KR20230081001A - Method for quantitative analysis of target gene and device using the same - Google Patents

Abstract

Provided is a device for quantitative analysis of a target gene and a method using the same according to an embodiment of the present invention. A quantitative analysis method of a target gene according to an embodiment of the present invention uses a confocal lens-based quantitative analysis device for a plurality of first sheets for microdroplets containing a target gene and a fluorescent material. ) acquiring an image, acquiring a second sheet image based on a plurality of first sheet images using an artificial intelligence algorithm-based optical model, and based on the fluorescence intensity of microdroplets in the second sheet image and performing quantitative analysis of the target gene.

Description

Method for quantitative analysis of target gene and device using the same {METHOD FOR QUANTITATIVE ANALYSIS OF TARGET GENE AND DEVICE USING THE SAME}

The present invention relates to a device for quantitative analysis of a target gene and a method using the same.

DNA amplification technology is widely used for R&D and diagnostic purposes in life science, genetic engineering, and medical fields, and among them, DNA amplification technology using polymerase chain reaction (PCR) is widely used.

Specifically, PCR is a molecular biology technique for replicating DNA from an isolated biological sample, and is used for various tasks, such as diagnosis of infectious diseases, detection of genetic diseases, and genetic fingerprinting. It can be used routinely in fingerprint identification, gene cloning, paternity testing, genotyping, gene sequencing and DNA computing.

In particular, digital polymerase chain reaction (dPCR) technology is a genetic testing method that divides a conventional sample into nanoliter droplets and observes a fluorescence change of a target gene contained therein. Such digital PCR has high sensitivity and enables absolute quantitative analysis, so it is highly utilized in genetic analysis, biomarker development, gene sequencing, and the like.

On the other hand, digital PCR technology can compensate for the disadvantages of the second-generation real-time PCR (RT) as it can perform absolute quantitative analysis, but it is based on a geometric optical reader, resulting in optical interference and the use of a separate fluorescence reader. , limitations may still exist in the assay step due to the low fluorescence intensity.

Therefore, there is a continuous demand for the development of a novel target gene quantitative analysis system capable of overcoming the limitations of the conventional digital PCR and performing high-precision analysis of the target gene in a sample.

The background description of the invention has been prepared to facilitate understanding of the present invention. It should not be construed as an admission that matters described in the background art of the invention exist as prior art.

On the other hand, the inventors of the present invention, in the conventional digital PCR technology, is carried out while flowing the PCR step-completed microdroplets to a channel-shaped detector for quantitative analysis of the target gene, and is based on a geometric optical reader. noticed.

More specifically, the inventors of the present invention, in the case of the conventional digital PCR technology, analyzes the intensity of the fluorescent substance for each of the microdroplets flowing into the detector, which takes a long analysis time and requires an expensive Photo Multiplier Tube (PMT). It was recognized that droplet reproduction may be required, and errors in quantitative analysis may occur due to light interference.

Accordingly, the inventors of the present invention paid attention to the fact that image-based quantitative analysis of microdroplets can solve the above problems.

In particular, the inventors of the present invention paid attention to the fact that the limitations of conventional digital PCR can be overcome by acquiring images of microdroplets containing a target gene and a fluorescent material and performing quantitative analysis.

As a result, the inventors of the present invention have developed a new target gene quantification system based on microdroplet image, which enables detection of target genes in microdroplets without the flow of microdroplets and enables faster quantitative analysis of target genes. .

At this time, the inventors of the present invention were able to design a target gene quantification system to perform quantitative analysis based on the microdroplet image reconstructed in 3D form.

As a result, it could be expected that precise quantitative analysis of the microdroplet and the target gene in the microdroplet would be possible.

In particular, the inventors of the present invention expected that as minute droplet analysis is possible, it is possible to detect viruses present in trace amounts, and to easily distinguish patients with asymptomatic viral infections.

In addition, the inventors of the present invention tried to further apply an artificial intelligence-based algorithm to a new target gene quantification system.

More specifically, the inventors of the present invention intended to apply an optical model learned to reconstruct a low-resolution image into a high-resolution image to a new target gene quantification system, which could be expected to enable advancement of diagnostic technology.

In this regard, the inventors of the present invention could expect high-precision quantitative analysis of the target gene even when using a low-performance lens.

Therefore, the problem to be solved by the present invention is to receive a sheet image of a microdroplet based on a confocal lens, obtain a high-resolution sheet image using an artificial intelligence algorithm-based optical model, and based on this, a target gene It is to provide a method for quantitative analysis of a target gene configured to perform quantitative analysis on and a device for quantitative analysis of a target gene using the same.

