Gene single nucleotide polymorphic site analysis method based on SNaPshot

Abstract

The invention relates to the field of bioinformatics and molecular biology, and discloses a gene single nucleotide polymorphism (SNP) site analysis method based on SNaPshot, which comprises the following steps: acquiring genome DNA sequence data of a sample to be detected, extracting SNP site information in the genome DNA sequence data, designing site specific primers, carrying out PCR amplification by using an SNaPshot technology, and determining the SNP site of the sample to be detected. And an electrophoretogram is obtained through capillary electrophoresis separation. By analyzing the maps, the genotype of each SNP site can be determined, and an SNP feature map can be constructed. And finally, performing statistical analysis based on the feature maps to obtain a target analysis result, evaluating gene polymorphism according to the target analysis result, and obtaining related information. According to the method, the efficiency and accuracy of SNP analysis can be improved, and support is provided for genetic research and individualized medical treatment.

Description

Technical Field

[0001] The invention relates to the fields of bioinformatics and molecular biology, and in particular to a gene single nucleotide polymorphism site analysis method based on SNaPshot. Background Art

[0002] In genetic research and clinical diagnosis, the analysis of single nucleotide polymorphisms (SNPs) is a key link because SNPs are closely related to the risk of various diseases and individual drug responses. Although traditional SNP analysis methods, such as microarray chips and direct sequencing, can provide a large amount of genetic information, they are often costly, complex to operate, and time-consuming. In addition, these methods are inefficient when processing large-scale samples and have certain limitations in data analysis and genotype determination. With the development of molecular biology technology, SNaPshot technology, as a cost-effective and easy-to-operate SNP analysis method, has been widely used for genotype identification. However, the existing SNaPshot method still needs to be improved in terms of automated processing, data analysis, and gene polymorphism assessment.

[0003] In the process of implementing the embodiments of the present invention, the inventors found that there are at least the following problems or defects in the prior art: the existing SNaPshot analysis process lacks an automated data processing and analysis module, resulting in low efficiency when processing a large number of samples; in addition, the lack of accurate statistical models to evaluate genetic polymorphisms limits the accuracy and reliability of the results; at the same time, the existing methods lack sufficient flexibility and accuracy in genotype analysis and feature map construction, which limits their application in complex genetic studies. Summary of the invention

[0004] The embodiments of the present invention aim to provide a gene single nucleotide polymorphism site analysis method, medium and electronic device based on SNaPshot to solve the technical problems raised in the prior art.

[0005] The embodiment of the present invention solves the technical problem by adopting the following technical solution:

[0006] In a first aspect, a gene single nucleotide polymorphism site analysis method based on SNaPshot is provided, comprising:

[0007] Obtaining genomic DNA sequence data of the sample to be tested;

[0008] Extracting SNP site information from the genomic DNA sequence data, including but not limited to identifying sites in the reference genomic sequence that differ from the genomic sequence of the sample to be tested;

[0009] Design site-specific primers for each identified SNP site to ensure that the target SNP site can be specifically amplified in the subsequent PCR amplification process;

[0010] The designed site-specific primers were used for PCR amplification using SNaPshot technology to obtain the amplicon of each SNP site;

[0011] The obtained amplicons are separated by capillary electrophoresis to obtain the electrophoretic profile of each SNP site;

[0012] Analyze the electrophoresis pattern to determine the genotype of each SNP site, including homozygous, heterozygous or unknown genotype;

[0013] Based on the genotype information of each SNP site, a SNP characteristic map of the sample to be tested is constructed, in which the genotype of each site is represented by a specific value or symbol;

[0014] Perform statistical analysis on the SNP feature map to obtain the target analysis results;

[0015] Gene polymorphism assessment is performed based on the target analysis results to obtain gene polymorphism information.

[0016] Further, the performing gene polymorphism assessment based on the target analysis result includes: obtaining an assessment result of performing gene polymorphism assessment on the target analysis result based on a pre-established gene polymorphism assessment model;

[0017] Wherein, the gene polymorphism assessment model includes: a statistical model obtained by pre-training a training set constructed from sample genome DNA sequence data, which is used to assess gene polymorphism;

[0018] The feature extraction module in the statistical model is used to obtain the sample SNP feature map of the sample genome DNA sequence data, so that the statistical model can perform gene polymorphism assessment based on the sample SNP feature map.

[0019] Furthermore, the extracting of SNP site information from the genomic DNA sequence data includes: inputting the genomic DNA sequence data into the gene polymorphism evaluation model to obtain the SNP site information of the genomic DNA sequence data extracted by a feature extractor in the gene polymorphism evaluation model.

[0020] Further, the feature extractor is bridged via a preset data processing module;

[0021] The data processing module is used to obtain the SNP site information; and assign corresponding weight coefficients to the SNP site information;

[0022] The determining the SNP characteristic graph of the sample to be tested based on the SNP site information includes: determining the SNP characteristic graph of the sample to be tested based on the SNP site information and the weight coefficient.

