Biomarker composition for diagnosing multiple cancers comprising metabolites and artificial intelligence-based method for providing information for diagnosing multiple cancers

Abstract

The present invention relates to: a biomarker composition for diagnosing multiple cancers, the biomarker composition comprising metabolites; and an artificial intelligence-based method for providing information for diagnosing multiple cancers and, more specifically, to a biomarker composition for diagnosing multiple cancers and an artificial intelligence-based method for providing information for diagnosing multiple cancers, the biomarker composition comprising at least five biomarkers selected from the group consisting of valine (Val), glutamate (Glu), N-methyl-2-pyridone-5-carboxamide (2PY), tryptophan (Trp), kynurenine (KN), acetylcarnitine (AC), hexanoylcarnitine (HC), octanoylcarnitine (OC), decanoylcarnitine (DC), lauroylcarnitine (LAC), myristoylcarnitine (MC), palmitoylcarnitine (PC), 16:0 Lyso PC (LPC16), 18:0 Lyso PC (LPC18), 15:0-18:1 PC (15PC), 16:0 SM (16SM), 18:1 SM (18SM), and 24:1 SM (24SM).

Description

A biomarker composition for diagnosing multiple cancers including metabolites and an artificial intelligence-based information providing method for diagnosing multiple cancers

[0001] The present invention relates to a biomarker composition for diagnosing multiple cancers including metabolites and an artificial intelligence-based information providing method for diagnosing multiple cancers, and more specifically, to a biomarker composition for diagnosing multiple cancers including metabolites, including valine (Val), glutamate (Glu), N-methyl-2-pyridone-5-carboxamide (2PY), tryptophan (Trp), kynurenine (KN), acetylcarnitine (AC), hexanoylcarnitine (HC), octanoylcarnitine (OC), decanoylcarnitine (DC), lauroylcarnitine (LAC), myristoylcarnitine (MC), palmitoylcarnitine (PC), Five or more biomarker compositions selected from the group consisting of 16:0 Lyso PC (1-hexadecanoyl-sn-glycero-3-phosphocholine; LPC16), 18:0 Lyso PC (1-octadecanoyl-sn-glycero-3-phosphocholine; LPC18), 15:0-18:1 PC (1-pentadecanoyl-2-oleoyl-sn-glycero-3-phosphocholine; 15PC), 16:0 SM (N-palmitoyl-D-erythro-sphingosylphosphorylcholine, 16SM), 18:1 SM (N-oleoyl-D-erythro-sphingosylphosphorylcholine; 18SM), and 24:1 SM (N-nervonoyl-D-erythro-sphingosylphosphorylcholine; 24SM), and artificial intelligence-based information for multiple cancer diagnosis using the biomarkers It's about how to provide it.

[0002]

[0003] Cancer is a disease in which cells proliferate indefinitely and interfere with normal cell functions. Representative cancers include liver cancer, lung cancer, stomach cancer, breast cancer, colon cancer, and ovarian cancer, but in reality, it can occur in any tissue.

[0004] Early cancer diagnosis was based on the external changes in biological tissues caused by cancer cell growth. However, more recently, diagnostic methods have been developed that utilize the detection of trace biomolecules present in biological tissues or cells, such as blood, glycoproteins, and DNA. However, the most common cancer diagnostic methods utilize tissue samples obtained through biopsy or imaging.

[0005] Among these, biopsy procedures cause significant pain to patients, are expensive, and require a long time to diagnose. Furthermore, if the patient has actual cancer, there is a risk of metastasis during the biopsy process. Furthermore, in areas where tissue samples cannot be obtained through biopsy, diagnosis is impossible until the suspected tissue is surgically removed. Therefore, research is being conducted to identify biomarkers using non-invasive liquid biopsy methods that can be applied in clinical and screening settings.

[0006] Metabolomics, a cutting-edge field following genomics, transcriptomics, and proteomics, is a field of biology that comprehensively analyzes and studies metabolites and metabolic pathways within cells. It is a crucial research area that studies metabolic processes within the body, identifies key biomarkers associated with metabolic characteristics, and elucidates metabolic mechanisms. In particular, cancer research is identifying cancer metabolites altered during carcinogenesis, elucidating how these changes contribute to specific genes or mechanisms, and attempting to diagnose cancer using metabolomic biomarkers (Korean Patent Publication No. 10-2015-0072207).

[0007] Currently, several single biomarkers are being used clinically for the diagnosis of cancer, but they suffer from low specificity and sensitivity, resulting in poor diagnostic yields. Biomarker values ​​constantly fluctuate depending on an individual's genetic factors and lifestyle, and are closely linked to various factors in the cancer development and cancer microenvironment. Therefore, accurate diagnosis based on a single biomarker alone is virtually impossible. Therefore, there is a pressing need to develop novel multi-biomarkers that can improve specificity and sensitivity to simultaneously diagnose various cancers with high accuracy.

[0008] Furthermore, research is currently underway on methods utilizing artificial intelligence to achieve more accurate cancer diagnosis. AI-based analyses primarily utilize machine learning or deep learning, and various studies are currently underway to utilize this AI in the bio field (Republic of Korea Patent Publication No. 10-2014-0002149, Republic of Korea Patent Registration No. 10-2268963).

[0009]

[0010] Accordingly, the present inventors have made great efforts to select biomarkers capable of more accurately diagnosing various cancers, and as a result, biomarkers including valine (Val), glutamate (Glu), N-methyl-2-pyridone-5-carboxamide (2PY), tryptophan (Trp), kynurenine (KN), acetylcarnitine (AC), hexanoylcarnitine (HC), octanoylcarnitine (OC), decanoylcarnitine (DC), lauroylcarnitine (LAC), myristoylcarnitine (MC), palmitoylcarnitine (PC), 16:0 Lyso PC (LPC16), 18:0 Lyso PC (LPC18), 15:0-18:1 PC (15PC), 16:0 SM (16SM), 18:1 SM (18SM), and 24:1 SM (24SM) were selected, and at least five of the above biomarkers The present invention was completed by analyzing quantitative values ​​for biomarkers, more than 10 biomarkers, and 18 biomarkers using an artificial intelligence-based algorithm, and confirming that cancer diagnostic ability was improved.

[0011]

[0012] Accordingly, an object of the present invention is to provide a biomarker composition for multiple cancer diagnosis comprising a metabolite.

[0013] Another object of the present invention is to provide a multi-cancer diagnostic composition comprising a substance for measuring the expression level of the biomarker and a multi-cancer diagnostic kit using the same.

[0014] Another object of the present invention is to provide a method for providing artificial intelligence-based information for diagnosing multiple cancers using the above biomarkers.

[0015]

[0016] To achieve the above purpose,

[0017] The present invention relates to a method for producing a pharmaceutical composition comprising valine (Val), glutamate (Glu), N-methyl-2-pyridone-5-carboxamide (2PY), tryptophan (Trp), kynurenine (KN), acetylcarnitine (AC), hexanoylcarnitine (HC), octanoylcarnitine (OC), decanoylcarnitine (DC), lauroylcarnitine (LAC), myristoylcarnitine (MC), palmitoylcarnitine (PC), 16:0 Lyso PC (1-hexadecanoyl-sn-glycero-3-phosphocholine; The present invention provides a biomarker composition for diagnosing multiple cancers, comprising or including 18:0 Lyso PC (1-octadecanoyl-sn-glycero-3-phosphocholine; LPC16), 15:0-18:1 PC (1-pentadecanoyl-2-oleoyl-sn-glycero-3-phosphocholine; 15PC), 16:0 SM (N-palmitoyl-D-erythro-sphingosylphosphorylcholine; 16SM), 18:1 SM (N-oleoyl-D-erythro-sphingosylphosphorylcholine; 18SM), and 24:1 SM (N-nervonoyl-D-erythro-sphingosylphosphorylcholine; 24SM).

[0018] In addition, the present invention provides a biomarker composition for diagnosing multiple cancers, comprising five or ten or more biomarkers selected from the group consisting of valine (Val), glutamate (Glu), N-methyl-2-pyridone-5-carboxamide (2PY), tryptophan (Trp), kynurenine (KN), acetylcarnitine (AC), hexanoylcarnitine (HC), octanoylcarnitine (OC), decanoylcarnitine (DC), lauroylcarnitine (LAC), myristoylcarnitine (MC), palmitoylcarnitine (PC), 16:0 Lyso PC (LPC16), 18:0 Lyso PC (LPC18), 15:0-18:1 PC (15PC), 16:0 SM (16SM), 18:1 SM (18SM), and 24:1 SM (24SM).

[0019]

[0020] In a preferred embodiment of the present invention, the five or more biomarkers may include or consist of kynurenine (KN), octanoylcarnitine (OC), decanoylcarnitine (DC), N-methyl-2-pyridone-5-carboxamide (2PY), and 24:1 SM (24SM).

[0021] In a preferred embodiment of the present invention, the 10 or more biomarkers may include or consist of kynurenine (KN), octanoylcarnitine (OC), decanoylcarnitine (DC), lauroylcarnitine (LAC), valine (Val), glutamate (Glu), tryptophan (Trp), N-methyl-2-pyridone-5-carboxamide (2PY), 15:0-18:1 PC (15PC), and 24:1 SM (24SM).

[0022]

[0023] In a preferred embodiment of the present invention, the biomarker can be extracted from blood, and the blood can be whole blood, plasma or serum.

[0024] In another preferred embodiment of the present invention, the cancer may be at least one selected from the group consisting of liver cancer, biliary tract cancer, lung cancer, pancreatic cancer, stomach cancer, colorectal cancer, breast cancer, and cervical cancer.

[0025]

[0026] To achieve other purposes,

[0027] The present invention provides a composition for diagnosing multiple cancers, comprising a formulation for measuring the blood level of the above-described biomarker composition for diagnosing multiple cancers.

[0028] In a preferred embodiment of the present invention, the agent for measuring the level of the multi-cancer diagnostic biomarker composition may be a mass spectrometry agent.

[0029]

[0030] Additionally, the present invention provides a kit for diagnosing multiple cancers, comprising a formulation for measuring the blood level of the biomarker composition for diagnosing multiple cancers.

[0031]

[0032] To achieve another purpose,

[0033] The present invention comprises the steps of: (a) measuring the level of the above multiple cancer diagnostic biomarker from the blood of a subject; and

[0034] (b) Provided is a method for providing information for multiple cancer diagnosis using artificial intelligence, including a step of applying the expression level of the above biomarker to a machine learning algorithm model.

[0035] In a preferred embodiment of the present invention, the blood in step (a) may be whole blood, plasma or serum.

[0036] In another preferred embodiment of the present invention, the concentration of the biomarker in step (a) can be obtained by mass spectrometry of whole blood, plasma, or serum samples based on the mass peak area. Specifically, the concentration can be obtained through liquid chromatography-mass spectrometry (LC-MS), and the mass spectrometer can be any one of Triple TOF, Triple Quadrupole, and MALDI TOF capable of quantitative measurement.

[0037] In another preferred embodiment of the present invention, in the step of applying the algorithm model (b), the biomarker level in the blood of the subject of the test may be input into the algorithm model to output whether cancer has developed as an output value.

[0038] In another preferred embodiment of the present invention, the algorithm model of step (b) is

[0039] (i) a step of measuring the level of multiple cancer diagnostic biomarkers of step (a) from the blood of a cancer patient group and a normal control group;

[0040] (ⅱ) It can be derived through a step of creating a cancer incidence prediction model by learning the level of the above biomarker using a machine learning algorithm.

[0041] In another preferred embodiment of the present invention, the artificial intelligence may be machine learning or deep learning, and more specifically, the algorithm of step (b) may be any one selected from linear or nonlinear classification algorithms including a k-nearest neighbor algorithm; a logistic regression algorithm; a discriminant analysis algorithm; a partial least squares-discriminant analysis algorithm; a support vector machine algorithm; a decision tree algorithm; a decision tree ensemble algorithm; and a neural network algorithm.

[0042]

[0043] In addition, the present invention provides an artificial intelligence-based multiple cancer diagnosis prediction device including a measuring unit for measuring the level of multiple cancer diagnosis biomarkers in the blood of a subject; and a cancer diagnosis unit for inputting the biomarker levels into a learned artificial intelligence algorithm to determine whether cancer has occurred.

[0044]

[0045] In the present invention, we selected metabolite biomarkers capable of more accurately diagnosing various cancers and established an AI-based algorithm for cancer diagnosis using these biomarkers. Combining these biomarkers significantly improves the diagnostic performance of various cancers, enabling the clear diagnosis or differentiation of cancer and non-cancer groups. In particular, since it provides a pan-cancer diagnostic method capable of diagnosing multiple cancer types in a single test, the biomarkers of the present invention can be useful for diagnosing and prognosing multiple cancers.

[0046]

[0047] Figure 1 shows data confirming the concentrations of (A) valine and (B) glutamate in blood obtained from a normal control group and various cancer patient groups.

[0048] Figure 2 shows data confirming the concentrations of (A) N-methyl-2-pyridone-5-carboxamide and (B) tryptophan in blood obtained from a normal control group and various cancer patient groups.

[0049] Figure 3 shows data confirming the concentrations of (A) kynurenine and (B) acetylcarnitine in blood obtained from a normal control group and various cancer patient groups.

[0050] Figure 4 shows data confirming the concentrations of (A) hexanoylcarnitine and (B) octanoylcarnitine in blood obtained from a normal control group and various cancer patient groups.

[0051] Figure 5 shows data confirming the concentrations of (A) decanoylcarnitine and (B) lauroylcarnitine in blood obtained from a normal control group and various cancer patient groups.

[0052] Figure 6 shows data confirming the concentrations of (A) myristoyl carnitine and (B) palmitoyl carnitine in blood obtained from a normal control group and various cancer patient groups.

[0053] Figure 7 shows data confirming the concentrations of (A) 16:0 Lyso PC and (B) 18:0 Lyso PC in blood obtained from a normal control group and various cancer patient groups.

[0054] Figure 8 shows data confirming the concentrations of (A) 15:0-18:1 PC and (B) 16:0 SM in blood obtained from a normal control group and various cancer patient groups.

[0055] Figure 9 shows data confirming the concentrations of (A) 18:1 SM and (B) 24:1 SM in blood obtained from a normal control group and various cancer patient groups.

[0056] Figure 10 is data showing the accuracy of cancer diagnosis through a ROC curve when five biomarkers among the multiple cancer diagnostic metabolite biomarkers of the present invention are used.

[0057] Figure 11 shows data showing (A) the accuracy of cancer diagnosis through a ROC curve and (B) the sensitivity for each cancer diagnosis when 10 biomarkers among the metabolite biomarkers for multiple cancer diagnosis of the present invention are used.

[0058] Figure 12 shows data showing (A) the accuracy of cancer diagnosis through a ROC curve and (B) the sensitivity for each cancer diagnosis when all of the metabolite biomarkers for multiple cancer diagnosis of the present invention are used.

[0059]

[0060] Hereinafter, the present invention will be described in detail.

