Construction method of microsatellite instability detection model, detection method and electronic device

By constructing a microsatellite instability detection model and utilizing machine learning methods to achieve single-sample microsatellite instability detection, the cost and accuracy issues of NGS single-sample detection are solved, providing an efficient detection solution.

CN118969076APending Publication Date: 2024-11-15BEIJING USCI MEDICAL DEVICES CO LTD

Patent Information

Application Number
CN202410862809.9
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-06-28
Publication Date
2024-11-15

AI Technical Summary

Technical Problem

The lack of NGS-based single-sample microsatellite instability detection methods in the current technology leads to high detection costs and makes it impossible to conduct retrospective studies.

Method used

A microsatellite instability detection model was constructed. By calculating the microsatellite site mutation frequency of the reference set samples, a machine learning method was used to obtain the microsatellite instability judgment threshold, thereby achieving single-sample detection.

Benefits of technology

This invention enables single-sample microsatellite instability detection based on NGS, with high accuracy, specificity, and sensitivity, while reducing detection costs and making it suitable for clinical applications.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118969076A_ABST
    Figure CN118969076A_ABST
Patent Text Reader

Abstract

The invention provides a microsatellite instability detection model construction method, a microsatellite instability detection method and an electronic device. The construction method comprises the following steps: S1) calculating and obtaining microsatellite mutation frequencies of microsatellite loci of all samples in reference set samples, and combining the microsatellite mutation frequencies to obtain a reference set feature matrix; the samples in the reference set comprise microsatellite stable samples and microsatellite unstable samples; s2) performing machine learning on the reference set feature matrix to obtain a microsatellite instability detection model; the microsatellite instability detection model contains a reference set feature vector and a microsatellite instability judgment threshold value. The problem that microsatellite instability detection of a single sample is difficult to realize in the prior art can be solved, and the method is suitable for the field of microsatellite instability detection.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the field of microsatellite instability detection, and in particular to a method for constructing a microsatellite instability detection model, a detection method and an electronic device. Background Art

[0002] Microsatellites are DNA repeat sequences containing 1 to 6 or up to 10 nucleotides. During DNA replication, there is a high risk of replication errors in these motifs, which should be recognized and corrected by mismatch repair (MMR) proteins. If there are defects / mutations in the MMR proteins, microsatellite replication errors are not corrected, resulting in microsatellite instability. The loss of MMR function in tumor suppressor genes leads to the accumulation of mutations, which can eventually lead to the formation of adenomas and the transformation of adenomas to cancer. The patient's microsatellite instability status is of great significance for the choice of clinical treatment methods, and accurate detection of the patient's microsatellite status is very important clinically.

[0003] Among the many methods for detecting microsatellite instability, multiplex fluorescence PCR-capillary electrophoresis (MSI-PCR) is one of the most commonly used methods due to its high sensitivity and good specificity. However, MSI-PCR is relatively expensive, and PCR technology can only detect a limited number of sites. When cancer patients also have other testing needs such as detecting targeted drug sites, this method has obvious limitations. In addition, Sanger and IHC detection methods also have limitations in detection accuracy, ease of operation, and detection range. The method of detecting microsatellite instability based on NGS is currently a trend due to its accuracy and the ability to detect multiple targeted sites at the same time. Detecting the microsatellite instability status of patients' genes through NGS is a current trend.

[0004] However, most algorithms for detecting microsatellite instability based on NGS need to be based on dual samples, that is, detection is performed based on tumor tissue and control tissue at the same time. However, simultaneous sequencing of dual samples increases the cost of detection, and in many cases (such as retrospective studies) control samples are not available. Based on a single sample, the detection algorithm of NGS data is not mature enough and has poor performance. Therefore, the prior art lacks a method for detecting microsatellite instability based on a single sample based on NGS. Summary of the invention

[0005] The main purpose of the present invention is to provide a method for constructing a microsatellite instability detection model, a detection method and an electronic device to solve the problem that it is difficult to realize microsatellite instability detection of a single sample in the prior art.

[0006] In order to achieve the above-mentioned object, according to a first aspect of the present invention, a method for constructing a microsatellite instability detection model is provided, the method comprising: S1) calculating and obtaining the microsatellite mutation frequencies of the microsatellite loci of all samples in the reference set sample, and merging them to obtain a reference set feature matrix; the samples in the reference set include microsatellite stable samples and microsatellite unstable samples; S2) performing machine learning on the reference set feature matrix to obtain a microsatellite instability detection model; the microsatellite instability detection model contains a reference set feature vector and a microsatellite instability judgment threshold;The microsatellite loci are selected from any one or more of the following: chr22: 29682882-29682893, chr3: 52696311-52696321, chr21: 42873556-42873563, chrX: 44949952-44949962, chr1: 161309336-161309346, chr3: 149290606-149290615, chr22: 29690901-29690911, chr14: 68944322-68944332, chr2: 212495337-2 12495347, chr12:12030237-12030252, chr9:87487519-87487529, chr6:109319968-109319978, chr17:40468976-40468987, chr3:71 008351-71008354, chr2:158637137-158637150, chr11:94212931-94212941, chr1:245977726-245977735, chr5:170818291-17081830 0. chr5:67584513-67584524, chr2:141625631-141625641, chr9:8484398-8484407, chr19:50911948-50911959, chr14:65542680-65 542691, chr17:30320861-30320871, chr21:42838094-42838103, chr17:47696765-47696774, chr2:46583273-46583282, chr2:192011 486-192011496, chr7:140421096-140421107, chr7:140489020-140489029, chr6:32790100-32790109, chr1:46597497-46597507, chr3:30691872-30691881, chrX:70608764-70608773, chr4:1919853-1919862, chr20:39702015-39702027 and chr14:68944344-68944357. ;

[0007] Furthermore, in S2), the method for obtaining the microsatellite instability judgment threshold includes: cross-multiplying the microsatellite mutation frequency of the microsatellite loci of all samples with the reference set feature vector to obtain the microsatellite instability score of all samples; and performing machine learning on the microsatellite instability scores of all samples to obtain the microsatellite instability judgment threshold.

[0008] Further, in S2), the machine learning method includes dimensionality reduction processing; preferably, the dimensionality reduction processing method includes one or more of PCA, tSNE or UMAP.

