Colorectal cancer intestinal microbial marker, application thereof and method for constructing colorectal cancer detection model

Abstract

The invention discloses a colorectal cancer intestinal microbial marker, application thereof and a method for constructing a colorectal cancer detection model, and belongs to the technical field of biomedicine. Biomarkers related to colorectal cancer pathogenesis and progress are extracted from metagenome data, and a random forest model is constructed; the metagenome of the patient to be detected and the abundance information of the metagenome are input into the colorectal cancer detection model for identification, so that the generalization ability and the anti-overfitting ability of the colorectal cancer detection model are improved, and the condition of the colorectal cancer can be predicted and evaluated more accurately; a doctor can formulate a more effective treatment scheme, and the survival rate and the life quality of a patient are improved; the method also has the advantages of non-invasiveness, simplicity and convenience in operation and the like, a new way can be provided for diagnosis of the colorectal cancer, and the screened microbial marker and the constructed colorectal cancer detection model have relatively high accuracy and specificity and are beneficial to improving the diagnosis efficiency of the colorectal cancer.

Description

Technical Field

[0001] The present invention relates to the field of biomedical technology, and more specifically to a colorectal cancer intestinal microbial marker and its application and a method for constructing a colorectal cancer detection model. Background Art

[0002] Colorectal cancer is a malignant tumor that originates from the epithelial cells of the lining of the colon or rectum. It is one of the most common cancers in the world, with an increasing incidence and mortality rate. The early symptoms of colorectal cancer are not obvious and are often ignored or misdiagnosed; as the disease progresses, patients may experience abdominal pain, diarrhea, constipation, blood in the stool, anemia and other symptoms. If cancer cells spread to other parts of the body, they may also metastasize to organs such as the liver and lungs.

[0003] The diagnosis of colorectal cancer includes colonoscopy, tissue biopsy and imaging examination. At present, there are still some shortcomings in the diagnosis methods of colorectal cancer. For example, colonoscopy requires patients to prepare their intestines, which is traumatic and risky. CT scans can provide high-resolution images to help doctors determine the location, size, shape and other information of the tumor, but radiation may cause certain radiation damage to patients. Although tumor markers in the blood such as CEA and CA19-9 can be used to screen for colorectal cancer, their sensitivity and specificity are not high and cannot be used as a basis for diagnosis. The prognosis assessment of colorectal cancer is not accurate enough, and it is impossible to formulate personalized treatment plans based on the specific conditions of patients.

[0004] Early detection and treatment can significantly improve the survival rate and quality of life of patients; studies have shown that the imbalance of intestinal microbial communities is closely related to the occurrence and development of colorectal cancer. Therefore, there is an urgent need for a microbial marker as a basis for early diagnosis and prognosis evaluation of colorectal cancer. By analyzing the composition and functional changes of patients' intestinal microorganisms, signs of cancer can be detected earlier and the treatment effect can be monitored. Summary of the invention

[0005] The purpose of the present invention is to provide a colorectal cancer intestinal microbial marker and its application and a method for constructing a colorectal cancer detection model, so as to detect signs of cancer earlier and monitor the treatment effect by analyzing the composition and functional changes of the patient's intestinal microorganisms.

[0006] To achieve the above object, the present invention provides the following technical solutions:

[0007] The present invention mentions a colorectal cancer intestinal microbial marker, wherein the intestinal microbial marker includes the following species: TM7phylum_sp_oral_taxon_348, Clostridium_sp_NSJ_42, Parabacteroides_distasonis, Streptococcus_sanguinis, Turicibactersanguinis), Candidatus_Nanosynsacchari_sp_TM7_ANC_38_39_G1_1, Sutterella_wadsworthensis, Actinomyces_dentalis, Veillonella_atypica, Actinomyces_sp_ICM47, Gemmiger_formicilis, Escherichia_coli, Blautia_faecicola, Eubacterium_sulci, Isoptericola_variabilis, Sellimonas_intestinalis, Ruminococcus_sp_AF41_9, Dorea_longicatena, Phocaeicola_vulgatus, Enterococcus_faecium ), Coprococcus catus, Eubacterium recale, Clostridium sp AF20 17LB, Romboutsia timonensis, Agathobaculum butyriciproducens, Bacteroides thetaiotaomicron, Adlercreutzia equolifaciens, Peptostreptococcus stomatis, Candidatus Cibiobacter qucibialis, Bacteroides ovatus, Bacteroides fragilis, Faecalibacterium prausnitzii, Fusicatenibacter saccharivorans.

