Single cell barcode identification method based on SNP polymorphism

Abstract

The application relates to the technical field of bioinformatics, and discloses a single-cell barcode identity recognition method based on SNP polymorphism, a plurality of high-variation SNP sites based on population genetics analysis are selected; a genomic data integration method is used to optimize the selection of the SNP sites, so as to ensure the uniqueness of the barcode; a machine learning algorithm is used to filter noise of the barcode of a low-abundance cell, and the recognition sensitivity is improved; in combination with the phenotype information of the cell, a multi-dimensional data fusion analysis technology is used to improve the diversity and accuracy of the barcode; redundant information is added in the barcode sequence, the stability of the barcode is enhanced, and barcode loss is avoided. Through the combination of multiple SNP sites and the selection of high-variation SNP sites, the barcode of each cell has high specificity and stability, and the recognition rate of the low-abundance cell is improved through the machine learning algorithm, especially in a complex sample, accurate recognition can be realized, and the occurrence of false positives and false negatives is reduced.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of bioinformatics, in particular to a single-cell barcode identification method based on SNP polymorphism. BACKGROUND

[0002] The single-cell barcode identification method based on SNP (single nucleotide polymorphism) polymorphism is a technology that uses genetic markers (SNPs) within cells to efficiently identify individual cells. In this method, each cell's genome produces a unique "barcode" through specific SNP sites. These SNP markers are individual-specific, so they can be used to distinguish different individual cells. Through high-throughput sequencing technology, researchers can obtain sequence information of these SNP sites at the single-cell level and accurately identify the identity of each cell through computational analysis. This method not only accurately tracks and labels individual cells, but also enables the analysis of cell population diversity, which is of great significance for single-cell transcriptomics, genomics, and other research.

[0003] The SNP-based single-cell barcode identification method, although having high resolution and specificity, still has some drawbacks in the prior art: SNP site selection limitations: SNP markers rely on specific genetic loci, however, in different individuals or different species, the number of SNP sites suitable for barcode is limited. For some populations, the diversity of SNP sites may not be sufficient, resulting in reduced identification accuracy or difficulty in distinguishing very similar cells; High cost and high throughput demand: SNP-based barcode identification methods usually require large-scale genome sequencing, involving high costs, especially when high-throughput sequencing is performed at the single-cell level. The genomic information of each cell needs to be accurately extracted and analyzed, which requires high equipment and technical requirements, resulting in increased overall cost; Sample processing and data complexity: Single-cell sequencing is usually accompanied by high background noise, especially in low-abundance samples, which can lead to loss or misidentification of some SNP information. In addition, single-cell barcode identification involves a large amount of data analysis, requiring powerful computing resources and algorithm support, and the data processing process is complex and prone to errors; Sensitivity issues of SNP detection: For some SNP sites, especially in cells with low expression or low gene copy number, the detection sensitivity may not be sufficient, resulting in the barcode of these cells being unable to be accurately identified. Different SNP sites may have different mutation frequencies, and some SNP sites may have low mutation frequencies, which may not be stably detected in large-scale single-cell sequencing; Challenges of cell heterogeneity: Genetic heterogeneity at the single-cell level can cause similar SNP variations to occur in different cells, resulting in cross-identification or mislabeling between "barcodes". Especially in highly heterogeneous cell populations, the genetic differences between cells are small, which can make it difficult to accurately distinguish; Time-consuming: In performing SNP-based identification, a series of experimental and data processing steps are required to extract and analyze the genetic information of each single cell. For large-scale single-cell analysis, the entire process can consume a long time, reducing overall experimental efficiency; Dependence on specific reference genomes: This method usually requires the use of existing reference genomes to select SNP sites, and for some species that are not fully annotated or lack reference genomes, SNP-based barcode identification methods may not be effectively applied, limiting their universality.

[0004] To this end, we propose a SNP-based single-cell barcode identification method. SUMMARY

[0005] To achieve the above purpose, the present application provides the following technical scheme: A SNP-based single-cell barcode identification method, comprising the following steps:

[0006] S1: Select a plurality of high-variation SNP sites based on population genetics analysis;

[0007] S2: Optimize SNP site selection using genomic data integration methods to ensure barcode uniqueness;

[0008] S3: Use machine learning algorithms to filter noise from low-abundance cell barcodes, improving recognition sensitivity;

[0009] S4: Combine cell phenotype information and use multi-dimensional data fusion analysis techniques to improve barcode diversity and accuracy;

[0010] S5: Add redundant information to barcode sequences to enhance barcode stability and prevent barcode loss;

[0011] S6: Decode barcode data using deep learning algorithms to ensure recognition accuracy.

