Semi-supervised SNP typing method, device and electronic device based on control group

Abstract

The present invention provides a semi-supervised SNP typing method, device and electronic device based on a control group, which relates to the technical field of genotyping. The method comprises: determining a category center based on pre-collected sample data; the sample data comprises a control group sample and a sample to be tested; performing adaptive clustering analysis on the sample data according to the category center to generate a clustering result; classifying the clustering result according to the genotype characteristics of the SNP to determine the SNP typing of the sample to be tested. This method alleviates the technical problem of poor typing effect due to irregular distribution of genotype clusters, and achieves the technical effect of improving typing accuracy and being easy to implement.

Description

Technical Field

[0001] The present invention relates to the technical field of genotyping, and in particular to a semi-supervised SNP typing method, device and electronic equipment based on a control group. Background Art

[0002] Single nucleotide polymorphism (SNP) mainly refers to DNA sequence polymorphism caused by the variation of a single nucleotide at the genomic level. It is the most common type of heritable variation in humans, accounting for more than 90% of all known polymorphisms. SNP is widely present in the human genome, and a variety of typing detection technologies have been formed, including direct sequencing, amplification curve method, and high-resolution melting curve analysis (High Resolution Melting, HRM). Among them, the amplification curve method is widely used due to its advantages such as simple operation, fast speed, high throughput, and easy interpretation of results.

[0003] The amplification curve method usually collects the fluorescence intensity data of each sample at the end of amplification of each allele, and then conducts research based on this (also known as the "end point method"). Among them, the most commonly used analysis method is cluster analysis, but through experiments, it is found that the irregularity of cluster distribution has a greater impact on the clustering results. If the cluster distribution is very irregular, the clustering effect is usually not very good. At this time, to achieve a good clustering effect, more labeled data is required, and the more irregular the cluster distribution, the more labeled data is required.

[0004] That is to say, in the existing SNP genotyping technology, there is a technical problem that the typing effect is poor due to the irregular distribution of genotype clusters. Summary of the invention

[0005] The purpose of the present invention is to provide a semi-supervised SNP typing method, device and electronic device based on a control group to alleviate the technical problem existing in the prior art that the typing effect is poor due to the irregular distribution of genotype clusters.

[0006] In a first aspect, an embodiment of the present invention provides a semi-supervised SNP typing method based on a control group, comprising:

[0007] Determine the category center based on the sample data collected in advance; the sample data includes the control group sample and the sample to be tested;

[0008] According to the category center, the sample data is adaptively clustered and the clustering results are generated;

[0009] The clustering results are classified according to the genotype characteristics of SNPs to determine the genotype of the sample to be tested.

[0010] In some possible implementations, before the step of determining the category center based on the pre-collected sample data, the method further includes:

[0011] Collect the endpoint fluorescence intensity data of each channel for the SNP site;

[0012] The endpoint fluorescence intensity data is preprocessed to generate sample data.

[0013] In some possible implementations, the step of determining the category center based on pre-collected sample data includes:

[0014] Based on the sample data collected in advance, the known categories of the control group samples are determined; the known categories of the control group samples include: blank samples, homozygotes, and heterozygotes;

[0015] Based on the known categories of the control group samples, determine the first category center.

[0016] In some possible implementations, the step of determining the category center based on the pre-collected sample data further includes:

[0017] Determine the number of unknown categories based on pre-collected sample data and a predetermined total number of categories;

[0018] Based on the minimum distance maximum principle, the second category center of the unknown category is determined.

[0019] In some possible implementations, the step of performing adaptive clustering analysis on sample data according to category centers to generate clustering results includes:

[0020] According to the first category center and the second category center, combined with a predetermined setting mode, an adaptive clustering analysis is performed on the sample data to generate an optimal clustering result.

[0021] In some possible implementations, the setting mode includes allowing changes and not allowing changes;

[0022] When the setting mode of the control group is to allow changes, the categories to which each sample in the control group belongs are allowed to be changed during clustering; when the setting mode of the control group is to not allow changes, the categories to which each sample in the control group belongs are not allowed to be changed during clustering.

