Gene sequencing data analysis method and apparatus, computing device and readable storage medium

Abstract

The embodiments of the present application belong to the field of data processing. Provided are a gene sequencing data analysis method and apparatus, a computing device and a readable storage medium. The gene sequencing data analysis method is applied to a user equipment. The gene sequencing data analysis method comprises: encoding gene sequencing data of a user to obtain a plurality of gene sequencing plaintexts corresponding to the gene sequencing data (S110); using a public key to encrypt each of the gene sequencing plaintexts to obtain a plurality of gene sequencing ciphertexts (S120); sending the gene sequencing ciphertexts to a server (S130); receiving a gene sequencing data analysis result ciphertext sent by the server (S140); and using a private key to decrypt the gene sequencing data analysis result ciphertext to determine a gene sequencing data analysis result of the user (S150). The user equipment sends the plurality of encrypted gene sequencing ciphertexts to the server, thereby avoiding leakage of user privacy. The server uses a preset sparse model to perform data analysis and process the gene sequencing ciphertexts to be tested, thereby improving the gene sequencing data analysis efficiency.

Description

Gene sequencing data analysis method, device, computing device and readable storage medium

[0001] CROSS-REFERENCE TO RELATED APPLICATIONS

[0002] This application claims the benefit of Chinese patent application No. 202410385100.4 filed on March 29, 2024, the contents of which are incorporated herein by reference. Technical Field

[0003] The embodiments of the present application relate to the field of data processing, and specifically to a gene sequencing data analysis method, apparatus, computing device, and readable storage medium. Background Art

[0004] With the rapid advancement of medical diagnostic technology, remote diagnosis has become widely used. Users can use their devices to send personal information, including genetic sequencing data, to remote diagnostic equipment. The remote diagnostic equipment analyzes the received genetic sequencing data and returns the results to the user device. The user receives the results through the user device and determines whether they have a specific disease, preventing them from missing the best treatment opportunities.

[0005] When local medical institutions are unable to accurately analyze a user's medical condition, remote diagnostic equipment can be used to remotely analyze the user's genetic sequencing data to determine whether the user has a disease, thereby improving the efficiency of analyzing and processing genetic sequencing data. However, remote analysis of genetic sequencing data requires the user to provide a large amount of medical information, such as the genetic sequencing data to be analyzed and processed, and send this medical information to the remote diagnostic equipment, which can easily lead to the leakage of the user's medical information. In addition, when the remote diagnostic equipment returns the analysis results of the genetic sequencing data, the analysis results are also prone to leakage, making it easy to leak user privacy when conducting remote analysis of genetic sequencing data. Summary of the Invention

[0006] The purpose of the embodiments of the present application is to provide a gene sequencing data analysis method, apparatus, computing device, and readable storage medium. The gene sequencing data analysis method is used to solve the problem of user privacy being easily leaked during remote analysis of gene sequencing data.

[0007] To achieve the above objectives, in a first aspect, the present application provides a gene sequencing data analysis method, which is applied to a user device. The gene sequencing data analysis method includes:

[0008] Encode the user's gene sequencing data to obtain multiple gene sequencing plaintexts corresponding to the gene sequencing data;

[0009] Use the public key to encrypt each gene sequencing plaintext separately to obtain multiple gene sequencing ciphertexts;

[0010] Sending the gene sequencing ciphertext to the server, wherein the server is used to input the gene sequencing ciphertext into a preset sparse model to obtain the gene sequencing data analysis result ciphertext;

[0011] Receive the encrypted gene sequencing data analysis results sent by the server;

[0012] The private key is used to decrypt the ciphertext of the gene sequencing data analysis results to determine the user's gene sequencing data analysis results.

[0013] In an embodiment of the present application, the gene sequencing data analysis method further includes:

[0014] Generate security parameters based on the degree of the homomorphic encryption ciphertext polynomial and the number of bits of the ciphertext modulus;

[0015] Generate public and private keys based on security parameters.

[0016] In an embodiment of the present application, the user's gene sequencing data is encoded to obtain multiple gene sequencing plaintexts corresponding to the gene sequencing data, including:

[0017] According to the degree of the ciphertext polynomial, the encoding dimension corresponding to each gene sequencing ciphertext is determined;

[0018] Based on the encoding dimension and the dimension of the user's gene sequencing data, the gene sequencing data is encoded to obtain multiple gene sequencing plaintexts.

[0019] In an embodiment of the present application, the gene sequencing data analysis method further includes:

[0020] When the dimension of the gene sequencing plaintext is smaller than the encoding dimension, data padding is performed on the gene sequencing plaintext until the dimension of the gene sequencing plaintext is equal to the encoding dimension.

[0021] In an embodiment of the present application, the dimension of the model parameters of the preset sparse model is equal to the dimension of the gene sequencing data, and the model parameters include model sub-parameters corresponding to each gene sequencing plaintext;

[0022] The preset sparse model is used to obtain multiple result ciphertexts according to the model sub-parameters and the gene sequencing ciphertext, and the multiple result ciphertexts are summed to obtain the gene sequencing data analysis result ciphertext.

[0023] In the embodiment of the present application, the private key is used to decrypt the ciphertext of the gene sequencing data analysis result to determine the user's gene sequencing data analysis result, including:

[0024] Decrypting the ciphertext of the gene sequencing data analysis result using the private key to obtain a plaintext vector corresponding to the gene sequencing data analysis result, wherein the plaintext vector includes multiple components;

[0025] Get any component in the plaintext vector;

[0026] When the value of the component is positive, it is determined that the analysis result of the user's gene sequencing data is abnormal;

[0027] When the value of the component is negative, it is determined that the analysis result of the user's gene sequencing data is that there is no abnormality in the gene sequencing data.

