A dynamic mutation detection method and related apparatus

Abstract

This application discloses a dynamic mutation detection method and related apparatus, relating to the field of bioinformatics. The method includes: preprocessing raw WES sequencing data to obtain preprocessed data; constructing a dynamic mutation annotation database based on information on common known pathogenic dynamic mutations; performing dynamic mutation analysis and feature extraction in parallel using several core detection tools based on the preprocessed data and the dynamic mutation annotation database to obtain a feature matrix; calculating the pathogenicity probability using a logistic regression algorithm fusion model based on the feature matrix; and calculating a pathogenicity score using a logistic function based on the pathogenicity probability. This application can achieve highly accurate and robust dynamic mutation detection on WES data.

Description

Technical Field

[0001] This application relates to the field of bioinformatics, and in particular to a dynamic mutation detection method and related apparatus. Background Technology

[0002] Dynamic mutations, primarily caused by the abnormal expansion of highly polymorphic repeat sequences (STRs) of short (1-6 base pairs) motifs, account for approximately 3-5% of the human genome and are the cause of many neurodegenerative diseases. More than one million STR sites are known, and expansion at at least 60 sites can lead to serious genetic disorders such as Fragile X syndrome, ankylosing dystrophy, ataxia, and Huntington's disease.

[0003] Currently, the gold standard for clinical detection of dynamic mutations is based on capillary electrophoresis fragment analysis and third-generation sequencing. Although these methods are accurate, they have obvious limitations: (1) low throughput, only one or a few sites can be detected in a single experiment; or (2) high cost and long cycle; or (3) reliance on prior knowledge, making it impossible to discover new pathogenic expansion sites.

[0004] Whole-exome sequencing (WES) has become a first-line tool for the diagnosis of genetic diseases, but its standard bioinformatics analysis workflow is designed for single nucleotide variants (SNVs) and small insertions / deletions (Indels), and cannot effectively handle the detection of dynamic mutations. Directly using WES data to detect dynamic mutations faces three major challenges: 1) Alignment difficulties, as long repetitive sequences lead to alignment errors or information loss in sequencing reads; 2) Technical biases, as the capture and amplification process of WES has technical biases for high GC content and long repetitive sequences; 3) Limited algorithm availability, as existing dynamic mutation detection tools for WES (such as ExpansionHunter and exSTRa) are based on different algorithm principles, each with its own emphasis on detection sensitivity and specificity, resulting in both false positives and false negatives, and lacking a unified, highly reliable judgment standard.

[0005] Therefore, there is an urgent need in this field for a new method that can integrate the advantages of existing tools, overcome the limitations of single tools, and thus achieve high accuracy and robust dynamic mutation detection on WES data. Summary of the Invention

[0006] The purpose of this application is to provide a dynamic mutation detection method and related apparatus that can achieve highly accurate and robust dynamic mutation detection on WES data.

[0007] To achieve the above objectives, this application provides the following solution.

[0008] In a first aspect, this application provides a dynamic mutation detection method, which includes the following steps.

[0009] The raw WES sequencing data were preprocessed to obtain the preprocessed data.

[0010] A dynamic mutation annotation database is constructed based on information on common known pathogenic dynamic mutations.

[0011] Based on the preprocessed data and the dynamic mutation annotation database, several core detection tools are used in parallel to perform dynamic mutation analysis and feature extraction to obtain a feature matrix.

[0012] Based on the aforementioned feature matrix, a logistic regression algorithm is used to fuse the model and calculate the pathogenicity probability.

[0013] Based on the pathogenicity probability, a pathogenicity score is calculated using the logistic function.

[0014] Optionally, the dynamic mutation annotation database includes: dynamic mutation gene name, disease name, repetitive sequence, normal repetition range, and minimum pathogenic repetition count.

[0015] Optionally, the core detection tools include: ExpansionHunter, exSTRa, REViewer, Bamdst, and STRetch.

[0016] Optionally, the formula for calculating the pathogenicity probability is as follows.

[0017] .