The tasks of the present invention are not limited to the tasks mentioned above, and other tasks not mentioned will be clearly understood by those skilled in the art from the following description.

In order to solve the above problems, a method for quantitative analysis of a target gene according to an embodiment of the present invention is provided.

A method for quantitative analysis of a target gene according to an embodiment of the present invention, using a device for quantitative analysis based on a confocal lens, a plurality of first sheets ( sheet) Acquiring an image, using an artificial intelligence algorithm-based optical model, obtaining a plurality of second sheet images based on the plurality of first sheet images, and measuring microdroplets in the plurality of second sheet images. and performing quantitative analysis of the target gene based on the fluorescence intensity.

According to a feature of the present invention, acquiring a plurality of first sheet images may include acquiring sheet images of micro droplets including a target gene and a fluorescent material in a tube in which PCR has been completed.

According to another feature of the present invention, a plurality of tubes, and obtaining a plurality of first sheet images, arranging the plurality of tubes in a row, controlling each of the plurality of tubes arranged in a row to move in one direction and acquiring a first sheet image of the tube including the microdroplets by using a device for quantitative analysis while moving in one direction.

According to another feature of the present invention, the method may further include generating a three-dimensional image based on the plurality of second sheet images after the acquiring of the plurality of second sheet images. In this case, performing the quantitative analysis may include performing quantitative analysis of the target gene based on the fluorescence intensity of the microdroplet in the 3D image.

According to another feature of the present invention, performing the quantitative analysis may include counting microdroplets expressing fluorescence in the 3D image.

According to another feature of the present invention, performing the quantitative analysis may include performing quantitative analysis of the target gene for each microdroplet based on the fluorescence intensity in the 3D image.

According to another feature of the present invention, the method may further include, after generating the 3D image, determining a size of each microdroplet.

According to another feature of the present invention, the performing quantitative analysis may include determining the number of micro-droplets in a plurality of second sheet images by using a predictive model configured to detect micro-droplets by taking an image of micro-droplets as an input. Prediction may be included.

According to another feature of the present invention, the optical model may be a model learned through the step of learning to reconstruct a low-resolution image for training into a high-resolution image.

According to another feature of the present invention, the method further includes, after the learning step, converting the reconstructed high-resolution image into a medium-resolution image for training, and re-learning to reconstruct the medium-resolution image for training into a high-resolution image. can include

According to another feature of the present invention, the obtaining of a plurality of second sheet images may include comparing the plurality of first sheet images with a pre-stored reconstructed high-resolution image using an optical model to obtain a high-resolution second sheet image. It may include a step of converting to.

In order to solve the above problems, a device for quantitative analysis of a target gene according to another embodiment of the present invention is provided. The device includes a tube in which microdroplets containing a target gene and a fluorescent substance for which polymerase chain reaction (PCR) has been completed are disposed; a light source for radiating light to at least one surface of the tube; a confocal lens corresponding to at least one surface of the tube; An image sensor disposed in a direction different from light emitted through the light source and configured to provide a plurality of first sheet images of the microdroplets in the tube, and a processor operatively connected to the image sensor. At this time, the processor obtains a plurality of second sheet images based on the plurality of first sheet images by using an artificial intelligence algorithm-based optical model, and obtains a plurality of second sheet images based on fluorescence intensities of microdroplets in the plurality of second sheet images. It is configured to perform quantitative analysis of a target gene.

According to a feature of the present invention, the device may further include a tube control unit for controlling the tube to be disposed and to move the disposed tube in one direction.

According to another feature of the present invention, the processor is further configured to generate a three-dimensional image based on the plurality of second sheet images, and perform quantitative analysis of the target gene based on the fluorescence intensity of the microdroplets in the three-dimensional image. can

According to another feature of the present invention, the processor may be further configured to count microdroplets expressing fluorescence in a three-dimensional image.

According to another feature of the present invention, the processor may be further configured to perform quantitative analysis of the target gene for each microdroplet based on the fluorescence intensity in the three-dimensional image.

According to another feature of the present invention, the processor is further configured to predict the number of micro-droplets in the plurality of second sheet images using a predictive model configured to detect the micro-droplets by taking the micro-droplet image as an input. can

According to another feature of the present invention, the optical model may be a model learned through the step of learning to reconstruct a low-resolution image for training into a high-resolution image.