[0028] In an embodiment of the present application, the gene sequencing data analysis method further includes:

[0029] Generate user data analysis and processing documents based on the user's gene sequencing data analysis results;

[0030] Convert the data analysis and processing documents into a QR code image and generate a display interface for the QR code image.

[0031] In a second aspect, the present application provides a gene sequencing data analysis method, which is applied to a server. The gene sequencing data analysis method includes:

[0032] Receive multiple gene sequencing ciphertexts sent by a user device;

[0033] Inputting multiple gene sequencing ciphertexts into a preset sparse model to obtain a gene sequencing data analysis result ciphertext, wherein the preset sparse model is used to process the target gene sequencing ciphertext and output the gene sequencing data analysis result ciphertext, where the target gene sequencing ciphertext is the gene sequencing ciphertext including the gene locus data to be detected in the multiple gene sequencing ciphertexts;

[0034] The ciphertext of the gene sequencing data analysis result is sent to the user device, so that the user device decrypts the ciphertext of the gene sequencing data analysis result to determine the user's gene sequencing data analysis result.

[0035] In a third aspect, the present application provides a gene sequencing data analysis device, which is applied to a user device. The gene sequencing data analysis device includes:

[0036] A data encoding module is used to encode the user's gene sequencing data to obtain multiple gene sequencing plaintexts corresponding to the gene sequencing data;

[0037] A plaintext encryption module is used to encrypt each gene sequencing plaintext using a public key to obtain multiple gene sequencing ciphertexts;

[0038] A ciphertext sending module is used to send the gene sequencing ciphertext to the server, wherein the server is used to input the gene sequencing ciphertext into a preset sparse model to obtain the ciphertext of the gene sequencing data analysis result;

[0039] The ciphertext receiving module is used to receive the ciphertext of the gene sequencing data analysis results sent by the server;

[0040] The result determination module is used to decrypt the ciphertext of the gene sequencing data analysis result using the private key to determine the user's gene sequencing data analysis result.

[0041] In a fourth aspect, the present application provides a gene sequencing data analysis device, which is applied to a server. The gene sequencing data analysis device includes:

[0042] A gene sequencing ciphertext receiving module, configured to receive multiple gene sequencing ciphertexts sent by a user device;

[0043] A gene sequencing ciphertext input module is used to input multiple gene sequencing ciphertexts into a preset sparse model to obtain a gene sequencing data analysis result ciphertext, wherein the preset sparse model is used to process the target gene sequencing ciphertext and output the gene sequencing data analysis result ciphertext, where the target gene sequencing ciphertext is the gene sequencing ciphertext that includes the gene locus data to be detected among the multiple gene sequencing ciphertexts;

[0044] The result ciphertext sending module is used to send the ciphertext of the gene sequencing data analysis result to the user device, so that the user device can decrypt the ciphertext of the gene sequencing data analysis result and determine the user's gene sequencing data analysis result.

[0045] In a fifth aspect, the present application provides a computing device, comprising:

[0046] a memory configured to store instructions; and

[0047] The processor is configured to call instructions from the memory and implement the above-mentioned gene sequencing data analysis method when executing the instructions.

[0048] In a sixth aspect, the present application provides a machine-readable storage medium, on which instructions are stored, and the instructions are used to enable a machine to execute the above-mentioned gene sequencing data analysis method.

[0049] The present application provides a genetic sequencing data analysis method, which is applied to a user device. The genetic sequencing data analysis method includes: encoding the user's genetic sequencing data to obtain multiple genetic sequencing plaintexts corresponding to the genetic sequencing data; encrypting each genetic sequencing plaintext using a public key to obtain multiple genetic sequencing ciphertexts; sending the genetic sequencing ciphertexts to a server; receiving the genetic sequencing data analysis result ciphertext sent by the server; and decrypting the genetic sequencing data analysis result ciphertext using a private key to determine the user's genetic sequencing data analysis result. When performing genetic sequencing data analysis on a user, the user device sends the encrypted multiple genetic sequencing ciphertexts, thereby preventing the leakage of the user's genetic sequencing data. At the same time, the server uses a preset sparse model to perform genetic sequencing data analysis. This does not require processing all genetic sequencing ciphertexts, but only processes the genetic sequencing ciphertext to be tested, thereby improving the computational efficiency of the model and, in turn, the efficiency of genetic sequencing data analysis. Furthermore, even if all genetic sequencing ciphertexts sent by the user device are intercepted and decrypted by a third-party device, since the user's genetic sequencing ciphertext to be tested cannot be determined, user privacy is avoided during remote genetic sequencing data analysis.

[0050] Other features and advantages of the embodiments of the present application will be described in detail in the subsequent detailed description. BRIEF DESCRIPTION OF THE DRAWINGS

[0051] The accompanying drawings are used to provide a further understanding of the embodiments of the present application and constitute a part of the specification. Together with the following detailed description, they are used to explain the embodiments of the present application but do not constitute a limitation on the embodiments of the present application. In the accompanying drawings:

[0052] FIG1 shows a first flow chart of a gene sequencing data analysis method provided in an embodiment of the present application;

[0053] FIG2 shows an example diagram of an application of a user equipment provided in an embodiment of the present application;

[0054] FIG3 shows a second flow chart of the gene sequencing data analysis method provided in an embodiment of the present application;

[0055] FIG4 shows a schematic diagram of a first structure of a gene sequencing data analysis device provided in an embodiment of the present application;

[0056] FIG5 shows a second structural diagram of the gene sequencing data analysis device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0057] The following will be combined with the accompanying drawings in the embodiments of the present application to describe in detail the specific implementation of the embodiment of the present application. It should be understood that the specific implementation described here is only used to illustrate and explain the embodiments of the present application, and is not used to limit the embodiments of the present application.

