Trace element evaluation method, device, equipment and medium

Abstract

The invention relates to the technical field of trace element analysis, in particular to a trace element evaluation method, device and equipment and a medium. The method comprises the following steps: firstly, calculating a first change feature of a to-be-evaluated trace element, then calculating the first change feature and a second change feature of a trace element corresponding to a disease stored in a database, and calculating a similarity score between the two change features; the method also calculates a first correlation between any two of the to-be-evaluated trace elements, then calculates a second correlation between the two elements related to diseases and stored in the database, and then calculates a similarity score between the first correlation and the second correlation. And finally, based on the two similarity scores, obtaining a comprehensive score of the to-be-evaluated trace elements. According to the method, the correlation between two elements is fully considered when the comprehensive score is calculated, so that the finally obtained comprehensive score can fully reflect the disease risk.

Description

Technical Field

[0001] The present invention relates to the technical field of trace element analysis, and in particular to a method, device, equipment and medium for evaluating trace elements. Background Art

[0002] Iron, zinc, copper, manganese, molybdenum, cobalt, nickel, chromium, vanadium, selenium, fluorine, and iodine are trace elements found in living organisms. While trace elements are present in very low concentrations, they are closely related to the growth and development of living organisms, as well as various physiological activities. Excessive or insufficient intake of these trace elements can lead to disease, so disease risk can be indirectly assessed by evaluating trace elements. Existing technologies only consider individual trace elements when evaluating them, without considering the correlations between them. Existing research has shown that correlations between trace elements are also associated with disease risk. Therefore, existing technologies independently evaluate each trace element, resulting in assessment results that are insufficient to reflect disease risk.

[0003] In summary, the trace element assessment results obtained by existing technologies are not sufficient to characterize disease risks.

[0004] Therefore, the existing technology still needs to be improved and enhanced. Summary of the Invention

[0005] To solve the above technical problems, the present invention provides a method, device, equipment and medium for evaluating trace elements, which solves the problem that the trace element evaluation results obtained in the prior art are insufficient to characterize disease risks.

[0006] To achieve the above object, the present invention adopts the following technical solutions:

[0007] In a first aspect, the present invention provides a method for evaluating trace elements, comprising:

[0008] Obtain the trace element to be evaluated in the human body, and determine the similarity score S between the first change feature of the trace element to be evaluated and the second change feature of the trace element ele , the second change characteristic is the change characteristic of the trace element corresponding to each disease already in the database;

[0009] Screening out element pairs with correlation from the trace elements to be evaluated, and determining a first correlation of the element pairs based on the first variation characteristics of the two elements in the element pairs;

[0010] Calculate the similarity score S between the first correlation of the element pair and the second correlation of the element pair cor , the second correlation is the correlation of the element pair corresponding to the disease already in the database;

[0011] According to the similarity score S ele and the similarity score S cor , obtaining a comprehensive score of the trace element to be evaluated for each of the diseases, and the comprehensive score is used to screen out the target disease from the various diseases.

[0012] In one implementation, a similarity score S is determined between the first variation characteristic of the trace element to be evaluated and the second variation characteristic of the trace element. ele ,include:

[0013] determining a difference between the first variation characteristic and the second variation characteristic;

[0014] Obtaining the degree of influence of the trace element on the disease;

[0015] According to the difference and the influence degree, the similarity score S is obtained. ele .

[0016] In one implementation, determining a first correlation of the element pair based on the first variation characteristics of the two elements in the element pair includes:

[0017] multiplying the first variation characteristic of one element in the element pair by the first variation characteristic of the other element to obtain a product result;

[0018] A first correlation of the element pair is obtained according to the multiplication result.

[0019] In one implementation, the second correlation is constructed by:

[0020] Obtaining documents in the database where the element pair appears;

[0021] Obtaining the correlation between each of the two elements in the element pair and the disease recorded in the literature;

[0022] The second correlation is obtained based on the correlation between each of the two elements recorded in the document and the disease and the total number of the documents.

[0023] In one implementation, obtaining the second correlation based on the correlation between each of the two elements recorded in the document and the disease and the total number of the documents includes:

[0024] Assigning a value to the relevance of each of the two elements to the disease;

[0025] Calculate the difference between two assignments;

[0026] The second correlation is obtained according to the difference and the total number of the documents.

