Nucleic acid molecule sequencing methods and related devices

Abstract

This disclosed nucleic acid molecular sequencing method first obtains a sequencing image of a target nucleic acid sample; then processes the sequencing image based on an image processing model to obtain a target image, wherein the image processing model is a model trained using a constructed true image of nucleic acid molecules and a corresponding simulated nucleic acid image; and finally, nucleic acid molecular sequencing is performed based on the target image to obtain the sequencing results corresponding to the target nucleic acid sample.

Description

Nucleic acid molecule sequencing method and related device Technical Field

[0001] The present disclosure relates to the fields of image processing and biological molecule sequencing technology, and in particular to a nucleic acid molecule sequencing method and related devices. Background Art

[0002] High-throughput sequencing is a technology for sequencing nucleic acid molecules, enabling parallel sequencing of large numbers of nucleic acid molecules simultaneously. High-throughput sequencing can immobilize nucleic acid molecules on arrayed sequencing chips. During each round of reactions between the nucleic acid molecules, specific enzymes, and fluorescent probes, different bases emit fluorescent signals of varying wavelengths. This process is captured by an imaging system, which then reconstructs and identifies the captured images, from which the base sequence can be determined.

[0003] According to relevant technologies, during the above-mentioned determination of base sequences, reducing the distance between adjacent nucleic acid molecules and increasing the arrangement density of nucleic acid molecules on the chip can effectively increase the number of bases per unit field of view, thereby increasing sequencing throughput and reducing the unit throughput sequencing cost. However, due to the optical diffraction limit, when the distance between nucleic acid molecules is less than the resolution of the imaging system, the fluorescent signals of adjacent nucleic acid molecules will crosstalk, thereby significantly affecting the accuracy of base calls. Therefore, how to effectively improve the accuracy of base calls during the sequencing of nucleic acid molecules has become a major problem that needs to be solved urgently in the industry.

[0004] Summary of the Invention

[0005] The present disclosure aims to solve at least one of the technical problems existing in the prior art. To this end, the present disclosure provides a nucleic acid molecule sequencing method and related apparatus that can effectively improve the accuracy of base calling during the nucleic acid molecule sequencing process.

[0006] The nucleic acid molecule sequencing method according to the first embodiment of the present disclosure includes:

[0007] Acquire a sequencing image of the target nucleic acid sample, wherein the sequencing image is an image acquired by capturing the target nucleic acid sample using a preset optical sequencing system;

[0008] performing image processing on the sequencing image based on an image processing model to obtain a target image, wherein the image processing model is a model trained using a constructed true image of a nucleic acid molecule and a corresponding simulated nucleic acid image, wherein the simulated nucleic acid image is an image obtained by simulated sequencing of a simulated nucleic acid sample corresponding to the true image of the nucleic acid molecule based on a simulated optical system, and the simulated optical system is an optical system obtained by simulating the preset optical sequencing system;

[0009] Nucleic acid molecule sequencing is performed according to the target image to obtain a sequencing result corresponding to the target nucleic acid sample.

[0010] According to some embodiments of the present disclosure, before performing image processing on the sequencing image based on the image processing model to obtain the target image, the image processing model is further trained, specifically including:

[0011] constructing the true value image of the nucleic acid molecule based on the simulated nucleic acid sample;

[0012] performing simulated sequencing based on the simulated nucleic acid sample by the simulated optical system to obtain the simulated nucleic acid image;

[0013] Inputting the true value image of the nucleic acid molecule and the simulated nucleic acid image corresponding to the true value image of the nucleic acid molecule into the original image processing model, and iteratively training the image processing model;

[0014] When the image processing model meets the first predetermined condition during iterative training, the trained image processing model is obtained.

[0015] According to some embodiments of the present disclosure, performing simulated sequencing based on the simulated nucleic acid sample using the simulated optical system to obtain the simulated nucleic acid image includes:

[0016] simulating optical calibration information of the preset optical sequencing system;

[0017] The nucleic acid distribution information is simulated based on the simulated optical calibration information to obtain the simulated nucleic acid image.

[0018] According to some embodiments of the present disclosure, the nucleic acid molecules in the simulated nucleic acid sample include a plurality of bases, each of which is labeled with a fluorescent signal;

[0019] The simulating the optical calibration information of the preset optical sequencing system includes:

[0020] Determining a pixel size of the preset optical sequencing system; wherein the pixel size is the size of a single pixel in the preset optical sequencing system corresponding to an imaging plane;

[0021] Performing optical imaging analysis based on the fluorescence signal corresponding to the base in the simulated nucleic acid sample to obtain an optical transfer function;

[0022] The pixel size is integrated with the optical transfer function to obtain the simulated optical calibration information.

[0023] According to some embodiments of the present disclosure, performing optical imaging analysis on the fluorescence signal corresponding to the base in the simulated nucleic acid sample to obtain an optical transfer function includes:

[0024] Scanning and imaging the simulated nucleic acid sample to obtain a scanned nucleic acid image;

[0025] Performing a local maximum search based on the scanned nucleic acid image to obtain a fluorescence image reflecting each of the fluorescence signals;

[0026] Performing Gaussian fitting and averaging processing on the fluorescence images corresponding to the multiple fluorescence signals to obtain a point spread function;

[0027] Performing Fourier transform on the point spread function to obtain the optical transfer function.

[0028] According to some embodiments of the present disclosure, integrating the pixel size with the optical transfer function to obtain the simulated optical calibration information includes:

[0029] performing noise extraction on the blank areas between the nucleic acid molecules in the simulated nucleic acid sample to obtain simulated noise information;

[0030] The pixel size, the optical transfer function and the simulated noise information are integrated to obtain the simulated optical calibration information.

[0031] According to some embodiments of the present disclosure, simulating the nucleic acid distribution information based on the simulated optical calibration information to obtain the simulated nucleic acid image includes:

[0032] Mapping the nucleic acid distribution information to an imaging space based on the pixel size to obtain a first simulated image of the simulated nucleic acid sample in the imaging space;

[0033] Performing imaging performance simulation on the first simulation image based on the optical transfer function to obtain a second simulation image;

[0034] Environmental noise simulation is performed on the second simulated image based on the simulated noise information to obtain the simulated nucleic acid image.

[0035] According to some embodiments of the present disclosure, inputting the true nucleic acid molecule image and the simulated nucleic acid image corresponding to the true nucleic acid molecule image into the original image processing model and iteratively training the image processing model includes:

[0036] In each round of iterative training, the simulated nucleic acid image is input into the image processing model for image processing training to obtain the processing result of this round;

[0037] Comparing the processing result of this round with the true value image of the nucleic acid molecule to obtain training deviation data;

[0038] Based on the training bias data, the weight parameters of the image processing model are updated.

[0039] According to some embodiments of the present disclosure, when the image processing model meets a first predetermined condition during iterative training, obtaining the trained image processing model includes:

[0040] When the training deviation data reflects that the image processing model converges during iterative training, it is determined that the image processing model meets the first predetermined condition during the iterative training, and the trained image processing model is obtained.

[0041] According to the second aspect of the present disclosure, a nucleic acid molecule sequencing device includes:

[0042] An image acquisition module, configured to acquire a sequencing image of a target nucleic acid sample, wherein the sequencing image is an image acquired by acquiring an image of the target nucleic acid sample using a preset optical sequencing system;

[0043] an image processing module, configured to perform image processing on the sequencing image based on an image processing model to obtain a target image, wherein the image processing model is a model trained using a constructed true image of a nucleic acid molecule and a corresponding simulated nucleic acid image, wherein the simulated nucleic acid image is an image obtained by simulated sequencing of a simulated nucleic acid sample corresponding to the true image of the nucleic acid molecule based on a simulated optical system, wherein the simulated optical system is an optical system obtained by simulating the preset optical sequencing system;

[0044] The sequence determination module is used to perform nucleic acid molecule sequencing according to the target image to obtain a sequencing result corresponding to the target nucleic acid sample.

[0045] In a third aspect, an embodiment of the present disclosure provides an electronic device comprising: a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, it implements the nucleic acid molecule sequencing method as described in any one of the embodiments of the first aspect of the present disclosure.

[0046] In a fourth aspect, an embodiment of the present disclosure provides a computer-readable storage medium, wherein the storage medium stores a program, and the program is executed by a processor to implement the nucleic acid molecule sequencing method as described in any one of the embodiments of the first aspect of the present disclosure.