[0023] Furthermore, the statistical analysis of the SNP characteristic graph includes calculating allele frequency, genetic distance, and population genetic structure.

[0024] Further, the gene polymorphism assessment model is trained in the following manner: the statistical model is trained based on the genomic DNA sequence data of each sample with annotated gene polymorphism to obtain a preliminarily trained gene polymorphism assessment model;

[0025] Inputting a certain number of sample genomic DNA sequence data into the gene polymorphism evaluation model to obtain an evaluation result output by the gene polymorphism evaluation model, and obtaining the uncertainty of each sample genomic DNA sequence data based on the evaluation result; wherein each sample genomic DNA sequence data includes a group of genomic DNA sequence data, and the samples to be tested in a group of genomic DNA sequence data are the same sample to be tested;

[0026] The uncertainty indicates: the probability that the polymorphism of the sample genome DNA sequence data evaluated by the gene polymorphism evaluation model is a true polymorphism;

[0027] Selecting target sample genomic DNA sequence data from each sample genomic DNA sequence data based on the uncertainty corresponding to each sample genomic DNA sequence data, and obtaining manual annotation of the target sample genomic DNA sequence data;

[0028] The gene polymorphism assessment model is trained based on the target sample genome DNA sequence data to obtain a trained gene polymorphism assessment model.

[0029] Furthermore, the method of selecting target sample genomic DNA sequence data from each sample genomic DNA sequence data based on the uncertainty corresponding to each sample genomic DNA sequence data includes: selecting a certain number of sample genomic DNA sequence data with the highest uncertainty, clustering based on the selected sample genomic DNA sequence data, and obtaining sample genomic DNA sequence data corresponding to a target number of clustering centers as target sample genomic DNA sequence data.

[0030] Furthermore, the uncertainty is calculated as follows:

[0031]

[0032] Where U represents the uncertainty of the genomic DNA sequence data of the i-th group of samples; wi is the weight coefficient of uncertainty of polymorphism category i in the evaluation result; C ij N is the confidence of the jth target of polymorphism category i in the sample genome DNA sequence data in the evaluation result; ij is the frequency of the jth target of polymorphism category i in the sample genomic DNA sequence data in the evaluation result; n is the total number of sample genomic DNA sequence data; and m is the total number of targets in polymorphism category i.

[0033] In a second aspect of the present invention, a computer-readable storage medium is provided, which includes instructions, and when the instructions are executed on a computer, the computer is caused to execute the method according to any one of the first aspects.

[0034] In a third aspect of the present invention, an electronic device is provided, comprising: at least one processor, a memory and an input-output unit; wherein the memory is used to store a computer program, and the processor is used to call the computer program stored in the memory to execute any one of the methods described in the first aspect.

[0035] The above-mentioned embodiments of the present invention have at least the following beneficial effects: The present invention provides a method for analyzing single nucleotide polymorphism sites of genes based on SNaPshot technology, which can improve the efficiency and accuracy of SNP analysis through automated data processing and accurate statistical models. By constructing a statistical model obtained by pre-training of a training set, the method can effectively evaluate the polymorphism of genes, and obtain the SNP feature map of the sample genome DNA sequence data through a feature extraction module, and then perform gene polymorphism evaluation. In addition, the method also includes statistical analysis of the SNP feature map, such as calculating allele frequency, genetic distance and population genetic structure, so as to provide more accurate and comprehensive genotype information for genetic research and clinical diagnosis.

[0036] The method of the present invention also includes selecting target samples for manual annotation based on the uncertainty of sample genome DNA sequence data, and further training and optimizing the gene polymorphism assessment model. This iterative training process can continuously improve the accuracy and robustness of the model. In this way, the present invention can achieve rapid and accurate analysis of a large number of samples, providing strong technical support for genetic research and personalized medicine. At the same time, the present invention also provides a computer program and electronic equipment for implementing the method, so that the method can be easily applied in various laboratories and medical institutions. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] One or more embodiments are exemplarily described by the figures in the corresponding drawings, and these exemplifications do not constitute limitations on the embodiments. Elements with the same reference numerals in the drawings represent similar elements, and unless otherwise stated, the figures in the drawings do not constitute proportional limitations.

[0038] Figure 1 It is a schematic diagram of the process of the gene single nucleotide polymorphism site analysis method based on SNaPshot provided by the present invention. DETAILED DESCRIPTION

[0039] In order to facilitate the understanding of the present invention, the present invention is described in more detail below in conjunction with the accompanying drawings and specific embodiments. It should be noted that when an element is described as "connecting" another element, it can be directly on another element, or there can be one or more centered elements therebetween. The orientation or positional relationship indicated by the terms "upper", "lower", "left", "right", "upper end", "lower end", "top" and "bottom" used in this specification is based on the orientation or positional relationship shown in the accompanying drawings, only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as a limitation of the present invention. In addition, the terms "first", "second", etc. are only used for descriptive purposes and cannot be understood as indicating or implying relative importance.

