Medical information expression spectrum processing method based on privacy protection and multi-party secure calculation

Abstract

The embodiment of the present application provides a kind of medical information expression spectrum processing method based on privacy protection and multi-party secure computing, method includes: obtaining first gene expression profile data and the preset category corresponding to first gene expression profile data;The gene identification of the first gene expression profile data corresponds to the second gene expression profile data to be identified in user terminal;Determine the first gene relative expression between first gene expression profile data and preset internal reference gene expression profile data;The first gene relative expression and the preset category are sent to multi-party secure computing server, so that the multi-party secure computing server determines the identification result of the association between the second gene expression profile data and the preset category according to the first gene relative expression, second gene relative expression and the preset category.The method of the embodiment of the present application improves the security of privacy data processing process.

Description

Technical Field

[0001] This invention relates to the field of medical data processing technology, and in particular to a method for processing medical information expression spectra based on privacy protection and multi-party secure computation. Background Technology

[0002] High-throughput technologies are increasingly being used in clinical research, with more and more being applied clinically, primarily DNA and RNA sequencing. Due to the degradability of RNA, RNA sequencing is mainly used on fresh tissues and cells to obtain expression profiles of specific genes. However, these conventional methods cannot help identify heterogeneity within fresh tissues and cells.

[0003] With the development of information technology and the maturity of biotechnology, many institutions have obtained expression profiles of specific cell or tissue subtypes through experimental methods. However, these profiles are difficult to obtain and are considered private data by each institution. If this private data is used to identify the expression profiles of unknown cells in practice, the specific expression profile data within the private data must be known, leading to potential data leakage and low security in the processing of such private data. Summary of the Invention

[0004] This invention provides a medical information expression spectrum processing method based on privacy protection and multi-party secure computation, which aims to solve the problems of easy data leakage of privacy data in various institutions and the low security of privacy data processing.

[0005] The first aspect of this invention provides a method for processing medical information expression profiles based on privacy protection and multi-party secure computation, applied to an expression profile data providing server, the method comprising:

[0006] Acquire first gene expression profile data and the preset category corresponding to the first gene expression profile data; the first gene expression profile data corresponds to the gene identifier of the second gene expression profile data to be identified in the user terminal;

[0007] Determine the relative expression level of the first gene between the first gene expression profile data and the preset internal reference gene expression profile data;

[0008] The first gene relative expression level and the preset category are sent to a multi-party secure computing server so that the multi-party secure computing server can determine the identification result of the association between the second gene expression profile data and the preset category based on the first gene relative expression level, the second gene relative expression level and the preset category; the second gene relative expression level is the gene relative expression level between the second gene expression profile data and the preset internal reference gene expression profile data.

[0009] Optionally, in the method described above, obtaining the first gene expression profile data and the preset category corresponding to the first gene expression profile data includes:

[0010] Obtain the gene identifier corresponding to the second gene expression profile data to be identified in the user terminal;

[0011] Gene expression profile queue data corresponding to the gene identifier and a preset category corresponding to the gene expression profile queue data are obtained from a preset database; the preset database stores the mapping relationship between gene identifiers, gene expression profile queue data and preset categories corresponding to the gene expression profile queue data; the gene expression profile queue data has a mapping relationship with at least one preset category.

[0012] The gene expression profile cohort data is subjected to RNA sequencing normalization to generate the first gene expression profile data;

[0013] The preset category corresponding to the gene expression profile queue data is determined as the preset category corresponding to the first gene expression profile data.

[0014] Optionally, in the method described above, determining the relative expression level of the first gene between the first gene expression profile data and the preset internal reference gene expression profile data includes:

[0015] The t-validation algorithm is used to determine the corresponding validation statistic t value based on the first gene expression profile data and the preset internal reference gene expression profile data.

[0016] Based on the t-value, query the corresponding t-boundary table to determine the p-value, which is the parameter for the decision hypothesis test result corresponding to the t-value;

[0017] The p-value, the first gene expression profile data, and the preset internal reference gene expression profile data are input into a preset relative expression level algorithm to determine the relative expression level of the first gene corresponding to the p-value.

[0018] Optionally, in the method described above, the first gene expression profile data includes expression profile data corresponding to multiple identical gene identifiers; the preset internal reference gene expression profile data includes expression profile data corresponding to multiple identical internal reference genes.

[0019] The step of using the t-validation algorithm to determine the corresponding validation statistic t value based on the first gene expression profile data and the preset internal reference gene expression profile data includes:

[0020] Calculate the variance, mean, and total number of gene identifiers for the same gene identifier in the first gene expression profile data;

[0021] Calculate the variance, mean, and total number of internal reference genes for the expression profile data corresponding to the same internal reference gene in the preset internal reference gene expression profile data;

[0022] The variance, mean, and total number of gene identifiers corresponding to the same gene identifier in the first gene expression profile data, and the variance, mean, and total number of internal reference genes corresponding to the same internal reference gene in the preset internal reference gene expression profile data are input into the t-validation algorithm to determine the corresponding validation statistic t value.

[0023] A second aspect of this invention provides a method for processing medical information expression spectra based on privacy protection and multi-party secure computation, applied to a user terminal, the method comprising:

[0024] Determine the relative expression level of the second gene between the expression profile data of the second gene to be identified and the expression profile data of the preset internal reference gene;

[0025] The relative expression level of the second gene is sent to a multi-party secure computing server, so that the multi-party secure computing server can determine the identification result of the association between the second gene expression profile data and the preset category based on the relative expression level of the first gene, the relative expression level of the second gene, and the preset category; the preset category is the category corresponding to the first gene expression profile data in the expression profile data providing server; the gene identifiers of the first gene expression profile data and the second gene expression profile data correspond; the relative expression level of the first gene is the relative gene expression level between the first gene expression profile data and the preset internal reference gene expression profile data.

[0026] Optionally, in the method described above, determining the relative expression level of the second gene between the second gene expression profile data and the preset internal reference gene expression profile data includes:

[0027] The t-validation algorithm is used to determine the corresponding validation statistic t value based on the expression profile data of the second gene and the expression profile data of the preset internal reference gene.

[0028] Based on the t-value, query the corresponding t-boundary table to determine the p-value, which is the parameter for the decision hypothesis test result corresponding to the t-value;

[0029] The p-value, the second gene expression profile data, and the preset internal reference gene expression profile data are input into a preset relative expression level algorithm to determine the relative expression level of the second gene corresponding to the p-value.

[0030] Optionally, in the method described above, the second gene expression profile data includes expression profile data corresponding to multiple identical gene identifiers; the preset internal reference gene expression profile data includes expression profile data corresponding to multiple identical internal reference genes.

[0031] The step of using the t-validation algorithm to determine the corresponding validation statistic t-value based on the second gene expression profile data and the preset internal reference gene expression profile data includes:

[0032] Calculate the variance, mean, and total number of gene identifiers for the expression profile data corresponding to the same gene identifier in the second gene expression profile data;

[0033] Calculate the variance, mean, and total number of internal reference genes for the expression profile data corresponding to the same internal reference gene in the preset internal reference gene expression profile data;

[0034] The variance, mean, and total number of gene identifiers of the expression profile data corresponding to the same gene identifier in the second gene expression profile data, and the variance, mean, and total number of internal reference genes of the expression profile data corresponding to the same internal reference gene in the preset internal reference gene expression profile data are input into the t-validation algorithm to determine the corresponding validation statistic t value.

[0035] A third aspect of this invention provides a method for processing medical information expression profiles based on privacy protection and multi-party secure computation, applied to a multi-party secure computation server, the method comprising:

[0036] Receive the relative expression level of the second gene sent by the user terminal; the relative expression level of the second gene is the relative gene expression level between the expression profile data of the second gene to be identified in the user terminal and the preset internal reference gene expression profile data.

[0037] The system receives the relative expression levels of a first gene and the preset categories corresponding to those relative expression levels from the expression profile data provider server. The relative expression level of the first gene is the relative gene expression level between the first gene expression profile data and the preset internal reference gene expression profile data in the expression profile data provider server. The gene identifiers of the first gene expression profile data and the second gene expression profile data correspond to each other.

[0038] The identification result determines the association between the second gene expression profile data and the preset category based on the relative expression level of the first gene, the relative expression level of the second gene, and the preset category.

