A method, system and device for predicting colorectal cancer

Abstract

The present invention provides a method, system, device, medium and program product for predicting colorectal cancer, which relates to the field of intelligent medical care. The method comprises: obtaining expression data of a prediction gene of a sample to be tested; performing classification prediction based on the expression data of the prediction gene to obtain a classification result of a high or low risk of colorectal cancer for the sample to be tested; if the expression amount of the prediction gene is higher than a threshold, obtaining a classification result of a high risk of colorectal cancer for the sample to be tested. The method of the present invention detects the expression level of the prediction gene of the sample to be tested to achieve a classification result of predicting a high or low risk of colorectal cancer for the sample to be tested, which can be used for clinical evaluation and solve related life science problems.

Description

Technical Field

[0001] The present invention relates to the field of intelligent medical care, and more specifically, to a prediction method, system, device, medium and program product for colorectal cancer. Background Art

[0002] Colorectal cancer (CRC), also known as colorectal cancer, refers to primary malignant tumors originating from the large intestine epithelium, including colon cancer and rectal cancer. It is a common digestive tract malignancy in my country. Prevention, screening, early diagnosis and treatment of colorectal cancer are effective measures to reduce the mortality rate of colorectal cancer in the population. In recent years, its incidence and mortality rates have both been on the rise. Statistics in 2020 show that there were 1.96 million new cases of colorectal cancer worldwide; 555,000 new cases and 286,000 deaths in my country. On average, one person is diagnosed with colorectal cancer every minute, and one person dies from colorectal cancer every 2 minutes; the number of new cases of colorectal cancer in my country accounts for 28.8% of the world's total, and the number of deaths accounts for 30.6%. From 2010 to 2020, in 10 years, the incidence of colorectal cancer in my country increased by 126%, with an average annual increase of 9.5%. It is very important to clarify the occurrence and development mechanism of colorectal cancer and find appropriate targets for early diagnosis, treatment and prognosis assessment to improve the survival of colorectal cancer patients.

[0003] Studying genetic markers associated with early colorectal cancer can predict the risk of colorectal cancer in subjects, thereby providing new means and directions for early intervention and treatment. Summary of the invention

[0004] The present invention aims to solve at least one of the technical problems existing in the prior art. To this end, the present invention provides a method for predicting colorectal cancer; the method of the present invention detects the expression level of the predicted gene of the sample to be tested to achieve a classification result of predicting the risk of the sample to be tested for colorectal cancer, so as to be used for clinical evaluation and solve related life science problems.

[0005] The first aspect of the present application discloses a method for predicting colorectal cancer, the method comprising:

[0006] Obtaining expression data of predicted genes of the sample to be tested;

[0007] Based on the expression data of the predicted gene, classification prediction is performed to obtain a classification result of whether the sample to be tested has a high or low risk of colorectal cancer; if the expression amount of the predicted gene is higher than a threshold, a classification result is obtained that the sample to be tested has a high risk of colorectal cancer.

[0008] In some embodiments, the predicted gene is obtained by taking the intersection of the exosome-derived targeted gene candidate panel and the tissue-derived targeted gene candidate panel;

[0009] Optionally, the exosome-derived targeted gene candidate panel is obtained by the following method:

[0010] Acquire colorectal cancer exosome data; the colorectal cancer exosome data is obtained from an exosome database; the exosome database includes a first exosome database and a second exosome database; the colorectal cancer data includes differential expression data of a first category and a second category in the first exosome database; the differential expression data of the first category and the second category are respectively screened according to a first screening standard to obtain the screened differential expression data of the first category and the second category, and the genes in the screened differential expression data of the first category and the screened differential expression data of the second category are merged to obtain a first exosome candidate target panel; the colorectal cancer data also includes gene expression data of lncRNA and mRNA in the second exosome database; the gene expression data of lncRNA and mRNA are respectively differentially screened according to a second screening standard to obtain the screened gene expression data of lncRNA and mRNA; the genes in the screened gene expression data of lncRNA and the screened gene expression data of mRNA are merged to obtain a third exosome candidate target panel;

[0011] The intersection of the first exosome candidate target panel and the third exosome candidate target panel was taken to obtain the exosome-derived targeted gene candidate panel.

