MACHINE LEARNING-BASED ASN GROUPING FOR PREDICTING CERVICAL CANCER PROGNOSIS AND CHEMORADIOTHERAPY RESPONSE USING ATP5H, SCP3, AND NANOG

Abstract

Provided are biomarkers for predicting the prognosis of cervical cancer. In the case of using the biomarkers of the present disclosure, it is possible to select patients into a high-risk group, an intermediate-risk group, or a low-risk group, and thus, it is possible to provide tailored treatment for each patient according to prognosis prediction.

Claims

1. Biomarkers for predicting prognosis of cervical cancer comprising at least one protein of ATP5H, NANOG, PTEN, SCP and pERK or genes encoding the proteins.

2. The biomarkers for predicting the prognosis of cervical cancer of claim 1, wherein the biomarkers are ATP5H, SCP and NANOG.

3. A composition for predicting prognosis of cervical cancer comprising a preparation for measuring expression levels of proteins of ATP5H, SCP, and NANOG or genes encoding the proteins.

4. The composition for predicting the prognosis of cervical cancer of claim 3, wherein the preparation for measuring the expression levels of the proteins of ATP5H, SCP, and NANOG includes at least one selected from the group consisting of antibodies, oligopeptides, ligands, peptide nucleic acid (PNA) and aptamers that specifically bind to the proteins of ATP5H, SCP, and NANOG.

5. The composition for predicting the prognosis of cervical cancer of claim 3, wherein the preparation for measuring the expression levels of the genes encoding the proteins of ATP5H, SCP, and NANOG includes at least one selected from the group consisting of primers, probes and antisense nucleotides that specifically bind to the genes encoding the proteins of ATP5H, SCP3, and NANOG.

6. A method for providing information for predicting prognosis of cervical cancer, comprising measuring expression levels of at least one protein selected from the group consisting of ATP5H, SCP and NANOG or genes encoding the proteins in a biological sample isolated from a subject.

7. The method for providing information for predicting the prognosis of cervical cancer of claim 6, further comprising: classifying the proteins or the genes into any one of groups 1 to 4 according to the measured expression level.

8. The method for providing information for predicting the prognosis of cervical cancer of claim 7, further comprising: providing results for predicting the prognosis of cervical cancer for the subject according to the classified groups.

9. The method for providing information for predicting the prognosis of cervical cancer of claim 8, wherein in the providing of the results for predicting the prognosis of cervical cancer for the subject according to the classified groups, the group 1 is a group with overexpressed ATP5H as compared with a normal control group.

10. The method for providing information for predicting the prognosis of cervical cancer of claim 8, wherein in the providing of the results for predicting the prognosis of cervical cancer for the subject according to the classified groups, the group 2 is a group with low-expressed ATP5H as compared with a normal control group.

11. The method for providing information for predicting the prognosis of cervical cancer of claim 8, wherein in the providing of the results for predicting the prognosis of cervical cancer for the subject according to the classified groups, the group 3 is a group with low-expressed ATP5H, SCP, and NANOG.

12. The method for providing information for predicting the prognosis of cervical cancer of claim 8, wherein in the providing of the results for predicting the prognosis of cervical cancer for the subject according to the classified groups, the group 4 is a group with low-expressed ATP5H and SCP, and overexpressed NANOG.

13. The method for providing information for predicting the prognosis of cervical cancer of claim 8, further comprising: classifying the group 1 as a low-risk group.

14. The method for providing information for predicting the prognosis of cervical cancer of claim 8, further comprising: classifying the groups 2 and 3 as intermediate-risk groups.

15. The method for providing information for predicting the prognosis of cervical cancer of claim 8, further comprising: classifying the group 4 as a high-risk group.

16. The method for providing information for predicting the prognosis of cervical cancer of claim 6, wherein the providing of the results for predicting the prognosis of cervical cancer for the subject according to the classified groups further includes providing results for predicting the prognosis of cervical cancer for the subject by including the expression levels of at least one protein selected from the group consisting of ATP5H, SCP and NANOG or genes encoding the proteins in the biological sample isolated from the subject and clinical data information on the subject.

17. The method for providing information for predicting the prognosis of cervical cancer of claim 16, wherein the clinical data is data on FIGO stage, tumor size, lymph node metastasis, oncological grade, and age.