Other embodiment specifics are included in the detailed description and drawings.

The present invention can provide a novel target gene quantification system based on a microdroplet image, capable of detecting a target gene in a microdroplet without flow of the microdroplet.

More specifically, the present invention can provide a target gene quantification system configured to perform quantitative analysis based on a high-resolution microdroplet image reconstructed based on an artificial intelligence algorithm.

In particular, as the present invention provides a target gene quantification system configured to perform quantitative analysis based on a microdroplet image reconstructed in a 3D form, precise quantitative analysis of a microdroplet and a target gene within the microdroplet may be possible.

Therefore, in the present invention, as the intensity of the fluorescent material for each microdroplet flowing into the detection channel is analyzed, the analysis time is long, an expensive Photo Multiplier Tube (PMT) is required, and droplet reproduction may be required. There is an effect that can overcome the limitations of the conventional digital PCR technology that may cause errors in quantitative analysis due to optical interference.

In particular, the present invention can shorten the quantitative analysis time of the target gene compared to conventional digital PCR, and can provide fast and precise analysis results for a large amount of samples.

Furthermore, as the present invention enables analysis in microdroplet units, it is possible to detect viruses present in trace amounts, and it is possible to provide ease of discrimination of patients with asymptomatic viral infections.

Effects according to the present invention are not limited by the contents exemplified above, and more various effects are included in the present specification.

1a and 1b exemplarily illustrate the structure and configurations of a device for quantitative analysis of a target gene used in various embodiments of the present invention.
Figure 2a shows the configuration of integrated equipment based on the device for quantitative analysis of target genes according to various embodiments of the present invention by way of example.
FIG. 2B illustratively shows microdroplets after PCR reaction according to the presence or absence of a target gene.
3a to 3d exemplarily illustrate procedures of quantitative analysis of a target gene using a device for quantitative analysis of a target gene according to various embodiments of the present invention.
4a and 4b exemplarily illustrate a procedure for learning an optical model of a device for quantitative analysis of a target gene according to various embodiments of the present disclosure.

The advantages of the invention, and how to achieve them, will become clear with reference to the detailed description of the following embodiments taken in conjunction with the accompanying drawings. However, the present invention is not limited to the embodiments disclosed below, but will be implemented in various different forms, only these embodiments make the disclosure of the present invention complete, and common knowledge in the art to which the present invention belongs. It is provided to fully inform the holder of the scope of the invention, and the present invention is only defined by the scope of the claims.

The shapes, sizes, ratios, angles, numbers, etc. disclosed in the drawings for explaining the embodiments of the present invention are illustrative, so the present invention is not limited to the details shown. In addition, in describing the present invention, if it is determined that a detailed description of related known technologies may unnecessarily obscure the subject matter of the present invention, the detailed description will be omitted. When 'includes', 'has', 'consists of', etc. mentioned in this specification is used, other parts may be added unless 'only' is used. In the case where a component is expressed in the singular, the case including the plural is included unless otherwise explicitly stated.

In interpreting the components, even if there is no separate explicit description, it is interpreted as including the error range.

Each feature of the various embodiments of the present invention can be partially or entirely combined or combined with each other, and as those skilled in the art can fully understand, various interlocking and driving operations are possible, and each embodiment can be implemented independently of each other. It may be possible to implement together in an association relationship.

For clarity of interpretation of this specification, terms used in this specification will be defined below.

As used herein, the term "sample" may refer to a fluid sample of a phase to be analyzed. For example, the fluid sample may be a microdroplet containing a detection target, cell lysate, whole blood, plasma, serum, saliva, ocular fluid, cerebrospinal fluid, sweat, urine, milk, ascites fluid, synovial fluid, and peritoneal fluid, It is not limited thereto.

Meanwhile, the target gene in the sample may be specific DNA or RNA. Preferably, the target gene may be RNA for a specific virus, but is not limited thereto.

As used herein, the term "micro droplet" is a micro droplet for digital PCR, and may include a target gene (or non-target gene) to be amplified, a fluorescent material, and a sample for PCR. Furthermore, the microdroplet may contain a PCR-completed target gene and a fluorescent material.

At this time, the fine droplets may be generated by contact between the sample and oil having immiscible properties.

As used herein, the term "confocal lens" is a lens that selectively provides an optical image matching the focal length using a special pinhole, and can provide 3D images according to the adjustment of the focal length. .