[0008] The present invention also mentions an application of a colorectal cancer intestinal microbial marker, which includes a product for preparing a diagnosis of whether a patient has colorectal cancer or the risk of colorectal cancer, a target for colorectal cancer disease assessment and treatment, and a construction of a colorectal cancer detection model; the product includes any one of a detection reagent, a detection kit, and a detection chip.

[0009] The present invention also provides a method for constructing a colorectal cancer detection model using colorectal cancer intestinal microbial markers, comprising the following steps:

[0010] (1) Total DNA was extracted from the feces of colorectal cancer patients and healthy people, and high-throughput sequencing was performed after pretreatment. The sequencing results were annotated with species and analyzed for composition, gene abundance statistics, functional annotation, and differential analysis to screen out intestinal microbial markers for colorectal cancer;

[0011] (2) Establish a random forest model to identify colorectal cancer and healthy people through colorectal cancer intestinal microbial markers, evaluate, and obtain a colorectal cancer detection model;

[0012] (3) The metagenome and abundance information of the patient to be tested are input into the colorectal cancer detection model for identification.

[0013] Furthermore, in step (1), the species annotation and composition spectrum analysis includes:

[0014] Alpha diversity: Shannon, Simpson, Insimpson index analysis;

[0015] beta diversity: Bray-CurtisPCoa, PCA, NMDS, UPGMA analysis;

[0016] Bacteria sample composition, sample heatmap;

[0017] Species interaction network analysis.

[0018] Furthermore, in step (1), the gene abundance statistics include: gene Core-Pan curve, gene dilution curve, and correlation analysis between gene numbers in samples.

[0019] Furthermore, in the step (1), the functional annotation includes: KEGG data rate functional annotation analysis, HUMAnN3: quantitative pathway abundance, KO functional abundance and analysis, Module functional abundance and analysis, Pathway functional abundance and analysis.

[0020] Furthermore, in the step (1), the difference analysis includes: Lefse analysis, dominant species difference, multivariate variance adonis, MaAsLin, rank sum test difference, random forest, pathway functional abundance and analysis.

[0021] Furthermore, high-throughput sequencing is performed in step (1), including: removing adapters using fastp, removing host sequences using bowtie2, performing marker-based species abundance analysis using MetaPhlAn4, and performing functional analysis using HUMAnN33.

[0022] Furthermore, in step (2), a random forest model for identifying colorectal cancer and healthy people is established by using colorectal cancer intestinal microbial markers, and an evaluation is performed to obtain a colorectal cancer detection model, specifically:

[0023] Colorectal cancer patients and healthy people were divided into training sets and test sets, and the random forest model was trained on the training sets using sklearn.ensemb1e.RandomForestClassifier in Python;

[0024] The evaluation method is: measuring the degree of fit of the random forest model to the data by drawing a learning curve, and evaluating the performance of each set of parameters in the random forest model by ten-fold cross validation to select the optimal parameter combination.

[0025] Furthermore, the training parameters of the random forest model in step (2) are: base learner data nesfimators = {100, 500, 1000}, maximum tree depth max_depth = {1, 2, 3, 7, 9}, maximum feature number max_features = ["log2", "sqrt"], and parameter tuning is performed using GridSearchCV from the sci kit-learn library of Python.

[0026] According to the specific embodiments provided by the present invention, the present invention discloses the following technical effects:

[0027] (1) The present invention extracts biomarkers related to the pathogenesis and progression of colorectal cancer from metagenomic data; and uses a random forest algorithm to construct a colorectal cancer detection model, specifically: constructing a random forest model, and performing an evaluation to obtain a colorectal cancer detection model, thereby increasing the generalization ability and anti-overfitting ability of the colorectal cancer detection model, being able to more accurately predict and evaluate the condition of colorectal cancer, helping doctors to develop more effective treatment plans, and improving patients' survival rates and quality of life.

[0028] (2) The method provided by the present invention has the advantages of being non-invasive and easy to operate, and can provide a new approach for the diagnosis of colorectal cancer. The screened colorectal cancer microbial markers and the constructed colorectal cancer detection model have high accuracy and specificity, which helps to improve the diagnostic efficiency of colorectal cancer. The application of the present invention can provide strong support for early screening, personalized treatment and disease monitoring of colorectal cancer.