[0023] In a second aspect, an embodiment of the present invention provides a semi-supervised SNP typing device based on a control group, comprising:

[0024] A category center determination module is used to determine the category center of the control group samples based on the pre-collected sample data; the sample data includes the control group samples and the samples to be tested;

[0025] The cluster analysis module is used to perform adaptive cluster analysis on sample data according to category centers and generate clustering results;

[0026] The classification module is used to classify the clustering results according to the genotype characteristics of SNPs and determine the genotype of the sample to be tested.

[0027] In some possible implementations, the method further includes: a collection module for collecting endpoint fluorescence intensity data of each channel for the SNP site; and preprocessing the endpoint fluorescence intensity data to generate sample data.

[0028] In a third aspect, an embodiment of the present invention provides an electronic device, comprising a memory and a processor, wherein the memory stores a computer program executable on the processor, and when the processor executes the computer program, the steps of any one of the methods described in the first aspect are implemented.

[0029] In a fourth aspect, an embodiment of the present invention provides a computer-readable storage medium, wherein the computer-readable storage medium stores machine-executable instructions. When the computer-executable instructions are called and executed by a processor, the computer-executable instructions cause the processor to execute any method described in the first aspect above.

[0030] The present invention provides a semi-supervised SNP typing method, device and electronic device based on a control group, the method comprising: determining a category center based on pre-collected sample data; the sample data comprises a control group sample and a sample to be tested; performing adaptive cluster analysis on the sample data according to the category center to generate a clustering result; classifying the clustering result according to the genotype characteristics of the SNP to determine the SNP typing of the sample to be tested. This method alleviates the technical problem of poor typing effect due to irregular distribution of genotype clusters, and achieves a technical effect of improving typing accuracy and being easy to implement. BRIEF DESCRIPTION OF THE DRAWINGS

[0031] In order to more clearly illustrate the specific implementation methods of the present invention or the technical solutions in the prior art, the drawings required for use in the specific implementation methods or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are some implementation methods of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0032] Figure 1 A schematic diagram of a process flow of a semi-supervised SNP typing method based on a control group provided in an embodiment of the present invention;

[0033] Figure 2 A schematic diagram of typing results of a semi-supervised SNP typing method based on a control group provided in an embodiment of the present invention;

[0034] Figure 3 A semi-supervised SN based on a control group provided in an embodiment of the present invention P A schematic diagram of the structure of the typing device;

[0035] Figure 4 A schematic diagram of the structure of an electronic device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0036] In order to make the purpose, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Generally, the components of the embodiments of the present invention described and shown in the drawings here can be arranged and designed in various different configurations.

[0037] Therefore, the following detailed description of the embodiments of the present invention provided in the accompanying drawings is not intended to limit the scope of the invention claimed for protection, but merely represents selected embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0038] It should be noted that similar reference numerals and letters represent similar items in the following drawings, so once an item is defined in one drawing, it does not need to be further defined and explained in the subsequent drawings. Some embodiments of the present invention are described in detail below in conjunction with the drawings. The following embodiments and features in the embodiments can be combined with each other without conflict.

[0039] SNP is single nucleotide polymorphism. Currently, a variety of typing detection technologies have been formed, including direct sequencing, amplification curve method, HRM (high-resolution melting curve analysis), etc. Among them, although the amplification curve method only targets 1-2 known sites, it is favored because of its simple operation, fast speed, high throughput, and easy interpretation of results. The amplification curve method usually adopts the endpoint method, that is, the fluorescence intensity data of each sample at the end of amplification of each allele is collected, and then the research is carried out based on this. Among them, the most commonly used analysis method is cluster analysis, but it is found through experiments that the irregularity of cluster distribution has a greater impact on the clustering results. If the cluster distribution is very irregular, the clustering effect is usually not very good. At this time, to achieve a good clustering effect, more labeled data is needed, and the more irregular the cluster distribution, the more labeled data is needed.

[0040] The labeled data is the control group, which usually includes blank control, negative control or positive control. In the SNP typing experiment, it is the blank control sample, homozygous control sample, and heterozygous control sample. In a specific experiment, one or several control samples may be included, and the number of samples in a control sample class is also uncertain. Because some sample types are already given, if the experiment meets expectations, these samples will present the specified genotype. How to make full use of the known control group data to classify the genotype of the final unknown sample is a conventional semi-supervised learning problem. However, if the experiment does not meet expectations, some samples may not present the specified genotype, that is, the final classification result is related to the experimental situation. At this time, it is a more special semi-supervised learning problem.

