Method and system for generating biomarker of specific disease

The method preprocesses genetic data to generate biomarkers using an AI model that identifies bacteria associated with diseases, addressing the limitations of conventional biomarkers by enabling non-invasive prediction of disease presence through symbiotic flora changes.

WO2024253325A1PCT designated stage expired Publication Date: 2024-12-12GRADIANT BIOCONVERGENCE INC
View PDF 5 Cites 0 Cited by

Patent Information

Application Number
PCT/KR2024/005606
Authority / Receiving Office
WO · WO
Patent Type
Applications
Current Assignee / Owner
Priority Date
2023-06-09
Filing Date
2024-04-25
Publication Date
2024-12-12

AI Technical Summary

Technical Problem

Conventional biomarkers based on gene expression levels are difficult to use due to the instability and scarcity of RNA, and there is a lack of developed kits for diseases other than colon cancer using DNA methylation patterns, highlighting the need for alternative methods to predict disease presence through changes in human symbiotic flora.

Method used

A method and system that preprocess genetic data to generate a biomarker by creating a learning dataset from bacterial type and number information, using an artificial intelligence model to extract bacteria associated with specific diseases and group them based on interrelationship information, enabling non-invasive prediction of disease presence.

Benefits of technology

Enables the prediction of disease presence through specific changes in the human body's symbiotic flora, confirming bacterial distribution in a non-invasive manner and generating biomarkers for specific diseases.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure KR2024005606_12122024_PF_FP_ABST
    Figure KR2024005606_12122024_PF_FP_ABST
Patent Text Reader

Abstract

One embodiment of the present disclosure provides a method for generating a biomarker. The method comprises the steps of: generating a training data set by preprocessing gene data including bacterial type and number information on specific genetic material information of normal persons and patients with a specific disease; generating an artificial intelligence model, which is trained to extract bacteria having a high correlation with the specific disease from gene data inputted on the basis of the training data set; and generating a biomarker for the specific disease by grouping the bacteria extracted by the artificial intelligence model on the basis of correlation information of the bacteria extracted by the artificial intelligence model.
Need to check novelty before this filing date? Find Prior Art

Description

Method and system for generating a biomarker for a specific disease

[0001] The present invention relates to a method and system for generating a biomarker for a specific disease, and more particularly, to a method and system for generating a biomarker based on genetic data for normal people and patients with a specific disease.

[0002] Traditionally, the cause of diseases was considered to be an internal trigger or the introduction and infection of a specific foreign body (e.g., virus), and the cause, diagnosis, and treatment of the disease were performed targeting the tissue where the disease occurred.

[0003] However, recently, the distribution of the microbiota is changing in a special direction due to changes in the living environment caused by diseases or the bacteria that coexist in the human body, such as intestinal microbes, becoming the cause of diseases.

[0004] In addition, conventional biomarkers based on differences in the expression level of specific genes must confirm the mRNA-based transcript expression level, but RNA is relatively easy to degrade and difficult to obtain in large quantities, making it difficult to use as a marker in the medical field.

[0005] In contrast, to confirm DNA methylation patterns, blood-derived DNA can be isolated and the degree of methylation can be determined using methods such as bisulfite sequencing (BSP), making it relatively easy and quick to diagnose and predict the prognosis of specific diseases. For example, kits have already been developed to diagnose or predict the prognosis of colon cancer by confirming DNA methylation patterns from samples such as stool. However, for other diseases, kit development and biomarker discovery research based on DNA methylation information are relatively poorly conducted.

[0006] Accordingly, there is a need for research on technologies that can predict the presence or absence of disease by identifying specific changes in the microbiota that coexist in the human body.

[0007] The present disclosure is intended to solve the problems of the prior art described above, and to provide a method and system for generating biomarkers based on genetic data for normal people and patients with specific diseases.

[0008] The technical problems to be solved by the present invention are not limited to the technical problems described above, and other technical problems of the present invention can be derived from the following description.

[0009] As a technical means for solving the above-described technical problem, an embodiment according to a first aspect of the present disclosure provides a method for generating a biomarker. The method includes a step of preprocessing genetic data including bacterial type and number information regarding specific genetic material information of normal people and patients with a specific disease to generate a learning data set, a step of generating an artificial intelligence model trained to extract bacteria highly correlated with the specific disease from input genetic data based on the learning data set, and a step of grouping bacteria extracted by the artificial intelligence model based on information on mutual relationships between the bacteria extracted by the artificial intelligence model to generate a biomarker for the specific disease.