[0012] Preferably, the SNP site selection is based on genetic diversity analysis and population variation evaluation based on whole genome data, and the selected SNP site includes at least 10 high-variation sites.

[0013] Preferably, the low-abundance cell recognition algorithm uses a support vector machine (SVM) or convolutional neural network (CNN) model to further improve the recognition sensitivity of low-abundance cells.

[0014] Preferably, the redundant information enhances the stability of the barcode by short sequence splicing or repeated sequence insertion, and the design of the redundant information ensures that the barcode is not lost during high-throughput sequencing.

[0015] Preferably, the data fusion analysis uses statistical learning methods to combine cell morphology, functional characteristics, and marker expression information to further enhance barcode diversity and accuracy.

[0016] Preferably, the data decoding is achieved through a deep learning network or other efficient computing models, and the decoding process further optimizes the recognition accuracy of barcode information.

[0017] Preferably, the SNP site selection further includes the spanning range of gene segments to ensure that the selected SNP sites are widely distributed in different gene regions, increasing the diversity of cell barcodes.

[0018] Preferably, during the decoding process of the barcode data, the influence of low-variation regions on barcode information is optimized by combining population variation data to further improve accuracy.

[0019] Preferably, the SNP site selection strategy further comprises analyzing the variation degree among populations by population genetic diversity evaluation, and selecting the SNP site combination with the largest variation degree.

[0020] Compared with the prior art, the present application provides a single cell barcode identity recognition method based on SNP polymorphism, which has the following beneficial effects:

[0021] 1. The single cell barcode identity recognition method based on SNP polymorphism ensures that the barcode of each cell has high specificity and stability through the selection of multiple SNP site combinations and high variation SNP sites, and improves the recognition rate of low abundance cells through machine learning algorithm, especially in complex samples, which can accurately identify and reduce the occurrence of false positives and false negatives.

[0022] 2. The single cell barcode identity recognition method based on SNP polymorphism can be applied to different species and individual populations by using genome data integration and genetic diversity analysis strategy, has strong universality, can meet different research needs, avoids the problems of barcode loss or mismatch in traditional methods by introducing redundant information, improves the stability and reliability of barcode, especially in high-throughput sequencing process.

[0023] 3. The single cell barcode identity recognition method based on SNP polymorphism can more accurately identify and classify cells by fusing the phenotype data of cells, further improves the diversity and accuracy of the method, reduces the cost of high-throughput sequencing by optimizing the selection of SNP sites and efficient data decoding method, and improves the data processing efficiency, which is suitable for large-scale single cell analysis. DETAILED DESCRIPTION

[0024] The technical solutions in the embodiments of the present application will be described below. Obviously, the described embodiments are only part of the embodiments of the present application, not all. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor are within the scope of protection of the present application.

[0025] EMBODIMENT

[0026] An embodiment of a single cell barcode identity recognition method based on SNP polymorphism

[0027] A single cell barcode identity recognition method based on SNP polymorphism comprises the following steps:

[0028] S1: Select a plurality of high-variation SNP sites based on population genetics analysis;

[0029] S2: Optimize SNP site selection using genomic data integration methods to ensure barcode uniqueness;

[0030] S3: Use machine learning algorithms to filter noise from low-abundance cell barcodes, improving recognition sensitivity;

[0031] S4: Combine cell phenotype information and use multi-dimensional data fusion analysis techniques to improve barcode diversity and accuracy;

[0032] S5: Add redundant information to barcode sequences to enhance barcode stability and prevent barcode loss;

[0033] S6: Decode barcode data using deep learning algorithms to ensure accurate recognition.

[0034] Specifically, SNP site selection is based on genetic diversity analysis and population variation evaluation based on whole genome data. The selected SNP sites include at least 10 high-variation sites.

[0035] Specifically, the low-abundance cell recognition algorithm uses a support vector machine (SVM) or convolutional neural network (CNN) model to further improve the recognition sensitivity of low-abundance cells.

[0036] Specifically, redundant information enhances barcode stability through short sequence splicing or repeated sequence insertion. The design of the redundant information ensures that the barcode is not lost during high-throughput sequencing.

