection points on the second trajectory line, and fit the third trajectory equation of the second trajectory line on the third image based on the pixel coordinates of all trajectory intersection points on the second trajectory line in the third image.

[0144] In one embodiment, multiple DNA nanospheres are supported on a biochip. (See [link to relevant documentation]). Figure 8The trajectory line recognition device also includes a coordinate determination module 705, which, after reconstructing the trajectory line on the fourth image according to the fourth trajectory equation, is further used for:

[0145] The coordinate determination module 705 is used to determine the coordinates of the DNA nanospheres on the fourth image based on multiple trajectory lines on the fourth image.

[0146] In one embodiment, the multiple trajectory lines include multiple first trajectory lines parallel to each other in a first direction and multiple second trajectory lines parallel to each other in a second direction. The multiple first trajectory lines and multiple second trajectory lines intersect to form multiple trajectory intersection points. When determining the coordinates of the DNA nanospheres on the fourth image based on the multiple trajectory lines on the fourth image, the coordinate determination module 705 is further configured to:

[0147] Multiple blocks on the biochip are determined based on every two adjacent first trajectory lines and every two adjacent second trajectory lines.

[0148] The target block containing the DNA nanospheres is determined based on their location, as well as the two first trajectory lines and two second trajectory lines corresponding to the target block.

[0149] The coordinates of the DNA nanosphere on the fourth image are determined based on the fourth trajectory equations of the two first trajectory lines and the two second trajectory lines, as well as the distances of the DNA nanosphere to the two first trajectory lines and the two second trajectory lines.

[0150] The aforementioned trajectory reconstruction device acquires a first image, a second image, and a third image that have been successfully registered. The image acquisition module 701 acquires the first image, the second image, and the third image that have been successfully registered, and acquires a fourth image that has failed to register. The first and second images are obtained by the first camera taking pictures of the biochip, and the third and fourth images are obtained by the second camera taking pictures of the biochip. The first and third images are obtained in the same round of shooting, and the second and fourth images are obtained in the same round of shooting. The relative positions of the first camera and the second camera remain constant. Multiple trajectory lines are distributed on the biochip. Registration is used to identify the trajectory lines in the images. The equation acquisition module 702 acquires the first trajectory equation in the first image, the second trajectory equation in the second image, and the third trajectory equation in the third image. The equation transformation module 703 transforms the third trajectory equation according to the first trajectory equation and the second trajectory equation to obtain the fourth trajectory equation. The trajectory reconstruction module 704 reconstructs the trajectory lines on the fourth image according to the fourth trajectory equation. In this way, the trajectory equation of the trajectory line in the failed registration image can be inferred from the trajectory equation of the trajectory line in the successfully registered image, based on the other three successfully registered images. Then, the trajectory line can be reconstructed in the failed registration image, avoiding the inability to identify the trajectory line and thus preventing the subsequent sequencing process from being impossible, thereby improving the efficiency of gene sequencing.

[0151] Specific limitations regarding the trajectory reconstruction device can be found in the limitations of the trajectory reconstruction method described above, and will not be repeated here. Each module in the aforementioned trajectory reconstruction device can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in hardware or independently of the processor in a computer device, or stored in software in the memory of a computer device, so that the processor can call and execute the operations corresponding to each module.

[0152] Terms such as “component,” “module,” and “system” are intended to refer to computer-related entities, which can be hardware, a combination of hardware and software, software, or software in execution. For example, a component can be, but is not limited to, a process running on a processor, a processor, an object, executable code, a thread of execution, a program, and / or a computer. For illustration, a running program on a server and the server itself can both be components. One or more components may reside within a process and / or a thread of execution, and components may be located within a single computer and / or distributed across two or more computers.

[0153] In one exemplary embodiment, a computer device is provided, which may be a server, and its internal structure diagram may be as follows: Figure 9As shown, this computer device includes a processor, memory, input / output (I / O) interfaces, and a communication interface. The processor, memory, and I / O interfaces are connected via a system bus, and the communication interface is also connected to the system bus via the I / O interfaces. The processor provides computational and control capabilities. The memory includes a non-volatile computer-readable storage medium and internal memory. The non-volatile computer-readable storage medium stores an operating system, computer-readable instructions, and a database. The internal memory provides an environment for the operation of the operating system and computer-readable instructions in the non-volatile computer-readable storage medium. The database stores feature data corresponding to gene loci. The I / O interfaces are used for exchanging information between the processor and external devices. The communication interface is used for communication with external terminals via a network connection. When the computer-readable instructions are executed by the processor, they implement a trajectory reconstruction method or a trajectory reconstruction model generation method.