[0047] The nucleic acid molecule sequencing method and related apparatus according to the embodiments of the present disclosure have at least the following beneficial effects:

[0048] The disclosed nucleic acid molecule sequencing method can first obtain a sequencing image of a target nucleic acid sample, where the sequencing image is an image obtained by collecting an image of the target nucleic acid sample using a preset optical sequencing system; perform image processing on the sequencing image based on an image processing model to obtain a target image, where the image processing model is a model trained using a constructed true nucleic acid molecule image and a corresponding simulated nucleic acid image, where the simulated nucleic acid image is an image obtained by simulated sequencing of a simulated nucleic acid sample corresponding to the true nucleic acid molecule image based on a simulated optical system, where the simulated optical system is an optical system simulated by the preset optical sequencing system; and then perform nucleic acid molecule sequencing based on the target image to obtain a sequencing result corresponding to the target nucleic acid sample. Since the image processing model is trained using the true nucleic acid molecule image and the corresponding simulated nucleic acid image, and the simulated nucleic acid image is an image obtained by simulated sequencing of a simulated nucleic acid sample corresponding to the true nucleic acid molecule image based on a simulated optical system, where the simulated optical system is an optical system simulated by the preset optical sequencing system, the image processing model is used to process the sequencing image, thereby improving the resolution. In this way, the accuracy of base calling can be effectively improved during nucleic acid molecule sequencing.

[0049] Additional aspects and advantages of the present disclosure will be given in part in the description that follows and, in part, will be obvious from the description that follows, or will be learned through practice of the present disclosure. BRIEF DESCRIPTION OF THE DRAWINGS

[0050] The above and / or additional aspects and advantages of the present disclosure will become apparent and readily understood from the description of the embodiments in conjunction with the following drawings, in which:

[0051] FIG1 is a flow chart of a nucleic acid molecule sequencing method provided by an embodiment of the present disclosure;

[0052] FIG2 is a schematic diagram of an image processing model of a deep residual channel attention neural network structure provided by an embodiment of the present disclosure;

[0053] FIG3 is a schematic diagram showing the principle of the nucleic acid molecule sequencing method provided by an embodiment of the present disclosure;

[0054] 4 , a flowchart of training the image processing model before step S102;

[0055] FIG5 is a flow chart of step S402 in FIG4 ;

[0056] FIG6 is a flow chart of step S501 in FIG5 ;

[0057] FIG7 is a flow chart of step S602 in FIG6 ;

[0058] FIG8( a ) to FIG8 ( g ) are schematic diagrams of obtaining optical transfer functions according to an embodiment of the present disclosure;

[0059] FIG9 is a flow chart of step S603 in FIG6 ;

[0060] FIG10 is a schematic diagram of determining the average value, standard deviation of the signal in the blank area and the average maximum value of the nucleic acid molecule area according to an embodiment of the present disclosure;

[0061] FIG11 is a flow chart of step S502 in FIG5 ;

[0062] Figures 12(a) to 12(c) are schematic diagrams of obtaining simulated nucleic acid images according to embodiments of the present disclosure;

[0063] FIG13 is a flow chart of step S403 in FIG4 ;

[0064] FIG14 is a sequencer provided in a specific embodiment of the present disclosure for sequencing a multi-spaced nucleic acid molecule chip;

[0065] FIG15 is a diagram showing the sequencing results of a multi-spacing nucleic acid molecule chip using a high-sampling optical machine according to a second specific embodiment of the present disclosure;

[0066] FIG16 is a schematic structural diagram of a nucleic acid molecule sequencing device provided in an embodiment of the present disclosure;

[0067] FIG17 is a schematic diagram of the hardware structure of an electronic device provided in an embodiment of the present disclosure. DETAILED DESCRIPTION

[0068] The following describes in detail embodiments of the present disclosure, examples of which are shown in the accompanying drawings, wherein the same or similar reference numerals throughout represent the same or similar elements or elements having the same or similar functions. The embodiments described below with reference to the accompanying drawings are exemplary and are only used to explain the present disclosure, and are not to be construed as limiting the present disclosure.

[0069] In the description of this disclosure, "a plurality" means more than two. "greater than," "less than," and "exceed" are understood to exclude the number itself, while "above," "below," and "within" are understood to include the number itself. The terms "first" and "second" are used solely to distinguish technical features and are not to be construed as indicating or implying relative importance, or as implicitly specifying the number or order of the technical features indicated.

[0070] In the description of the present disclosure, it can be understood that the descriptions involving orientations, such as up, down, left, right, front, back, etc., indicating orientations or positional relationships, are based on the orientations or positional relationships shown in the accompanying drawings, and are only for the convenience of describing the present disclosure and simplifying the description, rather than indicating or implying that the device or element referred to has a specific orientation, is constructed and operated in a specific orientation, and therefore cannot be understood as a limitation on the present disclosure.

[0071] Throughout this specification, reference to terms such as "one embodiment," "some embodiments," "illustrative embodiments," "examples," "specific examples," or "some examples" means that the specific features, structures, materials, or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present disclosure. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples.

[0072] In the description of this disclosure, it should be noted that, unless otherwise explicitly defined, terms such as "set," "install," and "connect" should be understood in a broad sense, and those skilled in the art can reasonably determine the specific meanings of these terms in this disclosure based on the specific content of the technical solution. Furthermore, the identification of specific steps below does not constitute a limitation on the order and execution logic of the steps. The order and execution logic of each step should be understood and inferred with reference to the content described in the embodiments.

[0073] High-throughput sequencing is a technology for sequencing nucleic acid molecules, enabling parallel sequencing of large numbers of nucleic acid molecules at once. High-throughput sequencing involves attaching nucleic acid molecules to a solid surface, attaching complementary probes with fluorescent groups to the molecules, and then sequentially confirming the base sequence through fluorescence imaging.

[0074] According to relevant technologies, nucleic acid molecules are fixed on arrayed sequencing chips. Through each round of reaction between nucleic acid molecules, specific enzymes and fluorescent probes, different bases will emit fluorescent signals of different wavelengths. This process is collected by the imaging system, and the collected images are reconstructed and identified on this basis, from which the base sequence can be determined. Among them, reducing the distance between adjacent nucleic acid molecules and increasing the arrangement density of nucleic acid molecules on the chip can effectively increase the number of bases per unit field of view, thereby increasing sequencing throughput and reducing unit throughput sequencing costs. However, due to the optical diffraction limit, when the distance between nucleic acid molecules is less than the resolution of the imaging system, the fluorescent signals of adjacent nucleic acid molecules will crosstalk, thereby greatly affecting the accuracy of base calling. Therefore, how to effectively improve the accuracy of base calling in the process of sequencing nucleic acid molecules has become a major problem that needs to be solved urgently in the industry.

[0075] The present disclosure aims to solve at least one of the technical problems existing in the prior art. To this end, the present disclosure provides a nucleic acid molecule sequencing method and related apparatus that can effectively improve the accuracy of base calling during the nucleic acid molecule sequencing process.

[0076] The following description is based on the accompanying drawings.

[0077] 1 , the nucleic acid molecule sequencing method provided according to an embodiment of the present disclosure may include, but is not limited to, the following steps S101 to S103 .

[0078] Step S101, obtaining a sequencing image of a target nucleic acid sample, where the sequencing image is an image acquired by capturing the target nucleic acid sample using a preset optical sequencing system;

[0079] Step S102: performing image processing on the sequencing image based on an image processing model to obtain a target image. The image processing model is a model trained using a constructed true nucleic acid molecule image and a corresponding simulated nucleic acid image. The simulated nucleic acid image is an image obtained by simulated sequencing of a simulated nucleic acid sample corresponding to the true nucleic acid molecule image based on a simulated optical system. The simulated optical system is an optical system simulated from a preset optical sequencing system.

[0080] Step S103 , performing nucleic acid molecule sequencing according to the target image to obtain a sequencing result corresponding to the target nucleic acid sample.

