Apparatus and method for computational compensation of undercorrected aberrations

Abstract

Disclosed are an apparatus and a method that compensate for an under-corrected aberration by calculation. The system includes an excitation radiation source that emits an excitation beam focused on the flow cell surface. More specifically, the excitation beam is focused on an upper surface, on a lower surface, or in a channel between the upper surface and the lower surface of the flow cell. Since simultaneous imaging of both the upper surface and the lower surface will result in aberration in at least one of the upper surface and the lower surface, aberration correction is useful for dual surface imaging. The processor is configured to determine a base detection of an irradiated site that fluoresces within the flow cell. An aberration compensation model is trained to compensate for aberrations in at least one image or image data corresponding to the upper surface, the lower surface, or the channel between the upper surface and the lower surface.

Description

[0001] CROSS-REFERENCE TO RELATED APPLICATIONS

[0002] This application claims the benefit of U.S. Provisional Patent Application Serial No. 63 / 463,200, filed on May 1, 2023, the disclosure of which is incorporated herein by reference in its entirety. Background Art

[0003] Currently, imaging systems are used to detect radiation emissions from biological materials, such as optical fluorescence. The detected optical data often includes aberrations, which can increase the difficulty of base calling in biological materials. Previous systems have used additional optical elements to account for aberrations in the detected optical data (e.g., correction compensator components). Summary of the invention

[0004] Imaging methods and apparatus for detecting radiation emissions on a support structure are provided. The optical train includes imaging optics. The imaging optics are configured to focus the optical train toward the support structure. In some embodiments, the support structure is a flow cell. For example, the support structure can be a multi-surface flow cell. The support structure can include a first surface and a second surface. A first emitting component associated with a biological sample can be disposed on the first surface. A second emitting component associated with the biological sample can be disposed on the second surface.

[0005] In some embodiments, the optical train may include an adjustment optical device. The adjustment optical device may be configured to generate a substantially linear excitation radiation beam from an excitation radiation source. For example, the adjustment optical device may be configured to combine beams from one or more excitation radiation sources and / or modify the geometric pattern of one or more excitation beams (for example, to form a substantially linear excitation line beam, a square excitation beam, a rectangular beam, etc.). In some embodiments, the optical train may include a guide optical device. The guide optical device may be configured to redirect one or more excitation beams from the excitation radiation source. For example, the guide optical device may be configured to redirect one or more excitation beams from the excitation radiation source toward the focusing optical device. In some embodiments, the guide optical device may be configured to redirect one or more excitation beams from the excitation radiation source toward the support structure. Alternatively or additionally, the excitation radiation source may be configured to guide radiation toward one or more of the first emitting component and the second emitting component. For example, the excitation radiation source may be configured to guide radiation along a radiation line toward one or more of the first emitting component and the second emitting component. In some embodiments, the radiation line can be configured to reside between the first emitting component and the second emitting component. The excitation radiation source can be, for example, a laser source, an electron beam source, one or more light emitting diodes (LEDs), a plasma source, an arc lamp, a halogen lamp, or any other excitation radiation source. In some embodiments, the radiation can be excitation radiation. The system can include, for example, only one excitation radiation source.

[0006] Detection optics may be included in the system or method. In some embodiments, the detection optics may be configured to detect radiation emission. The radiation emission may be returned to the detection optics from one or more of the first emission component and the second emission component. In some embodiments, the first emission component may be positioned within the first nanopore, such as a fluorophore or multiple fluorophores associated with a first cluster of substantially monoclonal samples within the first nanopore. The second emission component may be positioned in the second nanopore, such as a fluorophore or multiple fluorophores associated with a second cluster of substantially monoclonal samples within the second nanopore. In some examples, the first nanopore may be located in a first pattern, and the second nanopore may be located in a second pattern. The second nanopore may be different from the first nanopore. The radiation emission may be returned to the imaging sensor of the detection optics, for example, via one or more portions of the optical train. In some embodiments, a translation system may be provided. For example, the translation system may be configured to allow the support structure to be focused and / or moved before and / or during imaging. The translation system may be configured to perform relative motion between the support structure and the optical train and / or the excitation radiation source.

[0007] A focusing optic may be included in the optical train. The focusing optic may be configured to focus radiation onto the surface of the support structure. For example, the focusing optic may be configured to direct radiation confocally onto the surface of the support structure. In some embodiments, the focusing optic may be configured for a single design point for diffraction limited focusing and imaging. For example, the design point may be located at one or more of the first surface, the second surface, and between the first and second surfaces of the support structure. The design point may be midway between the first and second surfaces, or any percentage (e.g., 10%, 20%, etc.) of the distance between the first and second surfaces. In some embodiments, the focusing optic may be defined by a numerical aperture (NA). For example, the numerical aperture may have a value of at least about 0.5, at least about 0.55, at least about 0.6, at least about 0.65, at least about 0.7, at least about 0.75, at least about 0.8, at least about 0.85, at least about 0.9, at least about 0.95, above about 1.0, above about 1.1, above about 1.2, or above about 1.3. In some examples, the focusing optics may be configured to direct radiation confocally on a line, such as by scanning. A time delay integration (TDI) sensor may be used to detect the radiation emission. Alternatively or additionally, the focusing optics may be configured to scan an area, such as in a two-dimensional excitation illumination pattern. The radiation emission may be detected by a two-dimensional image sensor.

[0008] The system may be configured to generate image data. For example, the image data may include one or more of first image data of the first emission component based on the detected radiation and second image data of the second emission component based on the detected radiation. In some embodiments, the detector may be configured to generate image data of the first emission component when the focusing optics directs radiation confocally to the first emission component, and / or to generate image data of the second emission component when the focusing optics directs radiation confocally to the second emission component. Image data of the second emission component may be generated when the focusing optics directs radiation confocally to the first emission component. Image data of the first emission component may be generated when the focusing optics directs radiation confocally to the second emission component. For example, since both the image data of the first emission component and the image data of the second emission component may be generated regardless of where the radiation is directed, refocusing may not be required. The detector may include a charge coupled device (CCD) sensor. For example, the CCD sensor may be configured to generate image data based on one or more locations where photons strike the detector. In some embodiments, the detector may include one or more of a detector array configured for time delay integration (TDI) operation, a complementary metal oxide semiconductor (CMOS) detector, an avalanche photodiode (APD) detector, and a Geiger mode photon counter.

[0009] The system may include a processor configured to determine base calls (e.g., using a base calling algorithm). For example, the processor may be configured to determine base calls of irradiated sites that fluoresce within one or more of the first and second emitting components of the support structure. In some embodiments, the processor may be configured to determine base calls using an aberration compensation model. The aberration compensation model may be trained to compensate for aberrations of one or more of the first and second image data.

[0010] The processor may be configured to use the aberration correction model to generate one or more reconstructed images of a first reconstructed image of the first image data and a second reconstructed image of the second image data. For example, the aberration correction model may compensate for aberrations in one or more of the first image and the second image. In some embodiments, the processor may be configured to determine one or more base calls of base calls of irradiated sites that fluoresce within the first emitting component of the support structure and base calls of irradiated sites that fluoresce within the second emitting component of the support structure. For example, the processor may use a base call algorithm. In some embodiments, the base call algorithm may include the aberration compensation model. For example, the processor may be configured to generate an aberration compensation model using one or more of decoding, deep learning, deep learning, deep Fourier channel attention network (DFCAN), optical transfer function (OTF) inversion, point spread function (PSF), iterative deconvolution, linear deconvolution, or nonlinear deconvolution (e.g., Lucy-Richardson). In some embodiments, the processor may be configured to generate one or more of the first image and the second image without using a correction compensator component. For example, the imaging system may not include a correction compensator component.

[0011] The aberration compensation model may include one or more of a first coefficient for compensating the aberration of the first image data and a second coefficient for compensating the aberration of the second image data. For example, the first coefficient may be based on a distance between a focal point of the focusing optics and the first surface of the support structure. In some examples, the second coefficient may be based on a distance between the focal point of the focusing optics and the second surface of the support structure. BRIEF DESCRIPTION OF THE DRAWINGS

[0012] Figure 1 is a diagram of an example imaging system.

[0013] Figure 2 is a diagram of an example semi-confocal line scanning method for imaging a support structure.

[0014] Figure 3A An example objective lens focused on the bottom surface of a support structure is illustrated.

[0015] Figure 3B An example objective lens focused on the upper surface of a support structure is illustrated.

[0016] Figure 4 An example of a production imaging system for imaging a support structure is illustrated.

[0017] Figure 5 An example of base calling is depicted.

[0018] Fig. 6A and Figure 6B An example of images taken from two surfaces of a support structure is illustrated, where the images have spherical aberration.

[0019] Figure 7 A diagram illustrating a system.

[0020] Figure 8 An example of AI-driven aberration correction of sequenced images using a CNN-based image-to-image autoencoder model is illustrated.

[0021] Fig. 9A and Fig. 9B Example results for base calling based on various defocus levels are illustrated.

[0022] Fig.10 is a block diagram of an example computer system.

[0023] Fig.11 is a flow chart of an example procedure for using an aberration compensation model to determine base calls for irradiated sites that fluoresce within an emitting component of a support structure.

[0024] Fig.12 is a flow chart of an example procedure for using an aberration compensation model to determine base calls for irradiated sites that fluoresce within an emitting component of a support structure. DETAILED DESCRIPTION

[0025] Figure 1An example imaging system 10 is illustrated. The imaging system 10 can be a production imaging system and / or a training imaging system (e.g., an imaging system for training a machine learning model). The imaging system 10 may be capable of imaging one or more biological samples 12, 14 within a support structure 16. For example, in the illustrated embodiment, a first biological sample 12 may be present on a first surface 18 of the support structure 16, and / or a second biological sample 14 may be present on a second surface 20 of the support structure. The support structure 16 may, for example, be a flow cell. The support structure 16 may include an array of biological samples 12, 14 located on one or more inner surfaces of the inner surfaces 18, 20. The inner surfaces may generally face each other. Reagents, rinses, and / or other fluids may be introduced between the first surface and the second surface. For example, a fluid may be introduced to bind nucleotides and / or other molecules to sites of the biological samples 12, 14. The support structure 16 may be manufactured in conjunction with the present technology, or may be purchased or otherwise obtained from a separate entity. The fluorescent label bound to the molecule of the sample may, for example, include a dye that fluoresces when excited by appropriate excitation radiation. In some embodiments, the support structure can be a multi-surface flow cell. In some examples, the fluid introduced into the support structure can only contact / exist on the second surface 20 of the support structure. For example, the fluid can be less than the entire channel depth (e.g., half the flow cell channel depth).

