Apparatus and method for early disease detection based on high-depth cell-free nucleic acid sequencing

Abstract

The present invention relates to an apparatus for early disease detection based on high-depth cell-free nucleic acid sequencing, and may comprise: a library production unit for producing, on the basis of cell-free nucleic acids extracted from blood, a library set including a whole genome sequencing library, a whole epigenome sequencing library, a transcriptome sequencing library, and an epi-transcriptome sequencing library; a sequencing unit for generating high-depth cell-free nucleic acid sequencing data by sequencing the library set; a signal calculation unit which maps the high-depth cell-free nucleic acid sequencing data to a genome reference so as to specify the position, on the genome, of the high-depth cell-free nucleic acid sequencing data, and which calculates at least one disease-specific signal value on the basis of the mapped high-depth cell-free nucleic acid sequencing data; a prediction signal value generation unit for generating a disease prediction signal value by processing the at least one disease-specific signal value; and a prediction model generation unit for generating a disease prediction model, which detects whether a disease occurs and the type of disease for input blood, by using labeling information related to blood and the disease prediction signal value.

Description

Device and method for early disease detection based on high-depth cell-free nucleic acid sequencing

[0001] The present invention relates to a disease detection technology based on high-depth nucleic acid sequencing, and more particularly, to a technology capable of early detection of a disease based on high-depth sequencing of cell-free nucleic acids.

[0002] Even in modern times, with advanced medicine, the majority of human deaths are caused by disease. According to 2019 statistics, disease is responsible for 88% of all deaths worldwide. Specifically, non-communicable diseases account for 74%, infectious diseases account for 14%, and non-communicable diseases such as cancer and heart disease account for 51% of all deaths (https: / ourworldindata.org).

[0003] One of the main reasons for death from disease is the lack of early detection. For example, cancer, the leading cause of death worldwide, is diagnosed at an advanced stage, making treatment extremely difficult. Consequently, many patients die within two years. This high cancer mortality rate is not solely due to treatment issues; it is also closely linked to the lack of methods for early detection.

[0004] Early detection of disease has consistently been shown to significantly improve patient survival rates. According to a 2022 report by Cancer Research UK, survival rates differ significantly between those detected early and those detected late. While survival rates for lung cancer, colon cancer, and breast cancer are high at approximately 60%, 90%, and 100%, respectively, when detected early, they are significantly lower at approximately 10%, 10%, and 30%, respectively, when detected late. This is particularly true for cases like pancreatic cancer, where early symptoms are minimal or effective early detection methods are lacking, and cancer is often only detected at a late stage, often leading to death.

[0005] Early detection can vary depending on the type of disease, but it is quite challenging. Currently, successful early detection requires patients to voluntarily undergo comprehensive health screenings for various diseases (even when painless or mild). Even these screenings may not be successful. For example, in clinical practice, cancer is initially diagnosed through a medical history and physical examination. If suspicious findings are present, radiological and endoscopic examinations are performed. Finally, a biopsy is performed to confirm the diagnosis. However, clinical testing requires a significant number of cancer cells and a diameter exceeding a certain size. More than half of cancers of this size are detected in a metastatic state. Furthermore, current clinical cancer detection technologies are limited to specific cancer types, requiring multiple independent, cancer-specific tests, making cancer detection difficult and cumbersome. Only a small minority of patients with early-stage cancer, with minimal or no symptoms, proactively and voluntarily undergo these multiple, independent cancer screening tests.

[0006] The development of accessible and convenient disease detection tests, such as blood tests, could increase the frequency of voluntary disease screening, thereby increasing the sensitivity of early disease detection. Numerous previous studies suggest that analyzing cell-free nucleic acid sequencing data from blood can detect specific diseases. These attempts have been performed for several diseases, including cancers such as colon cancer, lung cancer, and breast cancer (Klein et al., 2022, Ann. Oncol.; Fairchild et al., 2023, Sci. Transl. Med.), rare diseases including Erdheim-Chester disease and Klippel-Trenaunay syndrome (Janku et al., 2014, Oncotarget; Palmieri et al., 2020, Vascular.), and immune diseases including systemic lupus erythematosus and rheumatoid arthritis (Truszewska et al., 2020, Lupus; Ding et al., 2022, Clin. Chem.; Zhou et al., 2023, PNAS; Plant et al. al., 2016, Arthritis Rheumatol.), chronic diseases including hypertension (Brusca et al., 2022, Circulation), cardiac diseases including chronic heart disease (Zemmour et al., 2018, Nat. Commun.), metabolic diseases including fatty liver disease and diabetes (Karlas et al., 2017, J. Transl. Med.; Lehmann-Werman et al., 2016, PNAS), infectious diseases including infectious pneumonia and invasive fungal infections (Langelier et al., 2020, Am. J. Respir. Crit.Car. Med.; Hong et al., 2018, Diagn. Microbiol. Infect. Dis.) exist.

[0007] Recently, attempts have been reported to extract disease markers from cell-free nucleic acid sequencing data in patient blood to detect diseases early. A recent cancer study (Klein et al., 2022, Ann. Oncol.) reported that panel sequencing of an epigenomic library of cell-free nucleic acids could detect stage 1 cancer with a sensitivity of approximately 17% at a specificity of 99.5%. However, this figure is significantly lower than the sensitivity of the same study for stage 3 and 4 cancer (approximately 70% at a specificity of 99.5%). Another study (Nicholson et al., 2023, Lancet) also reported a low detection rate of approximately 24% at a specificity of 98% for stage 1 cancer. These prior research findings demonstrate the potential for early disease detection, but also strongly suggest the need for the development of highly accurate early disease detection tests.

[0008] Meanwhile, research results for early disease detection using whole genome sequencing rather than panel sequencing have been recently reported, sequencing cell-free nucleic acids in blood at a low depth of 1 to 5 (Cristiano et al., 2019, Nature; Mouliere et al., 2019, Sci. Transl. Med.; Wan et al., 2022, Nat. Commun.; An et al., 2023, Nat. Commun.; Bruhm et al., 2023, Nat. Genet.; Budhraja et al., 2023, Sci. Transl. Med.). Depth refers to the average number of sequencing reads that have information on a specific location on the genome. The higher the depth, the more sequencing reads that have information on a specific location on the genome, which can increase the amount and accuracy of genomic information that can be obtained. This suggests that utilizing high-depth cell-free nucleic acid sequencing for disease detection could lead to more accurate, early disease detection than existing cell-free nucleic acid-based cancer detection methods. Therefore, there is a need for methods for early disease detection based on high-depth cell-free nucleic acid sequencing.

[0009] One embodiment of the present invention relates to a device and method for early detection of a disease based on high-depth cell-free nucleic acid sequencing, which can obtain high-depth cell-free nucleic acid sequencing data for cell-free nucleic acid extracted from blood.