[0039] Optionally, in the method described above, the identification result of determining the association between the second gene expression profile data and the preset category based on the relative expression level of the first gene, the relative expression level of the second gene, and the preset category includes:

[0040] The similarity between the relative expression levels of the first gene and the relative expression levels of the second gene in the same category is determined according to the preset category.

[0041] The identification result of the association between the second gene expression profile data and the preset category is determined based on the similarity and the preset similarity threshold.

[0042] Optionally, in the method described above, the second relative gene expression level includes the relative gene expression levels corresponding to multiple gene markers; the first relative gene expression level includes the relative gene expression levels corresponding to the multiple gene markers.

[0043] Determining the similarity between the relative expression levels of the first gene and the second gene within the same category according to the preset category includes:

[0044] The number of similar genes that meet the preset conditions is determined within the same category according to the preset category; the preset conditions are that the relative expression levels of the first gene and the second gene corresponding to the same gene identifier are equal;

[0045] The similarity is determined by the quotient of the number of similar genes and the total number of gene identifiers in the same category.

[0046] Optionally, in the method described above, the preset category is a cell identifier or a tissue identifier;

[0047] The identification result of determining the association between the second gene expression profile data and the preset category based on the similarity and the preset similarity threshold includes:

[0048] If the similarity within the same category is greater than or equal to the preset similarity threshold, then the identification result is determined to be an association between the second gene expression profile data and the corresponding cell or tissue identifier;

[0049] If the similarity within the same category is less than the preset similarity threshold, then the identification result is determined to be that the second gene expression profile data is not associated with the corresponding cell or tissue identifier.

[0050] A fourth aspect of this invention provides a medical information expression profile processing device based on privacy protection and multi-party secure computation, located on an expression profile data providing server, the device comprising:

[0051] The acquisition module is used to acquire first gene expression profile data and a preset category corresponding to the first gene expression profile data; the first gene expression profile data corresponds to the gene identifier of the second gene expression profile data to be identified in the user terminal.

[0052] The determination module is used to determine the relative expression level of the first gene between the first gene expression profile data and the preset internal reference gene expression profile data.

[0053] The sending module is used to send the first gene relative expression level and the preset category to a multi-party secure computing server, so that the multi-party secure computing server can determine the identification result of the association between the second gene expression profile data and the preset category based on the first gene relative expression level, the second gene relative expression level and the preset category; the second gene relative expression level is the gene relative expression level between the second gene expression profile data and the preset internal reference gene expression profile data.

[0054] Optionally, in the apparatus described above, the acquisition module is specifically used for:

[0055] Obtain the gene identifier corresponding to the second gene expression profile data to be identified in the user terminal; obtain the gene expression profile queue data corresponding to the gene identifier and the preset category corresponding to the gene expression profile queue data from a preset database; the preset database stores the mapping relationship between gene identifiers, gene expression profile queue data and preset categories corresponding to the gene expression profile queue data; the gene expression profile queue data has a mapping relationship with at least one preset category; perform RNA sequencing standardization processing on the gene expression profile queue data to generate the first gene expression profile data; determine the preset category corresponding to the gene expression profile queue data as the preset category corresponding to the first gene expression profile data.

[0056] Optionally, in the apparatus described above, the determining module is specifically used for:

[0057] The t-test algorithm is used to determine the corresponding t-value based on the first gene expression profile data and the preset internal reference gene expression profile data. The corresponding t-limit table is consulted based on the t-value to determine the p-value, which is the result parameter of the decision hypothesis test. The p-value, the first gene expression profile data and the preset internal reference gene expression profile data are input into the preset relative expression level algorithm to determine the relative expression level of the first gene corresponding to the p-value.

[0058] Optionally, in the apparatus described above, the first gene expression profile data includes expression profile data corresponding to multiple identical gene identifiers; the preset internal reference gene expression profile data includes expression profile data corresponding to multiple identical internal reference genes.

[0059] When the determining module uses the t-validation algorithm to determine the corresponding validation statistic t value based on the first gene expression profile data and the preset internal reference gene expression profile data, it is specifically used for:

[0060] Calculate the variance, mean, and total number of gene identifiers for the expression profile data corresponding to the same gene identifier in the first gene expression profile data; calculate the variance, mean, and total number of internal reference genes for the expression profile data corresponding to the same internal reference gene in the preset internal reference gene expression profile data; input the variance, mean, and total number of gene identifiers for the expression profile data corresponding to the same gene identifier in the first gene expression profile data and the variance, mean, and total number of internal reference genes for the expression profile data corresponding to the same internal reference gene in the preset internal reference gene expression profile data into the t-validation algorithm to determine the corresponding validation statistic t value.

[0061] A fifth aspect of this invention provides a medical information expression spectrum processing device based on privacy protection and multi-party secure computation, located in a user terminal, the device comprising:

[0062] The determination module is used to determine the relative expression level of the second gene between the second gene expression profile data to be identified and the preset internal reference gene expression profile data.

[0063] The sending module is used to send the relative expression level of the second gene to a multi-party secure computing server, so that the multi-party secure computing server can determine the identification result of the association between the second gene expression profile data and the preset category based on the relative expression level of the first gene, the relative expression level of the second gene, and the preset category; the preset category is the category corresponding to the first gene expression profile data in the expression profile data providing server; the gene identifiers of the first gene expression profile data and the second gene expression profile data correspond; the relative expression level of the first gene is the relative expression level of the gene between the first gene expression profile data and the preset internal reference gene expression profile data.

[0064] Optionally, in the apparatus described above, the determining module is specifically used for:

[0065] The t-test algorithm is used to determine the corresponding t-value based on the second gene expression profile data and the preset internal reference gene expression profile data. The corresponding t-limit table is consulted based on the t-value to determine the p-value, which is the result parameter of the decision hypothesis test. The p-value, the second gene expression profile data and the preset internal reference gene expression profile data are input into the preset relative expression level algorithm to determine the relative expression level of the second gene corresponding to the p-value.

[0066] Optionally, in the device described above, the second gene expression profile data includes expression profile data corresponding to multiple identical gene identifiers; the preset internal reference gene expression profile data includes expression profile data corresponding to multiple identical internal reference genes.

[0067] When the determining module uses the t-validation algorithm to determine the corresponding validation statistic t value based on the second gene expression profile data and the preset internal reference gene expression profile data, it is specifically used for:

[0068] Calculate the variance, mean, and total number of gene identifiers for the expression profile data corresponding to the same gene identifier in the second gene expression profile data; calculate the variance, mean, and total number of internal reference genes for the expression profile data corresponding to the same internal reference gene in the preset internal reference gene expression profile data; input the variance, mean, and total number of gene identifiers for the expression profile data corresponding to the same gene identifier in the second gene expression profile data and the variance, mean, and total number of internal reference genes for the expression profile data corresponding to the same internal reference gene in the preset internal reference gene expression profile data into the t-validation algorithm to determine the corresponding validation statistic t value.

[0069] A sixth aspect of this invention provides a medical information expression spectrum processing device based on privacy protection and multi-party secure computation, located on a multi-party secure computation server, the device comprising:

[0070] The first receiving module is used to receive the relative expression level of the second gene sent by the user terminal; the relative expression level of the second gene is the relative gene expression level between the second gene expression profile data to be identified in the user terminal and the preset internal reference gene expression profile data.

[0071] The second receiving module is used to receive the relative expression level of a first gene and the preset category corresponding to the relative expression level of the first gene sent by the expression profile data providing server; the relative expression level of the first gene is the relative expression level of the gene between the first gene expression profile data and the preset internal reference gene expression profile data in the expression profile data providing server; the gene identifiers of the first gene expression profile data and the second gene expression profile data correspond to each other.

[0072] The identification module is used to determine the identification result of the association between the second gene expression profile data and the preset category based on the relative expression level of the first gene, the relative expression level of the second gene, and the preset category.

[0073] Optionally, in the apparatus described above, the identification module is specifically used for:

[0074] The similarity between the relative expression levels of the first gene and the relative expression levels of the second gene within the same category is determined according to the preset category; the identification result of the association between the second gene expression profile data and the preset category is determined based on the similarity and the preset similarity threshold.

[0075] Optionally, in the device described above, the second relative gene expression level includes the relative gene expression levels corresponding to multiple gene identifiers; the first relative gene expression level includes the relative gene expression levels corresponding to the multiple gene identifiers.