[0026] The assay methods including the use of fluorescent tags and that can be used for the devices or methods described herein may include, for example, genotyping assays, gene expression analysis, methylation analysis, and / or nucleic acid sequencing analysis. Those skilled in the art will recognize that a flow cell or other support structure can be used with any of the various arrays known in the art to achieve similar results. In addition, known methods for making arrays can be used, and, for example, modified according to the teachings set forth herein, to produce a flow cell and / or other support structure with multiple surfaces that can be used for the detection methods set forth herein. The biological components of the sample can be arranged randomly and / or in a predetermined pattern on one or more surfaces of the support to form an array by any known technique. Different surfaces of the support structure may have different nanopore patterns. In some embodiments, the clustered array of nucleic acid colonies can be prepared as described in the following patents: U.S. Patent No. 7,115,400; U.S. Patent Application Publication No. 2005 / 0100900; PCT Publication No. WO 00 / 18957; or PCT Publication No. WO 98 / 44151, each of which is incorporated herein by reference. Such methods are known as bridge amplification or solid phase amplification and are particularly useful for sequencing applications.

[0027] Other random arrays and methods of constructing them that can be used can include, but are not limited to, random arrays of beads associated with a solid support, examples of which are described in U.S. Patent Nos. 6,355,431; 6,327,410; and U.S. Patent No. 6,770,441; U.S. Patent Application Publication Nos. 2004 / 0185483 and US 2002 / 0102578; and PCT Publication No. WO 00 / 63437, each of which is incorporated herein by reference. The beads can be located at discrete locations on the solid support, such as wells, with each location housing a single bead. Other structures and methods of constructing them that can be used can include, but are not limited to, flow cell structures, examples of which are described in U.S. Patent Nos. 9,512,422; and U.S. Patent No. 10,682,829, each of which is incorporated herein by reference.

[0028] The sites or features of the array can be discrete, e.g., spaced apart from each other. The size of the sites and / or the spacing between the sites can vary, such that the array can have sites spaced apart by less than 100 micrometers (μm), 50 μm, 10 μm, 5 μm, 1 μm, 900 nanometers (nm), 800 nm, 700 nm, 600 nm, 500 nm, 400 nm, 350 nm, 300 nm, 250 nm, or 200 nm.

[0029] In some embodiments, the surface used in the device or method can be a manufactured surface. A natural surface or the surface of a natural support structure can also be used; however, the surface may not be a surface of a natural material or a natural support structure. Thus, components of a biological sample can be removed from their native environment and attached to a manufactured surface.

[0030] Any of the various biological samples may be present on the surface. Example samples and / or components include, but are not limited to, nucleic acids (such as, for example, DNA or RNA), proteins (such as enzymes or receptors), polypeptides, nucleotides, amino acids, sugars, cofactors, metabolites or derivatives of these natural samples. Although the apparatus and methods of the present invention are exemplified herein with respect to components of biological samples, it should be understood that other samples or components may also be used. For example, synthetic samples may be used, such as combinatorial libraries, or libraries of compounds with species known or suspected to have a desired structure or function. Therefore, the apparatus or method may be used to synthesize a batch of compounds and / or screen a batch of compounds for a desired structure or function. The terms sample and component are used interchangeably herein.

[0031] Return to Figure 1In an exemplary system, the imaging system 10 may include at least an excitation radiation source 22. The excitation radiation source 22 may be a laser source, an electron beam source, one or more light emitting diodes, a plasma source, an arc lamp, a halogen lamp, or any other excitation radiation source. For example, the laser may operate at different wavelengths. The selection of the laser wavelength may depend on the fluorescent properties of the dye used to image the component site. The multiple different wavelengths of the laser used may allow the dyes at various sites within the support structure 16 to be distinguished, and / or imaging may be performed by continuously acquiring a series of images so that the molecules at the component sites can be identified according to the image processing and reading logic in the art. Other excitation radiation sources may be used, including, for example, an electron beam source, a plasma source, an arc lamp, or a quartz halogen lamp. In some embodiments, the excitation radiation source may generate electromagnetic radiation in the ultraviolet (UV) range (e.g., about 200nm to 390nm), the visible (VIS) range (e.g., about 390nm to 770nm), the infrared (IR) range (e.g., about 0.77 microns to 25 microns), or other ranges of the electromagnetic spectrum.

[0032] For ease of description, the embodiment utilizing fluorescence-based detection is used as an example. However, other detection methods can be used in combination with the apparatus and methods described herein. For example, a variety of different emission types can be detected, such as fluorescence, luminescence or chemiluminescence. Therefore, a sample to be detected can be labeled with a compound or part of fluorescence, luminescence or chemiluminescence. It is also possible to use a signal other than the light signal from one or more surfaces using apparatus and methods similar to those illustrated herein.

[0033] Output from the excitation radiation source 22 can be directed through conditioning optics 26 for filtering and shaping one or more excitation beams. In some embodiments, conditioning optics can be included in the optical train. For example, in some embodiments, conditioning optics 26 can generate a substantially linear radiation beam, such as a reference beam. Figure 2 The radiation beam shown and described, and / or combining excitation beams from multiple excitation radiation sources, such as described in U.S. Pat. No. 7,329,860. In other embodiments, conditioning optics 26 can form a rectilinear footprint, such as a rectangular or square footprint for illumination, a circular footprint, an oval footprint, or any other geometric configuration, such as reference Figure 4 The laser module may include a measurement component that records the power of one or more lasers. The measurement of power may be used as a feedback mechanism. The feedback mechanism may be used to control the length of time that an image is recorded, for example, in order to obtain a uniform exposure and thus a more easily comparable signal.

[0034] The excitation beam may be directed toward the guiding optics 30. In some embodiments, the guiding optics may be included in the optical train. For example, after passing through the conditioning optics 26, one or more excitation beams may be directed toward the guiding optics 30, which may redirect the one or more excitation beams. The guiding optics 30 may be configured to redirect one or more beams from the excitation radiation source. For example, one or more excitation beams may be directed from the excitation radiation source 22 toward the focusing optics 32. The guiding optics 30 may include a dichroic mirror configured to redirect the one or more excitation beams toward the focusing optics 32 and / or allow certain wavelengths of the retrobeam to pass. The focusing optics 32 may confocally direct the radiation to one or more surfaces 18, 20 of the support structure 16, on which the individual biological samples 12, 14 are positioned. For example, the focusing optics 32 may include a microscope objective that confocally directs and focuses the excitation radiation source 22 along a line to the surfaces 18, 20 of the support structure 16. In other implementations, focusing optics 32 may form a rectilinear footprint, such as a rectangular or square footprint for illumination, a circular footprint, an oval footprint, or any other geometric configuration on one or both of surfaces 18, 20. In some embodiments, the guiding optics may be configured to redirect an excitation beam from an excitation radiation source toward a support structure.

[0035] The focusing optics 32 may be included in the optical train. The focusing optics 32 may be configured to focus radiation to a surface of a support structure. For example, the focusing optics 32 may be configured to direct radiation confocally to a surface of a support structure 16. In some embodiments, the focusing optics 32 may be configured for a single design point for diffraction limited focusing and imaging. For example, the design point may be located at one or more of the first surface 18, the second surface 20, between the first surface 18 and the second surface 20, below the second surface 20, or above the first surface 18 of the support structure 16. In some embodiments, the focusing optics 32 may be defined by a numerical aperture (NA). For example, the numerical aperture may have a value of at least about 0.5, at least about 0.55, at least about 0.6, at least about 0.65, at least about 0.7, at least about 0.75, at least about 0.8, at least about 0.85, at least about 0.9, at least about 0.95, above about 1.0, above about 1.1, above about 1.2, or above about 1.3.

[0036] The biological sample may include an emitting component. For example, a first emitting component associated with the biological sample may be disposed on the first surface 18 of the support structure 16, and / or a second emitting component associated with the biological sample may be disposed on the second surface 20 of the support structure 16. The first emitting component or the second emitting component associated with the biological sample site on the support structure 16 may emit fluorescence of a specific wavelength in response to the excitation beam, thereby returning radiation for imaging. For example, the fluorescent component may be generated by a fluorescently labeled nucleic acid that hybridizes with a complementary molecule of the component or with a fluorescently labeled nucleotide incorporated into an oligonucleotide using a polymerase. As described above, the fluorescent properties of these components may be changed by introducing reagents into the support structure 16 (e.g., by cutting the dye from the molecule, blocking the attachment of additional molecules, adding a quenching agent, adding an acceptor for energy transfer, etc.). The wavelength at which the sample dye is excited and / or the wavelength at which the sample dye fluoresces may depend on the absorption and / or emission spectrum of the specific dye. The returned radiation may be propagated back through the guiding optical device 30. The reverse beam may be directed toward the detection optical device 34. For example, the detection optics 34 may filter the beam to separate different wavelengths within the reverse beam and / or direct the reverse beam toward at least one detector 36. For example, two or more detectors as described herein may be provided. In some embodiments, there may be one detector for each specific wavelength and / or wavelength range. Additionally or alternatively, there may be one excitation radiation source for each specific wavelength and / or wavelength range.

[0037] In some embodiments, the detection optical device 34 can be configured to detect radiation emissions. The radiation emissions can be returned to the detection optical device 34 from one or more of the emission components and / or the second emission components. In some embodiments, the first emission component can include a first nanopore pattern, and / or the second emission component can include a second nanopore pattern. The first nanopore pattern can be different from the second nanopore pattern, or can be the same nanopore pattern. The radiation emissions can be returned to the detection optical device 34, for example, via an optical train.

[0038] The detector 36 may be based on any suitable technology and may be, for example, a charge coupled device (CCD) sensor. The detector may generate pixelated image data based on photons striking one or more locations in the detector. However, any of a variety of other detectors may also be used, including but not limited to detector arrays configured for time delay integration (TDI) operation, complementary metal oxide semiconductor (CMOS) detectors, avalanche photodiode (APD) detectors, Geiger mode photon counters, or any other suitable detector. TDI mode detection may be coupled with line scanning, as described in U.S. Pat. No. 7,329,860, which is incorporated herein by reference.

[0039] The detector 36 may generate image data. In some examples, the resolution of the image data may be between 0.1 microns and 50 microns. The image data may be forwarded to the control / processing system 38. The control / processing system 38 may perform various operations, such as (for example) analog-to-digital conversion, scaling, filtering and / or multi-frame data association, to appropriately and accurately image multiple sites at a specific location on the sample. The control / processing system 38 may store the image data and / or may forward the image data to a post-processing system (not shown) for analyzing the data. Depending on the type of sample, the reagents used and the processing performed, the image data may be used in many different ways. For example, nucleotide sequence data may be derived from the image data, and / or the data may be used to determine the presence of a specific gene, characterize one or more molecules at a component site, etc. As described in more detail herein, the system (e.g., a server) may use an aberration compensation model (e.g., an algorithm) configured to compensate for the aberration (e.g., spherical aberration) of the image data received from the imaging system (e.g., from the control / processing system 38) (e.g., spherical aberration of the image data obtained from the emitting components located on two different surfaces of the support structure). Furthermore, as mentioned herein, an imaging system may not include a corrective compensator component.