[0009] In order to achieve the above object, according to a second aspect of the present invention, a method for detecting microsatellite instability is provided, the method comprising: S1) calculating and obtaining the microsatellite mutation frequency of one or more microsatellite loci of the sample to be tested; S2) inputting the microsatellite mutation frequency of the microsatellite loci of the sample to be tested into the microsatellite instability detection model constructed by the method for constructing a microsatellite instability detection model according to any one of claims 1 to 3, and obtaining the microsatellite instability detection result of the sample to be tested;The microsatellite loci are selected from any one or more of the following: chr22: 29682882-29682893, chr3: 52696311-52696321, chr21: 42873556-42873563, chrX: 44949952-44949962, chr1: 161309336-161309346, chr3: 149290606-149290615, chr22: 29690901-29690911, chr14: 68944322-68944332, chr2: 212495337-2 12495347, chr12:12030237-12030252, chr9:87487519-87487529, chr6:109319968-109319978, chr17:40468976-40468987, chr3:71 008351-71008354, chr2:158637137-158637150, chr11:94212931-94212941, chr1:245977726-245977735, chr5:170818291-17081830 0. chr5:67584513-67584524, chr2:141625631-141625641, chr9:8484398-8484407, chr19:50911948-50911959, chr14:65542680-65 542691, chr17:30320861-30320871, chr21:42838094-42838103, chr17:47696765-47696774, chr2:46583273-46583282, chr2:192011 486-192011496, chr7:140421096-140421107, chr7:140489020-140489029, chr6:32790100-32790109, chr1:46597497-46597507, chr3:30691872-30691881, chrX:70608764-70608773, chr4:1919853-1919862, chr20:39702015-39702027 and chr14:68944344-68944357. ;

[0010] Further, S2) includes: S2-1) cross-producting the microsatellite mutation frequency of the microsatellite locus of the sample to be tested with the characteristic vector of the reference set to obtain the microsatellite instability score of the sample to be tested; S2-2) comparing the microsatellite instability score of the sample to be tested with a microsatellite instability judgment threshold; if the microsatellite instability score of the sample to be tested is greater than the threshold, the sample to be tested is a microsatellite unstable sample; if the microsatellite instability score of the sample to be tested is less than the threshold, the sample to be tested is a microsatellite stable sample.

[0011] According to a third aspect of the present invention, an electronic device for microsatellite instability detection is provided, the electronic device comprising a microsatellite mutation frequency acquisition unit for a sample to be tested and a microsatellite instability detection result acquisition unit for the sample to be tested, wherein the microsatellite mutation frequency acquisition unit for the sample to be tested is used to calculate and obtain the microsatellite mutation frequency of one or more microsatellite loci of the sample to be tested; the microsatellite instability detection result acquisition unit for the sample to be tested is used to input the microsatellite mutation frequency of the microsatellite loci of the sample to be tested into the microsatellite instability detection model constructed by any of the above-mentioned methods for constructing a microsatellite instability detection model, and obtain the microsatellite instability detection result of the sample to be tested;The microsatellite loci are selected from any one or more of the following: chr22: 29682882-29682893, chr3: 52696311-52696321, chr21: 42873556-42873563, chrX: 44949952-44949962, chr1: 161309336-161309346, chr3: 149290606-149290615, chr22: 29690901-29690911, chr14: 68944322-68944332, chr2: 212495337-2 12495347, chr12:12030237-12030252, chr9:87487519-87487529, chr6:109319968-109319978, chr17:40468976-40468987, chr3:71 008351-71008354, chr2:158637137-158637150, chr11:94212931-94212941, chr1:245977726-245977735, chr5:170818291-17081830 0. chr5:67584513-67584524, chr2:141625631-141625641, chr9:8484398-8484407, chr19:50911948-50911959, chr14:65542680-65 542691, chr17:30320861-30320871, chr21:42838094-42838103, chr17:47696765-47696774, chr2:46583273-46583282, chr2:192011 486-192011496, chr7:140421096-140421107, chr7:140489020-140489029, chr6:32790100-32790109, chr1:46597497-46597507, chr3:30691872-30691881, chrX:70608764-70608773, chr4:1919853-1919862, chr20:39702015-39702027 and chr14:68944344-68944357. ;

[0012] Furthermore, the microsatellite instability detection result acquisition unit of the sample to be tested includes a microsatellite instability score acquisition unit of the sample to be tested and a microsatellite instability result judgment unit of the sample to be tested, wherein the microsatellite instability score acquisition unit of the sample to be tested is used to cross-product the microsatellite mutation frequency of the microsatellite site of the sample to be tested with the reference set feature vector to obtain the microsatellite instability score of the sample to be tested; the microsatellite instability result judgment unit of the sample to be tested is used to compare the microsatellite instability score of the sample to be tested with a microsatellite instability judgment threshold; if it is greater than the threshold, the sample to be tested is judged to be a microsatellite unstable sample; if it is less than the threshold, the sample to be tested is judged to be a microsatellite stable sample.

[0013] According to a fourth aspect of the present invention, there is provided an application of a microsatellite locus in detecting a microsatellite instability product, wherein the microsatellite locus comprises any one or more of the following: chr22:29682882-29682893, chr3:52696311-52696321, chr21:42873556-42873563, chrX:44949952-44949962, chr1:161309336-161309346, chr3:149290606-149290615, chr22:29690901-29690911, chr14:6894 4322-68944332, chr2:212495337-212495347, chr12:12030237-12030252, chr9:87487519-87487529, chr6:109319968-109319978, chr17: 40468976-40468987、chr3:71008351-71008354、chr2:158637137-158637150、chr11:94212931-94212941、chr1:245977726-245977735、chr 5:170818291-170818300, chr5:67584513-67584524, chr2:141625631-141625641, chr9:8484398-8484407, chr19:50911948-50911959, ch r14:65542680-65542691, chr17:30320861-30320871, chr21:42838094-42838103, chr17:47696765-47696774, chr2:46583273-46583282, c hr2:192011486-192011496, chr7:140421096-140421107, chr7:140489020-140489029, chr6:32790100-32790109, chr1:46597497-46597507, chr3:30691872-30691881, chrX:70608764-70608773, chr4:1919853-1919862, chr20:39702015-39702027, and chr14:68944344-68944357.

[0014] Further, detecting microsatellite instability includes detecting the microsatellite mutation frequency of the microsatellite locus; preferably, the product includes a kit, a chip and / or an electronic detection device.

[0015] According to a fifth aspect of the present invention, a kit for detecting microsatellite instability is provided, the kit comprising a detection reagent for the microsatellite mutation frequency of a microsatellite locus, wherein the microsatellite locus comprises any one or more of the following: chr22:29682882-29682893, chr3:52696311-52696321, chr21:42873556-42873563, chrX:44949952-44949962, chr1:161309336-161309346, chr3:149290606-149290615, chr22:29690901-2969091 1. chr14:68944322-68944332, chr2:212495337-212495347, chr12:12030237-12030252, chr9:87487519-87487529, chr6:109319968-109319 978, chr17:40468976-40468987, chr3:71008351-71008354, chr2:158637137-158637150, chr11:94212931-94212941, chr1:245977726-24597 7735, chr5:170818291-170818300, chr5:67584513-67584524, chr2:141625631-141625641, chr9:8484398-8484407, chr19:50911948-50911 959, chr14:65542680-65542691, chr17:30320861-30320871, chr21:42838094-42838103, chr17:47696765-47696774, chr2:46583273-465832 82, chr2:192011486-192011496, chr7:140421096-140421107, chr7:140489020-140489029, chr6:32790100-32790109, chr1:46597497-46597507, chr3:30691872-30691881, chrX:70608764-70608773, chr4:1919853-1919862, chr20:39702015-39702027 and chr14:68944344-68944357.

[0016] Furthermore, the kit includes probes and / or primers for detecting the microsatellite mutation frequency at the microsatellite loci; preferably, the DNA at the microsatellite loci is prepared into relevant reagents for high-throughput sequencing.

[0017] According to a sixth aspect of the present invention, there is provided an electronic device, the electronic device comprising: a processor; and a memory for storing executable instructions of the processor;

[0018] The processor is configured to execute any of the above-mentioned methods for constructing a microsatellite instability detection model or any of the above-mentioned methods for detecting microsatellite instability by executing executable instructions.

