Biomarkers for the detection of early colorectal cancer and their applications

Abstract

The present invention provides a biomarker for detecting early colorectal cancer and its application. By using the proteomics method, by analyzing the proteins with significantly different abundance levels in the blood of patients with advanced adenomas in the colorectal cancer tumor process, patients with early colorectal cancer and healthy controls, the biomarkers that can be used to predict the risk of early colorectal cancer (including advanced adenomas and early colorectal cancer) in an individual are screened out, and a multi-marker combined detection model is further constructed, which can achieve accurate, non-invasive and efficient prediction of the risk of early colorectal cancer in an individual to meet clinical needs.

Description

Technical Field

[0001] The present invention relates to the field of early diagnosis of colorectal cancer, and in particular to a biomarker for early colorectal cancer detection and application thereof. Background Art

[0002] Colorectal cancer is one of the most common clinical malignant tumors. According to statistics from the National Cancer Center, the incidence and mortality of colorectal cancer are both among the top five malignant tumors. Affected by factors such as the aging of the population and changes in dietary structure, the incidence of colorectal cancer is also increasing year by year. At present, the incidence of colorectal cancer in my country is surging at a rate of 4% per year, far exceeding the global average annual growth rate; on the contrary, the 5-year survival rate of colorectal cancer patients in my country is only 47%, far lower than that of developed countries such as Europe and the United States.

[0003] Discovering and identifying colorectal malignant lesions at an early stage is an important measure to reduce the incidence and mortality of colorectal cancer and improve the survival of colorectal cancer in my country. The 5-year survival rate after radical surgery for patients who are found and diagnosed in the adenoma and stage I colorectal cancer stage is over 90%; however, the 5-year survival rate of patients who have already developed distant metastasis at the time of discovery is only about 5%. At present, colonoscopy is the gold standard for the detection of colorectal tumors. However, colonoscopy requires advanced instruments and specialized operators, has high technical requirements, is expensive, and subjects need to prepare their intestines and have poor compliance, which is not suitable for repeated examinations and population censuses. In addition, there are some other methods for screening colorectal cancer, such as fecal occult blood test (FOBT), but this method has limitations such as being easily disturbed by diet, high false positive rate, and low sensitivity. The currently commonly used blood markers for colorectal cancer (CEA, CA199) are not ideal for the diagnosis of early colorectal cancer and precancerous lesions (advanced adenomas), with insufficient sensitivity and high false positive rate. Although some molecular diagnostic techniques based on blood and feces (such as DNA methylation detection) have improved the detection sensitivity of early colorectal cancer to a certain extent, the diagnostic sensitivity of advanced adenomas is only about 60%. There is a lack of biomarkers for early diagnosis of colorectal cancer in clinical practice, especially the discovery of highly sensitive biomarkers for the diagnosis of advanced adenomas is of great significance.

[0004] Proteomics is the science of studying the composition, location, changes and interaction of proteins in cells, tissues or organisms, including the study of protein expression patterns and proteome functional patterns. With the development of proteomics technology, high-performance liquid chromatography-high-resolution tandem mass spectrometry has gradually become the mainstream technology of proteomics, and more and more new tumor markers have been discovered. Although there have been many reports on the discovery of new tumor markers in recent years, they have only remained in the laboratory research stage, and there are few in clinical application and market promotion. Moreover, in most cases, a single indicator is far from enough for the in vitro diagnosis of tumors. Only by combining various dimensions of detection in the form of combined joint testing can the accuracy of prediction be enhanced. Therefore, it is of great clinical value to find new markers related to the early diagnosis of colorectal cancer and its precancerous lesions and to combine multiple markers to build an early prediction model.

[0005] Therefore, the present invention screens protein markers related to the diagnosis of early colorectal cancer through high-throughput proteomics technology, and combines multiple markers to construct a prediction model for early colorectal cancer, which will be of great significance for the early diagnosis and treatment of colorectal cancer. Summary of the invention

[0006] In response to the problems existing in the prior art, the present invention provides a biomarker for detecting early colorectal cancer and its application. By using proteomics methods, proteins with significantly different abundance levels in the blood of patients with advanced adenomas in the colorectal cancer tumor process, patients with early colorectal cancer and healthy controls are analyzed to screen out biomarkers that can be used to predict the risk of early colorectal cancer (including advanced adenomas and early colorectal cancer) in an individual, and further construct a multi-marker combined detection model, which can achieve accurate, non-invasive and efficient prediction of the risk of early colorectal cancer in an individual to meet clinical needs.

[0007] On the one hand, the present invention provides a marker for preparing a reagent for predicting whether an individual suffers from early colorectal cancer, wherein the marker includes any one or more of trefoil factor 1, trefoil factor 3, insulin-like growth factor binding protein 1, insulin-like growth factor binding protein 4, serine protease inhibitor A1, osteopontin, and growth differentiation factor 15, and the early colorectal cancer includes advanced adenoma and early colorectal cancer.

[0008] In the present invention, early colorectal cancer is defined as including colorectal cancer + advanced adenoma, that is, the markers provided by the present invention can simultaneously distinguish people with advanced adenoma and early colorectal cancer from healthy people.

[0009] Although there are reports on existing markers for distinguishing early colorectal cancer, they can usually only be used to distinguish healthy people from people with early colorectal cancer, and cannot distinguish patients with advanced adenomas who are in the earlier stage of the disease, resulting in insufficient detection sensitivity.

[0010] The markers provided by the present invention can simultaneously diagnose people with advanced adenomas and early colorectal cancer, distinguish them from healthy people, and thus identify colorectal malignant lesions at an earlier stage, which is of great significance for improving the survival rate of colorectal cancer.

[0011] Furthermore, the markers include trefoil factor 1, trefoil factor 3, insulin-like growth factor binding protein 1, insulin-like growth factor binding protein 4, serine protease inhibitor A1, osteopontin and growth differentiation factor 15.

[0012] In this example, proteomics methods were used to collect plasma samples from patients at different stages of colorectal cancer tumor progression (inflammatory diseases-benign polyps-advanced adenomas-early colorectal cancer) and healthy controls, and different samples were analyzed by high performance liquid chromatography-tandem mass spectrometry (HPLC-MS / MS). Based on orthogonal partial least squares discriminant analysis and significance analysis methods, proteins with significant differences between early colorectal cancer patients and healthy controls were first screened, and finally 12 differential proteins with obvious correlation with colorectal cancer were screened. However, when a random forest model was constructed using these 12 proteins to distinguish early colorectal cancer (including early colorectal cancer and advanced adenomas) from healthy people, the diagnostic efficacy was low, and it could not be used to distinguish advanced adenomas from healthy people.

[0013] Therefore, in order to improve the diagnostic efficacy of early colorectal cancer (including early colorectal cancer and advanced adenoma) or advanced adenoma, differential proteins were screened again for advanced adenoma and healthy group, and finally the top 10 differential proteins ranked by importance were screened, and the Boruta algorithm was further used to screen 7 protein markers to construct the model, which has good risk prediction ability in the groups of early colorectal cancer, advanced adenoma and early colorectal cancer (including early colorectal cancer and advanced adenoma).

[0014] Furthermore, the reagent is used to detect the content of biomarkers in a body fluid sample; the body fluid sample includes any one or more of saliva, blood, urine, plasma, serum, and cerebrospinal fluid.

[0015] In some embodiments, the reagent for predicting whether a patient has early colorectal cancer is a detection reagent prepared with the biomarker as the detection target, such as sample pretreatment reagents, antigens or antibodies, and other biological reagents and kits suitable for the detection of the biomarker; it can also be developed into a standardized reagent or kit suitable for liquid chromatography-ultraviolet (LC-UV) or liquid chromatography-mass spectrometry (LC-MS) detection of the biomarker.

[0016] In some embodiments, the ELISA method is used to conduct team validation on 12 candidate protein markers screened in early colorectal cancer and 10 candidate protein markers screened in advanced adenomas, a total of 18 candidate protein markers for colorectal cancer. It was finally found that 7 new biomarkers (TFF1, TFF3, IGFBP1, IGFBP4, SERPINA1, OPN, GDF-15) with significant differences were found in the two groups of early colorectal cancer vs. healthy controls and advanced adenomas vs. healthy controls. They can be used as candidate biomarkers for the differential diagnosis of early colorectal cancer (including early colorectal cancer and advanced adenomas) and advanced adenomas; at the same time, the model constructed with the 7 protein markers has good risk prediction ability in the groups of early colorectal cancer, advanced adenomas, and early colorectal cancer + advanced adenomas (early colorectal cancer). In the canceration vs healthy control group, the model AUC value reached 0.896; in the early colorectal cancer vs healthy control group, the model AUC value reached 0.983; in the advanced adenoma vs healthy control group, the model AUC value reached 0.807, and the AUC values ​​were all above 0.8, with high diagnostic value; and the 7 markers that finally screened out and made significant contributions to the model were all differential markers contained in advanced adenomas, while when screening only from the protein markers of early colorectal cancer, the best 7 markers that made significant contributions to the model of the present invention could not be screened out.

[0017] Therefore, seven markers are preferably selected in the present invention: trefoil factor 1 (TFF1), trefoil factor 3 (TFF3), insulin-like growth factor binding protein 1 (IGFBP1), insulin-like growth factor binding protein 4 (IGFBP4), serine protease inhibitor A1 (SERPINA1), osteopontin (OPN), and growth differentiation factor 15 (GDF-15). A diagnostic model is constructed, which has good clinical diagnostic value for early colorectal cancer, can significantly improve the diagnostic identification ability and diagnostic efficacy of early colorectal cancer (including early colorectal cancer + advanced adenoma) or advanced adenoma, and realize the risk prediction of early colorectal cancer (including early colorectal cancer + advanced adenoma) or advanced adenoma.

[0018] Furthermore, the reagent is used to detect the presence or relative abundance or concentration of a biomarker in a body fluid sample.