[0061]

[0062] Biomarker composition for multiple cancer diagnosis

[0063] The present invention relates to a method for producing a pharmaceutical composition comprising: a) valine (Val), glutamate (Glu), N-methyl-2-pyridone-5-carboxamide (2PY), tryptophan (Trp), kynurenine (KN), acetylcarnitine (AC), hexanoylcarnitine (HC), octanoylcarnitine (OC), decanoylcarnitine (DC), lauroylcarnitine (LAC), myristoylcarnitine (MC), palmitoylcarnitine (PC), 16:0 Lyso The present invention relates to a biomarker composition for diagnosing multiple cancers, comprising or including PC (1-hexadecanoyl-sn-glycero-3-phosphocholine; LPC16), 18:0 Lyso PC (1-octadecanoyl-sn-glycero-3-phosphocholine; LPC18), 15:0-18:1 PC (1-pentadecanoyl-2-oleoyl-sn-glycero-3-phosphocholine; 15PC), 16:0 SM (N-palmitoyl-D-erythro-sphingosylphosphorylcholine, 16SM), 18:1 SM (N-oleoyl-D-erythro-sphingosylphosphorylcholine; 18SM), and 24:1 SM (N-nervonoyl-D-erythro-sphingosylphosphorylcholine; 24SM).

[0064] In another aspect, the present invention relates to a biomarker composition for diagnosing multiple cancers, comprising at least five biomarkers or at least ten biomarkers selected from the group consisting of valine (Val), glutamate (Glu), N-methyl-2-pyridone-5-carboxamide (2PY), tryptophan (Trp), kynurenine (KN), acetylcarnitine (AC), hexanoylcarnitine (HC), octanoylcarnitine (OC), decanoylcarnitine (DC), lauroylcarnitine (LAC), myristoylcarnitine (MC), palmitoylcarnitine (PC), 16:0 Lyso PC (LPC16), 18:0 Lyso PC (LPC18), 15:0-18:1 PC (15PC), 16:0 SM (16SM), 18:1 SM (18SM), and 24:1 SM (24SM).

[0065]

[0066] The above biomarkers may include five or more biomarkers, ten or more biomarkers, or all eighteen biomarkers, as needed. The five or more biomarkers may include or consist of kynurenine (KN), octanoylcarnitine (OC), decanoylcarnitine (DC), N-methyl-2-pyridone-5-carboxamide (2PY), and 24:1 SM (24SM).

[0067] Additionally, the above 10 or more biomarkers may include or consist of kynurenine (KN), octanoylcarnitine (OC), decanoylcarnitine (DC), lauroylcarnitine (LAC), valine (Val), glutamate (Glu), tryptophan (Trp), N-methyl-2-pyridone-5-carboxamide (2PY), 15:0-18:1 PC (15PC), and 24:1 SM (24SM).

[0068]

[0069] In the present invention, the biomarker is extracted from blood, and the blood may be whole blood, plasma, or serum.

[0070] In the present invention, the multi-cancer diagnostic biomarker composition can be used to diagnose which cancer among one or more cancers, and preferably, the cancer can be at least one selected from the group consisting of liver cancer, biliary tract cancer, lung cancer, pancreatic cancer, stomach cancer, colon cancer, breast cancer, and cervical cancer.

[0071]

[0072] The term "diagnosis" as used herein refers to confirming the presence or characteristics of a pathological condition. For the purposes of the present invention, diagnosis refers to confirming the presence or absence of cancer.

[0073] The term "diagnostic biomarker" used in the present invention refers to an organic biomolecule such as a polypeptide, nucleic acid (e.g., mRNA, etc.), lipid, glycolipid, glycoprotein, sugar (monosaccharide, disaccharide, oligosaccharide, etc.) that shows a significant increase or significant decrease in a specific cancer patient group.

[0074] In a specific embodiment of the present invention, blood was obtained from each of a normal control group, liver cancer, biliary tract cancer, lung cancer, pancreatic cancer, stomach cancer, colon cancer, breast cancer, and cervical cancer patient group, and the concentrations of Val, Glu, 2PY, Trp, KN, AC, HC, OC, DC, LAC, MC, PC, LPC16, LPC18, 15PC, 16SM, 18SM, and 24SM in the blood were measured, respectively (Figs. 1 to 9).

[0075] As a result, the blood concentrations of 2PY, HC, OC, DC, and LAC were confirmed to be decreased in all cancers compared to the normal control group. In addition, compared to the normal control group, the blood concentrations of Val were confirmed to be increased in liver cancer, lung cancer, pancreatic cancer, and stomach cancer; Glu in liver cancer, biliary tract cancer, lung cancer, pancreatic cancer, stomach cancer, colon cancer, and cervical cancer; Trp in biliary tract cancer and lung cancer; KN in liver cancer, biliary tract cancer, and pancreatic cancer; AC in liver cancer and pancreatic cancer; LPC16 and LPC18 in lung cancer and stomach cancer; 15PC and 24SM in biliary tract cancer, lung cancer, and pancreatic cancer; 16SM in biliary tract cancer and lung cancer; and 18SM in lung cancer.

[0076]

[0077] Composition for multiple cancer diagnosis

[0078] In another aspect, the present invention relates to a composition for diagnosing multiple cancers, comprising a formulation for measuring the blood level of the biomarker composition for diagnosing multiple cancers of the present invention.

[0079] The composition for diagnosing multiple cancers according to the present invention applies the <biomarker composition for diagnosing multiple cancers> described above.

[0080] The biomarker of the present invention is a metabolite, and the preparation for measuring the level of the biomarker composition may be a preparation for mass spectrometry.

[0081] The above mass spectrometry preparation is a preparation capable of analyzing the concentration of a biomarker in whole blood, plasma, or serum, and specifically refers to a preparation capable of performing liquid chromatography-mass spectrometry (LC-MS).

[0082]

[0083] Multi-cancer diagnostic kit

[0084] In another aspect, the present invention relates to a kit for diagnosing multiple cancers, comprising a formulation for measuring the blood level of the biomarker composition for diagnosing multiple cancers of the present invention.

[0085] The composition for diagnosing multiple cancers according to the present invention applies the <biomarker composition for diagnosing multiple cancers> described above.

[0086] The above kit can be manufactured using conventional manufacturing methods known in the art. The kit may include, for example, antibodies or chemicals in lyophilized form, buffers, stabilizers, inactive proteins, etc.

[0087]

[0088] Method for providing information for multiple cancer diagnosis using an artificial intelligence-based algorithm

[0089] In another aspect, the present invention provides a method for diagnosing multiple cancers, comprising: (a) measuring the level of a biomarker for diagnosis of multiple cancers, comprising or consisting of valine (Val), glutamate (Glu), N-methyl-2-pyridone-5-carboxamide (2PY), tryptophan (Trp), kynurenine (KN), acetylcarnitine (AC), hexanoylcarnitine (HC), octanoylcarnitine (OC), decanoylcarnitine (DC), lauroylcarnitine (LAC), myristoylcarnitine (MC), palmitoylcarnitine (PC), 16:0 Lyso PC (LPC16), 18:0 Lyso PC (LPC18), 15:0-18:1 PC (15PC), 16:0 SM (16SM), 18:1 SM (18SM), and 24:1 SM (24SM) from the blood of a test subject; or

[0090] A step of measuring the level of a multiple cancer diagnostic biomarker comprising at least 5 biomarkers or at least 10 biomarkers selected from the group consisting of valine (Val), glutamate (Glu), N-methyl-2-pyridone-5-carboxamide (2PY), tryptophan (Trp), kynurenine (KN), acetylcarnitine (AC), hexanoylcarnitine (HC), octanoylcarnitine (OC), decanoylcarnitine (DC), lauroylcarnitine (LAC), myristoylcarnitine (MC), palmitoylcarnitine (PC), 16:0 Lyso PC (LPC16), 18:0 Lyso PC (LPC18), 15:0-18:1 PC (15PC), 16:0 SM (16SM), 18:1 SM (18SM), and 24:1 SM (24SM); and

[0091] (b) Provided is a method for providing information for multiple cancer diagnosis using artificial intelligence, including a step of applying the expression level of the above biomarker to a machine learning algorithm model.

[0092] The above biomarkers may include five or more biomarkers, ten or more biomarkers, or all eighteen biomarkers, as needed. The five or more biomarkers may include or consist of kynurenine (KN), octanoylcarnitine (OC), decanoylcarnitine (DC), N-methyl-2-pyridone-5-carboxamide (2PY), and 24:1 SM (24SM).

[0093] Additionally, the above 10 or more biomarkers may include or consist of kynurenine (KN), octanoylcarnitine (OC), decanoylcarnitine (DC), lauroylcarnitine (LAC), valine (Val), glutamate (Glu), tryptophan (Trp), N-methyl-2-pyridone-5-carboxamide (2PY), 15:0-18:1 PC (15PC), and 24:1 SM (24SM).

[0094]

[0095] In the present invention, the blood in step (a) may be whole blood, plasma or serum.

[0096] In the present invention, the multi-cancer diagnostic biomarker composition can be used to diagnose which cancer among one or more cancers, and preferably, the cancer can be at least one selected from the group consisting of liver cancer, biliary tract cancer, lung cancer, pancreatic cancer, stomach cancer, colon cancer, breast cancer, and cervical cancer.

[0097] In the present invention, the concentration of the biomarker in step (a) can be obtained by mass spectrometry of whole blood, plasma, or serum samples based on the mass peak area. Specifically, the concentration can be obtained through liquid chromatography-mass spectrometry (LC-MS), and the mass spectrometer can be any one of a triple TOF, a triple quadrupole, and a MALDI TOF capable of quantitative measurement.

[0098] In the present invention, the step of applying the above (b) algorithm model can input the level of the biomarker in the blood of the subject of the test into the algorithm model and output whether or not cancer has developed as an output value.

[0099] In the present invention, the algorithm model of step (b) comprises: (i) a step of measuring the level of the multiple cancer diagnostic biomarker of step (a) from the blood of a cancer patient group and a normal control group;

[0100] (ⅱ) It can be derived through a step of creating a cancer incidence prediction model by learning the level of the above biomarker using a machine learning algorithm.

[0101] The above artificial intelligence may be machine learning or deep learning, and more specifically, the algorithm of step (b) may be any one selected from linear or nonlinear classification algorithms including a k-nearest neighbor algorithm; a logistic regression algorithm; a discriminant analysis algorithm; a partial least squares-discriminant analysis algorithm; a support vector machine algorithm; a decision tree algorithm; a decision tree ensemble algorithm; and a neural network algorithm.

[0102] Specifically, if the algorithm of step (b) above is a support vector machine algorithm, it is expressed by the kernel function of the following mathematical expression 1,

[0103] [Mathematical Formula 1]

[0104]

[0105]

[0106] In the above, x is a blood level measurement value of a biomarker composition for multiple cancer diagnosis, and γ is a parameter for the flexibility (curvature) of the decision boundary.

[0107]

[0108] In a specific embodiment of the present invention, the diagnostic accuracy was measured using a receiver operating characteristic (ROC) curve for cancer diagnosis using five biomarkers of the present invention, and it was confirmed that the AUC (area under the ROC curve) value was 0.943, showing statistically very significant cancer diagnostic ability (Fig. 10).

[0109] As a result of measuring the diagnostic accuracy using the ROC curve for cancer diagnosis using 10 biomarkers among the 18 biomarkers of the present invention, it was confirmed that the cancer diagnostic ability was statistically very significant with an AUC value of 0.971 (Fig. 11A).

[0110] In addition, the diagnostic accuracy was measured using the ROC curve for cancer diagnosis using the 18 biomarkers of the present invention, and it was confirmed that the cancer diagnostic ability was statistically very significant with an AUC value of 0.987 (Fig. 12A).

[0111] The receiver operating characteristic (ROC) curve is a widely used method for comparing the accuracy of diagnostic methods (Akobeong, 2007). The vertical axis represents "sensitivity" and the horizontal axis represents "1-specificity." The area under the diagonal is 0.5, and the higher the ROC curve is above the diagonal, the better the model is evaluated. The AUC ranges from 0.5 to 1, with a value closer to 1 indicating a wider area under the curve and higher model accuracy.

[0112] That is, it was confirmed that the biomarker of the present invention is the most suitable biomarker for pan-cancer diagnosis.

[0113]

[0114] In addition, the present invention, from another consistent viewpoint, is a biomarker for diagnosing multiple cancers, which comprises or consists of valine (Val), glutamate (Glu), N-methyl-2-pyridone-5-carboxamide (2PY), tryptophan (Trp), kynurenine (KN), acetylcarnitine (AC), hexanoylcarnitine (HC), octanoylcarnitine (OC), decanoylcarnitine (DC), lauroylcarnitine (LAC), myristoylcarnitine (MC), palmitoylcarnitine (PC), 16:0 Lyso PC (LPC16), 18:0 Lyso PC (LPC18), 15:0-18:1 PC (15PC), 16:0 SM (16SM), 18:1 SM (18SM), and 24:1 SM (24SM) in the blood of a test subject, or

[0115] A measuring unit for measuring the level of a multi-cancer diagnostic biomarker comprising at least five biomarkers selected from the group consisting of valine (Val), glutamate (Glu), N-methyl-2-pyridone-5-carboxamide (2PY), tryptophan (Trp), kynurenine (KN), acetylcarnitine (AC), hexanoylcarnitine (HC), octanoylcarnitine (OC), decanoylcarnitine (DC), lauroylcarnitine (LAC), myristoylcarnitine (MC), palmitoylcarnitine (PC), 16:0 Lyso PC (LPC16), 18:0 Lyso PC (LPC18), 15:0-18:1 PC (15PC), 16:0 SM (16SM), 18:1 SM (18SM), and 24:1 SM (24SM), and

[0116] The present invention relates to an artificial intelligence-based multi-cancer diagnosis prediction device including a cancer diagnosis unit that inputs the above biomarker level into a learned artificial intelligence algorithm to determine whether cancer has occurred.

[0117] The above biomarkers may include five or more biomarkers, ten or more biomarkers, or all eighteen biomarkers, as needed. The five or more biomarkers may include or consist of kynurenine (KN), octanoylcarnitine (OC), decanoylcarnitine (DC), N-methyl-2-pyridone-5-carboxamide (2PY), and 24:1 SM (24SM).

[0118] Additionally, the above 10 or more biomarkers may include or consist of kynurenine (KN), octanoylcarnitine (OC), decanoylcarnitine (DC), lauroylcarnitine (LAC), valine (Val), glutamate (Glu), tryptophan (Trp), N-methyl-2-pyridone-5-carboxamide (2PY), 15:0-18:1 PC (15PC), and 24:1 SM (24SM).

[0119]

[0120] Hereinafter, the present invention will be described in more detail through examples.

[0121] These examples are intended solely to illustrate the present invention, and it will be apparent to those skilled in the art that the scope of the present invention is not to be construed as being limited by these examples.

[0122]

[0123] Example 1: Measurement of biomarker concentrations in the blood of various cancer patient groups and normal control subjects.