[0040] Figure 1 The operation of the various elements illustrated in the drawings may also be coordinated with the control / processing system 38. For example, the control / processing system 38 may include hardware, firmware, and / or software as designed. The hardware, firmware, and / or software may control one or more of the operation of the excitation radiation source 22, the movement and focusing of the focusing optics 32, the translation system 40, and the detection optics 34, and the acquisition and processing of signals from the detector 36. The control / processing system 38 may store the processed data and / or further process the data. For example, the data may be used to generate a reconstructed image of the irradiated sites that fluoresce within the support structure 16. The image data may be analyzed by the system and / or may be stored for analysis by other systems and / or at different times after imaging.

[0041] The image data may include one or more of first image data of a first emission component based on the detected radiation emission and second image data of a second emission component based on the detected radiation emission. In some embodiments, the detector may be configured to generate image data of the first emission component when the focusing optical device confocally directs radiation to the first emission component, and / or generate image data of the second emission component when the focusing optical device confocally directs radiation to the second emission component.

[0042] The support structure 16 may be supported on a translation system 40. The translation system 40 may allow the support structure 16 to be focused and / or moved before and / or during imaging. The stage may be configured to move the support structure 16, thereby changing the relative position of the excitation radiation source 22 and the detector 36 relative to the surface-bound biological sample for progressive scanning. The movement of the translation system 40 may be in one or more dimensions, including, for example, one or two dimensions (usually represented as the X dimension and the Y dimension) orthogonal to the propagation direction of the excitation radiation. In some embodiments, the translation system 40 may be configured to move in a direction perpendicular to the scanning axis of the detector array. The translation system 40 may be further configured to move in the dimension (usually represented as the Z dimension) along which the excitation radiation line propagates. Movement in the Z dimension may also be used for focusing. In some examples, multiple detectors may be provided. In other specific implementations, the support structure 16 may remain stationary, and the guide optical device 30 and / or the focusing optical device 32 may be translated orthogonal to the propagation direction of the excitation radiation.

[0043] Figure 2 4 is a diagram of an exemplary semi-confocal line scanning method for imaging the support structure 16. In the illustrated embodiment, the support structure 16 may include an upper substrate 42 and / or a lower substrate 44. An internal volume 46 may be provided between the upper substrate 42 and the lower substrate 44. The upper substrate 42 and the lower substrate 44 may be made of any of a variety of materials, such as a substrate material that is substantially transparent at the wavelength of the excitation radiation and the fluorescent reverse beam, thereby allowing the excitation radiation and the returned fluorescent emission to pass without significant loss of signal quality. One of the surfaces through which the radiation passes may be substantially transparent at the relevant wavelength, while the other surface (which is not passed by the radiation) may be less transparent, translucent, or even opaque or reflective. Both the upper substrate 42 and the lower substrate 44 may contain biological samples 12, 14 on their respective inwardly facing surfaces 18, 20. As discussed herein, the internal volume 46 may, for example, include one or more internal channels of a circulation pool, through which reagent fluids may flow.

[0044] The support structure 16 may be irradiated by the excitation radiation 48 along a radiation line 50. The radiation line 50 may be formed by the excitation radiation 48 from the excitation radiation source 22 and / or guided by the guiding optical device 30 through, for example, the focusing optical device 32. The radiation may be directed toward one or more of the first emitting component and the second emitting component. In some examples, the radiation line 50 may be configured to reside between the first emitting component and the second emitting component. The excitation radiation source 22 may generate one or more excitation beams, or more than one excitation radiation source 22 may be used, and each excitation radiation source may generate a corresponding excitation beam. One or more excitation beams may be processed and / or shaped to provide a linear cross-section, a rectangular cross-section, or any other geometric cross-section, and each radiation line may be a specific radiation wavelength for producing a corresponding wavelength of fluorescence from a dye associated with the biological sample 12, 14, depending on the specific dye used. The focusing optical device 32 may semi-confocally direct the excitation radiation 48 toward the first surface 18 of the support structure 16 to irradiate the dye associated with the site of the biological sample 12 along the radiation line 50. In some embodiments, one or more of the support structure 16, the guide optics 30, the focusing optics 32, or some combination thereof, can be translated so that the resulting radiation line 50 progressively irradiates these components as indicated by arrow 52. The translation can allow for a continuous scan of the area 54. The scanning can allow for progressive irradiation of the entire first surface 18 of the support structure 16. As will be discussed in more detail below, the same process can also be used to progressively irradiate the second surface 20 of the support structure 16. For example, the method can be used for multiple surfaces within the support structure 16.

[0045] Exemplary methods and apparatus for line scanning are described in U.S. Pat. No. 7,329,860, which is incorporated herein by reference, and which describes a line scanning apparatus having a detector array configured to achieve confocality on the scanning axis by limiting the scanning axis size of the detector array. More specifically, the scanning apparatus may be configured so that the detector array has rectangular dimensions, so that the shorter dimension of the detector is in the scanning axis size, and the imaging optics are placed to direct a rectangular image of the sample area to the detector array, so that the shorter dimension of the image is also in the scanning axis size. In some embodiments, semi-confocality may be achieved because confocality occurs on a single axis (e.g., the scanning axis). For example, detection may be specific to features on the surface of a substrate, thereby rejecting signals that may be generated by a solution around the feature. The apparatus and method described in U.S. Pat. No. 7,329,860 may be modified so that two or more surfaces of a support are scanned according to the description herein. The optical train may include imaging optics. For example, the imaging optics may be configured to focus the optical train toward the support structure.

[0046] Detection devices and methods other than line scanning may also be used. For example, point scanning may be used as described in U.S. Pat. No. 5,646,411, which is incorporated herein by reference. In some embodiments, wide-angle area detection may be used with or without scanning motion.

[0047] Roughly like Figure 2 As shown in , the radiation line 50 used to irradiate the fluorescent dye to be imaged associated with the site of the biological sample 12, 14 can be a continuous or discontinuous line. Therefore, some embodiments may include a discontinuous line composed of multiple confocal and / or semi-confocally directed excitation radiation beams that can irradiate multiple points along the radiation line 50. The discontinuous excitation beams can be generated by one or more sources, which can be positioned or scanned to provide excitation radiation 48. The excitation beam can be directed confocally or semi-confocally toward the first surface 18 or the second surface 20 of the support structure 16 to irradiate the site of the biological sample 12, 14. As with the continuous semi-confocal line scanning herein, the support structure 16, the guiding optical device 30, the focusing optical device 32, or some combination thereof can be advanced as shown by arrow 52 to irradiate a continuous scan area 54 along the first surface 18 or the second surface 20 of the support structure 16, and thereby irradiate a continuous area of ​​the site of the biological sample 12, 14.

[0048] In some embodiments, the system 10 can simultaneously form and direct the excitation and return radiation for imaging. For example, confocal scanning can be used so that the optical train guides the excitation pattern through the biological sample by scanning the excitation beam through the objective lens. For example, the detector can image the emission from the excitation area on the detector without "de-scanning" the reverse beam. The reason why this may happen is that the reverse beam is collected by the objective lens and / or separated from the excitation beam optical path before returning through the scanning device. When the excitation pattern is scanned across the sample, the image of the excitation pattern at the detector 36 can appear in the shape of a line. The reverse beam of radiation is different from the wavelength of the excitation beam. Alternatively or additionally, the emission signals can be collected sequentially after sequential excitation of different wavelengths.

[0049] In some embodiments, the system 10 may be at least about 0.01 mm 2 Faster rates may also be used, including, for example, at least about 0.02 mm in area scanned or otherwise inspected. 2 / sec、0.05mm 2 / sec、0.1mm 2 / sec、1mm 2 / sec、1.5mm 2 / sec、5mm 2 / sec、10mm 2 / sec、50mm 2 / sec、100mm 2 / sec or faster. If desired, for example to reduce noise, the detection rate may be about 0.05mm / sec. 2 / sec、0.1mm 2 / sec、1mm 2 / sec、1.5mm 2 / sec、5mm 2 / sec、10mm 2 / sec、50mm 2 / sec or 100mm 2 The upper limit of / sec.

[0050] Figure 3A An example objective lens 300 is illustrated focusing on the bottom surface (surface 2) of a support structure (e.g., a flow cell), and Figure 3B An example objective lens 300 is illustrated focusing on an upper surface (surface 1) of a support structure (e.g., a flow cell). Objective lens 300 can focus on and detect a bottom surface (e.g., Figure 3A ) or an upper surface (e.g., as shown in Figure 3B ) of the image. Positioning one or more of the optical train, the flow cell, and the excitation radiation source can shift the focus of the objective lens 300 to the top surface or the bottom surface. For example, optical components can be inserted into the optical train and / or removed from the optical train to compensate for the focus between the top surface and the bottom surface. Alternatively or additionally, optical components within the tube lens can be moved to compensate for the focus between the top surface and the bottom surface, such as described in U.S. Patent Publication No. 2018 / 0259768, entitled "Continuous Spherical Aberration Corrected Tube Lens," published on September 13, 2018, the disclosure of which is incorporated herein by reference in its entirety. The excitation beam 370 can be focused and / or delivered to any location on the support structure. For example, the excitation beam 370 may be focused and / or delivered to one or more locations between the top surface (or surface 1) and the bottom surface (or surface 2), a location on the top surface (or surface 1), a location on the bottom surface (or surface 2), a location above the top surface (or surface 1), or a location below the bottom surface (or surface 2). Additionally or alternatively, the excitation beam 370 may be focused and / or delivered to one or more locations within the upper substrate and / or the lower substrate (e.g., Figure 2 ).

[0051] Figure 4An example of an imaging system 400 for imaging a functional structure (e.g., a flow cell) such as flow cell 402 and example opportunities for flow cell image improvement, enhancement, refinement, and / or other operations, such as enabling improved base calling during sequencing by synthesis, are shown. Flow cell 402 can be generally planar and / or include a plurality of generally parallel channels that are imaged sequentially (e.g., as shown in the present invention). Figure 4 ) is a series of tiles or one or more consecutively imaged columns (e.g., as shown in Figure 2 ) and processed as a series of one or more tiles 406. Imager 414 may include one or more of sensor 408, semi-reflective mirror 410, and objective lens 412. In some examples, one or more excitation radiation sources (e.g., laser 404 or LED) and imager 414, as well as a mirror 416 positioned to direct the emission of laser 404 toward semi-reflective mirror 410, may be arranged in a module.