[0037] Specifically, data fusion analysis uses statistical learning methods to combine cell morphology, functional characteristics, and marker expression information to further enhance barcode diversity and accuracy.

[0038] Specifically, data decoding is achieved through deep learning networks or other efficient computing models, and the decoding process further optimizes the recognition accuracy of barcode information.

[0039] Specifically, SNP site selection further includes the spanning range of gene segments to ensure that the selected SNP sites are widely distributed in different gene regions, increasing the diversity of cell barcodes.

[0040] Specifically, during the decoding process of barcode data, population variation data is combined to optimize the influence of low-variation regions on barcode information, further improving accuracy.

[0041] Specifically, the SNP site selection strategy further includes analyzing the variation degree among populations through population genetic diversity evaluation, and selecting a combination of SNP sites with the largest variation degree.

[0042] Through the above technical solutions, in the present application, by selecting multiple SNP site combinations and high-variation SNP sites, the barcodes of each cell have high specificity and stability, and the recognition rate of low-abundance cells is improved through machine learning algorithms, especially in complex samples, accurate identification and reduction of false positives and false negatives can be achieved, through the use of genomic data integration and genetic diversity analysis strategies, the method can be applied to different species and populations, has strong versatility, can meet different research needs, through the introduction of redundant information, the problems of barcode loss or mismatch in traditional methods are avoided, the stability and reliability of the barcode are improved, especially in high-throughput sequencing, by fusing the phenotype data of cells, more accurate identity recognition and classification analysis of cells can be achieved, further improving the diversity and accuracy of the method, through optimized SNP site selection and efficient data decoding method, the cost of high-throughput sequencing is reduced, and the data processing efficiency is also improved, suitable for large-scale single cell analysis.

[0043] SNP site selection and optimization

[0044] SNP site selection:

[0045] A set of high-variation SNP sites is obtained from the human genome database (such as 1000 Genomes Project). Using genomic variation analysis method, through population genetics analysis, the variation frequency of each site in the target population is calculated. At least 10 high-variation SNP sites are selected, which have high variation rate in different individuals and are distributed across multiple gene regions to ensure the uniqueness and reliability of cell barcode.

[0046] SNP site optimization and data integration:

[0047] Using genomic data integration method, data from different individuals or species is integrated, and gene region spanning analysis is applied to optimize SNP site selection. This strategy ensures that the selected SNP sites not only work in a specific species or population, but also have the same diversity effect in different backgrounds. Through this method, the adaptability of the barcode in different samples is improved.

[0048] Low-abundance cell recognition and data denoising

[0049] Low-abundance cell recognition algorithm:

[0050] Deep learning algorithms such as Support Vector Machine (SVM) or Convolutional Neural Network (CNN) are used to analyze high-throughput sequencing data. By training on sample data of low-abundance cells, the model can identify and remove background noise, especially when the number of cells is small or in complex samples, the machine learning model can effectively enhance the recognition sensitivity of low-abundance cells.

[0051] De-noising and accuracy improvement:

[0052] Through training samples, the model can identify the unique pattern of each cell barcode. This algorithm not only removes background noise in the data, but also optimizes the matching of cell barcodes, avoiding misjudgment of low-abundance cells. Finally, through high-precision recognition, the genetic markers of each cell can be accurately restored.

[0053] Redundant barcode design

[0054] Redundant information added:

[0055] To ensure the stability of the barcode and prevent loss, short sequence splicing or repeated sequence insertion techniques are used to add redundant information in each barcode. These redundant information ensures that even if some SNP sites cannot be read correctly, the complete barcode information can still be supplemented by other redundant sites.

[0056] Redundancy enhancement effect:

[0057] Through this redundancy design, even if there is data loss or sequencing error in high-throughput sequencing, the stability and accuracy of the barcode information can be ensured, thereby greatly reducing the problem of barcode loss caused by sequencing errors.

[0058] Multi-dimensional data fusion analysis

[0059] Integration of cell phenotype data:

[0060] Based on SNP data, further combine cell phenotype information (such as morphology, functional characteristics, marker expression, etc.), use multi-dimensional data fusion analysis technology, and enhance the diversity of each cell barcode. Through comprehensive analysis of cell functional characteristics, combined with SNP variation information, further improve the accuracy of cell recognition.