[0027] In one implementation, the second correlation is derived from a correlation network in the database, the nodes of the correlation network are trace elements, and the attributes of the edge between two of the nodes represent the second correlation between the two trace elements corresponding to the two nodes respectively.

[0028] In one implementation, the correlation network includes a network composed of trace elements derived from multiple biological tissues, and trace elements of one biological tissue constitute one correlation network.

[0029] In a second aspect, an embodiment of the present invention further provides a device for evaluating trace elements, wherein the device includes the following components:

[0030] The first similarity calculation module is used to obtain the trace element to be evaluated in the human body and determine the similarity score S between the first change feature of the trace element to be evaluated and the second change feature of the trace element ele , the second change characteristic is the change characteristic of the trace element corresponding to each disease already in the database;

[0031] a correlation calculation module, configured to screen out element pairs having correlation from the trace elements to be evaluated, and determine a first correlation of the element pairs based on the first variation characteristics of the two elements in the element pairs;

[0032] The second similarity calculation module is used to calculate the similarity score S between the first correlation of the element pair and the second correlation of the element pair. cor , the second correlation is the correlation of the element pair corresponding to the disease already in the database;

[0033] Comprehensive score calculation module, used to calculate the similarity score S ele and the similarity score S cor , obtaining a comprehensive score of the trace element to be evaluated for each of the diseases, and the comprehensive score is used to screen out the target disease from the various diseases.

[0034] In a third aspect, an embodiment of the present invention further provides a terminal device, wherein the terminal device includes a memory, a processor, and a trace element evaluation program stored in the memory and runnable on the processor, and when the processor executes the trace element evaluation program, the steps of the trace element evaluation method described above are implemented.

[0035] In a fourth aspect, an embodiment of the present invention further provides a computer-readable storage medium, on which a trace element evaluation program is stored. When the trace element evaluation program is executed by a processor, the steps of the trace element evaluation method described above are implemented.

[0036] Beneficial effects: The present invention first calculates the first change characteristic of the trace element to be evaluated, then calculates the first change characteristic and the second change characteristic of the trace element corresponding to the disease stored in the database, and calculates the similarity score between the two change characteristics. The present invention also calculates the first correlation between any two of the trace elements to be evaluated, then calculates the second correlation of the above two elements related to the disease stored in the database, and then calculates the similarity score between the first correlation and the second correlation. Finally, based on the above two similarity scores, the comprehensive score of the trace element to be evaluated is obtained. Since the present invention fully considers the correlation between the two elements when calculating the comprehensive score, the final comprehensive score can fully reflect the risk of disease. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] Figure 1 It is the overall flow chart of the present invention;

[0038] Figure 2 A structural diagram of the trace element evaluation device provided by the present invention;

[0039] Figure 3 This is a block diagram of the internal structure of a terminal device according to an embodiment of the present invention. DETAILED DESCRIPTION

[0040] The following is a clear and complete description of the technical solutions of the present invention in conjunction with the embodiments and the accompanying drawings. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present invention.

[0041] Research has found that trace elements such as iron, zinc, copper, manganese, molybdenum, cobalt, nickel, chromium, vanadium, selenium, fluorine, and iodine are found in organisms. While trace elements are present in very low concentrations, they are closely related to the organism's growth, development, and various physiological activities. Excessive or insufficient intake of these trace elements can lead to disease, so disease risk can be indirectly assessed by evaluating trace elements. Existing technologies only consider individual trace elements when evaluating them, without considering the correlations between them. Existing research has shown that correlations between trace elements are also associated with disease risk. Therefore, existing technologies independently evaluate each trace element, resulting in assessment results that are insufficient to reflect disease risk.

[0042] To solve the above technical problems, the present invention provides a method, device, equipment and medium for evaluating trace elements, which solves the problem that the trace element evaluation results obtained in the prior art are insufficient to characterize disease risks. In specific implementation, the trace element to be evaluated in the human body is first obtained, and the similarity score S between the first change characteristic of the trace element to be evaluated and the second change characteristic of the trace element is determined. ele , the second change feature is the change feature of the trace element corresponding to each disease in the database; then, element pairs with correlation are screened from the trace elements to be evaluated, and based on the first change features of the two elements in the element pair, the first correlation of the element pair is determined; and the similarity score S between the first correlation of the element pair and the second correlation of the element pair is calculated cor , the second correlation is the correlation of the element pair corresponding to the disease in the database; finally, based on the similarity score S ele and similarity score S cor , and obtain the comprehensive score of the trace elements to be evaluated for each disease. The comprehensive score is used to screen out the target disease from various diseases.