[0010] One embodiment of the present invention relates to a device and method for early detection of a disease based on high-depth cell-free nucleic acid sequencing, which can detect a disease by calculating a disease-specific signal value based on high-depth cell-free nucleic acid sequencing data mapped to a genome reference.

[0011] One embodiment of the present invention relates to a device and method for early detection of a disease based on high-depth cell-free nucleic acid sequencing, which can detect whether a subject has a disease and the type of disease using only free nucleic acids extracted from the blood of the subject by using a disease prediction signal value obtained by high-depth sequencing of free nucleic acids extracted from the blood.

[0012] One embodiment of the present invention relates to a method for early detection of a disease using only free nucleic acids extracted from the blood of a subject by using a disease prediction signal value obtained by performing high-depth sequencing of free nucleic acids extracted from the blood.

[0013] A disease detection device based on high-depth cell-free nucleic acid sequencing according to one embodiment of the present invention may include: a library production unit for producing a library set including a whole-genome sequencing library, a whole-genome epigenome sequencing library, a transcriptome sequencing library, and a transcriptome epigenome sequencing library based on cell-free nucleic acids extracted from blood; a sequencing unit for generating high-depth cell-free nucleic acid sequencing data by sequencing the library set at a high depth of 10 or more; a signal production unit for mapping the high-depth cell-free nucleic acid sequencing data to a genome reference to specify a location of the high-depth cell-free nucleic acid sequencing data on a genome, and for generating at least one disease-specific signal value based on the mapped high-depth cell-free nucleic acid sequencing data; a prediction signal value production unit for processing the at least one disease-specific signal value and generating a disease prediction signal value; and a prediction model production unit for generating a disease prediction model for detecting whether a disease has occurred and the type of disease in input blood using labeling information related to the blood and the disease prediction signal value.

[0014] The blood can be extracted from a person without a disease, a person with a history of a specific disease but currently without the disease, a patient in the early, middle and late stages of a specific disease, and a patient with a relapse of a specific disease.

[0015] The signal generating unit can generate the disease-specific signal value based on one or more of a DNA signal value, a DNA modification signal value, an RNA signal value, and an RNA modification signal value.

[0016] The above prediction signal value generation unit can generate the disease prediction signal value by processing a plurality of disease-specific signal values ​​into vector data.

[0017] The above prediction signal value generation unit can generate the disease prediction signal value according to the type of target disease.

[0018] The above-described high-depth cell-free nucleic acid sequencing-based early disease detection device may further include an onset prediction unit that receives data of blood extracted from a subject and detects whether the subject has the disease and the type of disease through the disease prediction model.

[0019] The above sequencing unit may utilize two or more sequencers to sequence a library set.

[0020] A method for detecting a disease based on high-depth cell-free nucleic acid sequencing according to one embodiment of the present invention comprises the steps of: creating a library set including a whole-genome sequencing library, a whole-genome epigenome sequencing library, and a transcriptome sequencing library based on cell-free nucleic acid extracted from blood; sequencing the library set to generate high-depth cell-free nucleic acid sequencing data; mapping the high-depth cell-free nucleic acid sequencing data to a genome reference to specify a location of the high-depth cell-free nucleic acid sequencing data on a genome, and calculating at least one disease-specific signal value based on the mapped high-depth cell-free nucleic acid sequencing data; processing the at least one disease-specific signal value to generate a disease prediction signal value; generating a disease prediction model using labeling information related to the blood and the disease prediction signal value; and detecting whether or not a subject has a disease and the type of disease using the disease prediction model and data of blood extracted from the subject.

[0021] The disclosed technology may have the following effects. However, this does not mean that a particular embodiment must include all or only the following effects, and therefore the scope of the disclosed technology should not be construed as being limited thereby.

[0022] A disease detection device and method based on high-depth cell-free nucleic acid sequencing according to one embodiment of the present invention can obtain high-depth cell-free nucleic acid sequencing data for cell-free nucleic acid extracted from blood.

[0023] A disease detection device and method based on high-depth cell-free nucleic acid sequencing according to one embodiment of the present invention can detect a general disease at an early stage by calculating a disease-specific signal value based on high-depth cell-free nucleic acid sequencing data mapped to a genome reference.

[0024] A disease detection device and method based on high-depth cell-free nucleic acid sequencing according to one embodiment of the present invention can detect early onset of a disease in a subject using only cell-free nucleic acids contained in the blood of the subject by using a disease prediction signal value obtained by high-depth sequencing of cell-free nucleic acids extracted from blood.

[0025] A disease detection device and method based on high-depth cell-free nucleic acid sequencing according to one embodiment of the present invention can early distinguish the type of disease using only cell-free nucleic acids contained in the blood of a subject by using a disease prediction signal value obtained by high-depth sequencing of cell-free nucleic acids extracted from blood.

[0026] FIG. 1 is a diagram illustrating a disease early detection system based on high-depth cell-free nucleic acid sequencing according to one embodiment of the present invention.

[0027] FIG. 2 is a drawing for explaining the physical configuration of a disease early detection device based on high-depth cell-free nucleic acid sequencing according to one embodiment of the present invention.

[0028] FIG. 3 is a diagram illustrating the functional configuration of a disease early detection device based on high-depth cell-free nucleic acid sequencing according to one embodiment of the present invention.

[0029] Figure 4 is a diagram comparing high-depth whole genome sequencing and conventional whole genome sequencing.

[0030] FIG. 5 illustrates an example of cancer detection based on high-depth cell-free nucleic acid sequencing according to one embodiment of the present invention.

[0031] FIG. 6 is a diagram illustrating a method for classifying cancer patients based on cancer-specific signal values ​​according to one embodiment of the present invention.

[0032] FIG. 7 shows specific examples of disease-specific signal values ​​for generating disease prediction signal values ​​according to one embodiment of the present invention.

[0033] FIG. 8 is a diagram illustrating a disease prediction signal value according to one embodiment of the present invention.

[0034] FIG. 9 is a diagram illustrating the sequence of a disease early detection method based on high-depth cell-free nucleic acid sequencing according to one embodiment of the present invention.

[0035] The description of the present invention is merely an example for structural and functional explanation, and therefore, the scope of the present invention should not be construed as being limited by the embodiments described in the text. That is, since the embodiments can be modified in various ways and can take various forms, the scope of the present invention should be understood to include equivalents that can realize the technical idea. In addition, the purposes or effects presented in the present invention do not mean that a specific embodiment must include all of them or only such effects, and therefore, the scope of the present invention should not be construed as being limited thereby.

[0036] Meanwhile, the meaning of the terms described in this application should be understood as follows.

[0037] Terms such as "first" and "second" are intended to distinguish one component from another, and the scope of the rights should not be limited by these terms. For example, the first component may be referred to as the second component, and similarly, the second component may also be referred to as the first component.