[0058] The components of the embodiments of the present application generally described and illustrated in the drawings herein may be arranged and designed in a variety of different configurations. Therefore, the following detailed description of the embodiments of the present application provided in the drawings is not intended to limit the scope of the claimed application, but rather merely represents selected embodiments of the present application. All other embodiments derived by those skilled in the art based on the embodiments of the application without creative effort are within the scope of protection of the present application.

[0059] Hereinafter, the terms "including", "having" and their cognates, which may be used in various embodiments of the present application, are intended only to indicate specific features, numbers, steps, operations, elements, components or combinations of the foregoing items, and should not be understood as first excluding the existence of one or more other features, numbers, steps, operations, elements, components or combinations of the foregoing items or the possibility of adding one or more features, numbers, steps, operations, elements, components or combinations of the foregoing items.

[0060] Furthermore, the terms “first,” “second,” “third,” etc., are merely used for distinguishing descriptions and are not to be understood as indicating or implying relative importance.

[0061] Unless otherwise defined, all terms used herein (including technical and scientific terms) have the same meaning as commonly understood by those skilled in the art to which the various embodiments of the present application belong. The terms (such as those defined in generally used dictionaries) will be interpreted as having the same meaning as in the context of the relevant technical field and will not be interpreted as having an idealized meaning or an overly formal meaning unless clearly defined in the various embodiments of the present application.

[0062] Example 1

[0063] Please refer to Figure 1, which shows a first flow chart of the gene sequencing data analysis method provided in an embodiment of the present application. The gene sequencing data analysis method in Figure 1 is applied to a user device, and the gene sequencing data analysis method includes:

[0064] S110 , encoding the user's gene sequencing data to obtain multiple gene sequencing plaintexts corresponding to the gene sequencing data.

[0065] Gene sequencing is a technology used to determine the DNA (deoxyribonucleic acid) sequence in an organism's genome. Gene sequencing is performed on users to obtain their gene sequencing data. A locus refers to a location on a user's genome that has a specific genetic variation. Gene sequencing data includes all of the user's gene loci, enabling analysis and processing of the gene sequencing data to produce analysis results. The user's gene sequencing data is encoded to obtain multiple gene sequencing plaintexts corresponding to the gene sequencing data. This encoding of the gene sequencing data into multiple gene sequencing plaintexts is done.

[0066] S120: Use the public key to encrypt each gene sequencing plaintext to obtain multiple gene sequencing ciphertexts.

[0067] When analyzing a user's genetic sequencing data, the user's device generates a public key and a private key. The public key is used to encrypt the data, and the private key is used to decrypt it. Each genetic sequencing plaintext is encrypted using the public key, resulting in the corresponding genetic sequencing ciphertext. By encoding the genetic sequencing data into multiple genetic sequencing plaintexts and encrypting each genetic sequencing plaintext separately, the need to simultaneously process data with a large numerical range is avoided, improving data processing efficiency. Furthermore, encrypting the genetic sequencing plaintext into genetic sequencing ciphertext protects the user's privacy and prevents the leakage of their genetic sequencing data.

[0068] S130, sending the gene sequencing ciphertext to the server, wherein the server is used to input the gene sequencing ciphertext into a preset sparse model to obtain the gene sequencing data analysis result ciphertext.

[0069] Please refer to Figure 2, which shows an application example diagram of a user equipment provided in an embodiment of the present application.

[0070] It should be understood that the type of user device 210 is determined based on actual needs and can be a mobile terminal, a PC (Personal Computer), etc., and is not limited here. Server 220 includes a preset sparse model 221. User device 210 communicates with server 220, and user device 210 sends the multiple gene sequencing ciphertexts obtained to server 220. Server 220 receives the encrypted gene sequencing ciphertext, preventing the leakage of user privacy.

[0071] Because the multiple gene sequencing plaintexts are obtained by encoding the gene sequencing data, all of the user's gene locus data can be determined from the obtained multiple gene sequencing plaintexts. Server 220 inputs the received gene sequencing ciphertexts into a preset sparse model 221, processes the gene sequencing ciphertexts using the preset sparse model 221, and then obtains the gene sequencing data analysis result ciphertext based on the gene locus data in the gene sequencing ciphertexts.

[0072] In the actual scenario of determining the analysis results of the user's genetic sequencing data, usually only a specific disease category is analyzed, and only a small amount of gene site data to be detected related to the specific disease category needs to be processed and analyzed, and there is no need to process and analyze all the gene site data. During the communication process between the user device 210 and the server 220, the encrypted complete genetic sequencing data is sent to the server 220. Different disease categories to be analyzed will result in different genetic sequencing ciphertexts to be detected. Compared with only sending the genetic site data to be detected, even if all the genetic sequencing ciphertexts sent by the user device 210 are intercepted and decrypted by a third-party device, since the user's genetic sequencing ciphertext to be detected cannot be determined, the disease category of the user to be analyzed cannot be determined, thereby avoiding the leakage of the user's privacy.

[0073] S140: Receive the encrypted gene sequencing data analysis result sent by the server.

[0074] Because most of the parameters in the preset sparse model are zero, even if the user device sends multiple genetic sequencing ciphertexts, the preset sparse model does not need to process all genetic sequencing ciphertexts. Instead, it processes the genetic sequencing ciphertext to be tested, improving the model's computational efficiency and, in turn, the efficiency of genetic sequencing data analysis. After obtaining the genetic sequencing data analysis result ciphertext, the server sends it to the user device. The user device receives the genetic sequencing data analysis result ciphertext sent by the server to determine the user's genetic sequencing data analysis result.

[0075] S150, using the private key to decrypt the ciphertext of the gene sequencing data analysis result to determine the gene sequencing data analysis result of the user.