[0040] Unless otherwise defined, all technical and scientific terms used in this specification have the same meaning as those commonly understood by those skilled in the art of the present invention. The terms used in the specification of the present invention are only for the purpose of describing specific embodiments and are not intended to limit the present invention.

[0041] Combine the following Figure 1 , the gene single nucleotide polymorphism site analysis method 100 based on SNaPshot provided in the embodiment of the present application is described in detail through a specific example.

[0042] Figure 1 1 is a schematic diagram of a flow chart of a gene single nucleotide polymorphism site analysis method based on SNaPshot provided by the present invention. A gene single nucleotide polymorphism site analysis method based on SNaPshot provided by one embodiment of the present invention comprises:

[0043] Step 101, obtaining genomic DNA sequence data of a sample to be tested;

[0044] Step 102, extracting SNP site information in the genomic DNA sequence data, including but not limited to identifying sites in the reference genome sequence that differ from the genome sequence of the sample to be tested;

[0045] Step 103, designing site-specific primers for each identified SNP site to ensure that the target SNP site can be specifically amplified in the subsequent PCR amplification process;

[0046] Step 104, using the SNaPshot technology to perform PCR amplification on the designed site-specific primers to obtain an amplicon of each SNP site;

[0047] Step 105, performing capillary electrophoresis separation on the obtained amplicons to obtain an electrophoresis pattern of each SNP site;

[0048] Step 106, analyzing the electrophoresis pattern to determine the genotype of each SNP site, including homozygous, heterozygous or unknown genotype;

[0049] Step 107, constructing a SNP characteristic map of the sample to be tested based on the genotype information of each SNP site, wherein the genotype of each site is represented by a specific value or symbol;

[0050] Step 108, performing statistical analysis on the SNP characteristic graph to obtain a target analysis result;

[0051] Step 109: Perform gene polymorphism assessment based on the target analysis result to obtain gene polymorphism information.

[0052] It should be noted that the method first involves obtaining genomic DNA sequence data of the sample to be tested, where the genomic DNA sequence data refers to the complete DNA sequence information that constitutes the individual genome. In actual operation, these data can be obtained through high-throughput sequencing technology, such as next-generation sequencing (NGS).

[0053] Specifically, the process of obtaining genomic DNA sequence data includes sample collection, DNA extraction, library construction, and sequencing. After sequencing, bioinformatics tools are used to perform sequence alignment to identify the differences between the reference genome sequence and the genome sequence of the sample to be tested. These differences constitute the SNP site information. In terms of parameter setting, the appropriate sequencing depth and coverage can be selected according to the complexity of the sample and the required accuracy.

[0054] More specifically, the step of extracting SNP site information can be implemented by specialized bioinformatics software, such as using GATK (Genome Analysis Toolkit) for variation detection. In this process, specific parameters, such as the minimum allele frequency threshold, can be set to filter out possible sequencing errors.

[0055] Furthermore, multiple alignment and correction algorithms can be used to improve the accuracy of SNP site identification. For the design of site-specific primers, online tools such as Primer3 can be used to design highly specific primers based on the sequence characteristics of the SNP site to ensure that the target SNP site can be specifically amplified in the subsequent PCR amplification process.

[0056] Capillary electrophoresis separation is an analytical technique based on the principle of electrophoresis. It uses a high voltage electric field as a driving force and a capillary as a separation channel to achieve separation based on the differences in electrophoretic mobility and distribution behavior between the components in the sample. When performing single nucleotide polymorphism (SNP) analysis based on SNaPshot, capillary electrophoresis separation is used to distinguish and identify amplicons of different SNP sites.

[0057] Specifically, SNaPshot technology is a small sequencing technology that performs SNP typing by primer extension. In this process, the DNA region containing the SNP site is first PCR amplified, and then a single base extension is performed on each SNP site using specific primers to generate amplicons of different lengths. These amplicons are then separated by capillary electrophoresis, and the migration speed of each amplicon depends on its size and electrophoretic mobility, forming different peaks on the electrophoretic spectrum.

[0058] The electrophoresis pattern obtained by capillary electrophoresis separation can clearly show the amplicon of each SNP site. The position of the peak corresponds to the specific amplicon length, and the height of the peak reflects the concentration of the amplicon. By analyzing the position and height of these peaks, the genotype of the sample at each SNP site can be determined.