That is, it may be possible to acquire an image of sheet-shaped microdroplets by using a confocal lens and an image sensor.

As used herein, the term “sheet image” may refer to a plurality of slice images constituting 3D micro droplets. In this case, the sheet image, as an image obtainable from a device based on a confocal lens, may correspond to an optical sheet image by microdroplets expressing fluorescence due to amplification of a target gene.

Meanwhile, according to a feature of the present invention, a sheet image may be obtained from a tube containing fine droplets. That is, the sheet image may be an image of a tube in which fine droplets exist.

Also, the sheet image may be a still cut image of a tube moving in one direction.

As used herein, the term "first sheet image" is an original sheet image obtained from a device based on a confocal lens, in which a microdroplet (or a tube including the microdroplet) containing a target gene and a fluorescent material is attached. It can mean a sheet image for In this case, the microdroplet may include the target gene amplified according to the PCR reaction as described above, but is not limited thereto.

As used herein, the term “second sheet image” may refer to an image whose resolution (or image quality) is improved from the first sheet image. That is, the resolution of the second sheet image may be higher than that of the first sheet image. Therefore, the second sheet image may be easier to quantitatively analyze the microdroplets than the first sheet image.

As used herein, the term “optical model” may be an artificial intelligence algorithm-based model configured to convert a low resolution (or low quality) image into a high resolution (or high quality) image.

More specifically, the optical model may be a model learned to restore an original high-resolution micro-droplet image by taking a low-resolution micro-droplet training image as an input.

That is, the optical model can be learned to reconstruct the first sheet image and output a high-resolution second sheet image.

In this case, the low-resolution image used for learning may be an image obtained by converting a high-resolution micro-droplet image (or a tube image including the micro-droplet) into a low-resolution image.

According to a feature of the present invention, the optical model may be a convolutional neural network (CNN)-based model using a convolutional layer. For example, the optical model is based on Generative Adversarial Network (GAN), Very Deep Super Resolution (VDSR) based, Super-Resolution Using a Generative Adversarial Network (SRUGAN) based, Deep Convolution GAN (DCGAN), Interactive GAN (iGAN) based , or a resolution restoration algorithm based on StackGAN (StackGAN).

Thus, the optical model can provide precise quantitative analysis results for target genes in microdroplets under various imaging conditions, such as using low-performance lenses that provide low-quality images.

As used herein, the term “prediction model” may be a model trained to predict the number of microdroplets expressing fluorescence in the image by taking a sheet image of microdroplets as an input.

That is, the predictive model can be configured to provide a quantitative value of the target gene by detecting fluorescence-expressing microdroplets in the image.

In this case, the prediction model may be based on a deep learning algorithm for image segmentation based on Segnet, Unet, faster rcnn, FCN, or Voxnet, but is not limited thereto.

Hereinafter, with reference to 1a and 1b, a device for quantitative analysis of a target gene according to various embodiments of the present invention and its configuration will be described in detail.

1a and 1b exemplarily illustrate the structure and configurations of a device for quantitative analysis of a target gene used in various embodiments of the present invention.

First, referring to FIG. 1A, the device 1000 for quantitative analysis of a target gene according to an embodiment of the present invention includes a tube 110 including microdroplets, particularly PCR-completed microdroplets and a fluorescent material, a tube ( 110) is disposed, and a tube controller 120 for controlling the disposed tube to move in one direction, a confocal lens 210, a light source 310, an image sensor 400 for providing a sheet image, and configured to communicate therewith It may consist of a processor 500.

At this time, the device 1000 for quantitative analysis of the target gene according to an embodiment of the present invention changes the direction of the objective lenses 220a and 220b disposed in close proximity to the tube 110 including the microdroplet, and the light source. A reflector 320 may be further included.

More specifically, the sheet-light is irradiated into fine droplets on the tube 110 through the light source 310 and the reflector 320, and at the same time the tube 110 is moved in one direction by the tube control unit 120 for scanning. It can move or stop. At this time, by the confocal lens 210, the objective lens 220 and the image sensor 400, a plurality of first sheet images of the tube 110 moving at a constant speed or stopped can be obtained.

Meanwhile, the obtained plurality of first sheet images are images of a tube including microdroplets, and may correspond to optical sheet images of microdroplets expressing fluorescence according to amplification of a target gene.

The plurality of first sheet images obtained from the image sensor 400 are transmitted to a processor 500 configured to communicate with the image sensor 400, and the processor 500 determines a target based on the fluorescence intensity of microdroplets in the image. Quantitative analysis of genes can be performed.