[0019] According to a sixth aspect of the present invention, there is provided a computer-readable storage medium including a stored computer program, which, when the computer program is executed, controls the device where the computer-readable storage medium is located to carry out any of the above-mentioned methods for constructing a microsatellite instability detection model or any of the above-mentioned methods for detecting microsatellite instability.

[0020] By applying the technical solution of the present invention, the microsatellite mutation frequencies of the microsatellite loci of all samples in all microsatellite stable samples and all microsatellite unstable samples are calculated and obtained, and the reference set feature matrix containing the mutation frequency vectors of all the above samples is obtained after merging. After machine learning of the feature matrix, the microsatellite instability detection model of the present application can be obtained, and the detection model contains the reference set feature vector and the microsatellite instability judgment threshold. When the microsatellite instability model constructed by the present application is used for microsatellite instability detection, single-sample detection can be achieved, which overcomes the disadvantage of double-sample detection in the prior art. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] The drawings constituting a part of the present application are used to provide a further understanding of the present invention. The exemplary embodiments of the present invention and their descriptions are used to explain the present invention and do not constitute an improper limitation of the present invention. In the drawings:

[0022] Figure 1 A schematic flow chart of a method for constructing a microsatellite instability detection model according to an embodiment of the present invention is shown.

[0023] Figure 2 A schematic diagram of an electronic device for detecting microsatellite instability according to an embodiment of the present invention is shown.

[0024] Figure 3 A hardware structure block diagram of an electronic device (or mobile device) for detecting microsatellite instability according to an embodiment of the present invention is shown.

[0025] Figure 4A schematic diagram of the ROC curve of the microsatellite instability detection model according to Example 2 of the present invention is shown. DETAILED DESCRIPTION

[0026] It should be noted that, in the absence of conflict, the embodiments and features in the embodiments of the present application can be combined with each other. The present invention will be described in detail below in conjunction with the embodiments.

[0027] Terminology explanation:

[0028] Microsatellite: A microsatellite is a series of tandemly repeated (i.e. adjacent) DNA motifs ranging from 1 to 6 or up to 10 nucleotides in length and usually repeated 5–50 times.

[0029] Microsatellite instability: Microsatellite instability (MSI) refers to the change in microsatellite length caused by the insertion or deletion of repeat units at a certain microsatellite site in tumor tissue compared with normal tissue, resulting in the appearance of new microsatellite alleles. This phenomenon is caused by the defect of DNA mismatch repair function in tumor tissue. Microsatellite instability is an important molecular marker for the diagnosis of solid tumors such as gastric cancer and colorectal cancer in clinical practice.

[0030] NGS: Next Generation Sequencing, also known as high-throughput sequencing. Compared with the previous Sanger sequencing, it is faster and cheaper. With its high throughput, high speed and low cost, the second-generation sequencing technology provides a powerful tool for scientific research and clinical fields, helping to deepen the understanding and research of various diseases and pathogens.

[0031] Microsatellite mutation frequency: indicates the frequency of mutations in microsatellite sequences at microsatellite loci.

[0032] ROC curve: Receiver Operating Characteristic curve is a tool used to evaluate the performance of classification models. The ROC curve evaluates the performance of the model by plotting the relationship between the True Positive Rate (TPR) and the False Positive Rate (FPR).

[0033] True Positive Rate (TPR), also known as Sensitivity, indicates the proportion of samples correctly predicted as positive by the model to the total number of positive samples.

[0034] The false positive rate (FPR) indicates the proportion of negative samples that the model incorrectly predicts as positive samples; specificity is the proportion of samples correctly predicted as negative samples, which can be calculated by the false positive rate.

[0035] As mentioned in the background technology, in the detection of microsatellite instability in the prior art, it is usually necessary to perform detection based on double samples. However, the simultaneous sequencing of double samples increases the detection cost, and the control sample cannot be obtained when conducting a retrospective study. As for single sample detection, the performance of the detection method of the prior art is not mature enough, and the detection effect is poor. Therefore, in the present application, the inventor attempts to develop a new method for constructing a detection model of microsatellite instability, and uses the detection model to detect the microsatellite instability of the sample to be tested. By calculating and obtaining the microsatellite mutation frequency of the microsatellite locus in the sample to be tested, and inputting the microsatellite mutation frequency of the microsatellite locus of the sample to be tested into the detection model, the microsatellite instability detection result of the sample to be tested can be obtained, and a method for detecting the microsatellite instability state of the sample to be tested by a single sample is realized, thereby proposing a series of protection schemes of the present application.

[0036] In a first typical embodiment of the present application, a method for constructing a microsatellite instability detection model is provided. The schematic diagram of the construction process of the microsatellite instability detection model is as follows: Figure 1As shown, the construction method includes: S1) calculating and obtaining the microsatellite mutation frequencies of the microsatellite loci of all samples in the reference set sample, and merging them to obtain the reference set feature matrix; the samples in the reference set include microsatellite stable samples and microsatellite unstable samples; S2) performing machine learning on the reference set feature matrix to obtain a microsatellite instability detection model; the microsatellite instability detection model contains a reference set feature vector and a microsatellite instability judgment threshold;The microsatellite loci are selected from any one or more of the following: chr22: 29682882-29682893, chr3: 52696311-52696321, chr21: 42873556-42873563, chrX: 44949952-44949962, chr1: 161309336-161309346, chr3: 149290606-149290615, chr22: 29690901-29690911, chr14: 68944322-68944332, chr2: 212495337-2 12495347, chr12:12030237-12030252, chr9:87487519-87487529, chr6:109319968-109319978, chr17:40468976-40468987, chr3:71 008351-71008354, chr2:158637137-158637150, chr11:94212931-94212941, chr1:245977726-245977735, chr5:170818291-17081830 0. chr5:67584513-67584524, chr2:141625631-141625641, chr9:8484398-8484407, chr19:50911948-50911959, chr14:65542680-65 542691, chr17:30320861-30320871, chr21:42838094-42838103, chr17:47696765-47696774, chr2:46583273-46583282, chr2:192011 486-192011496, chr7:140421096-140421107, chr7:140489020-140489029, chr6:32790100-32790109, chr1:46597497-46597507, chr3:30691872-30691881, chrX:70608764-70608773, chr4:1919853-1919862, chr20:39702015-39702027 and chr14:68944344-68944357. ;

[0037] Microsatellite instability is one of the important markers for determining the condition of tumor patients. Among the current methods for detecting the microsatellite instability of samples to be tested, although the MSI-PCR detection method has high sensitivity and good specificity, it is too expensive and has limitations of the PCR method itself. The NGS-based MSI detection method has high accuracy and can detect multiple target sites at the same time. However, since the NGS-based detection method usually requires double sample testing to determine the microsatellite instability of the sample to be tested, the detection cost is high, and in subsequent studies, control samples can no longer be obtained. Therefore, retrospective experiments cannot be performed using this detection method. When using a single sample for testing, due to the limitations of the NGS detection method itself, the accuracy of the final test result is poor.