[0059] Each peak on the electropherogram represents a specific amplicon, and its position corresponds to the length of the amplicon. Since fluorescently labeled ddNTPs are used in the SNaPshot reaction, the color of each peak can indicate the type of base incorporated, thereby determining the genotype of the sample at the SNP site. In the electropherogram, homozygous sites usually appear as a single peak, which means that the sample has only one allele at the site. Heterozygous sites appear as two or more peaks, indicating that the sample has two or more different alleles at the site. For example, if a SNP site is a C / T polymorphism, the homozygous CC or TT genotype will appear as a single peak, while the heterozygous CT genotype will appear as two peaks, one corresponding to C and the other corresponding to T.

[0060] If the peaks in the electropherogram do not conform to the expected homozygous or heterozygous pattern, or if the peaks are unclear, this may indicate that the genotype is unknown or there is a problem with the sample. This may require further experimental verification, such as re-PCR amplification or use of other methods for genotype confirmation.

[0061] Capillary electrophoresis separation of SNP sites has the characteristics of high resolution and high sensitivity, and can accurately distinguish very close DNA fragments, which is very important for genotyping and genetic variation research. In addition, capillary electrophoresis separation technology also has the advantages of simple operation, fast analysis speed, low sample consumption, and compatibility with multiple detection methods.

[0062] SNaPshot technology is used to perform PCR amplification on the designed site-specific primers to obtain the amplicon of each SNP site. First, based on the sequence information of the target SNP site, primers that can specifically recognize and bind to the vicinity of these sites are designed. These primers need to be designed to ensure that they can effectively complement the target DNA sequence and promote the PCR reaction. During the PCR amplification process, these site-specific primers are mixed with the sample DNA, and an appropriate PCR reaction system is added, including reaction components such as dNTPs, DNA polymerase, and Mg2+. By controlling the reaction conditions, such as denaturation, annealing, and extension, the DNA polymerase synthesizes a new DNA chain along the template DNA, thereby obtaining an amplicon containing the SNP site.

[0063] In some embodiments, after PCR amplification is completed, the PCR product needs to be purified to remove excess primers, dNTPs and other impurities that may interfere with subsequent reactions. This step is crucial to ensure the accuracy of the SNaPshot reaction. Subsequently, the SNaPshot reaction is performed using the purified PCR product as a template. In this reaction, a special primer is used that is adjacent to the SNP site, and a single base extension can only be performed when the primer is correctly paired with the template DNA. This single base extension will produce amplicons of different lengths, each length corresponding to a specific allele of the SNP site.

[0064] These amplicons are separated by capillary electrophoresis, and the electric field is used to drive the amplicons through the capillary, so that they form different peaks on the electrophoresis spectrum according to their length and electrophoretic mobility. By analyzing the position and intensity of these peaks, the genotype of the sample at each SNP site can be accurately determined. This method can not only provide high-resolution genotype data, but also is easy to operate and fast in analysis.

[0065] In some embodiments, the performing gene polymorphism assessment based on the target analysis result comprises: obtaining an assessment result of performing gene polymorphism assessment on the target analysis result based on a pre-established gene polymorphism assessment model;

[0066] Wherein, the gene polymorphism assessment model includes: a statistical model obtained by pre-training a training set constructed from sample genome DNA sequence data, which is used to assess gene polymorphism;

[0067] The feature extraction module in the statistical model is used to obtain the sample SNP feature map of the sample genome DNA sequence data, so that the statistical model can perform gene polymorphism assessment based on the sample SNP feature map.

[0068] It should be noted that this implementation method obtains the evaluation result of the gene polymorphism evaluation of the target analysis result based on the pre-established gene polymorphism evaluation model. The gene polymorphism evaluation model here refers to a model constructed using statistical methods, which can evaluate the gene polymorphism of the sample based on the SNP characteristic map of the sample. This model usually includes a training set, which is constructed from the sample genomic DNA sequence data of the known gene polymorphism for pre-training the statistical model.

[0069] Specifically, the training of the gene polymorphism assessment model involves using a set of sample data with known gene polymorphisms to train the statistical model so that the model can learn and identify features associated with gene polymorphisms. In this process, machine learning algorithms such as random forests, support vector machines, or neural networks can be used to process and analyze the data. The feature extraction module is part of the model, which is responsible for extracting SNP feature maps for evaluation from the sample genomic DNA sequence data. These feature maps contain the genotype information of all relevant SNP sites in the sample, providing a basis for the model to be evaluated.

[0070] Preferably, the gene polymorphism assessment model can be optimized by cross-validation to ensure the generalization ability of the model. After the model training is completed, a set of independent test data can be used to verify the performance of the model to ensure that it can accurately assess gene polymorphisms on new, unseen data.

[0071] Furthermore, different feature selection methods can be considered to improve the efficiency and accuracy of the model, for example, recursive feature elimination (RFE) can be used to select the most informative features. In actual operation, model parameters can also be adjusted according to specific application scenarios, such as adjusting the depth of the decision tree or the number of layers of the neural network to achieve the best evaluation effect.