18. A kit for predicting prognosis of cervical cancer comprising the biomarkers of claim 1.

Description

BRIEF DESCRIPTION OF THE DRAWINGS

[0049] The above and other aspects, features and other advantages of the present disclosure will be more clearly understood from the following detailed description taken in conjunction with the accompanying drawings, in which:

[0050] FIG. 1 exemplarily illustrates a procedure of a method for providing information on the prognosis of cervical cancer according to an exemplary embodiment of the present disclosure.

[0051] FIG. 2 illustrates results of ranking the top 11 biomarkers associated with recurrence of cervical cancer using a random forest algorithm.

[0052] FIGS. 3 and 4 illustrate expression patterns for each group classified according to expression levels of biomarkers used in various Examples of the present disclosure.

[0053] FIG. 5 is a diagram illustrating progression free survival (PFS) using Kaplan-Meier survival analysis.

[0054] FIG. 6 illustrates evaluation results for prognosis prediction of biomarkers used in various Examples of the present disclosure.

DETAILED DESCRIPTION OF THE EMBODIMENT

[0055] Advantages and features of the present disclosure, and methods for accomplishing the same will be more clearly understood from exemplary embodiments to be described below in detail with reference to the accompanying drawings. However, the present disclosure is not limited to the exemplary embodiments set forth below, and will be embodied in various different forms. The exemplary embodiments are just for rendering the disclosure of the present disclosure complete and are set forth to provide a complete understanding of the scope of the invention to a person with ordinary skill in the art to which the present disclosure pertains, and the present disclosure will only be defined by the scope of the claims. In connection with the description of the drawings, like reference numerals may be used for like components.

[0056] In this document, expressions such as have, may have, include, or may include indicate the existence of a corresponding feature (e.g., numerical value, function, operation, or component such as a part), and do not exclude the existence of additional features.

[0057] In the present document, the expression such as A or B, at least one of A and/or B, or one or more of A and/or B may include all possible combinations of items listed together. For example, A or B, at least one of A and B, or at least one of A or B may refer to all cases of (1) including at least one A, (2) including at least one B, or (3) including both at least one A and at least one B.

[0058] Expressions such as first, and second, used herein may modify various components regardless of the order and/or importance, and will be used only to distinguish one component from the other component, but are not limit the corresponding components. For example, a first user device and a second user device may represent different user devices, regardless of the order or importance. For example, a first component may be referred to as a second component, and similarly, the second component may also be referred to as the first component without departing from the scope of the present document.

[0059] When a certain component (e.g., a first component) is referred to as being (operatively or communicatively) coupled with/to or connected to the other component (e.g., a second component), it will be understood that the component may be directly connected to the other component, or may be connected to the other component through another component (e.g., a third component). On the contrary, when a certain component (e.g., a first component) is referred to as being directly coupled with/to or directly connected to the other component (e.g., a second component), it will be understood that another component (e.g., a third component) is not present between the certain component and the other component.

[0060] The expression of configured to (or set to) used herein may be changed and used to, for example, suitable for, having the capacity to, designed to, adapted to, made to or capable of, depending on the situation. The term of configured to (or set to) may not necessarily mean only specially designed to in hardware. In some situations, the expression a device configured to may mean that the device is capable of together with other devices or parts. For example, the phrase a processor configured (or set) to perform A, B, and C may mean a dedicated processor (e.g., an embedded processor) for performing the corresponding operation, or a generic-purpose processor (e.g., a CPU or application processor) capable of performing the corresponding operations by executing one or more software programs stored in a memory device.

[0061] The terms used herein are used to illustrate only specific exemplary embodiments, and may not be intended to limit the scope of other exemplary embodiments. A singular form may include a plural form unless otherwise clearly meant in the contexts. The terms used herein, including technical or scientific terms, may have the same meaning as generally understood by those of ordinary skill in the art described in the present document. The terms defined in a general dictionary among the terms used herein may be interpreted in the same or similar meaning as or to the meaning on the context of the related art, and will not be interpreted as an ideal or excessively formal meaning unless otherwise defined in the present document. In some cases, even the terms defined in the present document cannot be interpreted to exclude the exemplary embodiments of the present disclosure.

[0062] The features of various exemplary embodiments of the present disclosure can be partially or entirely coupled or combined with each other and can be interlocked and operated in technically various ways to be sufficiently appreciated by those skilled in the art, and the exemplary embodiments can be implemented independently of or in association with each other.

[0063] For the clarity of the interpretation of the present specification, hereinafter, the terms used in the present specification will be defined.