[0038] The detection model obtained by constructing the microsatellite instability detection model construction method of the present application can realize the detection of microsatellite instability state based on the NGS method using a single sample. The present application uses the microsatellite mutation frequency of the microsatellite loci containing microsatellite stable negative samples and microsatellite unstable positive samples to obtain a reference set feature matrix, and uses the reference set feature matrix to obtain a microsatellite instability detection model through machine learning. The microsatellite instability detection model of the present application contains a reference set feature vector and a microsatellite instability judgment threshold. In subsequent detections, the microsatellite loci mutation frequency of the sample to be tested obtained by calculation is input into the detection model constructed by the present application to obtain the microsatellite instability score of the sample to be tested, and finally the microsatellite instability score of the sample to be tested is compared with the microsatellite instability judgment threshold and the detection result is output.

[0039] In the microsatellite instability detection model of the present application, the microsatellite mutation frequency of the microsatellite locus of a single sample to be tested is detected and input into the detection model, and the microsatellite instability score of the sample is output. The microsatellite instability judgment threshold in the reference detection model can be used to judge the microsatellite instability of the sample. After testing and verification, the specificity of the microsatellite instability detection model of the present application is 100%, and the sensitivity is 95%, indicating that the detection method of the detection model constructed by the present application has high sensitivity and good specificity, and can accurately and quickly judge the microsatellite instability characteristics of the sample to be tested, and the judgment result can provide a reference for the treatment plan of tumor patients. Moreover, the detection method of the present application overcomes the limitation that the detection method based on NGS needs to rely on double samples. The detection method is simple and low-cost, and is more suitable for promotion in clinical applications.

[0040] The method for screening the above-mentioned microsatellite loci in the present application includes: 1. DNA extraction and probe capture are performed on multiple microsatellite unstable positive samples and multiple microsatellite stable negative samples, and second-generation sequencing data is performed to obtain sequencing files covering microsatellite unstable loci for all samples.

[0041] 2. Align the sequencing files of all the above samples with the human genome hg19 to obtain BAM files, use the alignment and deduplication software to remove the aligned duplicate sequences and sequences aligned to multiple positions, and generate the final BAM file for each sample; preferably, the alignment and deduplication software includes Picard software and Samtools software.

[0042] 3. Screening of microsatellite loci:

[0043] (1) Analyze the human hg19 reference genome using genome analysis software to obtain repetitive sequence sites on the reference genome, i.e., unscreened microsatellite unstable sites in the whole genome; preferably, the genome analysis software includes RepeatMasker software.

[0044] (2) filtering the unscreened microsatellite unstable sites in the whole genome using the bed files captured by hybridization in step (1), filtering out sites that are not within the scope of these bed files, and summarizing to obtain the microsatellite unstable sites filtered by the hybridization capture range;

[0045] (3) Counting the sequencing results of the microsatellite unstable sites of the above negative samples and the above positive samples:

[0046] a) Calculate the sequencing status of each sample at each microsatellite instability site filtered by the hybridization capture range, count the number of reads that are identical to the reference genome and the number of reads that are different from the reference genome at each site, and divide the number of reads that are different from the reference genome by the number of reads that are identical to the reference genome to obtain the microsatellite mutation frequency of microsatellite instability at each site;

[0047] b) using statistical methods to test and calculate, calculating each microsatellite instability site filtered by the hybridization capture range, the P value of the frequency of microsatellite instability of 20 positive samples and the frequency of microsatellite instability of 80 negative samples, the microsatellite instability site with a P value less than 0.001, i.e., the above-mentioned microsatellite site, can be used to construct a microsatellite instability monitoring model or detect the microsatellite instability state of the sample to be tested, or be prepared as a related detection product for the microsatellite instability of the sample to be tested; preferably, the statistical method includes the kruskal.test test.

[0048] In a preferred embodiment, in S2), the method for obtaining the microsatellite instability judgment threshold includes: cross-multiplying the microsatellite mutation frequency of the microsatellite loci of all samples with the reference set feature vector to obtain the microsatellite instability score of all samples; and performing machine learning on the microsatellite instability scores of all samples to obtain the microsatellite instability judgment threshold.

[0049] In a preferred embodiment, in S2), the machine learning method includes dimensionality reduction processing; preferably, the dimensionality reduction processing method includes but is not limited to one or more of PCA (Principal Component Analysis), tSNE (t-distributed Stochastic Neighbor Embedding) or UMAP (Uniform Manifold Approximation and Projection).

[0050] The purpose of dimensionality reduction is to reduce the dimension of the data while retaining important information in the data set, improve the efficiency of calculation, and avoid the problems of complex algorithms and overfitting caused by dimensions. The present application uses the method of principal component analysis to screen and retain the main features of the reference set feature matrix containing multiple sets of feature data, by extracting the first principal component in the matrix, that is, the matrix composed of all microsatellite sites of all samples (for example: there are 10 samples, a total of 8 microsatellite sites are screened out, the reference set feature matrix is ​​a 10×8 vector matrix, and the first principal component, i.e., an 8-dimensional vector, is extracted as the reference set feature vector for the final construction of the detection model. The dimensionality reduction processing method of the present application is not limited to principal component analysis, and the dimensionality reduction processing method known to those skilled in the art can be used to reduce the dimensionality of the reference set feature matrix of the present application.

[0051] The present application constructs a microsatellite instability detection model by utilizing the microsatellite mutation frequencies of microsatellite loci of microsatellite stable negative samples and microsatellite unstable positive samples in a reference set. The model is obtained through principal component analysis dimensionality reduction training based on the above-mentioned microsatellite mutation frequencies. The idea of ​​dimensionality reduction is used to process multiple groups of feature data, thereby avoiding complex calculation costs and modeling costs. The constructed detection model can realize microsatellite instability detection of a single sample with high accuracy and sensitivity and stable performance.

[0052] In a second typical embodiment of the present application, a method for detecting microsatellite instability is provided, the method comprising: S1) calculating and obtaining the microsatellite mutation frequency of one or more microsatellite loci of the sample to be tested; S2) inputting the microsatellite mutation frequency of the microsatellite loci of the sample to be tested into any of the above-mentioned microsatellite instability detection models to obtain the microsatellite instability detection result of the sample to be tested;The microsatellite loci are selected from any one or more of the following: chr22: 29682882-29682893, chr3: 52696311-52696321, chr21: 42873556-42873563, chrX: 44949952-44949962, chr1: 161309336-161309346, chr3: 149290606-149290615, chr22: 29690901-29690911, chr14: 68944322-68944332, chr2: 212495337-2 12495347, chr12:12030237-12030252, chr9:87487519-87487529, chr6:109319968-109319978, chr17:40468976-40468987, chr3:71 008351-71008354, chr2:158637137-158637150, chr11:94212931-94212941, chr1:245977726-245977735, chr5:170818291-17081830 0. chr5:67584513-67584524, chr2:141625631-141625641, chr9:8484398-8484407, chr19:50911948-50911959, chr14:65542680-65 542691, chr17:30320861-30320871, chr21:42838094-42838103, chr17:47696765-47696774, chr2:46583273-46583282, chr2:192011 486-192011496, chr7:140421096-140421107, chr7:140489020-140489029, chr6:32790100-32790109, chr1:46597497-46597507, chr3:30691872-30691881, chrX:70608764-70608773, chr4:1919853-1919862, chr20:39702015-39702027 and chr14:68944344-68944357. ;

[0053] The microsatellite instability model of the present application contains reference set features and a microsatellite instability judgment threshold. The microsatellite instability score of the sample to be tested is obtained by cross-producting the calculated microsatellite frequency of the sample to be tested with the reference set feature vector. Finally, the microsatellite instability score of the sample to be tested is compared with the microsatellite instability judgment threshold, and the detection result is output. The operation is simple and fast, and the accuracy and sensitivity are high. The detection can be performed based on a single sample, and the detection cost and algorithm cost are relatively low. In addition, the microsatellite instability state of a single sample can be detected, and the performance is stable, and the accuracy and sensitivity are high. The disadvantage of the NGS-based method in the prior art, which requires the use of double samples for detection to ensure the detection stability and the accuracy of the detection results, is avoided.