[0018] in, Probability of causing disease; For bias terms; The longest allele repeat; It is the characteristic transformation function; The p-value is the statistical test value for anomalous amplification at the locus. Standard scores for aberrant amplification of loci; This is the ratio relative to the average depth of the control sample set; This is a Boolean feature indicating whether local assembly supports extension. Score the reliability of the assembly results; The intensity fraction of the amplified signal; The first regression coefficient; The second regression coefficient; The third regression coefficient; The fourth regression coefficient; This is the fifth regression coefficient; The sixth regression coefficient; This is the seventh regression coefficient.

[0019] Optionally, the pathogenicity score is calculated using the following formula.

[0020] .

[0021] in, For pathogenicity score; This represents the probability of causing disease.

[0022] Optionally, the dynamic mutation detection method further includes: determining whether the pathogenicity score exceeds a decision threshold, and obtaining a determination result.

[0023] If the judgment result is negative, then it is negative.

[0024] If the judgment result is yes, then it is positive.

[0025] Secondly, this application provides a dynamic mutation detection system for implementing the dynamic mutation detection method described in any one of the first aspects, the dynamic mutation detection system comprising the following modules.

[0026] The preprocessing module is used to preprocess the raw WES sequencing data to obtain preprocessed data.

[0027] The Dynamic Mutation Annotation Database Construction Module is used to construct a dynamic mutation annotation database based on information on common known pathogenic dynamic mutations.

[0028] The dynamic mutation analysis and feature extraction module is used to perform dynamic mutation analysis and feature extraction in parallel using several core detection tools based on the preprocessed data and the dynamic mutation annotation database, to obtain a feature matrix.

[0029] The pathogenicity probability calculation module is used to calculate the pathogenicity probability based on the feature matrix and by using a logistic regression algorithm to fuse the model.

[0030] The pathogenicity score calculation module is used to calculate the pathogenicity score based on the pathogenicity probability using a logistic function.

[0031] Thirdly, this application provides a computer device, including: a memory, a processor, and a computer program stored in the memory and capable of running on the processor, wherein the processor executes the computer program to implement the dynamic mutation detection method described in any one of the first aspects.

[0032] Fourthly, this application provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the dynamic mutation detection method described in any one of the first aspects.

[0033] Fifthly, this application provides a computer program product, including a computer program that, when executed by a processor, implements the dynamic mutation detection method described in any one of the first aspects.

[0034] Based on the specific embodiments provided in this application, the following technical effects are disclosed.

[0035] This application provides a dynamic mutation detection method and related apparatus. The method includes: preprocessing raw WES sequencing data to obtain preprocessed data; this removes data noise and corrects sequencing errors, providing a high-quality and reliable data foundation for subsequent detection and analysis. A dynamic mutation annotation database is constructed based on information on common known pathogenic dynamic mutations; this provides accurate reference and reduces the risk of missed and false detections during the detection process. Based on the preprocessed data and the dynamic mutation annotation database, several core detection tools are used in parallel to perform dynamic mutation analysis and feature extraction to obtain a feature matrix; this comprehensively mines mutation features in the data, improves the completeness of feature extraction and detection efficiency, and provides rich and effective feature support for subsequent modeling. Based on the feature matrix, a logistic regression algorithm is used to fuse the model to calculate the pathogenicity probability; this achieves accurate integration of multi-dimensional features, improving the accuracy and stability of pathogenicity probability assessment. Based on the pathogenicity probability, a pathogenicity score is calculated using a logistic function; this transforms the abstract pathogenicity probability into an intuitive and quantifiable score result, facilitating clinical interpretation and practical application. This application, through a standardized process design, with each step from data preprocessing to final pathogenicity scoring working in a progressive and synergistic manner, effectively improves the accuracy, efficiency, and practicality of dynamic mutation detection, providing reliable technical support for the screening and diagnosis of clinically pathogenic dynamic mutations. Attached Figure Description

[0036] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0037] Figure 1 This is a diagram illustrating the application environment of a dynamic mutation detection method according to an embodiment of this application.

[0038] Figure 2 This is a flowchart illustrating a dynamic mutation detection method provided in an embodiment of this application.

[0039] Figure 3 This is a structural block diagram of a dynamic mutation detection method provided in an embodiment of this application.