[0010] In addition, an embodiment according to a second aspect of the present disclosure provides a biomarker generation system. The system includes a communication module, at least one processor, and a memory electrically connected to the processor and storing at least one code to be executed by the processor, wherein the memory stores a code that, when executed through the processor, causes the processor to preprocess genetic data including bacterial species and number information regarding specific genetic material information of normal people and patients with a specific disease to generate a learning data set, generate an artificial intelligence model trained to extract bacteria highly correlated with the specific disease from the input genetic data based on the learning data set, and group bacteria extracted by the artificial intelligence model based on information on mutual relationships between the bacteria extracted by the artificial intelligence model to generate a biomarker for the specific disease.

[0011] According to the present invention, the presence or absence of a disease can be predicted through specific changes in the microflora coexisting in the body.

[0012] Additionally, according to the present invention, the distribution of bacteria can be confirmed in a non-invasive manner.

[0013] The effects of the present invention are not limited to the effects described above, and include all effects understood from the following description.

[0014] FIG. 1 is a diagram illustrating a biomarker generation system according to one embodiment of the present invention.

[0015] Figure 2 is a drawing showing the detailed configuration of the server illustrated in Figure 1.

[0016] [Correction under Rule 91 24.09.2024] Figures 3a, 3b, 4, 5a and 5b are diagrams showing examples of genetic data including information on the type and number of bacteria.

[0017] Figure 6 is a flowchart illustrating the sequence of a biomarker generation method according to another embodiment of the present invention.

[0018] Figure 7 is a flowchart illustrating an example of a biomarker generation method according to another embodiment of the present invention.

[0019] Hereinafter, the present disclosure will be described in detail with reference to the attached drawings. However, the present disclosure may be implemented in various different forms and is not limited to the embodiments described herein. In addition, the attached drawings are only intended to facilitate understanding of the embodiments disclosed in the present specification, and the technical concepts disclosed in the present specification are not limited by the attached drawings. All terms, including technical and scientific terms, used herein should be interpreted as having meanings generally understood by a person of ordinary skill in the technical field to which the present disclosure pertains. Terms defined in the dictionary should be interpreted as having additional meanings consistent with the relevant technical literature and the present disclosure, and shall not be interpreted in an extremely ideal or restrictive sense unless otherwise defined.

[0020] To clearly explain the present disclosure in the drawings, parts irrelevant to the description have been omitted, and the size, shape, and appearance of each component shown in the drawings may vary. Identical / similar parts throughout the specification are designated with identical / similar drawing reference numerals.

[0021] The suffixes "module" and "part" used in the following description for components are assigned or used interchangeably solely for the convenience of writing the specification, and do not in themselves have distinct meanings or roles. Furthermore, in describing the embodiments disclosed herein, detailed descriptions of related known technologies have been omitted if they are deemed to obscure the gist of the embodiments disclosed herein.

[0022] Throughout the specification, when a part is said to be "connected (connected, in contact with, or coupled)" to another part, this includes not only cases where it is "directly connected (connected, in contact with, or coupled)" but also cases where it is "indirectly connected (connected, in contact with, or coupled)" with another member in between. Furthermore, when a part is said to "include (have or provide)" a certain component, this does not mean that it excludes other components, but rather that it may "include (have or provide)" other components, unless otherwise specifically stated.

[0023] As used herein, ordinal terms such as "first," "second," etc., are used solely to distinguish one component from another and do not limit the order or relationship of the components. For example, the first component of the present disclosure may be referred to as the "second component," and similarly, the second component may also be referred to as the "first component." As used herein, singular forms should be construed to include plural forms, unless explicitly stated otherwise.

[0024] FIG. 1 is a diagram illustrating a biomarker generation system according to one embodiment of the present invention.

[0025] *Referring to FIG. 1, the biomarker generation system includes a server (100) and a user terminal (200), and the server (100) and the user terminal (200) can be connected to each other through a communication network.

[0026] The server (100) preprocesses genetic data containing bacterial species and count information regarding specific genetic material information of normal individuals and patients with specific diseases to generate a learning data set. For example, the specific genetic material information may include at least one of 16s rRNA data and metagenomic data.