[0072] In some embodiments, extracting the SNP site information from the genomic DNA sequence data includes: inputting the genomic DNA sequence data into the gene polymorphism evaluation model to obtain the SNP site information of the genomic DNA sequence data extracted by the feature extractor in the gene polymorphism evaluation model.

[0073] It should be noted that this embodiment involves inputting genomic DNA sequence data into a gene polymorphism assessment model to obtain SNP site information extracted by a feature extractor in the model. The feature extractor here refers to a component within the model, and its function is to identify and extract features useful for gene polymorphism assessment, i.e., SNP sites, from the input data.

[0074] Specifically, the feature extractor can be implemented through a variety of algorithms, such as using data in a variant call format (VCF) file to identify SNP sites. In actual operation, the feature extractor may use specific parameters, such as the minimum allele frequency threshold, the P value of the Hardy-Weinberg equilibrium test, etc., to filter out sites that are unlikely to affect the evaluation of genetic polymorphism. In addition, the feature extractor can also include a weight assignment mechanism to assign weight coefficients to different SNP sites, and these weight coefficients reflect the importance of the site in the evaluation of genetic polymorphism.

[0075] Preferably, the feature extractor can be implemented using deep learning methods, such as convolutional neural networks (CNN) or recurrent neural networks (RNN), to automatically identify and extract complex patterns and features. In this case, the effect of feature extraction can be optimized by adjusting the network architecture, such as the number of layers, the number of neurons, or the activation function.

[0076] Furthermore, it is also possible to consider using ensemble learning methods, such as random forests or gradient boosting machines (GBM), to improve the robustness and accuracy of feature extraction. In terms of weight allocation, a weight allocation strategy based on information gain or model importance can be adopted to ensure that the model can pay more attention to those sites that have a greater impact on the evaluation of genetic polymorphisms.

[0077] In some embodiments, the feature extractor is bridged via a preset data processing module;

[0078] The data processing module is used to obtain the SNP site information; and assign corresponding weight coefficients to the SNP site information;

[0079] The determining the SNP characteristic graph of the sample to be tested based on the SNP site information includes: determining the SNP characteristic graph of the sample to be tested based on the SNP site information and the weight coefficient.

[0080] It should be noted that this embodiment involves a feature extractor bridged by a preset data processing module to obtain SNP site information and assign corresponding weight coefficients to this information. The data processing module here refers to a software component for processing and analyzing genomic data, which can identify SNP sites and calculate their corresponding weight coefficients for subsequent analysis.

[0081] Specifically, the data processing module may include a series of algorithms and parameter settings. For example, it may set a threshold to determine which SNP sites are significant, or use a specific statistical method to calculate the weight coefficient of each site.

[0082] More specifically, these weight coefficients can be based on the allele frequency of the site, the Hardy-Weinberg equilibrium state, the linkage disequilibrium pattern, or other genetics-related indicators. In actual operation, the data processing module may also involve data cleaning and preprocessing steps, such as removing duplicate sites, filtering low-quality data, etc.

[0083] Preferably, the data processing module can integrate a variety of bioinformatics tools and algorithms to improve the accuracy and efficiency of SNP site information extraction. For example, Burrows-Wheeler Aligner (BWA) can be used for sequence alignment, GATK can be used for variation detection, and PLINK or VCFtools can be used for subsequent genetic analysis.

[0084] Furthermore, the weight coefficients can be assigned based on the output of machine learning models, such as random forests or gradient boosted decision trees, which can learn which features are most important for predicting genetic polymorphisms. When determining the SNP feature map, clustering algorithms, such as K-means or hierarchical clustering, can also be considered to identify genetic subgroups in the sample, thereby more finely constructing the SNP feature map.

[0085] In some embodiments, the statistical analysis of the SNP feature map includes calculating allele frequencies, genetic distances, and population genetic structure.

[0086] It should be noted that this implementation involves statistical analysis of SNP feature maps, including calculation of allele frequency, genetic distance and population genetic structure. Here, allele frequency refers to the proportion of a certain allele in a specific population; genetic distance refers to the degree of difference between individuals or groups based on genetic variation; and population genetic structure refers to the pattern of genetic differences within and between groups.

[0087] Specifically, statistical analysis can be performed using a range of biostatistical methods. For example, allele frequencies can be calculated using the Hardy-Weinberg equilibrium principle, which assumes that the frequencies of alleles and genotypes in a population remain constant from generation to generation in the absence of other evolutionary forces.

[0088] More specifically, genetic distance can be estimated by calculating the differences in single nucleotide polymorphism sites between different individuals or populations. Commonly used methods include Euclidean distance or Manhattan distance. Analysis of population genetic structure may involve principal component analysis (PCA) or structural analysis (STRUCTURE), which can help identify genetic subgroups in a population and genetic relationships between individuals.

[0089] Preferably, the implementation of statistical analysis can be completed using a variety of software and tools. For example, the genetics package of R language such as adegenet can be used to calculate allele frequencies and analyze population genetic structure, or the scikit-learn library of Python can be used to calculate genetic distances.