[0076] When determining the similarity between the relative expression levels of the first gene and the relative expression levels of the second gene within the same category according to the preset category, the identification module is specifically used for:

[0077] The number of similar genes that meet the preset conditions is determined in the same category according to the preset category; the preset conditions are that the relative expression levels of the first gene and the second gene corresponding to the same gene identifier are equal; the similarity is determined by the quotient of the number of similar genes and the total number of gene identifiers in the same category.

[0078] Optionally, in the device described above, the preset category is a cell identifier or a tissue identifier;

[0079] When determining the recognition result of the association between the second gene expression profile data and the preset category based on the similarity and the preset similarity threshold, the recognition module is specifically used for:

[0080] If the similarity within the same category is greater than or equal to the preset similarity threshold, the identification result is determined to be that the second gene expression profile data is associated with the corresponding cell identifier or tissue identifier; if the similarity within the same category is less than the preset similarity threshold, the identification result is determined to be that the second gene expression profile data is not associated with the corresponding cell identifier or tissue identifier.

[0081] A seventh aspect of the present invention provides an expression profile data providing server, comprising: a processor, a memory, and a transceiver;

[0082] The processor, the memory, and the transceiver circuit are interconnected;

[0083] The memory stores computer-executed instructions; the transceiver is used for sending and receiving data.

[0084] The processor executes computer execution instructions stored in the memory to implement the medical information expression spectrum processing method based on privacy protection and multi-party secure computation as described in any of the first aspects.

[0085] An eighth aspect of the present invention provides a user terminal, including: a processor, a memory, and a transceiver;

[0086] The processor, the memory, and the transceiver circuit are interconnected;

[0087] The memory stores computer-executed instructions; the transceiver is used for sending and receiving data.

[0088] The processor executes computer execution instructions stored in the memory to implement the medical information expression spectrum processing method based on privacy protection and multi-party secure computation as described in any of the second aspects.

[0089] A ninth aspect of this invention provides a multi-party secure computing server, comprising: a processor, a memory, and a transceiver;

[0090] The processor, the memory, and the transceiver circuit are interconnected;

[0091] The memory stores computer-executed instructions; the transceiver is used for sending and receiving data.

[0092] The processor executes the computer execution instructions stored in the memory to implement the medical information expression spectrum processing method based on privacy protection and multi-party secure computation as described in any of the third aspects.

[0093] The tenth aspect of this invention provides a computer-readable storage medium storing computer-executable instructions, which, when executed by a processor, are used to implement the medical information expression spectrum processing method based on privacy protection and multi-party secure computation as described in any one of the first, second, or third aspects.

[0094] The eleventh aspect of this invention provides a computer program product, including a computer program that, when executed by a processor, implements the medical information expression spectrum processing method based on privacy protection and multi-party secure computation as described in any one of the first, second, or third aspects.

[0095] This invention provides a medical information expression profile processing method based on privacy protection and multi-party secure computation, applied to an expression profile data providing server. The method includes: acquiring first gene expression profile data and a preset category corresponding to the first gene expression profile data; the first gene expression profile data corresponding to a gene identifier of a second gene expression profile data to be identified in a user terminal; determining a first gene relative expression level between the first gene expression profile data and preset internal reference gene expression profile data; sending the first gene relative expression level and the preset category to a multi-party secure computation server, so that the multi-party secure computation server determines the identification result of the association between the second gene expression profile data and the preset category based on the first gene relative expression level, the second gene relative expression level, and the preset category; the second gene relative expression level is the gene relative expression level between the second gene expression profile data and the preset internal reference gene expression profile data. The medical information expression profile processing method based on privacy protection and multi-party secure computation of this invention sends the relative expression levels of a first gene and the corresponding preset categories of a preset internal reference gene expression profile to a multi-party secure computation server. This allows the multi-party secure computation server to determine the association between the second gene expression profile data and the preset categories based on the relative expression levels of the first and second genes and the preset categories. Since the multi-party secure computation server is unaware of the first and second gene expression profile data, it avoids disclosing the privacy data of the expression profile data providing server and the user terminal, thus improving the security of the privacy data processing process. Attached Figure Description

[0096] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with the invention and, together with the description, serve to explain the principles of the invention.

[0097] Figure 1 This is a scenario diagram illustrating the medical information expression spectrum processing method based on privacy protection and multi-party secure computation, as described in the embodiments of the present invention.

[0098] Figure 2 A flowchart illustrating the medical information expression spectrum processing method based on privacy protection and multi-party secure computation provided by this invention. Figure 1 ;

[0099] Figure 3 A flowchart illustrating the medical information expression spectrum processing method based on privacy protection and multi-party secure computation provided by this invention. Figure 2 ;

[0100] Figure 4 A flowchart illustrating the medical information expression spectrum processing method based on privacy protection and multi-party secure computation provided by this invention. Figure 3 ;

[0101] Figure 5 Schematic diagram of the medical information expression spectrum processing device based on privacy protection and multi-party secure computation provided by the present invention Figure 1 ;

[0102] Figure 6 Schematic diagram of the medical information expression spectrum processing device based on privacy protection and multi-party secure computation provided by the present invention Figure 2 ;

[0103] Figure 7 Schematic diagram of the medical information expression spectrum processing device based on privacy protection and multi-party secure computation provided by the present invention Figure 3 ;

[0104] Figure 8 A schematic diagram of the structure of the server providing the expression spectrum data provided by this invention.

[0105] The accompanying drawings have illustrated specific embodiments of the invention, which will be described in more detail below. These drawings and descriptions are not intended to limit the scope of the invention in any way, but rather to illustrate the concept of the invention to those skilled in the art through reference to particular embodiments. Detailed Implementation

[0106] Exemplary embodiments will now be described in detail, examples of which are illustrated in the accompanying drawings. When the following description relates to the drawings, unless otherwise indicated, the same numerals in different drawings denote the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the present invention. Rather, they are merely examples of apparatuses and methods consistent with some aspects of the invention as detailed in the appended claims.

[0107] The technical solution of the present invention will be described in detail below with reference to specific embodiments. These specific embodiments can be combined with each other, and the same or similar concepts or processes may not be described again in some embodiments. The embodiments of the present invention will now be described with reference to the accompanying drawings.

[0108] To clearly understand the technical solution of this application, the existing technology will first be described in detail. In the current medical field, to identify whether someone has diseased cells, the gene expression profile data of suspected diseased cells can be matched against a gene expression profile database of diseased cells to determine the presence of diseased cells. However, obtaining the expression profile of this specific cell or tissue subtype is difficult, and it is generally considered private data of each institution. If this private data is used in practice to identify the expression profile of unknown cells, it could easily lead to data leakage, resulting in low security in the private data processing process.

[0109] Therefore, addressing the issues of data leakage and low security in privacy data processing among various institutions in existing technologies, the inventors discovered that a trusted execution environment, such as a multi-party secure computation server, can be added to both the privacy data and the data to be identified. This trusted execution environment allows for data comparison and identification. Furthermore, to enhance the security of privacy data, intermediate processing can be applied to the gene expression profile data provided by the data provider (i.e., the gene expression profile data provider server), ensuring that the data uploaded to the multi-party secure computation server is not the original gene expression profile data, thereby improving the security of privacy data.

[0110] Specifically, taking an expression profile data provider server as the data provider and a user terminal as the demand identifier as an example, the expression profile data provider server obtains first gene expression profile data and a preset category corresponding to the first gene expression profile data. The first gene expression profile data corresponds to the gene identifier of the second gene expression profile data to be identified in the user terminal. Simultaneously, it determines the first gene relative expression level between the first gene expression profile data and the preset internal reference gene expression profile data; this first gene relative expression level is the aforementioned intermediate data. The first gene relative expression level and the preset category are sent to a multi-party secure computing server, so that the multi-party secure computing server can determine the identification result of the association between the second gene expression profile data and the preset category based on the first gene relative expression level, the second gene relative expression level, and the preset category. The second gene relative expression level is the gene relative expression level between the second gene expression profile data and the preset internal reference gene expression profile data. Since the multi-party secure computing server is unaware of the first and second gene expression profile data, it does not leak the privacy data of the expression profile data provider server and the user terminal, thus improving the security of the privacy data processing process.

[0111] Based on the above-mentioned inventive discovery, the inventor has proposed the technical solution of this application.