[0064] As used herein, the term subject may mean any subject for which the prognosis of cervical cancer is to be predicted. For example, the subject may be a subject with cervical cancer. At this time, the subject disclosed in the present specification may be any mammal except for humans, but is not limited thereto.

[0065] As used herein, the term biological sample refers to any material, biological fluid, tissue, or cell obtained from the subject or derived from the subject. The biological sample may be at least one selected from the group consisting of whole blood, leukocytes, peripheral blood mononuclear cells, buffy coat, plasma, serum, sputum, tears, mucus, nasal washes, nasal aspirate, breath, urine, semen, saliva, peritoneal washings, ascites, cystic fluid, meningeal fluid, amniotic fluid, glandular fluid, pancreatic fluid, lymph fluid, pleural fluid, nipple aspirate, bronchial aspirate, synovial fluid, joint aspirate, organ secretions, cells, cell extract and cerebrospinal fluid. Preferably, the biological sample may be cervical cancer tissue (cells) isolated from a subject.

[0066] As used herein, the term biomarker is a biological indicator that may determine internal changes using cells, blood vessels, proteins, DNA, RNA, metabolites, etc. in the body, and the National Institutes of Health (NIH) has defined the biomarker as an index capable of objectively measuring and evaluating normal biological processes, disease progression conditions, and drug responsiveness to treatment methods. That is, in the case of a specific disease or cancer, the biomarker refers to a marker capable of distinguishing between normal and pathological conditions, or predicting a treatment response and objectively measuring the treatment response. Accordingly, the biomarkers should serve to objectively measure and evaluate the normal biological processes, disease progression situations, and drug responsiveness to treatment methods. Depending on applications, the biomarkers include target markers to confirm the existence of drug targets, diagnostic markers to diagnose the presence or absence of diseases, predictive markers to distinguish between responders and non-responders to a specific drug, and surrogate markers to monitor drug treatment effects, prognosis biomarkers to inform the prognosis of diseases, and the like.

[0067] As used herein, the term prognosis refers to the act of predicting the course of a disease and the outcome of death or survival in advance. The prognosis or prognosis prediction may be interpreted to mean all actions that the course of the disease may vary depending on physiological or environmental conditions of the patient, and the course of the disease before/after treatment is predicted by comprehensively considering the patient's condition.

[0068] As used herein, the term antibody refers to a substance that specifically binds to an antigen and causes an antigen-antibody reaction. For the purpose of the present disclosure, the antibody refers to an antibody that specifically binds to each protein of ATP5H, SCP and NANOG. The antibody of the present disclosure includes all polyclonal antibodies, monoclonal antibodies and recombinant antibodies. The antibodies may be easily prepared using techniques well-known in the art. For example, the polyclonal antibodies may be produced by a method well known in the art, including a process of injecting an antigen of the protein into an animal and collecting blood from the animal to obtain serum containing the antibody. These polyclonal antibodies may be prepared from any animal such as goat, rabbit, sheep, monkey, horse, pig, cow, dog, and the like. In addition, the monoclonal antibodies may be prepared using a hybridoma method well-known in the art (see Kohler and Milstein (1976) European Journal of Immunology 6:511-519), or a phage antibody library technique (see Clackson et al, Nature, 352:624-628, 1991; Marks et al, J. Mol. Biol., 222:58, 1-597, 1991). The antibodies prepared by the method may be separated and purified using methods such as gel electrophoresis, dialysis, salt precipitation, ion exchange chromatography, and affinity chromatography. In addition, the antibodies of the present disclosure include functional fragments of antibody molecules as well as complete forms having two full-length light chains and two full-length heavy chains. The functional fragments of the antibody molecules refer to fragments having at least an antigen binding function, and may be Fab, F(ab), F(ab)2, Fv and the like.

[0069] As used herein, the term oligopeptide consists of 2 to amino acids as a peptide and may include dipeptide, tripeptide, tetrapeptide and pentapeptides, but is not limited thereto.

[0070] As used herein, the term peptide nucleic acid (PNA) refers to an artificially synthesized polymer similar to DNA or RNA, and was first introduced in 1991 by Professors Nielsen, Egholm, Berg and Buchardt of the University of Copenhagen, Denmark. While DNA has a phosphate-ribose backbone, PNA has a repeated N-(2-aminoethyl)-glycine backbone linked by peptide bonds to greatly increase the binding force and stability to DNA or RNA, and accordingly, has been used in molecular biology, diagnostic assay and antisense therapies.