[0090] Furthermore, graphical tools such as PLINK or online platforms such as GWAS Catalog can be used to assist in the analysis and interpretation of results. In terms of parameter settings, they can be adjusted according to the specific purpose of the study and the characteristics of the sample. For example, different significance level thresholds can be set or different numbers of PCA components can be used to capture the main variations in population structure. In addition, Bayesian methods or machine learning techniques can also be considered to improve the accuracy and reliability of statistical analysis.

[0091] In some embodiments, the gene polymorphism assessment model is trained in the following manner: the statistical model is trained based on the genomic DNA sequence data of each sample with annotated gene polymorphisms to obtain a preliminarily trained gene polymorphism assessment model;

[0092] Inputting a certain number of sample genomic DNA sequence data into the gene polymorphism evaluation model to obtain an evaluation result output by the gene polymorphism evaluation model, and obtaining the uncertainty of each sample genomic DNA sequence data based on the evaluation result; wherein each sample genomic DNA sequence data includes a group of genomic DNA sequence data, and the samples to be tested in a group of genomic DNA sequence data are the same sample to be tested;

[0093] The uncertainty indicates: the probability that the polymorphism of the sample genome DNA sequence data evaluated by the gene polymorphism evaluation model is a true polymorphism;

[0094] Selecting target sample genomic DNA sequence data from each sample genomic DNA sequence data based on the uncertainty corresponding to each sample genomic DNA sequence data, and obtaining manual annotation of the target sample genomic DNA sequence data;

[0095] The gene polymorphism assessment model is trained based on the target sample genome DNA sequence data to obtain a trained gene polymorphism assessment model.

[0096] It should be noted that this embodiment describes a method for training a gene polymorphism assessment model, which includes preliminary training of a statistical model based on sample genomic DNA sequence data with annotated gene polymorphisms, and subsequent optimization of the model through the uncertainty of the sample genomic DNA sequence data. The uncertainty here refers to the probability of the difference between the polymorphism of the sample genomic DNA sequence data assessed by the model and the true polymorphism.

[0097] Specifically, the initial training of the gene polymorphism assessment model involves using a set of sample data with known polymorphism labels, which can be derived from public databases or previous research results of the laboratory. During the training process, a variety of machine learning algorithms, such as support vector machines (SVM), random forests or neural networks, can be used to identify and learn features related to gene polymorphisms.

[0098] Further, after the initial training is completed, the model will evaluate new sample data and output the polymorphism evaluation results of each sample. Based on these evaluation results, the uncertainty of each sample can be calculated, which usually involves the probability distribution of the statistical model output.

[0099] Preferably, the specific method for calculating uncertainty can adopt a Bayesian statistical framework, in which the output probability of the model is used to estimate uncertainty. For example, the confidence interval width or standard deviation of the model output can be used as a measure of uncertainty.

[0100] Furthermore, cross-validation can be used to evaluate the uncertainty of the model and adjust the model parameters by comparing the consistency of the evaluation results between different sample sets. During the model training process, regularization techniques such as L1 or L2 regularization can also be introduced to prevent the model from overfitting.

[0101] More specifically, hyperparameter optimization methods such as grid search or random search can be used to select the best model parameters, such as tree depth, learning rate, or regularization coefficient. In addition, ensemble learning methods such as boosting trees or gradient boosting machines can also be considered to further improve the predictive performance and robustness of the model.

[0102] In some embodiments, the method of selecting target sample genomic DNA sequence data from each sample genomic DNA sequence data based on the uncertainty corresponding to each sample genomic DNA sequence data includes: selecting a certain number of sample genomic DNA sequence data with the highest uncertainty, clustering based on the selected sample genomic DNA sequence data, and obtaining sample genomic DNA sequence data corresponding to a target number of clustering centers as target sample genomic DNA sequence data.

[0103] It should be noted that this embodiment describes a method for selecting target samples based on the uncertainty of sample genomic DNA sequence data. The target samples here refer to those samples with the highest uncertainty, which will be used for further training and optimization of gene polymorphism assessment models. Clustering is a statistical method for grouping samples in a data set according to similarity.

[0104] Specifically, the process of selecting target samples may include the following steps: first, using the evaluation model to perform polymorphism evaluation on the genomic DNA sequence data of all samples, and then calculating the uncertainty of each sample based on the evaluation results. Next, a certain number of samples with the highest uncertainty are selected, for example, the top 10% of samples with the highest uncertainty can be selected.

[0105] Furthermore, these samples are clustered, and the clustering method can be K-means, hierarchical clustering or density clustering. The goal of clustering is to divide the samples into several groups, and the samples in each group have high similarity in genetic characteristics. Finally, a sample is selected from each cluster as the target sample corresponding to the cluster center.