[0027] The server (100) generates an artificial intelligence model trained to extract bacteria with a high correlation with a specific disease from input genetic data based on a learning data set. For example, the server (100) may generate an artificial intelligence model trained to extract bacteria with a high probability of developing diabetes from input genetic data based on a learning data set.

[0028] The server (100) groups bacteria extracted by the artificial intelligence model based on information about the mutual relationships between bacteria extracted by the artificial intelligence model to generate a biomarker for a specific disease. For example, if the first bacteria, the third bacteria, and the fifth bacteria are extracted from patients with diabetes by the artificial intelligence model, and the first bacteria, the third bacteria, and the fifth bacteria are not extracted from normal people by the artificial intelligence model, the server (100) can group the first bacteria, the third bacteria, and the fifth bacteria to generate a biomarker for diabetes.

[0029] The user terminal (200) can receive a biomarker generated for a specific disease from the server (100). In addition, the user terminal (200) can transmit genetic data of normal individuals and patients with specific diseases to the server.

[0030] The user terminal (200) can be connected to the server (100) through a communication network. The user terminal (200) may refer to any type of handheld-based wireless communication device, such as a notebook, desktop, laptop, or wireless communication device with portability and mobility, equipped with a web browser, or a smartphone or tablet PC.

[0031] Figure 2 is a drawing showing the detailed configuration of the server illustrated in Figure 1.

[0032] Referring to FIG. 2, the server (100) may include a communication module (110), a processor (120), and a memory (130).

[0033] The communication module (110) may include a device including hardware and software necessary to transmit and receive signals such as control signals or data signals through wired or wireless connections with other network devices.

[0034] *The communication module (110) can receive genetic data of normal individuals and patients with specific diseases from user terminals. In addition, the communication module (110) can transmit biomarkers generated for specific diseases.

[0035] The processor (120) may include various types of devices that control and process data. The processor (120) may refer to a data processing device built into hardware that has a physically structured circuit to perform functions expressed in code or instructions included in a program.

[0036] In one example, the processor (120) may be implemented in the form of a microprocessor, a central processing unit (CPU), a processor core, a multiprocessor, an application-specific integrated circuit (ASIC), a field programmable gate array (FPGA), etc., but the scope of the present invention is not limited thereto.

[0037] The processor (120) performs operations according to the code stored in the memory (130).

[0038] The memory (130) can store at least one of information and data input to the communication module (110), information and data required for functions performed by the processor (120), and data generated according to the execution of the processor (120).

[0039] Memory (130) should be interpreted as a general term for a non-volatile storage device that maintains stored information even when no power is supplied and a volatile storage device that requires power to maintain stored information. Memory (130) may include magnetic storage media or flash storage media in addition to a volatile storage device that requires power to maintain stored information, but the scope of the present invention is not limited thereto.

[0040] The memory (130) is electrically connected to the processor (120) and stores at least one code to be executed by the processor (120). The memory (130) stores code that, when executed by the processor (120), causes the processor (120) to perform the following functions and procedures.

[0041] A code that causes genetic data of normal individuals and patients with the specific disease to be added may be stored in the memory (130). For example, the genetic data may include at least one of 16s rRNA data and metagenomic data.

[0042] The memory (130) stores a code that causes genetic data including information on the type and number of bacteria regarding specific genetic material information of normal people and patients with specific diseases to be preprocessed to generate learning data.

[0043] The memory (130) may store code that reduces the dimensionality of the number of bacteria in the genetic data and causes two columns to be selected from the reduced bacteria. For example, the memory (130) may store code that causes the dimensionality of the number of bacteria to be reduced based on at least one of the Lasso technique, the Ridge technique, the Recursive Feature Elimination technique, and the Autoencoder technique.

[0044] Additionally, the memory (130) may store code that causes the removal of bacteria found to be associated with a specific disease, the reduction of the dimension of the number of bacteria in the genetic data, and the selection of two columns from among the reduced bacteria.

[0045] For example, if Bacteroides_vulgatus data is found to be related, 'Escherichia_coli', 'Agathobacter_rectalis', 'Prevotella_copri', 'Bacteroides_vulgatus', 'Prevotella_copri' and 'Faecalibacterium_prausnitzii' related to the Bacteroides_vulgatus data can be removed.

