A method and system for monitoring early recurrence of colorectal cancer

Abstract

The present invention provides a method and system for monitoring early recurrence of colorectal cancer, which belongs to the field of data detection technology, and specifically comprises: determining the matching credible sequencing number of the gene mutation site based on the sequencing number corresponding to different gene mutation sites, and using it as the matching sequencing number, determining the patient's recurrence risk coefficient by the sequencing credibility coefficient of the matching sequencing number corresponding to different gene mutation sites, and the association data of the gene mutation site and colorectal cancer when the requirements are met, obtaining the distribution data of the patient's gene mutation site in different credible sequencing numbers, and outputting the patient's monitoring strategy in combination with the sequencing credibility coefficient of different sequencing numbers and the recurrence risk coefficient, thereby realizing differentiated detection of different patients.

Description

Technical Field

[0001] The present invention belongs to the technical field of data detection, and in particular relates to a method and system for monitoring early recurrence of colorectal cancer. Background Art

[0002] In order to achieve early recurrence monitoring and treatment of colorectal cancer, the invention patent application CN202411153096.5 "Biomarkers for early colorectal cancer detection and their applications" screened out risk prediction biomarkers by analyzing the proteins with significantly different abundance levels in the blood of patients with advanced adenomas, early colorectal cancer and healthy controls in the process of colorectal cancer tumors, thereby accurately, non-invasively and efficiently predicting the risk of early colorectal cancer in individuals, meeting clinical needs. However, there are the following technical problems:

[0003] Early recurrence monitoring of colorectal cancer is often accompanied by gene mutations. Therefore, when determining an individual's risk of early colorectal cancer, if a differentiated recurrence monitoring strategy cannot be determined based on changes in the patient's genetic testing data, timely and effective output of the recurrence risk cannot be guaranteed.

[0004] In response to the above technical problems, the present invention provides a method and system for monitoring early recurrence of colorectal cancer. Summary of the invention

[0005] To achieve the purpose of the present invention, the present invention adopts the following technical solutions:

[0006] According to one aspect of the present invention, a method for monitoring early recurrence of colorectal cancer is provided.

[0007] A method for monitoring early recurrence of colorectal cancer, specifically comprising:

[0008] S1 determines the gene mutation sites of the patient at different sequencing times, obtains the sequencing times corresponding to different gene mutation sites, and determines that the patient has a suspected recurrence risk by combining the association data of different gene mutation sites with colorectal cancer, and then proceeds to the next step;

[0009] S2 obtains sequencing parameters corresponding to different sequencing times, and determines sequencing credibility coefficients and credible sequencing times for different sequencing times in combination with distribution data of gene mutation sites at different sequencing times and corresponding sequencing times;

[0010] S3: Determine the matching credible sequencing number of the gene mutation site based on the sequencing number corresponding to different gene mutation sites, and use it as the matching sequencing number. When the recurrence risk coefficient of the patient is determined to meet the requirements based on the sequencing credibility coefficient of the matching sequencing number corresponding to different gene mutation sites and the association data between the gene mutation site and colorectal cancer, proceed to the next step;

[0011] S4 obtains the distribution data of the gene mutation sites of the patient in different credible sequencing times, and outputs the monitoring strategy of the patient in combination with the sequencing credibility coefficients and recurrence risk coefficients of different sequencing times.

[0012] The beneficial effects of the present invention are:

[0013] The reliable sequencing times are determined based on the corresponding sequencing parameters, distribution data of gene mutation sites and the corresponding sequencing times. This not only takes into account the influence of parameters such as the sequencing processing depth corresponding to different sequencing times on the credibility of data at different sequencing times, but also realizes the influence of the matching of gene mutation sites and other sequencing times on the credibility of data results at different sequencing times. It realizes the screening of reliable sequencing times from multiple angles and lays the foundation for further differentiated determination of patient monitoring strategies.