[0043] For example, for example, the trace elements to be evaluated in the human body include iron, zinc, and copper, and the first change characteristics of iron, zinc, and copper are calculated respectively. The change characteristics can be whether the trace element content of the human body has increased or decreased relative to the normal value. The second change characteristics of the iron element corresponding to disease A, the second change characteristics of the zinc element corresponding to disease A, and the second change characteristics of the copper element corresponding to disease A are stored in the database. Calculate the similarity score between the first change characteristic of human iron and the second change characteristic of iron in the database, and use the same method to calculate the similarity score of zinc and the similarity score of copper. Add the similarity score of iron, zinc, and copper to obtain the similarity score S. ele .

[0044] Iron and zinc constitute an element pair for the human body, iron and copper constitute an element pair for the human body, and zinc and copper constitute an element pair for the human body. Based on the iron and zinc content of the human body, the first correlation of the iron and zinc element pair is calculated; the iron and zinc content corresponding to the occurrence of the disease recorded in the database is calculated, and the second correlation of the iron and zinc element pair is calculated. Based on the first correlation and second correlation of the iron and zinc element pair, the similarity score of the iron and zinc element pair is calculated. The similarity score of the iron and copper element pair and the similarity score of the zinc and copper element pair are calculated in the same way, and the similarity score S is obtained by adding the above three similarity scores. cor .

[0045] Finally, according to the similarity score S ele and similarity score S cor Assess the risk of this person developing disease A.

[0046] The trace element evaluation method of this embodiment can be applied to a terminal device, which can be a terminal product with a trace element analysis function, such as a disease diagnostic instrument. Figure 1 As shown in , the trace element evaluation method specifically includes the following steps:

[0047] S100, obtaining a trace element to be evaluated in a human body, and determining a similarity score S between a first variation feature of the trace element to be evaluated and a second variation feature of the trace element ele , the second change characteristic is the change characteristic of the trace element corresponding to each disease already in the database;

[0048] S200, screening out correlated element pairs from the trace elements to be evaluated, and determining a first correlation of the element pairs based on the first variation characteristics of the two elements in the element pairs;

[0049] S300, calculating a similarity score S between the first correlation of the element pair and the second correlation of the element pair cor , the second correlation is the correlation of the element pair corresponding to the disease already in the database;

[0050] S400, based on the similarity score S ele and the similarity score S cor , obtaining a comprehensive score of the trace element to be evaluated for each of the diseases, and the comprehensive score is used to screen out the target disease from the various diseases.

[0051] In the first embodiment, the similarity score S is calculated in step S100. ele , including: determining the difference between the first change feature and the second change feature; obtaining the degree of influence of the trace element on the disease; obtaining a similarity score S based on the difference and the degree of influence ele .

[0052] Among them S ele The calculation formula is as follows:

[0053]

[0054] n represents the total number of trace elements obtained from human biological samples, where biological samples include human blood, urine, and hair. m represents the number of trace elements to be evaluated, and m is the number of elements involved in diseases in the database. For example, if three elements, iron, zinc, and copper, are extracted from human biological samples, then the value of n is 3, and if one of the diseases included in the database involves zinc and copper, then the value of m is 2. Used to obtain the normalized S ele .

[0055] C1 i Represents the first change characteristic of the i-th trace element to be evaluated. The first change characteristic represents the changing trend of the amount of the trace element in the human body. The changing trend includes increasing and decreasing. Increasing means positive correlation and can be assigned a value of 1; decreasing means negative correlation and can be assigned a value of -1; or the first change characteristic represents the degree to which the amount of the element in the human body deviates from the standard amount.

[0056] C2 i The second variation characteristic of the trace element i represents the variation trend of the trace element i corresponding to the diseases in the database. Alternatively, the second variation characteristic represents the degree to which the amount of the trace element i corresponding to the diseases in the database deviates from the standard amount.