[0081] According to the nucleic acid molecule sequencing method shown in steps S101 to S103 of the present disclosure, a sequencing image of a target nucleic acid sample can be first obtained, where the sequencing image is an image obtained by capturing an image of the target nucleic acid sample using a preset optical sequencing system; the sequencing image is processed based on an image processing model to obtain a target image, where the image processing model is a model trained using a constructed true nucleic acid molecule image and a corresponding simulated nucleic acid image, where the simulated nucleic acid image is an image obtained by simulated sequencing of a simulated nucleic acid sample corresponding to the true nucleic acid molecule image based on a simulated optical system, where the simulated optical system is an optical system simulated from the preset optical sequencing system; and nucleic acid molecule sequencing is then performed based on the target image to obtain a sequencing result corresponding to the target nucleic acid sample. Since the image processing model is trained using the true nucleic acid molecule image and the corresponding simulated nucleic acid image, and the simulated nucleic acid image is an image obtained by simulated sequencing of a simulated nucleic acid sample corresponding to the true nucleic acid molecule image based on a simulated optical system, where the simulated optical system is an optical system simulated from the preset optical sequencing system, the image processing model is used to process the sequencing image to achieve an improvement in resolution, thereby effectively improving the accuracy of base calls during nucleic acid molecule sequencing.

[0082] In step S101 of some embodiments, a sequencing image of a target nucleic acid sample is obtained, and the sequencing image is an image obtained by capturing an image of the target nucleic acid sample using a preset optical sequencing system. It can be explained that in order to sequence a nucleic acid molecule, a sequencing image of the target nucleic acid sample can be first obtained. The target nucleic acid sample refers to a nucleic acid sample that serves as a sequencing target, and by capturing an image of the target nucleic acid sample, a sequencing image of the target nucleic acid sample can be obtained. It should be understood that image capture of the target nucleic acid sample can rely on a preset optical sequencing system, and the preset optical sequencing system refers to a nucleic acid image capture and sequencing system that is pre-set with certain optical conditions. It can be pointed out that capturing an image of the target nucleic acid sample using a preset optical sequencing system under different optical conditions will have different effects.

[0083] In step S102 of some embodiments, the sequencing image is processed based on an image processing model to obtain a target image. The image processing model is a model trained using a constructed true image of a nucleic acid molecule and a corresponding simulated nucleic acid image. The simulated nucleic acid image is an image obtained by simulated sequencing of a simulated nucleic acid sample corresponding to the true image of the nucleic acid molecule based on a simulated optical system. The simulated optical system is an optical system obtained by simulating a preset optical sequencing system. It can be emphasized that the nucleic acid molecules are fixed on an arrayed sequencing chip. Through each round of reaction between the nucleic acid molecules, a specific enzyme, and a fluorescent probe, different bases will emit fluorescent signals of different wavelengths. This process is captured by the imaging system. On this basis, the captured image is reconstructed and identified, and the base sequence can be determined therefrom. It can be pointed out that both the target nucleic acid sample and the simulated nucleic acid sample can be prepared in the above manner. The difference is that the target nucleic acid sample is the nucleic acid sample used as the sequencing target in actual application, while the simulated nucleic acid sample is used to construct training data for the image processing model.

[0084] Some embodiments can effectively increase the number of bases per unit field of view by reducing the spacing between adjacent nucleic acid molecules and increasing the density of nucleic acid molecules on the chip, thereby increasing sequencing throughput and reducing sequencing costs per unit throughput. However, due to the optical diffraction limit, when the spacing between nucleic acid molecules is smaller than the resolution of the imaging system, crosstalk between the fluorescent signals of adjacent nucleic acid molecules occurs, significantly affecting the accuracy of base calls.

[0085] To address this issue, in step S102 of the disclosed embodiment, the sequencing image can be processed based on the image processing model to obtain a target image. It can be noted that processing the sequencing image based on the image processing model aims to improve the resolution of the sequencing image through the image processing model, which is also known as super-resolution processing. Super-resolution processing is the process of increasing the resolution of the original image through hardware or software methods. The process of obtaining a high-resolution image from a series of low-resolution images is super-resolution reconstruction.

[0086] It is clear that the image processing model is a model trained using the constructed true value image of the nucleic acid molecule and the corresponding simulated nucleic acid image, wherein the simulated nucleic acid image is an image obtained by performing simulated sequencing on the simulated nucleic acid sample corresponding to the true value image of the nucleic acid molecule based on the simulated optical system, and the simulated optical system is an optical system obtained by simulating the preset optical sequencing system. It should be understood that the image obtained by performing simulated sequencing on the simulated nucleic acid sample corresponding to the true value image of the nucleic acid molecule by the simulated optical system can more realistically simulate the actual acquisition of the sequencing image. Therefore, using the true value image of the nucleic acid molecule and the corresponding simulated nucleic acid image to train the image processing model can improve the image processing model's super-resolution processing capability for images. After the sequencing image is processed based on the image processing model, a target image with higher resolution can be obtained, so that nucleic acid molecules can be sequenced according to the target image in the subsequent steps. In this way, when the spacing between nucleic acid molecules is less than the resolution of the imaging system, the crosstalk effect caused by the fluorescent signals of adjacent nucleic acid molecules can be reduced, and the accuracy of base calling can be effectively improved during the sequencing of nucleic acid molecules.

[0087] Referring to Figure 2, in some more specific embodiments, the image processing model can be a deep residual channel attention neural network structure. By performing image processing on the sequenced image based on the image processing model, the target image can be obtained. Specifically, the sequenced image can first be subjected to shallow feature extraction to obtain sequenced image features, which are then sequentially passed through multiple layers of RG and Conv and output, and input together with the initial sequenced image features into the reconstruction module to generate the target image. Among them, RG: residual shallow feature extraction module, FCAB: channel attention module, Conv: convolution layer, RELU: linear rectifier activation layer, FFT: Fourier transform layer; Sigmoid: S-type function activation layer.

[0088] In step S103 of some embodiments, nucleic acid molecule sequencing is performed based on the target image to obtain sequencing results corresponding to the target nucleic acid sample. It can be illustrated that, due to the image processing model performing image processing on the sequencing image, the resolution of the nucleic acid molecules in the target image is improved compared to the resolution of the nucleic acid molecules in the sequencing image. On this basis, performing nucleic acid molecule sequencing based on the target image helps reduce the crosstalk caused by the fluorescent signals of adjacent nucleic acid molecules when the spacing between nucleic acid molecules is less than the resolution of the imaging system, thereby effectively improving the accuracy of base calls during nucleic acid molecule sequencing.

[0089] In some embodiments, a gene sequencer can be used to sequence nucleic acid molecules. It should be noted that a gene sequencer, also known as a DNA sequencer, is an instrument that determines the base sequence, type, and quantity of DNA fragments. It is primarily used in human genome sequencing, genetic diagnosis of human genetic diseases, infectious diseases, and cancer, forensic paternity testing and individual identification, screening of bioengineering drugs, and hybrid breeding of animals and plants. Currently, the operating principles of DNA sequencers are primarily based on the dideoxy chain termination method or the chemical degradation method. Although these two methods differ in principle, both are based on initiating nucleotide chain extension at a fixed site and randomly terminating at a specific base, generating a series of nucleotide chains of four different lengths, terminated by A, T, C, and G. The fragments are then separated and detected by electrophoresis on a denaturing polyacrylamide gel to obtain the DNA sequence. Because the dideoxy chain termination method is simpler and more suitable for optical automated detection, it is widely used in fully automated DNA sequencers designed solely for DNA sequence determination. The chemical degradation method, on the other hand, has important applications in studying DNA secondary structure and protein-DNA interactions. It should be understood that there are various ways to perform nucleic acid molecule sequencing based on the target image, which may include, but are not limited to, the specific embodiments listed above.

[0090] Refer to the schematic diagram of the principle of the nucleic acid molecule sequencing method shown in Figure 3. The simulated nucleic acid sample corresponding to the true value image of the nucleic acid molecule obtains a simulated nucleic acid image after simulated sequencing, and then the image processing model is trained based on the true value image of the nucleic acid molecule and the corresponding simulated nucleic acid image. In the process of nucleic acid molecule sequencing, the sequencing image of the target nucleic acid sample is first obtained, and then the sequencing image is processed based on the image processing model to obtain the target image. The nucleic acid molecule is sequenced according to the target image to obtain the sequencing result corresponding to the target nucleic acid sample. The image processing model is used to perform image processing on the sequencing image to achieve an improvement in resolution. In this way, the accuracy of base calling can be effectively improved in the process of sequencing nucleic acid molecules.

[0091] Since steps S101 to S103 of the embodiment of the present disclosure have been described in detail above, the steps that may be included before step S102 will be described in detail below.