[0124] 1-1: Sample preparation

[0125] To confirm whether the biomarker of the present invention can diagnose various cancers, 120 normal controls (non-cancer), 20 liver cancer patients, 19 bile duct cancer patients, 19 lung cancer patients, 19 pancreatic cancer patients, 19 stomach cancer patients, 19 colon cancer patients, 20 breast cancer patients, and 20 cervical cancer patients were selected through Seoul National University Bundang Hospital (SNUBH), Ajou University Hospital (AJUH), Keimyung University Dongsan Hospital (KMUH), and Asan Medical Center (ASMCS), and blood samples were collected.

[0126]

[0127] 1-2: Measurement of biomarker concentration in blood

[0128] Plasma was separated from the above blood sample, and standard substances at each concentration required for the biomarker standard curve of valine (Val), glutamate (Glu), N-methyl-2-pyridone-5-carboxamide (2PY), tryptophan (Trp), kynurenine (KN), acetylcarnitine (AC), hexanoylcarnitine (HC), octanoylcarnitine (OC), decanoylcarnitine (DC), lauroylcarnitine (LAC), myristoylcarnitine (MC), palmitoylcarnitine (PC), 16:0 Lyso PC (LPC16), 18:0 Lyso PC (LPC18), 15:0-18:1 PC (15PC), 16:0 SM (16SM), 18:1 SM (18SM), and 24:1 SM (24SM) were prepared.

[0129]

[0130] 80 μl of methanol (Sigma) was added to an Ep tube containing 20 μl of plasma and standards and 10 μl of internal standard, vortexed for 3 minutes, and centrifuged (13,000 rpm, 10 minutes, 15°C). After centrifugation, 60 μl of the supernatant was transferred to a new tube, diluted 2 / 3 with 30 μl of sample dilution buffer (0.3% FA in water), and analyzed using LC-MS / MS (liquid chromatography - mass spectrometry / mass spectrometry). The LC used was a Shimadzu LC 40 system, and the MS was an AB Sciex Triple Quad 5500+ system. The MS was equipped with a turbo spray ion source. The analytical samples were separated on a BEH C18 column (1.7 μm, 2.1*50 mm; Waters) of a Shimadzu LC 40 system. A two-step linear gradient (solvent A, 0.1% FA in water; solvent B, 0.1% FA in 100% acetonitrile; 5–55% solvent B 2.5 min, 55% solvent B 5.5 min, 55–95% solvent B 7.5 min, 95% solvent B 11 min, 95–5% solvent B 11.1 min, and 5% solvent B 14.5 min) was used.

[0131] Mass spectrometry (MS / MS) was performed using multiple reaction monitoring (MRM) mode. The area of ​​the mass peak with the same mass value among the mass spectrum at the same time point as the time point at which the metabolite corresponding to each biomarker passed through liquid chromatography was calculated. A standard curve was created using the mass peaks of each biomarker standard substance, and the mass peaks of each sample were input into the standard curve to measure the concentration of each biomarker.

[0132]

[0133] 정상 대조군 혈액 내 바이오마커 농도 (1)No.Sample sourceSample NameAge (year)Sex (M / F)SmokingVal(㎍ / ml)Glu(㎍ / ml)2PY (ng / ml)Trp(㎍ / ml)KN (ng / ml)1AJUHAJ_N_05157MNever smoking24.7312.3023.4218.85656.452AJUHAJ_N_07057FNever smoking26.609.2513.0618.69364.543AJUHAJ_N_07151FNever smoking24.426.7123.5316.92362.534AJUHAJ_N_07253FNever smoking25.305.3315.7016.84471.715AJUHAJ_N_07455FNever smoking23.657.4219.6914.99421.226AJUHAJ_N_07559FNever smoking18.455.259.1319.32362.537AJUHAJ_N_07758MNever smoking29.706.2211.9327.25433.498AJUHAJ_N_07957FNever smoking25.106.7422.5424.81559.599AJUHAJ_N_08158FNever smoking23.837.0619.2217.40376.3110AJUHAJ_N_08357MCurrently smoking24.759.4426.9718.51341.7311AJUHAJ_N_08452FNever smoking15.934.9235.6615.98319.4312AJUHAJ_N_08555MNever smoking18.865.469.6417.70304.4813AJUHAJ_N_08656MNever smoking29.177.6419.2520.40419.6814AJUHAJ_N_08854MNever smoking26.448.2130.9320.46378.4715AJUHAJ_N_08952FNever smoking21.256.1522.8814.62303.0116AJUHAJ_N_09053FNever smoking19.927.309.5515.33358.7817AJUHAJ_N_09257MCurrently smoking26.207.8110.4319.83405.3118SNUBHSN_N_07251FNever smoking19.284.1313.8916.20296.9719SNUBHSN_N_07950FNever smoking19.834.4720.1513.05274.6920SNUBHSN_N_08050MCurrently smoking27.2114.3822.6417.06251.2221SNUBHSN_N_10549MCurrently Smoking22.687.860.7518.24318.7122SNUBHSN_N_11750FNever Smoking21.816.9814.2313.88278.2023SNUBHSN_N_12151FNever Smoking28.615.0129.8413.90315.8024SNUBHSN_N_13053MCurrently Smoking22.006.931.5416.86267.1025SNUBHSN_N_13349MNever Smoking25.926.199.5218.14263.0026SNUBHSN_N_14148MEx-Smoking21.718.050.7618.45368.5027SNUBHSN_N_14249MNever Smoking30.5210.7717.4218.42364.1028SNUBHSN_N_14854FNever Smoking20.085.1516.7613.12300.5529SNUBHSN_N_15451FNever Smoking21.095.5411.6013.87292.7330SNUBHSN_N_15748MEx-Smoking24.6612.6914.2913.61340.2331SNUBHSN_N_15850FNever Smoking24.185.557.7516.90328.3032SNUBHSN_N_16348FNever Smoking23.308.7829.8214.96373.1933SNUBHSN_N_17851FNever Smoking20.435.5216.7713.98290.4634SNUBHSN_N_18244MCurrently smoking24.896.8916.5819.55332.5035SNUBHSN_N_18346FNever smoking14.953.492.9510.54218.6836SNUBHSN_N_18643MCurrently smoking33.388.457.8716.99300.4337SNUBHSN_N_18744MEx-smoking24.778.9413.7615.73363.1138SNUBHSN_N_18838MNever smoking20.879.278.5917.54355.7339SNUBHSN_N_19051MEx-Smoking24.626.0031.5614.76309.5540SNUBHSN_N_19252MEx-Smoking29.8410.667.1915.89518.1641SNUBHSN_N_19346MNever smoking28.149.1218.3017.70299.8242SNUBHSN_N_19551FNever Smoking22.777.1911.1417.80431.2643SNUBHSN_N_19950MEx-Smoking25.449.3667.2514.25250.8944SNUBHSN_N_20951MCurrently Smoking26.6911.8219.9315.38386.7445SNUBHSN_N_21156MEx-Smoking29.4011.0020.7516.62335.8246SNUBHSN_N_22053MEx-Smoking31.639.6312.0418.25348.9447SNUBHSN_N_24749MCurrently Smoking31.3210.1916.2715.81324.4748SNUBHSN_N_25353MNever Smoking26.4414.3712.1116.75355.9149SNUBHSN_N_25449MNever Smoking31.529.415.2511.68292.8250SNUBHSN_N_26148FNever Smoking33.095.9516.7312.78232.9051SNUBHSN_N_26252MNever Smoking41.487.6328.7712.67335.5452SNUBHSN_N_26353MNever Smoking27.857.7013.2514.87340.9553SNUBHSN_N_26958MEx-Smoking27.7812.195.0317.10429.2254SNUBHSN_N_27448FNever Smoking24.737.5528.0515.72314.2755SNUBHSN_N_28750MEx-Smoking32.0018.4611.0818.25351.3656SNUBHSN_N_28949FNever Smoking30.3510.4010.6512.20249.4357SNUBHSN_N_29058MEx-Smoking29.7413.3519.9316.93430.9858SNUBHSN_N_29138MNever smoking36.5016.4611.2119.27483.4359SNUBHSN_N_29450MEx-Smoking30.5210.447.6214.69239.0460SNUBHSN_N_29536MEx-smoking38.7320.5825.2523.48392.5261SNUBHSN_N_29644FNever smoking24.396.5414.3912.45243.4962SNUBHSN_N_30039FNever smoking33.847.5612.7113.69304.1263SNUBHSN_N_30150MCurrently Smoking28.0911.7520.0711.70336.2664SNUBHSN_N_30954MNever Smoking28.9113.5914.7415.95369.1365SNUBHSN_N_31648MEx-Smoking26.416.9321.0115.87303.6366SNUBHSN_N_31835MNever smoking22.5610.2513.2219.45291.2667SNUBHSN_N_32254MNever Smoking28.9111.1027.5716.69443.3468SNUBHSN_N_32453FNever Smoking20.6311.1015.0114.47222.4769SNUBHSN_N_32854FNever Smoking26.536.5317.3012.73264.4970SNUBHSN_N_33135MEx-smoking30.3214.977.7314.26403.0071SNUBHSN_N_33339MEx-smoking21.5810.986.9213.17314.1472SNUBHSN_N_33438MNever smoking31.669.7719.6315.52332.2573SNUBHSN_N_33752MNever Smoking28.386.5618.8820.77306.0774SNUBHSN_N_33959MNever Smoking26.297.0924.7115.99388.2575SNUBHSN_N_34049MCurrently Smoking26.1812.7615.7314.57323.3176SNUBHSN_N_34133MCurrently smoking30.049.3127.6012.51548.8177SNUBHSN_N_34250FNever Smoking24.6915.4735.6714.95419.0778SNUBHSN_N_34443FNever smoking21.814.4514.2212.56313.6179SNUBHSN_N_34552MCurrently Smoking33.039.7316.2717.14337.1180SNUBHSN_N_35051FNever Smoking25.236.6616.0813.56256.8981SNUBHSN_N_35158MEx-Smoking24.0511.447.9819.36459.4282SNUBHSN_N_35751FNever Smoking18.267.3438.1212.65278.5583SNUBHSN_N_36048MEx-Smoking23.118.942.6317.52328.8184SNUBHSN_N_36249FNever Smoking22.306.7812.3911.36326.1485SNUBHSN_N_36346MEx-smoking27.476.999.3016.30383.8786SNUBHSN_N_37248FNever Smoking20.964.9730.718.80236.8687SNUBHSN_N_37350MEx-Smoking34.057.4112.0515.72422.9988SNUBHSN_N_37453MEx-Smoking26.198.1213.2216.04402.3589SNUBHSN_N_37548FNever Smoking24.886.0819.5714.25289.3790SNUBHSN_N_37649MEx-Smoking32.5111.3444.8315.90523.2591SNUBHSN_N_37750FNever Smoking20.863.7113.0814.24349.1692SNUBHSN_N_37848FNever Smoking23.284.8219.2512.56273.0493SNUBHSN_N_37948MEx-Smoking24.707.0227.6318.30520.7594SNUBHSN_N_38252MEx-Smoking23.636.735.1619.66386.3695SNUBHSN_N_38351FNever Smoking19.788.4729.5512.45442.1496SNUBHSN_N_38549MNever Smoking31.468.3021.4819.86444.8297SNUBHSN_N_38647MEx-smoking26.077.862.9819.16368.0298SNUBHSN_N_38850FNever Smoking26.009.8446.1612.21284.4899SNUBHSN_N_39343FNever smoking24.066.679.9513.85325.79100SNUBHSN_N_39439MCurrently smoking28.9314.458.2216.02259.31101SNUBHSN_N_39858MEx-Smoking30.449.963.2717.05341.60102SNUBHSN_N_40165MEx-Smoking38.1112.3319.8614.61322.52103SNUBHSN_N_40261MEx-Smoking30.7910.269.7817.39364.80104SNUBHSN_N_40361MEx-Smoking31.046.9113.2414.47351.05105SNUBHSN_N_40463MEx-Smoking23.006.519.0715.15399.39106SNUBHSN_N_40563MEx-Smoking29.539.4725.8116.17401.74107SNUBHSN_N_40663MNever Smoking22.606.991.2617.35304.85108SNUBHSN_N_40765MEx-Smoking29.298.6410.4314.98311.56109SNUBHSN_N_40865MEx-Smoking33.3010.5631.0811.84416.45110SNUBHSN_N_40961MCurrently Smoking30.2410.5455.2114.53415.65111SNUBHSN_N_41166MEx-Smoking29.9913.5812.9016.72386.88112SNUBHSN_N_41263MNever Smoking31.029.0835.7816.46428.39113SNUBHSN_N_41361MEx-Smoking25.929.2415.5414.79369.12114SNUBHSN_N_41461MEx-Smoking28.3414.6429.5221.07525.12115SNUBHSN_N_41565MEx-Smoking31.1110.1827.8513.01403.41116SNUBHSN_N_41661MNever Smoking29.0010.7616.8514.82452.39117SNUBHSN_N_41769MNever Smoking37.3010.5620.2718.22633.83118SNUBHSN_N_41861MNever Smoking28.6410.7025.8014.74447.38119SNUBHSN_N_41961FNever Smoking30.4415.2226.5017.55426.21120SNUBHSN_N_42064FNever Smoking26.587.5913.4215.69500.58.