[0040] Figure 4 This is a schematic diagram of the functional modules of a dynamic mutation detection system provided in an embodiment of this application.

[0041] Figure 5 This is a schematic diagram of the structure of a computer device provided in an embodiment of this application. Detailed Implementation

[0042] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0043] The purpose of this invention is to overcome the technical limitations of existing WES data in detecting dynamic mutations and to provide a dynamic mutation detection method and related apparatus. This method integrates multiple detection tools in parallel and fuses their results using a machine learning model, aiming to significantly improve the accuracy and robustness of detection, thereby achieving efficient utilization of WES data and enhancing the detection efficiency of dynamic mutation screening.

[0044] To make the above-mentioned objectives, features and advantages of this application more apparent and understandable, the application will be further described in detail below with reference to the accompanying drawings and specific embodiments.

[0045] The dynamic mutation detection method provided in this application can be applied to, for example... Figure 1In the application environment shown, terminal 102 communicates with server 104 via a network. A data storage system can store the data that server 104 needs to process. The data storage system can be set up independently, integrated into server 104, or placed in the cloud or on another server. Terminal 102 can send raw WES sequencing data to server 104. After receiving the raw WES sequencing data, server 104 preprocesses the raw WES sequencing data to obtain preprocessed data; based on common known pathogenic dynamic mutation information, a dynamic mutation annotation database is constructed; based on the preprocessed data and the dynamic mutation annotation database, several core detection tools are used in parallel to perform dynamic mutation analysis and feature extraction to obtain a feature matrix; based on the feature matrix, a logistic regression algorithm is used to calculate the pathogenicity probability using a fusion model; based on the pathogenicity probability, a pathogenicity score is calculated using a logistic function. Server 104 can feed back the obtained pathogenicity score to terminal 102. In addition, in some embodiments, the dynamic mutation detection method can also be implemented by the server 104 or the terminal 102 alone. For example, the terminal 102 can directly perform dynamic mutation detection on the raw WES sequencing data, or the server 104 can obtain the raw WES sequencing data from the data storage system and perform dynamic mutation detection on the raw WES sequencing data.

[0046] The terminal 102 can be, but is not limited to, various desktop computers, laptops, smartphones, and tablets. The server 104 can be implemented using a standalone server or a server cluster consisting of multiple servers, or it can be a cloud server.

[0047] In one exemplary embodiment, such as Figure 2 and Figure 3 As shown, a dynamic mutation detection method is provided. This method is executed by a computer device, specifically by a terminal or server alone, or by both a terminal and a server. In this embodiment, the method is applied to... Figure 1 Taking server 104 as an example, the following steps are included.

[0048] S1: Preprocess the raw WES sequencing data to obtain preprocessed data.

[0049] S2: Construct a dynamic mutation annotation database based on common known pathogenic dynamic mutation information.

[0050] S3: Based on the preprocessed data and the dynamic mutation annotation database, several core detection tools are used in parallel to perform dynamic mutation analysis and feature extraction to obtain a feature matrix.

[0051] S4: Based on the aforementioned feature matrix, the probability of pathogenicity is calculated using a logistic regression algorithm to fuse the model.

[0052] S5: Based on the pathogenicity probability, the pathogenicity score is calculated using the logistic function.

[0053] Implementing steps S1 to S5 above can integrate the advantages of existing tools and overcome the limitations of single tools, thereby achieving highly accurate and robust dynamic mutation detection on WES data.

[0054] As an optional implementation, the dynamic mutation annotation database includes: dynamic mutation gene name, disease name, repetitive sequence, normal repetition number range, and pathogenic minimum repetition number.

[0055] As an optional implementation, the core detection tools include: ExpansionHunter, exSTRa, REViewer, Bamdst, and STRetch.

[0056] As an optional implementation, the dynamic mutation detection method further includes: determining whether the pathogenicity score exceeds a decision threshold, and obtaining a determination result.

[0057] If the judgment result is negative, then it is negative.

[0058] If the judgment result is yes, then it is positive.