[0014] The patient's monitoring strategy is output based on the distribution data of the patient's gene mutation sites in different credible sequencing times, the sequencing confidence coefficient and the recurrence risk coefficient. This takes into account the differences in the patient's gene mutation conditions caused by the differences in the distribution numbers of gene mutation sites at different credible times, while also taking into account the patient's risk of recurrence. The output of the patient's monitoring strategy is achieved based on the recurrence risk and the abnormal degree of gene mutation, which not only ensures the reliability of the patient's monitoring and treatment, but also improves the efficiency of the patient's monitoring and treatment.

[0015] A further technical solution is that the gene mutation stage is determined according to analysis results of gene mutation data at different sequencing times.

[0016] A further technical solution is that the association data between the gene mutation site and colorectal cancer include the number and proportion of recurrent patients with the gene mutation site.

[0017] A further technical solution is to determine that the patient has a suspected risk of recurrence, specifically including:

[0018] Determine the number of complex patients including the gene mutation site based on the association data between different gene mutation sites and colorectal cancer, and use the number of relapsed patients to determine the associated fragments in the gene breakthrough fragment;

[0019] The total number of sequencing times including the associated fragments is determined based on the number of sequencing times corresponding to different associated fragments, and the total number of sequencing times including the associated fragments is used to determine whether the patient has a suspected recurrence risk.

[0020] A further technical solution is that the associated fragments are gene mutation sites in which the number of relapsed patients is greater than a preset number of relapsed patients.

[0021] A further technical solution is that when the total number of sequencing times including the associated fragments is greater than a preset number threshold, it is determined that the patient has a suspected risk of recurrence.

[0022] A further technical solution is to use the monitoring requirement coefficient to determine the monitoring strategy for the patient, specifically including:

[0023] The matching monitoring strategy corresponding to the monitoring requirement coefficient of the patient is determined using the monitoring requirement coefficient, and the monitoring strategy of the patient is determined using the matching monitoring strategy corresponding to the monitoring requirement coefficient of the patient.

[0024] A further technical solution is that the monitoring strategy includes the sequencing depth of gene monitoring.

[0025] In a second aspect, the present invention provides a computer system comprising: a memory and a processor that are communicatively connected, and a computer program stored in the memory and capable of running on the processor, wherein the processor executes the above-mentioned method for monitoring early recurrence of colorectal cancer when running the computer program.

[0026] Other features and advantages will be described in the following description. The objects and other advantages of the present invention are realized and obtained by the structures particularly pointed out in the description and drawings.

[0027] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, preferred embodiments are given below and described in detail with reference to the accompanying drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0028] The above and other features and advantages of the present invention will become more apparent by describing in detail exemplary embodiments thereof with reference to the attached drawings.

[0029] Figure 1 is a flow chart of a method for monitoring early recurrence of colorectal cancer;

[0030] Figure 2 is a flow chart of the method for identifying patients at suspected risk of recurrence;

[0031] Figure 3 is a flow chart of a method for determining a sequencing confidence coefficient of sequencing times;

[0032] Figure 4 A flowchart of a method for determining an output of a patient monitoring strategy;

[0033] Figure 5 It is a framework diagram of a computer system. DETAILED DESCRIPTION

[0034] In order to enable those skilled in the art to better understand the technical solutions in this specification, the technical solutions in the embodiments of this specification will be clearly and completely described below in conjunction with the drawings in the embodiments of this specification. Obviously, the described embodiments are only part of the embodiments of this specification, not all of the embodiments. Based on the embodiments of this specification, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of this specification.

[0035] Because there are differences in the changes in patients' genetic testing data when determining their risk of early colorectal cancer, different patients adopt differentiated recurrence monitoring strategies, that is, speeding up the detection frequency for patients with higher mutation levels and improving the real-time monitoring and analysis of cancer risk.

