Recommendation method, device and equipment of traditional Chinese medicine compound, medium and product

Abstract

The invention provides a recommendation method, device and equipment of a traditional Chinese medicine compound, a medium and a product, and relates to the field of biomedical treatment. Comprising the following steps: in response to a received determination request, querying a target protein corresponding to initial traditional Chinese medicine compound related information included in the determination request from a preset database; calculating a first score corresponding to each target protein and determining at least one candidate target protein from each target protein; obtaining traditional Chinese medicinal materials related to each candidate target protein; determining a first attribute feature tag corresponding to each traditional Chinese medicinal material and a second attribute feature tag corresponding to the symptom according to a preset mapping relationship; calculating a second score corresponding to each traditional Chinese medicinal material based on the first attribute tag and the second attribute tag; and determining a recommended Chinese herbal compound based on the first score and the second score. The correlation degree between the traditional Chinese medicinal materials and the diseases is determined through the correlation target protein, and then the correlation degree between the traditional Chinese medicinal materials and the symptoms is determined through the correlation attribute feature tag, so that the matching degree between the recommended traditional Chinese medicine compound and the diseases is higher.

Description

Technical Field

[0001] This application relates to the field of biomedical technologies, and particularly to a method, device, equipment, medium and product for recommending traditional Chinese medicine compound prescriptions. Background Art

[0002] Traditional Chinese medicine compound prescriptions are an important means for traditional Chinese medicine to treat diseases. The rationality of their compound composition directly relates to the treatment effect. Traditional Chinese medicine emphasizes syndrome differentiation and treatment, that is, based on comprehensive information such as the patient's symptoms, signs, pulse conditions, tongue manifestations, etc., to judge the cause, pathogenesis and location of the disease, and then formulate corresponding traditional Chinese medicine compound prescriptions for treatment. Due to the complex and changeable nature of diseases, the matching degree between the traditional Chinese medicine compound prescriptions determined simply by symptoms and diseases is gradually decreasing.

[0003] To improve the adaptability of traditional Chinese medicine compound prescriptions to diseases, related solutions analyze the pharmacodynamic substance basis of traditional Chinese medicine compound prescriptions through high-throughput screening, molecular biology and network pharmacology. For example, clinical phenotypes are used as screening indicators for pharmacodynamic models, combined with chemometric methods to optimize traditional Chinese medicine compound prescriptions, and network pharmacology technology is used to predict the association between active ingredients and targets, improving the matching degree between traditional Chinese medicine compound prescriptions and diseases, and providing a scientific basis for clinical applications.

[0004] However, traditional Chinese medicine compound prescriptions have complex components and diverse attribute characteristics. Only considering the relationship between the active ingredients of traditional Chinese medicinal materials and target proteins is likely to result in the problem of low adaptability between the determined traditional Chinese medicine compound prescriptions and diseases. Summary of the Invention

[0005] This application provides a method, device, equipment, medium and product for recommending traditional Chinese medicine compound prescriptions to solve the technical problem of low adaptability between traditional Chinese medicine compound prescriptions and diseases.

[0006] In a first aspect, this application provides a method for recommending traditional Chinese medicine compound prescriptions, the method comprising:

[0007] In response to receiving a determination request, query target proteins corresponding to the initial traditional Chinese medicine compound-related information included in the determination request from a preset database, where the determination request includes the names of each traditional Chinese medicinal material in the initial traditional Chinese medicine compound, the name of the disease corresponding to the initial traditional Chinese medicine compound, and the symptoms corresponding to the disease;

[0008] Calculate a first score corresponding to each of the target proteins and determine at least one candidate target protein from each of the target proteins; the first score is a relevance score between the target protein and the corresponding information;

[0009] Obtain traditional Chinese medicinal materials related to each of the candidate target proteins;

[0010] Determine a first attribute feature label corresponding to each of the traditional Chinese medicinal materials and a second attribute feature label corresponding to the symptoms according to a preset mapping relationship;

[0011] Calculate the second score corresponding to each of the traditional Chinese medicinal materials based on the first attribute label and the second attribute label; the second score is the relevance score between the traditional Chinese medicinal material and the symptoms corresponding to the disease.

[0012] Determine the recommended traditional Chinese medicine compound based on the first score and the second score.

[0013] In a possible design, the calculating the first score corresponding to each of the target proteins and determining at least one candidate target protein from each of the target proteins includes:

[0014] Obtain the interaction scores between each of the target proteins.

[0015] Construct a protein-protein interaction network topology map according to the interaction scores.

[0016] Calculate the numerical values of various centrality indicators for each of the target proteins based on the protein-protein interaction network topology map, and calculate the first score corresponding to each of the target proteins by using the weighted summation method based on the numerical values of various centrality indicators of each of the target proteins and the weights corresponding to the various centrality indicator numerical values.

[0017] Determine at least one candidate target protein according to the first score corresponding to each of the target proteins.

[0018] In a possible design, the calculating the second score corresponding to each of the traditional Chinese medicinal materials based on the first attribute label and the second attribute label includes:

[0019] Calculate the similarity between the first attribute label corresponding to each of the traditional Chinese medicinal materials and the second attribute label to obtain the second score corresponding to each of the traditional Chinese medicinal materials.