[0134] Biomarker concentration in blood of normal control group (2) No. Sample Name AC (㎍ / ml) HC (ng / ml) OC (ng / ml) DC (ng / ml) LAC (ng / ml) MC (ng / ml) PC (ng / ml) 1 AJ_N_05 10.93 20.16 57.35 81.93 23.44 10.23 62.27 2 AJ_N_07 0.95 16.86 50.17 75.06 18.837.564 1.52 3 AJ_N_07 10.87 13.36 34.36 50.839.083.33 25.00 4 AJ_N_07 20.92 17.08 4.23 65.47 20.28 8.78 36.08 5 AJ_N_ 0741.3621.8262.3393.6123.799.6646.696AJ_N_0751.8450.85185.82 334.0998.2526.6687.357AJ_N_0770.678.3319.6425.237.486.1851.77 8AJ_N_0791.2930.1791.61127.9536.4410.6243.469AJ_N_0811.2922. 0175.16115.2028.2910.2355.2310AJ_N_0831.2932.4997.01154.3738. 5812.6854.6511AJ_N_0841.8937.57123.36210.8574.2521.7165.9812 AJ_N_0851.4329.1288.95133.9129.6810.8852.6813AJ_N_0861.8334.9 8153.00235.0542.8513.3369.4514AJ_N_0880.9425.9081.75138.5634 .7011.0157.7015AJ_N_0890.9216.5135.8054.8516.829.6660.2516AJ_ N_0901.1122.9072.83111.4623.609.1249.8617AJ_N_0920.6213.2639 .8159.6515.768.3953.9018SN_N_0721.2122.5963.2599.4922.229.115 4.7119SN_N_0790.7614.2150.1078.5015.874.8731.6120SN_N_0800.8 610.6522.7034.197.864.9543.0021SN_N_1051.0315.2149.6178.7026.988.6750.1222SN_N_1172.4835.9072.29111.0431.4714.2758.8323SN_N_1211.8821.8360.2190.9326.7010.0946.2724SN_N_1300.7610.8736.1349.8011.785.7040.2425SN_N_1330.8914.5932.0246.7512.815.9945.5426SN_N_1410.9811.9330.7946.5815.656.3644.4327SN_N_1421.1527.8398.35149.0627.1311.3765.2928SN_N_1481.3320.3752.0688.3123.939.5048.8729SN_N_1541.1410.9230.4346.8614.706.0335.5530SN_N_1571.3217.5735.5646.1011.185.5443.1531SN_N_1581.2021.2876.50119.1120.357.8141.1032SN_N_1631.9526.9677.37111.6524.949.5051.8833SN_N_1781.2323.1277.12116.7420.457.1629.9534SN_N_1820.849.6124.2440.8411.645.4141.3935SN_N_1831.5215.2645.7175.7820.108.7249.0036SN_N_1860.8616.7747.6274.6223.389.7649.1437SN_N_1870.9919.5071.51114.6627.868.3553.8138SN_N_1881.3619.0441.2961.6221.928.6849.7739SN_N_1901.6424.4897.84162.5049.1414.3665.1340SN_N_1921.8423.0042.6971.5317.389.0356.0741SN_N_1931.2815.2940.9260.9215.347.0044.7642SN_N_1950.9515.5550.4084.9221.368.1242.9343SN_N_1991.5826.9479.58121.8631.1011.6957.9244SN_N_2090.769.5718.8330.519.215.7951.4145SN_N_2111.5418.9544.6080.7021.4510.0555.3046SN_N_ 2202.0027.2590.63124.3431.699.5548.5147SN_N_2471.3018.7258.0884 .7126.438.4441.3648SN_N_2531.2017.0531.2142.7715.099.7659.2449 SN_N_2540.9215.1959.92106.3326.949.0955.2650SN_N_2612.5326.6760 .2488.9837.4517.0464.1651SN_N_2622.5347.17122.25207.3670.8326. 8781.9452SN_N_2631.1117.0257.0688.4222.008.6144.1153SN_N_2690.8 018.5943.4461.8017.529.6549.4354SN_N_2741.3327.6889.87124.0839 .4511.8749.2355SN_N_2871.6622.5363.1297.1533.1413.1162.5056SN_N _2890.9612.2728.7245.5912.666.7649.3457SN_N_2902.2026.1536.5159.2529.7812.9366.9358SN_N_2911.0916.0046.8681.6327.8610.7253.9259SN_N_2940.9811.4223.7241.7012.256.8145.9160SN_N_2951.6431.4981.62157.4544.8316.8869.9761SN_N_2961.4958.43196.78288.8140.311 0.2642.4662SN_N_3001.189.3229.5649.8412.675.5637.2663SN_N_3011 .5829.9875.51133.4040.6415.1065.1364SN_N_3091.8926.8663.15100.9 134.2511.7053.1465SN_N_3162.2622.2856.5490.9033.3413.1264.7766 SN_N_3180.8914.9435.4456.0817.477.2946.3067SN_N_3222.2828.9177.71132.4932.7813.4463.4968SN_N_3242.4826.6946.4265.0320.6811.2756.8569SN_N_3280.669.7619.0729.747.364.8332.0870SN_N_3311.5719.8833.4556.8517.548.8557.4971SN_N_3331.2612.2035.7452.7820.1510.9861.7272SN_N_3341.7220.0432.8455.4023.9210.2661.2273SN_N_3371.8838.20121.51227.8555.1114.1357.0274SN_N_3391.0520.5551.3077.6520.827.6552.9775SN_N_3400.766.9314.1918.335.325.8040.1576SN_N_3411.0017.5952.9980.9421.037.2134.4677SN_N_3420.759.1019.5727.788.214.4034.0178SN_N_3440.7610.6039.0160.7817.007.2560.6879SN_N_3452.3357.09191.00308.1883.1629.22132.5980SN_N_3501.8535.8895.55153.5636.5913.3084.2781SN_N_3510.9822.90108.30171.8543.0613.1879.0682SN_N_3571.1614.7831.8646.9613.697.4745.0983SN_N_3600.6711.5131.8750.7014.537.3748.6884SN_N_3621.1513.4429.0445.5211.305.8637.5085SN_N_3631.5730.38100.61146.4351.5516.2971.1486SN_N_3721.8328.2466.5895.1445.2615.8052.8587SN_N_3730.999.2836.2256.9424.029.6952.5388SN_N_3741.4418.7743.6554.0918.828.9551.8489SN_N_3751.5227.9478.17122.9938.9111.7050.3490SN_N_3761.2526.4376.95133.9030.6314.7876.7591SN_N_3770.759.9247.6671.9116.256.3444.8692SN_N_3781.4771.40351.21420.1645.5510.6957.6693SN_N_3791.2514.4536.2753.7914.298.1459.4594SN_N_3820.9115.9858.5590.5228.8710.5663.5795SN_N_3831.6826.0265.7795.7730.4010.8058.7496SN_N_3851.5126.44111.39194.1447.4314.6156.2597SN_N_3861.1323.76104.03195.4147.5516.4169.4998SN_N_3881.7119.0633.2648.2917.898.9942.6999SN_N_3930.8510.2741.8070.4325.839.2251.14100SN_N_3940.638.5221.2029.839.235.5742.34101SN_N_3980.8513.3348.0865.7317.275.5630.36102SN_N_4012.3223.0556.92103.5935.0712.8151.02103SN_N_4020.8019.8469.09109.3921.526.9742.23104SN_N_4030.8914.7348.0671.6526.259.4748.43105SN_N_4041.3630.42127.36237.1753.4613.6658.98106SN_N_4051.9225.1676.15132.6748.7217.4977.63107SN_N_4060.9125.50112.71176.9146.1414.6063.55108SN_N_4070.8420.4791.26114.0320.869.6742.71109SN_N_4082.9228.5549.0773.5026.7913.8766.12110SN_N_4093.5644.8486.76133.3139.8519.2570.50111SN_N_4110.599.5324.8234.3010.715.9039.60112SN_N_4122.7838.2788.29133.9751.5221.5684.96113SN_N_4131.1714.7339.0158.6018.408.9551.91114SN_N_4141.0219.9945.0167.3620.9010.2359.24115SN_N_4151.8737.1998.52160.2137.7913.4357.96116SN_N_4161.5615.0628.8443.5111.777.8756.84117SN_N_4171.7022.5658.4194.9732.7012.1759.12118SN_N_4180.9416.2038.3551.4012.927.0846.73119SN_N_4190.6311.1222.3129.148.816.4635.65120SN_N_4200.9819.6957.8685.0120.779.6348.00.

[0135] Biomarker concentration in blood of normal control group (3) No. Sample Name LPC16 (㎍ / ml) LPC18 (㎍ / ml) 15PC (㎍ / ml) 16SM (㎍ / ml) 18SM (㎍ / ml) 24SM (㎍ / ml) 1 AJ_N_05 158.47 21.994.5990.829.9073.452 AJ_N_07 039.02 15.263.1989.54 13.4180.853 AJ_N_07 148.22 21.282.36 119.4112.46 83.234 AJ_N_07 249.53 25.033.63 109.64 10.9889.685 AJ_N_07 440.76 18.664 .4998.8811.9694.196AJ_N_07552.5417.524.4298.8314.8593.757AJ_ N_07769.0828.457.1290.089.0980.408AJ_N_07931.9113.232.84103. 509.4667.499AJ_N_08141.0415.312.9485.839.7372.8910AJ_N_08334 .1713.724.4088.759.28106.6411AJ_N_08431.2313.374.11146.3213. 81118.9212AJ_N_08546.6123.483.64119.9010.6784.0313AJ_N_0864 7.5018.682.7498.3112.0980.6614AJ_N_08846.4216.864.4672.9111. 5759.4615AJ_N_08949.5720.386.8584.7711.9167.6416AJ_N_09038.4 511.946.1193.6611.70111.1617AJ_N_09246.4421.414.04118.128.95 94.6718SN_N_07239.7317.524.53108.1910.3882.1719SN_N_07932.29 12.172.0895.817.6761.8220SN_N_08036.6212.502.9390.8312.9684. 7521SN_N_10547.7917.182.3284.2211.3782.3722SN_N_11732.2512.0 03.29131.6314.06102.1523SN_N_12126.9110.741.89131.4820.3299.4824SN_N_13034.6612.382.2492.549.9480.2225SN_N_13348.3718.533.13121.2111.37100.8726SN_N_14133.4210.593.3076.999.5666.3227SN_N_14235.1513.333.19102.3713.2578.8328SN_N_14840.7017.164.3999.7111.7277.0029SN_N_15431.1210.504.2291.7012.2980.5930SN_N_15725.358.972.3696.2211.4582.6031SN_N_15843.7817.854.4199.3214.1577.3832SN_N_16333.2811.093.10136.0916.08101.5533SN_N_17820.597.972.89105.2910.5584.1134SN_N_18244.8718.152.9999.538.2764.5035SN_N_18328.7611.443.14111.0411.6673.1136SN_N_18637.9713.072.9169.207.1558.2437SN_N_18742.9715.912.8490.9012.4083.7138SN_N_18835.8813.972.9197.4610.8278.2039SN_N_19028.1110.112.4895.5011.3576.4140SN_N_19230.689.642.8488.1911.8870.1641SN_N_19331.7412.992.7396.1610.2978.3242SN_N_19534.1312.862.84115.9611.1279.2843SN_N_19930.919.442.60101.079.6381.8544SN_N_20949.8616.913.6570.1112.9565.1145SN_N_21131.0312.313.4592.4313.5387.0946SN_N_22032.3711.842.78113.5810.8394.2247SN_N_24729.829.503.3798.1913.2975.2548SN_N_25353.5419.983.7584.7310.9983.2349SN_N_25441.6517.112.42124.8711.2893.6150SN_N_26132.0910.893.50128.1916.3789.1551SN_N_26223.386.692.4794.789.0189.7352SN_N_26335.4512.193.56109.7612.0592.8053SN_N_26937.0212.824.1379.979.7573.9654SN_N_27438.2913.923.75119.4112.58104.0655SN_N_28748.4014.893.79104.9912.1381.6956SN_N_28943.4515.073.1598.6611.9780.7157SN_N_29036.8012.033.0899.948.6283.2858SN_N_29141.3714.063.3899.469.7677.2659SN_N_29438.6611.173.33106.2811.55100.3160SN_N_29540.1315.174.0593.1213.8385.2461SN_N_29632.2811.252.2995.1010.0592.6362SN_N_30031.4612.262.16138.7315.7188.9163SN_N_30135.3110.913.07101.4910.7193.4564SN_N_30925.218.852.54109.819.0193.7765SN_N_31640.8313.722.43131.4514.2093.1366SN_N_31840.0716.402.3181.057.7671.1267SN_N_32232.208.672.63109.2811.2094.1668SN_N_32427.7512.491.87117.1313.8882.3269SN_N_32854.1522.992.8075.429.0949.7670SN_N_33132.8812.043.0679.019.0866.6171SN_N_33341.4911.344.1192.129.1673.3372SN_N_33448.1716.083.22103.3812.7275.4673SN_N_33736.0112.463.12131.1813.69102.8074SN_N_33942.8115.383.63115.628.52118.1075SN_N_34048.2515.314.62102.049.9597.7776SN_N_34123.838.322.9894.049.7973.1577SN_N_34232.6712.472.8797.598.7375.1778SN_N_34433.7412.023.6492.409.9362.9179SN_N_34534.699.082.05102.7713.7783.1680SN_N_35031.009.954.0982.6312.1978.6081SN_N_35149.7314.864.1284.9310.3478.3282SN_N_35743.4415.934.11100.869.8392.3083SN_N_36033.0710.363.1474.2610.7876.0584SN_N_36223.908.492.1779.239.2164.7385SN_N_36335.9111.834.30102.3012.0386.5586SN_N_37228.0913.274.35125.0610.4052.0987SN_N_37337.5313.103.1394.269.6282.7788SN_N_37431.9310.902.4383.158.3074.7689SN_N_37534.7113.653.4587.4210.5365.7890SN_N_37639.1814.593.65106.7412.2295.8791SN_N_37742.8217.272.1791.959.6365.3492SN_N_37840.5316.302.2394.329.5165.1993SN_N_37936.0414.853.32117.7410.98121.8194SN_N_38249.0615.063.2187.376.7577.4795SN_N_38322.709.202.02105.3710.4581.9796SN_N_38544.3017.224.76103.1112.6389.5797SN_N_38645.6115.823.0188.9811.3875.3898SN_N_38827.3911.272.85114.9111.7078.0199SN_N_39334.5912.642.5397.4010.9868.01100SN_N_39452.7419.264.2265.677.1656.12101SN_N_39846.4217.922.6793.536.7689.87102SN_N_40133.8111.052.6077.7212.3688.77103SN_N_40232.0114.172.7372.096.4278.43104SN_N_40342.6016.752.3996.687.9286.21105SN_N_40443.1916.743.43109.089.98109.20106SN_N_40535.0311.433.1691.249.7780.57107SN_N_40642.3915.742.9089.997.70102.83108SN_N_40739.5716.492.78103.258.9293.26109SN_N_40830.2410.513.2189.9510.4699.56110SN_N_40931.858.753.5883.3410.07110.54111SN_N_41132.2712.302.5067.026.0167.50112SN_N_41238.7912.252.73101.5712.1684.51113SN_N_41336.4213.642.5776.115.9666.70114SN_N_41436.8411.813.2274.938.8477.30115SN_N_41531.1710.732.8783.3110.7879.09116SN_N_41630.2910.342.3583.137.5383.40117SN_N_41735.7511.143.2161.817.9466.99118SN_N_41833.0611.532.9869.266.0768.63119SN_N_41937.5814.712.8276.508.3464.49120SN_N_42034.1014.025.1884.8013.7179.58.

[0136] 간암 환자 혈액 내 바이오마커 농도 (1)No.Sample sourceSample NameAge (year)Sex (M / F)SmokingVal(㎍ / ml)Glu(㎍ / ml)2PY (ng / ml)Trp(㎍ / ml)KN (ng / ml)1KMUHKM_C1_03153MNever Smoking29.8214.674.8713.19389.822KMUHKM_C1_03246MNever Smoking37.0110.777.558.30235.883KMUHKM_C1_03356MEx-Smoking28.0717.5914.7312.39334.914KMUHKM_C1_03472MNever Smoking28.8214.2837.047.85543.365KMUHKM_C1_03563MNever Smoking22.9513.4634.227.34367.876KMUHKM_C1_03661MEx-Smoking29.9618.976.2617.71431.007KMUHKM_C1_03774MEx-Smoking22.8111.258.1211.43317.698KMUHKM_C1_03873MEx-Smoking21.3814.014.6614.71306.619KMUHKM_C1_03946MCurrently Smoking20.5011.2910.2811.99276.4410KMUHKM_C1_04060MNever Smoking26.6812.7910.3914.62290.4511KMUHKM_C1_04165FNever Smoking34.848.6413.2710.93370.1412KMUHKM_C1_04275FNever Smoking27.2113.6330.9813.36531.6013KMUHKM_C1_04372MEx-Smoking19.6338.0117.0111.45428.7514KMUHKM_C1_04466FNever Smoking28.4122.6015.7820.19544.3715KMUHKM_C1_04553MEx-Smoking27.4013.5519.4816.51367.5616KMUHKM_C1_04672MEx-Smoking26.4514.5913.5722.43405.4617KMUHKM_C1_04759MNever Smoking31.2618.279.0216.87329.9218KMUHKM_C1_04880MCurrently Smoking25.8815.545.3813.67351.8519KMUHKM_C1_04970MEx-Smoking21.2518.3752.7311.13494.4520KMUHKM_C1_05060MNever Smoking24.7416.103.9813.76273.27.