[0036] Suspected recurrence risk: The change probability of different gene mutation sites is determined by the ratio of the sequencing times corresponding to different gene mutation sites to the sequencing times. The association coefficient is determined by the proportion of patients with colorectal cancer who have mutations at the gene mutation sites. The suspected risk coefficient is determined based on the sum of the change probabilities of different gene mutation sites and the product of the association coefficients. Patients with a suspected risk coefficient greater than 0.5 are considered to be at suspected recurrence risk.

[0037] Sequencing confidence coefficient of sequencing times: determine the mutant fragments whose sequencing times are greater than the preset sequencing times according to the sequencing times corresponding to the mutant fragments, and use them as screening mutant fragments. Use the number of screened mutant fragments and the sequencing depth to determine the sequencing confidence coefficient under the sequencing times. Specifically, if the number of screened mutant fragments is 5 and the preset weight coefficient corresponding to the sequencing depth under the sequencing times is 0.7, then the sequencing confidence coefficient is 0.1 multiplied by 5 multiplied by 0.7, which is 0.35.

[0038] The sequencing times with a sequencing reliability coefficient greater than 0.2 are regarded as reliable sequencing times.

[0039] Recurrence risk coefficient of patients: Based on the association data of gene mutation sites and colorectal cancer, the percentage of recurrent patients including gene mutation sites is determined, and the mutation association coefficient of the gene mutation site is determined by using the percentage of the number of recurrence patients. The mutation credibility coefficient of the gene mutation site is determined according to the sequencing credibility coefficient of the matching sequencing times corresponding to the gene mutation site. The recurrence risk coefficient of the patient is determined by the sum of the products of the mutation credibility coefficients and the mutation association coefficients of different gene mutation sites. Patients with a recurrence risk coefficient greater than 0.6 are regarded as patients who do not meet the requirements of the complex risk coefficient.

[0040] Output of the patient's monitoring strategy: based on the distribution data of the patient's gene mutation sites in different credible sequencing times, determine the number of the patient's gene mutation sites in different credible sequencing times, determine the preset mutation abnormality coefficients corresponding to different credible sequencing times through the number of gene mutation sites in different credible sequencing times, determine the mutation abnormality coefficients for different credible sequencing times by multiplying the preset mutation abnormality coefficients for different credible sequencing times by the sequencing credible coefficient, determine the patient's gene mutation abnormality coefficient according to the weight sum of the mutation abnormality coefficients for different credible sequencing times, determine the patient's monitoring requirement coefficient based on the average value of the gene mutation abnormality coefficient and the recurrence risk coefficient, and use the monitoring requirement coefficient to determine the patient's monitoring strategy.

[0041] Embodiment 1 To solve the above problem, according to one aspect of the present invention, Figure 1 As shown, a method for monitoring early recurrence of colorectal cancer is provided, which specifically includes:

[0042] S1 determines the gene mutation sites of the patient at different sequencing times, obtains the sequencing times corresponding to different gene mutation sites, and determines that the patient has a suspected recurrence risk by combining the association data of different gene mutation sites with colorectal cancer, and then proceeds to the next step;

[0043] S2 obtains sequencing parameters corresponding to different sequencing times, and determines sequencing credibility coefficients and credible sequencing times for different sequencing times in combination with distribution data of gene mutation sites at different sequencing times and corresponding sequencing times;

[0044] S3: Determine the matching credible sequencing number of the gene mutation site based on the sequencing number corresponding to different gene mutation sites, and use it as the matching sequencing number. When the recurrence risk coefficient of the patient is determined to meet the requirements based on the sequencing credibility coefficient of the matching sequencing number corresponding to different gene mutation sites and the association data between the gene mutation site and colorectal cancer, proceed to the next step;

[0045] S4 obtains the distribution data of the gene mutation sites of the patient in different credible sequencing times, and outputs the monitoring strategy of the patient in combination with the sequencing credibility coefficients and recurrence risk coefficients of different sequencing times.

[0046] Furthermore, the gene mutation stage is determined according to analysis results of gene mutation data at different sequencing times.

[0047] Specifically, the association data between the gene mutation site and colorectal cancer include the number and proportion of recurrent patients with the gene mutation site.