[0052] As the imager 414 is repositioned from one tile to the next (e.g., a "step" of a step-and-shoot), and then one or more lasers 404 illuminate tiles 406 of the flow cell 402 to excite fluorescence, which is then imaged by the sensor 408 of the imager 414 (e.g., a "shot" of a step-and-shoot), or as the flow cell 402 and / or imager 414 moves along one or more columns (e.g., a continuous line scan) and the excited fluorescence is imaged by the sensor 408 of the imager 414. Improved flow cell imaging includes, for example, flow cell image improvement, enhancement, refinement, and / or other operations, such as to enable improved base calling during sequencing by synthesis.

[0053] In some embodiments, the imager 414 and the circulation cell 402 move relative to each other (e.g., such as by advancing the circulation cell 402 on a movable platform along a predetermined path, or by repositioning the imager 414 and the laser 404 relative to the circulation cell 402 when capturing an image), as indicated by the movement of the arrow imager relative to the circulation cell. For example, in a point-and-shoot camera implementation, a previously imaged tile 418 and a tile 406 (e.g., imaged with a reduced / unreduced tile time) may represent two consecutive elements of a series of tiles imaged one after another. In a continuous scan implementation, a previously imaged tile 418 and a tile 406 (e.g., imaged with a reduced / unreduced tile time) may represent two adjacent regions of a portion of a channel (or a column thereof) of the circulation cell 402, which correspond to elements of a series of tiles.

[0054] In some embodiments, the movable platform (e.g., sometimes referred to as a stage) includes a circulation cell receiving surface capable of supporting the circulation cell 402. For example, a controller is coupled to the stage and the optical assembly. Some specific implementations of the controller are configured to move the stage and the optical assembly relative to each other in a step-and-shoot manner (sometimes referred to as a step and settle technique). Some specific implementations of the controller are configured to image the tiled area before the relative motion of the stage and the optical assembly is stabilized. Some specific implementations of the controller are configured to image the tiled area after the relative motion of the stage and the optical assembly is stabilized. In some embodiments, a biological sequencing instrument (e.g., such as a laboratory instrument or a production instrument) may include all or any portion of the elements depicted in the figure. In some examples, the biological sequencing instrument includes a stage, an optical assembly, and / or a controller.

[0055] In operation, imager 414 can be moved relative to flow cell 402, as indicated by the broad arrow (e.g., imager motion relative to flow cell), thereby repositioning imager 414 from being aligned with a first tile (e.g., previously imaged tile 418) to being aligned with a second tile (e.g., tile 406 imaged with reduced / unreduced tile time). Imaging can be performed by operating one or more lasers 404. Emissions from one or more lasers 404 or LEDs may be reflected from mirror 416 onto semi-reflective mirror 410 and / or from semi-reflective mirror 410 to illuminate tile 406 of flow cell 402, for example, as illustrated by the dashed arrow pointing to the second tile (e.g., power 420 (e.g., tile 406 imaged with reduced / unreduced tile time). In response to the illumination, fluorophores associated with the sample located at tile 402 may emit fluorescence. Light from the fluorescence may be focused by objective lens 412 and / or continue through semi-reflective mirror 410 to form an image (e.g., tile 406 imaged with reduced / unreduced tile time). The image may be captured by a sensor (e.g., sensor 408).

[0056] In some embodiments, a full moving tile time delay may occur before an image is captured (e.g., a "non-reduced" moving tile time, corresponding to an unreduced moving tile time image). In some examples, less than a full moving tile time delay may occur before an image is captured (e.g., a "reduced" moving tile time, corresponding to a reduced moving tile time image). When there is relative motion between the imager 414 and the tile 406, an image captured before the full moving tile time delay has elapsed may be captured. As a result, the image may suffer from aberrations, such as motion blur, and / or appear degraded relative to an image captured after the full moving tile time delay has elapsed. In some embodiments, capturing a reduced moving tile time image (e.g., an example conceptually represented in the figure as "motion blur") may be one of the example opportunities for improved circulation cell imaging.

[0057] Other examples of example opportunities for improved cell imaging may include one or more of reduced excitation power, tilt and / or non-planar blur, and reduced numerical aperture of the imager 414.

[0058] For example, reduced excitation power (e.g., conceptually illustrated in the figure by "power" 420) may be introduced by fluorescence-inducing illumination using one or more lasers or LEDs operating at the reduced excitation power. For example, the reduced excitation power may result in a degradation in image quality relative to an image captured using the non-reduced excitation power.

[0059] For example, tilt and / or non-planar blur (e.g., conceptually illustrated by "tilt" in the figure) may be introduced by differences in distance between imager 414 and various regions of the imaged tile. For example, a nominally planar flow cell may be misaligned (e.g., tilted) relative to imager 414 so that different portions (e.g., one or more edges) of the same tile are at different distances from imager 414. In some embodiments, depending on the depth of field of imager 414, one of these portions is incorrectly focused and thus degraded, e.g., resulting in aberrations in the resulting image. In some examples, a nominally planar flow cell may have a defect such that a portion of tile 406 is closer to imager 414 than another portion of tile 406.

[0060] For example, a reduced numerical aperture (e.g., conceptually shown in the figure by "NA") of the imager 414 may be introduced by using a lower numerical aperture imager 414 as compared to a larger numerical aperture imager 414. The lower numerical aperture may result in a degradation in image quality relative to an image captured with the larger numerical aperture imager 414. The reduced numerical aperture (e.g., NA) may be equal to n sin(θ), where n is the refractive index and θ is the half angle of the light cone detectable by the system (e.g., optics).

[0061] In some embodiments, an XY position encoder may be included. The XY position encoder can measure the xy position of the imager 414 relative to the circulation pool 402 and / or the tiles 406 therein in real time. In some examples, the xy position measurement can be referred to as the xy stage position and / or xy stage position of the image. During the pre-operation inspection of the instrument, the measurement result can be useful. In some embodiments, the measurement result can be used to provide an estimate of the expected amount of motion blur in the image. For example, in response to the imager 414 being located near the edge of the circulation pool and being located near the center of the circulation pool, there may be differences in motion blur. Information from the measurement can be processed according to the difference. In some embodiments, information from the measurement can be provided to training and / or generating context, such as (for example), by including metadata in the training and / or generating images.

[0062] In some embodiments, during the training described herein, information from the XY position encoders can be used with the training image data to learn parameters of the training context. During the generation described, for example, information from the XY position encoders can be used with the generation image data to generate an enhanced image.

[0063] In some embodiments, generalizing AI-based denoising to new noise profiles may be challenging (e.g., an AI model trained to remove Gaussian white noise with σ=x performs worse when σ=y). In some examples, using information from an XY position encoder during training and / or generation of the AI ​​model (e.g., such as any of the NN portions described elsewhere herein) can conceptually be used to feed knowledge about expected noise sources into the AI ​​model during training and / or generation, thereby achieving improved AI-based denoising performance.

[0064] As described herein, the system can be configured to capture images of emitting components located on multiple surfaces of a support structure (e.g., a circulation pool). The images can be of emitting components and can be based on the radiation emission of a biological sample. The radiation can be of different wavelengths (e.g., based on corresponding nucleotide channels A, C, G, and T). For example, at the end of each sequencing cycle, the control / processing system can receive a set of one or more (e.g., four) images of the optimal wavelength generated by the detector for each fluorophore to detect the emitted fluorescence. In other examples, the control / processing system can receive a collection of one or more images (e.g., two images). Each image can be received through a channel. For example, a first image can be received through a first channel and / or a second image can be received through a second channel. The first channel and / or the second channel can be used to encode (e.g., binary encoding) one or more nucleotide bases A, C, G, and T.

[0065] Figure 5 An example of base calling is depicted. A system (e.g., a server device) can include a base calling algorithm configured to perform base calling on a biological sample being sequenced. Figure 5 An example of sub-pixel based detection is described, but the present invention is not limited thereto. Figure 5 In the example, each sequencing cycle 510a to 510n has an image set having four different images (e.g., A, C, T, G images) captured using four different wavelength bands (e.g., image / imaging channels) and four different fluorescent dyes (e.g., one for each base). It should be understood that the systems described herein can be single-channel, dual-channel, or quad-channel systems.

[0066] The pixels in an image can be divided into multiple sub-pixels, such as Figure 5 . The base detector 514 may then perform base calling on the sub-pixels separately in each sequencing cycle. To base call a given sub-pixel in a particular sequencing cycle, the base detector 514 may use the intensity of a given sub-pixel in each of the A, C, T, G images. For example, the intensity in the image area covered by sub-pixel 1 in each of the A, C, T, G images of cycle 1 may be used to base call sub-pixel 1 in cycle 1. For sub-pixel 1, these image areas include the upper left sixteenth of the area of ​​the corresponding upper left pixel in each of the A, C, T, G images of cycle 1. Similarly, the intensity in the image area covered by sub-pixel m in each of the A, C, T, G images of cycle n may be used to base call sub-pixel m in cycle n. For sub-pixel m, these image areas may include the lower right sixteenth of the area of ​​the corresponding lower right pixel in each of the A, C, T, G images of cycle 1. In some embodiments, the process can generate a sub-pixel-wise base called sequence 516 across multiple sequencing cycles.

[0067] However, as described above, the image may include aberrations (e.g., spherical aberration, sometimes referred to as blur). Spherical aberration can be a type of aberration found in an optical train having spherical elements (e.g., a lens of focusing optics 32). Radiation (e.g., light) may impinge on a lens of the optical train off-center and may be refracted or reflected more or less than radiation impinged closer to the center of the lens, which may cause the resulting image to include spherical aberrations that reduce image quality. As described herein, the presence of aberrations, particularly spherical aberration, can prevent the system from successfully base calling a sample.

[0068] Fig. 6A and Figure 6B An example of images taken from two surfaces of a support structure is illustrated, where the images have spherical aberration. Fig. 6A In , the lens of the system can focus on the second surface such that the image 600 of the second surface has little or no spherical aberration (e.g., the design point of the objective lens can be on the second surface), while the image 610 of the first surface has significant spherical aberration. There can be aberration compensation for the second surface as described herein, and / or there can be no aberration compensation for the first surface (e.g., resulting in spherical aberration). In Figure 6B , the lens of the system can focus on an area between the first surface and the second surface (e.g., the design point of the objective lens can be between the first and second surfaces) so that both the image 620 of the first surface and the image 630 of the second surface experience similar levels of spherical aberration. For one or more of the first surface and the second surface (e.g., both), there can be aberration compensation (e.g., average aberration compensation) as described herein.

[0069] The system (e.g., from Figure 1 The imaging system 10 (the server from which the imaging system receives the image) may not be able to accurately base call an image having spherical aberration outside a specific range. Therefore, the system described herein may be configured to determine base calls from images having spherical aberration using an aberration compensation model. For example, the system may be configured to generate first image data of a first emitting component located on a first surface of a support structure (e.g., a first biological sample 12 located on a first surface 18 of the support structure 16), and second image data of a second emitting component located on a second surface of the support structure (e.g., a second biological sample 14 located on a second surface 20 of the support structure 16). One or more of the first image data and the second image data may include an intensity of an irradiated site.