[0137] Biomarker concentrations in the blood of liver cancer patients (2) No. Sample Name AC (㎍ / ml) HC (ng / ml) OC (ng / ml) DC (ng / ml) LAC (ng / ml) MC (ng / ml) PC (ng / ml) 1 KM_C1_03 11.39 13.89 23.89 31.18 17.27 16.34 123.50 2 KM_C1_03 21.9 113.82 19.63 28.20 14.87 12.50 81.55 3 KM_C1_03 31.25 13.29 24.43 36.62 17.02 11.33 87.45 4 KM_C1_03 41.66 39.27 29.05 38.36 16.66 12.5 038.645KM_C1_0351.8223.8820.7424.2313.9117.65107.096KM_C1_0 360.7813.6323.1038.0914.5010.3970.787KM_C1_0371.4414.9120.80 32.6917.1210.8090.698KM_C1_0380.767.0410.5115.225.575.7147. 829KM_C1_0390.949.4219.0527.1313.6411.1662.5110KM_C1_0400.95 13.2216.6424.499.1911.0484.2511KM_C1_0413.0524.8322.1825.85 26.5627.7998.9712KM_C1_0420.7012.5528.2333.719.305.8546.2913 KM_C1_0431.4324.1254.9077.6644.5529.69123.6514KM_C1_0441.17 14.3527.7738.3617.0313.93108.0715KM_C1_0451.0412.6721.2924.6 18.659.6277.2316KM_C1_0460.8012.9819.8127.339.8210.5070.821 7KM_C1_0471.229.5718.7235.0924.0618.8789.6518KM_C1_0481.6422 .0440.0078.8428.6515.5479.4719KM_C1_0492.7627.8148.0869.162 1.2713.0889.3520KM_C1_0501.5513.5214.9421.8111.3815.34115.95

[0138] Biomarker concentration in the blood of liver cancer patients (3) No. Sample Name LPC16 (㎍ / ml) LPC18 (㎍ / ml) 15PC (㎍ / ml) 16SM (㎍ / ml) 18SM (㎍ / ml) 24SM (㎍ / ml) 1 KM_C1_03 149.5213.082.2775.647.0251.582 KM_C1_03 240.5610.672.4992.1011.4097.593 KM_C1_03 341.2211.653.3374.347.0370.084 KM_C1_03 413.324.002.6264.524 .7063.165KM_C1_03519.877.012.96115.766.7699.266KM_C1_03635.8612.403.3568.815.9161.807KM_C1_03734.019.922. 8578.9610.2982.198KM_C1_03838.9313.461.9182.995.9956.419KM_C1_03935.4810.622.7586.036.5676.0110KM_C1_0402 9.0010.922.6390.076.5973.6411KM_C1_04127.236.683.7586.019.54121.1912KM_C1_04230.969.573.3490.068.6488.271 3KM_C1_04331.269.084.6594.609.06120.9014KM_C1_04450.5212.373.8284.149.8883.7315KM_C1_04544.2514.962.1873. 499.1156.9616KM_C1_04634.9613.403.2379.9310.8365.9817KM_C1_04739.7413.502.63101.739.9980.1618KM_C1_04837. 0411.303.1186.6910.60109.9519KM_C1_04938.5911.682.4470.646.4165.6620KM_C1_05048.7615.384.5578.308.5073.23

[0139] 담도암 환자 혈액 내 바이오마커 농도 (1)No.Sample sourceSample NameAge (year)Sex (M / F)SmokingVal(㎍ / ml)Glu(㎍ / ml)2PY(ng / ml)Trp(㎍ / ml)KN(ng / ml)1SNUBHSN_C2_00157MCurrently Smoking26.1812.031.1417.78312.702SNUBHSN_C2_00262MEx-Smoking35.4736.7320.5316.12388.603SNUBHSN_C2_00359MCurrently Smoking24.7820.817.2419.56740.814SNUBHSN_C2_00443FNever Smoking19.5319.718.5813.34300.115SNUBHSN_C2_00577FNever Smoking23.5217.317.5812.33208.816SNUBHSN_C2_00667FNever Smoking33.5820.182.899.62284.237SNUBHSN_C2_00776MNever Smoking17.728.830.969.44338.458SNUBHSN_C2_00876MCurrently Smoking22.6719.9828.9719.02444.629SNUBHSN_C2_00965MEx-Smoking19.279.3351.3714.24808.6810SNUBHSN_C2_01082MEx-Smoking25.8224.3323.7219.53669.9511SNUBHSN_C2_01174MCurrently Smoking30.3612.6030.5122.65577.9512SNUBHSN_C2_01258MCurrently Smoking24.2816.984.5519.42414.4213SNUBHSN_C2_01379MNever Smoking17.498.584.1814.98465.3114SNUBHSN_C2_01558MEx-Smoking25.7115.0919.0619.86543.0415SNUBHSN_C2_01663MCurrently Smoking30.7213.1513.5617.66404.2716SNUBHSN_C2_01765MNever Smoking33.5410.6013.7820.86639.0517SNUBHSN_C2_01869FNever Smoking30.8911.8711.8713.43260.1118SNUBHSN_C2_01949FNever Smoking27.8110.8121.5417.39495.3419SNUBHSN_C2_02066MCurrently Smoking33.8712.099.9621.30364.63.

[0140] Biomarker concentrations in the blood of patients with biliary tract cancer (2) No. Sample Name AC (㎍ / ml) HC (ng / ml) OC (ng / ml) DC (ng / ml) LAC (ng / ml) MC (ng / ml) PC (ng / ml) 1 SN_C2_001 1.75 40.31 82.16 141.30 41.41 14.75 64.76 2 SN_C2_002 1.58 17.05 27.5 137.94 12.27 6.04 43.04 3 SN_C2_003 1.43 15.67 29.03 43.64 21.14 11.23 58.55 4 SN_C2_004 1.21 15.18 40.28 59.2512.446.6947.795SN_C2_0051.8033.2780.34135.3838.6916.5469.146SN_C2_0061.5321.7027.8643.4019.6011.0947.657SN _C2_0071.4918.1322.9634.6116.689.0138.418SN_C2_0082.0120.1345.5470.2821.6512.7670.649SN_C2_0092.3020.2042.5155.7 917.599.7664.8310SN_C2_0100.7216.1222.3036.8517.7711.6758.0711SN_C2_0110.407.0317.6120.765.973.9439.3512SN_C2_0 120.659.4322.0538.2713.627.4946.4313SN_C2_0130.452.404.815.353.013.1522.2214SN_C2_0151.0522.5132.0047.7818.7812. 5488.2315SN_C2_0160.9916.3740.1247.7213.957.8646.8916SN_C2_0170.668.1811.3618.327.396.3939.7917SN_C2_0182.1733.1 761.3685.1527.8612.6568.1818SN_C2_0190.8117.2338.0952.4811.706.6346.0719SN_C2_0200.789.3017.2719.526.985.1534.16

[0141] Biomarker concentrations in the blood of patients with biliary tract cancer (3) No. Sample Name LPC16 (㎍ / ml) LPC18 (㎍ / ml) 15PC (㎍ / ml) 16SM (㎍ / ml) 18SM (㎍ / ml) 24SM (㎍ / ml) 1 SN_C2_001 40.59 9.723.83 110.56 12.56 96.55 2 SN_C2_002 27.97 10.133.41 102.46 7.45 120.46 3 SN_C2_003 28.766.613.71 61.65 6.149 0.524 SN_C2_004 44.90 13.242. 3494.7810.1195.965SN_C2_00540.5112.952.96138.7014.11134.706SN_C2_00617.195.593.29112.7910.32137.397SN_ C2_00713.173.402.9094.417.24100.898SN_C2_00851.9415.703.29143.7313.30127.169SN_C2_00931.3910.081.4484. 988.4776.9510SN_C2_01021.046.894.5869.936.7376.0411SN_C2_01130.527.124.2076.555.5176.0012SN_C2_01236.2 911.693.90114.3612.28117.7713SN_C2_01335.9011.643.01103.909.1680.8014SN_C2_01542.0017.098.53172.1021.2 6232.8915SN_C2_01642.9114.524.15111.479.05115.1916SN_C2_01734.6110.755.46108.577.4298.1017SN_C2_01828. 309.082.3596.2913.3690.9518SN_C2_01946.8319.254.4579.0312.8972.5519SN_C2_02035.689.062.5565.904.8062.80

[0142] 폐암 환자 혈액 내 바이오마커 농도 (1)No.Sample sourceSample NameAge (year)Sex (M / F)SmokingVal(㎍ / ml)Glu(㎍ / ml)2PY(ng / ml)Trp(㎍ / ml)KN(ng / ml)1SNUBHSN_C3_30178FNever Smoking24.616.531.7123.56247.582SNUBHSN_C3_30268MEx-Smoking23.268.760.8720.80464.343SNUBHSN_C3_30368MEx-Smoking51.1419.7626.0324.19373.844SNUBHSN_C3_30453FNever Smoking22.268.0615.7814.79314.495SNUBHSN_C3_30672MNever Smoking33.427.1311.3715.63457.406SNUBHSN_C3_30763MEx-Smoking26.4914.9411.7216.99308.187SNUBHSN_C3_30870FNever Smoking22.698.218.2314.58217.148SNUBHSN_C3_30939MCurrently Smoking30.5216.624.0615.38384.629SNUBHSN_C3_31048FNever Smoking25.778.9312.7610.49153.2710SNUBHSN_C3_31177FNever Smoking25.017.6828.1918.54329.8011SNUBHSN_C3_31271MEx-Smoking30.9611.3911.2215.32346.8412SNUBHSN_C3_31346FNever Smoking18.415.5110.4313.35189.1113SNUBHSN_C3_31477MEx-Smoking25.697.1510.8813.47351.9714SNUBHSN_C3_31556MNever Smoking24.155.446.4118.10231.9615SNUBHSN_C3_31650FNever Smoking18.053.443.355.79128.7016SNUBHSN_C3_31770FNever Smoking36.4412.4515.3023.28350.3717SNUBHSN_C3_31868FEx-Smoking30.506.410.2819.37453.8418SNUBHSN_C3_31954MEx-Smoking21.278.8321.1416.27357.2119SNUBHSN_C3_32059FNever Smoking25.085.8316.6219.44324.33.

[0143] Biomarker Concentrations in the Blood of Lung Cancer Patients (2) No. Sample Name AC (μg / ml) HC (ng / ml) OC (ng / ml) DC (ng / ml) LAC (ng / ml) MC (ng / ml) PC (ng / ml) 1 SN_C3_301 0.64 2.91 5.72 6.54 3.40 4.78 37.42 2 SN_C3_302 1.01 12.18 20.72 29.60 9.61 5.73 33.41 3 SN_C3_303 1.35 11.38 17.44 26.23 7.70 6.77 43.23 4 SN_C3_304 0.67 6.28 14.42 17.32 5.83 4.88 34.53 5 SN_C3_306 0.64 7.73 17.49 22.70 6.55 4.20 26.45 6 SN_C3_307 0.52 8.63 14.40 14.12 3.97 5.40 61.78 7 SN_C3_308 0.56 8.06 14.86 18.60 6.09 4.37 29.66 8 SN_C3_309 0.78 14.49 32.96 38.89 9.77 6..33 49.98 9 SN_C3_310 0.51 5.76 7.87 13.16 4.78 5.66 28.76 10 SN_C3_311 0.68 4.18 7.43 10.44 3.67 4.03 37.59 11 SN_C3_312 0.62 14.44 33.55 44.81 11.65 5.70 36.13 12 SN_C3_313 0.71 5.73 10.51 15.53 7.09 5.25 37.09 13 SN_C3_314 0.81 13.33 26.56 35.60 10.94 6.06 48.26 14 SN_C3_315 0.73 7.96 21.65 31.85 6.26 3.03 31.16 15 SN_C3_316 2.35 14.31 18.25 27.75 23.09 14.53 33.34 16 SN_C3_317 0.99 16.83 33.07 41.43 12.26 7.41 44.72 17 SN_C3_318 0.47 4.55 9.37 14.87 4.23 3.72 39.35 18 SN_C3_319 0.72 4.39 9.06 13.47 4.98 3.96 35.39 19 SN_C3_320 0.73 8.63 24.41 30.44 6.93 3.79 44.58

[0144] It should be noted that there seems to be a "6.." in item 8 of the translated content which might be a typo in the original. It should probably be "6.33".Biomarker Concentrations in the Blood of Lung Cancer Patients (3) No. Sample Name LPC16 (μg / ml) LPC18 (μg / ml) 15PC (μg / ml) 16SM (μg / ml) 18SM (μg / ml) 24SM (μg / ml) 1 SN_C3_301 42.64 18.52 8.36 93.07 15.98 71.16 2 SN_C3_302 14.56 4.76 2.13 53.65 6.23 49.38 3 SN_C3_303 37.95 14.02 4.83 86.37 11.87 67.83 4 SN_C3_304 38.84 14.55 6.21 84.63 10.32 60.76 5 SN_C3_306 39.52 17.52 2.98 110.13 8.37 87.66 6 SN_C3_307 43.90 15.16 4.72 69.37 7.42 61.36 7 SN_C3_308 34.00 16.06 2.87 124.62 12.75 100.54 8 SN_C3_309 42.05 17.63 3.89 101.86 14.44 68.51 9 SN_C3_310 33.86 13.88 4.64 142.53 16.53 105.95 10 SN_C3_311 51.82 16.79 5.15 113.29 10.96 99.32 11 SN_C3_312 37.22 13.05 2.96 96.50 9.16 74.59 12 SN_C3_313 38.95 14.53 2.46 121.13 13.17 82.53 13 SN_C3_314 33.67 14.49 3.31 116.39 10.74 138.47 14 SN_C3_315 48.38 18.65 3.46 102.34 9.98 80.36 15 SN_C3_316 34.86 15.45 2.72 143.49 13.55 103.35 16 SN_C3_317 36.32 12.82 2.75 132.39 13.25 104.74 17 SN_C3_318 51.15 19.80 3.12 129.58 13.01 108.40 18 SN_C3_319 27.71 11.99 2.16 145.95 11.65 101.49 19 SN_C3_320 51.30 22.56 5.72 82.19 14.56 65.50

[0145] 췌장암 환자 혈액 내 바이오마커 농도 (1)No.Sample sourceSample NameAge (year)Sex (M / F)SmokingVal(㎍ / ml)Glu(㎍ / ml)2PY(ng / ml)Trp(㎍ / ml)KN(ng / ml)1SNUBHSN_C4_12177FNever Smoking25.045.6424.7118.63297.842SNUBHSN_C4_12255MCurrently Smoking35.6719.072.9614.92316.353SNUBHSN_C4_12370MCurrently Smoking26.888.9212.7015.82478.914SNUBHSN_C4_12472FNever Smoking23.029.4332.1512.20517.085SNUBHSN_C4_12573FNever Smoking17.058.4620.5912.55446.196SNUBHSN_C4_12662MEx-Smoking29.7014.2713.0315.52250.837SNUBHSN_C4_12861MNever Smoking21.255.8211.9715.83362.968SNUBHSN_C4_12981MEx-Smoking21.7611.0133.7912.85461.369SNUBHSN_C4_13062FNever Smoking19.387.7328.1312.24351.8210SNUBHSN_C4_13148FNever Smoking26.968.648.4018.39329.2811SNUBHSN_C4_13279FNever Smoking23.887.0822.6812.96411.6012SNUBHSN_C4_13361MNever Smoking18.376.479.5215.01413.4213SNUBHSN_C4_13469FNever Smoking18.0722.6221.379.83285.1414SNUBHSN_C4_13563MNever Smoking37.6612.2225.8215.51291.1015SNUBHSN_C4_13681FNever Smoking15.9911.3722.929.55709.1916SNUBHSN_C4_13765MNever Smoking21.026.381.9013.47254.3817SNUBHSN_C4_13877FNever Smoking22.4616.400.7611.17321.5318SNUBHSN_C4_13976FNever Smoking19.0711.1211.9614.06276.2519SNUBHSN_C4_14077MNever Smoking27.627.474.0614.69279.66.