[0059] The core idea of ​​this application is to run multiple dynamic mutation detection tools based on different principles in parallel, extract multidimensional features from the output of each tool, construct a comprehensive feature matrix, and then use a trained machine learning fusion model to analyze the matrix, ultimately outputting a comprehensive and quantitative pathogenicity probability score. The overall process is shown below.

[0060] 1. Data preprocessing.

[0061] This method takes raw WES sequencing files as input, and its standard preprocessing workflow includes: data filtering, alignment to a reference genome (GRch37), and generation of sorted BAM / CRAM files and their index files. It is important to note that strict PCR repeat labeling and removal are not performed at this stage. This is because, in dynamic mutation detection, preserving PCR repeat sequences is crucial for accurately assessing the extent of allele amplification.

[0062] 2. Construct a specialized database.

[0063] By integrating multiple authoritative data resources, a systematic collection of known pathogenic dynamic mutation sites was conducted, constructing a dynamic mutation annotation database. Data sources primarily include population genome databases such as STRPY (https: / / stripy.org / database), GnomAD Tandem Repeats (https: / / gnomad.broadinstitute.org / short-tandem-repeats), and STRchive (https: / / strchive.org / loci / ), as well as clinical variant databases such as Clinvar (https: / / www.ncbi.nlm.nih.gov / clinvar / ), HGMD (https: / / www.hgmd.cf.ac.uk / ac / index.php), and relevant literature. For each site, the following table summarizes information such as the name of the dynamically mutated gene, the repeat sequence, the normal repeat count range, the minimum pathogenic repeat count, and the disease name. A summary of annotation information for known pathogenic dynamic mutation sites is shown in Table 1.

[0064] Table 1 Summary of Annotation Information for Known Pathogenic Dynamic Mutation Sites

[0065] 3. Parallel analysis and feature extraction.

[0066] Based on preprocessed data and a specialized database, multiple core detection tools are invoked in parallel for dynamic mutation analysis and feature extraction, generating an integrated feature matrix. For each sample, the following core detection tools are invoked in parallel for analysis based on a list of known pathogenic dynamic mutation sites.

[0067] a.ExpansionHunter (EH): Based on alignment patterns such as splitting, anchoring, and crossing of reads in regions near known pathogenic dynamic mutations, it infers the length of repetitive sequences through realignment.

[0068] b.exSTRa(EX): Based on the principle of statistical outlier detection, it calculates the significant difference between the sequencing depth of the target sample in the region near a specific dynamic mutation and the distribution of the control sample set (such as gnomAD), and outputs the statistical significance.

[0069] c. REViewer (EH companion tool, R): Performs local de novo assembly of high-confidence candidate regions nominated by tools such as ExpansionHunter, generating a visual repeat sequence map, providing intuitive assembly evidence to support expansion.

[0070] d.Bamdst: A statistical tool for the depth coverage of NGS sequencing reads in the target region.

[0071] e.STRetch (ST): Detects large-scale repetitive expansions at known and unknown genomic locations by aligning reads to an expanded reference genome containing all possible repetitive sequences.

[0072] For each sample-dynamic mutation site pair, features are extracted from the output of the above tools to construct a multidimensional feature vector. Feature vectors from five software programs were extracted to construct a feature matrix. The multidimensional feature vectors are illustrated in Table 2.

[0073] Table 2 Explanation of Multidimensional Feature Vectors

[0074] 4. The linear logistic regression algorithm is used to fuse the model to calculate the probability of disease.

[0075] The fusion model assigns a weight to each feature and calculates the probability of pathogenicity by combining the results.

[0076] .

[0077] in, Probability of causing disease; For the bias term (intercept); The longest allele repeat; Statistical test for aberrant amplification of loci p value; Standard scores for aberrant amplification of loci; This is the ratio relative to the average depth of the control sample set; This is a Boolean feature indicating whether local assembly supports extension. Score the reliability of the assembly results; The intensity fraction of the amplified signal; The first regression coefficient; The second regression coefficient; The third regression coefficient; The fourth regression coefficient; This is the fifth regression coefficient; The sixth regression coefficient; The seventh regression coefficient; These are regression coefficients, which are the weights of each feature learned by the model, representing the contribution of that feature to the pathogenicity assessment. This is a feature transformation function used for processing. PThe power-law distribution of the values ​​is the recommended transformation. One of these is a minimum value (set to 1E-12), primarily to prevent overflow in numerical calculations. Changing the value will reduce the minimum. P The value is converted to a larger positive value so that it is positively correlated with pathogenicity.