[0019] The present invention screens blood for biomarkers of early colorectal cancer or advanced adenoma. These biomarkers are significantly different in the blood of people with early colorectal cancer (including early colorectal cancer + advanced adenoma) and people without colorectal cancer (including but not limited to benign polyps, patients with gastrointestinal inflammatory diseases, and healthy controls). By collecting blood samples, the possibility of an individual suffering from early colorectal cancer or advanced adenoma can be predicted or assisted in diagnosis by detecting these biomarkers in the individual's blood, or these biomarkers in the blood of a certain group can be detected, and then the group can be divided into a high-risk group for colorectal cancer or a low-risk group for colorectal cancer.

[0020] Furthermore, the detection method includes a radiation method, an immunological method, a fluorescence method, a flow cytometry, a latex turbidimetry, a biochemical method, an enzyme method, a hybridization method, a gas chromatography-mass spectrometry method, a liquid chromatography-mass spectrometry method, a chromatography method, a chemiluminescence method, a magnetoelectric method or a photoelectric conversion method.

[0021] The presence or absence of markers or the level of their content is a relative concept. For example, when comparing the diseased group with the non-diseased group, the content of these specific markers is compared with the diseased group or the non-diseased group as a benchmark. It may be that for some markers, the content in the diseased group is higher than that in the non-diseased group, and this high has a statistical difference, such as a significant or extremely significant increase. Therefore, when these markers are judged, if it is a single marker, if the probability of the marker occurring at a certain risk increases, the content of the marker changes. The change here may be a relative increase or a relative decrease. This relative increase or relative decrease has a significant difference, and of course it can also be an extremely significant difference. Therefore, no matter what means are used for detection, a predetermined value can be used as a standard (cut-off value). If it is higher than this value, it is considered that the content has changed. Such results can be used as predictive or diagnostic values.

[0022] Therefore, in some aspects, the markers described in the present invention can be obtained by detecting the content of markers in samples by any known method, such as liquid chromatography, gas chromatography, mass spectrometry, LC-MS, gas chromatography-mass spectrometry (GC-MS), chromatography-mass spectrometry (CC-MS), liquid chromatography-tandem mass spectrometry (LC-MS-MS), nuclear magnetic resonance spectroscopy (NMR), immunochromatography test strips, immunoreaction chips, capillary electrophoresis, infrared spectroscopy, etc. As long as they can be used to detect the content of protein markers in samples, they can be used for the diagnosis of early colorectal cancer and advanced adenoma. As long as the content of protein markers in samples can be detected, they can be used to predict or diagnose the probability of a certain disease. It can be understood that the detection here is to detect individual samples, and then compare them with pre-set standards, and the results of the comparison are used to judge or predict the occurrence of the disease. For example, it can be used to predict the probability of early colorectal cancer or advanced adenoma. This prediction or diagnosis is whether it occurs within a certain period of time. Of course, such detection can be continuous detection, and the progress of the disease is inferred as the content of certain substances changes.

[0023] In some embodiments, the relative abundance is the peak area of ​​the biomarker in the detection spectrum obtained by high performance liquid chromatography-tandem mass spectrometry. For example, if the average peak area of ​​a biomarker measured in the control sample is 500, and the average peak area measured in the sample of a patient with early colorectal cancer or advanced adenoma is 3000, then the abundance of the biomarker in the sample is considered to be 6 times that in the control sample.

[0024] On the other hand, the present invention provides a biomarker combination for predicting whether an individual is in the early stage of colorectal cancer, which combination includes trefoil factor 1, trefoil factor 3, insulin-like growth factor binding protein 1, insulin-like growth factor binding protein 4, serine protease inhibitor A1, osteopontin and growth differentiation factor 15.

[0025] In yet another aspect, the present invention provides a kit for predicting whether an individual suffers from early colorectal cancer, comprising a detection reagent for a biomarker for use as described in any one of the above technical solutions.

[0026] In some embodiments, the detection reagent is an antibody against the biomarker, and the antibody is a monoclonal antibody.

[0027] On the other hand, the present invention provides a system for predicting whether an individual suffers from early colorectal cancer, the system comprising a data analysis module, the data analysis module being used to analyze the detection values ​​of biomarkers, the markers comprising any one or more of trefoil factor 1, trefoil factor 3, insulin-like growth factor binding protein 1, insulin-like growth factor binding protein 4, serine protease inhibitor A1, osteopontin, and growth differentiation factor 15, the early colorectal cancer comprising advanced adenoma and early colorectal cancer.

[0028] Furthermore, the markers include trefoil factor 1, trefoil factor 3, insulin-like growth factor binding protein 1, insulin-like growth factor binding protein 4, serine protease inhibitor A1, osteopontin and growth differentiation factor 15.

[0029] In some embodiments, a random forest model is first used to construct a model, and it is preliminarily confirmed that the concentration changes of any one of the 7 novel biomarkers screened out alone can be used to distinguish patients with early colorectal cancer (early colorectal cancer + advanced adenoma) from healthy people, patients with advanced adenoma from healthy people, and patients with early colorectal cancer from healthy people, indicating that these 7 biomarkers have extremely high diagnostic value.

[0030] In summary, the combined diagnostic model constructed in this embodiment, which contains 7 biomarkers (trefoil factor 1 (TFF1), trefoil factor 3 (TFF3), insulin-like growth factor binding protein 1 (IGFBP1), insulin-like growth factor binding protein 4 (IGFBP4), serine protease inhibitor A1 (SERPINA1), osteopontin (OPN), growth differentiation factor 15 (GDF-15)), has good clinical diagnostic value for early colorectal cancer, can significantly improve the diagnostic differentiation ability and diagnostic efficacy of early colorectal cancer, early colorectal cancer or advanced adenoma, and realize the accurate diagnosis of early colorectal cancer, early colorectal cancer or advanced adenoma.

[0031] Furthermore, the data analysis module uses the detection values ​​of markers of known samples as training sets, divides the samples into early colorectal cancer group and healthy group according to whether they suffer from early colorectal cancer, analyzes the relationship between the detection values ​​of the early colorectal cancer group and the healthy group, and constructs a model.

[0032] Furthermore, the system also includes a data storage module, a data input interface and a data output interface; the data storage module is used to store the detection values ​​of biomarkers; the data input interface is used to input the detection values ​​of biomarkers, and the data output interface is used to output the prediction results.

[0033] Furthermore, the detection value is the presence or relative abundance or concentration value of the seven biomarkers.

[0034] On the other hand, the present invention provides a use of a biomarker for preparing a reagent for predicting whether an individual has advanced adenoma, wherein the biomarker includes any one or more of trefoil factor 1, trefoil factor 3, insulin-like growth factor binding protein 1, insulin-like growth factor binding protein 4, serine protease inhibitor A1, osteopontin, growth differentiation factor 15, prion protein, guanylate cyclase activating factor 2A, and regeneration family member protein 1 alpha.

[0035] Furthermore, the biomarkers include trefoil factor 1, trefoil factor 3, insulin-like growth factor binding protein 1, insulin-like growth factor binding protein 4, serine protease inhibitor A1, osteopontin, and growth differentiation factor 15.

[0036] Furthermore, the reagent is used to detect the content of biomarkers in a body fluid sample; the body fluid sample includes any one or more of saliva, blood, urine, plasma, serum, and cerebrospinal fluid.

[0037] Furthermore, the reagent is used to detect the presence or relative abundance or concentration of a biomarker in a body fluid sample.

[0038] Furthermore, the detection method includes a radiation method, an immunological method, a fluorescence method, a flow cytometry, a latex turbidimetry, a biochemical method, an enzyme method, a hybridization method, a gas chromatography-mass spectrometry method, a liquid chromatography-mass spectrometry method, a chromatography method, a chemiluminescence method, a magnetoelectric method or a photoelectric conversion method.

[0039] In another aspect, the present invention provides a biomarker combination for predicting whether an individual has advanced adenoma, the combination comprising trefoil factor 1, trefoil factor 3, insulin-like growth factor binding protein 1, insulin-like growth factor binding protein 4, serine protease inhibitor A1, osteopontin and growth differentiation factor 15.

[0040] In yet another aspect, the present invention provides a kit for predicting whether an individual suffers from advanced adenoma, comprising a detection reagent for a biomarker for use as described in any one of the above technical solutions.

[0041] On the other hand, the present invention provides a system for predicting whether an individual suffers from advanced adenoma, the system comprising a data analysis module, the data analysis module being used to analyze the detection values ​​of biomarkers, the biomarkers comprising any one or more of trefoil factor 1, trefoil factor 3, insulin-like growth factor binding protein 1, insulin-like growth factor binding protein 4, serine protease inhibitor A1, osteopontin, growth differentiation factor 15, prion protein, guanylate cyclase activating factor 2A, and regeneration family member protein 1 alpha.

[0042] Furthermore, the biomarkers include trefoil factor 1, trefoil factor 3, insulin-like growth factor binding protein 1, insulin-like growth factor binding protein 4, serine protease inhibitor A1, osteopontin, and growth differentiation factor 15.

[0043] Furthermore, the data analysis module uses the detection values ​​of markers of known samples as training sets, divides the samples into an advanced adenoma group and a healthy group according to whether the samples have advanced adenoma, analyzes the relationship between the detection values ​​of the advanced adenoma group and the healthy group, and constructs a model.

[0044] Furthermore, the system also includes a data storage module, a data input interface and a data output interface; the data storage module is used to store the detection values ​​of biomarkers; the data input interface is used to input the detection values ​​of biomarkers, and the data output interface is used to output the prediction results.

[0045] Furthermore, the detection value is the presence or relative abundance or concentration value of the seven biomarkers.

[0046] Furthermore, the trefoil factor 1 is a protein or amino acid sequence with a UniProt database number of P04155; the trefoil factor 3 is a protein or amino acid sequence with a UniProt database number of Q07654; the insulin-like growth factor binding protein 1 is a protein or amino acid sequence with a UniProt database number of P08833; the insulin-like growth factor binding protein 4 is a protein or amino acid sequence with a UniProt database number of P22692; the serine protease inhibitor A1 is a protein or amino acid sequence with a UniProt database number of P01009; the osteopontin is a protein or amino acid sequence with a UniProt database number of P10451; and the growth differentiation factor 15 is a protein or amino acid sequence with a UniProt database number of Q99988.