[0048] It should be noted that if Figure 2 As shown, the patient is determined to be at suspected risk of recurrence, including:

[0049] Determine the number of complex patients including the gene mutation site based on the association data between different gene mutation sites and colorectal cancer, and use the number of relapsed patients to determine the associated fragments in the gene breakthrough fragment;

[0050] The total number of sequencing times including the associated fragments is determined based on the number of sequencing times corresponding to different associated fragments, and the total number of sequencing times including the associated fragments is used to determine whether the patient has a suspected recurrence risk.

[0051] Furthermore, the associated fragments are gene mutation sites in which the number of relapsed patients is greater than a preset number of relapsed patients.

[0052] It should also be noted that when the total number of sequencing times including the associated fragments is greater than a preset threshold number, it is determined that the patient is at suspected risk of recurrence.

[0053] It is understood that determining that the patient is at suspected risk of recurrence specifically includes:

[0054] Determine the number of complex patients including the gene mutation site based on the association data between different gene mutation sites and colorectal cancer, and use the number of relapsed patients to determine the associated fragments in the gene breakthrough fragment;

[0055] The associated matching fragments in the associated fragments are determined according to the sequencing times corresponding to different associated fragments, and the number of associated matching fragments is used to determine whether the patient has a suspected recurrence risk.

[0056] Optionally, determining that the patient is at suspected risk of recurrence specifically includes:

[0057] S11 determines the number of complex patients including the gene mutation site based on the association data between different gene mutation sites and colorectal cancer, and determines the association coefficient of the gene mutation site by using the number of relapsed patients and the proportion of the number;

[0058] S12 determines the fragment credibility coefficients of different gene mutation sites based on the sequencing times corresponding to different gene mutation sites;

[0059] S13 determines a comprehensive matching coefficient according to the fragment credibility coefficients and association coefficients of different gene mutation sites, and uses the comprehensive matching coefficient to determine whether the patient has a suspected recurrence risk.

[0060] Furthermore, the sequencing parameters corresponding to the sequencing times include the sequencing depth corresponding to the sequencing times.

[0061] It should be noted that the distribution data of gene mutation sites include the distribution positions of different types of gene mutation sites.

[0062] Specifically, Figure 3 As shown, the method for determining the sequencing confidence coefficient of the sequencing times is:

[0063] Determining the sequencing depth at the sequencing number according to the sequencing parameters corresponding to the sequencing number;

[0064] Determine the matching mutation fragments at the sequencing times based on the distribution data of the gene mutation sites at the sequencing times, determine the matching mutation fragments with a sequencing number greater than a preset sequencing number according to the sequencing number corresponding to the matching mutation fragments, and use them as screening mutation fragments;

[0065] The sequencing confidence coefficient under the sequencing times is determined according to the number of screened mutation fragments and the sequencing depth.

[0066] Furthermore, the sequencing confidence coefficient under the sequencing times is determined according to the product of a preset confidence coefficient corresponding to the number of the screened mutation fragments and a preset confidence coefficient corresponding to the sequencing depth.

[0067] It should also be noted that when the sequencing credibility coefficient under the sequencing times is greater than the preset credibility coefficient, the sequencing times are determined to be credible sequencing times.

[0068] Optionally, the method for determining the sequencing confidence coefficient of the sequencing times is:

[0069] Determining the sequencing depth at the sequencing number according to the sequencing parameters corresponding to the sequencing number;

[0070] Determine the matching mutation fragments at the sequencing times based on the distribution data of the gene mutation sites at the sequencing times, determine the matching mutation fragments with a sequencing number greater than a preset sequencing number based on the sequencing numbers corresponding to different matching mutation fragments, and use them as screening mutation fragments;

[0071] The sequencing confidence coefficient at the sequencing times is determined according to the number of screening mutation fragments at the sequencing depth.