[0054] In a preferred embodiment, S2) includes: S2-1) cross-multiplying the microsatellite mutation frequency of the microsatellite locus of the sample to be tested with the characteristic vector of the reference set to obtain the microsatellite instability score of the sample to be tested; S2-2) comparing the microsatellite instability score of the sample to be tested with a microsatellite instability judgment threshold; if the microsatellite instability score of the sample to be tested is greater than the threshold, the judgment result of the sample to be tested is a microsatellite unstable sample; if the microsatellite instability score of the sample to be tested is less than the threshold, the judgment result of the sample to be tested is a microsatellite stable sample.

[0055] In a third typical embodiment of the present application, an electronic device for detecting microsatellite instability is provided. The schematic diagram of the electronic device is as follows: Figure 2As shown, the electronic device includes a microsatellite mutation frequency acquisition unit 10 for a sample to be tested and a microsatellite instability detection result acquisition unit 20 for a sample to be tested, wherein the microsatellite mutation frequency acquisition unit for a sample to be tested is used to calculate and obtain the microsatellite mutation frequency of one or more microsatellite loci of the sample to be tested; the microsatellite instability detection result acquisition unit for a sample to be tested is used to input the microsatellite mutation frequency of the microsatellite loci of the sample to be tested into any of the above-mentioned microsatellite instability detection models to obtain the microsatellite instability detection result of the sample to be tested;The microsatellite loci are selected from any one or more of the following: chr22: 29682882-29682893, chr3: 52696311-52696321, chr21: 42873556-42873563, chrX: 44949952-44949962, chr1: 161309336-161309346, chr3: 149290606-149290615, chr22: 29690901-29690911, chr14: 68944322-68944332, chr2: 212495337-2 12495347, chr12:12030237-12030252, chr9:87487519-87487529, chr6:109319968-109319978, chr17:40468976-40468987, chr3:71 008351-71008354, chr2:158637137-158637150, chr11:94212931-94212941, chr1:245977726-245977735, chr5:170818291-17081830 0. chr5:67584513-67584524, chr2:141625631-141625641, chr9:8484398-8484407, chr19:50911948-50911959, chr14:65542680-65 542691, chr17:30320861-30320871, chr21:42838094-42838103, chr17:47696765-47696774, chr2:46583273-46583282, chr2:192011 486-192011496, chr7:140421096-140421107, chr7:140489020-140489029, chr6:32790100-32790109, chr1:46597497-46597507, chr3:30691872-30691881, chrX:70608764-70608773, chr4:1919853-1919862, chr20:39702015-39702027 and chr14:68944344-68944357. ;

[0056] In a preferred embodiment, the microsatellite instability detection result acquisition unit of the sample to be tested includes a microsatellite instability score acquisition unit of the sample to be tested and a microsatellite instability result judgment unit of the sample to be tested, wherein the microsatellite instability score acquisition unit of the sample to be tested is used to cross-multiply the microsatellite mutation frequency of the microsatellite locus of the sample to be tested with the reference set feature vector to obtain the microsatellite instability score of the sample to be tested. The microsatellite instability result judgment unit of the sample to be tested is used to compare the microsatellite instability score of the sample to be tested with the microsatellite instability judgment threshold; if it is greater than the threshold, the sample to be tested is judged as a microsatellite unstable sample; if it is less than the threshold, the sample to be tested is judged as a microsatellite stable sample.

[0057] In a fourth typical embodiment of the present application, a microsatellite locus is provided for use in detecting a microsatellite instability product, wherein the microsatellite locus comprises any one or more of the following: chr22:29682882-29682893, chr3:52696311-52696321, chr21:42873556-42873563, chrX:44949952-44949962, chr1:161309336-161309346, chr3:149290606-149290615, ch r22:29690901-29690911, chr14:68944322-68944332, chr2:212495337-212495347, chr12:12030237-12030252, chr9:8748 7519-87487529, chr6:109319968-109319978, chr17:40468976-40468987, chr3:71008351-71008354, chr2:158637137-158 637150, chr11:94212931-94212941, chr1:245977726-245977735, chr5:170818291-170818300, chr5:67584513-67584524, chr2:141625631-141625641, chr9:8484398-8484407, chr19:50911948-50911959, chr14:65542680-65542691, chr17:3032 0861-30320871, chr21:42838094-42838103, chr17:47696765-47696774, chr2:46583273-46583282, chr2:192011486-1920 11496, chr7:140421096-140421107, chr7:140489020-140489029, chr6:32790100-32790109, chr1:46597497-46597507, ch r3:30691872-30691881, chrX:70608764-70608773, chr4:1919853-1919862, chr20:39702015-39702027 and chr14:68944344-68944357.

[0058] In a preferred embodiment, detecting microsatellite instability comprises detecting the microsatellite mutation frequency of a microsatellite locus; preferably, the product comprises a kit, a chip and / or an electronic detection device.

[0059] In a fifth typical embodiment of the present application, a microsatellite instability detection kit is provided, the kit comprising a detection reagent for the microsatellite mutation frequency of a microsatellite locus, the microsatellite locus comprising any one or more of the following: chr22:29682882-29682893, chr3:52696311-52696321, chr21:42873556-42873563, chrX:44949952-44 949962, chr1:161309336-161309346, chr3:149290606-149290615, chr22:29690901-29690911, c hr14:68944322-68944332, chr2:212495337-212495347, chr12:12030237-12030252, chr9:87487 519-87487529, chr6:109319968-109319978, chr17:40468976-40468987, chr3:71008351-71008 354. chr2:158637137-158637150, chr11:94212931-94212941, chr1:245977726-245977735, chr5 :170818291-170818300, chr5:67584513-67584524, chr2:141625631-141625641, chr9:8484398- 8484407, chr19:50911948-50911959, chr14:65542680-65542691, chr17:30320861-30320871, ch r21:42838094-42838103, chr17:47696765-47696774, chr2:46583273-46583282, chr2:19 2011486-192011496, chr7:140421096-140421107, chr7:140489020-140489029, chr6:327 90100-32790109, chr1:46597497-46597507, chr3:30691872-30691881, chrX:70608764-70608773, chr4:1919853-1919862, chr20:39702015-39702027 and chr14:68944344-68944357.

[0060] In a preferred embodiment, the kit includes probes and / or primers for detecting the microsatellite mutation frequency at a microsatellite locus; preferably, the DNA at the microsatellite locus is prepared into a related reagent for high-throughput sequencing.