[0076] After receiving the encrypted genetic sequencing data analysis results from the server, the user's device decrypts them using the private key to determine the user's genetic sequencing data analysis results. Because both the data sent and received by the user's device is encrypted, user privacy is prevented during genetic sequencing data analysis.

[0077] In an embodiment of the present application, the gene sequencing data analysis method further includes:

[0078] Generate security parameters based on the degree of the homomorphic encryption ciphertext polynomial and the number of bits of the ciphertext modulus;

[0079] Generate public and private keys based on security parameters.

[0080] It should be understood that the encryption method used is selected according to actual needs, and any homomorphic encryption method can be used, which is not limited here. For ease of understanding, CKKS (Cheon Kim Kim Song) homomorphic encryption is used in the embodiments of the present application to generate public and private keys to encrypt each gene sequencing plaintext. CKKS homomorphic encryption is used so that the preset sparse model can perform calculations under data encryption to obtain the ciphertext of the gene sequencing data analysis results. The result after decrypting the ciphertext of the gene sequencing data analysis results is the same as the result obtained by performing the calculation when the gene sequencing data is not encrypted. The ciphertext polynomial degree will affect the depth of the homomorphic operation performed by the user device. The lower the ciphertext polynomial degree, the higher the computational efficiency, but it will also result in more complex operations performed for the corresponding ciphertext polynomial degree. The number of bits of the ciphertext modulus will affect the numerical range and numerical precision that the gene sequencing ciphertext can represent. The higher the number of bits of the ciphertext modulus, the higher the numerical precision of the gene sequencing ciphertext, but it will also result in an increase in the numerical range of the gene sequencing ciphertext, thereby affecting the computational efficiency.

[0081] It should be understood that the numerical value of the ciphertext polynomial degree and the numerical value of the number of bits of the ciphertext modulus are set according to actual needs, and the numerical value of the ciphertext polynomial degree and the numerical value of the number of bits of the ciphertext modulus can be determined by the homomorphic encryption security standard, which is not limited here. For ease of understanding, in the embodiment of the present application, the ciphertext polynomial degree is 8192, and the number of bits of the ciphertext modulus is 60+40+40+60=200. Based on the ciphertext polynomial degree and the number of bits of the ciphertext modulus of CKKS homomorphic encryption, the generated security parameter is 128. When the security parameters are determined, the public key and private key are generated according to the security parameters and the steps specified by CKKS homomorphic encryption.

[0082] In an embodiment of the present application, the user's gene sequencing data is encoded to obtain multiple gene sequencing plaintexts corresponding to the gene sequencing data, including:

[0083] According to the degree of the ciphertext polynomial, the encoding dimension corresponding to each gene sequencing ciphertext is determined;

[0084] Based on the encoding dimension and the dimension of the user's gene sequencing data, the gene sequencing data is encoded to obtain multiple gene sequencing plaintexts.

[0085] The encoding dimension corresponding to each gene sequencing ciphertext is determined based on the ciphertext polynomial degree. In the embodiment of the present application, the ciphertext polynomial degree is 8192, and the encoding dimension corresponding to each gene sequencing ciphertext is 8192 / 2=4096.

[0086] Based on the encoding dimension and the dimensionality of the user's genetic sequencing data, the genetic sequencing data is encoded to produce multiple genetic sequencing plaintexts. For example, if the genetic sequencing data has a dimension of 342669, the number of genetic sequencing plaintexts produced by encoding the genetic sequencing data is 342669 / 4096≈84 segments. Compared to directly encrypting the complete genetic sequencing data, encoding the genetic sequencing data into multiple genetic sequencing plaintexts and then encrypting these multiple segments improves data processing efficiency.

[0087] In an embodiment of the present application, the gene sequencing data analysis method further includes:

[0088] When the dimension of the gene sequencing plaintext is smaller than the encoding dimension, data padding is performed on the gene sequencing plaintext until the dimension of the gene sequencing plaintext is equal to the encoding dimension.

[0089] When encoding gene sequencing data, the dimension of the last segment of the plaintext may be smaller than the encoding dimension. Data padding is performed on the plaintext until the dimension of the plaintext equals the encoding dimension, ensuring that the dimension of each segment of the plaintext is the same. The padding data is set based on actual needs and is not limited here. For ease of understanding, the padding data in the examples of this application is 0.

[0090] In an embodiment of the present application, the dimension of the model parameters of the preset sparse model is equal to the dimension of the gene sequencing data, and the model parameters include model sub-parameters corresponding to each gene sequencing plaintext;

[0091] The preset sparse model is used to obtain multiple result ciphertexts according to the model sub-parameters and the gene sequencing ciphertext, and the multiple result ciphertexts are summed to obtain the gene sequencing data analysis result ciphertext.

[0092] The dimension of the model parameters of the preset sparse model is equal to the dimension of the gene sequencing data. That is, when the dimension of the gene sequencing data is 342669, the dimension of the model parameters of the preset sparse model is also 342669. In the embodiment of the present application, 84 gene sequencing plaintexts are obtained, and the model parameters include model sub-parameters corresponding to each gene sequencing plaintext, that is, the number of model sub-parameters is 84.

[0093] The preset sparse model is used to obtain multiple result ciphertexts based on the model sub-parameters and the gene sequencing ciphertext. The multiple result ciphertexts are summed to obtain the ciphertext, that is, the gene sequencing data analysis result ciphertext. For ease of understanding, in the embodiment of the present application, the preset sparse model is a linear model: f(x)=wTx+b, where f(x) is the output of the preset sparse model, x is the gene sequencing ciphertext, w and b are the model parameters of the preset sparse model, and T represents the transposition of w. The preset sparse model calculates the inner product of the plaintext-ciphertext vector based on w and x, and obtains the result ciphertext corresponding to each gene sequencing plaintext as zi, where i ranges from 1 to M / t, M is the dimension of the gene sequencing data, t is the encoding dimension corresponding to each gene sequencing ciphertext, x and w are both M-dimensional vectors, and x and w are both b-dimensional scalars. Divide w into M / t segments to obtain the model sub-parameters corresponding to each gene sequencing plaintext.