[0112] The following describes the application scenarios of the medical information expression spectrum processing method based on privacy protection and multi-party secure computation provided in the embodiments of the present invention. For example... Figure 1 As shown, 1 is the expression spectrum data providing server, 2 is the user terminal, and 3 is the multi-party secure computation server. User terminal 2 can be a smart terminal or other electronic device, which is not limited in this embodiment.

[0113] The network architecture of the medical information expression profile processing method based on privacy protection and multi-party secure computation provided in this embodiment of the invention includes: an expression profile data providing server 1, a user terminal 2, and a multi-party secure computation server 3. When the user terminal 2 needs to identify gene expression profile data, the expression profile data providing server 1 and the user terminal 2 process their own gene expression profile data simultaneously or sequentially. The expression profile data providing server 1 obtains first gene expression profile data and a preset category corresponding to the first gene expression profile data. The first gene expression profile data corresponds to the gene identifier of the second gene expression profile data to be identified in the user terminal, and the preset category can be a cell name or tissue name. Simultaneously, the expression profile data providing server 1 determines the relative expression level of a first gene between the first gene expression profile data and the preset internal reference gene expression profile data, and sends the relative expression level of the first gene and the preset category to the multi-party secure computation server 3.

[0114] Similar to the expression profile data providing server 1, user terminal 2 determines the relative expression level of the second gene between the expression profile data of the second gene to be identified and the preset internal reference gene expression profile data, and sends the relative expression level of the second gene to the multi-party secure computing server 3.

[0115] After receiving the relative expression level of a first gene, the preset category corresponding to the relative expression level of the first gene, and the relative expression level of a second gene, the multi-party secure computing server 3 determines the identification result of the association between the second gene expression profile data and the preset category based on the relative expression levels of the first and second genes and the preset category. The identification result can be either "association exists" or "no association exists." If an association exists, it means that the second gene expression profile data to be identified by user terminal 2 is related to the corresponding category, such as cell name or tissue name, and contains the corresponding cell or tissue. After the multi-party secure computing server 3 determines the identification result, it can send the identification result to user terminal 2 and expression profile data providing server 1, so that user terminal 2 and expression profile data providing server 1 can obtain the result of this identification and perform subsequent analysis processes.

[0116] The embodiments of the present invention will now be described with reference to the accompanying drawings.

[0117] Figure 2 A flowchart illustrating the medical information expression spectrum processing method based on privacy protection and multi-party secure computation provided by this invention. Figure 1 ,like Figure 2As shown, in this embodiment, the executing entity of this invention is a medical information expression spectrum processing device based on privacy protection and multi-party secure computation. This medical information expression spectrum processing device based on privacy protection and multi-party secure computation can be integrated into an expression spectrum data providing server. Therefore, the medical information expression spectrum processing method based on privacy protection and multi-party secure computation provided in this embodiment includes the following steps:

[0118] Step S101: Obtain the first gene expression profile data and the preset category corresponding to the first gene expression profile data. The first gene expression profile data corresponds to the gene identifier of the second gene expression profile data to be identified in the user terminal.

[0119] In this embodiment, the first gene expression profile data is standardized continuous expression profile data. The first gene expression profile data can be gene expression profile data corresponding to multiple gene identifiers, or it can be gene expression profile data corresponding to one gene identifier. In practical applications, gene expression profile data corresponding to multiple gene identifiers is generally used.

[0120] The first gene expression profile data, gene identifiers, and preset categories have a mapping relationship. For example, the gene name in the first gene expression profile data is EGFR, and the corresponding preset categories are lung cancer and CT4+ cells. The first gene expression profile data and gene names have a one-to-one mapping relationship. Since different cells or tissues may contain the same gene, if the preset category is a cell name or tissue name, then the first gene expression profile data and the preset category have a one-to-one or one-to-many relationship; the first gene expression profile data can correspond to multiple categories. Similarly, the gene name and the preset category have a one-to-one or one-to-many relationship.

[0121] In this embodiment, after the gene identifier corresponding to the second gene expression profile data is determined, the gene identifier of the first gene expression profile data must be the same as the gene identifier of the second gene expression profile data, thereby providing a basis for the subsequent identification process.

[0122] Optionally, in this embodiment, step S101 can specifically be as follows:

[0123] Obtain the gene identifier corresponding to the second gene expression profile data to be identified in the user terminal.

[0124] Retrieve gene expression profile queue data corresponding to gene identifiers and the corresponding preset categories from a preset database. The preset database stores the mapping relationships between gene identifiers, gene expression profile queue data, and the preset categories corresponding to the gene expression profile queue data. Each gene expression profile queue data has a mapping relationship with at least one preset category.

[0125] RNA sequencing normalization was performed on the gene expression profile cohort data to generate the first gene expression profile data.

[0126] The preset category corresponding to the gene expression profile cohort data is determined as the preset category corresponding to the first gene expression profile data.

[0127] The pre-set database can be TCGA (The Cancer Genome Atlas) to enrich the gene expression profiling cohort data available for identification. RNA sequencing standardization of the gene expression profiling cohort data is performed to standardize and maintain the data continuity, facilitating subsequent data processing and improving the accuracy of relative gene expression levels.

[0128] Step S102: Determine the relative expression level of the first gene between the first gene expression profile data and the preset internal reference gene expression profile data.

[0129] In this embodiment, the relative expression level of the first gene refers to the relative expression level between the first gene expression profile data and the preset internal reference gene expression profile data. Assuming the gene expression profile data for gene TP53 is 2 and the preset internal reference gene expression profile data is 15, the corresponding relative expression level of the first gene can be determined as -1 according to the preset relative expression level algorithm. If different preset relative expression level algorithms are set, the obtained relative expression level of the first gene may be different. However, since the user terminal also uses the same preset relative expression level algorithm to process the data, it will not affect the comparison between the relative expression level of the first gene and the relative expression level of the second gene.

[0130] Optionally, in this embodiment, step S102 can specifically be as follows:

[0131] The t-validation algorithm is used to determine the corresponding validation statistic t value based on the expression profile data of the first gene and the expression profile data of the preset internal reference gene.

[0132] The p-value is determined by querying the corresponding t-boundary table based on the t-value to determine the p-value of the hypothesis test result corresponding to the t-value.

[0133] Input the p-value, the first gene expression profile data, and the preset internal reference gene expression profile data into the preset relative expression level algorithm to determine the relative expression level of the first gene corresponding to the p-value.

[0134] The t-test algorithm can be used to verify whether the first gene expression profile data and the preset internal reference gene expression profile data come from the same distribution, thereby improving the accuracy of determining the correlation between the two.

[0135] After determining the t-value, based on the data statistics method, the corresponding t-boundary table can be consulted to determine the specific value of the p-value corresponding to that t-value. The p-value is generally between 0 and 1, such as 0.01, 0.05, etc. Then, combined with a preset relative expression level algorithm, the relative expression level of the first gene corresponding to the p-value is determined.

[0136] Optionally, in this embodiment, the first gene expression profile data includes expression profile data corresponding to multiple identical gene identifiers. The preset internal reference gene expression profile data includes expression profile data corresponding to multiple identical internal reference genes.

[0137] The process of determining the corresponding t-value of the validation statistic based on the expression profile data of the first gene and the expression profile data of the preset internal reference gene using the t-validation algorithm can be as follows:

[0138] Calculate the variance, mean, and total number of gene markers for the same gene marker in the first gene expression profile data.

[0139] Calculate the variance, mean, and total number of internal reference genes for the expression profile data corresponding to the same internal reference gene in the preset internal reference gene expression profile data.

[0140] The variance, mean, and total number of gene identifiers corresponding to the same gene identifier in the first gene expression profile data, and the variance, mean, and total number of internal reference genes corresponding to the same internal reference gene in the preset internal reference gene expression profile data are input into the t-validation algorithm to determine the corresponding validation statistic t value.

[0141] In this embodiment, the t-verification algorithm is as follows:

[0142]

[0143] in, and X1 and X2 represent the variances of the gene expression profile data and the preset internal reference gene expression profile data, respectively. X1 and X2 represent the mean values ​​of the gene expression profile data and the preset internal reference gene expression profile data, respectively. n1 and n2 represent the sample sizes of the gene expression profile data and the preset internal reference gene expression profile data, respectively. A subscript of 1 indicates the former (gene expression profile data and preset internal reference gene expression profile data), and a subscript of 2 indicates the latter (gene expression profile data and preset internal reference gene expression profile data).