[0047] On the other hand, the present invention provides a biomarker combination for preparing a reagent for distinguishing individuals as having early colorectal cancer, advanced adenoma, benign polyp, inflammatory bowel disease, healthy people or other cancers, wherein the biomarkers include trefoil factor 1, trefoil factor 3, insulin-like growth factor binding protein 1, insulin-like growth factor binding protein 4, serine protease inhibitor A1, osteopontin, and growth differentiation factor 15.

[0048] The models constructed above are all binary classification models, for example, they are used to distinguish between "healthy people and patients with early colorectal cancer", or "healthy people and patients with advanced adenoma", or "healthy people and patients with early colorectal cancer".

[0049] The present invention also attempts to use the seven protein markers to construct a six-category model, which includes six categories: early colorectal cancer, advanced adenoma, benign polyps, inflammatory bowel disease, healthy people and other cancers. It is found that the model constructed by the present invention also has very good diagnostic efficacy in distinguishing the six categories. At the same time, a variety of different algorithms are compared to construct a six-category model, and it is found that the six-category detection model constructed using the gradient boosting algorithm has the highest diagnostic efficacy and can be used for efficient differential diagnosis of early colorectal cancer, advanced adenoma, benign polyps, inflammatory bowel disease, healthy people and other cancers.

[0050] The other cancers include other digestive tract cancers, such as esophageal cancer, gastric cancer, liver cancer, pancreatic cancer, bile duct cancer, etc. The six-category detection model of the present invention can not only accurately distinguish early colorectal cancer from early colorectal cancer, advanced adenomas, benign polyps, inflammatory bowel disease and healthy people, but also shows significant advantages in distinguishing early colorectal cancer from other digestive tract cancers (such as esophageal cancer, gastric cancer, liver cancer, pancreatic cancer, bile duct cancer, etc.). Through this model, early colorectal cancer can be clearly distinguished from other cancers, which fully demonstrates its high specificity. This means that the model can accurately identify the unique characteristics of early colorectal cancer, avoid confusing it with other similar diseases or other types of cancer, and thus greatly reduce the possibility of misdiagnosis.

[0051] At the same time, in order to further improve the performance and accuracy of the six-classification model, the supervised classification algorithm model was preliminarily compared and screened. The final results showed that the optimal model constructed by gradient boosting (GBM) was selected as the final prediction model for the diagnosis of advanced adenoma or early colorectal cancer. The performance evaluation score of this algorithm was the best, and the comprehensive diagnostic accuracy of the prediction of each disease type was 0.768 and the consistency was 0.713. The optimal hyperparameters of the model were determined by training with a 10-fold cross-validation method: learning rate of 0.1, number of decision trees of 150, maximum tree depth of 3, and minimum number of samples of terminal nodes of 10.

[0052] In order to ensure the diagnostic efficacy of the model while maximizing the benefits, different combinations of protein markers were further screened. Finally, 7 markers were selected to construct the diagnostic model: trefoil factor 1 (TFF1), trefoil factor 3 (TFF3), insulin-like growth factor binding protein 1 (IGFBP1), insulin-like growth factor binding protein 4 (IGFBP4), serine protease inhibitor A1 (SERPINA1), osteopontin (OPN), and growth differentiation factor 15 (GDF-15). At this time, the model can be constructed with the least markers to achieve the highest diagnostic efficacy.

[0053] A more in-depth prediction analysis was performed based on the multi-classification model of the selected gradient boosting algorithm, and the prediction probability values ​​were calculated and the diagnostic indicators of each disease were re-given to more accurately determine the diagnostic performance and threshold of the model in different disease classifications. The multi-classification model of the gradient boosting (GBM) algorithm in the model group was used for prediction analysis, and the prediction results were calculated to obtain the prediction probability values ​​of 6 categories (healthy controls, inflammatory bowel disease, benign polyps, advanced adenomas, early colorectal cancer, and other cancers). The classification with the largest prediction probability value was the final prediction result of the system. The final result was that the accuracy of the model in the model group was 0.761 and the consistency was 0.705. The diagnostic sensitivity for early colorectal cancer was 76.9%, the specificity was 95.9%, the positive predictive value was 78.4%, and the negative predictive value was 95.5%; the diagnostic sensitivity for advanced adenomas was 69.8%, the specificity was 94.5%, the positive predictive value was 71.3%, and the negative predictive value was 94.1%; the diagnostic sensitivity for benign polyps was 74.3%, the specificity was 95.4%, the positive predictive value was 67.7%, and the negative predictive value was 96.6%; the diagnostic sensitivity for inflammatory bowel disease was 67.2%, the specificity was 94.2%, the positive predictive value was 67.7%, and the negative predictive value was 94.1%; the diagnostic sensitivity for other cancers was 77.7%, the specificity was 95.9%, the positive predictive value was 67.3%, and the negative predictive value was 97.5%; the diagnostic sensitivity for healthy controls was 83.6%, the specificity was 95.4%, the positive predictive value was 89.0%, and the negative predictive value was 92.9%, which was significantly better than that of the existing biomarker combined prediction model.

[0054] At the same time, in order to test the performance of the above-mentioned gradient boosting algorithm in the new sample validation set data, so as to more comprehensively evaluate the generalization ability and practical application effect of the model, the algorithm built based on the model group was applied to the new validation group to verify the prediction performance. In the new validation group samples, the final results showed that the accuracy was 0.78 and the consistency was 0.729. The diagnostic sensitivity for early colorectal cancer was 79.4%, the specificity was 94.4%, the positive predictive value was 73.5%, and the negative predictive value was 95.9%; the diagnostic sensitivity for advanced adenoma was 73.4%, the specificity was 94.7%, the positive predictive value was 73.4%, and the negative predictive value was 94.7%; the diagnostic sensitivity for benign polyps was 72.7%, the specificity was 95.9%, the positive predictive value was 69.6%, and the negative predictive value was 96.5%; the diagnostic sensitivity for inflammatory bowel disease was 68.3%, the specificity was 96.3%, the positive predictive value was 77.4%, and the negative predictive value was 94.3%; the diagnostic sensitivity for other cancers was 83.3%, the specificity was 96.0%, the positive predictive value was 68.2%, and the negative predictive value was 98.3%; the diagnostic sensitivity for healthy controls was 85.0%, the specificity was 96.3%, the positive predictive value was 91.1%, and the negative predictive value was 93.5%.

[0055] On the other hand, the present invention provides a biomarker combination for predicting whether an individual has early colorectal cancer, advanced adenoma, benign polyp, inflammatory bowel disease, healthy people or other cancers, the combination including trefoil factor 1, trefoil factor 3, insulin-like growth factor binding protein 1, insulin-like growth factor binding protein 4, serine protease inhibitor A1, osteopontin and growth differentiation factor 15.

[0056] On the other hand, the present invention provides a kit for predicting whether an individual has early colorectal cancer, advanced adenoma, benign polyp, inflammatory bowel disease, healthy people or other cancers, wherein the kit comprises a detection reagent for a biomarker for the use as described in any of the above technical solutions.

[0057] On the other hand, the present invention provides a system for predicting whether an individual has early colorectal cancer, advanced adenoma, benign polyp, inflammatory bowel disease, healthy people or other cancers, the system comprising a data analysis module, the data analysis module being used to analyze the detection values ​​of markers, the markers comprising any one or more of trefoil factor 1, trefoil factor 3, insulin-like growth factor binding protein 1, insulin-like growth factor binding protein 4, serine protease inhibitor A1, osteopontin, and growth differentiation factor 15.

[0058] Furthermore, the markers include trefoil factor 1, trefoil factor 3, insulin-like growth factor binding protein 1, insulin-like growth factor binding protein 4, serine protease inhibitor A1, osteopontin and growth differentiation factor 15.

[0059] Furthermore, the data analysis module uses the detection values ​​of markers of known samples as training sets, and divides them into early colorectal cancer group, advanced adenoma group, benign polyp group, inflammatory bowel disease group, healthy group and other cancer groups according to different disease classifications, analyzes the relationship between the detection values ​​of early colorectal cancer group, advanced adenoma group, benign polyp group, inflammatory bowel disease group, healthy group and other cancer groups, and constructs a model.

[0060] Furthermore, the system also includes a data storage module, a data input interface and a data output interface; the data storage module is used to store the detection values ​​of biomarkers; the data input interface is used to input the detection values ​​of biomarkers, and the data output interface is used to output the prediction results.

[0061] The beneficial effects of the present invention are:

[0062] 1. The present invention screened out 7 new biomarkers that can predict early colorectal cancer (early colorectal cancer + advanced adenoma) and the risk of advanced adenoma: trefoil factor 1, trefoil factor 3, insulin-like growth factor binding protein 1, insulin-like growth factor binding protein 4, serine protease inhibitor A1, osteopontin, and growth differentiation factor 15, and developed a new combination of protein markers, which can effectively evaluate and diagnose patients with advanced colorectal adenomas and colorectal cancer, effectively distinguish patients with early colorectal cancer from healthy people, early colorectal cancer patients from healthy people, and advanced adenoma patients from healthy people, and can more accurately identify patients with early colorectal cancer and advanced adenoma. Compared with traditional detection methods, it reduces the risk of misdiagnosis and missed diagnosis, and provides strong support for early detection and intervention of the disease.

[0063] 2. In the present invention, a binary classification algorithm is adopted, and a model is constructed by a random forest algorithm, which shows significant diagnostic value in the comparison of early colorectal cancer and healthy controls, early colorectal cancer and healthy controls, and advanced adenomas and healthy controls; in the early colorectal cancer vs healthy control group, the model AUC value reaches 0.896; in the early colorectal cancer vs healthy control group, the model AUC value reaches 0.983; in the advanced adenoma vs healthy control group, the model AUC value reaches 0.807, all exceeding 0.8, which is 10% higher than the performance of the model constructed by the traditional early colorectal cancer marker combination (ROC in the advanced adenoma vs healthy control group is 0.699), indicating that the model has a high diagnostic efficacy, which makes the screening of the disease more efficient and accurate, can timely detect potential patients, and provide valuable opportunities for early treatment.