[0061] Algorithm optimization of data fusion:

[0062] Statistical learning methods (such as Principal Component Analysis (PCA), correlation analysis, etc.) are used to fuse cell phenotype data and genomic data, so that in the analysis process, the phenotype characteristics and genetic information of the cells can jointly act on the generation and recognition of the barcode, improving the reliability of the results.

[0063] Data decoding and identification

[0064] Deep learning decoding:

[0065] Using deep learning networks such as convolutional neural networks (CNN) or long short-term memory networks (LSTM) to decode single-cell barcode data. Through neural network model pattern recognition of barcodes, accurately restore the identity of each cell.

[0066] Population variation analysis combined:

[0067] In the decoding process, combined with population variation data, the influence of low variation area is optimized and adjusted. By combining population genetic data, the interference of low-frequency variation between cells can be further excluded, ensuring the accuracy and stability of barcode decoding.

[0068] Application verification

[0069] Verification and experiment:

[0070] Experimental verification of selected SNP sites and designed barcode schemes, processing single-cell samples through high-throughput sequencing. The experimental results show that the single-cell barcode generated by this method can efficiently and accurately identify each cell, and is significantly superior to traditional methods in diversity and sensitivity.

[0071] Sample applicability:

[0072] This method can be applied to a variety of sample types, including human, animal, plant and microbial species, etc. In different species of cell populations, the use of the present method can effectively generate high specificity and high diversity barcode, with strong universality.

[0073] Although embodiments of the present application have been shown and described, it will be understood by those of ordinary skill in the art that various changes, modifications, substitutions and variations can be made to these embodiments without departing from the principles and spirit of the present application, and the scope of the present application is defined by the appended claims and their equivalents.

Claims

1. A single-cell barcode identity recognition method based on SNP polymorphism, characterized in that: Includes the following steps: S1: Select multiple highly variable SNP sites based on population genetics analysis; S2: Employ genomic data integration methods to optimize the selection of SNP sites to ensure the uniqueness of barcodes; S3: Utilize machine learning algorithms to filter noise from the barcodes of low-abundance cells, thereby improving recognition sensitivity; S4: Combining cell phenotypic information with multi-dimensional data fusion analysis technology to improve the diversity and accuracy of barcodes; S5: Add redundant information to the barcode sequence to enhance barcode stability and prevent barcode loss; S6: The barcode data is decoded using a deep learning algorithm to ensure accurate recognition.

2. The single-cell barcode identity recognition method based on SNP polymorphism according to claim 1, characterized in that: The selection of SNP sites is based on genetic diversity analysis and population variation assessment of whole genome data, and the selected SNP sites include at least 10 highly variable sites.

3. The single-cell barcode identity recognition method based on SNP polymorphism according to claim 1, characterized in that: The low-abundance cell identification algorithm employs a support vector machine (SVM) or convolutional neural network (CNN) model, which further improves the sensitivity of low-abundance cell identification.

4. The single-cell barcode identity recognition method based on SNP polymorphism according to claim 1, characterized in that: The redundant information enhances the stability of the barcode by splicing short sequences or inserting repetitive sequences, and the design of the redundant information ensures that the barcode is not lost during high-throughput sequencing.

5. The single-cell barcode identity recognition method based on SNP polymorphism according to claim 1, characterized in that: The data fusion analysis employs statistical learning methods, combining cell morphology, functional characteristics, and biomarker expression information to further enhance the diversity and accuracy of barcodes.

6. The single-cell barcode identity recognition method based on SNP polymorphism according to claim 1, characterized in that: Data decoding is achieved through deep learning networks or other efficient computing models, and the decoding process further optimizes the recognition accuracy of barcode information.

7. The single-cell barcode identity recognition method based on SNP polymorphism according to claim 1, characterized in that: The selection criteria for SNP sites further include the range of gene segments they span, ensuring that the selected SNP sites are widely distributed across different gene regions, thereby increasing the diversity of cell barcodes.

8. The single-cell barcode identity recognition method based on SNP polymorphism according to claim 1, characterized in that: During the decoding process of the barcode data, the impact of low-variation regions on barcode information is optimized by combining population mutation data, thereby further improving accuracy.

9. The single-cell barcode identity recognition method based on SNP polymorphism according to claim 1, characterized in that: The SNP site selection strategy further includes analyzing the variability among populations through population genetic diversity assessment and selecting the combination of SNP sites with the highest variability.