[0041] To this end, this scheme proposes a semi-supervised SNP typing method based on a control group. The main idea is to make full use of the control group information, calculate the initial class center with a control group, and determine other class centers based on the minimum distance maximum principle. Then, cluster analysis is performed based on the control group setting pattern related to the experiment to determine the genotype of the unknown sample, thereby alleviating the problem of poor typing effect in SNP typing due to irregular distribution of genotype clusters. It is easy to understand and easy to implement.

[0042] To facilitate understanding of this embodiment, firstly, a semi-supervised SNP typing method based on a control group disclosed in an embodiment of the present invention is described in detail, see Figure 1 The flowchart of a semi-supervised SNP typing method based on a control group is shown, and the method can be executed by an electronic device, and mainly includes the following steps S110 to S130:

[0043] S110: Determine the category center based on the sample data collected in advance; the sample data includes the control group sample and the sample to be tested;

[0044] The sample data is the pre-collected fluorescence intensity data of the real-time fluorescence quantitative PCR amplification endpoint of each channel. The category center is used to represent all category centers in the sample data group, including the first category center corresponding to the known category determined according to the control group and the second category center corresponding to the unknown category determined according to the minimum distance maximum principle.

[0045] S120: performing adaptive clustering analysis on the sample data according to the category center to generate a clustering result;

[0046] S130: Classify the clustering results according to the genotype characteristics of the SNPs to determine the genotype of the sample to be tested.

[0047] The present invention provides a semi-supervised SNP typing method based on a control group, the method comprising: determining a category center based on pre-collected sample data; the sample data comprises a control group sample and a sample to be tested; performing adaptive clustering analysis on the sample data according to the category center to generate a clustering result; and classifying the clustering result according to the genotype characteristics of the SNP to determine the SNP typing of the sample to be tested. This method alleviates the technical problem of poor typing effect due to irregular distribution of genotype clusters, and achieves a technical effect of improving typing accuracy and being easy to implement.

[0048] In one embodiment, before the above step S110, the method further includes:

[0049] S21: Collecting the endpoint fluorescence intensity data of each channel for the SNP site;

[0050] S22: Preprocess the endpoint fluorescence intensity data to generate sample data.

[0051] In the embodiment of the present invention, the endpoint fluorescence intensity data of real-time fluorescence quantitative PCR amplification of each channel is collected. Before determining the endpoint fluorescence intensity, the influence of the baseline, crosstalk between channels, and inter-well error should be removed. Preprocessing the endpoint fluorescence intensity data also includes normalization, using overall normalization, that is, first determining the maximum endpoint fluorescence intensity and the minimum endpoint fluorescence intensity in all channels, and then using the maximum and minimum normalization method.

[0052] In one embodiment, the above step S110 includes:

[0053] S31: Based on the sample data collected in advance, determine the known categories of the control group samples; the known categories of the control group samples include: blank samples, homozygotes, and heterozygotes;

[0054] S32: Determine the center of the first category based on the known categories of the control group samples.

[0055] In the embodiment of the present invention, the initial center of each category in the control group (i.e., the center of the first category) is first calculated. Dual channels are the basis of SNP typing. For multi-channel situations, dual channel analysis can be performed on any two channels. Taking the heterozygous control group as an example, assuming that there are n known heterozygous control samples, the end-point fluorescence intensities of channels 1 and 2 corresponding to sample i are (X i1 , X i2 ), then the initial center of this category (X 1 , X 2 )for:

[0056]

[0057] Similarly, determine the first category center of other known categories.

[0058] In one embodiment, the above step S110 further includes:

[0059] Determine the number of unknown categories based on pre-collected sample data and a predetermined total number of categories;

[0060] Based on the minimum distance maximum principle, the second category center of the unknown category is determined.

[0061] In the embodiment of the present invention, assuming that the number of known control group categories is m, the total number of categories M≥m, and the possible genotypes include blank sample, homozygote 1, homozygote 2, heterozygote, that is, 4 types, and in addition, 1-2 types of unknown types can be added according to the number of samples. In order to find the optimal classification result, cluster analysis is performed in turn with the number of categories C=m,...,6 (C is a positive integer), and then selection is made according to certain evaluation indicators.