[0071] As used herein, the term aptamer means an oligonucleic acid or peptide molecule.

[0072] In the present disclosure, the preparation for measuring the expression levels of the genes encoding the proteins of ATP5H, SCP, and NANOG may include at least one selected from the group consisting of primers, probes and antisense nucleotides that specifically bind to the genes encoding the proteins of ATP5H, SCP, and NANOG.

[0073] As used herein, the term primer is a fragment that recognizes a target gene sequence, and includes a pair of forward and reverse primers, preferably a primer pair that provides an analysis result having specificity and sensitivity. Since the nucleic acid sequence of the primer is a sequence that is inconsistent with a non-target sequence present in a sample, high specificity may be imparted in the case of a primer in which only a target gene sequence containing a complementary primer binding site is amplified and non-specific amplification is not caused.

[0074] As used herein, the term probe means a substance capable of specifically binding to a target substance to be detected in a sample, and a substance capable of specifically confirming the presence of the target substance in the sample through the binding. The type of probe is not limited as any material commonly used in the art, but may be preferably peptide nucleic acid (PNA), locked nucleic acid (LNA), peptide, polypeptide, protein, RNA or DNA, and most preferably PNA. More specifically, the probe is a biomaterial, which is derived from or similar to a living organism or produced in vitro, and may be, for example, enzymes, proteins, antibodies, microorganisms, animal and plant cells and organs, neurons, DNA, and RNA. DNA includes cDNA, genomic DNA, and oligonucleotides, RNA includes genomic RNA, mRNA, and oligonucleotides, and examples of proteins may include antibodies, antigens, enzymes, peptides, and the like.

[0075] As used herein, the term locked nucleic acids (LNA) means a nucleic acid analog containing a 2-O, 4-C methylene bridge. The LNA nucleoside includes common nucleic acid bases of DNA and RNA, and may form base pairs according to the Watson-Crick base pairing rules. However, due to the locking of the molecule by the methylene bridge, the LNA does not form an ideal shape in the Watson-Crick bond. When the LNA is included in DNA or RNA oligonucleotide, the LNA may more rapidly pair with a complementary nucleotide chain to increase the stability of a double helix.

[0076] As used herein, the term antisense refers to an oligomer having a sequence of nucleotide bases and a backbone between subunits in which an antisense oligomer hybridizes with a target sequence in RNA by Watson-Crick base pairing to typically allow the formation of heteroduplex of mRNA and RNA:oligomer in the target sequence. The oligomer may have exact sequence complementarity or approximate complementarity to the target sequence.

[0077] Since the information of the proteins of ATP5H, SCP and NANOG or the genes encoding the proteins according to the present disclosure is known, based on this, those skilled in the art may easily design primers, probes, or antisense nucleotides that specifically bind to the genes encoding the proteins.

[0078] As used herein, the term kit refers to a tool capable of evaluating the expression level of a biomarker by labeling a probe or antibody that specifically binds to a biomarker component with a detectable label. The kit includes not only direct labeling of a detectable substance in relation to the probe or antibody by reaction with a substrate, but also indirect labeling in which a color-developing marker is conjugated by reactivity with another directly labeled reagent. The kit may include a color-developing substrate solution to color-react with the marker, a washing solution, and other solutions, and may be prepared by including reagent components to be used. In the present disclosure, the kit may be a kit including essential elements necessary for performing RT-PCR, and may include a test tube, a reaction buffer, deoxynucleotides (dNTPs), Taq-polymerase, reverse transcriptase, DNase, RNase inhibitors, sterile water, and the like in addition to each pair of primers specific to the marker gene. In addition, the kit may be a kit for detecting a gene for predicting HPD prognosis including essential elements necessary for performing DNA chip. The DNA chip kit may include a substrate to which cDNA corresponding to a gene or a fragment thereof is attached as a probe, and the substrate may include cDNA corresponding to a quantitative control gene or a fragment thereof. The kit of the present disclosure is not limited thereto, as long as the kit is known in the art.

[0079] As used herein, the term subject data is data obtainable from a subject, and may include at least one of cancer stage, lymph node metastasis, and age.

[0080] However, the subject data is not limited thereto, and may include more various data obtainable from electronic medical record data.

[0081] Hereinafter, the present disclosure will be described in more detail through Examples. These Examples are to explain the present disclosure in more detail, and it will be apparent to those skilled in the art that the scope of the present disclosure is not limited by these Examples in accordance with the gist of the present disclosure.