[0038] When a component is said to be "connected" to another component, it should be understood that while it may be directly connected to that other component, there may also be other components intervening. Conversely, when a component is said to be "directly connected" to another component, it should be understood that there are no other intervening components. Similarly, other expressions describing relationships between components, such as "between" and "directly between," or "adjacent to" and "directly adjacent to," should be interpreted similarly.

[0039] Singular expressions should be understood to include plural expressions unless the context clearly indicates otherwise, and terms such as "comprises" or "have" should be understood to specify the presence of a feature, number, step, operation, component, part or combination thereof, but not to exclude the possibility of the presence or addition of one or more other features, numbers, steps, operations, components, parts or combinations thereof.

[0040] For each step, the identifiers (e.g., a, b, c, etc.) are used for convenience of explanation and do not describe the order of the steps. The steps may occur in a different order than stated unless the context clearly dictates a specific order. That is, the steps may occur in the same order as stated, may be performed substantially simultaneously, or may be performed in the opposite order.

[0041] The present invention can be implemented as computer-readable code on a computer-readable recording medium, and the computer-readable recording medium includes all types of recording devices that store data that can be read by a computer system. Examples of the computer-readable recording medium include ROM (Read Only Memory), RAM (Random Access Memory), CD-ROM, magnetic tape, floppy disk, optical data storage device, etc. In addition, the computer-readable recording medium can be distributed to computer systems connected to a network, so that the computer-readable code can be stored and executed in a distributed manner.

[0042] Unless otherwise defined, all terms used herein have the same meaning as commonly understood by those of ordinary skill in the art to which this invention pertains. Terms defined in commonly used dictionaries should be interpreted to be consistent with their meaning within the context of the relevant technology, and should not be interpreted as having an idealized or overly formal meaning unless explicitly defined herein.

[0043] FIG. 1 is a drawing illustrating a disease detection system (100) based on high-depth cell-free nucleic acid sequencing according to one embodiment of the present invention.

[0044] Referring to FIG. 1, a disease detection system (100) based on high-depth cell-free nucleic acid sequencing may include a user terminal (110), a disease detection device (130) based on high-depth cell-free nucleic acid sequencing, and a database (150).

[0045] The user terminal (110) may be implemented as a smart phone or a wearable device capable of checking the data generated based on the operations of generating a disease early detection device that creates a library set based on cell-free nucleic acids through a disease detection device (130) based on high-depth cell-free nucleic acid sequencing, generates high-depth cell-free nucleic acid sequencing data for the library set, generates disease-specific signal values ​​and disease prediction signal values ​​based on the mapped high-depth cell-free nucleic acid sequencing data, and generates a disease prediction model that predicts whether a disease occurs and the type of disease in the blood of the subject, and the data and metadata analyzed therefrom may be implemented as a device for analyzing the data, but is not necessarily limited thereto and may also be implemented as various devices such as a tablet PC. The user terminal (110) may be connected to the disease detection device (130) based on high-depth cell-free nucleic acid sequencing through a network, and a plurality of user terminals (110) may be simultaneously connected to the disease detection device (130) based on high-depth cell-free nucleic acid sequencing.

[0046] The disease detection device (130) based on deep cell-free nucleic acid sequencing can be implemented as a server corresponding to a computer or program that sequentially performs the operations of generating a disease early detection device. The disease detection device (130) based on deep cell-free nucleic acid sequencing can be wirelessly connected to a user terminal (110) via Bluetooth, WiFi, a communication network, etc., and can exchange data with the user terminal (110) via the network.

[0047] A disease detection device (130) based on high-depth cell-free nucleic acid sequencing can be provided by being included in a computer-readable recording medium by tangibly implementing a program of commands for implementing the same. In other words, the disease detection device (130) based on high-depth cell-free nucleic acid sequencing can be implemented in the form of program commands that can be executed through various computer means, and can be recorded in a computer-readable recording medium. In addition, the disease detection device (130) based on high-depth cell-free nucleic acid sequencing can be formed of a computer program that sequentially performs operations for generating a disease early detection device, and the computer program can be stored in a computer-readable recording medium.

[0048] The database (150) may correspond to a storage device that stores various pieces of information generated through the operations of generating a disease early detection device.

[0049] FIG. 2 is a drawing illustrating the physical configuration of a disease detection device (130) based on high-depth cell-free nucleic acid sequencing according to one embodiment.

[0050] Referring to FIG. 2, a disease detection device (130) based on high-depth cell-free nucleic acid sequencing can be implemented by including a processor (210), a memory (230), a user input / output unit (250), and a network input / output unit (270).

[0051] The processor (210) can execute a procedure for performing operations of generating a disease early detection device, manage a memory (230) that is read or written throughout the process, and schedule a synchronization time between volatile memory and non-volatile memory in the memory (230). The processor (210) can control the overall operation of the disease detection device (130) based on deep cell-free nucleic acid sequencing, and can be electrically connected to the memory (230), the user input / output unit (250), and the network input / output unit (270) to control data flow therebetween. The processor (210) can be implemented as a CPU (Central Processing Unit) or a GPU (Graphics Processing Unit) of the disease detection device (130) based on deep cell-free nucleic acid sequencing.

[0052] The memory (230) may include an auxiliary memory device implemented with a non-volatile memory such as an SSD (Solid State Drive) or an HDD (Hard Disk Drive) and used to store all data required for a disease detection device (130) based on high-depth cell-free nucleic acid sequencing, and may include a main memory device implemented with a volatile memory such as RAM.

[0053] The user input / output unit (250) may include an environment for receiving user input and an environment for outputting specific information to the user. For example, the user input / output unit (250) may include an input device including an adapter such as a touchpad, a touch screen, a virtual keyboard, or a pointing device, and an output device including an adapter such as a monitor or a touch screen. In one embodiment, the user input / output unit (250) may correspond to a computing device accessed via remote access, in which case the disease detection device (130) based on deep cell-free nucleic acid sequencing may be implemented as a server.

[0054] The network input / output unit (270) includes an environment for connecting to an external device or system via a network, and may include an adapter for communication such as a local area network (LAN), a metropolitan area network (MAN), a wide area network (WAN), and a value added network (VAN).

[0055] FIG. 3 is a diagram for explaining the functional configuration of a disease detection device (130) based on high-depth cell-free nucleic acid sequencing according to one embodiment of the present invention. Referring to FIG. 3, the disease detection device (130) based on high-depth cell-free nucleic acid sequencing may include a library production unit (310), a sequencing unit (320), a signal generation unit (330), a prediction signal value generation unit (340), a prediction model generation unit (350), and an onset prediction unit (360).

[0056] The library production unit (310) can produce a set of libraries including a whole genome sequencing library, a whole epigenome sequencing library, a transcriptome sequencing library, and an epitranscriptome sequencing library based on cell-free nucleic acids extracted from blood.