At this time, the processor 500 may be based on an artificial intelligence algorithm-based optical model.

More specifically, the received plurality of first sheet images may be converted into second sheet images by an optical model learned to reconstruct low-resolution images into high-resolution images. Therefore, even if a low-resolution image is acquired from the image sensor 400, a high-resolution sheet image may be acquired by an artificial intelligence algorithm-based optical model.

Optionally, the processor 500 may be configured to convert the reconstructed image into a 3D voxel, ie, a 3D image, and then count microdroplets that emit fluorescence.

According to a feature of the present invention, the processor 500 may be further configured to perform quantitative analysis of the target gene for each microdroplet based on the fluorescence intensity in the three-dimensional image.

According to another feature of the present invention, the processor 500 may be further configured to predict the number of micro-droplets in the second sheet image by using a prediction model learned to detect micro-droplets by taking the micro-droplet image as an input. can

Meanwhile, the configuration and location of the device 1000 for quantitative analysis of a target gene according to an embodiment of the present invention are not limited to those described above.

For example, the image sensor 400 is not limited to being located on the back side of the objective lens 220b, but acquires a sheet image of the micro droplets to which the light source is irradiated, and acquires a sheet image in a direction different from that of the light source (eg, vertical position) may exist.

Furthermore, a plurality of confocal lenses 210 may be provided on the device 1000 for quantitative analysis of a target gene.

Meanwhile, referring to FIG. 1B , according to another feature of the present invention, a device 1000 ′ for quantitative analysis of a target gene may include a plurality of tubes 110 .

At this time, the plurality of tubes 110 may be arranged in a row in a tube control unit (not shown) for scanning microdroplets and then move in a direction in which sheet light is irradiated.

For example, while PCR is being performed, a plurality of tubes 110 bundled together for temperature control may be arranged in a row on a tube controller for analysis on each tube 110 in the step of detecting a target gene.

At this time, the plurality of tubes 110 can move between the image sensors 400 disposed at a position perpendicular to the irradiated sheet-light, and temporarily during scanning to obtain a sheet image of each still cut of the tubes 110. may stop with

However, it is not limited thereto, and while the plurality of tubes 110 are arranged in a line and moved, a sheet image of each tube 110 may be acquired.

Furthermore, the moving direction of the tube 110 by the tube controller is not limited to a direction parallel to the image sensor 400, and can be set in more diverse directions.

According to the above structural features, analysis can be performed only with the image of the tube containing the PCR-completed microdroplets without the process of moving the microdroplets to the channel-shaped detector, enabling precise and fast quantitative analysis of the target gene. Furthermore, since artificial intelligence-based optical models and/or predictive models can be applied, the reliability of target genetic testing can be improved.

Hereinafter, with reference to FIGS. 2A and 2B, integrated analysis equipment equipped with a device for quantitative analysis of a target gene according to various embodiments of the present invention will be described. Figure 2a shows the configuration of integrated equipment based on the device for quantitative analysis of target genes according to various embodiments of the present invention by way of example. FIG. 2B illustratively shows microdroplets after PCR reaction according to the presence or absence of a target gene.

The integrated analysis equipment 10000 may include a device 1000 for quantitative analysis of a target gene according to various embodiments of the present invention, a microdroplet generation unit 2000, and a PCR unit 3000.

More specifically, in the microdroplet generating unit 2000, contact between a sample including a target gene and oil may be induced. When the sample and the oil come into contact, a plurality of micro droplets encapsulated in the oil may be formed. At this time, the micro-droplets may be generated including the target gene. In this case, the microdroplet may include a target gene, a fluorescent material, a primer, and a polymerase.

The microdroplets generated from the microdroplet generating unit 2000 move to the PCR unit 3000 . At this time, the fine droplets may be accommodated in a pre-equipped tube. Then, the temperature condition cycle for amplifying the target gene in the micro-droplet is provided to the micro-droplet, and as a result, the micro-droplet on the tube may contain the amplified target gene and the fluorescent material.

More specifically, with reference to FIG. 2B , microdroplets containing a target gene, such as a viral gene, can express fluorescence along with amplification of the gene.

In contrast, in the case of empty microdroplets and microdroplets containing normal genes, fluorescence expression may not occur even though PCR is performed by the PCR unit 3000 .

Then, the tube containing the microdroplet on which the PCR has been completed may be moved to the device 1000 for quantitative analysis of the target gene according to various embodiments of the present invention by the tube control unit.