[0064] 3. In the present invention, a six-classification algorithm is used at the same time, and a combined differential diagnosis model of 7 biomarkers is constructed through a gradient boosting algorithm. It is found that the colorectal cancer diagnosis model constructed using 7 biomarkers including trefoil factor 1, trefoil factor 3, insulin-like growth factor binding protein 1, insulin-like growth factor binding protein 4, serine protease inhibitor A1, osteopontin, and growth differentiation factor 15 has the best diagnostic efficacy and can be used to more efficiently predict early colorectal cancer. The accuracy of the model is 0.78 and the consistency is 0.729. The diagnostic sensitivity for early colorectal cancer is 79.4%, the specificity is 94.4%, the positive predictive value is 73.5%, and the negative predictive value is 95.9%; the diagnostic sensitivity for advanced adenomas is 73.4%, the specificity is 94.7%, the positive predictive value is 73.4%, and the negative predictive value is 94.7%. The effect is significantly better than the existing diagnostic model, and the accuracy, sensitivity and specificity of diagnosis are significantly improved. It can be used to efficiently differentiate and diagnose early colorectal cancer, advanced adenomas, benign polyps, inflammatory diseases, healthy individuals and other cancer populations, so as to intervene in patients in time; the multi-classification model can provide clinicians with a more comprehensive and accurate diagnostic basis, help to formulate personalized treatment plans, and improve the scientificity and effectiveness of medical decision-making.

[0065] 4. The combined differential diagnosis model of 7 biomarkers constructed by the present invention is convenient and fast, and the test results are highly consistent with the clinical gold standard test results. At the same time, it significantly reduces the cost of diagnosing early colorectal cancer and has good application prospects.

[0066] 5. The combined differential diagnosis model of 7 biomarkers constructed by the present invention can accurately identify and diagnose patients with early colorectal cancer, so as to facilitate early detection and early intervention, promote early detection and early treatment of early colorectal cancer, and meet urgent clinical needs.

[0067] Detailed description

[0068] (1) Diagnosis or testing

[0069] The diagnosis or detection here refers to the detection or assay of biomarkers in a sample, or the content of a target biomarker, such as the absolute content or relative content, and then the presence or quantity of the target marker is used to indicate whether the individual providing the sample may have or suffer from a certain disease, or the possibility of having a certain disease. The meanings of diagnosis and detection here are interchangeable. The result of such a test or diagnosis cannot be directly used as a direct result of illness, but is an intermediate result. If a direct result is obtained, other auxiliary means such as pathology or anatomy are required to confirm that a certain disease is present. For example, the present invention provides a variety of new biomarkers associated with early colorectal carcinogenesis, and changes in the content of these markers are directly associated with whether or not colorectal cancer is present.

[0070] (2) Association between markers or biomarkers or differentially expressed proteins and early colorectal cancer or advanced adenoma

[0071] Markers, biomarkers and differential proteins have the same meaning in the present invention. The connection here means that the appearance or change in the content of a certain biomarker in a sample has a direct correlation with a specific disease, for example, a relative increase or decrease in the content indicates that the possibility of suffering from the disease is higher than that of healthy people.

[0072] If multiple different markers appear in a sample at the same time or their contents change relatively, it means that the possibility of suffering from the disease is higher than that of healthy people. That is to say, among the types of markers, some markers are strongly associated with the disease, some markers are weakly associated with the disease, or some are even not associated with a specific disease. One or more of the markers with strong correlation can be used as markers for diagnosing the disease, and those markers with weak correlation can be combined with strong markers to diagnose a disease, increasing the accuracy of the test results.

[0073] For the numerous biomarkers in serum discovered by the present invention, these markers can be used to distinguish colorectal cancer from healthy people or benign disease people. The markers here can be used alone as a single marker for direct detection or diagnosis, and the selection of such a marker indicates that the relative change in the content of the marker has a strong correlation with early colorectal cancer. Of course, it is understandable that one or more markers with a strong correlation with early colorectal cancer can be selected for simultaneous detection. It is normal to understand that in some ways, selecting a biomarker with a strong correlation for detection or diagnosis can achieve a certain standard of accuracy, such as 60%, 65%, 70%, 80%, 85%, 90% or 95% accuracy, which can explain that these markers can obtain the intermediate value of diagnosing a certain disease, but it does not mean that it can be directly confirmed that a certain disease is present.

[0074] Of course, differential proteins with larger ROC values ​​can also be selected as diagnostic markers. The so-called strength is generally calculated and confirmed by some algorithms, such as the contribution rate of markers to colorectal cancer or weight analysis. Such calculation methods can be significance analysis (p value or FDR value) and fold change (Fold change). Multivariate statistical analysis mainly includes principal component analysis (PCA), partial least squares discriminant analysis (PLS-DA) and orthogonal partial least squares discriminant analysis (OPLS-DA), and of course other methods, such as ROC analysis. Of course, other model prediction methods are also possible. When selecting biomarkers, the differential proteins disclosed in the present invention can be selected, or other existing known marker combinations can be selected or combined for prediction through model methods.

[0075] (3) Definition of disease terms

[0076] Colorectal cancer: also known as colorectal cancer, refers to cancer originating from the large intestine epithelium, including colon cancer and rectal cancer. Adenocarcinoma is the most common pathological type, and very few are squamous cell carcinoma. In my country, rectal cancer is the most common, followed by colon cancer (sigmoid colon, cecum, ascending colon, descending colon and transverse colon). The treatment of colorectal cancer should adopt the principle of individualized treatment. According to the patient's age, constitution, pathological type of the tumor, and invasion range (staging), appropriate treatment methods should be selected, including radical surgery, chemotherapy, targeted therapy, radiotherapy, etc.; the formation of colorectal cancer generally goes through the development process of normal mucosal hyperplasia, advanced adenoma (malignant), and adenocarcinoma (malignant), which generally takes 5-10 years. Therefore, early screening, diagnosis and treatment are the most effective means to reduce the mortality rate of colorectal cancer. In particular, if intervention can be carried out at the polyp adenoma (malignant) stage, the occurrence of colorectal cancer can be effectively prevented. Advanced adenoma (AA) is a precancerous lesion that is ≥1 cm in size or has ≥25% of villous components of any size or high-grade dysplasia. Over time, it is easy to develop into colorectal cancer. If tumor biomarkers with certain early warning effects can be found in the early stages of colorectal cancer, and colorectal cancer and advanced adenoma (malignant tumor) can be diagnosed, it will be of great significance to improve the treatment effect and prognosis of patients.

[0077] Early colorectal cancer: In the present invention, early colorectal cancer includes early colorectal cancer and advanced adenoma.

[0078] Early colorectal cancer: Early colorectal cancer refers to colorectal epithelial tumors of any size whose invasion depth is limited to the mucosa and submucosa, regardless of the presence or absence of lymph node metastasis.

[0079] Adenoma: A benign tumor originating from the glandular epithelium of the colorectal mucosa, including colon adenoma and rectal adenoma, is a common benign intestinal tumor. According to the structural characteristics of adenoma, it can be divided into tubular adenoma, villous adenoma and tubulovillous adenoma. It can be removed by endoscopic high-frequency electrocoagulation, laser, microwave coagulation, etc., or surgical resection can be selected, and regular follow-up is required. Those with malignant transformation can choose other treatments (such as radiotherapy, chemotherapy, surgery, etc.) according to the situation.

[0080] Advanced adenoma: refers to tubulovillous adenoma, villous adenoma and / or adenoma with high-grade dysplasia with a diameter greater than 1 cm. It is considered a precancerous lesion because of its close relationship with the occurrence of colorectal cancer. Advanced adenoma should be removed in time to prevent it from evolving into colorectal cancer.

[0081] Polyp: A tumor that protrudes from the surface of the colorectum. It can be an adenoma or hyperplasia of the intestinal mucosa. Before the pathological nature is determined, it is collectively called a polyp. Benign polyps refer to adenomas or tumors that have been diagnosed as benign by pathological diagnosis. Whether polyps need surgical resection is mainly related to the size, shape, and nature of the polyps. 1. If the diameter of the polyp is less than 2cm, surgical resection is generally not required, and regular colonoscopy is sufficient; 2. If the diameter of the intestinal polyp is greater than 2cm, surgical resection is recommended; 3. If the intestinal polyp has a tendency to become malignant, surgical resection is recommended regardless of the diameter of the polyp.

[0082] Inflammatory bowel disease: It is a non-specific chronic inflammatory disease of the intestine, mainly including ulcerative colitis and Crohn's disease. The former mainly damages the colon and rectum, while the latter can damage any part of the gastrointestinal tract from the mouth to the anus, and is more common in the terminal small intestine and colon. Treatment mainly includes drug therapy, endoscopic therapy and surgical treatment. The treatment goal is to promote the healing of the intestinal mucosa, alleviate clinical symptoms, prevent the occurrence of related complications, improve the patient's quality of life, and prevent disease recurrence.

[0083] Therefore, the prediction model provided by the present invention can quickly distinguish patients with early colorectal cancer, advanced adenoma, benign polyps, inflammatory bowel disease and healthy people based on the changes in the concentration of biomarkers in body fluid samples.

[0084] (4) Gold standard for diagnosis of early colorectal cancer: Patients with early colorectal cancer often have no clinical symptoms or signs. Diagnosis relies on standardized colonoscopy performed by qualified physicians, with biopsy tissue pathology as the basis for diagnosis. BRIEF DESCRIPTION OF THE DRAWINGS

[0085] Figure 1 The volcano map shows the differentially expressed proteins between early colorectal cancer and healthy controls.