[0057] W i Represents the degree of influence of the trace element i on the existing diseases in the database.

[0058] In this embodiment, step S200 calculates the first correlation R1 j , including: changing the first change feature C1 of one element A in the element pair j j,A Multiply the first variation characteristic C1 of the other element B j,B , get the product result; according to the product result, get the first correlation R1 of the element pair j :

[0059] R1 j =sign(C1 j,A ×C1 j,B )

[0060] Where sign represents a function that returns the sign of a number and is used to determine the sign of a number.

[0061] In this embodiment, the method for constructing the second correlation in step S300 includes: obtaining documents in the database in which the element pair j appears; obtaining the correlation between the two elements in the element pair j recorded in the document and the disease; and obtaining the second correlation R2 based on the correlation between the two elements in the document and the disease and the total number of documents. j .

[0062] According to the correlation between the two elements recorded in the literature and the disease and the total number of the literature, the second correlation R2 is obtained. j , including: assigning a value to each of the two elements and the relevance to the disease; calculating the difference d between the two assigned valuesk ; According to the difference d k and the total number of documents N, we get the second correlation R2 j :

[0063]

[0064] In this embodiment, the two elements in the element pair j appear in the same document. The correlation between any one of the two elements and the disease can be the second variation feature of the element in the database. The correlation can also be the relationship between the element and the disease, that is, whether the element and the disease are positively correlated (1 indicates positive correlation), negatively correlated (-1 indicates negative correlation), or uncorrelated (0 indicates uncorrelated). The relationship between the two elements in the element pair j and the disease is assigned a value. The difference between the values ​​assigned to the two elements in the element pair j in the kth document is d k .

[0065] In this embodiment, the similarity score S in step S300 cor The calculation formula is as follows:

[0066]

[0067] P n is an element pair representing all trace elements obtained from biological samples of the human body (the total number of all trace elements is n). P t P n For example, human biological samples include three trace element pairs (A1, B1), (A2, B2), and (A3, B3). n The value of is 3), where (A1, B1) and (A2, B2) are recorded in the database as being related to one of the diseases, then P t The value of is 2.

[0068] The calculation formula of the comprehensive score S in step S400 is as follows:

[0069] S=S ele +S cor

[0070] The above-mentioned comprehensive score S in this embodiment represents the score of the element to be evaluated of the human body calculated with reference to the element information involved in one of the diseases in the database. The comprehensive score S of the element to be evaluated of the human body relative to all diseases is calculated in the same way. All comprehensive scores S are arranged in descending order. The ten diseases corresponding to the ten highest comprehensive scores S are the diseases that the human body may suffer from, that is, the risk of suffering from these ten diseases is higher.

[0071] The second embodiment provides a method for constructing the database of the first embodiment. The construction of the database in this embodiment includes collecting original literature resources, extracting disease-related information from the literature, and establishing a database based on the extracted information.

[0072] Among them, collecting original literature resources includes the following specific steps:

[0073] Step one, uses the full name and abbreviation (such as " iron " and " Fe ") of each trace element one by one as search keywords, searches from PubMed database, to search out all documents containing the above-mentioned trace elements. In this embodiment, trace elements include iron (Fe), zinc (Zn), copper (Cu), magnesium (Mg), selenium (Se), manganese (Mn), nickel (Ni), cobalt (Co), molybdenum (Mo), chromium (Cr), vanadium (V), iodine (I), boron (B), cadmium (Cd), arsenic (As), lead (Pb), mercury (Hg) and aluminum (Al) these 18 kinds of trace elements.

[0074] Step 2: Apply the Medical Subject Headings (MeSH) of MEDLINE to all the literature searched in step 1 to divide the above literature into literature in the disease category, literature in the health care category, and literature in the psychiatry and psychology category.

[0075] Step 3: Read the titles and abstracts of each category of literature obtained in step 2 to exclude literature unrelated to diseases and trace elements through manual screening, such as animal and cell line studies, imaging examination-related studies, and surgery / drug treatment-related studies.