[0106] Preferably, the parameter setting of cluster analysis can be adjusted based on the characteristics of sample data. For example, the number of clusters (K value) can be set based on the genetic diversity of sample data, or the silhouette coefficient can be used to evaluate the clustering effect under different K values. When selecting cluster centers, a weighted voting method can be considered, in which the probability of each sample being selected as the center is proportional to its uncertainty.

[0107] Furthermore, we can also consider using density-based clustering methods, such as DBSCAN, which does not require the number of clusters to be set in advance, but determines the cluster boundaries based on the density of the samples. In actual operation, we can also combine the results of multiple clustering methods and select the final target samples through ensemble learning to improve the accuracy and robustness of the selection process.

[0108] In some embodiments, the uncertainty is calculated as follows:

[0109]

[0110] Where U represents the uncertainty of the genomic DNA sequence data of the i-th group of samples; w i is the weight coefficient of uncertainty of polymorphism category i in the evaluation result; C ij N is the confidence of the jth target of polymorphism category i in the sample genome DNA sequence data in the evaluation result; ijis the frequency of the jth target of polymorphism category i in the sample genomic DNA sequence data in the evaluation result; n is the total number of sample genomic DNA sequence data; and m is the total number of targets in polymorphism category i.

[0111] It should be noted that this embodiment describes a specific method for calculating uncertainty. Uncertainty refers to the comprehensive reflection of the weight coefficient, confidence and frequency of the uncertainty of the polymorphism category in the evaluation result. The uncertainty here is a quantitative indicator used to measure the credibility of the model's evaluation of the polymorphism of the sample genome DNA sequence data.

[0112] Specifically, the calculation of uncertainty can be achieved through a specific formula, which involves multiple parameters, including the uncertainty weight coefficient of the polymorphism category, the confidence and frequency of the polymorphism category in the sample genomic DNA sequence data.

[0113] More specifically, in actual operation, the weight coefficient can be set according to the importance of the polymorphism category, the confidence can be the confidence level of each site in the model evaluation result, and the frequency is the number of times each site appears in the sample. The setting of these parameters needs to be determined according to the specific data set and research purpose.

[0114] Preferably, the calculation of uncertainty can be further refined into the following steps: first, determine the importance of each polymorphism category and assign a weight coefficient accordingly; second, for the genomic DNA sequence data of each sample, calculate its confidence and frequency of occurrence in each polymorphism category; then, substitute these values ​​into the formula to calculate the uncertainty of each sample.

[0115] Furthermore, machine learning methods, such as gradient boosting decision trees or neural networks, can be used to dynamically adjust weight coefficients to improve the accuracy of uncertainty calculations. When calculating frequencies, smoothing techniques, such as Laplace smoothing, can be considered to avoid zero frequency problems. More specifically, genetic background information of samples, such as ethnic group information, can also be introduced to weight the uncertainty of different samples, thereby more accurately reflecting the genetic diversity of samples.

[0116] The above-mentioned embodiments of the present invention have the following beneficial effects: The gene single nucleotide polymorphism site analysis method based on SNaPshot technology of the present invention can provide an efficient and accurate genotype analysis method, which extracts SNP site information from the genomic DNA sequence data of the sample to be tested through an automated process, and uses specific primer design and PCR amplification, combined with capillary electrophoresis separation and electrophoresis map analysis, to determine the genotype of each SNP site. This method can construct a detailed SNP feature map, and obtain the target analysis results through statistical analysis, and then perform gene polymorphism evaluation, providing important information for genetic research, disease risk assessment and personalized treatment.

[0117] In addition, the method also includes using a pre-established gene polymorphism assessment model to analyze the target analysis results. The model is pre-trained based on a training set constructed based on sample genomic DNA sequence data, and the sample SNP feature map is obtained through a feature extraction module to perform gene polymorphism assessment. This method can improve the accuracy of the assessment and further enhance the understanding of the population genetic structure by calculating statistical analyses such as allele frequency, genetic distance, and population genetic structure. With this method, researchers can more accurately identify and evaluate disease-related genetic variations, providing a scientific basis for precision medicine and public health decision-making.

[0118] Furthermore, the storage medium of the embodiment of the present application stores program instructions that can implement all the above methods, wherein the program instructions can be stored in the above storage medium in the form of a software product, including several instructions for enabling a computer device (which can be a personal computer, server, or network device, etc.) or a processor to execute all or part of the steps of the methods described in each embodiment of the present application. The aforementioned storage medium includes: various media that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, or terminal devices such as a computer, a server, a mobile phone, and a tablet.

[0119] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit them. Under the concept of the present invention, the technical features in the above embodiments or different embodiments can also be combined, the steps can be implemented in any order, and there are many other changes in different aspects of the present invention as above, which are not provided in detail for the sake of simplicity. Although the present invention is described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions recorded in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the scope of the technical solutions of the embodiments of the present invention.