[0057] Here, cell-free nucleic acids can be extracted from plasma separated from blood. Cell-free nucleic acids may include cell-free DNA and cell-free RNA, and cell-free DNA and cell-free RNA may include exosomal DNA and exosomal RNA, respectively. For example, cell-free nucleic acids can be extracted using a Circulating Nucleic Acid Kit.

[0058] Blood samples can be collected from individuals without disease, individuals with a history of a specific disease but who are currently disease-free, individuals in the early, middle, and late stages of a specific disease, and individuals experiencing a relapse. Beyond distinguishing between individuals with and without a disease, blood characteristics can vary depending on the stage of the disease and the presence or absence of treatment.

[0059] The library production unit (310) can produce a library set for cell-free nucleic acids extracted from blood through an adapter ligation step and a library quantification and size confirmation step using a library production kit. In addition, the library production unit (310) can produce a whole genome bisulfite sequencing library as one method of producing a whole-length epigenome sequencing library based on cell-free nucleic acids. For example, the library production unit (310) can produce a library set using the EpiNext High-Sensitivity DNA Library Preparation Kit, the EZ DNA Methylation-Lightning MagPrep Kit, or the EpiNext Post-Bisulfite DNA Library Preparation Kit. In addition, the library production unit (310) can produce a transcriptome bisulfite sequencing library as one method of producing a whole-length epigenome sequencing library based on cell-free nucleic acids. For example, the library production unit (310) can produce a library set using the AMPINEXT 5-mC RNA Bisulfite-Seq Easy Kit or the EpiNext RNA Bisulfite-Seq Kit.

[0060] Figure 4 is a diagram comparing high-depth whole genome sequencing and conventional whole genome sequencing.

[0061] Referring to FIG. 4, the sequencing unit (320) can generate high-depth genome sequencing data by sequencing a set of libraries. The sequencing unit (320) can generate high-depth genome sequencing data with a higher depth than general genome sequencing for the entire genome region. Compared to panel sequencing that sequences only a specific region of the genome, the sequencing unit (320) can generate sequencing data by sequencing the entire genome region at a high depth. Through this, the disease detection device (130) based on high-depth cell-free nucleic acid sequencing according to the present invention can detect a disease with high accuracy based on high-depth sequencing data for the entire genome region.

[0062] In one embodiment, the sequencing unit (320) can sequence a library set at a high depth of 10 or greater. Here, the depth refers to the average number of sequencing reads having specific location information on the genome. As the depth increases, the number of sequencing reads having specific location information on the genome increases, thereby increasing the amount and accuracy of genomic information that can be obtained.

[0063] Figure 5 illustrates the results of whole-genome sequencing of cell-free nucleic acids in blood at various sequencing depths, extracting cancer-specific signals, and then predicting cancer. The present invention can be applied not only to cancer, as shown in the example of Figure 5, but also to other diseases.

[0064] Figure 5a shows the prediction result when a cancer prediction signal value is generated using a DNA signal value.

[0065] The dataset used for training included data from 18 cancer patients and 18 healthy individuals, while the dataset used to evaluate the learning results included data from 8 cancer patients and 8 healthy individuals. The predicted cancer was colon cancer.

[0066] As a result of the experiment, it can be confirmed that when using whole genome sequencing data with a high depth of 10 or more of cell-free nucleic acid in blood according to the present invention, that is, when using sequencing data with depths of 10, 30, and 50, the cancer prediction signal scores of cancer patients and healthy people are more clearly distinguished, and when using low-depth whole genome sequencing data with a depth of less than 10, the boundary between the cancer prediction signal scores of cancer patients and healthy people is unclear.

[0067] Figure 5b shows the prediction result when a cancer prediction signal value is generated by additionally using a DNA mutation signal value in addition to a DNA signal value.

[0068] When tested for colon cancer under the same conditions as in Fig. 5a, it was confirmed that the cancer prediction signal scores of cancer patients and healthy people were more clearly distinguished when whole-genome sequencing of cell-free nucleic acids in blood was performed at a high depth of 10 or more, as when only DNA signal values ​​were used.

[0069] In one embodiment, the sequencing unit (320) may utilize one or more types of sequencers to sequence the library set. Examples of sequencers that may be utilized include sequencers from Illumina, MGI, Element Biosciences, Ultima Genomics, PacBio, Oxford Nanopore, etc. In addition, various sequencers may be utilized without being limited by the length of the sequencing read or the sequencing technology (e.g., chain termination, ligation, fluorescence, single / paired-end, etc.).

[0070] The signal generation unit (330) can map the high-depth cell-free nucleic acid sequencing data to a genome reference to specify the location of the sequencing read on the genome. More specifically, the signal generation unit (330) can map the high-depth cell-free nucleic acid sequencing data to a suitable genome reference so that the generated high-depth cell-free nucleic acid sequencing data can be analyzed by specifying the location on the genome. In other words, the signal generation unit (330) can specify the location so that the generated high-depth cell-free nucleic acid sequencing data can be analyzed.

[0071] In one embodiment, the signal generation unit (330) can map high-depth cell-free nucleic acid sequencing data to a reference genome. The high-depth cell-free nucleic acid sequencing data mapped to the genome reference can be stored as a file such as a Sequence Alignment Map (SAM), a Binary Alignment Map (BAM), or a Compressed Reference-oriented Alignment Map (CRAM). The genome reference to which the high-depth cell-free nucleic acid sequencing data is mapped is not limited to a human genome reference. In order to detect an infectious disease, the degree of presence of the genome sequence of an infectious agent can be confirmed by mapping to a genome reference of a non-human species (such as a virus, bacteria, or fungus). For example, in order to detect bacterial infectious pneumonia, the high-depth cell-free nucleic acid sequencing data can be mapped to the pneumococcus reference genome data.

[0072] The signal generation unit (330) can generate at least one disease-specific signal value based on mapped high-depth cell-free nucleic acid sequencing data. The signal generation unit (330) can analyze the high-depth cell-free nucleic acid sequencing data to generate a disease-specific signal value associated with the occurrence of the disease. More specifically, the disease-specific signal value may exhibit similar or different patterns depending on the type of disease.

[0073] FIG. 6 is a diagram illustrating a method for classifying a subject based on a disease-specific signal value according to one embodiment of the present invention.

[0074] For example, in Fig. 6a, one of the disease-specific signal values, the DNA modification signal value (using the degree of methylation modification by location), may be associated with colon cancer, and healthy people and cancer patients may be distinguished based on a specific cancer detection cut-off value.

[0075] For another example, in Fig. 6b, one of the cancer-specific signal values, the DNA signal value (using a set of base sequences around the mutation location), may be associated with pancreatic cancer, and healthy people and cancer patients may be distinguished based on a specific cancer detection threshold.