[0046] The memory (130) may store a code that causes an artificial intelligence model trained to extract bacteria with a high correlation with a specific disease from input genetic data based on a learning data set.

[0047] For example, an artificial intelligence model trained to extract bacteria with a high correlation with diabetes from input genetic data based on a learning data set based on code stored in memory (130) can be generated. Here, the artificial intelligence model can be at least one of logistic regression, KNN, and SVM.

[0048] In addition, the memory (130) may store a code that causes learning to proceed in two dimensions based on two columns of selected bacteria. For example, if 300 dimensions remain, the process of selecting two columns of bacteria and the process of proceeding with learning in two dimensions may be repeated 44850 times (300*299) / 2 = 44850. Here, the dimension may be the number of bacteria, and the memory (130) may store a code that causes learning to proceed with two numbers of bacteria based on two columns of selected bacteria.

[0049] A code that causes a list of data having a preset value or higher among genetic data may be stored in the memory (130).

[0050] The memory (130) stores a code that causes the bacteria extracted by the artificial intelligence model to be grouped based on the information on the mutual relationship between the bacteria extracted by the artificial intelligence model to generate a biomarker for a specific disease. Here, the mutual relationship information can be generated by a comparison result between the information on bacteria included in the genetic data of normal individuals and the information on bacteria extracted by the artificial intelligence model, and a comparison result between the information on bacteria included in the genetic data of patients with a specific disease and the information on bacteria extracted by the artificial intelligence model.

[0051] Figures 3 to 5 are diagrams illustrating examples of genetic data including information on the type and number of bacteria.

[0052] Referring to FIGS. 3 to 5, the server may provide the type (310) and number (320) of bacteria held by each person, person information, and species classification information for each bacteria. For example, the number of bacteria held by each person may be the number of ASVs (Amplicon Sequence Variants) held by each person, and may be the number of bacteria matching each ASV.

[0053] Based on the received genetic data, the bacteria possessed by each person can be obtained by obtaining information that person F001 possesses 4 types of bacteria and person F002 possesses 0 types of bacteria. For example, the genetic data of person A can be obtained by obtaining information that person A contains 162 types of bacteria of the second type, 191 types of bacteria of the eighth type, 208 types of bacteria of the thirteenth type, and 134 types of bacteria of the twenty-fourth type.

[0054] Human information can include sample ID (SampleID), age (Age), sex (Sex), family group ID (Family_ID) to indicate family, presence of twins (Family_relation), CC / CT / TT (mutation composition of APOA5, found to be a genetic risk factor for MtS disease), presence of metabolic syndrome (healthy OR MetS), diastolic blood pressure (DBP; diastolic blood pressure, pressure inside the arteries during diastole when the heart relaxes), systolic blood pressure (SBP; systolic blood pressure, pressure during ventricular systole when the heart contracts and blood is pumped into the aorta), waist circumference (Waist), triglyceride level (Triglyceride), fasting blood sugar (FBS), high-density lipoprotein (HDL), raw data Accession ID (Accession), and information about the age bin to which the data belongs when dividing the data into 5 groups by age.

[0055] Species classification information for bacteria can include data for each of the following categories: Kingdom, phylum, class, order, family, genus, and species. Kingdom, phylum, class, order, family, genus, and species can be a large list of taxonomic levels of information for a single organism. In other words, it can contain classification information for multiple species within the phylum of bacteria.

[0056] Figure 6 is a flowchart illustrating the sequence of a biomarker generation method according to another embodiment of the present invention.

[0057] The biomarker generation method described below can be performed by the biomarker generation system and server described above with reference to FIGS. 1 to 5. Accordingly, the content of the embodiments of the present disclosure described above with reference to FIGS. 1 to 5 can be equally applied to the embodiments described below, and any content overlapping with the above description will be omitted. The steps described below do not necessarily have to be performed in order, and the order of the steps can be set in various ways, and the steps can be performed almost simultaneously.

[0058] Referring to FIG. 6, the biomarker generation method includes a genetic data addition step (S100), a learning data set generation step (S200), an artificial intelligence model generation step (S300), and a biomarker generation step (S400).

[0059] The genetic data addition step (S100) may be a step of adding genetic data of a normal person and genetic data of a patient with a specific disease.