[0072] In another embodiment, the method for determining the sequencing confidence coefficient of the sequencing times is:

[0073] S21 determines the sequencing depth at the sequencing number according to the sequencing parameters corresponding to the sequencing number, and determines the sequencing parameter credibility coefficient at the sequencing number according to the sequencing depth;

[0074] Optionally, the above step S21 includes steps S211-S212, which specifically include:

[0075] S211 determines the sequencing depth at the sequencing times according to the sequencing parameters corresponding to the sequencing times. When the sequencing depth at the sequencing times is less than the preset sequencing depth, it is determined that the sequencing times do not belong to the credible sequencing times. When the sequencing depth at the sequencing times is not less than the preset sequencing depth, proceed to step S212.

[0076] S212 uses the sequencing depth to determine the credibility coefficient of the sequencing parameters under the sequencing times, and proceeds to step S22.

[0077] S22 determining the matching mutation fragments at the sequencing times based on the distribution data of the gene mutation sites at the sequencing times, and determining the data credibility coefficient according to the average of the sequencing times corresponding to the matching mutation fragments and the number of matching mutation fragments;

[0078] Optionally, the above step S22 includes steps S221-S223, specifically:

[0079] S221: When the sequencing parameter credibility coefficient under the sequencing times is within the preset credibility coefficient interval, proceed to step S222; when the sequencing parameter credibility coefficient under the sequencing times is not within the preset credibility coefficient interval, proceed to step S224;

[0080] S222: determining the matching mutation fragments at the sequencing times based on the distribution data of the gene mutation sites at the sequencing times, and when it is determined that there are matching mutation fragments with a sequencing number greater than a preset sequencing number based on the sequencing numbers corresponding to different matching mutation fragments, proceeding to step S223; when there are no matching mutation fragments with a sequencing number greater than the preset sequencing number, proceeding to step S224;

[0081] S223: taking the matching mutation fragments with a sequencing number greater than a preset sequencing number as screening mutation fragments; when the number of screening mutation fragments is greater than a preset mutation fragment number threshold, determining that the sequencing number does not belong to the credible sequencing number; when the number of screening mutation fragments is not greater than the preset mutation fragment number threshold, proceeding to step S224;

[0082] S224 determines the data credibility coefficient according to the average value of the sequencing times corresponding to the matching mutation fragments and the number of matching mutation fragments. When the data credibility coefficient is less than the preset credibility coefficient threshold, it is determined that the sequencing times do not belong to the credible sequencing times. When the data credibility coefficient is not less than the preset credibility coefficient threshold, proceed to step S23.

[0083] S23 determines the sequencing credibility coefficient under the sequencing number according to the sequencing parameter credibility coefficient under the sequencing number and the data credibility coefficient.

[0084] Specifically, determining whether the patient's recurrence risk coefficient meets the requirements specifically includes:

[0085] Based on the association data between the gene mutation site and colorectal cancer, determining the percentage of recurrent patients including the gene mutation site, and using the percentage to determine the mutation association coefficient of the gene mutation site;

[0086] Determining a mutation confidence coefficient of the gene mutation site according to a sequencing confidence coefficient of the matching sequencing times corresponding to the gene mutation site;

[0087] The recurrence risk coefficient of the patient is determined by the mutation credibility coefficient and mutation association coefficient of different gene mutation sites, and combined with the preset risk coefficient threshold to determine whether the recurrence risk coefficient of the patient meets the requirements.

[0088] Furthermore, the mutation confidence coefficient of the gene mutation site is determined according to the weighted sum of the sequencing confidence coefficients of the matching sequencing times corresponding to the gene mutation site.

[0089] It should also be noted that when the recurrence risk coefficient of the patient is less than the preset risk coefficient threshold, it is determined that the recurrence risk coefficient of the patient meets the requirement.

[0090] It is understandable that when the recurrence risk coefficient of the patient does not meet the requirements, the monitoring strategy of the patient is determined based on the preset monitoring strategy.