[0094] Summing all the zi values ​​yields z, which is then updated to produce the ciphertext z+b for the gene sequencing data analysis. Because the multiple model sub-parameters of the pre-set sparse model are all zero, a large number of zi values ​​are zero, leaving only a small number of non-zero zi values ​​involved in the summation. This reduces the computational effort required to sum multiple ciphertext results, improving computational efficiency and, consequently, the efficiency of gene sequencing data analysis.

[0095] In the embodiment of the present application, the private key is used to decrypt the ciphertext of the gene sequencing data analysis result to determine the user's gene sequencing data analysis result, including:

[0096] Decrypting the ciphertext of the gene sequencing data analysis result using the private key to obtain a plaintext vector corresponding to the gene sequencing data analysis result, wherein the plaintext vector includes multiple components;

[0097] Get any component in the plaintext vector;

[0098] When the value of the component is positive, it is determined that the analysis result of the user's gene sequencing data is abnormal;

[0099] When the value of the component is negative, it is determined that the analysis result of the user's gene sequencing data is that there is no abnormality in the gene sequencing data.

[0100] The ciphertext of the genetic sequencing data analysis results is decrypted using the private key to obtain the plaintext vector corresponding to the genetic sequencing data analysis results. The dimension of the ciphertext of the genetic sequencing data analysis results is equal to the encoding dimension of the corresponding genetic sequencing ciphertext, so that the plaintext vector includes multiple components. The components in the plaintext vector are extracted to obtain any component in the plaintext vector. Any obtained component is the genetic sequencing data analysis result.

[0101] When the numerical value of the component is positive, it is determined that the result of the user's genetic sequencing data analysis is that there is an abnormality in the genetic sequencing data, and then it is determined that the user has a disease. When the numerical value of the component is negative, it is determined that the result of the user's genetic sequencing data analysis is that there is no abnormality in the genetic sequencing data, and then it is determined that the user does not have a disease. Since the result of the user's genetic sequencing data analysis is represented by the numerical value of the component, when the ciphertext of the genetic sequencing data analysis result is intercepted and decrypted by a third-party device, since the genetic sequencing data analysis result does not include the category of the disease being analyzed, the user's privacy is avoided. Specifically, taking the example of the genetic sequencing data analysis result being that there is an abnormality in the genetic sequencing data, it can only be determined that the user has a disease, and the category of the disease the user has cannot be determined, thereby avoiding the user's privacy.

[0102] In an embodiment of the present application, the gene sequencing data analysis method further includes:

[0103] Generate user data analysis and processing documents based on the user's gene sequencing data analysis results;

[0104] Convert the data analysis and processing documents into a QR code image and generate a display interface for the QR code image.

[0105] Based on the user's gene sequencing data analysis results, a data analysis and processing document for the user is generated to provide the user's gene sequencing data analysis results through the data analysis and processing document. Specifically, when the gene sequencing data analysis result shows that the gene sequencing data has an abnormality, it is determined that the user has a disease, and the data analysis and processing document may include the gene sequencing data analysis results and treatment recommendations for the disease. When the user's gene sequencing data analysis result shows that the gene sequencing data has an abnormality, it is determined that the user does not have a disease, and the data analysis and processing document may include the gene sequencing data analysis results and prevention recommendations for the disease. It should be understood that the data analysis and processing document may also include other document information such as prompts that the disease requires further diagnosis. Other document information is set according to actual needs and is not limited here.

[0106] The data analysis and processing document is converted into a QR code image, and a display interface for the QR code image is generated. The user can read the QR code image in the display interface through a personal device such as a mobile terminal. After user authentication, the user's data analysis and processing document is displayed on the personal device, allowing the user to determine whether they have a disease based on the genetic sequencing data analysis results. It should be understood that the user device and the user's personal device can be the same device or different devices. In the case where the user device and the personal device are the same device, the display interface for the data analysis and processing document can be directly generated.

[0107] The present application provides a genetic sequencing data analysis method, which is applied to a user device. The genetic sequencing data analysis method includes: encoding the user's genetic sequencing data to obtain multiple genetic sequencing plaintexts corresponding to the genetic sequencing data; encrypting each genetic sequencing plaintext using a public key to obtain multiple genetic sequencing ciphertexts; sending the genetic sequencing ciphertexts to a server; receiving the genetic sequencing data analysis result ciphertext sent by the server; and decrypting the genetic sequencing data analysis result ciphertext using a private key to determine the user's genetic sequencing data analysis result. When performing genetic sequencing data analysis on a user, the user device sends the encrypted multiple genetic sequencing ciphertexts, thereby preventing the leakage of the user's genetic sequencing data. At the same time, the server uses a preset sparse model to perform genetic sequencing data analysis. This does not require processing all genetic sequencing ciphertexts, but only processes the genetic sequencing ciphertext to be tested, thereby improving the computational efficiency of the model and, in turn, the efficiency of genetic sequencing data analysis. Furthermore, even if all genetic sequencing ciphertexts sent by the user device are intercepted and decrypted by a third-party device, since the user's genetic sequencing ciphertext to be tested cannot be determined, user privacy is avoided during remote genetic sequencing data analysis.

[0108] Example 2

[0109] Please refer to Figure 3, which shows a second flow chart of the gene sequencing data analysis method provided in an embodiment of the present application. The gene sequencing data analysis method in Figure 3 is applied to a server and includes:

[0110] S310: Receive multiple gene sequencing ciphertexts sent by a user device.