[0062] Assume that there are 3 known category initial centers. If C=3, then all initial category centers have been determined. If C>3, taking C=4 as an example, a category center needs to be determined in addition to the 3 known initial category centers. The selection is based on the minimum distance maximum principle, that is, the shortest distance between each sample and the 3 initial category centers is calculated, and then the shortest distances of all samples are compared. If a sample has the largest shortest distance, then the position of the sample is the 4th initial clustering center. And so on, determine the other initial clustering centers.

[0063] In one embodiment, the above step S120 includes: performing adaptive clustering analysis on the sample data according to the first category center and the second category center in combination with a predetermined setting mode to generate an optimal clustering result.

[0064] The predetermined setting mode includes allowing changes and not allowing changes;

[0065] When the setting mode of the control group is to allow changes, the categories to which each sample in the control group belongs are allowed to be changed during clustering; when the setting mode of the control group is to not allow changes, the categories to which each sample in the control group belongs are not allowed to be changed during clustering.

[0066] In an embodiment of the present invention, according to whether the category to which each sample of the control group belongs is allowed to be changed during clustering, the setting mode of the control group is divided into two types: one is "allowed" and the other is "not allowed". The setting mode of the above-mentioned control group can be determined according to the experimental situation. If the artificial criterion of the fluorescence intensity at the endpoint of each channel of each known control group in the experiment meets expectations, the setting mode can be set to "not allowed"; if the artificial criterion of the fluorescence intensity at the endpoint of each channel of each known control group in the experiment does not meet expectations, and it is a problem of the experimental process, method, consumables, etc., the experiment should be repeated in a safe manner, but if it is due to other factors, such as unknown mutations, the setting mode can also be cautiously set to "allowed", that is, the genotype of each sample in the control group can be changed during the clustering process.

[0067] In an embodiment of the present invention, in the above-mentioned optimization stage, when the control setting mode is set to allow, the sampling clustering analysis tool k-means can be used for clustering, that is, the distance between each sample and each cluster center is calculated, and each sample is assigned to the cluster center closest to it, and then iterated continuously until the final termination condition is met, such as the number of iterations reaches the specified number, the cluster center no longer changes, or the sum of squared distances is minimized.

[0068] When the control group setting mode is set to not allowed, after calculating the new cluster center, there is no need to recalculate the distance between the control group sample and each center, that is, each control group sample is still classified into the category to which it belongs. For other samples, they are reclassified according to the shortest distance between the sample and each cluster center.

[0069] The silhouette coefficient is used as the evaluation index. Since the number of optional categories C = m, ..., 6 (C is a positive integer) is selected when performing cluster analysis, cluster analysis is performed in sequence, and the clustering result with the highest silhouette coefficient is selected.

[0070] According to the biological characteristics of each genotype, when it is homozygous, the end point fluorescence intensity of one channel will be significantly larger than that of other channels, that is, close to the coordinate axis corresponding to the channel. When it is heterozygous, the end point fluorescence intensity of two channels will be closer, that is, close to the interface of two orthogonal coordinate axes. For this reason, the cluster centers are comprehensively examined. When a cluster center is close to a coordinate axis, it is a homozygous channel corresponding to the coordinate axis, otherwise it is a heterozygous.

[0071] As a specific example, the Biori Fluorescence Quantitative PCR Detection System was used to perform PCR amplification experiments on multiple template reagents, and the above method was used for SNP typing. Here, one of the SNP loci has two allele data as an example, and the contour coefficient threshold is set to 0.90. There are 17 samples in total, of which there are 8 known control groups, including 2 samples in the blank control group, homozygous 1 control group, homozygous 2 control group and heterozygous control group, and the remaining 9 samples are samples of unknown types. The experimental results were judged by experts, and the genotypes of the control groups were all in line with expectations. Set the control group setting mode to "Not Allowed".

[0072] According to the above steps, due to the small number of samples, we took C = 4, 5 and analyzed them in turn. It was found that when C = 4, the silhouette coefficient was higher, 0.99. The clustering result was taken as follows: Figure 2 For comparison, we can artificially change the genotypes of several control groups. If the control group mode is set to "not allowed", most samples are defined as unknown samples because of their low individual silhouette coefficients, and the overall silhouette coefficient is <0.5, which obviously does not meet the requirements. On the contrary, if the control group mode is set to "allowed", although the initial set cluster center is wrong, after iterative optimization, it can finally reach Figure 2 That is, without considering other factors and simply looking at the clustering effect, setting the control group mode to “allow” has better robustness.