[0091] Optionally, determining whether the patient's recurrence risk coefficient meets the requirements specifically includes:

[0092] Based on the association data between the gene mutation site and colorectal cancer, the proportion of recurrent patients including the gene mutation site is determined, and the mutation association coefficient of the gene mutation site is determined by using the proportion of the number, and the gene mutation site is divided into different association coefficient intervals by using the mutation association coefficient, and when the number of gene mutation sites within the preset association coefficient interval is not less than the preset fragment number threshold, it is determined that the recurrence risk coefficient of the patient does not meet the requirement;

[0093] When the number of gene mutation sites within the preset correlation coefficient interval is less than the preset fragment number threshold:

[0094] Determining the comprehensive correlation coefficient of the patient by using the mutation correlation coefficients of different gene mutation sites, and when the comprehensive correlation coefficient of the patient is greater than a preset comprehensive correlation coefficient threshold, determining that the recurrence risk coefficient of the patient does not meet the requirement;

[0095] When the comprehensive correlation coefficient of the patient is not greater than the preset comprehensive correlation coefficient threshold:

[0096] Determine the mutation confidence coefficient of the gene mutation site according to the sequencing confidence coefficient of the matching sequencing times corresponding to the gene mutation site, and determine the association risk coefficients of different gene mutation sites by multiplying the mutation confidence coefficients of different gene mutation sites and the mutation association coefficients;

[0097] When there is a gene mutation site whose associated risk coefficient is greater than the preset associated risk coefficient threshold:

[0098] When the number of gene mutation sites whose associated risk coefficient is greater than the preset associated risk coefficient threshold does not meet the requirement, it is determined that the recurrence risk coefficient of the patient does not meet the requirement;

[0099] When there is no gene mutation site with an association risk coefficient greater than the preset association risk coefficient threshold or the number of gene mutation sites with an association risk coefficient greater than the preset association risk coefficient threshold meets the requirements:

[0100] The recurrence risk coefficient of the patient is determined by the mutation credibility coefficient and mutation association coefficient of different gene mutation sites, and combined with the preset risk coefficient threshold to determine whether the recurrence risk coefficient of the patient meets the requirements.

[0101] Specifically, Figure 4 As shown, the method for determining the output of the patient monitoring strategy is:

[0102] Determining the number of gene mutation sites of the patient at different credible sequencing times based on the distribution data of the gene mutation sites of the patient at different credible sequencing times;

[0103] Determine the preset mutation abnormality coefficients corresponding to different credible sequencing times by the number of gene mutation sites in different credible sequencing times, and determine the mutation abnormality coefficients of different credible sequencing times by multiplying the preset mutation abnormality coefficients of different credible sequencing times by the sequencing credible coefficient;

[0104] The patient's gene mutation abnormality coefficient is determined according to the weights of the mutation abnormality coefficients of different credible sequencing times, the patient's monitoring requirement coefficient is determined based on the gene mutation abnormality coefficient and the average value of the recurrence risk coefficient, and the patient's monitoring strategy is determined using the monitoring requirement coefficient.

[0105] Further, the monitoring strategy for the patient is determined using the monitoring requirement coefficient, specifically including:

[0106] The matching monitoring strategy corresponding to the monitoring requirement coefficient of the patient is determined using the monitoring requirement coefficient, and the monitoring strategy of the patient is determined using the matching monitoring strategy corresponding to the monitoring requirement coefficient of the patient.

[0107] It should be noted that the monitoring strategy includes the sequencing depth of gene monitoring.

[0108] Embodiment 2 In the second aspect, as Figure 5 As shown, the present invention provides a computer system, comprising: a memory and a processor connected in communication, and a computer program stored in the memory and capable of running on the processor, wherein the processor executes the above-mentioned method for monitoring early recurrence of colorectal cancer when running the computer program.