[0078] 5. Output pathogenicity score.

[0079] The pathogenicity probability obtained in step 4 By mapping the sigmoid function to the range [0, 1], a pathogenicity score is obtained to determine whether the pathogenicity is positive or negative.

[0080] The expression for the logistic function is shown below.

[0081] .

[0082] in, For pathogenicity score; This represents the probability of causing disease.

[0083] Final output This is a value between 0 and 1, representing the overall probability score of pathogenic spread of the sample at that site. Users can set a decision threshold (e.g., 0.75) based on the sample's test results, at which point it is considered positive.

[0084] Real-world application case: Subject A underwent WES sequencing to obtain raw WES sequencing data. This raw data underwent filtering, alignment to a reference genome, and sequence sorting to obtain a preprocessed sequence file. This file was then input into a pre-built fusion model for risk prediction. The pathogenicity score for the HTT gene CAG duplication was 0.8, and the pathogenicity score for the ATN1 gene CAG duplication was 0.45. Based on the preset pathogenicity score thresholds, this subject was considered positive for pathogenicity of the HTT gene CAG duplication and negative for pathogenicity of the ATN1 gene CAG duplication.

[0085] Based on the same inventive concept, this application also provides a dynamic mutation detection system for implementing the dynamic mutation detection method described above. The solution provided by this system is similar to the implementation described in the above method; therefore, the specific limitations in one or more embodiments of the dynamic mutation detection system provided below can be found in the limitations of the dynamic mutation detection method described above, and will not be repeated here.

[0086] In one exemplary embodiment, such as Figure 4 As shown, a dynamic mutation detection system is provided, which includes the following modules.

[0087] The preprocessing module is used to preprocess the raw WES sequencing data to obtain preprocessed data.

[0088] The Dynamic Mutation Annotation Database Construction Module is used to construct a dynamic mutation annotation database based on information on common known pathogenic dynamic mutations.

[0089] The dynamic mutation analysis and feature extraction module is used to perform dynamic mutation analysis and feature extraction in parallel using several core detection tools based on the preprocessed data and the dynamic mutation annotation database, to obtain a feature matrix.

[0090] The pathogenicity probability calculation module is used to calculate the pathogenicity probability based on the feature matrix and by using a logistic regression algorithm to fuse the model.

[0091] The pathogenicity score calculation module is used to calculate the pathogenicity score based on the pathogenicity probability using a logistic function.

[0092] In one exemplary embodiment, a computer device is provided, which may be a server or a terminal, and its internal structure diagram may be as follows. Figure 5 As shown, this computer device includes a processor, memory, input / output (I / O) interfaces, and a communication interface. The processor, memory, and I / O interfaces are connected via a system bus, and the communication interface is also connected to the system bus via the I / O interfaces. The processor provides computational and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system, computer programs, and a database. The internal memory provides the environment for the operating system and computer programs in the non-volatile storage media to run. The database stores raw WES sequencing data. The I / O interfaces are used for exchanging information between the processor and external devices. The communication interface is used for communicating with external terminals via a network connection. When executed by the processor, the computer program implements a dynamic mutation detection method.

[0093] Those skilled in the art will understand that Figure 5 The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the computer device to which the present application is applied. Specific computer devices may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0094] In one exemplary embodiment, a computer device is also provided, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the above-described method embodiments.

[0095] In one exemplary embodiment, a computer-readable storage medium is provided storing a computer program that, when executed by a processor, implements the above-described method embodiments.

[0096] In one exemplary embodiment, a computer program product is provided, including a computer program that, when executed by a processor, implements the above-described method embodiments.

[0097] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, data stored, data displayed, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties. Moreover, the collection, use and processing of the relevant data are carried out in compliance with the relevant data protection laws and policies of the country where the location is located, and with the authorization granted by the owner of the corresponding device.