[0092] The following describes an embodiment of the present disclosure of training an image processing model before step S102.

[0093] 4 , according to some embodiments of the present disclosure, before performing image processing on the sequencing image based on the image processing model to obtain the target image in step S102 , the image processing model may be trained, which may specifically include, but is not limited to, the following steps S401 to S404 .

[0094] Step S401, constructing a true image of nucleic acid molecules based on a simulated nucleic acid sample;

[0095] Step S402, performing simulated sequencing based on a simulated nucleic acid sample using a simulated optical system to obtain a simulated nucleic acid image;

[0096] Step S403: inputting the true value image of the nucleic acid molecule and the simulated nucleic acid image corresponding to the true value image of the nucleic acid molecule into the original image processing model, and iteratively training the image processing model;

[0097] Step S404: When the image processing model meets the first predetermined condition during iterative training, a trained image processing model is obtained.

[0098] In step S401 of some embodiments, a true image of nucleic acid molecules is constructed based on a simulated nucleic acid sample. It can be emphasized that the nucleic acid molecules are fixed on an arrayed sequencing chip, and through each round of reaction between the nucleic acid molecules, a specific enzyme and a fluorescent probe, different bases will emit fluorescent signals of different wavelengths. This process is collected by the imaging system, and the collected image is reconstructed and identified on this basis, and the base sequence can be determined therefrom. It can be pointed out that the simulated nucleic acid sample can be prepared in the above manner, and the simulated nucleic acid sample is used to construct training data for the image processing model. It can be pointed out that the base sequence of the simulated nucleic acid sample is known, and on this basis, a true image of nucleic acid molecules can be constructed based on the known base sequence of the simulated nucleic acid sample.

[0099] According to some more specific embodiments, each nucleic acid molecule of the simulated nucleic acid sample is regularly loaded into the sequencing chip for arrangement, and the arrangement unit of the nucleic acid arrangement is called a block. Each imaging field of view contains multiple arrangement unit blocks, and the distance between adjacent arrangement unit blocks is called a tracking line. It can be pointed out that the information such as the number of arrangement unit blocks, the arrangement order, and the distance between nucleic acid molecules divided in each imaging field of view of the simulated nucleic acid sample is recorded in the mask file. Since the mask file contains the known nucleic acid arrangement situation in the simulated nucleic acid sample, the true value image of the nucleic acid molecule can be constructed based on the mask file to obtain the true value image of the nucleic acid molecule. Among them, a set of simulations can include multiple mask files describing different imaging fields.

[0100] According to some more specific embodiments, each nucleic acid molecule is composed of a base sequence, which can be randomly generated or derived from a standard genomic library such as Escherichia coli or human. In the process of constructing a true image of a nucleic acid molecule based on a mask file, multiple rounds of imaging of the nucleic acid molecule can be performed one base at a time. After several rounds of imaging of the nucleic acid molecule in each imaging field of view, the bases of the nucleic acid molecule in each imaging field of view can be clearly presented in the true image of the nucleic acid molecule obtained by simulated sequencing. Since different bases can emit fluorescence signals of different wavelengths, the brightness of the fluorescence signal corresponding to each base can be represented by a set of normalized four-dimensional vectors [i_a, i_c, i_g, i_t]. When the base type is one of A, C, G, and T, the brightness of the corresponding position is set to a certain range of values. If there is no base at a certain position, all four elements of the vector are 0. In this way, the true value of the simulated nucleic acid sample can be clearly presented in the true image of the nucleic acid molecule.

[0101] In step S402 of some embodiments, simulated sequencing is performed on a simulated nucleic acid sample using a simulated optical system to obtain a simulated nucleic acid image. It should be noted that the simulated optical system is an optical system obtained by simulating a preset optical sequencing system. Therefore, by simulating the optical conditions of the preset optical sequencing system using the simulated optical system, simulated sequencing can be performed on the simulated nucleic acid sample to obtain a simulated nucleic acid image.

[0102] During the execution of the disclosed nucleic acid molecule sequencing method, a sequencing image is obtained by capturing an image of a target nucleic acid sample using a preset optical sequencing system. Therefore, to enable the trained image processing model to be adaptable to super-resolution processing of sequencing images, during the training of the image processing model, a simulated nucleic acid image can be obtained by performing simulated sequencing on a simulated nucleic acid sample using a simulated optical system.

[0103] 5 , according to some embodiments of the present disclosure, step S402 performs simulated sequencing based on a simulated nucleic acid sample through a simulated optical system to obtain a simulated nucleic acid image, which may include, but is not limited to, the following steps S501 to S502 .

[0104] Step S501, simulating optical calibration information of a preset optical sequencing system;

[0105] Step S502 , simulating the nucleic acid distribution information based on the simulated optical calibration information to obtain a simulated nucleic acid image.

[0106] In some embodiments, step S501 simulates the optical calibration information of a preset optical sequencing system. It can be explained that because the simulated optical system is an optical system obtained by simulating the preset optical sequencing system, the simulated optical system simulates the optical conditions of the preset optical sequencing system, thereby enabling simulated sequencing based on a simulated nucleic acid sample to obtain a simulated nucleic acid image. Specifically, the simulated optical system simulates the optical conditions of the preset optical sequencing system, which can be achieved by simulating the optical calibration information of the preset optical sequencing system. The so-called optical calibration information refers to the optical physical quantity information that can be obtained by the simulated optical system during the image acquisition process of the simulated optical sequencing system.

[0107] In some embodiments, since the preset optical sequencing system is a nucleic acid image acquisition and sequencing system that is pre-set with certain optical conditions, the optical calibration information of the preset optical sequencing system can be simulated by querying its pre-set parameters.

[0108] Referring to Figure 6 , according to some specific embodiments of the present disclosure, the nucleic acid molecules in the simulated nucleic acid sample include multiple bases, each of which is labeled with a fluorescent signal. Step S501 simulates optical calibration information of a preset optical sequencing system, which may include, but is not limited to, steps S601 through S603 described below.

[0109] Step S601, determining a pixel size of a preset optical sequencing system; wherein the pixel size is the size of a single pixel in the preset optical sequencing system corresponding to an imaging plane;

[0110] Step S602, performing optical imaging analysis based on the fluorescence signals corresponding to the bases in the simulated nucleic acid sample to obtain an optical transfer function;

[0111] Step S603 : Integrate the pixel size and the optical transfer function to obtain simulated optical calibration information.

[0112] In some embodiments, step S601 involves determining the pixel size of a preset optical sequencing system; the pixel size is the size of a single pixel in the preset optical sequencing system corresponding to the imaging plane. It can be noted that if the preset optical sequencing system uses a camera to capture images, the pixel size represents the size of a single pixel in the camera corresponding to the imaging plane. For example, if the physical size of a camera pixel is 2 μm and the magnification of the preset optical sequencing system is 20x, then the corresponding pixel size of the preset optical sequencing system is 0.1 μm. It can be noted that determining the pixel size of the preset optical sequencing system is intended to establish a mapping from the simulated nucleic acid sample to the camera imaging space.

[0113] In some specific embodiments, the pixel size of a predetermined optical sequencing system can be determined by using a high-precision stage to move a sequencing chip loaded with a simulated nucleic acid sample a large distance (e.g., 100 μm). During this process, the number of pixels displaced at the corresponding position on the image is measured. The distance moved is then divided by the number of pixels displaced to calculate the system pixel size. It should be understood that various implementations for determining the pixel size of a predetermined optical sequencing system may include, but are not limited to, the specific embodiments listed above.

[0114] In some embodiments, step S602 involves performing optical imaging analysis based on the fluorescence signals corresponding to the bases in the simulated nucleic acid sample to obtain an optical transfer function. It should be noted that the optical transfer function is used to model the imaging performance of the optical system, and the modeled imaging performance can be used to generate a simulated nucleic acid image. Performing optical imaging analysis based on the fluorescence signals corresponding to the bases in the simulated nucleic acid sample, i.e., modeling the imaging performance of the optical system, can thereby obtain the corresponding optical transfer function.

[0115] 7 , according to some more specific embodiments of the present disclosure, step S602 performs optical imaging analysis based on the fluorescence signals corresponding to the bases in the simulated nucleic acid sample to obtain an optical transfer function, which may include, but is not limited to, the following steps S701 to S704 .