[0012] In some embodiments, the tissue-derived targeted gene candidate panel is obtained by:

[0013] Obtain colorectal cancer tissue sequencing data from NCBI and SRA;

[0014] The colorectal cancer tissue sequencing data is sequentially subjected to connector processing and quality control processing, and aligned to the human reference genome to obtain an alignment result; the alignment result is subjected to differential expression analysis to obtain the tissue-derived targeted gene candidate panel.

[0015] In some embodiments, the colorectal cancer data further includes: differential expression data of a third category in the first exosome database, the method further includes: screening the differential expression data of the third category according to the first screening standard to obtain the screened differential expression data of the third category, merging the genes in the first exosome candidate target panel and the screened differential expression data of the first category to obtain a second exosome candidate target panel;

[0016] Taking the intersection of the second exosome candidate target panel and the third exosome candidate target panel, we can obtain the exosome-derived targeted gene candidate panel;

[0017] Optionally, the first type is lncRNA;

[0018] Optionally, the second type is mirna;

[0019] Optionally, the third type is mrna;

[0020] Optionally, the first screening criteria for lncRNAs were adj-pvalue < 0.01 and FoldChange > 2;

[0021] Optionally, the first screening criteria for mirna is adj-pvalue < 0.05 and FoldChange > 1;

[0022] Optionally, the first screening criteria for mRNAs were adj-pvalue < 0.01 and FoldChange > 2;

[0023] Optionally, the second screening criteria for lncRNA and mRNA are adj-pvalue<0.01 and FoldChange>2.

[0024] In some embodiments, the predicted genes include: CEMIP (ENSG00000103888);

[0025] Optionally, the predicted genes further include any one or two of ENC1 (ENSG00000171617) and NFE2L3 (ENSG00000050344).

[0026] In some embodiments, the first exosome database is a BBCancer database, and the second exosome database is an exoRBase database.

[0027] The second aspect of the present application discloses a prediction system for colorectal cancer, the system comprising:

[0028] An acquisition module is used to obtain the expression data of the predicted gene of the sample to be tested;

[0029] The prediction module is used to perform classification prediction based on the expression data of the prediction gene to obtain a classification result of whether the sample to be tested has a high or low risk of colorectal cancer; if the expression amount of the prediction gene is higher than a threshold, a classification result is obtained that the sample to be tested has a high risk of colorectal cancer.

[0030] The third aspect of the present application discloses a computer device, which includes: a memory and a processor; the memory is used to store program instructions; the processor is used to call the program instructions, and when the program instructions are executed, it is used to execute the steps of the method described in the first aspect.

[0031] A fourth aspect of the present application discloses a computer-readable storage medium having a computer program stored thereon, wherein the computer program implements the steps of the method of the first aspect when executed by a processor.

[0032] The fifth aspect of the present application discloses a computer program product, including a computer program, which implements the steps of the method of the first aspect when executed by a processor.

[0033] This application has the following beneficial effects:

[0034] 1. This application innovatively discloses a method for predicting colorectal cancer. This method can well predict the risk of a sample suffering from colorectal cancer by detecting the expression level of the predicted gene, and provide guidance information for early intervention and early treatment;

[0035] 2. This application innovatively combines the differential expression data of different types (lncRNA, miRNA, mRNA) in at least two different exosome databases, first taking the gene union from different types of data in the same exosome database, and then taking the intersection between different exosome databases; this application also innovatively combines the differential expression data of different tissues in different exosome databases and colorectal cancer tissue sequencing databases, taking the intersection between the exosome-derived targeted gene candidate panel and the tissue-derived targeted gene candidate panel to finally determine the candidate prediction gene. The prediction gene obtained in this way is more accurate and reliable in predicting the risk of colorectal cancer, and is more practical for clinical guidance of colorectal cancer. BRIEF DESCRIPTION OF THE DRAWINGS

[0036] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative work.

[0037] Figure 1 is a schematic diagram of a method flow chart provided by the first aspect of an embodiment of the present invention;

[0038] Figure 2 is a schematic flow chart of a system provided by the second aspect of an embodiment of the present invention;

[0039] Figure 3 is a schematic diagram of a computer device provided by an embodiment of the present invention;

[0040] Figure 4It is a statistical and visualized schematic diagram of the expression trend of the prediction gene CEMIP in normal tissues, polyp tissues, and cancer TNMI1-TNM4 provided by an embodiment of the present invention;

[0041] Figure 5 It is a statistical and visualized schematic diagram of the expression trend of the prediction gene ENC1 in normal tissues, polyp tissues, and cancer TNMI1-TNM4 provided by an embodiment of the present invention;