[0146] 췌장암 환자 혈액 내 바이오마커 농도 (2)No.Sample NameAC(㎍ / ml)HC(ng / ml)OC(ng / ml)DC(ng / ml)LAC(ng / ml)MC(ng / ml)PC(ng / ml)1SN_C4_1210.476.618.0610.095.386.6155.362SN_C4_1221.2814.2416.0721.879.777.3450.503SN_C4_1231.2518.2247.9480.5126.8810.6753.544SN_C4_1241.3724.1446.0967.0722.4811.8255.525SN_C4_1251.1512.1923.5734.7413.217.6643.496SN_C4_1260.6210.0113.1115.975.104.9643.527SN_C4_1280.9714.2450.9677.4318.069.3850.308SN_C4_1292.4516.8728.7640.6521.1313.9356.269SN_C4_1301.4910.2717.9225.888.524.6730.3010SN_C4_1311.0221.5170.43104.6822.0310.4658.2611SN_C4_1323.3516.0219.2828.2015.7311.1863.5412SN_C4_1330.7412.7717.3227.7517.6913.5852.9513SN_C4_1341.0416.2028.1537.9913.657.9940.2514SN_C4_1351.8710.6312.2417.509.257.2452.8615SN_C4_1361.8930.88121.88185.5159.6224.2595.6216SN_C4_1372.4520.4540.4155.3818.6413.7263.3217SN_C4_1382.0212.7322.9931.8512.156.8533.2418SN_C4_1392.0021.5735.3844.0713.209.6358.4919SN_C4_1401.0712.5022.4431.3611.827.6738.20

[0147] 개장안 동이트 내 배마이 concentration (3)No.Sample NameLPC16(㎍ / ml)LPC18(㎍ / ml)15PC(㎍ / ml)16SM(㎍ / ml)18SM(㎍ / ml)24SM(㎍ / ml)1SN_C4_12151.0413.746.2292.039.6760 .582SN_C4_12233.7711.512.1594.168.7171.823SN_C4_12337.1613.932.1095.137.7590.254SN_C4_12420.857.942.1 080.816.8672.615SN_C4_12532.9713.693.61112.2811.8986.316SN_C4_12646.7714.733.2698.957.81103.397SN_C4_12830.8311.843.55102.516.83105.078SN_C4_12919.296.172.42107.747.4099.489SN_C4_13013.485.121.9679.647. 7978.0710SN_C4_13147.6416.873.42110.4420.61118.8611SN_C4_13223.475.212.2478.8812.0686.8512SN_C4_13312 .444.6111.8645.748.56141.5913SN_C4_13416.975.3713.1467.3513.35208.5114SN_C4_13525.726.742.6899.1710.4 892.3115SN_C4_13627.737.782.52108.5610.25107.5316SN_C4_13733.848.102.09112.3012.0198.3517SN_C4_13815.145.523.2074.6612.7184.0918SN_C4_13933.008.853.5874.8010.6490.9019SN_C4_14021.186.173.5262.756.8463.75

[0148] 위암 환자 혈액 내 바이오마커 농도 (1)No.Sample sourceSample NameAge (year)Sex (M / F)SmokingVal(㎍ / ml)Glu(㎍ / ml)2PY(ng / ml)Trp(㎍ / ml)KN(ng / ml)1ASMCSAS_C6_02152MNever Smoking39.5716.134.1116.27282.832ASMCSAS_C6_02251MEx-Smoking32.8316.862.3614.96268.993ASMCSAS_C6_02362FNever Smoking25.1615.745.9911.79213.054ASMCSAS_C6_02467MNever Smoking38.7115.145.9913.80211.925ASMCSAS_C6_02578MEx-Smoking30.0113.152.2620.39285.316ASMCSAS_C6_02669MEx-Smoking27.9019.556.1618.04358.027ASMCSAS_C6_02856MCurrently Smoking28.6911.235.4915.58271.448ASMCSAS_C6_02965MEx-Smoking31.4817.0412.1714.94430.299ASMCSAS_C6_03045MCurrently Smoking33.9018.081.9713.08224.3810ASMCSAS_C6_03164FNever Smoking37.1419.692.4310.51214.6511ASMCSAS_C6_03262MEx-Smoking27.1113.169.9614.90251.8312ASMCSAS_C6_03378MEx-Smoking22.7513.625.9911.15279.2713ASMCSAS_C6_03452MEx-Smoking38.6820.348.9412.24209.5914ASMCSAS_C6_03571MEx-Smoking28.6313.9411.4012.64321.9815ASMCSAS_C6_03649MCurrently Smoking31.4814.8813.0517.55229.7516ASMCSAS_C6_03764MNever Smoking33.9615.7314.9916.04283.5817ASMCSAS_C6_03857MEx-Smoking25.2112.477.9911.14211.6718ASMCSAS_C6_03973MNever Smoking26.0314.544.0113.58277.4619ASMCSAS_C6_04067MEx-Smoking28.2124.9126.4814.41242.62.

[0149] 위안 타이트 나이 내마마이 concentration (2)No.Sample NameAC(㎍ / ml)HC(ng / ml)OC(ng / ml)DC(ng / ml)LAC(ng / ml)MC(ng / ml)PC(ng / ml)1AS_C6_0210.5712.4220.8119.715.296.0829. 432AS_C6_0220.9814.2824.0140.518.098.4648.683AS_C6_0231.8813.6628.5339.7110.046.0464.664AS_C6_0240.644.886.6 57.162.183.4035.355AS_C6_0250.686.1811.1113.386.614.6349.306AS_C6_0260.758.0710.6926.266.115.9072.047AS_C6_ 0280.453.127.908.534.284.4639.498AS_C6_0290.816.5110.0613.604.886.5440.869AS_C6_0300.6710.9916.1632.6010.741 0.7274.8810AS_C6_0311.149.357.2714.397.698.3446.8611AS_C6_0320.598.5711.1515.906.994.2430.9412AS_C6_0330.64 4.787.738.144.495.1346.0213AS_C6_0340.876.8712.2326.935.939.1963.3014AS_C6_0350.879.0314.7120.987.027.2160.8 815AS_C6_0360.665.9812.7020.566.156.6146.9516AS_C6_0370.8213.7320.0526.916.838.4144.9617AS_C6_0381.5715.392 9.8432.538.376.6154.5718AS_C6_0391.2013.3828.6625.778.296.6736.8719AS_C6_0400.6710.3219.7525.286.807.7557.58

[0150] 위안 타이트 나다 내 바마지 concentration (3)No.Sample NameLPC16(㎍ / ml)LPC18(㎍ / ml)15PC(㎍ / ml)16SM(㎍ / ml)18SM(㎍ / ml)24SM(㎍ / ml)1AS_C6_02145.8715.843.0586.385.045 5.132AS_C6_02229.7711.232.6977.995.1867.583AS_C6_02346.0918.161.88120.0915.4277.884AS_C6_02444.5615. 663.7474.336.0754.705AS_C6_02547.7315.394.1282.207.4680.466AS_C6_02646.8513.552.7469.057.1067.697AS_ C6_02838.9612.972.3976.066.4570.178AS_C6_02939.3212.412.4157.454.6047.239AS_C6_03060.2721.132.97100.8 69.9784.8210AS_C6_03140.8513.783.5255.416.8045.7811AS_C6_03248.5521.072.6092.236.1178.3112AS_C6_0334 7.5716.023.5367.654.6659.1413AS_C6_03466.4316.283.3557.667.0651.4014AS_C6_03538.2713.632.7483.497.03 68.1615AS_C6_03653.8017.823.4482.727.2462.2316AS_C6_03750.4917.252.8571.356.5255.5017AS_C6_03841.451 4.031.8089.7810.1884.9018AS_C6_03945.0217.401.9577.826.4261.5819AS_C6_04044.5315.812.3574.795.7365.02

[0151] 대장암 환자 혈액 내 바이오마커 농도 (1)No.Sample sourceSample NameAge (year)Sex (M / F)SmokingVal(㎍ / ml)Glu(㎍ / ml)2PY(ng / ml)Trp(㎍ / ml)KN(ng / ml)1ASMCSAS_C7_01161FNever Smoking15.8415.696.8714.80225.382ASMCSAS_C7_01267FNever Smoking17.348.4018.049.79250.343ASMCSAS_C7_01362FNever Smoking16.446.6115.9215.93330.334ASMCSAS_C7_01465MNever Smoking23.5811.888.8215.35262.845ASMCSAS_C7_01559MCurrently Smoking20.8114.045.3119.47358.416ASMCSAS_C7_01647FNever Smoking21.616.578.7713.23233.017ASMCSAS_C7_01771FNever Smoking27.9014.445.9018.95241.368ASMCSAS_C7_01864FNever Smoking21.2510.545.0313.24245.689ASMCSAS_C7_01957FNever Smoking16.639.814.539.54205.1310ASMCSAS_C7_02073FNever Smoking20.7310.164.1013.51336.5011ASMCSAS_C8_01174FNever Smoking16.0410.641.4813.62255.0712ASMCSAS_C8_01250FNever Smoking16.786.930.9814.05218.0913ASMCSAS_C8_01366FNever Smoking46.6216.781.3524.89188.2814ASMCSAS_C8_01545FNever Smoking17.909.406.4013.69200.7615ASMCSAS_C8_01674MEx-Smoking29.6816.455.1419.92333.7516ASMCSAS_C8_01767MEx-Smoking26.9516.805.7611.73294.9517ASMCSAS_C8_01869MNever Smoking23.5113.236.0316.13333.1618ASMCSAS_C8_01951FNever Smoking25.1212.092.7515.89255.8819ASMCSAS_C8_02052MNever Smoking21.9413.207.4218.11386.21.

[0152] Biomarker concentrations in the blood of patients with colon cancer (2) No. Sample Name AC (㎍ / ml) HC (ng / ml) OC (ng / ml) DC (ng / ml) LAC (ng / ml) MC (ng / ml) PC (ng / ml) 1AS_C7_0110.848.8617.2916.936.845.9469.062AS_C7_0121.2314.8036.7460.2113.205.4061.033AS_C7_0131.7018.7436.6765.2926.2212.3058.294AS_C7_0141.3017.5428.0145. 6614.118.9663.475AS_C7_0150.8816.2439.9379.6213.887.3649.136AS_C7_0161.2822.3696.94114.8225.9810.0262.947AS_C7_ 0170.9715.8028.9140.5528.2710.1062.838AS_C7_0180.739.4719.9818.477.905.0837.099AS_C7_0191.8720.7154.83122.2020. 8610.8049.8510AS_C7_0201.2219.0537.3745.9611.726.5960.6411AS_C8_0110.545.105.9713.776.714.3638.3212AS_C8_0121.5 016.9937.6341.4411.285.6457.5613AS_C8_0130.735.907.7011.653.496.1745.4714AS_C8_0151.009.4320.1326.359.176.2342. 4015AS_C8_0160.7511.5327.3047.0313.275.7950.7216AS_C8_0171.1519.1430.0838.2916.229.6949.5117AS_C8_0180.9012.892 3.5328.0712.567.5653.2118AS_C8_0191.1715.0420.9834.9910.685.3434.4919AS_C8_0201.2212.2225.7945.4317.757.3365.55

[0153] Biomarker concentration in the blood of patients with colon cancer (3) No. Sample Name LPC16 (㎍ / ml) LPC18 (㎍ / ml) 15PC (㎍ / ml) 16SM (㎍ / ml) 18SM (㎍ / ml) 24SM (㎍ / ml) 1AS_C7_01142.1112.413.0788.0110.6287.182AS_C7_01232.669.842.3378.987.2062.353AS_C7_01328.029.362.9598.6213.5783.364AS_C7_01442.0216.043 .92105.3110.1073.445AS_C7_01534.6810.162.6963.934.5748.786AS_C7_01626.148.472.0392.2612.1577.587AS_C7 _01755.0121.955.0291.8511.8263.578AS_C7_01832.0115.091.5491.799.3559.699AS_C7_01941.8512.272.8293.721 3.4581.9210AS_C7_02036.6810.992.2259.499.6850.2611AS_C8_01140.2613.763.1887.9011.0884.2012AS_C8_0123 1.9111.002.2583.469.5471.3713AS_C8_01342.8515.066.4780.4112.7757.8614AS_C8_01532.8710.312.5592.179.16 79.4915AS_C8_01644.5814.423.5187.968.1068.4216AS_C8_01737.4011.683.2475.977.6662.9317AS_C8_01843.1313 .334.1794.509.8180.9718AS_C8_01931.2016.452.83102.618.8383.2019AS_C8_02028.6710.552.1295.4613.0869.36

[0154] 유방암 환자 혈액 내 바이오마커 농도 (1)No.Sample sourceSample NameAge (year)Sex (M / F)SmokingVal(㎍ / ml)Glu(㎍ / ml)2PY(ng / ml)Trp(㎍ / ml)KN(ng / ml)1ASMCSAS_C9_00150FNever Smoking18.887.046.199.52189.942ASMCSAS_C9_00257FNever Smoking22.097.154.929.50215.933ASMCSAS_C9_00352FNever Smoking23.908.168.9112.73231.254ASMCSAS_C9_00448FNever Smoking19.208.670.709.47140.845ASMCSAS_C9_00580FNever Smoking22.0511.3417.1812.22303.526ASMCSAS_C9_00676FNever Smoking19.068.2316.4211.48336.217ASMCSAS_C9_00765FNever Smoking17.689.4010.5712.80283.428ASMCSAS_C9_00856FNever Smoking21.205.9814.3312.18199.809ASMCSAS_C9_00951FNever Smoking23.115.984.658.2499.7410ASMCSAS_C9_01047FNever Smoking19.909.4814.2911.08165.1011ASMCSAS_C9_01158FNever Smoking21.868.095.5012.91303.6112ASMCSAS_C9_01246FNever Smoking18.147.2020.4810.79156.1213ASMCSAS_C9_01347FNever Smoking20.257.325.6215.56173.5714ASMCSAS_C9_01451FNever Smoking22.6813.590.7813.71246.3915ASMCSAS_C9_01554FNever Smoking18.947.430.9510.24146.6416ASMCSAS_C9_01669FNever Smoking23.136.1610.6313.16222.6417ASMCSAS_C9_01759FNever Smoking27.9712.286.5613.95211.7618ASMCSAS_C9_01852FNever Smoking22.6310.376.8712.73166.7719ASMCSAS_C9_01959FEx-Smoking19.428.526.5011.40166.2820ASMCSAS_C9_02045FNever Smoking18.648.6614.269.60343.05.