[0116] Step S701, scanning and imaging the simulated nucleic acid sample to obtain a scanned nucleic acid image;

[0117] Step S702, performing a local maximum search based on the scanned nucleic acid image to obtain a fluorescence image reflecting each fluorescence signal;

[0118] Step S703, performing Gaussian fitting and averaging processing on the fluorescence images corresponding to the multiple fluorescence signals to obtain a point spread function;

[0119] Step S704: Perform Fourier transform on the point spread function to obtain the optical transfer function.

[0120] In the step S701 of some embodiments, the simulation nucleic acid sample is scanned and imaged to obtain a scanned nucleic acid image. It can be explained that scanning and imaging refers to the process of capturing a physical object to accurately represent its geometric shape in a digital environment. Since the optical transfer function is used to model the imaging performance of an optical system, some embodiments can scan and image the region with sparse point-like features in the simulation nucleic acid sample. In this way, it is possible to more efficiently obtain a scanned nucleic acid image in the sparse point-like simulation nucleic acid sample. It should be understood that the region with sparse point-like features in the simulation nucleic acid sample refers to a region where the spacing between nucleic acid molecules is much greater than the optical resolution.

[0121] In some embodiments, in steps S702 to S704, a local maximum search is first performed on the scanned nucleic acid image to obtain a fluorescence image reflecting each fluorescence signal; the fluorescence images corresponding to the multiple fluorescence signals are then Gaussian-fitted and averaged to obtain a point spread function; and the point spread function is Fourier transformed to obtain an optical transfer function. It should be noted that the scanned nucleic acid image can also be filtered using a difference of Gaussian function, followed by a local maximum search to extract individual fluorescent globules corresponding to each base, forming a fluorescence image containing multiple fluorescent globules. The point spread function is then obtained through Gaussian fitting and averaging, and the optical transfer function of the system is then obtained through Fourier transformation.

[0122] In the disclosed embodiment illustrated by steps S701 to S704, a simulated nucleic acid sample is first scanned and imaged to obtain a scanned nucleic acid image. A local maximum search is then performed based on the scanned nucleic acid image to obtain a fluorescence image reflecting each fluorescence signal. The fluorescence images corresponding to the multiple fluorescence signals are Gaussian-fitted and averaged to obtain a point spread function (PSF). Finally, the PSF is Fourier transformed to obtain an optical transfer function (OTF). The resulting OTF can be used to more accurately model the imaging performance of an optical system.

[0123] 8(a) to 8(g) provide some embodiments of the present disclosure for obtaining optical transfer functions. It can be emphasized that the nucleic acid molecules in the simulated nucleic acid sample include multiple bases, each of which is labeled with a fluorescent signal.

[0124] In FIG8( a ), the simulated nucleic acid sample is scanned and imaged to obtain a scanned nucleic acid image. The scanned nucleic acid image shown in FIG8( a ) includes a plurality of fluorescent microspheres discretely distributed on a sequencing chip loaded with the simulated nucleic acid sample.

[0125] In FIG8( b ), the region where the fluorescent microspheres are located is extracted based on the scanned nucleic acid image;

[0126] In Figure 8(c), a filtering algorithm (e.g., local maximum search) is used to extract sparse, discrete regions of individual fluorescent globules that meet the requirements, and a fluorescence image reflecting each fluorescence signal is obtained;

[0127] FIG8( d ) shows one of the fluorescence images of a single fluorescent microsphere, and FIG8( e ) shows another fluorescence image of a single fluorescent microsphere;

[0128] A Gaussian function is used to fit the intercepted single fluorescent bead image to obtain the image center, and multiple fluorescent bead images are aligned and averaged. That is, the fluorescence images corresponding to multiple fluorescence signals are Gaussian-fitted and averaged to obtain the point spread function;

[0129] FIG8(f) and FIG8(g) are schematic diagrams of obtaining the optical transfer function by performing Fourier transform on the point spread function.

[0130] In some embodiments, step S603 integrates pixel size with the optical transfer function to obtain simulated optical calibration information. It can be explained that pixel size is used to establish a mapping from the simulated nucleic acid sample to the camera imaging space, and the optical transfer function is used to model the imaging performance of the optical system. By integrating pixel size with the optical transfer function, it is possible to obtain an image acquisition process for the simulated optical system that simulates the preset optical sequencing system, thereby determining the simulated optical calibration information.

[0131] 9 , according to some embodiments of the present disclosure, step S603 integrates the pixel size with the optical transfer function to obtain simulated optical calibration information, which may include, but is not limited to, steps S901 to S902 .

[0132] Step S901, performing noise extraction on the blank areas between nucleic acid molecules in the simulated nucleic acid sample to obtain simulated noise information;

[0133] Step S902 : Integrate the pixel size, optical transfer function, and simulated noise information to obtain simulated optical calibration information.

[0134] Through the embodiment shown in steps S901 to S902, noise extraction is performed on the blank areas between the nucleic acid molecules in the simulated nucleic acid sample to obtain simulated noise information, and then the pixel size, optical transfer function and simulated noise information are integrated to obtain simulated optical calibration information. It can be explained that the blank areas between the nucleic acid molecules in the simulated nucleic acid sample do not contain nucleic acids that can be sequenced, so the blank areas between the nucleic acid molecules are suitable for extracting noise therefrom to obtain simulated noise information. The embodiment of the present disclosure aims to incorporate the optical noise during image acquisition by the preset optical sequencing system into the consideration of simulation modeling, improve the accuracy of the simulation of nucleic acid distribution information by the optical calibration information, and obtain a higher quality simulated nucleic acid image.

[0135] In some more specific embodiments, optical noise can be extracted manually or algorithmically. During manual extraction, the image software can be used to read the average signal value bg_ave and standard deviation bg_std of the blank area on the tracking line, as well as the maximum average value sig of the nucleic acid molecule area. During algorithmic extraction, the algorithm can automatically locate the tracking line and blank area and extract the corresponding signal. During noise simulation, normalized Gaussian noise can be first generated for each pixel, with an average value of bg_ave / sig and a standard deviation of bg_std / sig. The Gaussian noise can then be added to the simulated signal and the pixel value of the superimposed shot noise calculated using the Poisson distribution function.

[0136] Referring to the embodiment shown in FIG10 , a more specific embodiment of the present disclosure is provided for determining the average signal value bg_ave and standard deviation bg_std of the blank region signal, and the average maximum value sig of the nucleic acid region signal. In FIG10 , the white box represents the tracking line background area, and the average signal value and standard deviation of the signal in this area are measured as bg_ave and bg_std. The white cross indicates the bright spot as the nucleic acid molecule signal. The brightness of the center position of 10 bright spots is measured and the average value is sig.

[0137] In the embodiment of the present disclosure illustrated by steps S601 to S603, the pixel size of the preset optical sequencing system is first determined; wherein the pixel size is the size of a single pixel corresponding to the imaging plane in the preset optical sequencing system; optical imaging analysis processing is performed based on the fluorescence signal corresponding to the base in the simulated nucleic acid sample to obtain the optical transfer function; the pixel size and the optical transfer function are then integrated to obtain optical calibration information. The pixel size in the optical calibration information can be used to establish a mapping from the simulated nucleic acid sample to the camera imaging space, and the optical transfer function in the optical calibration information can be used to model the imaging performance of the optical system. It should be understood that the optical calibration information obtained in this way helps to simulate the nucleic acid distribution information more accurately and obtain a higher-quality simulated nucleic acid image.

[0138] In some embodiments, step S502 simulates the nucleic acid distribution information based on the simulated optical calibration information to obtain a simulated nucleic acid image. It should be noted that after simulating the optical calibration information of the preset optical sequencing system, the nucleic acid distribution information can be simulated based on the simulated optical calibration information to obtain a simulated nucleic acid image. Since the simulated optical calibration information is obtained by simulating the preset optical sequencing system, the simulated nucleic acid image can more realistically simulate the actual acquisition of the sequencing image.

[0139] 11 , according to some embodiments of the present disclosure, step S502 simulates the nucleic acid distribution information based on the simulated optical calibration information to obtain a simulated nucleic acid image, which may include, but is not limited to, the following steps S1101 to S1103 .

[0140] Step S1101, mapping nucleic acid distribution information to an imaging space based on pixel size to obtain a first simulated image of a simulated nucleic acid sample in the imaging space;

[0141] Step S1102, performing imaging performance simulation on the first simulation image based on the optical transfer function to obtain a second simulation image;

[0142] Step S1103 : performing environmental noise simulation on the second simulated image based on the simulated noise information to obtain a simulated nucleic acid image.