[0154] In one exemplary embodiment, a computer device is provided, which may be a terminal, and its internal structure diagram may be as follows: Figure 10 As shown, the computer device includes a processor, memory, input / output interfaces, a communication interface, a display unit, and an input device. The processor, memory, and input / output interfaces are connected via a system bus, and the communication interface, display unit, and input device are also connected to the system bus via the input / output interfaces. The processor provides computational and control capabilities. The memory includes a non-volatile computer-readable storage medium and internal memory. The non-volatile computer-readable storage medium stores the operating system and computer-readable instructions. The internal memory provides an environment for the operation of the operating system and computer-readable instructions in the non-volatile computer-readable storage medium. The input / output interfaces are used for exchanging information between the processor and external devices. The communication interface is used for wired or wireless communication with external terminals; wireless communication can be achieved through Wi-Fi, mobile cellular networks, NFC (Near Field Communication), or other technologies. When the computer-readable instructions are executed by the processor, they implement a trajectory reconstruction method. The display unit is used to form a visually visible image and can be a display screen, a projection device, or a virtual reality imaging device. The display screen can be an LCD screen or an e-ink screen. The input device of the computer device can be a touch layer covering the display screen, or buttons, trackballs, or touchpads set on the casing of the computer device, or external keyboards, touchpads, or mice, etc.

[0155] Those skilled in the art will understand that Figure 9 , 10The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the computer device to which the present application is applied. Specific computer devices may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0156] In one embodiment, a computer device is also provided, including a memory and a processor, the memory storing computer-readable instructions, the processor executing the computer-readable instructions to implement the steps in the above method embodiments.

[0157] In one embodiment, a computer-readable storage medium is provided storing computer-readable instructions that, when executed by a processor, implement the steps in the above method embodiments.

[0158] In one embodiment, a computer program product is provided, the computer program product including computer-readable instructions stored in a computer-readable storage medium. A processor of a computer device reads the computer-readable instructions from the computer-readable storage medium, and executes the computer-readable instructions, causing the computer device to perform the steps in the above-described method embodiments.

[0159] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by instructing related hardware through computer-readable instructions. These computer-readable instructions can be stored in a non-volatile computer-readable storage medium. When executed, these computer-readable instructions can include the processes of the embodiments of the above methods. Any references to memory, databases, or other media used in the embodiments provided in this application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM). The databases involved in the embodiments provided in this application may include at least one type of relational database and non-relational database. Non-relational databases may include, but are not limited to, blockchain-based distributed databases. The processors involved in the embodiments provided in this application may be general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic devices, quantum computing-based data processing logic devices, etc., and are not limited to these.

[0160] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0161] The above embodiments are merely illustrative of several implementation methods of this application, and their descriptions are relatively specific and detailed. However, they should not be construed as limiting the scope of this application. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the protection scope of this application. Therefore, the protection scope of this application should be determined by the appended claims.

Claims

1. A trajectory line reconstruction method, characterized in that, include: The process involves acquiring a first image, a second image, and a third image that are successfully registered, and acquiring a fourth image that is not registered. The first and second images are obtained by taking pictures of the biochip with a first camera, and the third and fourth images are obtained by taking pictures of the biochip with a second camera. The first and third images are obtained in the same round of shooting, and the second and fourth images are obtained in the same round of shooting. The relative positions of the first and second cameras remain constant. Multiple trajectory lines are distributed on the biochip, and the registration is used to identify the trajectory lines in the image. Obtain the first trajectory equation of the trajectory line in the first image, the second trajectory equation in the second image, and the third trajectory equation in the third image; The third trajectory equation is transformed based on the first trajectory equation and the second trajectory equation to obtain the fourth trajectory equation; The trajectory line is reconstructed on the fourth image according to the fourth trajectory equation.