[0029] (3) The technical solution of the present invention for identifying specific intestinal microbial markers for colorectal cancer is helpful for discovering new biomarkers, new biomarkers or therapeutic targets. BRIEF DESCRIPTION OF THE DRAWINGS

[0030] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on the provided drawings without paying creative work.

[0031] The colorectal cancer intestinal microbial markers and their applications and the method for constructing a colorectal cancer detection model in the present invention are further described below in conjunction with the accompanying drawings;

[0032] Figure 1 Flow chart for obtaining the metagenomics for Example 1;

[0033] Figure 2 This is a graph of the error results of the cross validation performed ten times in Example 1;

[0034] Figure 3 is the "MeanDecrease Accuracy" indicator in the random forest model of Example 1;

[0035] Figure 4 This is the ROC curve of the random forest model established based on colorectal cancer microbial markers in Example 1. DETAILED DESCRIPTION

[0036] Various exemplary embodiments of the present invention will now be described in detail. This detailed description should not be considered as limiting the present invention, but should be understood as a more detailed description of certain aspects, features, and embodiments of the present invention.

[0037] It should be understood that the terms described in the present invention are only for describing special embodiments and are not intended to limit the present invention. In addition, for the numerical range in the present invention, it should be understood that each intermediate value between the upper and lower limits of the scope is also specifically disclosed. Each smaller range between the intermediate value in any stated value or stated range and any other stated value or intermediate value in the described range is also included in the present invention. The upper and lower limits of these smaller ranges can be independently included or excluded in the scope.

[0038] Unless otherwise indicated, all technical and scientific terms used herein have the same meanings as those generally understood by those skilled in the art. Although the present invention describes only preferred methods and materials, any methods and materials similar or equivalent to those described herein may also be used in the implementation or testing of the present invention. All documents mentioned in this specification are incorporated by reference to disclose and describe the methods and / or materials associated with the documents. In the event of a conflict with any incorporated document, the content of this specification shall prevail.

[0039] It will be apparent to those skilled in the art that various modifications and variations may be made to the specific embodiments of the present invention description without departing from the scope or spirit of the present invention. Other embodiments derived from the present invention description will be apparent to the skilled artisan. The present invention description and examples are exemplary only.

[0040] The words “include,” “including,” “have,” “contain,” etc. used in this document are open-ended terms, meaning including but not limited to.

[0041] The present invention provides a method for constructing a colorectal cancer detection model using colorectal cancer intestinal microbial markers, characterized in that it comprises the following steps:

[0042] (1) Total DNA was extracted from the feces of colorectal cancer patients and healthy people, and high-throughput sequencing was performed after pretreatment. The sequencing results were annotated with species and analyzed for composition, gene abundance statistics, functional annotation, and differential analysis to screen out intestinal microbial markers for colorectal cancer;

[0043] (2) Establish a random forest model to identify colorectal cancer and healthy people through colorectal cancer intestinal microbial markers, evaluate, and obtain a colorectal cancer detection model;

[0044] (3) The metagenome and abundance information of the patient to be tested are input into the colorectal cancer detection model for identification.

[0045] In the step (1), the species annotation and composition spectrum analysis includes:

[0046] Alpha diversity: Shannon, Simpson, Insimpson index analysis;

[0047] beta diversity: Bray-CurtisPCoa, PCA, NMDS, UPGMA analysis;

[0048] Bacteria sample composition, sample heatmap;

[0049] Species interaction network analysis.

[0050] In the step (1), the gene abundance statistics include: gene Core-Pan curve, gene dilution curve, and correlation analysis between samples of gene numbers.

[0051] In the step (1), the functional annotation includes: KEGG data rate functional annotation analysis, HUMAnN3: quantitative pathway abundance, KO functional abundance and analysis, Module functional abundance and analysis, Pathway functional abundance and analysis.

[0052] In the step (1), the difference analysis includes: Lefse analysis, dominant species difference, multivariate variance adonis, MaAsLin, rank sum test difference, random forest, pathway functional abundance and analysis.

[0053] The high-throughput sequencing is performed in the step (1), including: removing the adapter with fastp, removing the host sequence with bowtie2, performing marker-based species abundance analysis with MetaPhlAn4, and performing functional analysis with HUMAnN33.