[0143] In steps S1101 to S1103 of some embodiments, the nucleic acid distribution information is first mapped to the imaging space based on the pixel size to obtain a first simulated image of the simulated nucleic acid sample in the imaging space; then, the imaging performance of the first simulated image is simulated based on the optical transfer function to obtain a second simulated image; and the environmental noise of the second simulated image is simulated based on the simulated noise information to obtain a simulated nucleic acid image. It can be explained that the pixel size is used to establish a mapping of the simulated nucleic acid sample to the camera imaging space. Therefore, the nucleic acid distribution information can be mapped to the imaging space based on the pixel size to obtain the first simulated image of the simulated nucleic acid sample in the imaging space. Since the optical transfer function is used to model the imaging performance of the optical system, the imaging performance of the first simulated image can be simulated based on the optical transfer function to obtain the second simulated image. Furthermore, since the simulated noise information is the optical noise when the preset optical sequencing system performs image acquisition, the environmental noise can be simulated for the second simulated image based on the simulated noise information, and finally the simulated nucleic acid image is obtained. It should be understood that, based on the optical calibration information including pixel size, optical transfer function and simulated noise information, the optical calibration information helps to more accurately simulate the preset optical sequencing system. The simulated nucleic acid image obtained in this way can more realistically simulate the actual acquisition of the sequencing image.

[0144] Referring to some more specific embodiments shown in Figures 12(a) to 12(c), during simulation, the distribution of nucleic acid molecules in each imaging field of view can be first determined, and a simulated nucleic acid molecule list can be generated, as shown in Figure 12(a); the nucleic acid molecule list can be mapped to a two-color or four-color imaging space, as shown in Figure 12(b), which is mapping the nucleic acid molecule list to a four-color imaging space; the mapped image can then be low-pass filtered using the measured optical transfer function, and finally simulated noise can be added to obtain a sequencing image close to the low-resolution during nucleic acid molecule sequencing, that is, a simulated nucleic acid image, as shown in Figure 12(c).

[0145] In some more specific embodiments, when performing multiple rounds of simulation, the actual signal and noise levels are extracted based on the images actually captured by the system, and the decrease in signal-to-noise ratio in long-cycle sequencing can also be simulated.

[0146] In the disclosed embodiment illustrated in steps S501 and S502, optical calibration information of a preset optical sequencing system is first simulated, and then nucleic acid distribution information is simulated based on the simulated optical calibration information to obtain a simulated nucleic acid image. Using the optical calibration information obtained by simulating the preset optical sequencing system in the simulated nucleic acid image helps improve the simulation effect, allowing the simulated nucleic acid image to more realistically simulate the actual acquisition conditions of the sequencing image.

[0147] In step S403 of some embodiments, the true value image of the nucleic acid molecule and the simulated nucleic acid image corresponding to the true value image of the nucleic acid molecule are input into the original image processing model to iteratively train the image processing model. It can be explained that the simulated nucleic acid image is an image simulated based on the simulated nucleic acid sample corresponding to the true value image of the nucleic acid molecule, which can more realistically simulate the acquisition of the sequencing image. Inputting the simulated nucleic acid image into the original image processing model for training helps to make the trained image processing model adaptable to super-resolution processing of the sequencing image; the true value image of the nucleic acid molecule can reflect the real and accurate arrangement of the base sequence in the simulated nucleic acid sample. Inputting the simulated nucleic acid image into the original image processing model for training can improve the super-resolution processing capability of the image processing model. Therefore, inputting the true value image of the nucleic acid molecule and the simulated nucleic acid image corresponding to the true value image of the nucleic acid molecule into the original image processing model and iteratively training the image processing model can continuously improve the super-resolution processing capability of the image processing model for the image during the iterative training, and make the image processing model adaptable to super-resolution processing of the sequencing image.

[0148] 13 , according to some embodiments of the present disclosure, step S403 inputs the true value image of the nucleic acid molecule and the simulated nucleic acid image corresponding to the true value image of the nucleic acid molecule into the original image processing model, and iteratively trains the image processing model, which may include, but is not limited to, the following steps S1301 to S1303:

[0149] Step S1301: In each round of iterative training, the simulated nucleic acid image is input into the image processing model for image processing training to obtain the processing results of this round;

[0150] Step S1302, comparing the processing result of this round with the true value image of the nucleic acid molecule to obtain training deviation data;

[0151] Step S1303: Update the weight parameters of the image processing model based on the training deviation data.

[0152] In step S1301 of some embodiments, in each round of iterative training, the simulated nucleic acid image is input into the image processing model for image processing training to obtain the processing results of the current round. It can be explained that because the simulated nucleic acid image is an image simulated based on a simulated nucleic acid sample corresponding to the true nucleic acid molecule image, it can more realistically simulate the acquisition of sequencing images. Furthermore, the multiple rounds of iterative training are intended to optimize the super-resolution processing capabilities of the image processing model. Therefore, in each round of iterative training, the simulated nucleic acid image can be input into the image processing model for image processing training to obtain the processing results of the current round.

[0153] In step S1302 of some embodiments, the results of the current round of processing are compared with the true image of the nucleic acid molecule to obtain training deviation data. It can be explained that the true image of the nucleic acid molecule can reflect the real and accurate arrangement of the base sequence in the simulated nucleic acid sample. Therefore, the results of the current round of processing obtained in each round of iterative training can be compared with the true image of the nucleic acid molecule. In this way, training deviation data between the results of the current round of processing and the true image of the nucleic acid molecule is obtained. It can be pointed out that when the training deviation data between the results of the current round of processing and the true image of the nucleic acid molecule reflects that the closer the results of the current round of processing are to the true image of the nucleic acid molecule, it means that the image processing model has a better effect in improving the resolution, and the image processing model has a stronger super-resolution processing capability for the image.

[0154] In step S1303 of some embodiments, the weight parameters of the image processing model are updated based on the training deviation data. It can be explained that after obtaining the training deviation data, the weight parameters of the image processing model can be updated. It can be explained that there are generally two types of parameters in a neural network model: one type of parameter is the tuning parameters in the machine learning algorithm, which can be flexibly set based on existing or existing experience, also known as hyperparameters. For example, the regularization coefficient λ and the depth of the tree in the decision tree model. A hyperparameter is also a parameter that has the characteristics of a parameter, such as unknownness, that is, it is not a known constant, but a configurable value that can be assigned a "correct" value based on existing or existing experience, that is, a flexibly set value that is not learned by the system; the other type of parameter can be learned and estimated from the data, called model parameters, that is, the learnable parameters of the model itself. For example, the weight coefficient (slope) and the bias term (intercept) of the linear regression line are both model parameters. Learnable parameters specifically refer to parameter values ​​learned during the training process of the neural network model. For learnable parameters, they usually start from a set of random values, and then update these values ​​in an iterative manner as the neural network model learns. In fact, when the "neural network model is learning", it is more accurate to mean that the parameters of the neural network model are in the process of iterative update, and the appropriate values ​​of these parameters are gradually determined. It can be pointed out that the so-called appropriate values ​​can be values ​​that minimize or converge the loss function. Therefore, in some embodiments of the present disclosure, in order to gradually determine the appropriate values ​​of these model parameters during the iterative update of the data classification model, the weight parameters of the image processing model can be updated based on the training bias data.

[0155] In the disclosed embodiment illustrated by steps S1301 to S1303, in each round of iterative training, the simulated nucleic acid image is input into the image processing model for image processing training, resulting in the current round of processing results. This processing result is then compared with the true value image of the nucleic acid molecule to obtain training deviation data. Based on the training deviation data, the weight parameters of the image processing model are then updated. In this way, the image processing model's super-resolution processing capabilities for images can be continuously optimized over multiple rounds of iterative training.

[0156] In step S404 of some embodiments, when the image processing model meets the first predetermined condition during iterative training, a trained image processing model is obtained. It can be explained that when the image processing model meets the first predetermined condition during iterative training, it means that the image processing model's super-resolution processing capability for images has reached the expected level for practical application, and the image processing model is adaptable to super-resolution processing of sequencing images. In this case, iterative training of the image processing model is terminated, and the trained image processing model is obtained.