[0076] As another example, in Fig. 6c, the DNA signal value (distribution of fragment length), which is one of the cancer-specific signal values, may be associated with testicular cancer, liver cancer, bladder cancer, breast cancer, and prostate cancer, and healthy people and cancer patients may be distinguished based on a specific cancer detection threshold value.

[0077] The signal generation unit (330) can generate disease-specific signal values ​​that can distinguish between healthy individuals and diseased patients for a specific disease, and, as described below, can generate disease prediction signal values ​​by combining one or more disease-specific signal values, and can detect various types of diseases using the disease prediction signal values. This will be described in detail below.

[0078] In one embodiment, the signal generation unit (330) can generate a disease-specific signal value based on a DNA signal value, a DNA modification signal value, an RNA signal value, and an RNA modification signal value.

[0079] Figure 7 shows examples of data for producing these disease-specific signal values.

[0080] The signal generation unit (330) can generate a DNA signal value using high-depth whole-length cell-free nucleic acid sequencing data sequenced from a whole-length genome sequencing library.

[0081] The DNA signal value may include one or more of the amount of cell-free DNA extracted from blood, a set of base sequences at and around a mutation location, a gene copy number variation, a disease-specific mutation, a genome sequence of a detected pathogen, a distribution of fragment lengths, sequence information around fragment ends, an individual disease-specific nucleosome distribution obtained from position information at fragment ends, and a proportion of jagged ends.

[0082] In more detail, the signal generation unit (330) filters out previously known single nucleotide polymorphism (SNP) positions or filters out low-quality mutation positions by considering base quality, mapping quality, and depth on the sequencing read. A set of base sequences at the mutation position after filtering, a set of base sequences around the mutation position (for example, 2X+1 consecutive bases from -X nt to +X nt of the mutation position), a set of sequencing read information at and around the mutation position, a correlation coefficient level comparing the sets of base sequences at the mutation position with a well-known disease-specific mutation reference (for example, the mutational signature of COSMIC for cancer), and the presence or absence of a disease-specific associated mutation can be utilized to generate a DNA signal value. Previous studies have observed significant differences in mutation locations and surrounding base sequence sets between patients and non-patients in diseases such as cancer and clonal hematopoiesis (Bruhm et al., 2023, Nat. Genet.; Fairchild et al., 2023, Sci. Transl. Med.). These mutations include structural variations such as single base substitutions, doublet base substitutions, small and large insertions and deletions, tandem duplications, inversions, fusions, translocations, chromoplexy, and chromothripsis.In the case of structural mutations, the breakpoint position, which is a discontinuous point in the genome that the sequencing read has, and the set of base sequences around that position can be used as DNA signal values.

[0083] The signal generation unit (330) can utilize pathogen genome sequences detected from high-depth whole-cell free nucleic acid sequencing data to generate DNA signal values. Pathogens may include pathogenic DNA viruses, bacteria, fungi, etc. that can cause infectious diseases.

[0084] The signal generation unit (330) can utilize the degree of gene copy number alteration and the degree of chromosomal aneuploidy detected from high-depth whole-cell free nucleic acid sequencing data to generate a DNA signal value.

[0085] The signal generation unit (330) can utilize fragment information obtained from high-depth cell-free nucleic acid sequencing data to generate a DNA signal value.

[0086] More specifically, the distribution of fragment lengths, the set of sequence information of Y consecutive bases around the fragment ends, and the individual disease-specific nucleosome distribution obtained from the location information of the fragment ends on the genome can be utilized to generate DNA signal values. Previous studies have observed significant differences in fragment signals between patients and non-patients in diseases such as cancer, systemic lupus erythematosus, and fatty liver (Cristiano et al., 2019, Nature; Ding et al., 2022, Clin. Chem.; Zhou et al., 2023, PNAS; Karlas et al., 2017, J. Transl. Med.).

[0087] The signal generation unit (330) can utilize the amount of cell-free DNA extracted from blood in the library production unit (310) to generate a DNA signal value.

[0088] More specifically, the amount of cell-free DNA can be determined using methods such as electrophoresis or absorbance measurement of fluorescently labeled cell-free nucleic acids. For example, the amount of cell-free DNA can be determined using the Agilent 2100 Bioanalyzer or the Invitrogen Qubit 4.0 fluorometer. Previous studies have observed significant differences in the amount of cell-free DNA between patients and non-patients in diseases such as cancer, systemic lupus erythematosus, rheumatoid arthritis, hypertension, and heart disease (Chen et al., 2021, Sci. Rep.; Truszewska et al., 2020, Lupus; Hashimoto et al., 2016, Int. J. Rheum.; Jeong et al., 2015, Kidney. Res. Clin. Pract.; Antonatos et al., 2006, Ann. NY Acad. Sci.).

[0089] DNA modification signal values ​​are 1mA, 1mHyp, 3mA, 3mHyp, 4mA, 6mA, 7mA, 7mHyp, 9mA, 9mHyp, 6hmA, m2A, ncm6A, xI, m2C, e3C, 3mC, εC, 4mC, 5caC, 5fC, 5hmC, 5mC, 1mG, 2mG, 3mG, m6G, 7mG, CEG, M22G, N(2),3-εG, 1,N(2)-εG, ADG, 8oxoG, dU, dhpdU, 5-NedU, DHdU, 5-NeOmdU, 5caU, dhpUra, 5hmU, 5fU, base J, diHT, 1mT; It may include one or more of the position-specific modification degrees of DNA chemical modifications including 3mT, 4-meT, and putThy.

[0090] The signal generation unit (330) can generate a DNA modification signal value using high-depth whole-genome sequencing data sequenced from a sequencing library specifically designed to detect specific chemical modifications of DNA (e.g., including 5mC, 5hmC, 6mA, etc.), or high-depth whole-genome sequencing data based on a specific sequencer (e.g., Oxford Nanopore's sequencer) that can directly read DNA modification information from the whole-genome sequencing library.

[0091] For example, to detect 5mC, a type of DNA methylation modification, a whole-genome bisulfite sequencing library can be constructed and high-depth cell-free nucleic acid sequencing data can be used by sequencing it with an Illumina sequencer, or a whole-genome sequencing library can be sequenced with an Oxford Nanopore sequencer and high-depth cell-free nucleic acid sequencing data can be used.