[0144] Gene expression profile data can be either first gene expression profile data or second gene expression profile data.

[0145] Subsequently, based on the t-test results, 0.05 was set as the boundary value using conventional statistical methods. The preset relative expression level algorithm is as follows:

[0146]

[0147] Where X1 and X2 are the same as in the t-validation algorithm above, representing the average values ​​of a gene expression profile and a preset internal reference gene expression profile, respectively, and Ex is the relative expression level of the gene.

[0148] In the above-described algorithm for relative gene expression levels, the range and method of dividing relative gene expression levels are only illustrative examples. The range and method of dividing relative gene expression levels can be set according to actual needs; for example, it can be divided into five conditions: -2, -1, 0, 1, and 2. It can also be divided into more levels to obtain more accurate relative gene expression levels.

[0149] Step S103: The relative expression level of the first gene and the preset category are sent to the multi-party secure computing server, so that the multi-party secure computing server can determine the identification result of the association between the second gene expression profile data and the preset category based on the relative expression level of the first gene, the relative expression level of the second gene, and the preset category. The relative expression level of the second gene is the relative gene expression level between the second gene expression profile data and the preset internal reference gene expression profile data.

[0150] The multi-party secure computation server mainly compares whether the relative expression levels of the first gene and the second gene corresponding to each gene identifier in the same category are the same, thereby determining the similarity between the first gene expression profile data and the second gene expression profile data, and whether the second gene expression profile data is associated with the preset category.

[0151] The generation method for the relative expression level of the second gene is similar to that for the generation method of the relative expression level of the first gene. It is generated by determining the relative expression level of the second gene expression profile data and the preset internal reference gene expression profile data.

[0152] In this embodiment, the preset internal reference gene expression profile data can be selected according to actual needs. The preset internal reference gene expression profile data selected by the expression profile data providing server and the preset internal reference gene expression profile data selected by the user terminal can be different. When the preset internal reference gene expression profile data selected by the expression profile data providing server and the preset internal reference gene expression profile data selected by the user terminal are the same, the subsequent recognition effect can be improved.

[0153] This invention provides a medical information expression profile processing method based on privacy protection and multi-party secure computation. By sending the relative expression levels of a first gene and its corresponding preset category between first gene expression profile data and preset internal reference gene expression profile data to a multi-party secure computation server, the server can determine the association between the second gene expression profile data and the preset category based on the relative expression levels of the first and second genes and the preset category. Since the multi-party secure computation server is unaware of the first and second gene expression profile data, it avoids disclosing the privacy data of the expression profile data providing server and the user terminal, thus improving the security of the privacy data processing process.

[0154] Figure 3 A flowchart illustrating the medical information expression spectrum processing method based on privacy protection and multi-party secure computation provided by this invention. Figure 2 ,like Figure 3 As shown, the medical information expression spectrum processing method based on privacy protection and multi-party secure computation provided in this embodiment is executed by a medical information expression spectrum processing device based on privacy protection and multi-party secure computation, which can be integrated into a user terminal. The medical information expression spectrum processing method based on privacy protection and multi-party secure computation provided in this embodiment includes the following steps:

[0155] Step S201: Determine the relative expression level of the second gene between the expression profile data of the second gene to be identified and the preset internal reference gene expression profile data.

[0156] The second gene expression profile data in this embodiment is the same as the first gene expression profile data, which is also a standardized continuous expression profile data. If the gene expression profile data to be identified by the user terminal is non-standardized and non-continuous data, then RNA sequencing standardization processing is required.

[0157] Optionally, in this embodiment, determining the relative expression level of the second gene between the second gene expression profile data and the preset internal reference gene expression profile data includes:

[0158] The t-validation algorithm is used to determine the corresponding validation statistic t value based on the expression profile data of the second gene and the expression profile data of the preset internal reference gene.

[0159] The p-value is determined by querying the corresponding t-boundary table based on the t-value to determine the p-value of the hypothesis test result corresponding to the t-value.

[0160] Input the p-value, the second gene expression profile data, and the preset internal reference gene expression profile data into the preset relative expression level algorithm to determine the relative expression level of the second gene corresponding to the p-value.

[0161] Optionally, in this embodiment, the second gene expression profile data includes expression profile data corresponding to multiple identical gene identifiers. The preset internal reference gene expression profile data includes expression profile data corresponding to multiple identical internal reference genes.

[0162] The t-validation algorithm is used to determine the corresponding validation statistic t-value based on the expression profile data of the second gene and the expression profile data of the preset internal reference gene, including:

[0163] Calculate the variance, mean, and total number of gene markers for the expression profile data corresponding to the same gene marker in the second gene expression profile data.

[0164] Calculate the variance, mean, and total number of internal reference genes for the expression profile data corresponding to the same internal reference gene in the preset internal reference gene expression profile data.

[0165] The variance, mean, and total number of gene identifiers corresponding to the same gene identifier in the second gene expression profile data, and the variance, mean, and total number of internal reference genes corresponding to the same internal reference gene in the preset internal reference gene expression profile data are input into the t-validation algorithm to determine the corresponding validation statistic t value.

[0166] In this embodiment, the implementation of step 201 and its optional embodiments is similar to that of step 102 in the previous embodiment of the present invention, and will not be described in detail here.

[0167] Step S202: The relative expression level of the second gene is sent to a multi-party secure computing server, so that the multi-party secure computing server determines the identification result of the association between the second gene expression profile data and the preset category based on the relative expression level of the first gene, the relative expression level of the second gene, and the preset category. The preset category is the category corresponding to the first gene expression profile data in the expression profile data providing server. The gene identifiers of the first gene expression profile data and the second gene expression profile data correspond. The relative expression level of the first gene is the relative gene expression level between the first gene expression profile data and the preset internal reference gene expression profile data.

[0168] In this embodiment, in order to improve the accuracy of subsequent identification results, the user terminal adopts the same data processing method as the expression profile data providing server. It also determines the relative expression level of the second gene between the second gene expression profile data to be identified and the preset internal reference gene expression profile data, and sends the relative expression level of the second gene to a multi-party secure computing server for identification process processing, thereby improving the security of privacy data.

[0169] Figure 4 A flowchart illustrating the medical information expression spectrum processing method based on privacy protection and multi-party secure computation provided by this invention. Figure 3 ,like Figure 4As shown, the medical information expression spectrum processing method based on privacy protection and multi-party secure computation provided in this embodiment is executed by a medical information expression spectrum processing device based on privacy protection and multi-party secure computation, which can be integrated into a multi-party secure computation server. The medical information expression spectrum processing method based on privacy protection and multi-party secure computation provided in this embodiment includes the following steps:

[0170] Step S301: Receive the relative expression level of the second gene sent by the user terminal. The relative expression level of the second gene is the relative gene expression level between the expression profile data of the second gene to be identified in the user terminal and the preset internal reference gene expression profile data.

[0171] Step S302: Receive the relative expression level of a first gene and the preset category corresponding to the relative expression level of the first gene sent by the expression profile data providing server. The relative expression level of the first gene is the relative gene expression level between the first gene expression profile data and the preset internal reference gene expression profile data in the expression profile data providing server. The gene identifiers of the first gene expression profile data and the second gene expression profile data correspond.

[0172] Step S303: Determine the identification result of the association between the second gene expression profile data and the preset category based on the relative expression level of the first gene, the relative expression level of the second gene, and the preset category.

[0173] In this embodiment, during multi-party data analysis and processing, a trusted execution environment can be set up on the multi-party secure computing server, and identification and analysis processing can be performed in the trusted execution environment.

[0174] The relative expression levels of the first and second genes can be categorized using preset categories. For example, lung cancer corresponds to six genes, so the relative expression levels of the first and second genes for those six genes can be grouped together. Other types can have their relative expression levels of the first and second genes grouped together. The relative expression levels of the first and second genes within each category can then be compared separately.

[0175] Optionally, in this embodiment, step S303 can specifically be:

[0176] The similarity between the relative expression levels of the first gene and the relative expression levels of the second gene within the same category is determined according to a preset category.

[0177] The identification results determine the association between the second gene expression profile data and the preset category based on similarity and a preset similarity threshold.