[0042] Figure 6 It is a statistical and visualized schematic diagram of the expression trend of the prediction gene NFE2L3 in normal tissues, polyp tissues, and cancer TNMI1-TNM4 provided in an embodiment of the present invention;

[0043] Figure 7 It is a statistical and visual schematic diagram of the expression trend of the predicted gene ENC1 in cancer and normal tissues provided by an embodiment of the present invention;

[0044] Figure 8 It is a statistical and visual schematic diagram of the expression trend of the predicted gene NFE2L3 in cancer and normal tissues provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0045] In order to enable those skilled in the art to better understand the solutions of the present invention, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the accompanying drawings in the embodiments of the present invention.

[0046] In some of the processes described in the specification and claims of the present invention and the above-mentioned figures, multiple operations that appear in a specific order are included, but it should be clearly understood that these operations may not be executed in the order in which they appear in this article or executed in parallel. The serial numbers of the operations, such as 101, 102, etc., are only used to distinguish different operations, and the serial numbers themselves do not represent any execution order. In addition, these processes may include more or fewer operations, and these operations may be executed in sequence or in parallel. It should be noted that the descriptions of "first", "second", etc. in this article are used to distinguish different messages, devices, modules, etc., do not represent the order of precedence, and do not limit the "first" and "second" to be different types.

[0047] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of the present invention.

[0048] Figure 1: is a flow chart of a method for predicting colorectal cancer provided by an embodiment of the present invention. Specifically, the method comprises the following steps:

[0049] 101: Obtain expression data of predicted genes of the sample to be tested;

[0050] In some embodiments, the term "subject" or "test subject" or "test sample" used herein refers to any animal (e.g., mammal), including but not limited to humans, non-human primates, rodents, etc., which will be the recipient of a specific treatment. Generally, the terms "subject" and "patient" are used interchangeably herein when referring to human subjects.

[0051] Preferably, the sample to be tested is a human.

[0052] In some embodiments, the sample to be tested is a patient undergoing clinical prognosis assessment.

[0053] In some embodiments, the predicted gene is obtained by taking the intersection of the exosome-derived targeted gene candidate panel and the tissue-derived targeted gene candidate panel;

[0054] Optionally, the exosome-derived targeted gene candidate panel is obtained by the following method:

[0055] Acquire colorectal cancer exosome data; the colorectal cancer exosome data is obtained from an exosome database; the exosome database includes a first exosome database and a second exosome database; the colorectal cancer data includes differential expression data of a first category and a second category in the first exosome database; the differential expression data of the first category and the second category are respectively screened according to a first screening standard to obtain the screened differential expression data of the first category and the second category, and the genes in the screened differential expression data of the first category and the screened differential expression data of the second category are merged to obtain a first exosome candidate target panel; the colorectal cancer data also includes gene expression data of lncRNA and mRNA in the second exosome database; the gene expression data of lncRNA and mRNA are respectively differentially screened according to a second screening standard to obtain the screened gene expression data of lncRNA and mRNA; the genes in the screened gene expression data of lncRNA and the screened gene expression data of mRNA are merged to obtain a third exosome candidate target panel;

[0056] The intersection of the first exosome candidate target panel and the third exosome candidate target panel was taken to obtain the exosome-derived targeted gene candidate panel.

[0057] In some embodiments, the colorectal cancer data further includes: differential expression data of a third category in the first exosome database, the method further includes: screening the differential expression data of the third category according to the first screening standard to obtain the screened differential expression data of the third category, merging the genes in the first exosome candidate target panel and the screened differential expression data of the first category to obtain a second exosome candidate target panel;

[0058] Taking the intersection of the second exosome candidate target panel and the third exosome candidate target panel, we can obtain the exosome-derived targeted gene candidate panel;

[0059] Optionally, the first type is lncRNA;

[0060] Optionally, the second type is mirna;

[0061] Optionally, the third type is mrna;

[0062] Optionally, the first screening criteria for lncRNAs were adj-pvalue < 0.01 and FoldChange > 2;

[0063] Optionally, the first screening criteria for mirna is adj-pvalue < 0.05 and FoldChange > 1;

[0064] Optionally, the first screening criteria for mRNAs were adj-pvalue < 0.01 and FoldChange > 2;

[0065] Optionally, the second screening criteria for lncRNA and mRNA are adj-pvalue<0.01 and FoldChange>2.