[0061] In a sixth typical embodiment of the present application, an electronic device is provided, comprising a processor; and a memory for storing executable instructions of the processor; wherein the processor is configured to execute any one of the above-mentioned methods for detecting microsatellite instability, or any one of the above-mentioned methods for constructing a microsatellite instability detection model, by executing the executable instructions.

[0062] In a seventh typical embodiment of the present application, a computer-readable storage medium is provided, which includes a stored computer program, wherein when the computer program is running, the device where the computer-readable storage medium is located is controlled to execute any of the above-mentioned microsatellite instability detection methods, or any of the above-mentioned microsatellite instability detection model construction methods.

[0063] It should be noted that, for the above-mentioned method embodiments, for the sake of simplicity, they are all described as a series of action combinations, but those skilled in the art should know that the present invention is not limited by the order of the actions described, because according to the present invention, certain steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also know that the embodiments described in the specification are all preferred embodiments, and the actions involved are not necessarily required by the present invention.

[0064] It can be known from the description of the above implementation mode that a person skilled in the art can clearly understand that the present application can be implemented by means of software plus hardware devices such as a detection device. Based on such an understanding, the data processing part of the technical solution of the present application can be embodied in the form of a software product, and the computer software product can be stored in a storage medium such as ROM / RAM, a magnetic disk, an optical disk, etc., including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods of each embodiment of the present application or some parts of the embodiments.

[0065] The present application can be used in many general or special computing system environments or configurations, such as personal computers, server computers, handheld or portable devices, tablet devices, multiprocessor systems, microprocessor-based systems, set-top boxes, programmable consumer electronic devices, network PCs, minicomputers, mainframe computers, and distributed computing environments including any of the above systems or devices.

[0066] The method provided in this application can be executed in a terminal, a computer terminal or a similar computing device. Taking running on a terminal as an example, Figure 31 is a hardware structure block diagram of a microsatellite instability detection method and a microsatellite instability detection model according to an embodiment of the present invention. Figure 3 As shown, the terminal may include one or more ( Figure 3 Only one is shown in the figure) processor A1 (processor A1 may include but is not limited to a processing device such as a microprocessor MCU or a programmable logic device FPGA) and a memory B1 for storing data. Optionally, the terminal may also include a transmission device C1 and an input and output device D1 for communication functions. It can be understood by those skilled in the art that Figure 3 The structure shown is for illustration only and does not limit the structure of the above terminal. Figure 3 More or fewer components as shown, or with Figure 3 Different configurations shown.

[0067] The memory B1 can be used to store computer programs, for example, software programs and modules of application software, such as computer programs corresponding to methods such as read segment splicing, clustering, and consistency processing in the embodiments of the present invention. The processor A1 executes various functional applications and data processing by running the computer programs stored in the memory B1, that is, implementing the above method. The memory B1 may include a high-speed random access memory, and may also include a non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some instances, the memory B1 may further include a memory remotely arranged relative to the processor A1, and these remote memories may be connected to the terminal via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0068] The transmission device C1 is used to receive or send data via a network. The specific example of the above network may include a wireless network provided by a communication provider of the terminal. In one example, the transmission device C1 includes a network adapter (Network Interface Controller, referred to as NIC), which can be connected to other network devices through a base station so as to communicate with the Internet. In one example, the transmission device C1 can be a radio frequency (Radio Frequency, referred to as RF) module, which is used to communicate with the Internet wirelessly.

[0069] Obviously, those skilled in the art should understand that some modules or steps of the present application described above can be implemented in a general computing device, they can be concentrated on a single computing device, or distributed on a network composed of multiple computing devices, and optionally, they can be implemented with program codes executable by the computing device, so that they can be stored in a storage device and executed by the computing device, or they can be made into individual integrated circuit modules, or multiple modules or steps therein can be made into a single integrated circuit module for implementation. Thus, the present application is not limited to any specific combination of hardware and software.

[0070] The beneficial effects of the present application will be further explained in detail below in conjunction with specific embodiments.

[0071] Example 1

[0072] Screening of microsatellite loci:

[0073] 1. Perform DNA extraction, probe capture and next-generation sequencing on the samples to obtain sequencing files covering microsatellite unstable sites for all samples.

[0074] The above samples are single products of Beijing Youxun Colorectal Cancer, which include 20 positive samples verified as microsatellite instability by MSI-PCR, and 80 negative samples verified as microsatellite stability by MSI-PCR.

[0075] 2. Align the sequencing files of all the above samples with the human genome hg19 to obtain the BAM file of each sample. Use Picard software and Samtools software to remove the duplicate sequences and sequences aligned to multiple positions to generate the final BAM file of each sample.

[0076] 3. Screening of microsatellite loci for detection:

[0077] (1) RepeatMasker software was used to analyze the human hg19 reference genome to obtain the repetitive sequence sites on the reference genome, i.e., the unscreened microsatellite unstable sites in the whole genome;

[0078] (2) filtering the unscreened microsatellite unstable sites in the whole genome range with the bed files obtained after hybridization capture of all samples in step 1, filtering out the microsatellite sites that are not in these bed files, and obtaining the microsatellite unstable sites filtered by the hybridization capture range;

[0079] (3) Statistics of sequencing of microsatellite instability sites in negative and positive samples:

[0080] a) Calculate the sequencing status of each sample at each microsatellite instability site filtered by the hybridization capture range, count the number of reads that are identical to the reference genome and the number of reads that are different from the reference genome at each site, and divide the number of reads that are different from the reference genome by the number of reads that are identical to the reference genome to obtain the frequency of microsatellite instability at each site.

[0081] b) Using the kruskal.test test, the P value of the frequency of microsatellite instability of 20 positive sites and the frequency of microsatellite instability of 80 negative samples for each microsatellite unstable site filtered by the hybridization capture range was calculated. There were 37 microsatellite unstable sites with a P value less than 0.001, namely microsatellite sites.

[0082] c) The microsatellite loci obtained by screening are: chr22:29682882-29682893, chr3:52696311-52696321, chr21:42873556-42873563, chrX:44949952-44949962, chr1:161309336-161309346, chr3:149290606-149290615, chr22:29690901-29690911, chr14:68944322-68944332, chr2:212495337-212 495347, chr12:12030237-12030252, chr9:87487519-87487529, chr6:109319968-109319978, chr17:40468976-40468987, chr3:7100 8351-71008354, chr2:158637137-158637150, chr11:94212931-94212941, chr1:245977726-245977735, chr5:170818291-170818300 , chr5:67584513-67584524, chr2:141625631-141625641, chr9:8484398-8484407, chr19:50911948-50911959, chr14:65542680-655 42691, chr17:30320861-30320871, chr21:42838094-42838103, chr17:47696765-47696774, chr2:46583273-46583282, chr2:192011 486-192011496, chr7:140421096-140421107, chr7:140489020-140489029, chr6:32790100-32790109, chr1:46597497-46597507, chr3:30691872-30691881, chrX:70608764-70608773, chr4:1919853-1919862, chr20:39702015-39702027 and chr14:68944344-68944357.

[0083] Example 2

[0084] Construction of detection model:

[0085] The detection model was constructed using reference set samples, which included 20 positive samples verified as microsatellite instability by MSI-PCR and 80 negative samples verified as microsatellite stability by MSI-PCR. They are individual products of Beijing Youxun Colorectal Cancer.