[0092] In more detail, the signal generation unit (330) obtains DNA chemical modification sites and sites where DNA chemical modification does not occur from high-depth whole-genome sequencing data or a whole-genome sequencing library based on a specific sequencer, and filters out previously known single nucleotide polymorphism sites or removes inappropriate DNA modification sites by considering base quality, mapping quality, depth, etc. on the sequencing read. After that, the DNA chemical modification signals of disease patients and normal people are compared to select a DNA chemical modification region (differentially modified region, DMR) with a significantly different pattern in the disease patient, and the degree of DNA chemical modification at the corresponding site can be calculated as a DNA modification signal value. In addition, the signal generation unit (330) can reflect the degree of DNA chemical modification at the corresponding site, sequencing read information, etc., in the DNA modification signal value. Previous studies have observed significant differences in methylation signals between patients and non-patients in diseases such as cancer, systemic lupus erythematosus, rheumatoid arthritis, hypertension, heart disease, and fatty liver (Shen et al., 2018, Nature; Wang et al., 2022, Front. Immunol.; Plant et al., 2016, Arthritis Rheumatol.; Brusca et al., 2022, Circulation; Zemmour et al., 2018, Nat. Commun.; Yigit et al., 2018, Gut).

[0093] The signal generation unit (330) can generate an RNA signal value using high-depth transcriptome sequencing data sequenced from a transcriptome sequencing library.

[0094] The above RNA signal value may include one or more of the expression level of an individual disease-specific gene, the expression level of a fusion gene, and the degree of alternative splicing.

[0095] More specifically, the signal generation unit (330) can calculate an RNA signal value by removing low-quality sequencing reads by considering base quality, mapping quality, and depth on the sequencing reads, and checking whether there are enough sequencing reads that can support the expression of genes known to cause diseases. In addition, the signal generation unit (330) can utilize the gene expression level of a disease-specific gene, the expression level of a fusion gene, the type of expressed fusion gene, and the level of alternative splicing to calculate the RNA signal value. Alternative splicing may include one or more of intron retention, exon skipping, alternative 5' splicing, alternative 3' splicing, mutually exclusive splicing, alternative transcription initiation, and alternative polyadenylation. Previous studies have observed significant differences in the expression levels of disease-specific genes and fusion genes and the degree of alternative splicing between patients and non-patients in diseases such as cancer (Larson et al., 2021, Nat. Commun.; Hasegawa et al., 2021, Cancer Sci.; Zhu et al., 2021, Theranostics.).

[0096] RNA modification signal values ​​are ms2m6A, io6A, m6t6A, hn6A, Ar(p), m1I, m1Am, m1Im, m2A, m62A, ms2i6A, ms2t6A, i6A, ms2hn6A, m6Am, m1A, m6A, I, g6A, m62Am, ac6A, ms2io6A, Am, im, t6A, m8A, m2,8A, ct6A, hm6A, f6A, ms2ct6A, ht6A, msms2i6A, m5Cm, m4C, m42C, m5C, f5C, m4Cm, m3C, m42Cm, ac4C, Cm, s2C, k2C, f5Cm, ac4Cm, hm5C, C+, ho5C, hm5Cm, m2,7G, oQ, m22G, m1G, Gm, yW, Gr(p), m2G, m22Gm, gluQ, mimG, preQ1base, m1Gm, Q, yW-86, yW-72, galQ, imG2, manQ, OHyW, G+, m2Gm, imG-14, m227G, yW-58, m7G, preQ0, o2yW, preQ1, imG, m2,7Gm, f5U, m5s2U, s4U, m1acp3Y, cm5s2U, m5U, D, m5D, tm5U, cmnm5Um, f5Um, mcm5U, ncm5Um, nm5s2U, ncm5U, cm5U, cmnm5s2U, cmo5U, m3Y, m3U, Um, acp3Um, cmnm5se2U, m3Um, mcmo5U, nm5se2U, ho5U, f5s2U, mcm5s2U, chm5U, mo5U, acp3U, mnm5se2U, mcm5Um, mchm5U, cmnm5U, m1Y, tm5s2U, se2U, s2U, Ym, f5se2U, mnm5s2U, nm5U, s2Um, Y, m5Um, mnm5U, acp3D, acp3Y, inm5U, inm5Um, inm5s2U, ncm5s2U, nchm5U, mchm5Um, ges2U, cmnm5ges2U, mnm5ges2U, Contains nm5ges2U, cnm5U, mcmo5Um It may include one or more of the site-specific modification degrees of RNA chemical modification.

[0097] The signal generation unit (330) is a specific chemical modification of RNA (e.g., m 6 A, m 5 C, Ψ, I, ac 4 C, Nm, m 6 Am, m 1 A, m 7 G, hm 5 RNA modification signal values ​​can be calculated using high-depth transcriptome sequencing data sequenced from a sequencing library specifically designed to detect C, etc., or high-depth transcriptome sequencing data based on a specific sequencer (e.g., Oxford Nanopore's sequencer) that can directly read RNA chemical modification information from a transcriptome genome sequencing library.

[0098] For example, m, a type of RNA methylation modification 5 For C detection, high-depth cell-free nucleic acid sequencing data can be utilized by constructing a transcriptome bisulfite sequencing library and sequencing it with an Illumina sequencer, or high-depth cell-free nucleic acid sequencing data can be utilized by sequencing a whole-genome sequencing library with an Oxford Nanopore sequencer.

[0099] In more detail, the signal generation unit (330) obtains RNA chemical modification sites and sites where RNA chemical modification does not occur from high-depth epigenetic transcriptome sequencing data or a specific sequencer-based transcriptome sequencing library, and filters out previously known single nucleotide polymorphism (SNP) sites or removes inappropriate RNA modification sites by considering base quality, mapping quality, depth, etc. on the sequencing read. After that, the RNA chemical modification signals of disease patients and normal people are compared to select RNA chemical modification sites where the patterns are significantly different in disease patients, and the degree of RNA chemical modification at the corresponding site can be calculated as an RNA signal value. In addition, the signal generation unit (330) can reflect the degree of RNA chemical modification at the corresponding site, sequencing read information, etc., to the RNA signal value.

[0100] FIG. 8 is a diagram illustrating a disease prediction signal value according to one embodiment of the present invention.

[0101] Referring to FIG. 8, the prediction signal value generation unit (340) can generate a disease prediction signal value by processing at least one disease-specific signal value. The prediction signal value generation unit (340) can generate a disease prediction signal value by processing the disease-specific signal value through standardization, one-hot encoding, low-quality data filtering, random selection of some, or selection of some according to specific criteria. For example, the prediction signal value generation unit (340) can generate a disease prediction signal value according to the type of target disease by processing a DNA signal value and a DNA modification signal value.

[0102] In one embodiment, the prediction signal value generation unit (340) may process multiple disease prediction signal values ​​into vector data to generate a disease prediction signal value. For example, the prediction signal value generation unit (340) may express multiple disease prediction signal values ​​a, b, c, and d as vector values ​​by specifying their respective positions. More specifically, the prediction signal value generation unit (340) may select and process specific disease-specific signal values ​​according to the type of target disease to generate a disease prediction signal value.