[0111] The server communicates with the user device. When a user requests remote analysis of genetic sequencing data, the user device encodes the user's genetic sequencing data to obtain multiple genetic sequencing plaintexts corresponding to the genetic sequencing data. Simultaneously, the user device encrypts each genetic sequencing plaintext using the public key to obtain multiple genetic sequencing ciphertexts. The user device sends the multiple genetic sequencing ciphertexts to the server. The server receives the multiple genetic sequencing ciphertexts sent by the user device and obtains the genetic sequencing data analysis results ciphertext from the server.

[0112] S320: Inputting the plurality of gene sequencing ciphertexts into a preset sparse model to obtain a gene sequencing data analysis result ciphertext, wherein the preset sparse model is used to process the target gene sequencing ciphertext and output the gene sequencing data analysis result ciphertext, where the target gene sequencing ciphertext is the gene sequencing ciphertext of the gene locus to be detected among the plurality of gene sequencing ciphertexts;

[0113] The preset sparse model can be any preset model and is not limited here. The preset sparse model can be used to analyze a variety of diseases that require gene sequencing data processing, such as bladder cancer, acute myocardial infarction, and acute myeloid leukemia. Depending on the disease category analyzed by the preset sparse model, the preset sparse model processes different gene loci and a different number of gene loci.

[0114] A preset sparse model is used to process target gene sequencing ciphertexts and output a gene sequencing data analysis result ciphertext. The target gene sequencing ciphertext is the gene sequencing ciphertext containing the data of the gene locus to be tested, among multiple gene sequencing ciphertexts. For ease of understanding, assuming the number of gene sequencing ciphertexts is 84 and the number of gene loci to be tested is 9, machine learning models other than sparse models typically require all 84 gene sequencing ciphertexts to be calculated. In reality, there are only a maximum of 9 gene sequencing ciphertexts containing the gene loci to be tested. Models other than sparse models need to process all 84 gene sequencing ciphertexts, resulting in low computational efficiency. Due to the sparsity of the preset sparse model, the model parameters corresponding to at least 84 - 9 = 75 gene sequencing ciphertexts are all zero, resulting in the result ciphertexts corresponding to at least 75 gene sequencing ciphertexts also being zero. Only a maximum of 9 result ciphertexts corresponding to the gene sequencing ciphertexts are required to participate in the summation calculation to output the gene sequencing data analysis result ciphertext, significantly improving computational efficiency and, in turn, the efficiency of gene sequencing data analysis.

[0115] S330: Send the ciphertext of the gene sequencing data analysis result to the user device, so that the user device decrypts the ciphertext of the gene sequencing data analysis result to determine the user's gene sequencing data analysis result.

[0116] The server sends the encrypted genetic sequencing data analysis results to the user device. The user device receives the encrypted genetic sequencing data analysis results and decrypts them to determine the user's genetic sequencing data analysis results. Because most of the model parameters in the preset sparse model are zero, even if the user device sends multiple genetic sequencing ciphertexts, the preset sparse model does not need to process all genetic sequencing ciphertexts, thereby improving the model's computational efficiency and, in turn, the efficiency of genetic sequencing data analysis.

[0117] Example 3

[0118] Please refer to Figure 4, which shows a first structural diagram of a gene sequencing data analysis device provided in an embodiment of the present application. The gene sequencing data analysis device 400 in Figure 4 is applied to a user device and includes:

[0119] The data encoding module 410 is used to encode the user's gene sequencing data to obtain multiple gene sequencing plaintexts corresponding to the gene sequencing data;

[0120] A plaintext encryption module 420 is used to encrypt each gene sequencing plaintext using a public key to obtain multiple gene sequencing ciphertexts;

[0121] The ciphertext sending module 430 is used to send the gene sequencing ciphertext to the server, wherein the server is used to input the gene sequencing ciphertext into a preset sparse model to obtain the ciphertext of the gene sequencing data analysis result;

[0122] The ciphertext receiving module 440 is used to receive the ciphertext of the gene sequencing data analysis result sent by the server;

[0123] The result determination module 450 is used to decrypt the ciphertext of the gene sequencing data analysis result using the private key to determine the gene sequencing data analysis result of the user.

[0124] In an embodiment of the present application, the gene sequencing data analysis device 400 further includes:

[0125] A security parameter generation module is used to generate security parameters based on the degree of the ciphertext polynomial and the number of bits of the ciphertext modulus of the CKKS homomorphic encryption;

[0126] The public key and private key generation module is used to generate public keys and private keys according to security parameters.

[0127] In an embodiment of the present application, the data encoding module 410 includes:

[0128] The coding dimension determination submodule is used to determine the coding dimension corresponding to each gene sequencing ciphertext according to the degree of the ciphertext polynomial;

[0129] The plaintext obtaining submodule is used to encode the gene sequencing data based on the encoding dimension and the dimension of the user's gene sequencing data to obtain multiple gene sequencing plaintexts.

[0130] In an embodiment of the present application, the gene sequencing data analysis device 400 further includes:

[0131] The data filling module is used to fill the gene sequencing plaintext with data when the dimension of the gene sequencing plaintext is less than the encoding dimension, until the dimension of the gene sequencing plaintext is equal to the encoding dimension.

[0132] In an embodiment of the present application, the dimension of the model parameters of the preset sparse model is equal to the dimension of the gene sequencing data, and the model parameters include model sub-parameters corresponding to each gene sequencing plaintext;

[0133] The preset sparse model is used to obtain multiple result ciphertexts according to the model sub-parameters and the gene sequencing ciphertext, and the multiple result ciphertexts are summed to obtain the gene sequencing data analysis result ciphertext.