[0073] The present invention provides a semi-supervised SNP typing method based on a control group, the method comprising: determining the category center of the control group sample based on pre-collected sample data; the sample data comprises the control group sample and the sample to be tested; performing adaptive clustering analysis on the sample data according to the category center of the control group sample to generate clustering results; classifying the clustering results according to the genotype characteristics of the SNP to determine the SNP typing of the sample to be tested. This method alleviates the technical problem of poor typing effect due to irregular distribution of genotype clusters, and achieves the technical effect of improving typing accuracy and being easy to implement.

[0074] The embodiment of the present invention provides a semi-supervised SNP typing device based on a control group, see Figure 3 , the device comprises:

[0075] The category center determination module 310 is used to determine the category center based on the sample data collected in advance; the sample data includes the control group samples and the samples to be tested;

[0076] The cluster analysis module 320 is used to perform adaptive cluster analysis on the sample data according to the category center and generate cluster results;

[0077] The classification module 330 is used to classify the clustering results according to the genotype characteristics of the SNPs and determine the genotype of the sample to be tested.

[0078] In one embodiment, the above-mentioned device further includes: a collection module for collecting endpoint fluorescence intensity data of each channel for the SNP site; and preprocessing the endpoint fluorescence intensity data to generate sample data.

[0079] The semi-supervised SNP typing device based on the control group provided in the embodiment of the present application can be specific hardware on the device or software or firmware installed on the device. The device provided in the embodiment of the present application has the same implementation principle and technical effects as the aforementioned method embodiment. For the sake of brief description, the parts not mentioned in the device embodiment can refer to the corresponding contents in the aforementioned method embodiment. Technical personnel in the relevant field can clearly understand that for the convenience and simplicity of description, the specific working processes of the systems, devices and units described above can all refer to the corresponding processes in the aforementioned method embodiments, which will not be repeated here. The semi-supervised SNP typing device based on the control group provided in the embodiment of the present application P The typing device has the same technical features as the semi-supervised SNP typing method based on the control group provided in the above embodiment, so it can also solve the same technical problems and achieve the same technical effects.

[0080] An embodiment of the present application further provides an electronic device. Specifically, the electronic device includes a processor and a storage device. The storage device stores a computer program, and when the computer program is executed by the processor, it executes the method described in any one of the above-mentioned embodiments.

[0081] Figure 4 A structural schematic diagram of an electronic device provided in an embodiment of the present application, the electronic device 400 includes: a processor 40, a memory 41, a bus 42 and a communication interface 43, wherein the processor 40, the communication interface 43 and the memory 41 are connected via the bus 42; the processor 40 is used to execute an executable module stored in the memory 41, such as a computer program.

[0082] The memory 41 may include a high-speed random access memory (RAM), and may also include a non-volatile memory, such as at least one disk memory. The communication connection between the system network element and at least one other network element is realized through at least one communication interface 43 (which may be wired or wireless), and the Internet, wide area network, local area network, metropolitan area network, etc. may be used.

[0083] The bus 42 may be an ISA bus, a PCI bus, or an EISA bus, etc. The bus may be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Figure 4 Only one bidirectional arrow is used in the diagram, but this does not mean that there is only one bus or only one type of bus.

[0084] Among them, the memory 41 is used to store programs, and the processor 40 executes the program after receiving the execution instruction. The method executed by the device for flow process definition disclosed in any embodiment of the above-mentioned embodiment of the present invention can be applied to the processor 40 or implemented by the processor 40.

[0085] The processor 40 may be an integrated circuit chip with signal processing capabilities. In the implementation process, each step of the above method can be completed by the hardware integrated logic circuit or software instructions in the processor 40. The above processor 40 can be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc.; it can also be a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA), or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components. The methods, steps and logic block diagrams disclosed in the embodiments of the present invention can be implemented or executed. The general-purpose processor can be a microprocessor or the processor can also be any conventional processor. The steps of the method disclosed in the embodiments of the present invention can be directly embodied as a hardware decoding processor to execute, or can be executed by a combination of hardware and software modules in the decoding processor. The software module can be located in a mature storage medium in the field such as a random access memory, a flash memory, a read-only memory, a programmable read-only memory, or an electrically erasable programmable memory, a register, etc. The storage medium is located in the memory 41, and the processor 40 reads the information in the memory 41 and completes the steps of the above method in combination with its hardware.