[0086] Figure 2 This is a graph showing the performance analysis results of candidate markers for early colorectal cancer;

[0087] Figure 3 Random forest model analysis diagram for early colorectal cancer + advanced adenoma vs healthy controls constructed for 12 markers;

[0088] Figure 4 Random forest model analysis of 12 markers for early colorectal cancer vs healthy controls;

[0089] Figure 5 Random forest model analysis of advanced adenomas vs healthy controls constructed for 12 markers;

[0090] Figure 6 The volcano plot shows the differential proteins between advanced adenomas and healthy controls;

[0091] Figure 7 This is a graph showing the performance analysis results of candidate markers for advanced adenoma;

[0092] Figure 8 This is the result diagram of the importance analysis of 18 candidate markers;

[0093] Fig. 9 Performance analysis of the random forest model constructed for 7 markers between early colorectal cancer + advanced adenoma vs healthy controls;

[0094] Fig.10 Performance analysis of the random forest model constructed for 7 markers between early colorectal cancer and healthy controls;

[0095] Fig.11 Performance analysis of the random forest model constructed for 7 markers between advanced adenomas and healthy controls;

[0096] Fig.12 Performance analysis of the random forest model constructed for the 7 markers in the validation set between early colorectal cancer + advanced adenoma vs healthy controls;

[0097] Fig.13 Performance analysis of the random forest model constructed for the 7 markers in the validation set between early colorectal cancer and healthy controls;

[0098] Fig.14 Performance analysis of the random forest model constructed for the 7 markers in the validation set between advanced adenomas and healthy controls;

[0099] Fig.15 Figure 1. Performance evaluation (accuracy and consistency) results of the best models constructed for different marker combinations.

[0100] Fig.16This is a performance evaluation result diagram of the best combined joint diagnosis model constructed in Example 2 in the test group;

[0101] Fig.17 This is a performance evaluation result diagram of the best combined joint diagnosis model constructed in Example 2 in the validation group;

[0102] Fig.18 This is a graph showing the performance evaluation (accuracy and consistency) results of the optimal model constructed based on 6 different algorithms in Example 3. DETAILED DESCRIPTION

[0103] The present invention is further described in detail below in conjunction with the accompanying drawings and examples. It should be noted that the following examples are intended to facilitate understanding of the present invention and do not have any limiting effect on it. The reagents used in this example are all known products and were obtained by purchasing commercially available products.

[0104] Example 1 Screening of biomarkers for early colorectal carcinoma and advanced adenoma using proteomics and construction of models

[0105] In this embodiment, proteomics methods are used to collect plasma samples from patients at different stages of colorectal cancer tumor progression (inflammatory diseases-benign polyps-advanced adenomas-colorectal cancer) and healthy controls, and different samples are analyzed by high performance liquid chromatography-tandem mass spectrometry (HPLC-MS / MS). Based on orthogonal partial least squares discriminant analysis and significance analysis methods, proteins with significant differences between early colorectal cancer and healthy controls are first screened, and finally 12 differential proteins with obvious correlation with early colorectal cancer are screened. However, in the random forest model constructed with the 12 proteins, the diagnostic efficacy for early colorectal carcinogenesis (early colorectal cancer and advanced adenomas) is low, and the diagnostic efficacy for advanced adenomas is significantly reduced. Therefore, in order to improve the diagnostic efficacy of early colorectal cancer and advanced adenoma, differential proteins were screened again for advanced adenoma and healthy groups, and finally the top 10 differential proteins ranked in importance were screened, and the 7 protein markers screened by the Boruta algorithm were further used to construct a model, which had good risk prediction ability in the early colorectal cancer, advanced adenoma and early colorectal cancer + advanced adenoma (early colorectal cancer) groups. A multi-marker joint detection model was further constructed according to the gradient boosting algorithm, and the diagnostic efficacy of different models was evaluated by ROC analysis. It was finally found that the diagnostic efficacy of the 7 biomarkers constructed in the present invention was the highest, which can be used for the efficient differential diagnosis of early colorectal cancer, advanced adenoma, benign polyps, inflammatory diseases, healthy individuals and other cancers.

[0106] The specific steps are as follows:

[0107] 1. Sample Collection

[0108] This research team collected 150 cases of early colorectal cancer, 50 cases of advanced adenomas, 50 cases of inflammatory bowel disease, 50 cases of benign polyps and 50 healthy controls from January 2018 to December 2020. All patients enrolled signed informed consent. Among them, patients with early colorectal cancer, advanced adenomas, and benign polyps were diagnosed by colonoscopy and pathological histology, patients with inflammatory bowel disease were diagnosed by colonoscopy and laboratory tests combined with clinical diagnosis, and healthy controls were normal people with routine physical examinations. Inclusion criteria for patients with early colorectal cancer and advanced adenomas:

[0109] (a) No history of other malignant tumors;

[0110] (b) have not received radiotherapy, chemotherapy or anti-tumor treatment;

[0111] (c) Patients without other malignant tumors or autoimmune diseases.

[0112] The healthy subjects in the control group were selected from the physical examination center; the colonoscopy screening showed no intestinal lesions, laboratory examinations showed no abnormalities in tumor markers and biochemical indicators, and no history of malignant tumors. After informed consent, all collected plasma samples were stored in a plasma bank at -80°C.

[0113] 2. Sample processing and enzymatic hydrolysis

[0114] First, the plasma samples were centrifuged for 15 minutes (15000xg), and the supernatant was filtered and immunoaffinity chromatography was performed to remove 14 high-abundance proteins. Then, the samples were concentrated in a centrifuge (4000xg, 1 hour) using a concentration tube with a cut-off molecular weight of 3kDa. The concentrated solution was recovered and the solution was replaced (Buffer Exchange) using a desalting column with a cut-off molecular weight of 7kDa in a centrifuge (1000xg, 2 minutes). The replacement solution was AEX-A (20mM Tris, 4M Urea, 3% isopropanol, pH8.0). Using AEX-A as a blank, the protein concentration in the sample was determined using the BCA method (protein concentration detection method). According to the sample grouping in Table 1, TCEP (Thermo Scientific, CAT#77720) was added to the sample and incubated at 37°C for 30 minutes for protein reduction. Then, the corresponding 6-plex TMT reagent (Thermo Scientific, CAT#90309) was added and incubated for 1 hour at room temperature in the dark for TMT labeling reaction. After that, the sample was buffer exchanged with AEX-A using Zeba columns (Thermo Scientific, CAT#89890). After mixing the 6-plex TMT labeled samples, 2 mL of AEX-A was added to the mixed samples to a final volume of 5.5 mL. The samples were filtered using a 0.22 μm filter and separated using a 2D-HPLC system. The collected fractions were freeze-dried and finally Trypsin-Lysin C enzyme mixture (Thermo Scientific, CAT#A41007) was added. The samples were incubated at 37°C for 5 hours for enzymatic digestion, and 5 μL of 10% TFA (trifluoroacetic acid) was added to terminate the enzymatic digestion reaction. A total of 60 2D-HPLC fractions after digestion were used for nano-LC-MS / MS analysis.

[0115] Table 1. Proteomics research sample grouping (40 batches, taking batch 1 as an example)

[0116]

[0117] 3. LC-MS / MS Data Acquisition and Database Search Analysis

[0118] The LC-MS / MS system was Easy-nLC 1200 (Thermo Scientific) coupled with Q Exactive HFX (ThermoScientific). Mobile phase A was an aqueous solution containing 0.1% formic acid and 2% acetonitrile; mobile phase B was an aqueous solution containing 0.1% formic acid and 80% acetonitrile. The homemade analytical column was 20 cm long and filled with ReproSil-Pur C 18, 1.9 μm particles from Dr. Maisch GmbH. 1 μg of peptide was dissolved in mobile phase A and separated using the EASY-nLC 1200 ultra-high performance liquid phase system. The liquid phase gradient was set as follows: 0-26 min, 7%~22%B; 26-34 min, 22%~32%B; 34-37 min, 32%~80%B; 37-40 min, 80%B, and the liquid phase flow rate was maintained at 450 nL / min.

[0119] The peptides separated by the HPLC system were injected into the NanoFlex ion source for nebulization and then entered the Q Exactive HF-X for mass spectrometry analysis. The ion source voltage was set to 2.1 kV, the primary mass spectrometry scan range was set to 400-1200, and the resolution was 60,000 (MS Resolution); the starting point of the secondary mass spectrometry scan range was 100 m / z, and the resolution was set to 15,000 (MS2Resolution). The data-dependent scanning (DDA) mode was set so that the TOP 20 parent ions entered the HCD collision cell in sequence for fragmentation and then performed secondary mass spectrometry analysis in sequence. The automatic gain control (AGC) was set to 5E4, the signal threshold was set to 1E4, and the maximum injection time was set to 22 ms. In order to avoid repeated scanning of high-abundance peptides, the dynamic exclusion time of tandem mass spectrometry analysis was set to 30 seconds.

[0120] The mass spectrometry data obtained by LC-MS / MS were retrieved using Maxquant (v1.6.15.0). The data type is TMT proteomics data based on secondary reporter ion quantification. The secondary spectrum used for quantification requires that the parent ion accounts for more than 75% in the primary spectrum. The database source is Homo_sapiens_9606_proteome (release:2021-10-14, sequence: 20614) of the Uniprot database, and a common contamination library is added to the database. Contaminating proteins are deleted during data analysis; the enzyme cutting method is set to Trypsin / P; the number of missed cutting sites is set to 2; the parent ion mass error tolerance of the First search and Main search is set to 20ppm and 5ppm, respectively, and the mass error tolerance of the secondary fragment ion is 20ppm. The fixed modification is cysteine ​​alkylation, and the variable modification is methionine oxidation and protein N-terminal acetylation. The FDR for protein identification and PSM identification is set to 1%.