[0134] In the embodiment of the present application, the result determination module 450 includes:

[0135] A plaintext vector obtaining submodule is used to decrypt the ciphertext of the gene sequencing data analysis result using a private key to obtain a plaintext vector corresponding to the gene sequencing data analysis result, wherein the plaintext vector includes multiple components;

[0136] The component acquisition submodule is used to obtain any component in the plaintext vector;

[0137] An abnormality determination submodule is used to determine that the user's gene sequencing data analysis result indicates that the gene sequencing data has an abnormality when the value of the component is positive;

[0138] The no-abnormality determination submodule is used to determine that the user's gene sequencing data analysis result is no abnormality in the gene sequencing data when the component value is negative.

[0139] In an embodiment of the present application, the gene sequencing data analysis device 400 further includes:

[0140] An analysis document generation module is used to generate a user's data analysis and processing document based on the user's gene sequencing data analysis results;

[0141] The display interface generation module is used to convert the data analysis and processing document into a QR code image and generate a display interface for the QR code image.

[0142] The gene sequencing data analysis device 400 is used to perform the corresponding steps in the gene sequencing data analysis method described above. The specific implementation of each function will not be described here one by one. In addition, the optional examples in the gene sequencing data analysis method are also applicable to the gene sequencing data analysis device 400.

[0143] Example 4

[0144] Please refer to Figure 5, which shows a second structural diagram of the gene sequencing data analysis device provided in an embodiment of the present application. The gene sequencing data analysis device 500 in Figure 5 is applied to a server and includes:

[0145] Gene sequencing ciphertext receiving module 510, configured to receive multiple gene sequencing ciphertexts sent by a user device;

[0146] Gene sequencing ciphertext input module 520 is used to input multiple gene sequencing ciphertexts into a preset sparse model to obtain gene sequencing data analysis result ciphertexts, wherein the preset sparse model is used to process the target gene sequencing ciphertexts and output the gene sequencing data analysis result ciphertexts, where the target gene sequencing ciphertexts are the gene sequencing ciphertexts that include the gene locus data to be detected among the multiple gene sequencing ciphertexts;

[0147] The result ciphertext sending module 530 is used to send the ciphertext of the gene sequencing data analysis result to the user device, so that the user device decrypts the ciphertext of the gene sequencing data analysis result to determine the user's gene sequencing data analysis result.

[0148] The present application also provides a computing device, including:

[0149] a memory configured to store instructions; and

[0150] The processor is configured to call instructions from the memory and implement the above-mentioned gene sequencing data analysis method when executing the instructions.

[0151] In this embodiment, the data encoding module 410, the plaintext encryption module 420, the ciphertext sending module 430, the ciphertext receiving module 440, the result determination module 450, the gene sequencing ciphertext receiving module 510, the gene sequencing ciphertext input module 520 and the result ciphertext sending module 530 are all stored in the memory as program units, and the processor executes the above program units stored in the memory to realize the corresponding functions.

[0152] The processor contains a kernel, which retrieves the corresponding program unit from memory. One or more kernels can be configured, and kernel parameters can be adjusted to address the issue of user privacy leaks during remote analysis of genetic sequencing data.

[0153] The memory may include non-permanent memory in a computer-readable medium, random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM, and the memory includes at least one memory chip.

[0154] An embodiment of the present application also provides a machine-readable storage medium, on which instructions are stored, and the instructions are used to enable a machine to execute the above-mentioned gene sequencing data analysis method.

[0155] Those skilled in the art will appreciate that the embodiments of the present application can be provided as methods, systems, or computer program products. Therefore, the present application can adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment in combination with software and hardware. Moreover, the present application can adopt the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to magnetic disk storage, CD-ROM, optical storage, etc.) that contain computer-usable program code.

[0156] The present application is described with reference to the flow chart and / or block diagram of the method, device (system), and computer program product according to the embodiment of the present application. It should be understood that each flow process and / or box in the flow chart and / or block diagram and the combination of the flow process and / or box in the flow chart and / or block diagram can be realized by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processing machine or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device produce a device for realizing the function specified in one flow chart flow or multiple flows and / or one box or multiple boxes of the block diagram.

[0157] These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce a product including an instruction device that implements the functions specified in one or more processes in the flowchart and / or one or more boxes in the block diagram.

[0158] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, so that the instructions executed on the computer or other programmable device provide steps for implementing the functions specified in one or more processes in the flowchart and / or one or more boxes in the block diagram.

[0159] In a typical configuration, a computing device includes one or more processors (CPUs), input / output interfaces, network interfaces, and memory.

[0160] The memory may include non-permanent memory in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM. The memory is an example of a computer-readable medium.

[0161] Machine-readable storage media include permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. Information can be computer-readable instructions, data structures, program modules, or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disc read-only memory (CD-ROM), digital versatile disc (DVD) or other optical storage, magnetic cassettes, magnetic tape, magnetic disk storage or other magnetic storage devices, or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer-readable media does not include transitory media such as modulated data signals and carrier waves.

[0162] It should also be noted that the terms "comprises," "includes," or any other variations thereof are intended to encompass non-exclusive inclusion, such that a process, method, commodity, or apparatus that includes a series of elements includes not only those elements but also other elements not explicitly listed, or includes elements inherent to such process, method, commodity, or apparatus. In the absence of further limitations, an element defined by the phrase "comprises a ..." does not exclude the presence of other identical elements in the process, method, commodity, or apparatus that includes the element.

[0163] The above are merely embodiments of the present application and are not intended to limit the present application. For those skilled in the art, the present application may have various changes and variations. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principles of the present application should all be included within the scope of the claims of the present application.