[0076] Extracting disease-related information from the literature includes the following specific steps:

[0077] We further reviewed the retained literature and manually extracted information from each article, as shown in Table 1. This information includes disease name, sample type (including biological sample source, diet, and environmental exposure), disease stage, race and subgroup, total study population or number of case-controls, significantly altered elements (including elements of primary interest and other elements) and their relationship to the disease, study type, publication year, and references. Items such as disease stage, relationship between elements and disease, and study type were also manually collated and extracted.

[0078] Table 1

[0079]

[0080] The database was established, including: storing complete data in JSON format. Each record contained the original field information from Table 1. Furthermore, the database stored elemental variation spectra and elemental ion group correlation network data in CSV and Excel file formats. The database also used the Python pandas library to automatically check and organize data, automatically correcting any issues (e.g., standardizing disease nomenclature, deleting duplicate records, and correcting formatting issues).

[0081] The JSON (JavaScript Object Notation) of this embodiment is an open standard file format and data exchange format that is easy to read and write, and is also easy to parse and generate by computers.

[0082] This embodiment stores the JSON file format in the front-end project folder so that it can be directly imported and used through code. CSV and Excel files are placed in the back-end so that they can be imported into the front-end by reading them.

[0083] This embodiment reads commonly used data (such as a disease list) into the memory first, so that the commonly used data can be read directly from the memory without reading a file, thereby speeding up the data reading speed.

[0084] This embodiment uses Nginx as a proxy when developing an online platform for a database system, and distributes front-end requests to multiple back-end programs to prevent the system from freezing when the number of visits is too large.

[0085] In a third embodiment, a correlation network is established, wherein the nodes of the correlation network are trace elements. The attributes of the edge between two nodes (including the width of the edge) are used to characterize the second correlation between the two nodes, that is, the second correlation between the two trace elements corresponding to the two nodes. The edges of the correlation network of this embodiment provide the second correlation required for the trace element assessment of the first embodiment.

[0086] Establishing a correlation network includes integrating multi-element / ion group data, establishing element change spectra, and constructing an element ion group correlation network.

[0087] The integration of multi-element / ion group data and the establishment of element variation spectra include the following specific steps:

[0088] Step 1: When a disease of a sample type appears in more than three papers, the disease of the sample type is used as a specific disease of a specific sample type to construct an element variation profile. Sample types include whole blood, serum, plasma, and urine.

[0089] Step 2: Integrate the specific diseases and trace elements associated with specific sample types recorded in the literature, and select the most dominant relationship (the most dominant relationship is the trend of change with the highest proportion) from the relationship between the trace elements contained in each specific sample type and the specific disease, and use this most dominant relationship as the relationship between the trace element and the specific disease. For example, there is a positive correlation between iron in the whole blood sample type and specific disease A, there is a positive correlation between iron in the serum sample type and specific disease A, and there is no correlation between iron in the plasma sample type and specific disease A. Since the positive correlation ratio is the largest, the positive correlation between iron and specific disease A is the most dominant relationship.

[0090] Step 3: The correlation between the elements is calculated by the Spearman's correlation coefficient (SCC). This embodiment assigns a value to the most advantageous relationship between the trace element and the disease in step 2, and calculates the correlation between the two trace elements by this assignment (this correlation is the second correlation of the trace element pair in Example 1, and the SCC value is used to represent this correlation, which is the R2 in Example 1). j ).

[0091] This example constructs an elemental ion group correlation network, including: based on the element-disease relationships and element correlation data obtained through the above process, using the Cytoscape tool to generate elemental ion group correlation networks specific to different diseases and sample types. The nodes in the network represent the 18 trace elements and minerals of primary interest. A solid-line frame outside a node indicates that the trace element corresponding to the node is associated with the disease, while a dashed-line frame outside a node indicates that the trace element corresponding to the node is not associated with the disease. The color of the node represents the correlation between the trace element represented by the node and the disease, with red representing positive correlation, blue representing negative correlation, and white representing no correlation. The color depth represents the degree of correlation and no correlation, for example, the higher the proportion of positive correlation, the darker the red. The edges between the nodes represent the SCC values ​​between different elements. Positive correlations are represented in red, and negative correlations in blue. The color depth and width of the edges are proportional to the absolute value of the SCC value.