[0070] For example, for the reasons mentioned herein, the first image data and the second image data may include spherical aberration. The system may be configured to use the image data and the aberration compensation model as described herein to perform base calling of a biological sample located on multiple surfaces of a support structure. For example, the system may generate one or more reconstructed images of images of multiple surfaces of a support structure using the aberration compensation model, and then determine base calling using the reconstructed images. Alternatively, the system may be configured to determine base calling directly from one or more of the first image data and the second image data (e.g., which include spherical aberration) using the aberration compensation model (e.g., and without generating a reconstructed image prior to base calling).

[0071] Figure 7 A schematic diagram of a system 700 is illustrated. The system 700 may include one or more server devices 702 connected to one or more imaging systems 710. The imaging system 710 may be an imaging system of a sequencing device. For example, the imaging system 710 may include Figure 1708. The control / processing system 38 of the imaging system 10 is an example of an imaging system 10. One or more server devices 702 can be connected to one or more imaging systems or sequencing devices and / or client devices 708 via a network 712.

[0072] The server device 702 and the imaging system 710 may communicate with each other via a network 712. For example, the server device 702 may receive image data from the imaging system 710. The server device 702 may also communicate with a client device 708. In some examples, the server device 702 may send data, including sequencing data or other information, to the client device 708, and the server device may receive input from a user via the client device 708. The network 712 may include any suitable network through which a computing device and / or controller of the imaging system may communicate. The network 712 may include a wired and / or wireless communication network. An example wireless communication network may include one or more types of radio frequency (RF) communication signals using one or more wireless communication protocols, such as a cellular communication protocol, a wireless local area network (WLAN) or WIFI communication protocol, and / or another wireless communication protocol. In addition or as an alternative to communicating across the network 712, the server device 702, the imaging system 710, and / or the client device 708 may bypass the network 712 and may communicate directly with each other.

[0073] like Figure 7 As further illustrated, system 700 may include database 716. Database 716 may store information for access by devices in system 700. Server device 702 and imaging system 710 may communicate with database 716 (eg, directly or via network 712) to store and / or access information.

[0074] The imaging system 710 can be part of a sequencing device and / or can include a device for imaging a biological sample. The imaging system 710 can be a production imaging system or a training imaging system (e.g., an imaging system used (e.g., only used) to train one or more prediction models). The system can include one or more training imaging systems and / or one or more production imaging systems. The biological sample imaged by the imaging system 710 can include human and / or non-human deoxyribonucleic acid (DNA) to determine the individual nucleotide bases of the nucleic acid sequence (e.g., by synthetic sequencing). The biological sample can include human and / or non-human ribonucleic acid (RNA). Example samples and / or components include, but are not limited to, nucleic acids (such as (e.g.), DNA or RNA), proteins (such as enzymes or receptors), polypeptides, nucleotides, amino acids, sugars, cofactors, metabolites or derivatives of these natural samples. Although the apparatus and methods of the present invention are exemplified herein with respect to components of biological samples, it should be understood that other samples or components can also be used. For example, synthetic samples can be used, such as combinatorial libraries, or libraries of compounds with species known or suspected to have desired structures or functions.

[0075] An example of image collection can use an imager to simultaneously detect light emitted by a plurality of fluorescently labeled nucleotides when the nucleotides fluoresce in response to excitation energy (such as laser excitation energy) as a collected image. An image can have one or more dimensions (e.g., a row of pixels or a two-dimensional array of pixels). Pixels can be represented according to one or more values. For example, each pixel can be represented by a single integer (e.g., such as an 8-bit integer) representing the pixel intensity (e.g., such as a grayscale). In another example, each pixel can be represented by a plurality of integers (e.g., such as three 24-bit integers), and each of these integers can represent the intensity of the pixel according to a corresponding wavelength band (e.g., such as a corresponding color).

[0076] When implemented as a training imaging system, the imaging system 710 may be configured to generate images with aberrations, which are used as training data. The imaging system 710 may be configured to generate images without aberrations, which may be used to train an aberration compensation model based on training images with aberrations. The images with aberrations and the images without aberrations may be images of the same sample, images captured in the same cycle, and / or images where a large portion of the field of view overlaps between the images (e.g., images with aberrations and images without aberrations).

[0077] In some examples, an image with aberration may be captured without a spherical aberration compensator. An image without aberration may be captured using a spherical aberration compensator. The image with aberration and the image without aberration may be aligned, for example, using one or more fiducials. The one or more fiducials may be embedded in a support surface (e.g., a flow cell).

[0078] Alternatively or additionally, when the imaging system 710 is in focus (e.g., the flow cell is in focus), an image without aberrations can be captured. When the imaging system is out of focus (e.g., the flow cell is out of focus), an image with aberrations can be captured. For example, a translation system can be used to move the imaging system into and / or out of focus. The translation system can include one or more motors. The imaging system can be moved into and / or out of focus by a predetermined distance, such as a predetermined number of nanometers.

[0079] Alternatively or additionally, an image without aberrations and / or an image with aberrations can be captured by generating simulated images.For example, one or more models herein can be used to generate an image without aberrations and / or an image with aberrations.

[0080] The server device 702 may generate, receive, analyze, store, and / or transmit digital data (e.g., such as imaging data received from a training imaging system). Figure 7As shown, imaging system 710 may generate and / or send imaging data to server device 702. Server device 702 may include a distributed server collection, where server device 702 may include multiple server devices distributed across network 712 and / or located in the same and / or different physical locations. In addition, server device 702 may include a content server, an application server, a communication server, a web hosting server, and / or another type of server.

[0081] The server device 702 may include a server subsystem 704. The server subsystem 704 may include software and / or hardware used by the server device 702 to process sequencing requests and / or data, as described herein. The server subsystem 704 may be included in a single server device 702, or may be distributed across multiple server devices 702. The server subsystem 704 may include a sequencing system across multiple layers of software and / or hardware for servicing requests for sequencing services at the server subsystem 704.

[0082] The server subsystem 704 may include artificial intelligence (AI) or machine learning (ML), which may be trained and / or implemented for analyzing image data to perform AI-driven signal enhancement of sequence images (e.g., using a spherical aberration compensation model). Examples may include AI-driven (e.g., synthetic sequencing (SBS)) signal enhancement of sequencing images for base calling. AI-driven signal enhancement may be implemented, at least in part, for example, based on one or more machine learning techniques, such as deep learning using one or more neural networks (NNs). Various examples of neural networks include fully connected neural networks. Various examples of NNs generally include convolutional neural networks (CNNs) (e.g., any NN with one or more layers that perform convolution) and NNs with elements including one or more CNNs and / or CNN-related elements (e.g., various specific implementations of general generative adversarial networks (GANs) and various specific implementations of conditional generative adversarial networks (CGANs), cycle-consistent generative adversarial networks (cycle GANs), and / or autoencoders). Various examples of NNs also include general recurrent neural networks (RNNs) (e.g., any NN in which the output from the previous step is provided as an input to the current step and / or has a hidden state) and NNs with one or more recursive-related elements. Various examples of NN also include multi-layer perceptron (MLP) neural networks. In some implementations, the GAN is implemented at least in part via one or more MLP elements. Additionally or alternatively, the aberration compensation model may include decoding, deep learning, deep Fourier channel attention network (DFCAN), optical transfer function (OTF) inversion, point spread function (PSF), iterative deconvolution, linear deconvolution, or nonlinear deconvolution (e.g., Lucy-Richardson).

[0083] Example implementations of the NN architecture may include various collections of software elements and / or hardware elements that collectively perform operations according to the NN architecture. Various NN implementations vary according to machine learning frameworks, programming languages, runtime systems, operating systems, and / or underlying hardware resources. The underlying hardware resources variously include one or more computer systems, such as any combination of a central processing unit (CPU), a graphics processing unit (GPU), a field programmable gate array (FPGA), a coarse-grained reconfigurable architecture (FIELD), an application-specific integrated circuit (ASIC), an application-specific instruction set processor (ASIP), and a digital signal processor (DSP), as well as general computing systems, for example, elements capable of executing programming instructions specified via a programming language. Various NN implementations are capable of storing programming information (such as code and data) on a non-transitory computer-readable medium, and are further capable of executing code and referencing data according to a program that implements the NN architecture.

[0084] Examples of machine learning frameworks, platforms, runtime environments, and / or libraries (such as those that enable investigation, development, implementation, and / or deployment of NNs and / or NN-related elements) may include TensorFlow, Theano, Torch, PyTorch, Keras, MLpack, MATLAB, IBM Watson Studio, Google Cloud AI Platform, Amazon SageMaker, Google Cloud AutoML, RapidMiner, Azure Machine Learning Studio, Jupyter Notebook, and / or Oracle Machine Learning.

[0085] The server subsystem 704 may be implemented to train one or more NNs. Example techniques for training a NN, such as determining and / or updating parameters of the NN, include back-propagation based gradient updates and / or gradient descent techniques, such as stochastic gradient descent (SGD), synchronous SGD, asynchronous SGD, batch gradient descent, and / or mini-batch gradient descent. Back-propagation based gradient techniques may be used alone or in any combination (e.g., stochastic gradient descent may be used in a mini-batch context). Example optimization techniques that may be used (e.g., back-propagation based gradient techniques (primary gradient updates and / or gradient descent techniques)) may include momentum, Nesterov accelerated gradient, Adagrad, Adadelta, RMSprop, Adam, AdaMax, Nadam, and / or AMSGrad.

[0086] Each client device 708 can generate, store, receive and / or send digital data. Specifically, the client device 708 can receive sequencing metrics from the sequencing device. In addition, the client device 708 can communicate with the server device 702 to receive one or more files including nucleotide base calls and / or other metrics. The client device 708 can present or display information related to nucleotide base calls to a user associated with the client device 708 within a graphical user interface.

[0087] Figure 7 The client device 708 illustrated in the example may include various types of client devices. For example, the client device 708 may include a non-mobile device, such as a desktop computer or a server, or other types of client devices. In other examples, the client device 708 may include a mobile device, such as a laptop, a tablet computer, a mobile phone, and / or a smart phone.

[0088] like Figure 7 As further shown in FIG. 7 , each client device 708 may include a client subsystem 714. The client subsystem 714 may include software and / or hardware used by the client device 708 to process sequencing requests and / or data, as described herein. The client subsystem 714 may span multiple layers of software and / or hardware. The client subsystem 714 may be included in a single client device 708 or may be distributed across multiple client devices 708.

[0089] The client subsystem 714 and / or the imaging system 710 may include a sequencing application. The sequencing application may be a web application and / or a local application (e.g., a mobile application, a desktop application) stored and / or executed on the client device 708. The sequencing application may include instructions that (e.g., when executed) cause the client device 708 to receive data from the sequencing device and / or the server device 702 and / or present data to a user of the client device 708 for display at the client device 708.