[0157] In some embodiments, the image processing model meets the first predetermined condition during iterative training, which may be that after the image processing model performs image processing training on the simulated nucleic acid image during iterative training, the processing result reaches the resolution level of the true image of the nucleic acid molecule; the image processing model meets the first predetermined condition during iterative training, which may be that the image processing model's super-resolution processing capability for the image converges to a certain level during iterative training.

[0158] According to some more specific embodiments of the present disclosure, step S404, when the image processing model meets the first predetermined condition during iterative training, obtaining the trained image processing model, may include, but is not limited to: when the training deviation data reflects that the image processing model has converged during the iterative training, determining that the image processing model meets the first predetermined condition during the iterative training, and obtaining the trained image processing model. It can be explained that when the training deviation data reflects that the image processing model has converged during the iterative training, it means that the image processing model's super-resolution processing capability for images has been optimized to a current limit level and is difficult to further improve. At this time, it can be determined that the image processing model meets the first predetermined condition during the iterative training, and the trained image processing model is obtained.

[0159] It should be understood that there are various embodiments for determining whether the image processing model meets the first predetermined condition during iterative training, which may include, but are not limited to, the specific embodiments listed above.

[0160] In the embodiment of the present disclosure shown by steps S401 to S404, a true image of a nucleic acid molecule is first constructed based on a simulated nucleic acid sample; then, a simulated sequencing is performed based on the simulated nucleic acid sample through a simulated optical system to obtain a simulated nucleic acid image; the true image of the nucleic acid molecule and the simulated nucleic acid image corresponding to the true image of the nucleic acid molecule are input into the original image processing model, and the image processing model is iteratively trained; when the image processing model meets the first predetermined condition in the iterative training, a trained image processing model is obtained. In this way, the image processing model can be trained to improve the super-resolution processing capability of the image processing model for the image until the super-resolution processing capability of the image processing model for the image has reached the expected level that can be applied in practice, and the image processing model can be adapted to perform super-resolution processing on the sequencing image. On this basis, the trained image processing model is used for image processing of the sequencing image, which helps to improve the image resolution and helps to reduce the crosstalk caused by the fluorescence signals of adjacent nucleic acid molecules when the spacing between nucleic acid molecules is less than the resolution of the imaging system. In this way, the accuracy of base calling can be effectively improved in the process of sequencing nucleic acid molecules.

[0161] Next, two more specific examples are provided to illustrate the technical effects of the nucleic acid molecule sequencing method disclosed herein.

[0162] Specific embodiment 1: sequencing a multi-spaced nucleic acid molecule chip on a sequencer optical machine.

[0163] The sequencer uses a 0.8NA air microscope, with an optical resolution of approximately 500-600nm and a sampling resolution of 566nm. During normal operation, the nucleic acid molecular spacing used is 715nm. When sequencing an E. coli genomic library, the single-strand alignment rate for 100 cycles (SE100) can reach over 90%. Based on this, this specific example will sequence a multi-spacing sequencing chip (576nm, 480nm, 450nm).

[0164] First, nucleic acid molecule patterns with spacings of 576nm, 480nm, and 450nm were generated based on the chip template. Ground truth images of nucleic acid molecules from multiple rounds of sequencing and corresponding simulated nucleic acid images were generated to train the image processing model. Taking the 480nm chip template as an example, each imaging field of view (FoV) consists of 100 blocks (10x10). Each block contains 145, 120, 180, 210, 240, 240, 210, 180, 120, and 145 rows / columns of nucleic acid molecules, respectively. The tracking line width between adjacent blocks is 1440nm. First, a list of nucleic acid molecules required for simulation was generated based on the template. The nucleic acid molecules were then mapped into the corresponding four-color imaging space using the measured pixel size of 566nm.

[0165] The nucleic acid molecules on the sequencing chip are sequenced on a sequencer, and multiple rounds of sequencing images are captured. The signal-to-noise ratio of each image is extracted, and simulated data pairs are generated based on the system's optical transfer function and signal-to-noise ratio to train the image processing model.

[0166] After the resequencing image is processed by the image processing model, base interpretation and comparison are performed on the target image.

[0167] 14 , the sequencing results show that after sequencing a multi-spacing nucleic acid molecule chip using the nucleic acid molecule sequencing method disclosed herein, the alignment rate of nucleic acid molecules with a spacing of 576 nm can reach 90%, and the alignment rate of nucleic acid molecules with a spacing of 480 nm can reach 75%, an 18% improvement compared to traditional algorithms.

[0168] Specific embodiment 2: Sequencing a multi-spacing nucleic acid molecule chip on a self-built high-sampling optical machine.

[0169] The self-built high-sampling optical machine uses a 0.8NA air mirror, with an optical resolution of approximately 500-600nm and a sampling resolution of 260nm. The nucleic acid molecular spacing used in normal use is 715nm.

[0170] When sequencing an E. coli genomic library using the disclosed nucleic acid molecular sequencing method, a single-stranded 100-round (SE100) alignment rate of over 90% was achieved. The disclosed nucleic acid molecular sequencing method was used to sequence a multi-spacing sequencing chip (576 nm, 480 nm, 450 nm, 400 nm, 360 nm). The implementation steps are similar to those in the aforementioned Specific Example 1.

[0171] Referring to Figure 15, the final sequencing results show that compared with the traditional algorithm, the alignment rates of nucleic acid molecules with 576nm spacing, 480nm spacing, 450nm spacing, 400nm spacing and 360nm spacing using the algorithm described in this technical solution are increased by 10%, 14%, 18%, 17% and 24% respectively.

[0172] 16 , according to some embodiments, the present disclosure provides a nucleic acid molecule sequencing device 1600, comprising:

[0173] An image acquisition module 1601 is used to acquire a sequencing image of a target nucleic acid sample. The sequencing image is an image acquired by capturing an image of the target nucleic acid sample using a preset optical sequencing system.

[0174] Image processing module 1602 is configured to perform image processing on the sequencing image based on an image processing model to obtain a target image. The image processing model is a model trained using a constructed true nucleic acid molecule image and a corresponding simulated nucleic acid image. The simulated nucleic acid image is an image obtained by simulated sequencing of a simulated nucleic acid sample corresponding to the true nucleic acid molecule image using a simulated optical system. The simulated optical system is an optical system simulated from a preset optical sequencing system.

[0175] The sequence determination module 1603 is used to perform nucleic acid molecule sequencing according to the target image to obtain a sequencing result corresponding to the target nucleic acid sample.

[0176] It can be seen that the contents of the above-mentioned nucleic acid molecule sequencing method embodiment are all applicable to the embodiment of the present nucleic acid molecule sequencing device. The functions specifically implemented by the present nucleic acid molecule sequencing device embodiment are the same as those of the above-mentioned nucleic acid molecule sequencing method embodiment, and the beneficial effects achieved are also the same as those achieved by the above-mentioned nucleic acid molecule sequencing method embodiment.

[0177] 17 , which illustrates a hardware structure of an electronic device according to another embodiment, the electronic device includes:

[0178] The processor 1701 may be implemented as a general-purpose CPU (Central Processing Unit), a microprocessor, an application-specific integrated circuit (ASIC), or one or more integrated circuits to execute relevant programs to implement the technical solutions provided by the embodiments of the present disclosure.

[0179] The memory 1702 can be implemented in the form of a read-only memory (ROM), a static storage device, a dynamic storage device, or a random access memory (RAM). The memory 1702 can store an operating system and other application programs. When the technical solutions provided in the embodiments of this specification are implemented through software or firmware, the relevant program code is stored in the memory 1702 and is called by the processor 1701 to execute the nucleic acid molecule sequencing method of the embodiments of the present disclosure.

[0180] Input / output interface 1703, used to implement information input and output;

[0181] Communication interface 1704, used to implement communication interaction between this device and other devices, which can be achieved through wired means (such as USB, network cable, etc.) or wireless means (such as mobile network, WiFi, Bluetooth, etc.);

[0182] Bus 1705 , which transmits information between each component of the device (e.g., processor 1701 , memory 1702 , input / output interface 1703 , and communication interface 1704 );

[0183] The processor 1701 , the memory 1702 , the input / output interface 1703 and the communication interface 1704 are connected to each other in communication within the device via a bus 1705 .

[0184] The present disclosure also provides a computer program product, which includes a computer program. A processor of a computer device reads and executes the computer program, so that the computer device executes the above-mentioned nucleic acid molecule sequencing method.