[0155] Biomarker concentrations in the blood of breast cancer patients (2) No. Sample Name AC (㎍ / ml) HC (ng / ml) OC (ng / ml) DC (ng / ml) LAC (ng / ml) MC (ng / ml) PC (ng / ml) 1AS_C9_0010.56 11.39 11.67 16.75 4.42 2.54 26.67 2AS_C9_0021.31 10.24 11.32 16.018.84 6.29 34.62 3AS_C9_0030.88 7.87 14.23 17.895.893.69 27.034AS_C9_0040.87 10.46 16.92 19.95 5.16 3.6 932.895AS_C9_0051.0616.0927.5837.528.045.4836.306AS_C9_0060.8512.1330.6229.0610.056.2329.607AS_C9_0070.488.7116.36 19.204.093.1834.848AS_C9_0080.8711.7013.4617.095.602.7434.359AS_C9_0091.3314.1227.5426.679.596.4038.0110AS_C9_0100 .709.0912.3219.145.233.3728.1711AS_C9_0111.3515.6821.3026.458.565.4532.9312AS_C9_0120.778.1010.0416.897.955.7353.8 313AS_C9_0131.1010.1715.7217.465.114.5436.1514AS_C9_0140.696.066.5612.463.322.9432.1315AS_C9_0151.5112.1613.8221.9 36.204.5428.9416AS_C9_0161.8316.3229.4831.9710.726.6442.5217AS_C9_0170.9910.7218.8326.888.506.4442.9718AS_C9_0181. 088.8114.7121.567.334.1732.2419AS_C9_0190.9511.2412.6917.618.685.8442.0820AS_C9_0201.489.7311.5117.267.686.5335.38

[0156] Biomarker concentrations in the blood of breast cancer patients (3) No. Sample Name LPC16 (㎍ / ml) LPC18 (㎍ / ml) 15PC (㎍ / ml) 16SM (㎍ / ml) 18SM (㎍ / ml) 24SM (㎍ / ml) 1AS_C9_001 23.369.422.3292.099.4268.90 2AS_C9_002 15.355.352.1984.0811.4363.27 3AS_C9_003 29.64 11.971.9981.497.0848.064AS_C9_004 29.73 12.251.9667.85 7.4352.275AS_C9_00531.2110.742.9456.047.0853.846AS_C9_00626.647.232.7246.067.3238.797AS_C9_00731.7113.65 1.9683.177.7766.328AS_C9_00836.2215.463.0284.069.8552.179AS_C9_00922.368.433.1391.5910.9774.2410AS_C9_010 27.7611.842.0691.629.6564.7111AS_C9_01125.419.702.1780.446.2467.6012AS_C9_01230.6511.134.1295.489.5267.4 313AS_C9_01323.638.962.7185.478.9154.1214AS_C9_01435.0310.923.0066.828.3963.9315AS_C9_01526.8610.852.617 9.508.3063.5616AS_C9_01629.2013.572.82103.688.7270.5217AS_C9_01729.529.882.8265.068.6756.8218AS_C9_01828 .2010.823.8880.3912.0254.0719AS_C9_01926.289.073.3473.7910.6767.4920AS_C9_02021.198.101.74102.016.9366.95

[0157] 자궁경부암 환자 혈액 내 바이오마커 농도 (1)No.Sample sourceSample NameAge (year)Sex (M / F)SmokingVal(㎍ / ml)Glu(㎍ / ml)2PY(ng / ml)Trp(㎍ / ml)KN(ng / ml)1ASMCSAS_C10_00147FNever Smoking16.7912.212.2314.46181.592ASMCSAS_C10_00255FNever Smoking20.408.015.3412.77251.093ASMCSAS_C10_00357FNever Smoking14.9110.193.369.77170.704ASMCSAS_C10_00453FNever Smoking22.0011.246.1310.62194.955ASMCSAS_C10_00554FNever Smoking14.579.491.789.40198.926ASMCSAS_C10_00652FNever Smoking19.468.719.6211.06313.617ASMCSAS_C10_00764FNever Smoking20.4812.284.6612.57231.598ASMCSAS_C10_00855FNever Smoking20.589.405.3412.18204.629ASMCSAS_C10_00953FNever Smoking15.599.683.2511.85156.2210ASMCSAS_C10_01069FNever Smoking23.3816.386.0511.20208.1711ASMCSAS_C10_02145FNever Smoking18.0510.097.4811.79138.1912ASMCSAS_C10_02262FNever Smoking16.037.180.659.31118.2913ASMCSAS_C10_02358FNever Smoking17.2610.759.8711.31145.0714ASMCSAS_C10_02446FNever Smoking19.5112.007.409.55209.2515ASMCSAS_C10_02546FNever Smoking20.897.346.8713.16224.1816ASMCSAS_C10_02659FNever Smoking21.179.2810.7911.23185.4317ASMCSAS_C10_02748FNever Smoking16.1610.0212.309.63158.2718ASMCSAS_C10_02862FNever Smoking21.449.651.4911.38157.2819ASMCSAS_C10_02960FNever Smoking18.4212.635.3412.64247.0820ASMCSAS_C10_03056FNever Smoking18.4910.705.8411.99227.18.

[0158] Biomarker concentrations in the blood of patients with cervical cancer (2) No. Sample Name AC (㎍ / ml) HC (ng / ml) OC (ng / ml) DC (ng / ml) LAC (ng / ml) MC (ng / ml) PC (ng / ml) 1AS_C10_001 1.30 8.93 12.67 24.77 10.62 10.95 76.132AS_C10_002 0.68 8.60 15.96 19.58 6.88 5.42 48.493AS_C10_003 1.53 11.76 21.77 27.19 11.316.58 59.624AS_C10_004 1.29 13.96 24.74 30.71 11.86 11.3367.745AS_C10_0050.777.7310.3117.714.554.2436.266AS_C10_0061.3915.0224.5149.3112.598.6249.307AS_C10_0070.706.481 1.4720.116.375.4938.558AS_C10_0081.2113.3516.9129.838.514.5544.629AS_C10_0090.798.4211.7819.978.414.1937.9510AS_C10_ 0100.8010.8716.4218.036.775.6047.8411AS_C10_0210.826.468.6712.504.026.3449.8912AS_C10_0221.666.969.6414.586.287.5751 .5713AS_C10_0231.047.8217.4519.387.557.8251.8714AS_C10_0241.249.3315.5612.065.165.9243.8415AS_C10_0251.078.5221.1725 .107.256.3636.6316AS_C10_0261.075.7711.0612.304.074.1934.7517AS_C10_0271.607.8914.5513.127.638.0145.4318AS_C10_0280. 909.2514.7118.448.995.9642.8219AS_C10_0291.8111.6823.2529.925.543.9538.5620AS_C10_0300.967.6014.2220.448.996.8548.98

[0159] Biomarker concentration in the blood of cervical cancer patients (3) No. Sample Name LPC16 (㎍ / ml) LPC18 (㎍ / ml) 15PC (㎍ / ml) 16SM (㎍ / ml) 18SM (㎍ / ml) 24SM (㎍ / ml) 1AS_C10_001 35.56 12.112.63 70.399.2154.312 AS_C10_002 37.06 13.863.74 71.277.35 45.793 AS_C10_003 33.87 12.873.03 91.089.85 79.264 AS_C10_004 49.37 20.05 3.62 78.75 13. 0774.285AS_C10_00533.3110.742.6774.688.4752.796AS_C10_00631.8312.263.5591.6118.3669.237AS_C10_00737.7012.922 .4693.3410.2871.908AS_C10_00837.3612.392.43102.2413.6389.849AS_C10_00936.6413.064.0975.449.0867.6710AS_C10_0 1041.0916.944.2564.8611.1355.8711AS_C10_02132.6812.293.6390.857.8875.4012AS_C10_02225.846.862.5188.0513.1270 .0513AS_C10_02340.3616.012.8683.838.5167.0314AS_C10_02425.619.803.6599.6311.6679.6715AS_C10_02525.079.102.57 69.207.6853.8916AS_C10_02630.5612.802.6074.6311.6861.9517AS_C10_02728.119.402.2294.3111.4672.3718AS_C10_0283 0.4011.894.4972.2310.3767.1019AS_C10_02933.9311.343.0770.308.4573.1420AS_C10_03027.0610.723.0379.3711.0855.74

[0160]

[0161] As a result, as shown in FIGS. 1 to 9 and Tables 1 to 27, the blood concentrations of 2PY, HC, OC, DC, and LAC were confirmed to be decreased in all cancers compared to the normal control group.

[0162] In addition, compared to the normal control group, Val was found to have increased blood concentrations in liver, lung, pancreatic, and stomach cancer; Glu was found to have increased blood concentrations in liver, biliary tract, lung, pancreatic, stomach, colon, and cervical cancer; Trp was found to have increased blood concentrations in biliary tract and lung cancer; KN was found to have increased blood concentrations in liver, biliary tract, and pancreatic cancer; AC was found to have increased blood concentrations in liver and pancreatic cancer; LPC16 and LPC18 were found to have increased blood concentrations in lung and stomach cancer; 15PC and 24SM were found to have increased blood concentrations in biliary tract, lung, and pancreatic cancer; 16SM was found to have increased blood concentrations in biliary tract and lung cancer; and 18SM was found to have increased blood concentrations in lung cancer.

[0163]

[0164] Example 2: Verification of the ability of a cancer screening algorithm using metabolite biomarkers for multiple cancer diagnosis to distinguish between non-cancer and cancer patient groups.

[0165] 2-1: 5 types of biomarkers

[0166] In the present invention, a prediction model capable of diagnosing the occurrence of cancer was developed by applying a support vector machine algorithm that uses a radial basis function as a kernel to quantitative values ​​of five biomarkers, consisting of kynurenine (KN), octanoylcarnitine (OC), decanoylcarnitine (DC), N-methyl-2-pyridone-5-carboxamide (2PY), and 24:1 SM (24SM), among the 18 biomarkers selected in the above <Example 1>.

[0167] A cancer incidence prediction model was trained by using a kernel function represented by the following mathematical formula 1 and tuning the algorithm parameters.

[0168]

[0169] [Mathematical Formula 1]

[0170]

[0171] x: Blood level measurement of a biomarker composition for multiple cancer diagnosis

[0172] γ: parameter for the flexibility (curvature) of the decision boundary

[0173]

[0174] The parameter γ in Equation 1 determines the extent of influence a single training sample has, while another parameter, C, determines the degree to which training samples are misclassified. Since both parameters can lead to underfitting or overfitting of the learning model depending on their values, the optimal parameters were selected through repeated cross-validation.

[0175]

[0176] Confirmation of the ability of a cancer screening algorithm using five biomarkers to distinguish between non-cancer and cancer patients TRUEcancer(8 cancers) controlPredictedcancer(8 cancers) 1431689.94% PPV control 1210489.66% NPV 92.26% Sensitivity 86.67% Specificity 89.82% Accuracy

[0177] As a result of confirming the cancer diagnostic ability including 8 types of cancer using the developed prediction model, as shown in Table 28 above, it was confirmed that the cancer diagnostic ability was excellent with a sensitivity of 92.26%, a specificity of 86.67%, a negative predictive value (NPV) of 89.66%, a positive predictive value (PPV) of 89.94%, and an accuracy of 89.82%. In addition, as a result of measuring the diagnostic accuracy using the ROC curve, it was confirmed that the cancer diagnostic ability was statistically highly significant with an AUC value of 0.943 (Fig. 10).

[0178]

[0179] 2-2: 10 types of biomarkers

[0180] In the present invention, a prediction model capable of diagnosing the occurrence of cancer was developed using 10 markers consisting of kynurenine (KN), octanoylcarnitine (OC), decanoylcarnitine (DC), lauroylcarnitine (LAC), valine (Val), glutamate (Glu), tryptophan (Trp), N-methyl-2-pyridone-5-carboxamide (2PY), 15:0-18:1 PC (15PC), and 24:1 SM (24SM) among the 18 biomarkers selected in the above <Example 1>.

[0181] A prediction model was developed using the same method as in the above <Example 2-1>, and a cancer incidence prediction model was trained by using the kernel function represented by the above mathematical formula 1 and tuning the algorithm parameters.

[0182]

[0183] Confirmation of the ability of a cancer screening algorithm using 10 biomarkers to distinguish between non-cancer and cancer patient groups. TRUEcancer(8 cancers) controlPredictedcancer(8 cancers) 1461789.57% PPV control910391.96% NPV94.19% Sensitivity85.83% Specificity90.55% Accuracy

[0184] As a result of confirming the cancer diagnostic ability including 8 types of cancer using the developed prediction model, as shown in Table 29 above, it was confirmed that the cancer diagnostic ability was excellent with a sensitivity of 94.19%, a specificity of 85.83%, a negative predictive value (NPV) of 91.96%, a positive predictive value (PPV) of 89.96%, and an accuracy of 90.55%. In addition, as a result of measuring the diagnostic accuracy using the ROC curve, it was confirmed that the cancer diagnostic ability was statistically highly significant with an AUC value of 0.971 (Fig. 11A).

[0185]

[0186] 2-3: 18 biomarkers

[0187] In the present invention, a prediction model capable of diagnosing the occurrence of cancer was developed by applying a support vector machine algorithm that uses a radial basis function as a kernel to the quantitative values ​​of 18 biomarkers selected in the above <Example 1>.

[0188] A prediction model was developed using the same method as in the above <Example 2-1>, and a cancer incidence prediction model was trained by using the kernel function represented by the above mathematical formula 1 and tuning the algorithm parameters.

[0189]

[0190] Confirmation of the ability of a cancer screening algorithm using 18 biomarkers to distinguish between non-cancer and cancer patient groups. TRUEcancer(8 cancers) controlPredictedcancer(8 cancers) 148596.73% PPV control711594.26% NPV95.48% Sensitivity95.83% Specificity95.64% Accuracy

[0191] As a result of confirming the cancer diagnostic ability including 8 types of cancer using the developed prediction model, as shown in Table 30 above, it was confirmed that the cancer diagnostic ability was excellent with a sensitivity of 95.48%, a specificity of 95.83%, a negative predictive value (NPV) of 94.26%, a positive predictive value (PPV) of 96.73%, and an accuracy of 95.64%. In addition, as a result of measuring the diagnostic accuracy using the ROC curve, it was confirmed that the cancer diagnostic ability was statistically highly significant with an AUC value of 0.987 (Fig. 12A).