[0092] In summary, this invention has established for the first time a database system for the association of human diseases and trace elements. By collecting and integrating information on changes in trace element and mineral content in human disease samples from different sources, it has established disease sample-specific element change spectra and element ion group correlation networks, and developed online platforms and tools for researchers in related fields to use, thereby further understanding the important relationship between trace element imbalance and the occurrence, development and prognosis of human diseases. Therefore, it has good application prospects in fields such as clinical medicine and nutrition.

[0093] Based on the multi-element change trends of specific disease-specific types of biological samples in the core database, the present invention has developed a new disease risk assessment method to improve the lack of understanding of the relationship between trace elements and the complex element networks they constitute and complex diseases, providing new ideas for early screening and intervention of diseases.

[0094] The online resource platform developed based on this invention is significantly superior to existing disease and trace element-related data resources (existing resources can usually only manually extract relevant information from articles) in terms of data volume, interactivity, code maintenance, and data updates. It not only improves the user experience, but also facilitates developers to maintain and manage databases and software.

[0095] This embodiment also provides a device for evaluating trace elements, such as Figure 2 As shown, the device includes the following components:

[0096] The first similarity calculation module 01 is used to obtain the trace element to be evaluated in the human body and determine the similarity score S between the first change feature of the trace element to be evaluated and the second change feature of the trace element ele , the second change characteristic is the change characteristic of the trace element corresponding to each disease already in the database;

[0097] a correlation calculation module 02, configured to screen out element pairs having correlation from the trace elements to be evaluated, and determine a first correlation of the element pairs based on the first variation characteristics of the two elements in the element pairs;

[0098] The second similarity calculation module 03 is used to calculate the similarity score S between the first correlation of the element pair and the second correlation of the element pair. cor , the second correlation is the correlation of the element pair corresponding to the disease already in the database;

[0099] Comprehensive score calculation module 04, used to calculate the similarity score S ele and the similarity score S cor , obtaining a comprehensive score of the trace element to be evaluated for each of the diseases, and the comprehensive score is used to screen out the target disease from the various diseases.

[0100] Based on the above embodiment, the present invention further provides a terminal device, whose principle block diagram can be shown as follows: Figure 3As shown. The terminal device includes a processor, memory, network interface, and display screen connected via a system bus. The processor of the terminal device is used to provide computing and control capabilities. The memory of the terminal device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and computer program in the non-volatile storage medium. The network interface of the terminal device is used to communicate with an external terminal via a network connection. When the computer program is executed by the processor, a method for evaluating trace elements is implemented. The display screen of the terminal device can be a liquid crystal display or an electronic ink display.

[0101] Those skilled in the art will understand that Figure 3 The principle block diagram shown in the figure is only a block diagram of a partial structure related to the solution of the present invention, and does not constitute a limitation on the terminal device to which the solution of the present invention is applied. The specific terminal device may include more or fewer components than shown in the figure, or combine certain components, or have a different component arrangement.

[0102] In one embodiment, a terminal device is provided. The terminal device includes a memory, a processor, and a trace element evaluation program stored in the memory and executable on the processor. When the processor executes the trace element evaluation program, the following operating instructions are implemented:

[0103] Obtain the trace element to be evaluated in the human body, and determine the similarity score S between the first change feature of the trace element to be evaluated and the second change feature of the trace element ele , the second change characteristic is the change characteristic of the trace element corresponding to each disease already in the database;

[0104] Screening out element pairs with correlation from the trace elements to be evaluated, and determining a first correlation of the element pairs based on the first variation characteristics of the two elements in the element pairs;

[0105] Calculate the similarity score S between the first correlation of the element pair and the second correlation of the element pair cor , the second correlation is the correlation of the element pair corresponding to the disease already in the database;

[0106] According to the similarity score S ele and the similarity score S cor , obtaining a comprehensive score of the trace element to be evaluated for each of the diseases, and the comprehensive score is used to screen out the target disease from the various diseases.

[0107] Those skilled in the art will appreciate that all or part of the processes in the above-described embodiments can be implemented by instructing the relevant hardware through a computer program. The computer program can be stored in a non-volatile computer-readable storage medium. When executed, the computer program can include the processes of the above-described embodiments. Among them, any reference to memory, storage, database or other media used in the embodiments provided by the present invention can include non-volatile and / or volatile memory. Non-volatile memory can include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory can include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in various forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link DRAM (SLDRAM), RAMbus direct RAM (RDRAM), direct RAM bus dynamic RAM (DRDRAM), and RAMbus dynamic RAM (RDRAM).