At this time, a plurality of first sheet images and a high-resolution second sheet image of the tube are sequentially obtained by the device 1000 for quantitative analysis of the target gene, and a three-dimensional image is reconstructed. Then, the number of microdroplets containing the target gene is determined from the reconstructed 3D image.

That is, the integrated analysis equipment 10000 can be configured not only to generate microdroplets containing the target gene and amplify the target gene in the microdroplets, but also to perform quantitative analysis of the target gene.

Accordingly, molecular biological analysis of the target gene is possible without user handling, and thus highly reliable quantitative analysis results can be obtained.

Hereinafter, procedures of a method for quantitative analysis of a target gene using a device for quantitative analysis of a target gene according to various embodiments of the present invention will be described with reference to FIGS. 3A to 3D.

3A to 3D exemplarily illustrate procedures of a method for quantitative analysis of a target gene using a device for quantitative analysis of a target gene according to various embodiments of the present invention.

First, referring to FIG. 3A , first, a plurality of first sheet images of microdroplets are acquired from a device for quantitative analysis based on a confocal lens (S210), and a plurality of first sheet images are obtained by an optical model. A plurality of second sheet images are obtained (S220). Finally, quantitative analysis of the target gene is performed based on the fluorescence intensity of the microdroplets in the second sheet image (S230).

More specifically, referring to FIG. 3B , in step S210 in which a plurality of first sheet images are acquired, microfluids are analyzed by the confocal lens-based device 100 for quantitative analysis according to various embodiments of the present invention. A plurality of first sheet images 612 of the enemy are obtained.

At this time, the plurality of first sheet images 612 may correspond to images of tubes.

Furthermore, the plurality of first sheet images 612 may be low-resolution images.

Then, in step S220 of acquiring second sheet images, the plurality of first sheet images 612 are input to the artificial intelligence-based optical model 510, and the plurality of high-resolution second sheet images 614 are is obtained Then, the high-resolution second sheet image 614 is reconstructed into 3D voxels.

That is, in the step of acquiring the second sheet image (S220), the low-resolution image may be restored to a high-resolution image by the optical model 510.

In this case, the optical model 510 may be an artificial intelligence algorithm-based model configured to convert a low resolution (or low quality) image into a high resolution (or high quality) image.

More specifically, referring to FIG. 3C , in step S220 of acquiring second sheet images, a plurality of low-quality first sheet images 612 are obtained by sheet-light irradiating a tube including fine droplets. is input to the optical model 510. Next, the optical model 510 compares the previously stored second sheet image with the input plurality of first sheet images 612 in the learning step, and outputs a plurality of second sheet images 614 with high resolution. The plurality of high-resolution second sheet images 614 thus output are converted into 3D voxels, and as a result, a 3D image 616 of the microdroplets can be obtained.

Referring back to FIG. 3A , in step S230 where quantitative analysis of the target gene is performed, quantitative analysis of the target gene may be performed based on the fluorescence intensity of the microdroplet in the 3D image.

According to the features of the present invention, In the step of performing quantitative analysis of the target gene (S230), the microdroplets in the second sheet image may be detected using a prediction model configured to predict the number of microdroplets by taking the microdroplet image as an input. there is.

More specifically, referring to FIG. 3D , in the step of performing quantitative analysis of the target gene (S230), the reconstructed 3D image 616 is input to the artificial intelligence-based prediction model 520, and the prediction model 520 A quantitative analysis result 618 for the microdroplet including the target gene and the fluorescent material can be output from the above.

In this case, the prediction model may be a model learned to predict the number of microdroplets by segmenting microdroplets emitting fluorescence in the image by taking a sheet image of microdroplets as an input.

According to a feature of the present invention, the predictive model 520 may be based on a deep learning algorithm for image segmentation based on Segnet, Unet, faster rcnn, FCN, or Voxnet, but is not limited thereto.

Accordingly, the quantitative analysis result 618 of the microdroplet may include a result of region division of the microdroplet in which the fluorescence is expressed in the 3D image 616, and the microdroplet in which the fluorescence is expressed, that is, the target gene and the fluorescent material It may further include counting results for fine droplets containing.

On the other hand, according to the features of the present invention, In the step of performing quantitative analysis of the target gene ( S230 ), based on the fluorescence intensity in the 3D image 616 , quantitative analysis of the target gene for each microdroplet may be performed.