[0103] In one embodiment, the prediction signal value generation unit (340) can generate a disease prediction signal value depending on the type of target disease. As described above, the prediction signal value generation unit (340) can select a disease-specific signal value to be used depending on the type of target disease, and process the selected disease-specific signal value to generate a disease prediction signal value.

[0104] In the example of Fig. 8a, the prediction signal value generation unit (340) can generate a disease prediction signal value by combining a DNA signal value, a DNA modification signal value, an RNA signal value, and an RNA modification signal value for a disease called A.

[0105] In the example of FIG. 8b, the prediction signal value generation unit (340) can generate a cancer prediction signal value by combining the DNA signal value and the DNA modification signal value calculated for colon cancer, and can generate a cancer prediction signal value by combining the DNA modification signal value and the RNA signal value calculated for pancreatic cancer.

[0106] More specifically, each disease-specific signal value produced may be different depending on the type of target disease, and accordingly, the prediction signal value generation unit (360) can process the disease-specific signal value to generate a disease prediction signal value depending on the type of target disease. Accordingly, the prediction signal value generation unit (340) can detect various types of diseases by various combinations of DNA signal values, DNA modification signal values, RNA signal values, and RNA modification signal values.

[0107] The prediction model generation unit (350) can generate a disease prediction model that detects whether a disease occurs in the input blood using blood-related labeling information and disease prediction signal values.

[0108] More specifically, the prediction model generation unit (350) can create a disease prediction model through learning using labeling information related to blood and disease prediction signal values ​​generated through the blood. Here, creation through learning means that an artificial intelligence model is learned using a plurality of learning data by a learning algorithm, thereby creating a predefined operation rule or artificial intelligence model set to perform a desired characteristic (or purpose). This learning may be performed in the device itself on which the artificial intelligence according to the present disclosure is performed, or may be performed through a separate server and / or system. Examples of learning algorithms include, but are not limited to, supervised learning, unsupervised learning, semi-supervised learning, or reinforcement learning.

[0109] An AI model can be composed of multiple neural network layers. Each of the multiple neural network layers has multiple weight values ​​and performs neural network operations by calculating the results of previous layers and the multiple weights. The multiple weights of the multiple neural network layers can be optimized based on the learning results of the AI ​​model. For example, the multiple weights can be updated during the learning process to reduce or minimize the loss or cost values ​​obtained from the AI ​​model.

[0110] The artificial neural network may include a deep neural network (DNN), such as a convolutional neural network (CNN), a deep neural network (DNN), a recurrent neural network (RNN), a restricted boltzmann machine (RBM), a deep belief network (DBN), a bidirectional recurrent deep neural network (BRDNN), or deep Q-networks (DQN), but is not limited to the above examples. For example, learning algorithms such as linear discriminant analysis (LIA), logistic regression, probit regression, naive bayes, bayesian network, partial least squares, k-nearest neighbor, genetic programming, decision trees, random forests, and support vector machines may also be included.

[0111] Meanwhile, the artificial intelligence model used in the disclosed embodiments may be implemented in various embodiments depending on the manufacturer of the electronic device or the user of the electronic device, and is not limited by the examples above.

[0112] The disease prediction unit (360) can receive blood data extracted from a subject and detect whether the subject has developed a disease through a disease detection model. For example, by inputting high-depth cell-free nucleic acid sequencing data generated based on cell-free nucleic acid extracted from the blood of a specific subject into the disease detection model generated through the prediction signal value generation unit (340), the presence or absence of a disease in the subject can be detected.

[0113] Meanwhile, the blood of the subject to be tested for disease onset in the disease onset prediction unit (360) should not be used in the disease detection model generated by the prediction signal value generation unit (340), in order to prevent overfitting of the disease detection model.

[0114] For example, a library set can be created through a library creation unit (310) using cell-free nucleic acids extracted from the blood of a subject, the library set can be sequenced through a sequencing unit (320), high-depth cell-free nucleic acid data can be mapped to a genome reference through a signal generation unit (330), and a disease prediction signal value can be created from the mapped sequencing data through a prediction signal value generation unit (340). In addition, whether a subject has developed a disease and the type of disease can be predicted through the disease prediction signal value created through the onset prediction unit (360) and the pre-generated disease prediction model.

[0115] FIG. 9 is a diagram illustrating the sequence of a disease detection method based on high-depth cell-free nucleic acid sequencing according to one embodiment of the present invention.

[0116] Figure 9a is a schematic flowchart of a method for generating a disease prediction model based on high-depth cell-free nucleic acid sequencing.

[0117] Referring to FIG. 9a, a disease detection method based on high-depth cell-free nucleic acid sequencing can produce a library set including a whole-genome sequencing library, a whole-genome sequencing library, and a transcriptome sequencing library based on cell-free nucleic acids extracted from blood through a library production unit (310) (S110).

[0118] A disease detection method based on high-depth cell-free nucleic acid sequencing can generate high-depth cell-free nucleic acid sequencing data by sequencing a library set through a sequencing unit (320) (S120).

[0119] A disease detection method based on high-depth cell-free nucleic acid sequencing can map high-depth cell-free nucleic acid sequencing data to a genome reference through a signal generation unit (330), specify the location of the high-depth cell-free nucleic acid sequencing data on the genome, and generate at least one disease-specific signal value based on the mapped high-depth cell-free nucleic acid sequencing data (S130).

[0120] A disease detection method based on high-depth cell-free nucleic acid sequencing can generate a disease prediction signal value by processing at least one disease-specific signal value through a prediction signal value generation unit (340) (S140).

[0121] Referring to FIG. 9a, a disease detection method based on high-depth cell-free nucleic acid sequencing can generate a disease prediction model that detects whether a disease occurs and the type of disease in the input blood by using labeling information related to blood and a disease prediction signal value through a prediction model generation unit (350) (S150).

[0122] Figure 9b is a schematic flowchart of a method for predicting a disease using a disease prediction model generated based on high-depth cell-free nucleic acid sequencing.

[0123] Referring to FIG. 9b, a disease detection method based on high-depth cell-free nucleic acid sequencing can detect whether a disease has occurred and the type of disease in the input blood by using labeling information related to blood, a disease prediction signal value, and a parasitic disease prediction model through an onset prediction unit (360) (S250).

[0124] Although the present invention has been described above with reference to preferred embodiments thereof, it will be understood by those skilled in the art that various modifications and changes may be made to the present invention without departing from the spirit and scope of the present invention as set forth in the claims below.