[0060] The learning data set creation step (S200) preprocesses genetic data containing bacterial species and count information related to specific genetic material information of normal individuals and individuals with specific diseases to create a learning data set. For example, preprocessing may include removing bacteria already identified as being associated with disease, reducing the dimensionality of the bacterial counts per person, and selecting two columns from the reduced number of bacteria.

[0061] The AI ​​model creation step (S300) is a step for creating an AI model trained to extract bacteria with a high correlation with a specific disease from the input genetic data based on the learning data set. For example, in the AI ​​model creation step (S300), a two-dimensional classification is performed based on the two columns selected in the learning data set creation step (S200), and a list of data exceeding a specific value can be obtained.

[0062] The biomarker generation step (S400) is a step that groups bacteria extracted by an AI model based on their mutual relationship information to create biomarkers for specific diseases. For example, in the biomarker generation step (S400), bacteria that diabetic patients have but not healthy individuals can be grouped and these bacteria can be created as biomarkers for diabetes.

[0063] Figure 7 is a flowchart illustrating an example of a biomarker generation method according to another embodiment of the present invention.

[0064] The biomarker generation method described below can be performed by the biomarker generation system and server described above with reference to FIGS. 1 to 5. Accordingly, the content of the embodiments of the present disclosure described above with reference to FIGS. 1 to 5 can be equally applied to the embodiments described below, and any content overlapping with the above description will be omitted. The steps described below do not necessarily have to be performed in order, and the order of the steps can be set in various ways, and the steps can be performed almost simultaneously.

[0065] Referring to FIG. 7, the method may include a genetic data addition step (S710), a step of determining whether there is data related to a specific disease (720), a step of reducing the dimension of the number of ASVs per person (S730), a step of selecting two columns from the reduced ASVs (S740), a step of learning and classifying in two dimensions (S750), a step of grouping related factors (S760), a step of generating biomarkers using factors (S770), and a step of removing data related to a specific disease (S780).

[0066] The genetic data addition step (S710) may be a step of adding genetic data of a normal person and genetic data of a patient with a specific disease.

[0067] The step (720) of determining whether data related to a specific disease exists may be a step of determining whether data related to a specific disease exists among genetic data. If data related to a specific disease does not exist within the genetic data, a step of reducing the number of ASVs per person (S730) may be performed. If data related to a specific disease exists within the genetic data, a step of removing data related to a specific disease (S780) may be performed.

[0068] The dimensionality reduction step (S730) of the number of ASVs per person may be a step of reducing the dimensionality of the number of bacteria per person. For example, the dimensionality reduction step (S730) of the number of ASVs per person may be reduced based on at least one of the Lasso technique, the Ridge technique, the Recursive Feature Elimination technique, and the Autoencoder technique. Here, the number of ASVs per person may be the number of types of bacteria per person.

[0069] The step of selecting two columns from among the reduced ASVs (S740) may be a step of selecting two columns from among the reduced ASVs.

[0070] The two-dimensional learning and classification step (S750) may be a step for performing two-dimensional classification. For example, the two-dimensional learning and classification step (S750) may perform two-dimensional classification based on at least one of logistic regression, KNN, and SVM.

[0071] However, the two-column selection step (S740) and the two-dimensional learning and classification step (S750) among the reduced ASVs can be repeated to select two columns and perform classification along two dimensions if there are remaining dimensions. For example, if 300 dimensions remain, the calculation (300*299) / 2 can be repeated 44,850 times.

[0072] The grouping step (S760) of related factors may be a step of grouping related factors among factors.

[0073] The step of generating a biomarker using factors (S770) may be a step of generating a biomarker after Group Lasso analysis using grouped factors.

[0074] The step of removing data related to a specific disease (S780) may be a step of removing data already identified as being related to a specific disease. Here, the data may be a type of bacteria.

[0075] Those skilled in the art will appreciate that the present disclosure can be easily modified into other specific forms based on the above description without changing the technical spirit or essential characteristics of the present disclosure. Therefore, it should be understood that the embodiments described above are illustrative in all respects and not restrictive. The scope of the present disclosure is indicated by the following claims, and all changes or modifications derived from the meaning and scope of the claims and their equivalents should be construed as being included in the scope of the present disclosure. The scope of the present application is indicated by the following claims rather than the above detailed description, and all changes or modifications derived from the meaning and scope of the claims and their equivalents should be construed as being included in the scope of the present application.

[0076] The form for carrying out the invention is substantially the same as the best form for carrying out the invention.