[0090] A plurality of client devices 708 may transmit requests from the client subsystem 714 to the server subsystem 704 to perform sequencing services. The client device 708 transmitting the request may operate using different versions of a sequencing application for analyzing sequencing data. In one example, different versions of the sequencing application may support different types of analysis for the same or different types of sequencing devices. The server subsystem 704 of the server device 702 may load and / execute different versions of a sequencing system to support client sequencing applications operating on different versions of software at the client subsystem 714. Different versions of the sequencing system may span multiple layers of software and / or hardware of the server subsystem 704. For example, different versions of the sequencing system may span multiple software and / or hardware layers of a vertical solution stack.

[0091] Figure 8 An example of AI-driven aberration correction of sequence images using a CNN-based image-to-image autoencoder model (e.g., using a U-Net architecture) is illustrated. The process can be performed by a server (e.g., server device 702). The process includes a training stage 802 and a generation stage 804. Both the training stage 802 and the generation stage 804 include encoder stages 806a, 806b and decoder stages 808a, 808b. The encoder stages 806a, 806b include multiple layers, such as processing layers (e.g., convolutional layers), activation layers, and successively smaller pooling layers, which together can compress a representation of a reduced power image into a relatively smaller representation (as conceptually shown by latent variable elements). The decoder stages 808a, 808b include layers (e.g., similar to those of the encoder stage), but are organized in a "reverse" fashion in size compared to the layers of the encoder stage, arranged at successively larger sizes so as to conceptually decompress the latent variable information into a full-size reconstructed image (e.g., corresponding to all or substantially all of the field of view of the imager), or, alternatively, a reconstructed image of a size corresponding to the input provided to the encoder stage (e.g., corresponding to one of a plurality of small patches of a collected image).

[0092] The encoder stage 806a of the training context 802 may receive images with spherical aberration 810, process these images 810 as training data through the encoder stage 806a and the decoder stage 808a, and compare the output of the decoder stage 808a to images without spherical aberration 812 using a loss function 814. The comparison (e.g., update) of the loss function may be fed back into the training parameters (e.g., weights and biases) of the encoder stage 806a and the decoder stage 808a within the training context 802 to train and improve the aberration compensation model.

[0093] In the production context 804, encoder stage 806b and decoder stage 808b may be trained using data from encoder stage 806a and decoder stage 808a of the training context 802. For example, training parameters of encoder / decoder filter information may be provided from the training encoder 806a and decoder 808a to produce encoder 806b and decoder 808b. Encoder stage 806b may receive a product image 816 having spherical aberration, such as obtained by an imaging system (e.g., Figure 1 The image 816 is processed by the trained encoder stage 806b and decoder stage 808b to generate product images generated by the imaging system 10, and the spherical aberration-free image 818 is output. Therefore, the spherical aberration correction model of the generation stage 804 (e.g., the trained encoder stage 806b and the decoder stage 808b) can be configured to correct the spherical aberration generated by the imaging system (e.g., Figure 1The spherical aberration caused by the imaging system 10 of FIG. 81 is shown in FIG. 82. For example, the reconstructed image 818 may correspond to an enhanced image, the quality of which corresponds to the quality of an image without spherical aberration. During training, the parameters of the encoder and decoder levels are updated to effectively represent information that is significant for enhancement. All or any portion of the parameters when training is completed are referred to as filters.

[0094] In some examples, the autoencoder model includes one or more skip connections that allow feature representations (e.g., lower frequency content data) to pass through any particular layer for which further processing is inappropriate or unnecessary.

[0095] In some implementations, the training encoder stage 806a (e.g., such as implemented in a laboratory instrument) can be different from the production encoder stage 806b (e.g., such as implemented in a production instrument). In some implementations, the training encoder stage 806a can be used as a production encoder 806b after training, and the trained encoder / decoder filter information can be used in situ for production (e.g., the instrument is used as a dual-purpose laboratory instrument and production instrument).

[0096] In various implementations, the performance of a neural network (NN) can be improved by making the x and y input dimensions equal or approximately equal to the x and y output dimensions. Another improvement can be achieved by increasing the z input dimension (e.g., by the number of image and / or channel inputs, and / or additional encoding, such as the distance to the nearest cluster center). Another improvement can be achieved by collecting and using image information from multiple sequencing cycles. Other improvements include normalizing the entire image (e.g., instead of sub-images). For various implementations of CNN-based NNs, performance can be improved by using depth-wise convolutions, reverse bottlenecks, separate downsampling layers (e.g., replacing explicit downsampling with 3×3 convolutions with stride 2, 2×2 convolutions with stride 2), increasing kernel size, preferring layer normalization over batch normalization, preferring GELU over ReLU, and / or reducing the number of layers used (e.g., fewer activation layers and / or fewer normalization layers). For various implementations of transformer-based neural networks, performance is improved by moving windows between attention blocks so that spatial information can be encoded between patches.

[0097] Fig. 9A and Fig. 9B Example results for base calling based on various defocus levels are illustrated. Fig. 9A , graph 900 indicates throughput (e.g., the percentage of reads that passed filtering and aligned to a reference genome). Fig. 9B , graph 950 represents quality (e.g., error rate calculated after alignment to a reference genome). Run time assurance (RTA) line 902 shows the quality of the base calling algorithm at various micrometers (μm) of defocus (e.g., Fig. 9A ), while RTA line 952 shows the percentage of successful base calls achievable at various microns of defocus (e.g., Fig. 9B ) The RTA+NN line 904 shows the percentage error rate of base calls that can be achieved at various microns of defocus (e.g., Fig. 9A ), while the RTA+NN line 954 shows the percentage of successful base calls that can be achieved using the aberration compensation model prior to the base calling algorithm at various microns of defocus (e.g., Fig. 9B ) is the percentage error rate in base calls that can be achieved using the aberration compensation model prior to the base calling algorithm.

[0098] As shown, using the base calling model alone may result in base calling not being performed outside the defocus threshold of 0.75 μm (e.g. Fig. 9A and Fig. 9B However, when the aberration compensation model is used together with the base calling algorithm, approximately 40% of the otherwise failed base calls can be recovered at a defocus threshold of 1.0 μm (e.g., as shown in FIG. Fig. 9A and 9B 904 and 954 in FIG. 1 ). In addition, at 2 μm defocus, use of the aberration compensation model with the base calling algorithm may result in some (e.g., a small but significant proportion) reads being base called that would not be base called if the aberration compensation model was not used.

[0099] In some examples, the aberration compensation model can be trained to estimate and / or measure defocus in an image. The detector and / or equalizer can estimate and / or measure defocus in image data of one or more surfaces of a support structure. For example, the aberration compensation model can estimate the amount of defocus in the image data and use the amount of defocus to generate a reconstructed image that does not include spherical aberration. In some examples, one or more coefficients (e.g., a first coefficient and / or a second coefficient) can be trained for one or more defocus levels and / or ranges.

[0100] The level and / or range or defocus can be as large as the optical field of view (FOV) and / or tile. In some examples, the processor can be configured to divide the FOV and / or tile into defocus sub-regions, for example, to determine the median defocus for each defocus sub-region. The aberration compensation model can use the median defocus to estimate and / or measure the defocus in the image. In addition, in some cases, there may be tilt and / or curvature in the circulation pool, which may cause spatially varying defocus. The defocus sub-regions can be used to correct problems caused by tilt and / or curvature.

[0101] In some embodiments, one or more focus tracking points can be used to measure the focus of different points in the FOV. The difference in focus between a pair of points can provide an estimate of tilt and / or curvature. The processor can be configured to generate a spatial defocus map based on the focus difference, median defocus, level and / or range (e.g., coefficient) of defocus. In some examples, the processor can generate a spatial defocus map before sorting. The spatial defocus map can be updated during sequencing. This can account for disturbances such as target heating.

[0102] Fig.10 1 is a block diagram of an example computer system 1000. The computer system 1000 may be an example of a control / processing system for a sequencing device / imaging system (e.g., Figure 1 control / processing system 38), imaging system (e.g., Figure 7 imaging system 710), a server device (e.g., Figure 7 Server device 702), client device (e.g., Figure 7 client device 708) and / or another computing device.

[0103] The computer system may include one or more storage subsystems 1014, a user interface input device 1012, a processor (e.g., a central processing unit (CPU)) 1002, a network interface 1004, a user interface output device 1006, and one or more deep learning processors 1008 (e.g., such as a GPU, FPGA, and / or CGRA) interconnected by a bus subsystem 1010. The storage system 1014 may include a memory subsystem 1016 and / or a file storage subsystem. For example, the memory subsystem 1016 may include a randomly accessible read / write memory (RAM) and / or a read-only memory (ROM). The ROM and / or file storage subsystem elements may include non-transitory computer-readable media capabilities (e.g., for storing and executing programming instructions to implement all or any of the NN parts described herein). One or more memory subsystems may include one or more computer-readable storage media having computer-executable instructions stored thereon, which instructions, when executed by one or more processors, may be implemented to be executed as described herein. According to various implementations, the deep learning processor 1008 may implement all or any portion of the NN portion described herein, such as the training and / or use of the spherical aberration compensation model. In various implementations, the deep learning processor 1008 elements may include various combinations of CPUs, GPUs, FPGAs, CGRAs, ASICs, ASIPs, and / or DSPs. Although shown as being implemented on a single computer system, one or more computing systems or portions thereof may be implemented to store and execute programming instructions to implement one or more embodiments described herein.

[0104] In various implementations, one or more of the laboratory instruments and / or production instruments described herein include one or more computer systems that are the same or similar to the example computer system 1000. In various implementations, any one or more of the training contexts and / or production contexts may use any one or more computer systems that are the same or similar to the example computer system 1000 to perform NN-related processing and / or operations (e.g., as one or more servers associated with training data collection and / or synthesis and production data collection and / or processing, such as image enhancement).

[0105] In various implementations, the memory subsystem 1016 and / or the file storage subsystem 1018 may be enabled to store parameters of the NN, such as all or any portion of the parameters of the portions of the NN described herein. For example, all or any portion of the stored parameters may variously correspond to any combination of initialization parameters of the NN used in the training context, training parameters of the NN used in the training context, and / or training parameters of the NN used in the production context. For another example, all or any portion of the stored parameters may correspond to one or more intermediate representations, such as related to information provided by the training context to the production context, such as shown and described herein.

[0106] In some embodiments, at least some of the stored parameters may correspond to information provided by the training NN generator (G) to the generating NN generator (G). In some examples, at least some of the stored parameters may correspond to information retained in the generator stage after training in the training context for generation in the generating context. In some examples, at least some of the stored parameters may correspond to information provided by the training context to the generating context. In some examples, at least some of the stored parameters may correspond to information provided by the training context to the generating context.