[0108] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the various embodiments of the present invention.

Claims

1. A method for evaluating trace elements, characterized in that: include: Obtain the trace element to be evaluated in the human body, and determine the similarity score S between the first change feature of the trace element to be evaluated and the second change feature of the trace element ele , the second change characteristic is the change characteristic of the trace element corresponding to each disease already in the database; Screening out element pairs with correlation from the trace elements to be evaluated, and determining a first correlation of the element pairs based on the first variation characteristics of the two elements in the element pairs; Calculate the similarity score S between the first correlation of the element pair and the second correlation of the element pair cor , the second correlation is the correlation of the element pair corresponding to the disease already in the database; According to the similarity score S ele and the similarity score S cor , obtaining a comprehensive score of the trace element to be evaluated for each of the diseases, and the comprehensive score is used to screen out the target disease from the various diseases.

2. The method for evaluating trace elements according to claim 1, wherein: Determine the similarity score S between the first change feature of the trace element to be evaluated and the second change feature of the trace element ele ,include: determining a difference between the first variation characteristic and the second variation characteristic; Obtaining the degree of influence of the trace element on the disease; According to the difference and the influence degree, the similarity score S is obtained. ele .

3. The method for evaluating trace elements according to claim 1, wherein: Determining a first correlation of the element pair based on the first variation characteristics of two elements in the element pair includes: multiplying the first variation characteristic of one element in the element pair by the first variation characteristic of the other element to obtain a product result; A first correlation of the element pair is obtained according to the multiplication result.

4. The method for evaluating trace elements according to claim 1, wherein The second correlation is constructed in a manner including: Obtaining documents in the database where the element pair appears; Obtaining the correlation between each of the two elements in the element pair and the disease recorded in the literature; The second correlation is obtained based on the correlation between each of the two elements recorded in the document and the disease and the total number of the documents.

5. The method for evaluating trace elements according to claim 4, wherein: The second correlation is obtained based on the correlation between each of the two elements recorded in the document and the disease and the total number of the documents, including: Assigning a value to the relevance of each of the two elements to the disease; Calculate the difference between two assignments; The second correlation is obtained according to the difference and the total number of the documents.

6. The method for evaluating trace elements according to claim 1, wherein: The second correlation is derived from a correlation network in the database, the nodes of the correlation network are trace elements, and the attributes of the edge between two of the nodes represent the second correlation between the two trace elements corresponding to the two nodes respectively.

7. The method for evaluating trace elements according to claim 6, wherein: The correlation network includes a network composed of trace elements from multiple biological tissues, and the trace elements of one biological tissue constitute one correlation network.

8. A device for evaluating trace elements, characterized in that: The device comprises the following components: The first similarity calculation module is used to obtain the trace element to be evaluated in the human body and determine the similarity score S between the first change feature of the trace element to be evaluated and the second change feature of the trace element ele , the second change characteristic is the change characteristic of the trace element corresponding to each disease already in the database; a correlation calculation module, configured to screen out element pairs having correlation from the trace elements to be evaluated, and determine a first correlation of the element pairs based on the first variation characteristics of the two elements in the element pairs; The second similarity calculation module is used to calculate the similarity score S between the first correlation of the element pair and the second correlation of the element pair. cor , the second correlation is the correlation of the element pair corresponding to the disease already in the database; Comprehensive score calculation module, used to calculate the similarity score S ele and the similarity score S cor , obtaining a comprehensive score of the trace element to be evaluated for each of the diseases, and the comprehensive score is used to screen out the target disease from the various diseases.

9. A terminal device, characterized in that: The terminal device includes a memory, a processor, and a trace element evaluation program stored in the memory and runnable on the processor. When the processor executes the trace element evaluation program, the steps of the trace element evaluation method according to any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium, characterized in that The computer-readable storage medium stores a trace element evaluation program, and when the trace element evaluation program is executed by a processor, the steps of the trace element evaluation method according to any one of claims 1 to 7 are implemented.

Images