Claims

1. A gene sequencing data analysis method, characterized in that: Applied to a user device, the gene sequencing data analysis method includes: Encode the user's gene sequencing data to obtain multiple gene sequencing plaintexts corresponding to the gene sequencing data; Using a public key to encrypt each of the gene sequencing plaintexts to obtain multiple gene sequencing ciphertexts; Sending the gene sequencing ciphertext to a server, wherein the server is used to input the gene sequencing ciphertext into a preset sparse model to obtain a gene sequencing data analysis result ciphertext; Receiving the ciphertext of the gene sequencing data analysis result sent by the server; The private key is used to decrypt the ciphertext of the gene sequencing data analysis result to determine the gene sequencing data analysis result of the user.

2. The gene sequencing data analysis method according to claim 1, characterized in that: The gene sequencing data analysis method further comprises: Generate security parameters based on the degree of the homomorphic encryption ciphertext polynomial and the number of bits of the ciphertext modulus; The public key and the private key are generated according to the security parameters.

3. The gene sequencing data analysis method according to claim 2, characterized in that: The encoding of the user's gene sequencing data to obtain a plurality of gene sequencing plaintexts corresponding to the gene sequencing data includes: Determining the encoding dimension corresponding to each gene sequencing ciphertext according to the degree of the ciphertext polynomial; Based on the encoding dimension and the dimension of the user's gene sequencing data, the gene sequencing data is encoded to obtain multiple gene sequencing plaintexts.

4. The gene sequencing data analysis method according to claim 3, characterized in that: The gene sequencing data analysis method further comprises: In a case where the dimension of the gene sequencing plaintext is smaller than the encoding dimension, data padding is performed on the gene sequencing plaintext until the dimension of the gene sequencing plaintext is equal to the encoding dimension.

5. The gene sequencing data analysis method according to claim 1, characterized in that: The dimension of the model parameters of the preset sparse model is equal to the dimension of the gene sequencing data, and the model parameters include model sub-parameters corresponding to each of the gene sequencing plaintexts; The preset sparse model is used to obtain multiple result ciphertexts based on the model sub-parameters and the gene sequencing ciphertext, and to sum the multiple result ciphertexts to obtain the gene sequencing data analysis result ciphertext.

6. The gene sequencing data analysis method according to claim 1, characterized in that: Decrypting the ciphertext of the gene sequencing data analysis result using the private key to determine the gene sequencing data analysis result of the user includes: Decrypting the ciphertext of the gene sequencing data analysis result using a private key to obtain a plaintext vector corresponding to the gene sequencing data analysis result, wherein the plaintext vector includes multiple components; Obtaining any component of the plaintext vector; When the value of the component is positive, determining that the analysis result of the user's gene sequencing data is that the gene sequencing data is abnormal; When the value of the component is negative, it is determined that the analysis result of the user's gene sequencing data is that there is no abnormality in the gene sequencing data.

7. The gene sequencing data analysis method according to claim 1, characterized in that: The gene sequencing data analysis method further comprises: Generating a data analysis and processing document for the user based on the analysis results of the user's gene sequencing data; The data analysis and processing document is converted into a two-dimensional code image, and a display interface of the two-dimensional code image is generated.

8. A gene sequencing data analysis method, characterized in that: Applied to a server, the gene sequencing data analysis method includes: Receive multiple gene sequencing ciphertexts sent by a user device; Inputting the multiple gene sequencing ciphertexts into a preset sparse model to obtain a gene sequencing data analysis result ciphertext, wherein the preset sparse model is used to process the target gene sequencing ciphertext and output the gene sequencing data analysis result ciphertext, wherein the target gene sequencing ciphertext is the gene sequencing ciphertext that includes the gene locus data to be detected among the multiple gene sequencing ciphertexts; The gene sequencing data analysis result ciphertext is sent to the user device, so that the user device decrypts the gene sequencing data analysis result ciphertext to determine the gene sequencing data analysis result of the user.

9. A gene sequencing data analysis device, characterized in that: Applied to user equipment, the gene sequencing data analysis device includes: A data encoding module, used to encode the user's gene sequencing data to obtain multiple gene sequencing plaintexts corresponding to the gene sequencing data; A plaintext encryption module, configured to encrypt each of the gene sequencing plaintexts using a public key to obtain multiple gene sequencing ciphertexts; A ciphertext sending module, configured to send the gene sequencing ciphertext to a server, wherein the server is configured to input the gene sequencing ciphertext into a preset sparse model to obtain a ciphertext of the gene sequencing data analysis result; A ciphertext receiving module, configured to receive the ciphertext of the gene sequencing data analysis result sent by the server; The result determination module is used to decrypt the ciphertext of the gene sequencing data analysis result using a private key to determine the gene sequencing data analysis result of the user.

10. A gene sequencing data analysis device, characterized in that: Applied to a server, the gene sequencing data analysis device comprises: A gene sequencing ciphertext receiving module, configured to receive multiple gene sequencing ciphertexts sent by a user device; a gene sequencing ciphertext input module, configured to input the plurality of gene sequencing ciphertexts into a preset sparse model to obtain a gene sequencing data analysis result ciphertext, wherein the preset sparse model is used to process the target gene sequencing ciphertext and output the gene sequencing data analysis result ciphertext, wherein the target gene sequencing ciphertext is the gene sequencing ciphertext that includes the gene locus data to be detected among the plurality of gene sequencing ciphertexts; The result ciphertext sending module is used to send the ciphertext of the gene sequencing data analysis result to the user device, so that the user device decrypts the ciphertext of the gene sequencing data analysis result to determine the gene sequencing data analysis result of the user.

11. A computing device, characterized in that include: a memory configured to store instructions; as well as A processor is configured to call the instructions from the memory and to implement the gene sequencing data analysis method according to any one of claims 1 to 7 or claim 8 when executing the instructions.

12. A machine-readable storage medium, characterized in that The machine-readable storage medium stores instructions for enabling a machine to execute the gene sequencing data analysis method according to any one of claims 1 to 7 or any one of claim 8.

Images