[0178] For example, lung cancer corresponds to 6 genes, and each gene corresponds to the relative expression level of the first gene and the relative expression level of the second gene. If all genes have the same relative expression level of the first gene and the same relative expression level of the second gene, the similarity is 100%. If only 3 genes have the same relative expression level of the first gene and the same relative expression level of the second gene, the similarity is 50%.

[0179] By using similarity and preset similarity thresholds, the identification results of the association between the second gene expression profile data and preset categories can be determined, thereby preventing the leakage of private data and improving the security of private data.

[0180] In this embodiment, the preset similarity threshold can be set according to the actual application scenario, for example, it can be set to 50%.

[0181] Optionally, in this embodiment, the second gene relative expression level includes the gene relative expression levels corresponding to multiple gene markers. The first gene relative expression level includes the gene relative expression levels corresponding to multiple gene markers.

[0182] The process of determining the similarity between the relative expression levels of the first gene and the second gene within the same category according to a preset category can be specifically as follows:

[0183] The number of similar genes that meet preset criteria is determined within each preset category. The preset criteria are that the relative expression levels of the first gene and the second gene corresponding to the same gene identifier are equal.

[0184] The similarity is determined by the quotient of the number of similar genes and the total number of gene markers in the same category.

[0185] For example, a category contains three genes and their corresponding relative expression levels for the first and second genes. The first gene has a relative expression level of 1 and the second gene has a relative expression level of 1; the second gene has a relative expression level of 1 and the second gene has a relative expression level of 0; and the third gene has a relative expression level of -1 and the second gene has a relative expression level of -1. In this case, the number of similar genes is 2, the total number of gene markers in the same category is 3, and the similarity is two-thirds. This simple similarity calculation method can improve the efficiency of overall similarity calculation.

[0186] Optionally, in this embodiment, the preset category is cell identifier or tissue identifier.

[0187] The process for determining the recognition result can be specifically as follows:

[0188] If the similarity within the same category is greater than or equal to the preset similarity threshold, the identification result is determined to be the association between the second gene expression profile data and the corresponding cell or tissue identifier.

[0189] If the similarity within the same category is less than the preset similarity threshold, the identification result is determined to be that the second gene expression profile data is not associated with the corresponding cell or tissue identifier.

[0190] In the medical field, if a patient's second gene expression profile data is found to be associated with the name of a diseased cell after instrument testing, it means the patient contains that diseased cell. The more precise the preset similarity threshold is set, the more accurate the final identification result will be.

[0191] To further illustrate the medical information expression spectrum processing method based on privacy protection and multi-party secure computation in this embodiment, examples of practical application results will be provided below in conjunction with Tables 1-3.

[0192] Table 1 Data Provider Data Table

[0193]

[0194] In this embodiment, the expression profile data provider server acts as the data provider, providing six gene expression profiles as shown in Table 1. The gene names are EGFR, TP53, FLT4, ERBB2, BACH1, and TPO. These six gene names are the same as the six gene names provided by the user terminal as the data query party. These six gene names correspond to two preset categories: Lung Cancer and CT4+ cells. Table 1 shows the gene expression profile data provided by the expression profile data provider server, the selected internal reference gene expression profile data, and the relative gene expression levels between the gene expression profile data and the internal reference gene expression profile data.

[0195] Table 2 Data query data table

[0196]

[0197] Table 2 shows the gene expression profile data provided by the user terminal, the selected internal reference gene expression profile data, and the relative gene expression levels between the gene expression profile data and the internal reference gene expression profile data. After the multi-party secure computation server processed the data in Tables 1 and 2, the results are shown in Table 3.

[0198] Table 3 Comparison Results

[0199]

[0200] In the comparison of the relative expression levels of the six gene names in the lung cancer category, only four were the same, while in the comparison of the relative expression levels of the three gene names in the CT4+ category, only two were the same. Therefore, the similarity between lung cancer and CT4+ is two-thirds. If the similarity threshold is set to 0.5, then in this embodiment, the gene expression profile data provided by the user terminal may be from either lung cancer cells or CT4+ cells.

[0201] Figure 5 Schematic diagram of the medical information expression spectrum processing device based on privacy protection and multi-party secure computation provided by the present invention Figure 1 ,like Figure 5 As shown, in this embodiment, the medical information expression spectrum processing device 400 based on privacy protection and multi-party secure computation is located on the expression spectrum data providing server. The medical information expression spectrum processing device 400 based on privacy protection and multi-party secure computation includes:

[0202] The acquisition module 401 is used to acquire the first gene expression profile data and the preset category corresponding to the first gene expression profile data. The first gene expression profile data corresponds to the gene identifier of the second gene expression profile data to be identified in the user terminal.

[0203] The determination module 402 is used to determine the relative expression level of the first gene between the first gene expression profile data and the preset internal reference gene expression profile data.

[0204] The sending module 403 is used to send the relative expression level of the first gene and the preset category to the multi-party secure computing server, so that the multi-party secure computing server can determine the identification result of the association between the second gene expression profile data and the preset category based on the relative expression level of the first gene, the relative expression level of the second gene, and the preset category. The relative expression level of the second gene is the relative gene expression level between the second gene expression profile data and the preset internal reference gene expression profile data.

[0205] Optionally, in this embodiment, the acquisition module 401 is specifically used for:

[0206] Obtain the gene identifier corresponding to the second gene expression profile data to be identified in the user terminal. Retrieve the gene expression profile queue data corresponding to the gene identifier and the preset category corresponding to the gene expression profile queue data from a preset database. The preset database stores the mapping relationship between gene identifiers, gene expression profile queue data, and the preset categories corresponding to the gene expression profile queue data. The gene expression profile queue data has a mapping relationship with at least one preset category. Perform RNA sequencing normalization processing on the gene expression profile queue data to generate the first gene expression profile data. Determine the preset category corresponding to the gene expression profile queue data as the preset category corresponding to the first gene expression profile data.

[0207] Optionally, in this embodiment, the determining module 402 is specifically used for:

[0208] A t-test algorithm is used to determine the corresponding t-value based on the expression profile data of the first gene and the expression profile data of a preset internal reference gene. The corresponding t-limit table is then consulted to determine the p-value, which represents the hypothesis test result. The p-value, the first gene expression profile data, and the preset internal reference gene expression profile data are then input into a preset relative expression level algorithm to determine the relative expression level of the first gene corresponding to the p-value.

[0209] Optionally, in this embodiment, the first gene expression profile data includes expression profile data corresponding to multiple identical gene identifiers. The preset internal reference gene expression profile data includes expression profile data corresponding to multiple identical internal reference genes.

[0210] When determining the corresponding verification statistic t-value using the t-validation algorithm based on the first gene expression profile data and the preset internal reference gene expression profile data, module 402 is specifically used for:

[0211] Calculate the variance, mean, and total number of gene identifiers for the expression profile data corresponding to the same gene identifier in the first gene expression profile data. Calculate the variance, mean, and total number of internal reference genes for the expression profile data corresponding to the same internal reference gene in the preset internal reference gene expression profile data. Input the variance, mean, and total number of gene identifiers for the expression profile data corresponding to the same gene identifier in the first gene expression profile data and the variance, mean, and total number of internal reference genes for the expression profile data corresponding to the same internal reference gene in the preset internal reference gene expression profile data into a t-validation algorithm to determine the corresponding validation statistic t-value.

[0212] The medical information expression spectrum processing device based on privacy protection and multi-party secure computation provided in this embodiment can perform... Figure 2 The technical solution of the method embodiment shown has the same implementation principle and technical effect as... Figure 2 The methods and embodiments shown are similar and will not be described in detail here.

[0213] Figure 6 Schematic diagram of the medical information expression spectrum processing device based on privacy protection and multi-party secure computation provided by the present invention Figure 2 ,like Figure 6 As shown, the medical information expression spectrum processing device 500 based on privacy protection and multi-party secure computation is located on the user terminal. The medical information expression spectrum processing device 500 based on privacy protection and multi-party secure computation includes:

[0214] The determination module 501 is used to determine the relative expression level of the second gene between the second gene expression profile data to be identified and the preset internal reference gene expression profile data.