[0066] In some embodiments, the predicted genes include: CEMIP (ENSG00000103888);

[0067] Optionally, the predicted genes further include any one or two of ENC1 (ENSG00000171617) and NFE2L3 (ENSG00000050344).

[0068] The first exosome database is the BBCancer database (http: / / bbcancer.renlab.org / ), and the second exosome database is the exoRBase database (http: / / www.exorbase.org / ).

[0069] Specifically, BBCancer database: download lncRNA, mirna, mrna differential expression data, data screening criteria:

[0070] lncRNA: adj-pvalue<0.01 & FoldChange > 2

[0071] mirna: adj-pvalue<0.05 & FoldChange > 1

[0072] mrna: adj-pvalue<0.01 & FoldChange > 2;

[0073] Data operation process: Taking lncRNA data as an example: Use data.table::fread function to read the pre-downloaded differential expression file Colorectal.cancer-EVs.lncRNA.txt, save it as variable bbc.lnc, and perform data combination column screening on variable bbc.lnc, select the following columns: "gene", "FoldChange", "baseMean", "p-value", "adj-pvalue", and add the gene type class column, and fill the content with lncRNA. According to the above lncRNA differential expression gene screening criteria, the adj-pvalue column and FoldChange column are numerically filtered. The same above operations are performed on mirna and mrna. The results obtained from the above lncrna, mirna and mrna are merged using the rbind function to obtain the exosome candidate target panel based on the BBCancer database (the second exosome candidate target panel).

[0074] exoRBase exosome database: Download lncRNA and mrna gene TPM expression data for differential expression analysis. TPM (Transcripts Per Miion) is a unit commonly used in RNA sequencing data analysis, which represents the proportion of a transcript per million reads. TPM value can be used to compare the expression abundance of different genes or different samples, and can standardize the RNA-Seq sequencing depth of samples to eliminate the influence of the sequencing depth of samples on gene expression analysis.

[0075] Specifically, the calculation formula of TPM value is: the number of reads of each gene (Read Count) + the number of species-specific transcripts (Effective Length) ÷ the total number of reads (Total Read Count) x 1,000,000. Among them, Effective Length represents the effective length of each transcript.

[0076] The higher the TPM value of gene expression, the higher the expression level of the gene in the sample. If you want to analyze the expression differences of certain genes in a group of samples, the TPM value is usually used as an indicator of gene expression level:

[0077] The differential expression analysis was performed using the limma module of the R language. The screening criteria for differentially expressed genes were: adj-pvalue<0.01 & FoldChange > 2;

[0078] Data operation process: Taking lncRNA data as an example: Use the read.table function to read the pre-downloaded gene expression files CRC_lncRNA_TPM.txt and Normal_lncRNA_TPM.txt, save them as variables case and normal, use the log2(x+1) function to perform logarithmic transformation on the variables case and normal, use the intersect function to take the intersection of the case and normal variable row names to obtain the common gene features, and cbind to merge the common gene features of the case and normal variables to obtain the variable mat.data. Use the lmFit function of the limma module to perform differential expression analysis on mat.data. The screening criteria are as mentioned above. The data columns of the limma output results are screened, and the following columns are selected: "gene", "FoldChange", "baseMean", "p-value", "adj-pvalue", and the gene type class column is added, and the content is filled with lncrna. Perform the same above operations on mrna. The results obtained from the above lncRNA and mRNA were merged using the rbind function to obtain the exosome candidate target panel based on the exoRBase database (the third exosome candidate target panel).

[0079] For the exosome candidate target panel based on the BBCancer database and the exosome candidate target panel based on the exoRBase database, use the unique function to extract the unique value of the "gene" column in the collection, and save the result as the unique.lm variable. The unique.lm variable can be used as the exosome-derived targeting gene candidate panel.

[0080] In some embodiments, the tissue-derived targeted gene candidate panel is obtained by:

[0081] Obtain colorectal cancer tissue sequencing data from NCBI and SRA;

[0082] The colorectal cancer tissue sequencing data is sequentially subjected to connector processing and quality control processing, and aligned to the human reference genome to obtain an alignment result; the alignment result is subjected to differential expression analysis to obtain the tissue-derived targeted gene candidate panel.

[0083] The specific process is as follows:

[0084] 1. Sample source

[0085] The sequencing data of the PRJEB27536 dataset were downloaded from SRA and the gene expression data of colorectal cancer were downloaded from TCGA. The sample size was normal tissue: polyp tissue: colorectal cancer TNM1: TNM2: TNM3: TNM4=50:21:52:123:89:44.