[0054] In the step (2), a random forest model for identifying colorectal cancer and healthy people is established by using colorectal cancer intestinal microbial markers, and an evaluation is performed to obtain a colorectal cancer detection model, specifically:

[0055] Colorectal cancer patients and healthy people are divided into training sets and test sets, and the random forest model is trained on the training sets using sklearn.ensemble.RandomForestClassifier in python;

[0056] The evaluation method is: measuring the degree of fit of the random forest model to the data by drawing a learning curve, and evaluating the performance of each set of parameters in the random forest model by ten-fold cross validation to select the optimal parameter combination.

[0057] The training parameters of the random forest model in step (2) are: base learner data n_estimators = {100, 500, 1000}, maximum tree depth max_depth = {1, 2, 3, 7, 9}, maximum feature number max_features = ["log2", "sqrt"], and parameter tuning is performed using GridSearchCV from the scikit-learn library of Python.

[0058] Among them, the intestinal microbial markers screened included the following species: TM7_phylum_sp_oral_taxon_348, Clostridium_sp_NSJ_42, Parabacteroides_distasonis, Streptococcus_sanguinis, Turicibactersanguinis), Candidatus_Nanosynsacchari_sp_TM7_ANC_38_39_G1_1, Sutterella_wadsworthensis, Actinomyces_dentalis, Veillonella_atypica, Actinomyces_sp_ICM47, Gemmiger_formicilis, Escherichia_coli, Blautia_faecicola, Eubacterium_sulci, Isoptericola_variabilis, Sellimonas_intestinalis, Ruminococcus_sp_AF41_9, Dorea_longicatena, Phocaeicola_vulgatus, Enterococcus_faecium ), Coprococcus catus, Eubacterium recale, Clostridinm sp AF20 17LB, Romboutsia timonensis, Agathobaculum butyriciproducens, Bacteroides thetaiotaomicron, Adlercreutzia equolifaciens, Peptostreptococcus stomatis, Candidatus Cibiobacter qucibialis, Bacteroides ovatus, Bacteroides fragilis, Faecalibacterium prausnitzii, Fusicatenibacter saccharivorans.

[0059] The metagenome and abundance information of the patient to be tested are input into the colorectal cancer detection model for identification

[0060] The present invention also provides an application of a colorectal cancer intestinal microbial marker, the application including a product for diagnosing whether a patient has colorectal cancer or is at risk of colorectal cancer, a target for colorectal cancer disease assessment and treatment, and a construction of a colorectal cancer detection model; the product includes any one of a detection reagent, a detection kit, and a detection chip.

[0061] Example 1

[0062] Screening of intestinal microbial markers for colorectal cancer:

[0063] like Figure 1 As shown, stool samples from 44 patients with colorectal cancer and 5 healthy controls were collected from the clinic, and relevant clinical information was recorded; stool samples were collected in sterile containers to avoid cross contamination, and total DNA was extracted from the stool samples using a DNA extraction kit, and proteins and other impurities were removed to obtain pure DNA.

[0064] After adding adapter sequences to both ends of the broken DNA fragments, high-throughput sequencing was performed using the Illumina platform, which included removing the adapter using fastp, removing the host sequence using bowtie2, performing marker-based species abundance analysis using MetaPhlAn4, and performing functional analysis using tools such as HUMAnN33. The sequencing results are as follows: Figure 2After performing differential analysis, species annotation and composition spectrum analysis, functional annotation, and gene abundance statistics on the sequencing results, the differences between samples from colorectal cancer patients and healthy people were analyzed to screen out intestinal microbial markers of colorectal cancer with significant differences.Including TM7_phylum_sp_oral_taxon_348, Clostridium_sp_NSJ_42, Parabacteroides_distasonis, Streptococcus_sanguinis, Turicibacter sanguinis), Candidatus_Nanosynsacchari_sp_TM7_ANC_38_39_G1_1, Sutterella_wadsworthensis, Actinomyces_dentalis, Veillonella_atypica, Actinomyces_sp_ICM47, Gemmiger_formicilis, Escherichia_coli, Blautia_faecicola, Eubacterium_sulci, Isoptericola_variabilis, Sellimonas_intestinalis, Ruminococcus_sp_AF41_9, Dorea_longicatena, Phocaeicola_vulgatus, Enterococcus_faecium )、Coprococcus catus、Eubacterium recale、Clostridium sp AF20 17LB、Romboutsia timonensis、Agathobaculum butyriciproducens、Bacteroides thetaiotaomicron、Adlercreutzia equolifaciens、Peptostreptococcus stomatis、Candidatus Cibiobacter qucibialis、Bacteroides ovatus、Bacteroides fragilis、Faecalibacterium prausnitzii、Fusicatenibacter-saccharivorans。 ,