That is, the fluorescence intensity of each microdroplet can be determined by the quantitative analysis method according to various embodiments of the present invention, so that not only the quantitative analysis of the target gene for the entire sample, but also the quantitative analysis of the target gene for each microdroplet this could be possible Thus, precise analysis results for target genes can be provided.

According to another feature of the present invention, In the step of performing quantitative analysis of the target gene (S230), the size of each microdroplet may be determined according to the fluorescence intensity.

Therefore, according to various embodiments of the present invention, a device for quantitative analysis of a target gene based on a tube image and a quantitative analysis method using the same can perform quantitative analysis based on a micro-droplet image reconstructed in a 3D form, It is possible to provide accurate quantitative analysis results for the target gene in the droplet, and furthermore, the microdroplet.

In particular, as the present invention analyzes the intensity of the fluorescent material for each microdroplet flowing into the detection channel, it takes a long analysis time, requires an expensive Photo Multiplier Tube (PMT), and may require droplet reproduction. It is possible to overcome the limitations of the conventional digital PCR technology, which may cause errors in quantitative analysis due to optical interference.

Hereinafter, a method of learning an optical model used in various embodiments of the present invention will be described with reference to FIGS. 4A and 4B.

4a and 4b exemplarily illustrate a procedure for learning an optical model of a device for quantitative analysis of a target gene according to various embodiments of the present disclosure.

First, referring to FIG. 4A , a second sheet image of a microdroplet is obtained for learning an optical model (S310), and then the second sheet image is converted into a low-resolution image for learning (S320). Then, the optical model is learned to reconstruct the low-resolution image for training into a second sheet image (S330).

More specifically, referring to FIG. 4B , a high-resolution sheet image 712 with a low field of view (FOV) is obtained in step S310 of obtaining a second sheet image. Next, in order to acquire data for training of the optical model 510, a step of converting the low-resolution image for training (S320) is performed. As a result, a low-resolution learning sheet image 714 is obtained. At this time, various conversions such as ratio and size may be performed on the low-resolution learning sheet image 714 in order to diversify the learning data. Then, in the learning step (S330), the converted learning sheet image 716 is input to the optical model 510, and the optical model 510 converts the converted learning sheet image 716 into a high-resolution sheet image 712. It is learned to restore a corresponding image.

That is, the optical model 510 is trained to output a reconstructed high-resolution sheet image 718 from the low-resolution training sheet image 714. Optionally, the reconstructed high-resolution sheet image 718 can be converted to a medium-quality sheet image 719 and reused for training the optical model 510 .

The optical model 510 learned through the above procedures can provide accurate quantitative analysis results for target genes in microdroplets under various photographing conditions equipped with low-performance lenses or image sensors providing low-quality images.

In this case, the optical model 510 may be a convolutional neural network (CNN)-based model using a convolutional layer. For example, the optical model is based on Generative Adversarial Network (GAN), Very Deep Super Resolution (VDSR) based, Super-Resolution Using a Generative Adversarial Network (SRUGAN) based, Deep Convolution GAN (DCGAN), Interactive GAN (iGAN) based , or a resolution restoration algorithm based on StackGAN (StackGAN).

However, the learning procedures and algorithms of the optical model 510 are not limited to those described above.

Although the embodiments of the present invention have been described in more detail with reference to the accompanying drawings, the present invention is not necessarily limited to these embodiments, and may be variously modified and implemented without departing from the technical spirit of the present invention. Therefore, the embodiments disclosed in the present invention are not intended to limit the technical idea of the present invention, but to explain, and the scope of the technical idea of the present invention is not limited by these embodiments. Therefore, the embodiments described above should be understood as illustrative in all respects and not limiting. The protection scope of the present invention should be construed according to the claims below, and all technical ideas within the equivalent range should be construed as being included in the scope of the present invention.

10000: Integrated analysis equipment
1000, 1000': Device for quantitative analysis of target genes
110: tube
120: tube control
210: confocal lens
220a, 220b: objective lens
310: light source
320: reflector
400: image sensor
500: processor
510: optical model
520: prediction model
612: plurality of first sheet images
614: A plurality of high-resolution second sheet images
616: reconstructed 3D image
618: quantitative analysis result
712: high-resolution sheet image
714: low resolution learning sheet image
716: Converted learning sheet image
718: reconstructed high-resolution sheet image
719: medium quality sheet image
2000: micro droplet generating unit
3000: PCR unit

Claims (18)