[0086] 2. Data processing

[0087] The raw data from the SRA database was processed and quality controlled using fastq software, and the clean data was aligned to the human reference gene group using ICGC software, version (GRCh38.d1.vd1), and the bam file was quantified using htseq software.

[0088] Quantitative mode: intersection-nonempty;

[0089] Quantitative standard type: gene_id;

[0090] Chain Specificity: Nonspecific.

[0091] The expression files were merged according to geneID to construct an M*N gene expression matrix. The value of the i-th row and j-th column in the gene expression matrix represents the expression count value of the i-th gene corresponding to the j-th sample, where 1≤i≤M, 1≤j≤N; M represents the number of detected genes, and N represents the number of analyzed samples. The expression matrix was saved as a .Rdata object file.

[0092] The processed count expression matrix and TCGA expression matrix were merged, and the merging standard was gene ID.

[0093] 3. Differential Expression Analysis

[0094] The experiment was divided into the following groups: Group 1: cancer vs normal; Group 2: cancer vs polyps; Group 3: early cancer vs normal (TNM1+TNM2 vs normal); Group 4: late cancer vs normal (TNM4 vs normal).

[0095] According to the experimental grouping design, the differential expression grouping matrix was constructed, and the differential expression analysis was performed using the "deseq2" package in R software. The screening criteria for differential genes were adj.P value<0.05, |log2FC|>1.

[0096] Genes showing significant differences only in group 3 were screened.

[0097] 4. Results

[0098] The analysis results showed that there were 12070 genes with significant differential expression in group 1, 4820 differentially expressed genes were significantly upregulated, and 7250 differentially expressed genes were significantly downregulated; there were 11348 genes with significant differential expression in group 2, 4030 differentially expressed genes were significantly upregulated, and 7318 differentially expressed genes were significantly downregulated; there were 12147 genes with significant differential expression in group 3, 4546 differentially expressed genes were significantly upregulated, and 7601 differentially expressed genes were significantly downregulated; there were 11996 genes with significant differential expression in group 4, 4799 differentially expressed genes were significantly upregulated, and 7197 differentially expressed genes were significantly downregulated.

[0099] Screening for genes that showed significant differences only in group 3 Figure 1 As shown in Table 1 , there are 442 genes in total. Among them, compared with normal controls, EZH2 and TNFRSF10A are upregulated in early colorectal cancer, and CDH17, ALOX12-AS1, AMT, RP11-522B15.3, SPON1, FRZB or HOXA6 are downregulated in early colorectal cancer, and their expression is shown in Table 1 and Figure 2 As shown, FC (fold change) represents the difference between early colorectal cancer and normal, and (log2 expression level) represents the expression level of gene.

[0100] Table 1 Gene expression

[0101]

[0102] In some embodiments, the exosome-derived targeted gene candidate panel and the tissue-derived targeted gene candidate panel are intersected using the intersect function to obtain three candidate genes ENC1 (ENSG00000171617), NFE2L3 (ENSG00000050344), and CEMIP (ENSG00000103888). The three candidate targeted genes only appear in the BBCancer exosome database. The differential expression of the three candidate targeted genes in the BBCancer exosome database is extracted, as shown in the following table:

[0103]

[0104] 102: Performing classification prediction based on the expression data of the prediction gene to obtain a classification result of whether the sample to be tested has a high or low risk of colorectal cancer; if the expression amount of the prediction gene is higher than a threshold, obtaining a classification result that the sample to be tested has a high risk of colorectal cancer;

[0105] In some embodiments, as shown in the attached Figure 4-6 As shown in the figure, the expression of three candidate target genes in tissue sample data was extracted, and the boxplot function was used to perform statistics and visualization of the expression trends of normal tissue, polyp tissue, and cancer TNMI1-TNM4, a total of 6 types. The results showed that the expression levels of the three candidate target genes in cancer tissue were higher than those in normal tissue, and the three candidate target genes could be used as predictors for predicting the risk of colorectal cancer in samples (see Appendix). Figure 4 For ENC1, attached Figure 5 For CEMIP, Figure 6 The threshold is verified by multiple data sets to obtain a specific numerical range.