[0109] Optionally, the above step S11 includes steps S111-S113, which are specifically:

[0110] S111 determines the number of complex patients including the gene mutation site based on the association data between different gene mutation sites and colorectal cancer, and when there is a gene mutation site where the number of recurrent patients is greater than the preset number of patients, proceeds to step S113; when there is no gene mutation site where the number of recurrent patients is greater than the preset number of patients, proceeds to step S112;

[0111] S112: obtaining the percentage of relapsed patients including the gene mutation site; when the percentage of relapsed patients not having the gene mutation site is greater than the preset percentage, determining that the patient does not have a suspected relapse risk; when the percentage of relapsed patients not having the gene mutation site is greater than the preset percentage, proceeding to step S113;

[0112] S113 determines the correlation coefficient of the gene mutation site by using the number of relapsed patients and the proportion of the number. When the number of gene mutation sites with a correlation coefficient greater than a preset correlation coefficient is greater than the preset number of mutation fragments, it is determined that the patient has a suspected relapse risk. When the number of gene mutation sites with a correlation coefficient greater than the preset correlation coefficient is not greater than the preset number of mutation fragments, proceed to step S12.

[0113] Optionally, the above step S12 includes steps S121-S123, specifically:

[0114] S121: When it is determined that there is no gene mutation site with a sequencing number greater than a preset sequencing number based on the sequencing numbers corresponding to different gene mutation sites, it is determined that the patient does not have a suspected recurrence risk; when there is a gene mutation site with a sequencing number greater than the preset sequencing number, the process proceeds to step S122;

[0115] S122: taking the gene mutation sites with a sequencing number greater than a preset sequencing number as screening mutation fragments, and when there are screening mutation fragments with a correlation coefficient greater than a preset coefficient threshold, proceeding to step S123; when there are no screening mutation fragments with a correlation coefficient greater than the preset coefficient threshold, it is determined that the patient does not have a suspected recurrence risk;

[0116] S123 determines the fragment credibility coefficients of different gene mutation sites based on the number of sequencing times corresponding to different gene mutation sites. When the number of screening mutation fragments whose fragment credibility coefficients are greater than the preset credibility coefficients is greater than the preset number of mutation fragments, it is determined that the patient has a suspected recurrence risk. When the number of screening mutation fragments whose fragment credibility coefficients are greater than the preset credibility coefficients is not greater than the preset number of mutation fragments, proceed to step S13.

[0117] Optionally, the above step S13 includes steps S131-S133, specifically:

[0118] S131 determines the matching coefficients of different gene mutation sites according to the fragment credibility coefficients and association coefficients of different gene mutation sites. When there is a gene mutation site with a matching coefficient greater than a preset matching coefficient, the process proceeds to step S132. When there is no gene mutation site with a matching coefficient greater than the preset matching coefficient, the process proceeds to step S133.

[0119] S132: When the number of gene mutation sites with a matching coefficient greater than the preset matching coefficient is greater than the preset number of mutation fragments, it is determined that the patient has a suspected recurrence risk; when the number of gene mutation sites with a matching coefficient greater than the preset matching coefficient is not greater than the preset number of mutation fragments, proceed to step S133;

[0120] S133 determines a comprehensive matching coefficient according to the fragment credibility coefficients and association coefficients of different gene mutation sites, and uses the comprehensive matching coefficient to determine whether the patient has a suspected recurrence risk.

[0121] Each embodiment in this specification is described in a progressive manner, and the same or similar parts between the embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the device, equipment, and non-volatile computer storage medium embodiments, since they are basically similar to the method embodiments, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment.

[0122] The above is a description of a specific embodiment of the specification. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recorded in the claims can be performed in an order different from that in the embodiments and still achieve the desired results. In addition, the processes depicted in the drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0123] The above description is only one or more embodiments of this specification and is not intended to limit this specification. For those skilled in the art, one or more embodiments of this specification may have various changes and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of one or more embodiments of this specification shall be included in the scope of the claims of this specification.