[0077] The present invention can be used in a technique for diagnosing a specific disease, and thus has industrial applicability.

Claims

1. In a biomarker generation method performed by a biomarker generation system, a) A step of preprocessing genetic data including information on the type and number of bacteria regarding specific genetic material information of normal people and patients with a specific disease to create a learning data set; b) a step of generating an artificial intelligence model trained to extract bacteria with a high correlation with the specific disease from the input genetic data based on the learning data set; and c) A method for generating a biomarker, comprising a step of generating a biomarker for the specific disease by grouping bacteria extracted by the artificial intelligence model based on information on the mutual relationships between bacteria extracted by the artificial intelligence model.

2. In paragraph 1, Relationship information is, A method for generating a biomarker, wherein the method generates a result of comparing information on bacteria included in the genetic data of the above normal person with information on bacteria extracted by the artificial intelligence model, and a result of comparing information on bacteria included in the genetic data of patients with the above specific disease with information on bacteria extracted by the artificial intelligence model.

3. In paragraph 1, In step a) above, A biomarker generation method for reducing the dimension of the number of bacteria in the above genetic data and selecting two columns from among the reduced bacteria.

4. In paragraph 1, A biomarker generation method, wherein, in step a), if there is specific disease data among the genetic data that is found to be associated with the specific disease, the specific disease data is removed, the dimension of the number of bacteria in the genetic data is reduced, and two columns are selected from among the reduced bacteria.

5. In paragraph 1, A biomarker generation method, wherein, in step a), the genetic data is preprocessed based on at least one of the Lasso technique, the Ridge technique, the Recursive Feature Elimination technique, and the Autoencoder technique.

6. In paragraph 1, In step b) above, A method for generating a biomarker, which obtains a list of data having a preset value or higher among the above genetic data.

7. In paragraph 1, A method for generating a biomarker, wherein the artificial intelligence model is at least one of logistic regression, KNN, and SVM.

8. In paragraph 1, A biomarker generation method, further comprising, prior to step a), a step of adding genetic data of the normal person and patients with the specific disease.

9. Communication module; at least one processor; and A memory electrically connected to the processor and storing at least one code to be executed by the processor, A biomarker generation system, wherein the memory stores a code that causes the processor, when executed through the processor, to preprocess genetic data including information on the type and number of bacteria regarding specific genetic material information of normal people and patients with a specific disease to generate a learning data set, generate an artificial intelligence model trained to extract bacteria highly related to the specific disease from the input genetic data based on the learning data set, and group bacteria extracted by the artificial intelligence model based on information on the mutual relationships between the bacteria extracted by the artificial intelligence model to generate a biomarker for the specific disease.

10. In paragraph 9, Relationship information is, A biomarker generation system generated by comparing the information on bacteria included in the genetic data of the above normal person with the information on bacteria extracted by the artificial intelligence model, and the information on bacteria included in the genetic data of patients with the above specific disease with the information on bacteria extracted by the artificial intelligence model.

11. In paragraph 9, The above memory causes the processor to: A biomarker generation system, wherein a code is stored that reduces the dimension of the number of bacteria in the genetic data and causes two columns to be selected from among the reduced bacteria.

12. In paragraph 9, The above memory causes the processor to: A biomarker generation system that, if specific disease data found to be associated with the specific disease exists among the genetic data, removes the specific disease data, reduces the dimension of the number of bacteria in the genetic data, and selects two columns from among the reduced bacteria.

13. In paragraph 9, The above memory causes the processor to: A biomarker generation system, wherein code is stored that causes the genetic data to be preprocessed based on at least one of the Lasso technique, the Ridge technique, the Recursive Feature Elimination technique, and the Autoencoder technique.

14. In paragraph 9, The above memory causes the processor to: A biomarker generation system, wherein a code is stored that causes a list of data having a preset value or higher among the above genetic data to be obtained.

15. In paragraph 9, A biomarker generation system, wherein the artificial intelligence model is at least one of logistic regression, KNN, and SVM.

Citation Information

Patent Citations

  • Case based cancer risk assessment algorithm

    KR1020100045227A

  • System and Method for managing fault data based on Comtrade

    KR1020240022321A

  • Quantum dot color filter structure and Display device having the same

    KR102534437B1

  • KR20200133067A

  • KR20210033347A