[0106] In some embodiments, the present application also verifies three candidate genes by using the dataset GSE127069 in the GEO database:

[0107] https: / / www.ncbi.nlm.nih.gov / geo / query / acc.cgi?acc=GSE127069

[0108] Data operation process: data.table::fread function reads the pre-downloaded GSE127069_series_matrix.txt file and saves it as dataframe variable expr, reads the pre-downloaded chip annotation file GPL17077-17467.txt and saves it as dataframe variable panel, uses panel's "ID", "GENE_SYMBOL" information to annotate expr's ID_REF, and uses aggregate function to aggregate and average the expr of the annotated gene ID. Use R language's limma module lmFit function to perform differential expression analysis between colorectal cancer and normal tissues, and the differential expression gene screening criteria are: adj-pvalue<0.05 & FoldChange > 1. The obtained differentially expressed gene list was compared with the above candidate target genes, and only ENC1 and NFE2L3 genes were verified, with the following results:

[0109]

[0110] In some embodiments, ggboxplot is used to statistically and visualize the expression trends of the two genes ENC1 and NFE2L3 in cancer and normal tissues. The results are shown in the attached Figure 7 and 8 As shown, the expression of the two predicted genes in cancer tissues was much higher than that in normal tissues.

[0111] Figure 2 A prediction system for colorectal cancer provided by an embodiment of the present invention comprises:

[0112] An acquisition module 201 is used to acquire the expression data of the predicted gene of the sample to be tested;

[0113] The prediction module 202 is used to perform classification prediction based on the expression data of the prediction gene to obtain a classification result of whether the sample to be tested has a high or low risk of colorectal cancer; if the expression level of the prediction gene is higher than a threshold, a classification result is obtained that the sample to be tested has a high risk of colorectal cancer.

[0114] Figure 3 A computer device is provided in an embodiment of the present invention, and the device comprises: a memory and a processor; the memory is used to store program instructions; the processor is used to call the program instructions, and when the program instructions are executed, it is used to execute the steps of the method of the first aspect.

[0115] The embodiment of the present invention also provides a computer-readable storage medium having a computer program stored thereon, and the computer program implements the steps of the method of the first aspect when executed by a processor.

[0116] An embodiment of the present invention further discloses a computer program product, including a computer program, which implements the steps of the method of the first aspect when executed by a processor.

[0117] Definition: Exosomes are vesicle-like bodies of uniform size that are actively secreted by cells outside the cell, and have physiological functions such as anti-tumor immunity and angiogenesis. Different types of cells can release exosomes, and exosomes can also be isolated from blood, urine, milk and bronchial lavage fluid under normal physiological conditions. Exosomes play an important role in the information transmission and regulation between cells, especially in the interaction between cells and the immune system, virus transmission and tumor development.

[0118] The validation results of this validation example show that assigning intrinsic weights to indications can moderately improve the performance of the method relative to the default setting.

[0119] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0120] In the several embodiments provided in the present application, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be an indirect coupling or communication connection through some interfaces, devices or units, which can be electrical, mechanical or other forms.

[0121] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0122] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0123] A person skilled in the art may understand that all or part of the steps in the various methods of the above embodiments may be completed by instructing related hardware through a program, and the program may be stored in a computer-readable storage medium, and the storage medium may include: a read-only memory (ROM), a random access memory (RAM), a disk or an optical disk, etc.

[0124] A person skilled in the art can understand that all or part of the steps in the above-mentioned embodiment method can be completed by instructing related hardware through a program, and the program can be stored in a computer-readable storage medium. The above-mentioned storage medium can be a read-only memory, a disk or an optical disk, etc.

[0125] The above is a detailed introduction to a computer device provided by the present invention. For a person skilled in the art, according to the concept of the embodiments of the present invention, there may be changes in the specific implementation method and application scope. In summary, the content of this specification should not be understood as limiting the present invention.