[0065] Example 2

[0066] Establishing the ability to distinguish colorectal cancer patients from healthy controls using colorectal cancer gut microbial markers:

[0067] The training set was modeled using skleamensemble.RandomForestClassifier in Python, and the data set of colorectal cancer intestinal microbial markers was divided into a training set and a test set. GridSearchCV was used from the scikit-leam library in Python to tune parameters, and a ten-fold cross validation was performed to confirm the robustness and reliability of the model. Specifically, the key training parameters of the random forest model were set as follows: the number of base learners n_estimators was set to {100, 500, 1000}, the maximum depth of the tree max_depth considered {1, 2, 3, 7, 9}, and the maximum number of features max-features was set to [″log2″, ″sqrt″]. GridSearchCV was used from the scikit-learn library in Python to tune parameters, and a 10-fold cross validation was performed to evaluate the performance of each set of parameters, so as to select the optimal parameter combination. After determining the optimal parameters, a colorectal cancer detection model was obtained, and predictions were made on the test set to evaluate the performance of the model on unknown data. The learning curve was plotted to measure the degree of fit of the model to the data, and a colorectal cancer detection model was obtained.

[0068] The above ten-run cross validation provides a comprehensive view of the model stability and reliability. Figure 2 As shown, Figure 2 The vertical axis reflects the value of the cross-validation error, ranging from 0.10 to 0.30. There are multiple curves in the line chart, representing different variable selection methods. Figure 2 In the figure, the black curve shows the trend of cross-validation error as the number of variables increases. The curve initially shows a downward trend, indicating that when adding variables, the model prediction error gradually decreases, and the accuracy of the training set and test set is high, indicating that the model results are good.

[0069] As shown in Table 1, “MeanDecrease Accuracy” and “MeanDecrease Gini” are important indicators in the colorectal cancer detection model. “Mean Decrease Accuracy” indicates the degree of decrease in prediction accuracy. The larger the value, the more important the variable (e.g. Figure 3 "MeanDecrease Gini" calculates the impact of each variable on the heterogeneity of observations at the classification tree node and compares the importance of the variables. The larger the value, the more important the variable.

[0070] like Figure 4 As shown in the figure, the ROC curve is used to evaluate the performance of the colorectal cancer detection model. The horizontal axis (X-axis) represents 1-Specificity, that is, the false positive rate, ranging from 0 to 1, reflecting the proportion of negative cases that the colorectal cancer detection model incorrectly predicts as positive cases. The vertical axis (Y-axis) represents Sensitivity, that is, the true positive rate, which measures the ability of the colorectal cancer detection model to correctly identify positive cases. Figure 4 The red solid line in the figure depicts the ROC curve of the colorectal cancer detection model, and the shaded part represents the confidence interval (CI). The ROC curve in the present invention is close to the upper left corner, the true positive rate is high under each threshold, and the area under the curve (AUC) is close to 1, indicating good classification performance. The AUC value in the present invention is 0.9204, indicating that the classifier performs well in distinguishing positive and negative samples. The CI range is 0.8613 to 0.9796, and the AUC value is reliably evaluated, indicating that the performance of the colorectal cancer detection model is stable.

[0071] Table 1 is the important indicators in the colorectal cancer detection model

[0072]

[0073]

[0074]

[0075] The above is only a preferred embodiment of the present invention. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principle of the present invention. These improvements and modifications should also be regarded as the scope of protection of the present invention.