[0086] Corresponding to the above method, an embodiment of the present application also provides a computer-readable storage medium, which stores machine-executable instructions. When the computer-executable instructions are called and executed by a processor, the computer-executable instructions prompt the processor to execute the steps of the above method.

[0087] In the embodiments provided in the present application, it should be understood that the disclosed devices and methods can be implemented in other ways. The device embodiments described above are merely schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some communication interfaces, and the indirect coupling or communication connection of the devices or units can be electrical, mechanical or other forms.

[0088] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0089] In addition, each functional unit in the embodiments provided in the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0090] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or the part of the technical solution, can be embodied in the form of a software product, which is stored in a storage medium and includes several instructions for enabling a computer device (which can be a personal computer, electronic device, or network device, etc.) to perform all or part of the steps of the methods described in each embodiment of the present invention. 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.

[0091] It should be noted that similar numbers and letters represent similar items in the accompanying drawings. Therefore, once an item is defined in one drawing, it does not need to be further defined and explained in subsequent drawings. In addition, the terms "first", "second", "third", etc. are only used to distinguish the description and cannot be understood as indicating or implying relative importance.

[0092] 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 it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or replace some or all of the technical features therein with equivalents. However, these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present invention.

Claims

1. A semi-supervised SNP typing method based on a control group, characterized in that: include: Determine the category center based on pre-collected sample data; The sample data includes control group samples and samples to be tested; Among them, based on the pre-collected sample data, determining the category center includes: Based on the sample data collected in advance, the known categories of the control group samples are determined; the known categories of the control group samples include: blank samples, homozygotes, and heterozygotes; according to the known categories of the control group samples, the first category center is determined; Based on the pre-collected sample data and the predetermined total number of categories, the number of unknown categories is determined; based on the minimum distance maximum principle, the second category center of the unknown category is determined; According to the first category center and the second category center, in combination with a predetermined setting mode, the sample data is adaptively clustered to generate an optimal clustering result; the setting mode includes allowing changes and not allowing changes; when the setting mode of the control group is allowing changes, the category to which each sample in the control group belongs is allowed to be changed when clustering; when the setting mode of the control group is not allowing changes, the category to which each sample in the control group belongs is not allowed to be changed when clustering; The clustering results are classified according to the genotype characteristics of the SNPs to determine the genotype of the sample to be tested.

2. The method according to claim 1, characterized in that Before the step of determining the category center based on the pre-collected sample data, the method further includes: Collect the endpoint fluorescence intensity data of each channel for the SNP site; The endpoint fluorescence intensity data is preprocessed to generate sample data.

3. A semi-supervised SNP typing device based on a control group, characterized in that: include: A category center determination module, used to determine the category center based on pre-collected sample data; The sample data includes control group samples and samples to be tested; wherein, based on the pre-collected sample data, determining the category center includes: Based on the sample data collected in advance, the known categories of the control group samples are determined; the known categories of the control group samples include: blank samples, homozygotes, and heterozygotes; according to the known categories of the control group samples, the first category center is determined; Based on the pre-collected sample data and the predetermined total number of categories, the number of unknown categories is determined; based on the minimum distance maximum principle, the second category center of the unknown category is determined; a cluster analysis module is used to perform adaptive cluster analysis on the sample data according to the first category center and the second category center in combination with a predetermined setting mode to generate an optimal clustering result; the setting mode includes allowing changes and not allowing changes; when the setting mode of the control group is allowing changes, the category to which each sample in the control group belongs is allowed to be changed when clustering; when the setting mode of the control group is not allowing changes, the category to which each sample in the control group belongs is not allowed to be changed when clustering; The classification module is used to classify the clustering results according to the genotype characteristics of the SNP and determine the genotype of the sample to be tested.

4. The device according to claim 3, characterized in that Also includes: An acquisition module is used to collect the endpoint fluorescence intensity data of each channel for the SNP site; The endpoint fluorescence intensity data is preprocessed to generate sample data.

5. An electronic device comprising a memory and a processor, wherein the memory stores a computer program that can be run on the processor, characterized in that: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 2 are implemented.

6. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores machine executable instructions. When the computer-executable instructions are called and executed by a processor, the computer-executable instructions prompt the processor to execute the method according to any one of claims 1 to 2.

Images