[0098] Those skilled in the art will understand that all or part of the processes in the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium. When executed, the computer program can include the processes of the embodiments described above. Any references to memory, databases, or other media used in the embodiments provided in this application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM).

[0099] The databases involved in the embodiments provided in this application may include at least one type of relational database and non-relational database. Non-relational databases may include, but are not limited to, blockchain-based distributed databases. The processors involved in the embodiments provided in this application may be general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic devices, quantum computing-based data processing logic devices, etc., and are not limited to these.

[0100] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0101] This document uses specific examples to illustrate the principles and implementation methods of this application. The descriptions of the above embodiments are only for the purpose of helping to understand the methods and core ideas of this application. Furthermore, those skilled in the art will recognize that, based on the ideas of this application, there will be changes in the specific implementation methods and application scope. Therefore, the content of this specification should not be construed as a limitation of this application.

Claims

1. A dynamic mutation detection method, characterized by, The dynamic mutation detection method includes: The raw WES sequencing data were preprocessed to obtain the preprocessed data. A dynamic mutation annotation database is constructed based on information on common known pathogenic dynamic mutations. Based on the preprocessed data and the dynamic mutation annotation database, several core detection tools are used in parallel to perform dynamic mutation analysis and feature extraction to obtain a feature matrix. Based on the aforementioned feature matrix, a logistic regression algorithm is used to fuse the model and calculate the pathogenicity probability. Based on the pathogenicity probability, a pathogenicity score is calculated using the logistic function.

2. The dynamic mutation detection method of claim 1, wherein, The dynamic mutation annotation database includes: dynamic mutation gene name, disease name, repetitive sequence, normal repetition number range, and minimum pathogenic repetition number.

3. The dynamic mutation detection method of claim 1, wherein, The core detection tools include: ExpansionHunter, exSTRa, REViewer, Bamdst, and STRetch.

4. The dynamic mutation detection method according to claim 1, characterized in that, The formula for calculating the pathogenicity probability is: ； in, Probability of causing disease; For bias terms; The longest allele repeat; It is the characteristic transformation function; Statistical test for aberrant amplification of loci p value; Standard scores for aberrant amplification of loci; This is the ratio relative to the average depth of the control sample set; This is a Boolean feature indicating whether local assembly supports extension. Score the reliability of the assembly results; The intensity fraction of the amplified signal; The first regression coefficient; The second regression coefficient; The third regression coefficient; The fourth regression coefficient; This is the fifth regression coefficient; The sixth regression coefficient; This is the seventh regression coefficient.

5. The dynamic mutation detection method according to claim 1, characterized in that, The formula for calculating the pathogenicity score is as follows: ； in, For pathogenicity score; This represents the probability of causing disease.

6. The dynamic mutation detection method according to claim 1, characterized in that, The dynamic mutation detection method further includes: determining whether the pathogenicity score exceeds a decision threshold, and obtaining a determination result; If the judgment result is negative, then it is negative; If the judgment result is yes, then it is positive.

7. A dynamic mutation detection system, characterized in that, The dynamic mutation detection system is used to implement the dynamic mutation detection method according to any one of claims 1-6, and the dynamic mutation detection system comprises: The preprocessing module is used to preprocess the raw WES sequencing data to obtain preprocessed data; The dynamic mutation annotation database construction module is used to build a dynamic mutation annotation database based on information on common known pathogenic dynamic mutations. The dynamic mutation analysis and feature extraction module is used to perform dynamic mutation analysis and feature extraction in parallel using several core detection tools based on the preprocessed data and the dynamic mutation annotation database, to obtain a feature matrix. The pathogenicity probability calculation module is used to calculate the pathogenicity probability based on the feature matrix and by using a logistic regression algorithm to fuse the model. The pathogenicity score calculation module is used to calculate the pathogenicity score based on the pathogenicity probability using a logistic function.

8. A computer device, comprising: A memory, a processor, and a computer program stored in the memory and capable of running on the processor, characterized in that the processor executes the computer program to implement the dynamic mutation detection method according to any one of claims 1-6.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the dynamic mutation detection method according to any one of claims 1-6.

10. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by the processor, it implements the dynamic mutation detection method according to any one of claims 1-6.

Images