Claims

1. A method for monitoring early recurrence of colorectal cancer, characterized in that: Specifically include: Determine the gene mutation sites of the patient at different sequencing times, obtain the sequencing times corresponding to different gene mutation sites, and combine the association data of different gene mutation sites with colorectal cancer to determine that the patient has a suspected recurrence risk, and then proceed to the next step; Obtaining sequencing parameters corresponding to different sequencing times, and determining sequencing credibility coefficients and credible sequencing times for different sequencing times in combination with distribution data of gene mutation sites at different sequencing times and corresponding sequencing times; Determine the number of reliable sequencing times for matching the gene mutation site based on the number of sequencing times corresponding to different gene mutation sites, and use it as the number of matching sequencing times. When the recurrence risk coefficient of the patient is determined to meet the requirements based on the sequencing reliability coefficient of the number of matching sequencing times corresponding to different gene mutation sites and the association data between the gene mutation site and colorectal cancer, proceed to the next step. Obtaining the distribution data of the gene mutation sites of the patient at different credible sequencing times, and outputting the monitoring strategy of the patient in combination with the sequencing credibility coefficients and recurrence risk coefficients of different sequencing times; The output of the patient monitoring strategy is determined by: Determining the number of gene mutation sites of the patient at different credible sequencing times based on the distribution data of the gene mutation sites of the patient at different credible sequencing times; Determine the preset mutation abnormality coefficients corresponding to different credible sequencing times by the number of gene mutation sites in different credible sequencing times, and determine the mutation abnormality coefficients of different credible sequencing times by multiplying the preset mutation abnormality coefficients of different credible sequencing times by the sequencing credible coefficient; The patient's gene mutation abnormality coefficient is determined according to the weights of the mutation abnormality coefficients of different credible sequencing times, the patient's monitoring requirement coefficient is determined based on the gene mutation abnormality coefficient and the average value of the recurrence risk coefficient, and the patient's monitoring strategy is determined using the monitoring requirement coefficient.

2. The method for monitoring early recurrence of colorectal cancer according to claim 1, characterized in that: The gene mutation stage is determined according to the analysis results of the gene mutation data at different sequencing times.

3. The method for monitoring early recurrence of colorectal cancer according to claim 1, characterized in that: The association data between the gene mutation site and colorectal cancer include the number and proportion of recurrent patients with the gene mutation site.

4. The method for monitoring early recurrence of colorectal cancer according to claim 1, characterized in that: Determine that the patient is at suspected risk of recurrence, including: Determine the number of complex patients including the gene mutation site based on the association data between different gene mutation sites and colorectal cancer, and use the number of relapsed patients to determine the associated fragments in the gene breakthrough fragment; The total number of sequencing times including the associated fragments is determined based on the number of sequencing times corresponding to different associated fragments, and the total number of sequencing times including the associated fragments is used to determine whether the patient has a suspected recurrence risk.

5. The method for monitoring early recurrence of colorectal cancer according to claim 4, characterized in that: The associated fragments are gene mutation sites in which the number of relapsed patients is greater than the preset number of relapsed patients.

6. The method for monitoring early recurrence of colorectal cancer according to claim 1, characterized in that: The sequencing parameters corresponding to the sequencing times include the sequencing depth corresponding to the sequencing times.

7. The method for monitoring early recurrence of colorectal cancer according to claim 1, characterized in that: Determining the monitoring strategy for the patient using the monitoring requirement coefficient specifically includes: The matching monitoring strategy corresponding to the monitoring requirement coefficient of the patient is determined using the monitoring requirement coefficient, and the monitoring strategy of the patient is determined using the matching monitoring strategy corresponding to the monitoring requirement coefficient of the patient.

8. The method for monitoring early recurrence of colorectal cancer according to claim 1, characterized in that: The monitoring strategy includes the sequencing depth of gene monitoring.

9. A computer system comprising: A memory and a processor connected in communication, and a computer program stored in the memory and capable of running on the processor, characterized in that the processor executes a method for monitoring early recurrence of colorectal cancer as described in any one of claims 1-8 when running the computer program.

Images