[0125]

[0126] [Explanation of symbols]

[0127] 100: Disease detection system based on high-depth cell-free nucleic acid sequencing

[0128] 110: User terminal

[0129] 130: Disease detection device based on high-depth cell-free nucleic acid sequencing

[0130] 150: Database

[0131] 210: Processor 230: Memory

[0132] 250: User input / output section 270: Network input / output section

[0133] 310: Library Production Department

[0134] 320: Sequencing Department

[0135] 330: Signal generation unit 340: Prediction signal value generation unit

[0136] 350: Prediction Model Generation Unit 360: Outbreak Prediction Unit

Claims

1. A library production unit that produces a set of libraries including a whole-genome sequencing library, a whole-genome sequencing library, and a transcriptome sequencing library based on cell-free nucleic acids extracted from blood; A sequencing unit that sequences the above library set at a high depth of 10 or more to generate high-depth cell-free nucleic acid sequencing data; A signal generation unit that maps the high-depth cell-free nucleic acid sequencing data to a genome reference to specify a location of the high-depth cell-free nucleic acid sequencing data on the genome, and generates at least one disease-specific signal value based on the mapped high-depth cell-free nucleic acid sequencing data; A prediction signal value generation unit that processes at least one disease-specific signal value to generate a disease prediction signal value; and A prediction model generation unit that generates a disease prediction model that detects whether a disease occurs and the type of disease in the input blood using the labeling information related to the blood and the disease prediction signal value; A disease early detection device based on high-depth cell-free nucleic acid sequencing including .

2. In paragraph 1, A device for early detection of a disease based on high-depth cell-free nucleic acid sequencing, characterized in that the blood is extracted from a person without a disease, a person with a history of a specific disease but currently without the disease, a patient in the early, middle and late stages of a specific disease, and a patient with a relapse of a specific disease.

3. In paragraph 1, The above signal generating unit, A disease early detection device based on high-depth cell-free nucleic acid sequencing, characterized in that the disease-specific signal value is calculated based on at least one of a DNA signal value, a DNA modification signal value, an RNA signal value, and an RNA modification signal value.

4. In paragraph 1, The above predicted signal value generation unit, A disease early detection device based on high-depth cell-free nucleic acid sequencing, characterized in that it processes multiple disease-specific signal values ​​into vector data and generates the disease prediction signal value.

5. In paragraph 1, The above predicted signal value generation unit, A disease early detection device based on high-depth cell-free nucleic acid sequencing, characterized in that it generates the disease prediction signal value according to the type of target disease.

6. In paragraph 1, An outbreak prediction unit that receives blood data extracted from a subject and detects whether the subject has the disease and the type of disease through the disease prediction model; A disease early detection device based on high-depth cell-free nucleic acid sequencing, characterized by further including:

7. In paragraph 3, A disease early detection device based on high-depth cell-free nucleic acid sequencing, characterized in that the DNA signal value includes at least one of the amount of cell-free DNA extracted from blood, a set of base sequences at and around a mutation location, a gene copy number variation, a chromosomal aneuploidy, a disease-specific mutation, a genome sequence of a detected pathogen, a distribution of fragment lengths, sequence information around fragment ends, an individual disease-specific nucleosome distribution obtained from position information at fragment ends, and a ratio of jagged ends.

8. In paragraph 3, The DNA modification signal values ​​are 1mA, 1mHyp, 3mA, 3mHyp, 4mA, 6mA, 7mA, 7mHyp, 9mA, 9mHyp, 6hmA, m2A, ncm6A, xI, m2C, e3C, 3mC, εC, 4mC, 5caC, 5fC, 5hmC, 5mC, 1mG, 2mG, 3mG, m6G, 7mG, CEG, M22G, N(2),3-εG, 1,N(2)-εG, ADG, 8oxoG, dU, dhpdU, 5-NedU, DHdU, 5-NeOmdU, 5caU, dhpUra, 5hmU, 5fU, base J, diHT, A disease early detection device based on high-depth cell-free nucleic acid sequencing, characterized in that it comprises one or more position-specific modification degrees of 1mT, 3mT, 4-meT and putThy.

9. In paragraph 3, A disease early detection device based on high-depth cell-free nucleic acid sequencing, characterized in that the above RNA signal value includes at least one of the expression level of an individual disease-specific gene, the expression level of a fusion gene, and the degree of alternative splicing.

10. In paragraph 3, 상기 RNA I, g6A, m62Am, ac6A, ms2io6A, Am, Im, t6A, m8A, m2,8A, ct6A, hm6A, f6A, ms2ct6A, ht6A, msms2i6A, m5Cm, m4C, m42C, m5C, f5C, m4Cm, m3C, m42Cm, ac4C, Cm,s2C, k2C, f5Cm, ac4Cm, hm5C, C+, ho5C, hm5Cm, m2,7G, oQ, m22G, m1G, Gm, yW, Gr(p), m2G, m22Gm, gluQ, mimG, preQ1base, m1Gm, Q, yW-86, yW-72, galQ, imG2, manQ, OHyW, G+, m2Gm, imG-14, m227G, yW-58, m7G, preQ0, o2yW, preQ1, imG, m2,7Gm, f5U, m5s2U, s4U, m1acp3Y, cm5s2U, m5U, D, m5D, tm5U, cmnm5Um, f5Um, mcm5U, ncm5Um, nm5s2U, ncm5U, cm5U, cmnm5s2U, cmo5U, m3Y, m3U, Um, acp3Um, cmnm5se2U, m3Um, mcmo5U, nm5se2U, ho5U, f5s2U, mcm5s2U, chm5U, mo5U, acp3U, mnm5se2U, mcm5Um, mchm5U, cmnm5U, m1Y, tm5s2U, se2U, s2U, Ym, f5se2U, mnm5s2U, nm5U, s2U, Y, m5Um, mnm5U, acp3D, acp3Y, inm5U, inm5Um, inm5s2U, ncm5s2U, nchm5U, mchm5Um, ges2U, cmnm5ges2U, mnm5ges2U, nm5ges2U,A disease early detection device based on high-depth cell-free nucleic acid sequencing, characterized in that it includes a position-specific degree of modification of one or more of cnm5U and mcmo5Um.

11. In paragraph 1, A disease early detection device based on high-depth cell-free nucleic acid sequencing, characterized in that the above sequencing unit utilizes two or more sequencers to sequence a library set.

12. A step of producing a set of libraries including a whole-genome sequencing library, a whole-genome sequencing library, a transcriptome sequencing library, and an epigenetic transcriptome sequencing library based on cell-free nucleic acids extracted from blood; A step of sequencing the above library set at high depth to generate high depth cell-free nucleic acid sequencing data; A step of mapping the high-depth cell-free nucleic acid sequencing data to a genome reference to specify a location of the high-depth cell-free nucleic acid sequencing data on the genome, and calculating at least one disease-specific signal value based on the mapped high-depth cell-free nucleic acid sequencing data; A step of processing at least one disease-specific signal value to generate a disease prediction signal value; and A step of generating a disease prediction model using the labeling information related to the blood and the disease prediction signal value; A disease detection method based on high-depth cell-free nucleic acid sequencing including .

Images