[0121] 4. Screening of differentially expressed proteins with the highest diagnostic efficacy in early colorectal cancer

[0122] 1. Screening of differential protein markers in early colorectal cancer

[0123] Univariate analysis and multivariate statistical analysis were combined to screen for differentially expressed proteins between early colorectal cancer and healthy groups. Univariate analysis mainly included the significance analysis (p value or FDR value) and fold change of characteristic ions in different groups, and multivariate statistical analysis mainly included principal component analysis (PCA), partial least squares discriminant analysis (PLS-DA) and orthogonal partial least squares discriminant analysis (OPLS-DA). Unsupervised principal component analysis can analyze the separation trend of proteins between groups; supervised orthogonal partial least squares discriminant analysis can analyze the degree of protein difference between groups.

[0124] We identified a total of 3051 proteins and quantified 1631 proteins, including some newly discovered markers associated with early colorectal cancer. For the 1631 proteins found, we obtained proteins with significant differences in content. All statistical analyses were performed using R. Specific R-related information is shown in Table 2.

[0125] Table 2. R used in the present invention and its related information

[0126]

[0127] The variable importance for the projection (VIP) was calculated to measure the influence and explanatory power of the expression pattern of each protein on the classification and discrimination of each group of samples, and the Wilcoxon rank sum test was further performed to obtain the corrected p value (FDR). The volcano map of differential proteins between early colorectal cancer and healthy controls is shown in the figure. Figure 1 As shown in Figure 2, 57 proteins were significantly upregulated and 62 proteins were significantly downregulated in the serum of patients with early colorectal cancer and healthy controls. Figure 2 , the horizontal axis is the AUC obtained by ROC analysis, the vertical axis is the VIP value obtained by OPLS-DA analysis, and the size of the point represents the P value calculated by the Wilcoxon test.

[0128] The importance of the differential proteins was ranked by T-test difference analysis and OPLS-DA analysis. According to the ranking of the importance of the markers, in this embodiment, the top 12 differential proteins in importance between the early colorectal cancer and healthy groups were listed, and the information of the 12 differential proteins is shown in Table 3. At the same time, the single diagnostic performance ROC curves of the 12 differential proteins were established, and the area under the curve (AUC) was used to judge the quality of the experimental results. AUC of 0.5 indicates that a single protein has no diagnostic value; AUC greater than 0.5 indicates that a single protein has diagnostic value; the larger the AUC, the higher the diagnostic value of a single protein; similarly, the possible range of AUC values ​​- 95% confidence interval, the closer it is to 1, the higher and more reliable the diagnostic value of the protein; at the same time, the closer the ROC sensitivity and specificity are to 100%, the higher the diagnostic efficiency of the method; the cutoff value represents the specific threshold used to distinguish positive and negative results in the diagnostic test. When the cutoff value is too high, it may lead to an increase in false negatives and omission of individuals who are truly sick; when the cutoff value is too low, it may lead to an increase in false positives and misjudge healthy individuals as sick. Therefore, a suitable cutoff value can more accurately distinguish patients from healthy people, thereby improving the accuracy of diagnosis; median importance (medianImp) reflects the intermediate level of the relative importance of differential proteins in distinguishing different groups or states in differential marker screening. The higher the median importance, the greater the overall contribution of the protein to the distinction:

[0129] Table 3. The 12 most important differentially expressed proteins in early colorectal cancer vs. healthy controls

[0130]

[0131] The correlation between the concentration changes of the 12 biomarkers and whether or not a person has early colorectal cancer can be distinguished by the AUC value, 95% confidence interval, sensitivity, specificity, etc. in Table 3, among which the AUC value is the most intuitive and obvious. The higher the AUC value, the more accurately the biomarker can distinguish between people with early colorectal cancer and those without colorectal cancer.

[0132] As can be seen from Table 3, the concentration changes of the 12 biomarkers are significantly correlated with whether or not a patient has early colorectal cancer. The concentration changes of any one of the 12 biomarkers alone can be used to distinguish early colorectal cancer from healthy controls.

[0133] At the same time, the ELISA (enzyme-linked immunosorbent assay) method was used to further verify the 12 candidate protein markers for colorectal cancer, including blood samples from 64 patients with early colorectal cancer, 63 patients with advanced adenomas, and 121 healthy controls. The random forest algorithm was used to construct a model consisting of the 12 markers. The final performance of the model is as follows: Figure 3-Figure 5 As shown, Figure 3 Random forest model analysis of 12 markers for early colorectal cancer + advanced adenoma vs healthy controls. Figure 4 Random forest model analysis of 12 markers for early colorectal cancer vs healthy controls. Figure 5 Random forest model analysis of advanced adenomas vs healthy controls constructed for 12 markers. Figure 3~Figure 5 It can be seen that the model constructed using 12 protein markers screened from early colorectal cancer and healthy controls has a good risk prediction ability in the early colorectal cancer group (AUC=0.947), a reduced risk prediction ability in the early colorectal cancer + advanced adenoma (early colorectal cancer) group (AUC=0.824), and a significantly reduced prediction performance in advanced adenomas (AUC=0.699), with an AUC lower than 0.8. Therefore, it cannot effectively diagnose advanced adenomas, and its diagnostic value for early colorectal cancer (including early colorectal cancer + advanced adenomas) is also low.

[0134] 2. Re-screening of differential protein markers in advanced adenomas

[0135] Therefore, in order to improve the diagnostic efficiency of patients with early colorectal cancer (early colorectal cancer + advanced adenoma) and advanced adenoma patients, this example again screened for differential proteins in advanced adenoma and healthy groups. The TMT labeling quantitative technology strategy based on the mass spectrometry platform was used for the discovery of early protein markers for colorectal cancer. The research cohort included 50 healthy controls and 50 blood samples from patients with advanced adenoma. Candidate markers were screened out through T-test difference analysis and OPLS-DA analysis. The specific results are as follows: Figure 6~Figure 7 shown.

[0136] from Figure 6 It can be seen that in the advanced adenoma vs healthy group, 16 proteins were significantly upregulated in the serum of patients with advanced adenoma, and 27 proteins were significantly downregulated. The results of ROC and OPLS-DA analysis are shown in Figure 7 , the horizontal axis is the AUC obtained by ROC analysis, the vertical axis is the VIP value obtained by OPLS-DA analysis, and the size of the point represents the P value calculated by the Wilcoxon test. At the same time, the importance of the differential proteins is ranked. According to the importance ranking of the markers, in this embodiment, the top 10 differential proteins in the advanced adenoma and healthy groups are listed, and the information of the 10 differential proteins is specifically shown in Table 4;

[0137] Table 4. The top 10 differentially expressed proteins in advanced adenomas vs. healthy controls

[0138]

[0139] The correlation between the concentration changes of the 10 differentially expressed proteins and whether or not a patient has advanced adenoma can be distinguished by the AUC value, 95% confidence interval, sensitivity, specificity, etc. in Table 4, among which the AUC value is the most intuitive and obvious. The higher the AUC value, the more accurately the differentially expressed protein can distinguish between people with advanced adenoma and healthy people.

[0140] As can be seen from Table 4, the concentration changes of the 10 differential proteins are significantly correlated with whether or not the patient has advanced adenoma. The concentration change of any one of the 10 differential proteins can be used to distinguish advanced adenoma from healthy controls.

[0141] At the same time, the ELISA method was used in this example to conduct a large-scale validation of 12 candidate protein markers screened in early colorectal cancer and 10 candidate protein markers screened in advanced adenomas, a total of 18 candidate protein markers for colorectal cancer. The cohort included 327 blood samples of early colorectal cancer, 322 advanced adenomas, and 605 healthy control patients. The Boruta algorithm was used to evaluate the importance of the 18 candidate markers, and finally 7 markers that made significant contributions to the model were screened and used to build the final model. The specific results are as follows: Figure 8 As shown, from Figure 8 It can be seen that in this embodiment, the 7 markers that were finally screened and significantly contributed to the model were: TFF3, IGFBP4, OPN, SERPINA1, GDF-15, IGFBP1, and TFF1.

[0142] The parameters of the random forest model are specifically shown in Table 5.

[0143] Table 5. Random forest model parameters

[0144]

[0145] The model composed of 7 markers constructed using the random forest algorithm has the following final performance: Figure 9-11 As shown, Fig. 9 Performance analysis of the random forest model constructed for 7 markers between early colorectal cancer + advanced adenoma vs healthy controls, Fig.10 Performance analysis of the random forest model constructed for 7 markers between early colorectal cancer and healthy controls. Fig.11 Performance analysis of the random forest model constructed for 7 markers between advanced adenomas and healthy controls. Figure 9~Figure 11 It can be seen that the model constructed by using the 7 protein markers screened out has good risk prediction ability in the groups of early colorectal cancer, advanced adenoma and early colorectal cancer + advanced adenoma (early colorectal carcinoma). Among them, in the group of early colorectal carcinoma vs. healthy control, the model AUC value reached 0.896; in the group of early colorectal cancer vs. healthy control, the model AUC value reached 0.983; in the group of advanced adenoma vs. healthy control, the model AUC value reached 0.807. The AUC values ​​all reached above 0.8, and the diagnostic performance for early colorectal carcinoma (including advanced adenoma and early colorectal cancer) was also significantly improved.

[0146] In summary, the 7 markers that were finally screened and significantly contributed to the model are all differential markers contained in advanced adenomas. However, when only screening is performed from protein markers of early colorectal cancer, the best 7 markers that significantly contributed to the model of the present invention cannot be screened.

[0147] 3. Verification of the performance of the model constructed with 7 protein markers

[0148] In this example, the ELISA method was also used to further conduct independent cohort validation on the 7 candidate protein markers for colorectal cancer that were screened. The cohort contained blood samples from 86 patients with early colorectal cancer, 130 patients with advanced adenomas, and 173 healthy control patients. The random forest model constructed in the training cohort was used for validation.