[0215] The sending module 502 is used to send the relative expression level of the second gene to a multi-party secure computing server, so that the multi-party secure computing server can determine the identification result of the association between the second gene expression profile data and the preset category based on the relative expression level of the first gene, the relative expression level of the second gene, and the preset category. The preset category is the category corresponding to the first gene expression profile data in the expression profile data providing server. The gene identifiers of the first gene expression profile data and the second gene expression profile data correspond. The relative expression level of the first gene is the relative gene expression level between the first gene expression profile data and the preset internal reference gene expression profile data.

[0216] Optionally, in this embodiment, the determining module is specifically used for:

[0217] A t-test algorithm is used to determine the corresponding t-value based on the expression profile data of the second gene and the expression profile data of a preset internal reference gene. The corresponding t-limit table is then consulted to determine the p-value, which represents the hypothesis test result. The p-value, the second gene expression profile data, and the preset internal reference gene expression profile data are then input into a preset relative expression level algorithm to determine the relative expression level of the second gene corresponding to the p-value.

[0218] Optionally, in this embodiment, the second gene expression profile data includes expression profile data corresponding to multiple identical gene identifiers. The preset internal reference gene expression profile data includes expression profile data corresponding to multiple identical internal reference genes.

[0219] When determining the corresponding t-value of the validation statistic based on the expression profile data of the second gene and the preset internal reference gene expression profile data using the t-validation algorithm, the module is specifically used for:

[0220] Calculate the variance, mean, and total number of gene identifiers for the expression profile data corresponding to the same gene identifier in the second gene expression profile data. Calculate the variance, mean, and total number of internal reference genes for the expression profile data corresponding to the same internal reference gene in the preset internal reference gene expression profile data. Input the variance, mean, and total number of gene identifiers for the expression profile data corresponding to the same gene identifier in the second gene expression profile data, and the variance, mean, and total number of internal reference genes for the expression profile data corresponding to the same internal reference gene in the preset internal reference gene expression profile data, into a t-validation algorithm to determine the corresponding validation statistic t-value.

[0221] The medical information expression spectrum processing device based on privacy protection and multi-party secure computation provided in this embodiment can perform... Figure 3 The technical solution of the method embodiment shown has the same implementation principle and technical effect as... Figure 3 The methods and embodiments shown are similar and will not be described in detail here.

[0222] Figure 7 Schematic diagram of the medical information expression spectrum processing device based on privacy protection and multi-party secure computation provided by the present invention Figure 3 ,like Figure 7 As shown, the medical information expression spectrum processing device 600 based on privacy protection and multi-party secure computation is located on a multi-party secure computation server. The medical information expression spectrum processing device 600 based on privacy protection and multi-party secure computation includes:

[0223] The first receiving module 601 is used to receive the relative expression level of the second gene sent by the user terminal. The relative expression level of the second gene is the relative gene expression level between the expression profile data of the second gene to be identified in the user terminal and the preset internal reference gene expression profile data.

[0224] The second receiving module 602 is used to receive the relative expression levels of a first gene and the preset categories corresponding to the relative expression levels of the first gene, sent by the expression profile data providing server. The relative expression level of the first gene is the relative gene expression level between the first gene expression profile data and the preset internal reference gene expression profile data in the expression profile data providing server. The gene identifiers of the first gene expression profile data and the second gene expression profile data correspond.

[0225] The identification module 603 is used to determine the identification result of the association between the expression profile data of the second gene and the preset category based on the relative expression level of the first gene, the relative expression level of the second gene, and the preset category.

[0226] Optionally, in this embodiment, the identification module 603 is specifically used for:

[0227] The similarity between the relative expression levels of the first gene and the second gene within the same preset category is determined. Based on this similarity and a preset similarity threshold, the association between the second gene expression profile data and the preset category is identified.

[0228] Optionally, in this embodiment, the second gene relative expression level includes the gene relative expression levels corresponding to multiple gene markers. The first gene relative expression level includes the gene relative expression levels corresponding to multiple gene markers.

[0229] When determining the similarity between the relative expression levels of the first gene and the relative expression levels of the second gene within the same category according to a preset category, the identification module 603 is specifically used for:

[0230] The number of similar genes that meet preset criteria is determined within each preset category. The preset criteria are that the relative expression levels of the first gene and the second gene corresponding to the same gene identifier are equal. The similarity score is determined by dividing the number of similar genes by the total number of gene identifiers within the same category.

[0231] Optionally, in this embodiment, the preset category is cell identifier or tissue identifier.

[0232] When determining the association between the second gene expression profile data and the preset category based on similarity and a preset similarity threshold, the identification module 603 is specifically used for:

[0233] If the similarity within the same category is greater than or equal to a preset similarity threshold, the identification result is determined to be an association between the second gene expression profile data and the corresponding cell or tissue identifier. If the similarity within the same category is less than the preset similarity threshold, the identification result is determined to be an association between the second gene expression profile data and the corresponding cell or tissue identifier.

[0234] The medical information expression spectrum processing device based on privacy protection and multi-party secure computation provided in this embodiment can perform... Figure 4 The technical solution of the method embodiment shown has the same implementation principle and technical effect as... Figure 4 The methods and embodiments shown are similar and will not be described in detail here.

[0235] According to embodiments of the present invention, the present invention also provides an expression spectrum data providing server, a user terminal, a multi-party secure computing server, a computer-readable storage medium, and a computer program product.

[0236] like Figure 8 As shown, Figure 8 This is a schematic diagram of the structure of the expression spectrum data providing server provided by the present invention. The expression spectrum data providing server is intended for various forms of electronic devices, such as tablet computers and other suitable computers. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the invention described and / or claimed herein.

[0237] like Figure 8 As shown, the expression spectrum data providing server includes a processor 701, a memory 702, and a transceiver 703. The various components are interconnected via different buses and can be mounted on a common motherboard or installed in other ways as needed. The processor can process instructions executed within the electronic device.

[0238] The memory 702 is the non-transitory computer-readable storage medium provided by this invention. The memory stores instructions executable by at least one processor to cause the at least one processor to perform the medical information expression spectrum processing method based on privacy protection and multi-party secure computation provided by this invention. The non-transitory computer-readable storage medium of this invention stores computer instructions for causing a computer to perform the medical information expression spectrum processing method based on privacy protection and multi-party secure computation provided by this invention.

[0239] Memory 702, as a non-transitory computer-readable storage medium, can be used to store non-transitory software programs, non-transitory computer-executable programs, and modules, such as the program instructions / modules corresponding to the medical information expression spectrum processing method based on privacy protection and multi-party secure computation in this embodiment of the invention (e.g., attached). Figure 8 The acquisition module 401, determination module 402, and transmission module 403 are shown. The processor 701 executes various server functions and data processing by running non-transient software programs, instructions, and modules stored in the memory 702, thereby implementing the medical information expression spectrum processing method based on privacy protection and multi-party secure computation in the above method embodiments. The transceiver 703 is used for sending and receiving data.

[0240] The structure and function of the user terminal and multi-party secure computation server provided in this embodiment are similar to those of the expression spectrum data providing server, and will not be described in detail here.

[0241] Meanwhile, this embodiment also provides a computer product, which, when the instructions in the computer product are executed by the processor of an expression profile data providing server, a user terminal, or a multi-party secure computation server, enables the expression profile data providing server, user terminal, or multi-party secure computation server to execute the medical information expression profile processing method based on privacy protection and multi-party secure computation described in the above embodiment.

[0242] Other embodiments of the invention will readily conceive of by those skilled in the art upon consideration of the specification and practice of the invention disclosed herein. This invention is intended to cover any variations, uses, or adaptations of the embodiments thereof that follow the general principles of the embodiments thereof and include common knowledge or customary techniques in the art not disclosed in the embodiments thereof. The specification and embodiments are to be considered exemplary only, and the true scope and spirit of the embodiments thereof are indicated by the claims.

[0243] It should be understood that the embodiments of the present invention are not limited to the precise structures described above and shown in the accompanying drawings, and various modifications and changes can be made without departing from their scope. The scope of the embodiments of the present invention is limited only by the appended claims.