Claims

1. A method for predicting colorectal cancer, characterized in that: The method comprises: Acquire expression data of predicted genes of the sample to be tested; the predicted genes are obtained by taking the intersection of the candidate panel of exosome-derived targeted genes and the candidate panel of tissue-derived targeted genes; the candidate panel of exosome-derived targeted genes is obtained by the following method: obtain colorectal cancer exosome data; the colorectal cancer exosome data is obtained from an exosome database; the exosome database includes a first exosome database and a second exosome database; the colorectal cancer data includes differential expression data of lncRNA, mirna, and mrna in the first exosome database; the differential expression data of lncRNA, mirna, and mrna are screened according to the first screening standard to obtain the screened differential expression data of lncRNA, mirna, and mrna, and the screened differential expression data of lncRNA, mirna, and mrna are merged The genes in the expression data are used to obtain the second exosome candidate target panel; the colorectal cancer data also include the gene expression data of lncRNA and mrna in the second exosome database; the gene expression data of lncRNA and mrna are differentially screened according to the second screening standard to obtain the gene expression data of lncRNA and mrna after screening; the genes in the gene expression data of lncRNA after screening and the gene expression data of mrna after screening are combined to obtain the third exosome candidate target panel; the intersection between the second exosome candidate target panel and the third exosome candidate target panel is taken to obtain the exosome-derived targeting gene candidate panel; the predicted genes include: any one or two of CEMIP, ENC1, and NFE2L3; the first exosome database is the BBCancer database, and the second exosome database is the exoRBase database; Based on the expression data of the predicted gene, classification prediction is performed to obtain a classification result of whether the sample to be tested has a high or low risk of colorectal cancer; if the expression amount of the predicted gene is higher than a threshold, a classification result is obtained that the sample to be tested has a high risk of colorectal cancer.

2. The method for predicting colorectal cancer according to claim 1, characterized in that: The tissue-derived targeted gene candidate panel is obtained by the following method: Obtain colorectal cancer tissue sequencing data from NCBI and SRA; The colorectal cancer tissue sequencing data is sequentially subjected to connector processing and quality control processing, and aligned to the human reference genome to obtain an alignment result; the alignment result is subjected to differential expression analysis to obtain the tissue-derived targeted gene candidate panel.

3. The method for predicting colorectal cancer according to claim 1, characterized in that: The first screening criteria for lncRNA were adj-pvalue<0.01 and FoldChange > 2.

4. The method for predicting colorectal cancer according to claim 1, characterized in that: The first screening criteria for mirna were adj-pvalue<0.05 and FoldChange > 1.

5. The method for predicting colorectal cancer according to claim 1, characterized in that: The first screening criteria for mRNAs were adj-pvalue<0.01 and FoldChange > 2.

6. The method for predicting colorectal cancer according to claim 1, characterized in that: The second screening criteria for lncRNA and mRNA were adj-pvalue<0.01 and FoldChange>2.

7. A prediction system for colorectal cancer, characterized in that: The system comprises: An acquisition module is used to obtain expression data of predicted genes of the sample to be tested; the predicted genes are obtained by taking the intersection of the candidate panel of exosome-derived targeted genes and the candidate panel of tissue-derived targeted genes; the candidate panel of exosome-derived targeted genes is obtained by the following method: obtaining colorectal cancer exosome data; the colorectal cancer exosome data is obtained from an exosome database; the exosome database includes a first exosome database and a second exosome database; the colorectal cancer data includes differential expression data of lncRNA, mirna, and mrna in the first exosome database; the differential expression data of lncRNA, mirna, and mrna are screened by the first screening standard to obtain the screened differential expression data of lncRNA, mirna, and mrna, and the screened differential expression data of lncRNA, mirna, and mrna are merged The differential expression data of miRNA and the genes in the differential expression data of mRNA after screening are used to obtain the second exosome candidate target panel; the colorectal cancer data also include the gene expression data of lncRNA and mRNA in the second exosome database; the gene expression data of lncRNA and mRNA are differentially screened according to the second screening standard to obtain the gene expression data of lncRNA and mRNA after screening; the genes in the gene expression data of lncRNA after screening and the gene expression data of mRNA after screening are combined to obtain the third exosome candidate target panel; the intersection between the second exosome candidate target panel and the third exosome candidate target panel is taken to obtain the exosome-derived targeting gene candidate panel; the predicted genes include: any one or two of CEMIP, ENC1, and NFE2L3; The prediction module is used to perform classification prediction based on the expression data of the prediction gene to obtain a classification result of whether the sample to be tested has a high or low risk of colorectal cancer; if the expression amount of the prediction gene is higher than a threshold, a classification result is obtained that the sample to be tested has a high risk of colorectal cancer.

8. A computer device, characterized in that: The device comprises: a memory and a processor; the memory is used to store program instructions; the processor is used to call the program instructions, and when the program instructions are executed, it is used to execute the steps of the method described in any one of claims 1 to 6.

9. A computer-readable storage medium, characterized in that: A computer program is stored thereon, and when the computer program is executed by a processor, the steps of the method described in any one of claims 1 to 6 are implemented.

10. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

Images