[0086] 1. Calculate and obtain the microsatellite mutation frequency of each of the above microsatellite loci for all samples in the reference set, arrange the microsatellite mutation frequencies of all microsatellite loci from large to small, and obtain the characteristic vector of microsatellite instability for each sample. Obtain the characteristic vector of microsatellite instability that constitutes each sample.

[0087] 2. The characteristic vectors of microsatellite instability of all samples in the reference set are used to form a 37×100 digital matrix, and principal component analysis training is performed to extract the first principal component vector, which is the characteristic vector of the reference set.

[0088] 3. Obtaining the threshold for determining microsatellite instability

[0089] (1) Perform a vector cross multiplication of the microsatellite instability feature vector of each sample in the reference set with the reference set feature vector to obtain the microsatellite instability score of each sample;

[0090] (2) The ROC curve is constructed by combining the microsatellite instability scores of negative samples and the microsatellite instability scores of positive samples. The schematic diagram of the ROC curve is shown in Figure 4 As shown, AUC: 0.973 means: the area under the ROC curve is 0.973, and the AUC value is an indicator to measure the goodness of fit. The closer it is to 1, the better the model fit is. From the ROC curve, the threshold for judging microsatellite instability is 0.077, with a specificity of 100% and a sensitivity of 95%.

[0091] Comparative Example 1

[0092] The above 100 reference set samples were tested simultaneously using MSIseq and MSIpred. The default parameters of these two software for detecting microsatellite instability were selected as the detection parameters. The above 37 microsatellite loci were also used for detection. The final results were statistically analyzed and ROC curves were constructed respectively.

[0093] Among them, the sensitivity and specificity of the ROC curve of the MSIseq detection result were 90% and 96.3%, respectively, and the sensitivity and specificity of the ROC curve of the MSIpred detection result were 90% and 98.8%, respectively, both lower than the detection method of the present application.

[0094] Example 3

[0095] Three endometrial cancer-control samples, all of which were microsatellite unstable samples, were used for microsatellite instability testing;

[0096] The three pairs of paired samples were tested using the microsatellite instability detection software MSIseq and MSIpred, and the test results showed that one sample was a microsatellite unstable sample and two were microsatellite stable samples;

[0097] The detection method of the present application was used to perform microsatellite instability detection on the three tumor single samples, and the detection results were consistent with the results of the paired samples.

[0098] From the above description, it can be seen that the above-mentioned embodiments of the present invention achieve the following technical effects: the present application uses the idea of ​​dimensionality reduction through principal component analysis, and utilizes the microsatellite mutation frequencies of 37 microsatellite loci screened out from microsatellite stable negative samples and microsatellite unstable positive samples to construct a microsatellite instability detection model of the present application. When using this detection model to detect the microsatellite instability state of the sample to be tested, the accuracy and sensitivity are high, the specificity in the ROC curve reaches 100%, and the sensitivity reaches 95%. Compared with the methods of the prior art, the modeling cost, calculation cost and detection cost are low, and the detection can be based on a single sample, with stable performance, which is more suitable for promotion in clinical practice.

[0099] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. For those skilled in the art, the present invention may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A method for constructing a microsatellite instability detection model, characterized in that: The construction method comprises: S1) calculating and obtaining the microsatellite mutation frequencies of the microsatellite loci of all samples in the reference set sample, and merging them to obtain the reference set feature matrix; The samples in the reference set include microsatellite stable samples and microsatellite unstable samples; S2) performing machine learning on the reference set feature matrix to obtain the microsatellite instability detection model; The microsatellite instability detection model contains a reference set feature vector and a microsatellite instability judgment threshold; The microsatellite loci are selected from any one or more of the following: chr22: 29682882-29682893, chr3: 52696311-52696321, chr21: 42873556-42873563, chrX: 44949952-44949962, chr1: 161309336-161309346, chr3 :149290606-149290615, chr22:29690901-29690911, chr14:68944322-68944332, ch r2:212495337-212495347, chr12:12030237-12030252, chr9:87487519-87487529, c hr6:109319968-109319978, chr17:40468976-40468987, chr3:71008351-71008354, chr2:1 58637137-158637150, chr11:94212931-94212941, chr1:245977726-245977735, chr5:1708 18291-170818300, chr5:67584513-67584524, chr2:141625631-141625641, chr9:8484398- 8484407, chr19:50911948-50911959, chr14:65542680-65542691, chr17:30320861-3032087 1. chr21:42838094-42838103, chr17:47696765-47696774, chr2:46583273-46583282, chr2 :192011486-192011496, chr7:140421096-140421107, chr7:140489020-140489029, chr6:3 2790100-32790109, chr1:46597497-46597507, chr3:30691872-30691881, chrX:70608764-70608773, chr4:1919853-1919862, chr20:39702015-39702027 and chr14:68944344-68944357.

2. The construction method according to claim 1, characterized in that: In S2), the method for obtaining the microsatellite instability judgment threshold comprises: cross-multiplying the microsatellite mutation frequency of the microsatellite loci of all the samples with the reference set feature vector to obtain the microsatellite instability score of all the samples; The microsatellite instability scores of all the samples are subjected to machine learning to obtain the microsatellite instability judgment threshold.

3. The construction method according to claim 1, characterized in that: In said S2), said machine learning method includes dimensionality reduction processing; Preferably, the dimensionality reduction processing method includes one or more of PCA, tSNE or UMAP.

4. A method for detecting microsatellite instability, characterized in that: The detection method comprises: S1) calculating and obtaining the microsatellite mutation frequency of one or more microsatellite loci of the sample to be tested; S2) inputting the microsatellite mutation frequency of the microsatellite locus of the sample to be tested into the microsatellite instability detection model constructed by the method for constructing a microsatellite instability detection model according to any one of claims 1 to 3 to obtain the microsatellite instability detection result of the sample to be tested; The microsatellite loci are selected from any one or more of the following: chr22: 29682882-29682893, chr3: 52696311-52696321, chr21: 42873556-42873563, chrX: 44949952-44949962, chr1: 161309336-161309346, chr3 :149290606-149290615, chr22:29690901-29690911, chr14:68944322-68944332, ch r2:212495337-212495347, chr12:12030237-12030252, chr9:87487519-87487529, c hr6:109319968-109319978, chr17:40468976-40468987, chr3:71008351-71008354, chr2:1 58637137-158637150, chr11:94212931-94212941, chr1:245977726-245977735, chr5:1708 18291-170818300, chr5:67584513-67584524, chr2:141625631-141625641, chr9:8484398- 8484407, chr19:50911948-50911959, chr14:65542680-65542691, chr17:30320861-3032087 1. chr21:42838094-42838103, chr17:47696765-47696774, chr2:46583273-46583282, chr2 :192011486-192011496, chr7:140421096-140421107, chr7:140489020-140489029, chr6:3 2790100-32790109, chr1:46597497-46597507, chr3:30691872-30691881, chrX:70608764-70608773, chr4:1919853-1919862, chr20:39702015-39702027 and chr14:68944344-68944357.