Claims

1. A medical information expression spectrum processing method based on privacy protection and multi-party secure calculation, characterized in that, The method comprises: The expression profile data providing server acquires first gene expression profile data and a preset category corresponding to the first gene expression profile data; the first gene expression profile data corresponds to the gene identifier of the second gene expression profile data to be identified in the user terminal; Determine the first gene relative expression amount between the first gene expression profile data and the preset internal reference gene expression profile data; The first gene relative expression amount and the preset category are sent to the multi-party secure computing server, so that the multi-party secure computing server determines the identification result of the association relationship between the second gene expression profile data and the preset category according to the first gene relative expression amount, the second gene relative expression amount and the preset category; the second gene relative expression amount is the gene relative expression amount between the second gene expression profile data and the preset internal reference gene expression profile data; The user terminal determines the second gene relative expression amount between the second gene expression profile data to be identified and the preset internal reference gene expression profile data; The second gene relative expression amount is sent to the multi-party secure computing server, so that the multi-party secure computing server determines the identification result of the association relationship between the second gene expression profile data and the preset category according to the first gene relative expression amount, the second gene relative expression amount and the preset category; the preset category is the category corresponding to the first gene expression profile data in the expression profile data providing server; the first gene expression profile data corresponds to the gene identifier of the second gene expression profile data; the first gene relative expression amount is the gene relative expression amount between the first gene expression profile data and the preset internal reference gene expression profile data; The multi-party secure computing server receives the second gene relative expression amount sent by the user terminal; the second gene relative expression amount is the gene relative expression amount between the second gene expression profile data to be identified in the user terminal and the preset internal reference gene expression profile data; Receive the first gene relative expression amount and the preset category corresponding to the first gene relative expression amount sent by the expression profile data providing server; the first gene relative expression amount is the gene relative expression amount between the first gene expression profile data and the preset internal reference gene expression profile data in the expression profile data providing server; the first gene expression profile data corresponds to the gene identifier of the second gene expression profile data; Determine the identification result of the association relationship between the second gene expression profile data and the preset category according to the first gene relative expression amount, the second gene relative expression amount and the preset category.

2. The method of claim 1, wherein, The acquisition of the first gene expression profile data and the preset category corresponding to the first gene expression profile data comprises: Acquire the gene identifier corresponding to the second gene expression profile data to be identified in the user terminal; Obtain the gene expression profile queue data corresponding to the gene identifier and the preset category corresponding to the gene expression profile queue data from the preset database; the preset database stores the mapping relationship between the gene identifier, the gene expression profile queue data and the preset category corresponding to the gene expression profile queue data; the gene expression profile queue data has a mapping relationship with at least one preset category; The gene expression profile queue data is subjected to RNA sequencing normalization processing to generate the first gene expression profile data; The preset category corresponding to the gene expression profile queue data is determined as the preset category corresponding to the first gene expression profile data.

3. The method of claim 2, wherein, The determination of the first gene relative expression amount between the first gene expression profile data and the preset internal reference gene expression profile data comprises: The t test algorithm is used to determine the corresponding test statistic t value according to the first gene expression profile data and the preset internal reference gene expression profile data; According to the t value, the corresponding t limit table is queried to determine the judgment hypothesis test result parameter p value corresponding to the t value; The p value, the first gene expression profile data and the preset internal reference gene expression profile data are input into the preset relative expression amount algorithm to determine the first gene relative expression amount corresponding to the p value.

4. The method of claim 3, wherein, The first gene expression profile data comprises expression profile data corresponding to a plurality of same gene identifiers; and the preset internal reference gene expression profile data comprises expression profile data corresponding to a plurality of same internal reference genes. The t test algorithm is used to determine the corresponding test statistic t value according to the first gene expression profile data and the preset internal reference gene expression profile data, which comprises: The variance, mean value and total amount of gene identifiers of the expression profile data corresponding to the same gene identifiers in the first gene expression profile data are calculated; The variance, mean value and total amount of internal reference genes of the expression profile data corresponding to the same internal reference genes in the preset internal reference gene expression profile data are calculated; The variance, mean value and total amount of gene identifiers of the expression profile data corresponding to the same gene identifiers in the first gene expression profile data and the variance, mean value and total amount of internal reference genes of the expression profile data corresponding to the same internal reference genes in the preset internal reference gene expression profile data are input into the t test algorithm to determine the corresponding test statistic t value.

5. The method of claim 1, wherein, The determination of the second gene relative expression amount between the second gene expression profile data and the preset internal reference gene expression profile data comprises: The t test algorithm is used to determine the corresponding test statistic t value according to the second gene expression profile data and the preset internal reference gene expression profile data; According to the t value, the corresponding t limit table is queried to determine the judgment hypothesis test result parameter p value corresponding to the t value; The p value, the second gene expression profile data and the preset internal reference gene expression profile data are input into the preset relative expression amount algorithm to determine the second gene relative expression amount corresponding to the p value.

6. The method of claim 1, wherein, The determination of the second gene relative expression amount between the second gene expression profile data and the preset internal reference gene expression profile data comprises: The similarity of the first gene relative expression amount and the second gene relative expression amount in the same category is determined according to the preset category; According to the similarity and the preset similarity threshold, the recognition result of the association relationship between the second gene expression profile data and the preset category is determined.

7. The method of claim 6, wherein, The second gene relative expression amount comprises a plurality of gene identifiers corresponding to the gene relative expression amount; and the first gene relative expression amount comprises the gene relative expression amount corresponding to the plurality of gene identifiers. The similarity between the relative expression amount of the first gene and the relative expression amount of the second gene in the same category according to the preset category comprises: The number of similar genes in the same category according to the preset condition is determined; the preset condition is that the first gene relative expression amount and the second gene relative expression amount corresponding to the same gene identifier are equal; The quotient of the number of similar genes and the total number of gene identifiers in the same category is determined as the similarity.

8. A privacy protection and multi-party secure computation based medical information expression spectrum processing system comprising a privacy protection and multi-party secure computation based medical information expression spectrum processing device located at an expression spectrum data providing server, a privacy protection and multi-party secure computation based medical information expression spectrum processing device located at a user terminal, and a privacy protection and multi-party secure computation based medical information expression spectrum processing device located at a multi-party secure computation server, characterized in that The medical information expression spectrum processing device based on privacy protection and multi-party secure calculation located at the expression spectrum data providing server comprises: An acquisition module is configured to acquire first gene expression spectrum data and a preset category corresponding to the first gene expression spectrum data; the first gene expression spectrum data corresponds to a gene identifier of second gene expression spectrum data to be identified in a user terminal; A determination module is configured to determine a first gene relative expression amount between the first gene expression spectrum data and preset internal reference gene expression spectrum data; A sending module is configured to send the first gene relative expression amount and the preset category to a multi-party secure calculation server, so that the multi-party secure calculation server determines an identification result of an association relationship between the second gene expression spectrum data and the preset category according to the first gene relative expression amount, a second gene relative expression amount, and the preset category; the second gene relative expression amount is a gene relative expression amount between the second gene expression spectrum data and the preset internal reference gene expression spectrum data; The medical information expression spectrum processing device based on privacy protection and multi-party secure calculation located at the user terminal comprises: A determination module is configured to determine a second gene relative expression amount between the second gene expression spectrum data to be identified and the preset internal reference gene expression spectrum data; A sending module is configured to send the second gene relative expression amount to a multi-party secure calculation server, so that the multi-party secure calculation server determines an identification result of an association relationship between the second gene expression spectrum data and the preset category according to the first gene relative expression amount, the second gene relative expression amount, and the preset category; the preset category is a category corresponding to first gene expression spectrum data in an expression spectrum data providing server; the first gene expression spectrum data corresponds to a gene identifier of the second gene expression spectrum data; the first gene relative expression amount is a gene relative expression amount between the first gene expression spectrum data and the preset internal reference gene expression spectrum data; The medical information expression spectrum processing device based on privacy protection and multi-party secure calculation located at the multi-party secure calculation server comprises: A first receiving module is configured to receive the second gene relative expression amount sent by the user terminal; the second gene relative expression amount is a gene relative expression amount between the second gene expression spectrum data to be identified in the user terminal and the preset internal reference gene expression spectrum data; The second receiving module is used for receiving the first gene relative expression amount and the preset category corresponding to the first gene relative expression amount sent by the expression profile data providing server; the first gene relative expression amount is the gene relative expression amount between the first gene expression profile data and the preset internal reference gene expression profile data in the expression profile data providing server; the gene identifiers of the first gene expression profile data and the second gene expression profile data correspond to each other; The identifying module is used for determining the identifying result of the correlation relationship between the second gene expression profile data and the preset category according to the first gene relative expression amount, the second gene relative expression amount and the preset category.

Images