Claims

1. A gene single nucleotide polymorphism site analysis method based on SNaPshot, characterized in that: The method comprises: Obtaining genomic DNA sequence data of the sample to be tested; Extracting SNP site information from the genomic DNA sequence data, including but not limited to identifying sites in the reference genomic sequence that differ from the genomic sequence of the sample to be tested; Design site-specific primers for each identified SNP site to ensure that the target SNP site can be specifically amplified in the subsequent PCR amplification process; The designed site-specific primers were used for PCR amplification using SNaPshot technology to obtain the amplicon of each SNP site; The obtained amplicons are separated by capillary electrophoresis to obtain the electrophoretic profile of each SNP site; Analyze the electrophoresis pattern to determine the genotype of each SNP site, including homozygous, heterozygous or unknown genotype; Based on the genotype information of each SNP site, a SNP characteristic map of the sample to be tested is constructed, in which the genotype of each site is represented by a specific value or symbol; Perform statistical analysis on the SNP feature map to obtain the target analysis results; Gene polymorphism assessment is performed based on the target analysis results to obtain gene polymorphism information.

2. The method according to claim 1, characterized in that The performing gene polymorphism assessment based on the target analysis result comprises: obtaining an assessment result of performing gene polymorphism assessment on the target analysis result based on a pre-established gene polymorphism assessment model; Wherein, the gene polymorphism assessment model includes: a statistical model obtained by pre-training a training set constructed from sample genome DNA sequence data, which is used to assess gene polymorphism; The feature extraction module in the statistical model is used to obtain the sample SNP feature map of the sample genome DNA sequence data, so that the statistical model can perform gene polymorphism assessment based on the sample SNP feature map.

3. The method according to claim 2, characterized in that The extracting of SNP site information from the genomic DNA sequence data comprises: inputting the genomic DNA sequence data into the gene polymorphism evaluation model, and obtaining the SNP site information of the genomic DNA sequence data extracted by a feature extractor in the gene polymorphism evaluation model.

4. The method according to claim 3, characterized in that The feature extractor is bridged via a preset data processing module; The data processing module is used to obtain the SNP site information; Assigning a corresponding weight coefficient to the SNP site information; The determining the SNP characteristic graph of the sample to be tested based on the SNP site information includes: determining the SNP characteristic graph of the sample to be tested based on the SNP site information and the weight coefficient.

5. The method according to claim 1, characterized in that The statistical analysis of the SNP characteristic graph includes calculating allele frequency, genetic distance, and population genetic structure.

6. The method according to claim 2, characterized in that The gene polymorphism assessment model is trained in the following manner: the statistical model is trained based on the genomic DNA sequence data of each sample with annotated gene polymorphism to obtain a preliminarily trained gene polymorphism assessment model; Inputting a certain number of sample genomic DNA sequence data into the gene polymorphism evaluation model to obtain an evaluation result output by the gene polymorphism evaluation model, and obtaining the uncertainty of each sample genomic DNA sequence data based on the evaluation result; wherein each sample genomic DNA sequence data includes a group of genomic DNA sequence data, and the samples to be tested in a group of genomic DNA sequence data are the same sample to be tested; The uncertainty indicates: the probability that the polymorphism of the sample genome DNA sequence data evaluated by the gene polymorphism evaluation model is a true polymorphism; Selecting target sample genomic DNA sequence data from each sample genomic DNA sequence data based on the uncertainty corresponding to each sample genomic DNA sequence data, and obtaining manual annotation of the target sample genomic DNA sequence data; The gene polymorphism assessment model is trained based on the target sample genome DNA sequence data to obtain a trained gene polymorphism assessment model.

7. The method according to claim 6, characterized in that The method of selecting target sample genomic DNA sequence data from each sample genomic DNA sequence data based on the uncertainty corresponding to each sample genomic DNA sequence data includes: selecting a certain number of sample genomic DNA sequence data with the highest uncertainty, clustering based on the selected sample genomic DNA sequence data, and obtaining sample genomic DNA sequence data corresponding to a target number of clustering centers as target sample genomic DNA sequence data.

8. The method according to claim 6, characterized in that The uncertainty is calculated as follows: Where U represents the uncertainty of the genomic DNA sequence data of the i-th group of samples; w i is the weight coefficient of uncertainty of polymorphism category i in the evaluation result; C ij N is the confidence of the jth target of polymorphism category i in the sample genome DNA sequence data in the evaluation result; ij is the frequency of the jth target of polymorphism category i in the sample genomic DNA sequence data in the evaluation result; n is the total number of sample genomic DNA sequence data; and m is the total number of targets in polymorphism category i.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the method according to any one of claims 1 to 8 is implemented.

10. An electronic device, characterized in that: include: Memory, processor; The memory stores a computer program, and when the computer program is executed by the processor, the method according to any one of claims 1 to 8 is implemented.

Images