[0185] The terms "first," "second," "third," "fourth," and the like (if any) in the specification of the present disclosure and the accompanying drawings are used to distinguish similar objects and are not necessarily used to describe a particular order or precedence. It is understood that the terms used in this manner are interchangeable where appropriate, so that the embodiments of the present disclosure described herein, for example, can be implemented in orders other than those illustrated or described herein. In addition, the terms "comprises" and "comprising," and any variations thereof, are intended to cover non-exclusive inclusions, e.g., a process, method, system, product, or apparatus comprising a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such process, method, product, or apparatus.

[0186] It should be understood that in the present disclosure, "at least one (item)" refers to one or more, and "plurality" refers to two or more. "And / or" is used to describe the association relationship of associated objects, indicating that three relationships may exist. For example, "A and / or B" can mean: only A exists, only B exists, and A and B exist at the same time, where A and B can be singular or plural. The character " / " generally indicates that the previous and next associated objects are in an "or" relationship. "At least one of the following items" or similar expressions refers to any combination of these items, including any combination of single items or plural items. For example, at least one of a, b or c can mean: a, b, c, "a and b", "a and c", "b and c", or "a and b and c", where a, b, c can be single or multiple.

[0187] It should be understood that in the description of the embodiments of the present disclosure, the meaning of multiple (or multiple items) is more than two, greater than, less than, exceed, etc. are understood to exclude the number itself, and above, below, within, etc. are understood to include the number itself.

[0188] In the several embodiments provided in the present disclosure, it can be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of units is only a logical function division. There may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be an indirect coupling or communication connection through some interfaces, devices or units, which can be electrical, mechanical or other forms.

[0189] The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple network units. Some or all of the units may be selected based on practical needs to achieve the purpose of this embodiment.

[0190] In addition, each functional unit in each embodiment of the present disclosure may be integrated into a single processing unit, each unit may exist physically separately, or two or more units may be integrated into a single unit. The aforementioned integrated units may be implemented in the form of hardware or software functional units.

[0191] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present disclosure is essentially or the part that contributes to the prior art or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including multiple instructions for enabling a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of each embodiment method of the present disclosure. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM), random access memory (RAM), disk or optical disk, etc. Various media that can store program codes.

[0192] It should also be understood that the various implementations provided in the embodiments of the present disclosure can be combined arbitrarily to achieve different technical effects.

[0193] The above is a specific description of the implementation methods of the present disclosure, but the present disclosure is not limited to the above implementation methods. Those skilled in the art can make various equivalent modifications or substitutions without violating the spirit of the present disclosure. These equivalent modifications or substitutions are all included in the scope defined by the claims of the present disclosure.

Claims

1. [Corrected according to Rule 91 on 15.07.2024] A method for nucleic acid molecule sequencing, characterized in that, Including: Obtain a sequencing image of a target nucleic acid sample, where the sequencing image is an image obtained by collecting an image of the target nucleic acid sample using a preset optical sequencing system; Perform image processing on the sequencing image based on an image processing model to obtain a target image. The image processing model is a model trained using a constructed true nucleic acid molecule image and a corresponding simulated nucleic acid image. The simulated nucleic acid image is an image obtained by performing simulated sequencing on a simulated nucleic acid sample corresponding to the true nucleic acid molecule image using a simulated optical system, and the simulated optical system is an optical system obtained by simulating the preset optical sequencing system; Perform nucleic acid molecule sequencing according to the target image to obtain a sequencing result corresponding to the target nucleic acid sample.

2. The method according to claim 1, wherein Before performing image processing on the sequencing image based on the image processing model to obtain a target image, it further includes training the image processing model, including: Construct the true nucleic acid molecule image based on the simulated nucleic acid sample; Perform simulated sequencing on the simulated nucleic acid sample through the simulated optical system to obtain the simulated nucleic acid image; Input the true nucleic acid molecule image and the simulated nucleic acid image corresponding to the true nucleic acid molecule image into the original image processing model, and perform iterative training on the image processing model; When the image processing model meets a first predetermined condition during iterative training, obtain the trained image processing model.

3. The method according to claim 2, wherein The performing simulated sequencing on the simulated nucleic acid sample through the simulated optical system to obtain the simulated nucleic acid image includes: Simulate the optical calibration information of the preset optical sequencing system; Perform simulation on the nucleic acid distribution information based on the simulated optical calibration information to obtain the simulated nucleic acid image.

4. The method according to claim 3, wherein The nucleic acid molecules in the simulated nucleic acid sample include multiple bases, and each base is labeled with a fluorescence signal; The simulating the optical calibration information of the preset optical sequencing system includes: Determine the pixel size of the preset optical sequencing system; where the pixel size is the size corresponding to a single pixel in the imaging plane of the preset optical sequencing system; Perform optical imaging analysis processing on the fluorescence signals corresponding to the bases in the simulated nucleic acid sample to obtain an optical transfer function; Integrate the pixel size and the optical transfer function to obtain the simulated optical calibration information.

5. The method according to claim 4, wherein The performing optical imaging analysis processing on the fluorescence signals corresponding to the bases in the simulated nucleic acid sample to obtain an optical transfer function includes: Perform scanning imaging on the simulated nucleic acid sample to obtain a scanned nucleic acid image; Perform local maximum search on the scanned nucleic acid image to obtain a fluorescence image reflecting each fluorescence signal; Perform Gaussian fitting averaging processing on the fluorescence images corresponding to multiple fluorescence signals to obtain a point spread function; Perform Fourier transform on the point spread function to obtain the optical transfer function.

6. The method according to claim 4, characterized in that The integrating the pixel size and the optical transfer function to obtain the simulated optical calibration information includes: Extract noise from the blank areas between the nucleic acid molecules in the simulated nucleic acid sample to obtain simulated noise information; Integrate the pixel size, the optical transfer function, and the simulated noise information to obtain the simulated optical calibration information.

7. The method according to claim 6, wherein Simulating the nucleic acid distribution information based on the simulated optical calibration information to obtain the simulated nucleic acid image, including: Map the nucleic acid distribution information to the imaging space based on the pixel size to obtain a first simulated image of the simulated nucleic acid sample in the imaging space; Perform imaging performance simulation on the first simulated image based on the optical transfer function to obtain a second simulated image; Perform environmental noise simulation on the second simulated image based on the simulated noise information to obtain the simulated nucleic acid image.

8. The method according to claim 2, characterized in that Inputting the true nucleic acid molecule image and the corresponding simulated nucleic acid image into the original image processing model to perform iterative training on the image processing model, including: In each round of iterative training, input the simulated nucleic acid image into the image processing model for image processing training to obtain the processing result of this round; Compare the processing result of this round with the true nucleic acid molecule image to obtain training deviation data; Update the weight parameters of the image processing model based on the training deviation data.

9. The method according to claim 8, characterized in that When the image processing model meets the first predetermined condition in iterative training to obtain the trained image processing model, including: When the training deviation data reflects that the image processing model converges in iterative training, determine that the image processing model meets the first predetermined condition in iterative training to obtain the trained image processing model.

10. A nucleic acid molecule sequencing device, characterized in that, Including: An image acquisition module, configured to acquire a sequencing image of a target nucleic acid sample, where the sequencing image is an image obtained by collecting an image of the target nucleic acid sample using a preset optical sequencing system; An image processing module, configured to perform image processing on the sequencing image based on an image processing model to obtain a target image, where the image processing model is a model trained using a constructed true nucleic acid molecule image and a corresponding simulated nucleic acid image, the simulated nucleic acid image is an image obtained by performing simulated sequencing on a simulated nucleic acid sample corresponding to the true nucleic acid molecule image based on a simulated optical system, and the simulated optical system is an optical system obtained by simulating the preset optical sequencing system; A sequence determination module, configured to perform nucleic acid molecule sequencing according to the target image to obtain a sequencing result corresponding to the target nucleic acid sample.

11. An electronic device, comprising a memory and a processor, the memory storing a computer program, characterized in that, When the processor executes the computer program, it implements the nucleic acid molecule sequencing method according to any one of claims 1 to 9.

12. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed by a processor, it implements the nucleic acid molecule sequencing method according to any one of claims 1 to 9.

13. A computer program product, which includes a computer program, and the computer program is read and executed by a processor of a computer device, so that the computer device executes the nucleic acid molecule sequencing method according to any one of claims 1 to 9.

Images