[0107] In various implementations, the controller may include one or more elements similar to computer system 1000, such as storing and / or executing programming instructions to implement all or any portion of the NN described herein and / or storing parameters of the NN.

[0108] The processor 1002 may be configured to perform sequencing operations and / or determine base calls based on one or more images generated by the imaging system. For example, the processor 1002 may be configured to determine base calls of irradiated sites that fluoresce within one or more of the first emitting component and the second emitting component of the support structure. In some embodiments, the processor 1002 may be configured to receive images of multiple surfaces of the support structure that include spherical aberration, and determine base calls using an aberration compensation model applied to the images. Alternatively or additionally, the processor 1002 may be configured to generate a reconstructed version of the image that does not include spherical aberration, and determine base calls using an aberration compensation model applied to the reconstructed version of the image.

[0109] The processor 1002 may be configured to generate one or more reconstructed images of a first reconstructed image of the first image data and a second reconstructed image of the second image data using an aberration correction model. For example, the aberration correction model may compensate for aberrations in one or more of the first image and the second image. In some embodiments, the processor 1002 may be configured to determine one or more base calls of base calls of irradiated sites that fluoresce within the first emitting component of the support structure and base calls of irradiated sites that fluoresce within the second emitting component of the support structure. For example, the processor 1002 may use a base call algorithm. In some embodiments, the base call algorithm may include an aberration compensation model. For example, the processor 1002 may be configured to generate an aberration compensation model using one or more of decoding, deep learning, deep Fourier channel attention network (DFCAN), optical transfer function (OTF) inversion, point spread function (PSF), iterative deconvolution, linear deconvolution, or nonlinear deconvolution (e.g., Lucy-Richardson). In some embodiments, the processor 1002 may be configured to generate one or more of the first image and the second image without using a correction compensator component. For example, the imaging system may not include a correction compensator component. In some embodiments, image reconstruction may be performed (e.g., by deep learning). For example, an intermediate image may be generated. Basic detection may be performed based on one or more of the intermediate image, the first image data, and / or the second image data.

[0110] The aberration compensation model may include one or more of a first coefficient for compensating the aberration of the first image data and a second coefficient for compensating the aberration of the second image data. For example, the first coefficient may be based on a distance between a focal point of the focusing optics and the first surface of the support structure. In some examples, the second coefficient may be based on a distance between the focal point of the focusing optics and the second surface of the support structure.

[0111] Additionally or alternatively, an equalizer can be used to at least partially eliminate one or more aberrations. For example, the equalizer can be configured to filter crosstalk at a cluster from one or more adjacent clusters. In some embodiments, aberrations can be removed and / or base calling can be performed on a biological sample, as described in U.S. Pat. No. 11,188,778, which is incorporated herein by reference.

[0112] Additionally or alternatively, the examples described herein may be combined with a spatial equalizer for performing signal enhancement, as further described in U.S. Patent No. 11,188,778, which is incorporated herein by reference. The equalizer may be trained to generate and / or implement a lookup table (LUT). The equalizer may generate a LUT group (e.g., an equalizer filter) having multiple LUTs. Each LUT may have multiple coefficients learned from training. In one specific implementation, the number of coefficients in the LUT corresponds to the number of image pixels. For example, if the size of the local grid of image pixels is p×p (e.g., a 9×9 pixel block), each LUT has p 2 coefficients (e.g., 81 coefficients).

[0113] According to one or more embodiments described herein, supervised training can be used to train the coefficients of the equalizer. For example, paired images can be used to train the equalizer, such as a high-resolution target image and a low-resolution training image. The equalizer can receive low-resolution training image data as input, and can train coefficients based on the high-resolution target image in the image pair. Examples of training techniques for the equalizer can include least squares estimation, ordinary least squares, least mean squares, and recursive least squares. Least squares techniques adjust the parameters of the function to best fit the data set so that the sum of squared residuals is minimized.

[0114] In one implementation of training, low-resolution training data from sequenced images can be binned (e.g., by hole sub-pixel location). For example, for a 5×5 LUT, 1 / 25 of the holes are centered in bin (1, 1) (e.g., the upper left corner of the sensor pixel), 1 / 25 of the holes are in bin (1, 2), etc. The input to the equalizer can be the pixels of the low-resolution image of those bins. The resulting estimated equalizer coefficients are different for each bin.

[0115] Each LUT may have a number of coefficients learned from training. In one implementation, the number of coefficients in the LUT may correspond to the number of image pixels. For example, if the size of the local grid of image pixels (image or pixel patch) is p×p (e.g., 9×9 pixel patch), each LUT may have p 2 coefficients (e.g., 81 coefficients).

[0116] Training of the equalizer may produce equalizer coefficients that are configured to mix / combine intensity values ​​of pixels depicting intensity emissions of a target image or image cluster and / or intensity emissions from one or more adjacent clusters in a manner that maximizes the signal-to-noise ratio. The signal that maximizes the signal-to-noise ratio may be the intensity emission from the target image, and the noise that minimizes the signal-to-noise ratio is the intensity emission from adjacent clusters, i.e., spatial crosstalk, plus some random noise (e.g., to account for background intensity emissions). The equalizer coefficients may be used as weights, and the mixing / combining may include performing an element-by-element multiplication between the equalizer coefficients and the brightness value of the pixel to calculate a weighted sum of the brightness values ​​of the pixel. During production, the equalizer may receive low-resolution image data as input and interpolate the image using coefficients that have been trained using high-resolution image data to generate a high-resolution image.

[0117] Fig.11 1 is a flow chart of an example procedure 1100 for determining base calls of irradiated sites that fluoresce within an emitting component of a support structure using an aberration compensation model. The procedure 1100 can be executed by a processor of a system, such as a processor of a server device (e.g., server device 702 and / or one or more processors, such as Fig.10 1002 of a computer system 1000 of the present invention). The processor may be configured to execute procedure 1100 to perform base detection of biological samples located on multiple surfaces of a support structure, such as a first biological sample 12 present on a first surface 18 of a support structure 16 and a second biological sample 14 present on a second surface 20 of the support structure 16. As described herein, radiation emissions may be emitted by the biological sample, and the imaging system may be configured to generate images of the first emission component and the second emission component based on the detected radiation. The imaging system may have a high numerical aperture (e.g., at least 0.6 in some examples, at least 0.75 in some other examples, or at least 0.85 in some examples) and / or may not include a corrective compensator component. In addition, some support structures include a fluid layer between the first and second surfaces (e.g., the first biological sample and the second biological sample). Therefore, images captured by the imaging system of the first surface and the second surface may have spherical aberration (e.g., the spherical aberration may be different between the two surfaces). As described above, spherical aberration may limit the ability of the processor to accurately base call a biological sample located on the first and second surfaces (e.g., distinguishing nucleotide channels A, C, G, and T). Therefore, the processor may perform procedure 1100 to more accurately base call a biological sample based on an image generated using spherical aberration.

[0118] At 1102, the processor may receive first image data of a first emitting component located on a first surface of a support structure (e.g., a first biological sample 12 located on a first surface 18 of a support structure 16) and second image data of a second emitting component located on a second surface of the support structure (e.g., a second biological sample 14 located on a second surface 20 of the support structure 16). The processor may receive the first image data and the second image data from an imaging system. For example, for the reasons mentioned herein, the first image data and the second image data may include spherical aberration. In some examples, the image data may include an intensity of an irradiated site. As described herein, the imaging system may include a detector (e.g., detector 36) configured to generate image data. In some embodiments, the detector may be configured to generate image data of the first emitting component when a focusing optics (e.g., focusing optics 32) confocally directs radiation to the first emitting component, and / or to generate image data of the second emitting component when the focusing optics confocally directs radiation to the second emitting component.

[0119] At 1104, the processor can be configured to generate a first reconstructed image of the first image data using the aberration compensation model, for example, to correct for any spherical aberration present in the first image data. Thus, the first reconstructed image data may not include any spherical aberration, which can improve the ability of the processor to base call the biological sample on the first surface of the support structure, as described above.

[0120] At 1106, the processor can be configured to generate a second reconstructed image of the second image data using the aberration compensation model, for example, to correct for any spherical aberration present in the second image data. Thus, the second reconstructed image data may not include any spherical aberration, which, as described above, can improve the ability of the processor to base call the biological sample on the second surface of the support structure.

[0121] In some examples, the aberration compensation model may include a first coefficient to compensate for aberrations of the first image data when generating the first reconstructed image, and a second coefficient to compensate for aberrations of the second image data when generating the second reconstructed image. The first coefficient may be based on a distance between a focal point of the focusing optics and a first surface of the support structure, and the second coefficient may be based on a distance between a focal point of the focusing optics and a second surface of the support structure.

[0122] At 1108, the processor may use the first reconstructed image to determine base calls of irradiated sites that fluoresce within the first emitting component. For example, the processor may use the first reconstructed image to perform base calls on a biological sample disposed on a first surface of a support structure (e.g., itself generated using an aberration compensation model). Similarly, at 1110, the processor may use the second reconstructed image to determine base calls of irradiated sites that fluoresce within a second emitting component. For example, the processor may use the second reconstructed image to perform base calls on a biological sample disposed on a second surface of a support structure (e.g., itself generated using an aberration compensation model). Thus, the processor may be configured to accurately base call images having spherical aberration outside of a particular range by, for example, generating a reconstructed image that does not include spherical aberration using an aberration compensation model and performing base calls on the reconstructed image. Thus, the processor may be configured to determine base calls from images having spherical aberration that would otherwise not be possible. Using procedure 1100, the processor may generate one or more reconstructed images of images of multiple surfaces of a support structure using an aberration compensation model, and then determine base calls using the reconstructed images.

[0123] Fig.12 1 is a flow chart of an example procedure 1200 for determining base calls of irradiated sites that fluoresce within an emitting component associated with a support structure using an aberration compensation model. The procedure 1200 can be executed by a processor of a system, such as a processor of a server device (e.g., server device 702 and / or one or more processors, such as Fig.10 The processor 1002 of the computer system 1000 may be configured to execute the procedure 1200 to perform base calling of a biological sample located on multiple surfaces of a support structure, such as a base located on a plurality of surfaces of a support structure. Figure 1 16 and a second biological sample 14 present on a second surface 20 of the support structure 16. As described herein, images captured by an imaging system of the first surface and the second surface may have spherical aberration (e.g., the spherical aberration between the two surfaces may be different), and the spherical aberration may limit the ability of the processor to accurately base call biological samples located on the first surface and the second surface (e.g., distinguish nucleotide channels A, C, G, and T). Therefore, the processor may execute procedure 1200 to more accurately base call the biological sample based on the image generated using spherical aberration. In addition, as described below, the processor may be configured to determine a base call directly from one or more of the first image data and the second image data (e.g., including spherical aberration) using procedure 1200 (e.g., without generating a reconstructed image before base calling, as done in process 1100). For example, the aberration compensation model can be part of a base calling algorithm executed by the processor when executing procedure 1200.