[0082] Evaluation 1: Derivation of Biomarkers and Performance Evaluation

[0083] First, referring to Table 1, Table 1 shows a classification result of patient groups for deriving biomarkers of the present disclosure.

TABLE-US-00001 TABLE 1 All Test cohort Training cohort (N = 281) (N = 89) (N = 192) P value Age, years old 49.37 11.40 50.55 10.78 48.82 11.66 0.236 FIGO stage 0.363 I-IIA 190 (67.62%) 64 (71.91%) 126 (65.62%) IIB-IV 91 (32.38%) 25 (28.09%) 66 (34.38%) Cell Type 0.097 Squamous 229 (81.49%) 67 (75.28%) 162 (84.38%) Others 52 (18.51%) 22 (24.72%) 30 (15.62%) Grade 0.188 Low/Moderate 158 (60.77%) 57 (67.06%) 101 (57.71%) Poor 102 (39.23%) 28 (32.4%) 74 (42.29%) Tumor size (mm) 30.54 19.40 28.54 17.04 31.47 20.38 0.24 LVI 0.934 Negative 95 (51.35%) 28 (50.00%) 67 (51.94%) Positive 90 (48.65%) 28 (50.00%) 62 (46.06%) Lymph node metastasis 0.911 Negative 188 (73.68%) 50 (72.46%) 118 (74.21%) Positive 60 (26.32%) 19 (27.54%) 41 (25.79%) SCC antigen Response to Chemoradiation therapy 0.283 Good 81 (57.45%) 31 (64.58%) 50 (53.76%) Poor 60 (42.55%) 17 (35.42%) 43 (46.24%)

[0084] For the derivation of biomarkers for predicting the prognosis of cervical cancer, as shown in Table 1, patient groups were divided into a learning group (70%) and a verification group (30%), and then as illustrated in FIG. 2, the top 11 biomarkers associated with recurrence of cervical cancer were ranked using a random forest algorithm. Thereafter, considering the significance of the biomarkers, 5 major biomarkers consisting of ATP5H, SCP3, cytoplasmic pERK1/2, NANOG and PTEN were selected.

[0085] At this time, referring to FIGS. 3 and 4 together, the results of dividing the risk of recurrence of cervical cancer into 4 groups based on the expression levels of biomarkers ATP5H, SCP3, cytoplasmic pERK1/2, NANOG and PTEN were illustrated.

[0086] Group 1 was a low-risk group, in which ATP5H was expressed higher than a predetermined cutoff value (ATP5H>4). Groups 2 and 3 were intermediate-risk groups. First, in Group 2, it was confirmed that both ATP5H and SCP3 were expressed lower than the cutoff value (ATP5H4, SCP161), and in Group 3, it was confirmed that ATP5H, SCP3, and NANOG all were expressed lower than the cutoff value (ATP5H4, SCP161, and NANOG185). Group 4 was a high-risk group, and it was confirmed that ATP5H and SCP3 were expressed lower than the cutoff value, but the expression of NANOG was higher than the cutoff value (ATP5H4, SCP161, NANOG>185).

[0087] Referring to FIG. 5 together, FIG. 5 is a diagram illustrating progression free survival (PFS) using Kaplan-Meier survival analysis, and it was confirmed that in both the learning and verification groups in Group 1 as the low-risk group, Groups 2 and 3 as the intermediate-risk groups, and Group 4 as the high-risk group, there were clear differences among the low, intermediate, and high-risk groups. This indicated that the performance of the biomarkers for predicting recurrence of cervical cancer of the present disclosure was excellent.

[0088] Based on the results, when using the biomarkers of the present disclosure, it is possible to predict the prognosis of cervical cancer with high accuracy, so that it is expected to contribute to increasing the life expectancy of patients by providing customized treatment tailored to each patient.

[0089] Evaluation 2: Evaluation of Biomarkers

[0090] Hereinafter, evaluation results of biomarkers for predicting the prognosis of cervical cancer according to various Examples of the present disclosure will be described with reference to FIG. 6 and Table 2. Table 3 shows results of analyzing clinicopathological characteristics by group. FIG. 6 illustrates evaluation results for prognosis prediction of biomarkers used in various Examples of the present disclosure.