Acquiring a plurality of first sheet images of microdroplets including a target gene and a fluorescent material by using a confocal lens-based device for quantitative analysis;
Acquiring a plurality of high-resolution second sheet images based on the plurality of first sheet images by using an artificial intelligence algorithm-based optical model; and
And performing a quantitative analysis of the target gene based on the fluorescence intensities of the microdroplets in the plurality of second sheet images. According to claim 1,
The step of obtaining the plurality of first sheet images,
Acquiring a sheet image of a tube containing a target gene for which gene amplification has been completed and microdroplets containing a fluorescent material, a method for quantitative analysis of a target gene. According to claim 2,
The tube is plural,
The step of obtaining the plurality of first sheet images,
arranging the plurality of tubes in a row;
Controlling each of the plurality of tubes arranged in a row to move in one direction, and
Acquiring a first sheet image of a tube containing the microdroplets by using the device for quantitative analysis while moving in one direction, wherein the target gene is quantitatively analyzed. According to claim 1,
After acquiring the plurality of second sheet images,
Further comprising generating a three-dimensional image based on the plurality of second sheet images,
Performing the quantitative analysis,
Comprising the step of performing a quantitative analysis of the target gene based on the fluorescence intensity of the microdroplet in the three-dimensional image, a quantitative analysis method of the target gene. According to claim 4,
Performing the quantitative analysis,
A method for quantitative analysis of a target gene comprising counting microdroplets expressing fluorescence in the three-dimensional image. According to claim 4,
Performing the quantitative analysis,
Based on the fluorescence intensity in the three-dimensional image, performing a quantitative analysis of the target gene for each microdroplet, a quantitative analysis method of the target gene. According to claim 4,
After generating the three-dimensional image,
A method for quantitative analysis of a target gene, further comprising determining the size of each of the microdroplets. According to claim 1,
Performing the quantitative analysis,
A method for quantitatively analyzing a target gene, comprising predicting the number of microdroplets in the plurality of second sheet images using a prediction model configured to detect microdroplets by taking an image of microdroplets as an input. According to claim 1,
The optical model,
A method for quantitative analysis of a target gene, which is a model learned through the step of learning to reconstruct a low-resolution image for learning into a high-resolution image. According to claim 9,
After the learning step,
converting the reconstructed high-resolution image into a medium-resolution image for learning; and
Further comprising the step of re-learning to reconstruct a medium-resolution image for learning into a high-resolution image, a method for quantitative analysis of a target gene. According to claim 9,
The step of acquiring the plurality of second sheet images,
Using the optical model, comparing the plurality of first sheet images and the pre-stored reconstructed second sheet image to convert the high-resolution second sheet image into a quantitative analysis method of a target gene. a light source for radiating light to at least one surface of the tube on which the micro droplets containing the target gene and the fluorescent substance, for which polymerase chain reaction (PCR) has been completed, are disposed;
a confocal lens corresponding to at least one surface of the tube;
An image sensor disposed in a direction different from that of the light irradiated through the light source and configured to provide a plurality of first sheet images of the microdroplets in the tube, and
a processor operatively connected to the image sensor;
the processor,
Obtaining a plurality of high-resolution second sheet images based on the plurality of first sheet images using an artificial intelligence algorithm-based optical model,
A device for quantitative analysis of a target gene, configured to perform quantitative analysis of the target gene based on fluorescence intensities of microdroplets in the plurality of second sheet images. According to claim 12,
A device for quantitative analysis of a target gene, further comprising a tube control unit for controlling the tube to be disposed and to move the disposed tube in one direction. According to claim 12,
the processor,
A device for quantitative analysis of a target gene, further configured to generate a three-dimensional image based on the plurality of second sheet images, and perform quantitative analysis of the target gene based on the fluorescence intensity of microdroplets in the three-dimensional image. According to claim 14,
the processor,
A device for quantitative analysis of a target gene, further configured to count microdroplets expressing fluorescence in the three-dimensional image. According to claim 14,
the processor,
A device for quantitative analysis of a target gene, further configured to perform quantitative analysis of the target gene for each microdroplet based on the fluorescence intensity in the three-dimensional image. According to claim 12,
the processor,
The device for quantitative analysis of a target gene, further configured to predict the number of microdroplets in the plurality of second sheet images using a prediction model configured to detect microdroplets by taking an image of microdroplets as an input. According to claim 12,
The optical model,
A device for quantitative analysis of a target gene, which is a model learned through the step of learning to reconstruct a low-resolution image for learning into a high-resolution image.

Images