[0124] At 1202, the processor may receive first image data of a first emitting component located on a first surface of a support structure (eg, present on a Figure 1 ) and second image data of a second emitting component located on a second surface of the support structure (e.g., present in Figure 1 The processor may receive the first image data and the second image data from the imaging system. For example, the first image data and the second image data may include spherical aberration for the reasons mentioned herein. In some examples, the image data may include the intensity of the irradiated site. As described herein, the imaging system may include a detector (e.g., Figure 1 36 shown). In some embodiments, the detector can be configured as a focusing optic (e.g., Figure 1 The focusing optics 32 shown in FIG. 3 generates image data of a first emitting component when the focusing optics 32 confocally directs radiation to the first emitting component, and / or generates image data of a second emitting component when the focusing optics 32 confocally directs radiation to the second emitting component.

[0125] At 1204, the processor may determine base calls for irradiated sites that fluoresce within the first emitting component using the first image and the aberration compensation model (e.g., without generating a reconstructed first image). The aberration compensation model may be part of a base calling algorithm executed by the processor. For example, the aberration compensation model may be part of an equalizer that includes a spatial unsharp mask. The spatial unsharp mask may take into account features of the first surface of the support structure (e.g., nanopore locations), chemical properties (e.g., dye quantity), etc. The aberration compensation model may determine different coefficients for different degrees of defocus of the first image. In some cases, using the aberration compensation model (e.g., directly on) the first image data may require an independent measurement of the defocus of the first image. The processor (e.g., using an equalizer) may receive the first image and output the intensity at each known nanopore location on the first surface of the support structure. Then, at 1204, the processor may convert the intensity into a base call.

[0126] Similarly, at 1206, the processor may use the second image and the aberration compensation model (e.g., without generating a reconstructed second image) to determine base calls for irradiated sites that fluoresce within the second emitting component. For example, the aberration compensation model may be part of an equalizer that includes a spatial unsharp mask. The spatial unsharp mask may take into account features of the second surface of the support structure (e.g., nanopore locations), chemical properties (e.g., dye quantity), etc. The aberration compensation model may determine different coefficients for different degrees of defocus of the second image. In some cases, using the aberration compensation model on (e.g., directly on) the second image data may require an independent measurement of the defocus of the second image. The processor (e.g., using an equalizer) may receive the second image and output the intensity at each known nanopore location on the second surface of the support structure. Then, at 1206, the processor may convert the intensity into a base call. Thus, using procedure 1200, the processor may be configured to determine a base call using an aberration compensation model (e.g., directly from one or more of the first image data and the second image data (e.g., which include spherical aberration) and without generating a reconstructed image prior to the base call.

[0127] Although embodiments may be described herein as being performed by a processor configured to perform as described herein, one or more processors may be implemented on one or more computing devices to be enabled to perform as described herein.

Claims

1. An imaging system for detecting radiation emission on a support structure, the imaging system comprising: an optical train comprising imaging optics, wherein the imaging optics are configured to focus the optical train toward a support structure, wherein the support structure comprises a first emitting component associated with a biological sample disposed on a first surface of the support structure and a second emitting component associated with the biological sample disposed on a second surface of the support structure; an excitation radiation source configured to direct excitation radiation towards the first emitting component and the second emitting component; detection optics configured to detect radiation emissions returned from the first and second emitting components via the optical train; a detector configured to generate first image data of the first emission component based on the detected radiation emissions and to generate second image data of the second emission component based on the detected radiation emissions; and A processor, the processor being configured to: determining base calls of irradiated sites that fluoresce within the first emitting component of the support structure using an aberration compensation model; and Base calls of irradiated sites that fluoresce within the second emitting component of the support structure are determined using the aberration compensation model, wherein the aberration compensation model is trained to compensate for aberrations of the first image data and to compensate for aberrations of the second image data.

2. The imaging system of claim 1 , wherein the processor is configured to: generating a first reconstructed image of the first image data using the aberration compensation model to compensate for the aberration of the first image, and generating a second reconstructed image of the second image data using the aberration compensation model to compensate for the aberration of the second image; and The base calls of the irradiated sites that fluoresce within the first emitting component of the support structure are determined using the first reconstructed image, and the base calls of the irradiated sites that fluoresce within the first emitting component of the support structure are determined using the second The reconstructed image determines the base calls of the irradiated sites that fluoresce within the second emitting component of the support structure.

3. The imaging system of claim 1 , wherein the processor is configured to: The base calls of the irradiated sites that fluoresce within the first emitting component of the support structure and the base calls of the irradiated sites that fluoresce within the second emitting component of the support structure are determined using a base calling algorithm, wherein the base calling algorithm includes the aberration compensation model. 4 . The imaging system of claim 1 , wherein the aberration compensation model includes a first coefficient for compensating the aberration of the first image data, and includes a second coefficient for compensating the aberration of the second image data.

5. The imaging system of claim 4 , wherein the first coefficient is based on a distance between a focal point of a focusing optic and the first surface of the support structure, and the second coefficient is based on a distance between the focal point of the focusing optic and the second surface of the support structure.

6. The imaging system of claim 1, wherein the imaging system does not include a corrective compensator component.

7. The imaging system of claim 1, wherein the processor is configured to generate the first image and the second image without using a corrective compensator component.

8. The imaging system of claim 1, wherein the optical train further comprises focusing optics configured to direct radiation confocally to a surface of the support structure.

9. An imaging system according to claim 8, wherein the detector is configured to generate image data of the first emitting component when the focusing optical device confocally directs radiation to the first emitting component, and to generate image data of the second emitting component when the focusing optical device confocally directs radiation to the second emitting component.

10. The imaging system of claim 8, wherein the focusing optics are configured for a single design point for diffraction limited focusing and imaging, wherein the design point is located at one or more of the first surface, the second surface, and between the first and second surfaces of the support structure.

11. The imaging system of claim 8, wherein the focusing optics is defined by a numerical aperture (NA) value of at least about 0.

75.

12. The imaging system of claim 11, wherein the focusing optics is defined by a numerical aperture (NA) value of at least 0.

85.

13. The imaging system of claim 1, wherein the excitation radiation source is configured to direct the excitation radiation along a radiation line toward the first emitting component and the second emitting component, and wherein the radiation line is configured to reside between the first emitting component and the second emitting component.

14. The imaging system of claim 1, wherein the processor is configured to generate the aberration compensation model using one or more of deep learning, optical transfer function (OTF) inversion, iterative deconvolution, linear deconvolution, or nonlinear deconvolution.

15. The imaging system of claim 1, wherein the support structure is a multi-surface flow cell.

16. The imaging system of claim 1, wherein the first emitting component comprises a first nanohole pattern and the second emitting component comprises a second nanohole pattern, the first nanohole pattern being different from the second nanohole pattern.

17. The imaging system of claim 1, wherein the optical train further comprises conditioning optics configured to generate a substantially linear excitation beam of radiation or to combine excitation beams from excitation radiation sources.

18. The imaging system of claim 1, wherein the optical train further comprises steering optics configured to redirect an excitation beam from the excitation radiation source toward focusing optics.

19. The imaging system of claim 1, wherein the detector comprises a charge coupled device (CCD) sensor configured to generate the image data based on locations where photons impinge on the detector.

20. The imaging system of claim 1, wherein the detector comprises one or more of a detector array configured for time delay integration (TDI) operation, a complementary metal oxide semiconductor (CMOS) detector, an avalanche photodiode (APD) detector, and a Geiger mode photon counter.

21. The imaging system of claim 1, further comprising: A translation system is configured to allow focusing and movement of the support structure before and during imaging.

22. The imaging system of claim 1, wherein the imaging system comprises only a single excitation radiation source.

23. A method for detecting radiation emissions on a support structure, the method comprising: receiving first image data of a first emitting component based on first detected radiation emissions and second image data of a second emitting component based on second detected radiation emissions, wherein a support structure includes the first emitting component associated with a biological sample disposed on a first surface of the support structure and the second emitting component associated with the biological sample disposed on a second surface of the support structure; determining base calls of irradiated sites that fluoresce within the first emitting component of the support structure using an aberration compensation model; as well as Base calls of irradiated sites that fluoresce within the second emitting component of the support structure are determined using the aberration compensation model, wherein the aberration compensation model is trained to compensate for aberrations of one or more of the first image data or the second image data.

24. The method according to claim 23, further comprising: generating a first reconstructed image of the first image data using the aberration compensation model to compensate for the aberration of the first image, generating a second reconstructed image of the second image data using the aberration compensation model to compensate for the aberration of the second image; determining the base call of the irradiated site that fluoresces within the first emitting component of the support structure using the first reconstructed image; as well as The base calls of the irradiated sites that fluoresce within the second emitting component of the support structure are determined using the second reconstructed image.

25. The method according to claim 23, further comprising: The base calls of the irradiated sites that fluoresce within the first emitting component of the support structure and the base calls of the irradiated sites that fluoresce within the second emitting component of the support structure are determined using a base calling algorithm, wherein the base calling algorithm includes the aberration compensation model.

26. At least one computer-readable storage medium comprising executable instructions that, when executed by at least one processor, are configured to cause the at least one processor to: generating first image data of a first emitting component based on detecting radiation emissions and generating second image data of a second emitting component based on the detecting radiation emissions, wherein a support structure includes the first emitting component associated with a biological sample disposed on a first surface of the support structure and the second emitting component associated with the biological sample disposed on a second surface of the support structure; determining base calls of irradiated sites that fluoresce within the first emitting component of the support structure using an aberration compensation model; and Base calls of irradiated sites that fluoresce within the second emitting component of the support structure are determined using the aberration compensation model, wherein the aberration compensation model is trained to compensate for aberrations of the first image data and to compensate for aberrations of the second image data.

27. The computer-readable storage medium of claim 26, wherein when executed by the processor is configured to cause the processor to: generating a first reconstructed image of the first image data using the aberration compensation model to compensate for the aberration of the first image, and generating a second reconstructed image of the second image data using the aberration compensation model to compensate for the aberration of the second image; and The base calls of the irradiated sites that fluoresce within the first emitting component of the support structure are determined using the first reconstructed image, and the base calls of the irradiated sites that fluoresce within the second emitting component of the support structure are determined using the second reconstructed image.

28. The computer-readable storage medium of claim 26, wherein when executed by the processor is configured to cause the processor to: The base calls of the irradiated sites that fluoresce within the first emitting component of the support structure and the base calls of the irradiated sites that fluoresce within the second emitting component of the support structure are determined using a base calling algorithm, wherein the base calling algorithm includes the aberration compensation model.

Images