TABLE-US-00002 TABLE 2 Group1 Group2 Group3 Group4 P-value Age FIGO stage I-IIA 52 22 27 IIB-IV 4 4 Cell Type Squamous 19 44 Others 8 7 7 7 Grade Low/Moderate 31 37 Poor 17 22 27 Tumor size (mm) 22.42 LVI Negative Positive 15 24 Lymph node metastasis Negative 45 18 Positive 7 Response to Chemoradiation therapy Good 13 Poor 1 indicates data missing or illegible when filed

[0091] Referring to Table 2, it was confirmed that the FIGO stage increased significantly from Group 1 to Group 4.

[0092] In Group 1, the low-risk group, a ratio of subjects classified as FIGO stage IIB-IV was only 7.14%, but in Group 4, the high-risk group, it was confirmed that the ratio of subjects increased to 52.24%. It was confirmed that the tumor size also increased significantly from Group 1, the low-risk group to Group 4, the high-risk group, and the size increased from 21.9320.31 mm to 40.2517.21 mm.

[0093] In addition, in Group 4, lymph node metastasis was confirmed as 61.54%, and the ratio of subjects with poor treatment response was 59.62%, which was higher than those of Groups 1 to 3.

[0094] In the case of LVSI, it was confirmed that the expression rate was high in Groups 3 and 4 compared to other groups, and specifically, 80% in Group 3 and 60% in Group 4.

[0095] Referring to Table 3, Table 3 was a table comparing Groups 3 and 4.

TABLE-US-00003 TABLE 3 Group2 Group3 (N = 26) (N = 51) P value Age 3.92 11.29 47.38 30.15 0.027 FIGO stage <0.001 I-IIA 22 (84.62%) 25 (49.51%) IIB-IV 4 (15.38%) 26 (50.98%) Cell Type 0.099 Squamous 19 (75.1%) 44 (36.3%) Others 7 (26.9%) 7 (17.7%) Grade 0.729 Low/Moderate 14 (63.64%) 29 (56.36%) Poor (36.36%) 22 (43.54%) Tumor size (mm) 22.42 16.62 26.92 19.48 <0.001 LVI 0.044 Negative 15 (57.7%) 3 (20.0%) Positive 11 (42.3%) 12 (80.0%) LN metastasis 0.050 Negative 23 (81.46%) 18 (62.07%) Positive 3 ( ) 11 (37.93%) Response to chemoradiation therapy 0.018 Good 8 (100.00%) 11 (57.89%) Poor 0 (0.0%) (42.11%) indicates data missing or illegible when filed

[0096] As shown in Table 3, subjects in Group 3 were younger at the time of diagnosis, diagnosed as more advanced in the FIGO stage, and had larger tumor sizes and higher LVSI expression rate than those of Group 2.

[0097] As described above, according to the classification model of the present disclosure, it is possible to classify subjects according to the risk of cervical cancer, and according to the tumor size, lymph node metastasis, FIGO stage and LVSI for each group, it is possible to develop a tailored treatment plan appropriate for the patient and to more accurately predict the prognosis of patients, and thus it was confirmed the present disclosure can be usefully used to improve the prognosis of cervical cancer patients.

[0098] Hereinafter, evaluation results of a classification model according to various Examples of the present disclosure will be described with reference to FIG. 6.

[0099] FIG. 6 illustrates evaluation results of a classification model used for various Examples of the present disclosure. Specifically, clinical information, such as FIGO stage, tumor size, lymph node metastasis, oncological grade, and age, was integrated into the classification model of the present disclosure to be classified by combining molecular information such as expression levels of biomarkers, and C-indexes were compared by comparing a case of considering only clinical information and a clinical-molecular classification using the classification model of the present disclosure.

[0100] As a result, as illustrated in FIG. 6, it was confirmed that it is possible to predict the prognosis of cervical cancer with higher accuracy when using a model considering both molecular classification and clinical information than when the molecular classification and the clinical information were considered separately.

[0101] Although the exemplary embodiments of the present disclosure have been described in detail with reference to the accompanying drawings, the present disclosure is not limited thereto and may be embodied in many different forms without departing from the technical concept of the present disclosure. Therefore, the exemplary embodiments of the present disclosure are provided for illustrative purposes only but not intended to limit the technical concept of the present disclosure. The scope of the technical concept of the present disclosure is not limited thereto. Therefore, it should be appreciated that the aforementioned exemplary embodiments are illustrative in all aspects and are not restricted. The protective scope of the present disclosure should be construed on the basis of the appended claims, and all the technical spirits in the equivalent scope thereof should be construed as falling within the scope of the present disclosure.