5. The detection method according to claim 4, characterized in that: The S2) includes: S2-1) cross-multiplying the microsatellite mutation frequency of the microsatellite locus of the sample to be tested with the reference set feature vector to obtain the microsatellite instability score of the sample to be tested; S2-2) comparing the microsatellite instability score of the sample to be tested with the microsatellite instability judgment threshold; The microsatellite instability score of the sample to be tested is greater than a threshold value, and the sample to be tested is a microsatellite unstable sample; The microsatellite instability score of the sample to be tested is less than a threshold value, and the sample to be tested is a microsatellite stable sample.

6. An electronic device for detecting microsatellite instability, characterized in that: The electronic device comprises a unit for acquiring the microsatellite mutation frequency of a sample to be tested and a unit for acquiring the microsatellite instability detection result of the sample to be tested, wherein: A microsatellite mutation frequency acquisition unit for the sample to be tested, used to calculate and obtain the microsatellite mutation frequency of one or more microsatellite loci of the sample to be tested; A microsatellite instability detection result acquisition unit for a sample to be tested, used for inputting the microsatellite mutation frequency of the microsatellite locus of the sample to be tested into the microsatellite instability detection model constructed by the method for constructing a microsatellite instability detection model according to any one of claims 1 to 3, to obtain the microsatellite instability detection result of the sample to be tested; The microsatellite loci are selected from any one or more of the following: chr22: 29682882-29682893, chr3: 52696311-52696321, chr21: 42873556-42873563, chrX: 44949952-44949962, chr1: 161309336-161309346, chr3 :149290606-149290615, chr22:29690901-29690911, chr14:68944322-68944332, ch r2:212495337-212495347, chr12:12030237-12030252, chr9:87487519-87487529, c hr6:109319968-109319978, chr17:40468976-40468987, chr3:71008351-71008354, chr2:158637137-158637150, chr11:94212931-94212 941, chr1:245977726-245977735, chr5:170818291-170818300, chr5:67584513-67584524, chr2:141625631-141625641, chr9:8484398-8 484407, chr19:50911948-50911959, chr14:65542680-65542691, chr17:30320861-30320871, chr21:42838094-42 838103, chr17:47696765-47696774, chr2:46583273-46583282, chr2:192011486-192011496, chr7:140421096-140 421107, chr7:140489020-140489029, chr6:32790100-32790109, chr1:46597497-46597507, chr3:30691872-30691881, chrX:70608764-70608773, chr4:1919853-1919862, chr20:39702015-39702027 and chr14:68944344-68944357.

7. The electronic device according to claim 6, characterized in that: The microsatellite instability detection result acquisition unit of the sample to be tested includes a microsatellite instability score acquisition unit of the sample to be tested and a microsatellite instability result judgment unit of the sample to be tested, wherein: The microsatellite instability score acquisition unit of the sample to be tested is used to cross-multiply the microsatellite mutation frequency of the microsatellite locus of the sample to be tested with the reference set feature vector to obtain the microsatellite instability score of the sample to be tested; The microsatellite instability result judgment unit of the sample to be tested is used to compare the microsatellite instability score of the sample to be tested with the microsatellite instability judgment threshold; If the value is greater than the threshold, the sample to be tested is judged to be a microsatellite unstable sample; If the value is less than the threshold, the sample to be tested is judged to be a microsatellite stable sample.

8. The use of microsatellite loci in detecting microsatellite instability products, characterized in that: The microsatellite loci include any one or more of the following: chr22:29682882-29682893, chr3:52696311-52696321, chr21:42873556-42873563, chrX:44949952-44949962, chr1:161309336-161309346, chr3:149290606-149290615, chr22:29690901-29690911, chr14:68944322-68944332, ch r2:212495337-212495347, chr12:12030237-12030252, chr9:87487519-87487529, chr6:109319968-109319978, chr17:404689 76-40468987、chr3:71008351-71008354、chr2:158637137-158637150、chr11:94212931-94212941、chr1:245977726-24597773 5. chr5:170818291-170818300, chr5:67584513-67584524, chr2:141625631-141625641, chr9:8484398-8484407, chr19:50911 948-50911959, chr14:65542680-65542691, chr17:30320861-30320871, chr21:42838094-42838103, chr17:47696765-4769677 4. chr2:46583273-46583282, chr2:192011486-192011496, chr7:140421096-140421107, chr7:140489020-140489029, chr6:32 790100-32790109, chr1:46597497-46597507, chr3:30691872-30691881, chrX:70608764-70608773, chr4:1919853-1919862, c hr20:39702015-39702027 and chr14:68944344-68944357.

9. The use according to claim 8, characterized in that: The detecting of microsatellite instability comprises detecting the microsatellite mutation frequency of the microsatellite locus; Preferably, the product comprises a kit, a chip and / or an electronic detection device.

10. A kit for detecting microsatellite instability, characterized in that: The kit comprises a detection reagent for the microsatellite mutation frequency of a microsatellite locus, wherein the microsatellite locus comprises any one or more of the following: chr22:29682882-29682893, chr3:52696311-52696321, chr21:42873556-42873563, chrX:44949952-44949962, chr 1:161309336-161309346, chr3:149290606-149290615, chr22:29690901-29690911, chr14:68944322-68944332, chr 2:212495337-212495347, chr12:12030237-12030252, chr9:87487519-87487529, chr6:109319968-109319978, chr1 7:40468976-40468987, chr3:71008351-71008354, chr2:158637137-158637150, chr11:94212931-94212941, chr1:2 45977726-245977735, chr5:170818291-170818300, chr5:67584513-67584524, chr2:141625631-141625641, chr9:84 84398-8484407, chr19:50911948-50911959, chr14:65542680-65542691, chr17:30320861-30320871, chr21:428380 94-42838103, chr17:47696765-47696774, chr2:46583273-46583282, chr2:192011486-192011496, chr7:140421096 -140421107, chr7:140489020-140489029, chr6:32790100-32790109, chr1:46597497-46597507, chr3:30691872-30691881, chrX:70608764-70608773, chr4:1919853-1919862, chr20:39702015-39702027 and chr14:68944344-68944357.

11. The kit according to claim 10, characterized in that The kit includes probes and / or primers for detecting the microsatellite mutation frequency of the microsatellite locus; Preferably, the DNA at the microsatellite locus is prepared into relevant reagents for high-throughput sequencing.

12. An electronic device, characterized in that: The electronic device comprises: Processor; and A memory, configured to store executable instructions of the processor; The processor is configured to execute the method for constructing a microsatellite instability detection model according to any one of claims 1 to 3, or the method for detecting microsatellite instability according to claim 4 or 5, by executing the executable instructions.

13. A computer-readable storage medium, characterized in that: The computer-readable storage medium includes a stored computer program, wherein when the computer program is running, the device where the computer-readable storage medium is located is controlled to execute the method for constructing a microsatellite instability detection model according to any one of claims 1 to 3, or the method for detecting microsatellite instability according to claim 4 or 5.

Citation Information

Patent Citations

  • Microsatellite instability detection site screening method based on single tumor sample high-throughput sequencing

    CN110910957A

Cited By

  • Microsatellite instability detection method and device based on ctDNA and computer storage medium

    CN121528298A

  • A method, apparatus, and computer storage medium for detecting microsatellite instability based on ctDNA.

    CN121528298B