[0192] That is, it was confirmed that the artificial intelligence-based multiple cancer diagnosis method using the biomarker of the present invention can clearly diagnose or distinguish multiple cancers and non-cancer groups.

[0193]

[0194] Example 3: Verification of the ability of a multi-cancer screening algorithm using metabolite biomarkers for multiple cancer diagnosis to discriminate between cancer patient groups.

[0195] The support vector machine algorithm is used to classify two groups as in the above <Example 2>, but it can also be applied when constructing a model for classifying three or more groups. Therefore, in the present invention, a prediction model capable of diagnosing various cancers was developed by applying the support vector machine algorithm that uses a radial basis function as a kernel to quantitative values ​​for 18 types of biomarkers.

[0196]

[0197] 3-1: 10 types of biomarkers

[0198] The ability of the multiple cancer screening algorithm to discriminate between cancer patient groups was confirmed using the 10 types of biomarkers of the above <Example 2-2>.

[0199]

[0200] Verification of the ability of a multi-cancer screening algorithm using 10 biomarkers to discriminate between cancer patient groups. Cancer type diagnostic ability Control specificity 100.00% Liver cancer sensitivity 70.00% Biliary tract cancer 73.68% Lung cancer 84.21% Pancreatic cancer 42.11% Stomach cancer 89.47% Colorectal cancer 63.16% Breast cancer 85.00% Cervical cancer 80.00%

[0201] As a result of confirming the cancer diagnostic ability for each cancer using the prediction model developed using 10 types of biomarkers, it was confirmed that the cancer diagnostic ability was the same as in Table 31 and Figure 11B, and in particular, it was confirmed that it showed high diagnostic ability for lung cancer, stomach cancer, breast cancer, and cervical cancer.

[0202]

[0203] 3-2: 18 biomarkers

[0204] The ability of the multiple cancer screening algorithm to discriminate between cancer patient groups was confirmed using the 18 biomarkers of the above <Example 2-3>.

[0205]

[0206] Verification of the ability of multiple cancer screening algorithms to discriminate cancer patient groups. Cancer type diagnostic ability. Control specificity 100.00%. Liver cancer sensitivity 90.00%. Biliary tract cancer 73.68%. Lung cancer 78.95%. Pancreatic cancer 52.63%. Stomach cancer 100.00%. Colorectal cancer 78.95%. Breast cancer 95.00%. Cervical cancer 85.00%.

[0207] As a result of confirming the cancer diagnostic ability for each cancer using the prediction model developed using 18 types of biomarkers, it was confirmed that it showed cancer diagnostic ability as shown in Table 32 and Figure 12B, and in particular, it was confirmed that it showed high diagnostic ability for liver cancer, stomach cancer, breast cancer, and cervical cancer.

[0208]

[0209] Combining the metabolic biomarkers of the present invention can significantly enhance diagnostic capabilities for various cancers, enabling clear diagnosis or differentiation of cancer occurrence or cancer versus non-cancer groups. In particular, the biomarkers of the present invention can be useful for diagnosing multiple cancers and determining prognosis, as they can provide a pan-cancer diagnostic method capable of determining multiple cancer types in a single test.

Claims

1. Valine (Val), Glutamate (Glu), N-methyl-2-pyridone-5-carboxamide (2PY), Tryptophan (Trp), Kynurenine (KN), Acetylcarnitine (AC), Hexanoylcarnitine (HC), Octanoylcarnitine (OC), Decanoylcarnitine (DC), Lauroylcarnitine (LAC), Myristoylcarnitine (MC), Palmitoylcarnitine (PC), 16:0 Lyso PC (1-hexadecanoyl-sn-glycero-3-phosphocholine; A biomarker composition for diagnosing multiple cancers, comprising or comprising LPC16), 18:0 Lyso PC (1-octadecanoyl-sn-glycero-3-phosphocholine; LPC18), 15:0-18:1 PC (1-pentadecanoyl-2-oleoyl-sn-glycero-3-phosphocholine; 15PC), 16:0 SM (N-palmitoyl-D-erythro-sphingosylphosphorylcholine, 16SM), 18:1 SM (N-oleoyl-D-erythro-sphingosylphosphorylcholine; 18SM), and 24:1 SM (N-nervonoyl-D-erythro-sphingosylphosphorylcholine; 24SM).

2. Valine (Val), Glutamate (Glu), N-methyl-2-pyridone-5-carboxamide (2PY), Tryptophan (Trp), Kynurenine (KN), Acetylcarnitine (AC), Hexanoylcarnitine (HC), Octanoylcarnitine (OC), Decanoylcarnitine (DC), Lauroylcarnitine (LAC), Myristoylcarnitine (MC), Palmitoylcarnitine (PC), 16:0 Lyso PC (1-hexadecanoyl-sn-glycero-3-phosphocholine; A biomarker composition for diagnosing multiple cancers, comprising at least five biomarkers selected from the group consisting of LPC16), 18:0 Lyso PC (1-octadecanoyl-sn-glycero-3-phosphocholine; LPC18), 15:0-18:1 PC (1-pentadecanoyl-2-oleoyl-sn-glycero-3-phosphocholine; 15PC), 16:0 SM (N-palmitoyl-D-erythro-sphingosylphosphorylcholine, 16SM), 18:1 SM (N-oleoyl-D-erythro-sphingosylphosphorylcholine; 18SM), and 24:1 SM (N-nervonoyl-D-erythro-sphingosylphosphorylcholine; 24SM).

3. In paragraph 1, The above 5 or more biomarkers Contains kynurenine (KN), octanoylcarnitine (OC), decanoylcarnitine (DC), N-methyl-2-pyridone-5-carboxamide (2PY), and 24:1 SM (24SM), or A biomarker composition for diagnosing multiple cancers, characterized by comprising kynurenine (KN), octanoylcarnitine (OC), decanoylcarnitine (DC), lauroylcarnitine (LAC), valine (Val), glutamate (Glu), tryptophan (Trp), N-methyl-2-pyridone-5-carboxamide (2PY), 15:0-18:1 PC (15PC), and 24:1 SM (24SM).

4. In paragraph 1 or 2, A biomarker composition for diagnosing multiple cancers, characterized in that the biomarker is extracted from blood.

5. In paragraph 1 or 2, A biomarker composition for diagnosing multiple cancers, characterized in that the cancer is at least one selected from the group consisting of liver cancer, biliary tract cancer, lung cancer, pancreatic cancer, stomach cancer, colon cancer, breast cancer, and cervical cancer.

6. A composition for diagnosing multiple cancers, comprising a preparation for measuring the blood level of a biomarker composition for diagnosing multiple cancers according to any one of claims 1 to 5.

7. In paragraph 5, A composition for diagnosing multiple cancers, characterized in that the preparation for measuring the level of the above biomarker composition is a preparation for mass spectrometry.

8. A kit for diagnosing multiple cancers, comprising a preparation for measuring the blood level of a biomarker composition for diagnosing multiple cancers according to any one of claims 1 to 5. 9.(a) Valine (Val), glutamate (Glu), N-methyl-2-pyridone-5-carboxamide (2PY), tryptophan (Trp), kynurenine (KN), acetylcarnitine (AC), hexanoylcarnitine (HC), octanoylcarnitine (OC), decanoylcarnitine (DC), lauroylcarnitine (LAC), myristoylcarnitine (MC), palmitoylcarnitine (PC), 16:0 Lyso Levels of multiple cancer diagnostic biomarkers, consisting of or comprising PC (1-hexadecanoyl-sn-glycero-3-phosphocholine; LPC16), 18:0 Lyso PC (1-octadecanoyl-sn-glycero-3-phosphocholine; LPC18), 15:0-18:1 PC (1-pentadecanoyl-2-oleoyl-sn-glycero-3-phosphocholine; 15PC), 16:0 SM (N-palmitoyl-D-erythro-sphingosylphosphorylcholine, 16SM), 18:1 SM (N-oleoyl-D-erythro-sphingosylphosphorylcholine; 18SM), and 24:1 SM (N-nervonoyl-D-erythro-sphingosylphosphorylcholine; 24SM), or Valine (Val), Glutamate (Glu), N-methyl-2-pyridone-5-carboxamide (2PY), Tryptophan (Trp), Kynurenine (KN), Acetylcarnitine (AC), Hexanoylcarnitine (HC), Octanoylcarnitine (OC), Decanoylcarnitine (DC), Lauroylcarnitine (LAC), Myristoylcarnitine (MC), Palmitoylcarnitine (PC), 16:0 Lyso PC (1-hexadecanoyl-sn-glycero-3-phosphocholine; A step of measuring the level of a multiple cancer diagnostic biomarker comprising at least five biomarkers selected from the group consisting of LPC16), 18:0 Lyso PC (1-octadecanoyl-sn-glycero-3-phosphocholine; LPC18), 15:0-18:1 PC (1-pentadecanoyl-2-oleoyl-sn-glycero-3-phosphocholine; 15PC), 16:0 SM (N-palmitoyl-D-erythro-sphingosylphosphorylcholine, 16SM), 18:1 SM (N-oleoyl-D-erythro-sphingosylphosphorylcholine; 18SM), and 24:1 SM (N-nervonoyl-D-erythro-sphingosylphosphorylcholine; 24SM); and (b) A method for providing information for multiple cancer diagnosis using artificial intelligence, comprising a step of applying the expression level of the above biomarker to a machine learning algorithm model.

10. In paragraph 9, The above five or more biomarkers include kynurenine (KN), octanoylcarnitine (OC), decanoylcarnitine (DC), N-methyl-2-pyridone-5-carboxamide (2PY), and 24:1 SM (24SM), or A method for providing information for multiple cancer diagnosis using artificial intelligence, characterized in that it comprises kynurenine (KN), octanoylcarnitine (OC), decanoylcarnitine (DC), lauroylcarnitine (LAC), valine (Val), glutamate (Glu), tryptophan (Trp), N-methyl-2-pyridone-5-carboxamide (2PY), 15:0-18:1 PC (15PC), and 24:1 SM (24SM).

11. In paragraph 9, A method for providing information for multiple cancer diagnosis using artificial intelligence, characterized in that the level measurement of the biomarker in the above step (a) is obtained through liquid chromatography-mass spectrometry (LC-MS).

12. In paragraph 9, The step of applying the above (b) algorithm model inputs the level of the biomarker in the blood of the subject into the above algorithm model and outputs whether cancer has developed as an output value. The algorithm model of step (b) above is: (i) a step of measuring the level of the multiple cancer diagnostic biomarker of step (a) from the blood of a cancer patient group and a normal control group; and (ⅱ) A method for providing information for multiple cancer diagnosis using artificial intelligence, characterized in that the method is derived through a step of creating a cancer occurrence prediction model by learning the level of the above biomarker using a machine learning algorithm.

13. In paragraph 9, A method for providing information for multiple cancer diagnosis using artificial intelligence, characterized in that the algorithm of step (b) is any one selected from linear or nonlinear classification algorithms including a k-nearest neighbor algorithm; a logistic regression algorithm; a discriminant analysis algorithm; a partial least squares-discriminant analysis algorithm; a support vector machine algorithm; a decision tree algorithm; a decision tree ensemble algorithm; and a neural network algorithm.

14. In paragraph 9, If the algorithm of the above step (b) is a support vector machine algorithm, it is expressed as a kernel function of the following mathematical expression 1, [Mathematical Formula 1] x: Blood level measurement of a biomarker composition for multiple cancer diagnosis γ: parameter for the flexibility (curvature) of the decision boundary A method for providing information for lung cancer diagnosis using artificial intelligence, characterized in that, in the above, x is a blood level measurement value of a biomarker composition for multiple cancer diagnosis, and γ is a parameter for the flexibility (curvature) of the decision boundary:

15. In paragraph 9, A method for providing information for multiple cancer diagnosis using artificial intelligence, characterized in that the cancer is at least one selected from the group consisting of liver cancer, bile duct cancer, lung cancer, pancreatic cancer, stomach cancer, colon cancer, breast cancer, and cervical cancer.

16. Blood levels of valine (Val), glutamate (Glu), N-methyl-2-pyridone-5-carboxamide (2PY), tryptophan (Trp), kynurenine (KN), acetylcarnitine (AC), hexanoylcarnitine (HC), octanoylcarnitine (OC), decanoylcarnitine (DC), lauroylcarnitine (LAC), myristoylcarnitine (MC), palmitoylcarnitine (PC), 16:0 Lyso Levels of biomarkers for multiple cancer diagnosis, comprising or consisting of PC (1-hexadecanoyl-sn-glycero-3-phosphocholine; LPC16), 18:0 Lyso PC (1-octadecanoyl-sn-glycero-3-phosphocholine; LPC18), 15:0-18:1 PC (1-pentadecanoyl-2-oleoyl-sn-glycero-3-phosphocholine; 15PC), 16:0 SM (N-palmitoyl-D-erythro-sphingosylphosphorylcholine, 16SM), 18:1 SM (N-oleoyl-D-erythro-sphingosylphosphorylcholine; 18SM), and 24:1 SM (N-nervonoyl-D-erythro-sphingosylphosphorylcholine; 24SM), or Valine (Val), Glutamate (Glu), N-methyl-2-pyridone-5-carboxamide (2PY), Tryptophan (Trp), Kynurenine (KN), Acetylcarnitine (AC), Hexanoylcarnitine (HC), Octanoylcarnitine (OC), Decanoylcarnitine (DC), Lauroylcarnitine (LAC), Myristoylcarnitine (MC), Palmitoylcarnitine (PC), 16:0 Lyso PC (1-hexadecanoyl-sn-glycero-3-phosphocholine; A measuring unit for measuring the level of biomarkers for diagnosing multiple cancers, comprising at least five biomarkers selected from the group consisting of LPC16), 18:0 Lyso PC (1-octadecanoyl-sn-glycero-3-phosphocholine; LPC18), 15:0-18:1 PC (1-pentadecanoyl-2-oleoyl-sn-glycero-3-phosphocholine; 15PC), 16:0 SM (N-palmitoyl-D-erythro-sphingosylphosphorylcholine, 16SM), 18:1 SM (N-oleoyl-D-erythro-sphingosylphosphorylcholine; 18SM), and 24:1 SM (N-nervonoyl-D-erythro-sphingosylphosphorylcholine; 24SM); and An artificial intelligence-based multi-cancer diagnosis prediction device, comprising a cancer diagnosis unit that inputs the above biomarker level into a learned artificial intelligence algorithm to determine whether cancer has occurred.

17. In paragraph 16, The above five or more biomarkers include kynurenine (KN), octanoylcarnitine (OC), decanoylcarnitine (DC), N-methyl-2-pyridone-5-carboxamide (2PY), and 24:1 SM (24SM), or An artificial intelligence-based multi-cancer diagnosis prediction device characterized by comprising kynurenine (KN), octanoylcarnitine (OC), decanoylcarnitine (DC), lauroylcarnitine (LAC), valine (Val), glutamate (Glu), tryptophan (Trp), N-methyl-2-pyridone-5-carboxamide (2PY), 15:0-18:1 PC (15PC), and 24:1 SM (24SM).

Images