Claims

1. A colorectal cancer intestinal microbial marker, characterized in that: The intestinal microbial markers include the following species: TM7_phylum_sp_oral_taxon_348, Clostridium_sp_NSJ_42, Parabacteroides_distasonis, Streptococcus_sanguinis, Turicibacter sanguinis, Candidatus_Nanosynsacchari_sp_TM7_ANC_38_39_G1_1, Sutterella_wadsworthensis, Actinomyces_dentalis, Veillonella_atypica, Actinomyces sp ICM47, Gemmiger formicilis, Escherichia coli, Blautia faecicola, Eubacterium sulci, Isoptericola variabilis, Sellimonas intestinalis, Ruminococcus sp AF41 9, Dorea longicatena, Phocaeicola vulgatus, Enterococcus faecium, Coprococcus catus, Eubacterium recale, Clostridium sp AF20 17LB, Romboutsia timonensis,Agathobaculum_butyriciproducens, Bacteroides_thetaiotaomicron, Adlercreutzia_equolifaciens, Peptostreptococcus_stomatis, Candidatus_Cibiobacter_qucibialis, Bacteroides_ovatus, Bacteroides_fragilis, Faecalibacterium_prausnitzii, Fusicatenibacter_saccharivorans.

2. A use of the intestinal microbial marker for colorectal cancer according to claim 1, characterized in that: The application includes the preparation of products for diagnosing whether a patient has colorectal cancer or the risk of colorectal cancer, as a target for colorectal cancer disease assessment and treatment, and the construction of a colorectal cancer detection model; the product includes any one of a detection reagent, a detection kit, and a detection chip.

3. A method for constructing a colorectal cancer detection model using the colorectal cancer intestinal microbial markers according to claim 1, characterized in that: The following steps are involved: (1) Total DNA was extracted from the feces of colorectal cancer patients and healthy people, and high-throughput sequencing was performed after pretreatment. The sequencing results were annotated with species and analyzed for composition, gene abundance statistics, functional annotation, and differential analysis to screen out intestinal microbial markers for colorectal cancer; (2) Establish a random forest model to identify colorectal cancer and healthy people through colorectal cancer intestinal microbial markers, evaluate, and obtain a colorectal cancer detection model; (3) The metagenome and abundance information of the patient to be tested are input into the colorectal cancer detection model for identification.

4. The method for constructing a colorectal cancer detection model according to claim 3, characterized in that: In the step (1), the species annotation and composition spectrum analysis includes: Alpha diversity: Shannon, Simpson, Insimpson index analysis; beta diversity: Bray-CurtisPCoa, PCA, NMDS, UPGMA analysis; Bacteria sample composition, sample heatmap; Species interaction network analysis.

5. The method for constructing a colorectal cancer detection model according to claim 3, characterized in that: In the step (1), the gene abundance statistics include: gene Core-Pan curve, gene dilution curve, and correlation analysis between samples of gene numbers.

6. The method for constructing a colorectal cancer detection model according to claim 3, characterized in that: In the step (1), the functional annotation includes: KEGG data rate functional annotation analysis, HUMAnN3: quantitative pathway abundance, KO functional abundance and analysis, Module functional abundance and analysis, Pathway functional abundance and analysis.

7. The method for constructing a colorectal cancer detection model according to claim 3, characterized in that: In the step (1), the difference analysis includes: Lefse analysis, dominant species difference, multivariate variance adonis, MaAsLin, rank sum test difference, random forest, pathway functional abundance and analysis.

8. The method for constructing a colorectal cancer detection model according to claim 3, characterized in that: The high-throughput sequencing in step (1) includes: removing the adapter with fastp, removing the host sequence with bowtie2, performing marker-based species abundance analysis with MetaPhlAn4, and performing functional analysis with HUMAnN33.

9. The method for constructing a colorectal cancer detection model according to claim 3, characterized in that: In the step (2), a random forest model for identifying colorectal cancer and healthy people is established by using colorectal cancer intestinal microbial markers, and an evaluation is performed to obtain a colorectal cancer detection model, specifically: Colorectal cancer patients and healthy people are divided into training sets and test sets, and the random forest model is trained on the training sets using sklearn.ensemble.RandomForestClassifier in python; The evaluation method is: measuring the degree of fit of the random forest model to the data by drawing a learning curve, and evaluating the performance of each set of parameters in the random forest model by ten-fold cross validation to select the optimal parameter combination.

10. The method for constructing a colorectal cancer detection model according to claim 9, characterized in that: The training parameters of the random forest model in step (2) are: base learner data n_estimators={100, 500, 1000}, maximum tree depth max_depth={1, 2, 3, 7, 9}, maximum number of features max_features=["log2", "sqrt"], and parameter tuning is performed using GridSearchCV from the scikit-learn library of Python.

Images