2. The method according to claim 1, characterized in that, The step of transforming the third trajectory equation based on the first trajectory equation and the second trajectory equation to obtain the fourth trajectory equation includes: The photographing displacement is determined based on the first trajectory equation and the second trajectory equation, wherein the photographing displacement is the offset of the photographing position during the two rounds of photographing; The third trajectory equation is transformed based on the photographed displacement to obtain the fourth trajectory equation.

3. The method according to claim 2, characterized in that, The multiple trajectory lines include multiple first trajectory lines parallel to each other in a first direction and multiple second trajectory lines parallel to each other in a second direction. The photographing displacement includes a first displacement in the first direction and a second displacement in the second direction. The transformation of the third trajectory equation based on the photographing displacement to obtain the fourth trajectory equation includes: The third trajectory equation of the second trajectory line is transformed based on the first displacement to obtain the fourth trajectory equation of the second trajectory line. The third trajectory equation of the first trajectory line is transformed based on the second displacement to obtain the fourth trajectory equation of the first trajectory line.

4. The method according to claim 1, characterized in that, The multiple trajectory lines include multiple first trajectory lines distributed parallel to each other in a first direction and multiple second trajectory lines distributed parallel to each other in a second direction. The multiple first trajectory lines and the multiple second trajectory lines intersect to form multiple trajectory intersection points. Obtaining the third trajectory equation of the trajectory lines in the third image includes: Determine the pixel coordinates of the intersection points of the plurality of trajectories on the third image; For each first trajectory line, determine all trajectory intersections on the first trajectory line, and fit the third trajectory equation of the first trajectory line on the third image based on the pixel coordinates of all trajectory intersections on the first trajectory line in the third image. For each second trajectory line, determine all trajectory intersections on the second trajectory line, and fit the third trajectory equation of the second trajectory line on the third image based on the pixel coordinates of all trajectory intersections on the second trajectory line on the third image.

5. The method according to claim 1, characterized in that, Multiple DNA nanospheres are mounted on the biochip, and after reconstructing the trajectory line on the fourth image according to the fourth trajectory equation, the method further includes: The coordinates of the DNA nanospheres on the fourth image are determined based on multiple trajectory lines on the fourth image.

6. The method according to claim 5, characterized in that, The multiple trajectory lines include multiple first trajectory lines distributed parallel to each other in a first direction and multiple second trajectory lines distributed parallel to each other in a second direction. The multiple first trajectory lines and the multiple second trajectory lines intersect to form multiple trajectory intersection points. Determining the coordinates of the DNA nanospheres on the fourth image based on the multiple trajectory lines on the fourth image includes: Multiple blocks on the biochip are determined based on every two adjacent first trajectory lines and every two adjacent second trajectory lines. The target block where the DNA nanosphere is located is determined based on the location of the DNA nanosphere, as well as the two first trajectory lines and two second trajectory lines corresponding to the target block; The coordinates of the DNA nanosphere on the fourth image are determined based on the fourth trajectory equations of the two first trajectory lines and the two second trajectory lines, as well as the distances of the DNA nanosphere to the two first trajectory lines and the two second trajectory lines.

7. A trajectory line reconstruction device, characterized in that, The device includes: The image acquisition module is used to acquire a first image, a second image, and a third image that have been successfully registered, and to acquire a fourth image that has failed to be registered. The first image and the second image are obtained by the first camera taking pictures of the biochip, and the third image and the fourth image are obtained by the second camera taking pictures of the biochip. The first image and the third image are obtained in the same round of shooting, and the second image and the fourth image are obtained in the same round of shooting. The relative positions of the first camera and the second camera remain constant. Multiple trajectory lines are distributed on the biochip, and the registration is used to identify the trajectory lines in the image. The equation acquisition module is used to acquire the first trajectory equation of the trajectory line in the first image, the second trajectory equation in the second image, and the third trajectory equation in the third image; The equation transformation module is used to transform the third trajectory equation based on the first trajectory equation and the second trajectory equation to obtain the fourth trajectory equation; A trajectory reconstruction module is used to reconstruct the trajectory line on the fourth image according to the fourth trajectory equation.

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

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

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

Images