[0149] Specific results such as Figure 12~Figure 14 As shown, Fig.12 Performance analysis of the random forest model constructed for the 7 markers in the validation group between early colorectal cancer + advanced adenoma vs healthy controls, Fig.13 Performance analysis of the random forest model constructed for the 7 markers in the validation group for early colorectal cancer vs healthy controls. Fig.14 Performance analysis of the random forest model constructed for the 7 markers in the validation set between advanced adenomas and healthy controls. Figure 12~Figure 14 It can be seen that the prediction results in the validation group are highly consistent with the actual clinical diagnosis results, and have good risk prediction capabilities in the early colorectal cancer, advanced adenoma, and early colorectal cancer + advanced adenoma (early colorectal carcinoma) groups. Among them, in the early colorectal carcinoma vs. healthy control group, the model AUC value reached 0.873; in the early colorectal cancer vs. healthy control group, the model AUC value reached 0.984; in the advanced adenoma vs. healthy control group, the model AUC value reached 0.800. The AUC values ​​all reached 0.8 and above, and the diagnostic performance for early colorectal carcinoma (including advanced adenoma and early colorectal cancer) was also significantly improved.

[0150] Therefore, it can be seen that the diagnostic model constructed by the present invention using 7 markers has good predictive performance and accuracy and has the best diagnostic efficacy.

[0151] It has been confirmed that the specific information of the 7 new biomarkers (TFF1, TFF3, IGFBP1, IGFBP4, SERPINA1, OPN, GDF-15) that meet the standards, have significant differences and are highly important are as follows: Trefoil factor 1 (TFF1) is a protein or amino acid sequence with a UniProt database number of P04155; Trefoil factor 3 (TFF3) is a protein or amino acid sequence with a UniProt database number of Q07654; Insulin like growth factor binding protein 1 (IGFBP1) is a protein or amino acid sequence with a UniProt database number of P08833; Insulin like growth factor binding protein 4 (IGFBP4) is a protein or amino acid sequence with a UniProt database number of P22692; Serpin family A member 1,SERPINA1) is a protein or amino acid sequence with a UniProt database number of P01009; osteopontin (OPN) is a protein or amino acid sequence with a UniProt database number of P10451; growth differentiation factor 15 (GDF-15) is a protein or amino acid sequence with a UniProt database number of Q99988.

[0152] Example 2 Construction and verification of a six-category diagnostic model

[0153] Therefore, in this embodiment, the combination of seven different biomarkers obtained by screening in Example 1 is selected to construct a six-category joint diagnostic model. These models are used to distinguish early colorectal carcinoma, early colorectal cancer, advanced adenoma, benign polyps, inflammatory bowel disease and healthy people, and specifically include the following processes: (1) Construction and screening of the best diagnostic model; (2) Verification of the effect of the best diagnostic model. The specific screening process and results are as follows (in the present invention, the two-classification model adopts random forest to construct the model, and the AUC value is used as the evaluation index; when the six-classification model is constructed, because multiple categories are involved, the AUC value is usually not applicable. Therefore, the present invention uses accuracy, consistency, sensitivity, specificity and other indicators to measure the diagnostic efficacy of the model):

[0154] 1. Construction and screening of the best diagnostic model

[0155] 1. Get data

[0156] Study population:

[0157] From September 2022 to March 2023, 1962 colorectal cancer test cohorts and 390 colorectal cancer validation cohorts were collected, and all enrolled patients signed informed consent. Among them, patients with early colorectal cancer, advanced adenomas, benign polyps, and other cancers were diagnosed by colonoscopy and pathological histology, patients with inflammatory bowel disease were diagnosed by colonoscopy and laboratory tests combined with clinical diagnosis, and healthy controls were normal in routine physical examinations, tumor marks, and negative occult blood in stool. In the test group, early colorectal cancer n=321, advanced adenomas n=321, benign polyps n=226, inflammatory bowel disease n=299, healthy controls n=602, other cancers n=193) and validation group (early colorectal cancer n=64, advanced adenomas n=64, benign polyps n=43, inflammatory bowel disease n=60, healthy controls n=120, other cancers n=39). The data information is shown in Table 6 (in this embodiment, the other cancers include other digestive tract cancers, such as esophageal cancer, gastric cancer, liver cancer, pancreatic cancer, bile duct cancer, etc. The six-category detection model of the present invention can not only accurately distinguish early colorectal cancer from early colorectal cancer, advanced adenomas, benign polyps, inflammatory bowel disease and healthy people, but also shows significant advantages in distinguishing early colorectal cancer from other digestive tract cancers (such as esophageal cancer, gastric cancer, liver cancer, pancreatic cancer, bile duct cancer, etc.)):

[0158] Table 6. Modeling sample information

[0159]

[0160] The inclusion criteria for patients with early colorectal cancer were: (a) no history of other malignancies, and (b) surgical treatment within one month after blood collection, and colorectal cancer was confirmed by postoperative pathology. Healthy subjects in the control group were selected from the physical examination center; endoscopy confirmed that these individuals had no signs of gastric disease and no history of malignancies. After informed consent, all serum samples collected were stored in a serum bank at -80°C.

[0161] In this example, the collected serum samples were subjected to enzyme-linked immunosorbent assay to obtain the concentrations of seven protein markers, namely, TFF1, TFF3, IGFBP1, IGFBP4, SERPINA1, OPN, and GDF-15.

[0162] 2. Statistical analysis of experimental data

[0163] The Shapiro Wilk's test was used to assess normal distribution, and the nonparametric test Wilcoxon test was used to analyze the differences in blood marker concentrations between colorectal cancer patients and healthy controls in the model group and the test group, respectively. In the model group, a combined diagnostic model of seven colorectal cancer markers was constructed using a combination of multiple machine learning methods. The area under the receiver operator characteristic (ROC) curve (AUC) was estimated with a 95% confidence interval (CI) using the predicted probability values ​​to evaluate the discriminatory ability of the multivariate diagnostic model. Using the test group, the Youden index (YI) was calculated to determine the predicted probability cut-off value for distinguishing colorectal cancer patients from normal controls. In addition, ROCs for individual markers and different subgroups were constructed and compared. Standard descriptive statistics, such as frequency, mean, median, positive predictive value (PPV), negative predictive value (NPV), and standard deviation (SD), were calculated to describe the experimental results of the study population. Statistical analysis was performed using R3.6.1, and a p value less than 0.05 was considered statistically significant.

[0164] 3. Construction steps of the six-classification joint diagnosis model (7MP)

[0165] (1) Preliminary comparison and screening of supervised classification algorithm models to build the best diagnostic model

[0166] In this embodiment, in order to screen the best supervised classification algorithm for constructing a prediction model, the concentration matrix of the best 7 protein markers is first used as the original training data set, and the models under different supervised classification algorithms are constructed according to the following steps, and the performance of the different constructed models is compared to screen the best supervised classification algorithm. The specific process is as follows:

[0167] S101, the concentration matrix of seven protein markers, TFF1, TFF3, IGFBP1, IGFBP4, SERPINA1, OPN, and GDF-15, of the samples in the model group was used as the original training data set.

[0168] S102, set the supervised classification algorithm used to build the prediction model, and the grid search range during the algorithm's hyperparameter optimization process. The supervised classification algorithm includes six algorithms: gradient boosting, naive Bayes, support vector machine, neural network, generalized linear, and discriminant analysis. In this step, the grid search range for the hyperparameter optimization of the model is set for each algorithm as shown in Table 7 below.

[0169] Table 7. Parameter grid search ranges of the six algorithms

[0170]

[0171] S103, according to the algorithm and hyperparameter setting range set in step S102, one of the algorithms and the corresponding hyperparameter combination is selected as the parameters for constructing the prediction model.

[0172] S104, the original data set is divided into K subsets according to the K-fold cross validation mechanism. To ensure that the ratio of majority class samples to minority class samples in each fold is the same as that of the original data set, a Stratified K-Folds cross validation mechanism is used to perform data segmentation.

[0173] S105, according to the K training data subsets obtained by segmentation in step S104, one of the subsets is selected as a verification set Ddev.

[0174] S106, merging the training data subsets not selected in step S105 to form a training data set D.train.

[0175] S107, building a prediction model based on the selected supervised classification algorithm and hyperparameters according to the training data set D.train obtained in step S106.

[0176] S108, according to the prediction model obtained in step S107, the AUC value is evaluated on the validation set D.dev, and the prediction model and the corresponding AUC value are stored in the prediction model pool Pool. Step S108 is to evaluate the prediction model obtained in step S107 on the validation set determined in the current iteration, and store both the model and the evaluation results in the prediction model pool for future prediction model selection. The evaluation mentioned in this step can be an AUC value or other reasonable indicators for evaluating model performance.

[0177] S109, determine whether each subset has been used as a validation set. Step S109 is to determine whether the K subsets obtained in step S104 have all been used as validation sets and have been trained on the model. If all subsets have been used as validation sets and have completed training, execute step S110; if there are subsets that have not been used as validation sets, execute step S105. This step ensures that every sample in the original data set has been used as a validation set, improves model stability, and prevents the model from overfitting to a certain subset.

[0178] S110, the AUC average value of all models in the prediction model pool Pool is obtained as the final performance evaluation value of the combined model, and the model parameters and the final performance evaluation AUC value are stored in the optimal model pool Pool.best.

[0179] S111, determine whether all the algorithms and corresponding hyperparameter combinations have constructed prediction models. Step S111 is to determine whether all the algorithms and corresponding hyperparameter combinations obtained in step S102 have constructed prediction models. If all the combinations have completed the construction of the model, then execute step S112; if there are combinations that have not completed the construction of the model, then execute step S103.

[0180] S112, from the optimal model pool Pool.best obtained after the iteration of step S111, for each algorithm, select the prediction model with the highest AUC value, and store it in the candidate prediction model set M.set for colorectal cancer diagnosis.

[0181] S113, the model set M.set obtained in step S112 is evaluated in the test set D.test to obtain an AUC value. The model with the largest AUC value is used as the final prediction model for colorectal cancer diagnosis.

[0182] Through the above model building steps, the optimal models under 6 different algorithms were finally obtained. The 10-fold cross-validation method was used in the modeling process to evaluate the performance of the model in terms of accuracy, consistency, sensitivity, and specificity.

[0183] In the present invention, the test group and the validation group use two completely different batches of samples. The test group is a known sample, and the inventors only screen markers from the test group; the samples of the validation group are only used to verify the diagnostic efficacy of the marker combination of the present invention. The specific results are shown in Table 8 and Fig.15 As shown: the performance evaluation scores of the gradient boosting (GBM) algorithm are all optimal (the comprehensive diagnostic accuracy of prediction of each disease type is 0.768 and the consistency is 0.713).

[0184] Table 8 Performance evaluation of different algorithms for building models to distinguish different disease groups

[0185]

[0186] Based on the above analysis results, in this embodiment, the optimal model constructed by gradient boosting (GBM) is selected as the final prediction model for six-category joint diagnosis. The optimal hyperparameters of the model are obtained through training by 10-fold cross-validation method: learning rate is 0.1, number of decision trees is 150, maximum tree depth is 3, and minimum number of samples of terminal nodes is 10.

[0187] (2) Verification of the combined performance of the optimal joint diagnosis model (7MP)

[0188] In order to further analyze and study the diagnostic value of the six-category diagnostic model (gradient boosting) constructed based on biomarkers of different protein combinations, the diagnostic models constructed based on biomarkers of different protein combinations were compared in performance in the test group in this embodiment. The specific combination forms of different models are shown in Table 9.

[0189] Table 9. Combinations of different diagnostic models

[0190]

[0191] The results are as follows Fig.16 As shown in Table 10, Table 10 is the performance index comparison results of different diagnostic models constructed by the 7 biomarkers screened in Example 1 for six categories. The calculation method of the minimum value, first quartile, median, mean, third quartile and maximum value of accuracy and consistency is as follows: (1) Sort the accuracy or consistency values ​​from small to large; (2) Minimum value: the first value after sorting; (3) First quartile (Q1): multiply the number of data by 0.25. If the result is an integer, take the average of the values ​​of this position and the next position; if it is not an integer, round up to get the position, and the value of this position is Q1; (4) Median: If the number of data is an odd number, the median is the middle value; if it is an even number, it is the average of the two middle values; (5) Mean: the sum of all values ​​divided by the number of data; (6) Third quartile (Q3): multiply the number of data by 0.75, and the processing method is the same as Q1; (7) Maximum value: the last value after sorting.

[0192] Among them, the minimum and maximum values ​​can reflect the extreme conditions of the data and show the worst and best possible performance of the model; the quartiles can help understand the distribution range and dispersion of the data; Q1 and below indicate a lower performance level, and Q3 and above indicate a higher performance level; the median value can reflect the performance at the intermediate level; and the mean value comprehensively reflects the overall average performance. Combining the above statistical values, we can fully understand the overall status, distribution characteristics, and stability of the model performance, thus providing a strong basis for model selection and optimization.

[0193] Table 10. Performance comparison of diagnostic models based on different protein combination biomarkers

[0194]

[0195] As can be seen from Table 10, for the six-category diagnostic model, the seven-item joint detection model (7MP) composed of the best seven markers of the present invention has the best performance. Therefore, the six-category gradient boosting model constructed with the seven protein markers is used as the best joint diagnostic model.

[0196] 2. Determination and verification of the diagnostic performance of the optimal combined diagnostic model (7MP)

[0197] 1. Determination of diagnostic performance of the combined diagnostic model (7MP)

[0198] In order to more accurately determine the diagnostic performance and threshold of the model constructed in this embodiment in different disease classifications, the multi-classification model of the gradient boosting (GBM) algorithm in the model group was used to perform predictive analysis in the test group, and the predicted results were calculated to obtain the predicted probability values ​​of 6 categories (healthy controls, inflammatory bowel disease, benign polyps, advanced adenomas, early colorectal cancer, and other cancers), among which the classification with the largest predicted probability value was the final prediction result of the system.

[0199] The meaning and calculation method of each indicator are as follows:

[0200] The calculation results are as follows: Fig.17 As shown: the accuracy of the model in the model group was 0.761 and the consistency was 0.705. The diagnostic sensitivity of the model for early colorectal cancer was 76.9%, the specificity was 95.9%, the positive predictive value was 78.4%, and the negative predictive value was 95.5%; the diagnostic sensitivity of advanced adenoma was 69.8%, the specificity was 94.5%, the positive predictive value was 71.3%, and the negative predictive value was 94.1%; the diagnostic sensitivity of benign polyps was 74.3%, the specificity was 95.4%, the positive predictive value was 67.7%, and the negative predictive value was 96.6%; the diagnostic sensitivity of inflammatory bowel disease was 67.2%, the specificity was 94.2%, the positive predictive value was 67.7%, and the negative predictive value was 94.1%; the diagnostic sensitivity of other cancers was 77.7%, the specificity was 95.9%, the positive predictive value was 67.3%, and the negative predictive value was 97.5%; the diagnostic sensitivity of healthy controls was 83.6%, the specificity was 95.4%, the positive predictive value was 89.0%, and the negative predictive value was 92.9%.

[0201] 2. Verification of the optimal combined diagnostic model (7MP)

[0202] The prediction performance of the algorithm constructed based on the model group was verified in the validation group (Table 6). The specific results are as follows Fig.18As shown, the accuracy was 0.78 and the consistency was 0.729. The diagnostic sensitivity for early colorectal cancer was 79.4%, the specificity was 94.4%, the positive predictive value was 73.5%, and the negative predictive value was 95.9%; the diagnostic sensitivity for advanced adenoma was 73.4%, the specificity was 94.7%, the positive predictive value was 73.4%, and the negative predictive value was 94.7%; the diagnostic sensitivity for benign polyps was 72.7%, the specificity was 95.9%, the positive predictive value was 69.6%, and the negative predictive value was 96.5%; the diagnostic sensitivity for inflammatory bowel disease was 68.3%, the specificity was 96.3%, the positive predictive value was 77.4%, and the negative predictive value was 94.3%; the diagnostic sensitivity for other cancers was 83.3%, the specificity was 96.0%, the positive predictive value was 68.2%, and the negative predictive value was 98.3%; the diagnostic sensitivity for healthy controls was 85.0%, the specificity was 96.3%, the positive predictive value was 91.1%, and the negative predictive value was 93.5%.

[0203] In summary, the combined diagnostic model constructed in this embodiment, which contains 7 biomarkers (trefoil factor 1 (TFF1), trefoil factor 3 (TFF3), insulin-like growth factor binding protein 1 (IGFBP1), insulin-like growth factor binding protein 4 (IGFBP4), serine protease inhibitor A1 (SERPINA1), osteopontin (OPN), growth differentiation factor 15 (GDF-15)), has good diagnostic value for six categories of early colorectal cancer, advanced adenoma, benign polyps, inflammatory diseases, healthy people and other cancers.

[0204] All patents and publications mentioned in the present specification indicate that these are public technologies in the field and can be used in the present invention. All patents and publications cited here are also listed in the references, just as each publication is specifically cited separately. The present invention described here can be implemented in the absence of any one or more elements, one or more restrictions, and such restrictions are not specifically stated here. For example, in each example here, the terms "comprising", "consisting essentially of..." and "consisting of..." can be replaced by the other two terms of one of the two. The so-called "one" here only means "one", but does not exclude that it only includes one, and can also mean that it includes more than two. The terms and expressions used here are descriptive and not limited by them. There is no intention to indicate that these terms and explanations described in this book exclude any equivalent features, but it can be known that any appropriate changes or modifications can be made within the scope of the present invention and the claims. It can be understood that the embodiments described in the present invention are some preferred embodiments and features, and any person skilled in the art can make some changes and variations based on the essence of the present invention, and these changes and variations are also considered to belong to the scope of the present invention and the scope limited by the independent claims and the appended claims.

Claims

1. Use of a marker for preparing a reagent for predicting whether an individual suffers from early colorectal cancer, characterized in that: The markers consist of trefoil factor 1, trefoil factor 3, insulin-like growth factor binding protein 1, insulin-like growth factor binding protein 4, serine protease inhibitor A1, osteopontin and growth differentiation factor 15, and the early colorectal cancer includes advanced adenoma and early colorectal cancer.

2. The use according to claim 1, characterized in that The reagent is used to detect the content of biomarkers in a body fluid sample; the body fluid sample includes any one or more of saliva, blood, urine, plasma, serum, and cerebrospinal fluid.

3. The use according to claim 2, characterized in that The reagent is used to detect the presence or relative abundance or concentration of a biomarker in a body fluid sample.

4. A kit for predicting whether an individual suffers from early colorectal cancer, characterized in that: A detection reagent for a biomarker for use as described in any one of claims 1 to 3, wherein the early colorectal cancer includes advanced adenoma and early colorectal cancer.

5. A biomarker combination for predicting whether an individual has early colorectal cancer, characterized in that: The combination consists of trefoil factor 1, trefoil factor 3, insulin-like growth factor binding protein 1, insulin-like growth factor binding protein 4, serine protease inhibitor A1, osteopontin and growth differentiation factor 15, and the early colorectal cancer includes advanced adenoma and early colorectal cancer.

6. A system for predicting whether an individual suffers from early colorectal cancer, characterized in that: The system includes a data analysis module, which is used to analyze the detection values ​​of markers, wherein the markers are composed of trefoil factor 1, trefoil factor 3, insulin-like growth factor binding protein 1, insulin-like growth factor binding protein 4, serine protease inhibitor A1, osteopontin and growth differentiation factor 15, and the early colorectal cancer includes advanced adenoma and early colorectal cancer.

7. The system according to claim 6, characterized in that The data analysis module uses the detection values ​​of markers of known samples as a training set, divides the samples into an early colorectal cancer group and a healthy group according to whether they suffer from early colorectal cancer, analyzes the relationship between the detection values ​​of the early colorectal cancer group and the healthy group, and constructs a model.

8. The system according to claim 7, characterized in that The system also includes a data storage module, a data input interface and a data output interface; the data storage module is used to store the detection values ​​of the biomarkers; the data input interface is used to input the detection values ​​of the biomarkers, and the data output interface is used to output the prediction results.

Images