[0020] In a possible design, the determining the recommended traditional Chinese medicine compound based on the first score and the second score includes:

[0021] Calculate the third score corresponding to each traditional Chinese medicinal material by using the weighted summation method based on the first score, the second score corresponding to each of the traditional Chinese medicinal materials, and the weights corresponding to the first score and the second score.

[0022] Determine the recommended traditional Chinese medicine compound according to the third score.

[0023] In a possible design, after the determining the recommended traditional Chinese medicine compound based on the first score and the second score, the method further includes:

[0024] Perform permutation and combination on each traditional Chinese medicinal material in the recommended traditional Chinese medicine compound to obtain multiple pairs of medicines.

[0025] Determine the adjustment coefficient for each of the medicine pairs;

[0026] Based on the adjustment coefficient and the third score corresponding to each traditional Chinese medicine material in each medicine pair, determine the recommended level for each medicine pair.

[0027] In one possible design, the determining the adjustment coefficient for each of the medicine pairs includes:

[0028] Determine whether the medicine pair is a classical medicine pair. If so, determine that the adjustment coefficient is to increase the third score by a first preset adjustment coefficient. If not, determine that the adjustment coefficient is 0;

[0029] And / or, determine whether the properties and compatibility of the traditional Chinese medicine materials in the medicine pair are opposite. If so, determine that the adjustment coefficient is to decrease the third score by a second preset adjustment coefficient. If not, determine that the adjustment coefficient is 0;

[0030] And / or, determine whether there are toxic traditional Chinese medicine materials in the medicine pair. If so, determine that the adjustment coefficient is to decrease the third score by a third preset adjustment coefficient. If not, determine that the adjustment coefficient is 0.

[0031] In one possible design, after constructing the protein-protein interaction network topology map according to the interaction score, the method further includes:

[0032] Based on the protein-protein interaction network topology map, determine the directly acting proteins, indirectly acting proteins, and uncovered proteins;

[0033] Determine the side-effect proteins among the target proteins;

[0034] Output a list including the directly acting proteins, indirectly acting proteins, uncovered proteins, and side-effect proteins.

[0035] In one possible design, after querying the target proteins corresponding to the initial traditional Chinese medicine compound-related information included in the determination request from the preset database, the method further includes:

[0036] Query the functional analysis data and signaling pathway data corresponding to each of the target proteins, and label the functional analysis data and the signaling pathway data for each of the target proteins.

[0037] In one possible design, the responding to receiving a determination request and querying the target proteins corresponding to the initial traditional Chinese medicine compound-related information included in the determination request from the preset database includes:

[0038] In response to receiving a determination operation triggered by the user through the operation interface, display a disease name input component, a traditional Chinese medicine compound input component, and a symptom input component on the operation interface;

[0039] In response to receiving the disease name corresponding to the initial traditional Chinese medicine compound input by the user through the disease name input component, the names of each Chinese medicinal material in the initial traditional Chinese medicine compound input through the traditional Chinese medicine compound input component, and the symptoms corresponding to the disease input through the symptom input component, a confirmation component is displayed on the operation interface;

[0040] In response to receiving a confirmation request input by the user through the confirmation component, target proteins corresponding to the initial traditional Chinese medicine compound related information included in the confirmation request are queried from a preset database.

[0041] In a possible design, after determining the recommended traditional Chinese medicine compound based on the first score and the second score, the method further includes:

[0042] The determination result is displayed through the operation interface, and the determination result includes the names of each Chinese medicinal material in the recommended traditional Chinese medicine compound, the total number of target proteins corresponding to the recommended traditional Chinese medicine compound, the number of directly acting proteins, the number of indirectly acting proteins, the number of uncovered proteins, the number of side effect proteins, and the recommended grades of each drug pair.

[0043] In a possible design, after determining at least one candidate target protein, the method further includes:

[0044] Query the matching relationship between each candidate target protein and known drugs;

[0045] The operation interface includes a determination process display component, and the method further includes:

[0046] In response to receiving a determination process information display request triggered by the user through the determination process display component, determination process information is displayed, and the determination process information includes at least one of the following:

[0047] Functional analysis data and signaling pathway data corresponding to each target protein, protein-protein interaction network topological map, list of directly acting proteins, list of indirectly acting proteins, list of uncovered proteins, list of side effect proteins, and analysis results of each drug pair.

[0048] In a second aspect, the present application provides a device for recommending traditional Chinese medicine compounds, and the device includes:

[0049] A query module, which in response to receiving a confirmation request, queries target proteins corresponding to the initial traditional Chinese medicine compound related information included in the confirmation request from a preset database, and the confirmation request includes the names of each Chinese medicinal material in the initial traditional Chinese medicine compound, the disease name corresponding to the initial traditional Chinese medicine compound, and the symptoms corresponding to the disease;

[0050] A calculation module, configured to calculate a first score corresponding to each of the target proteins, where the first score is a correlation score between the target protein and the corresponding information;

[0051] A determination module, configured to determine at least one candidate target protein from each of the target proteins;

[0052] An acquisition module, configured to acquire traditional Chinese medicines related to each of the candidate target proteins;

[0053] The determination module is further configured to determine a first attribute feature label corresponding to each of the traditional Chinese medicines and a second attribute feature label corresponding to the symptom according to a preset mapping relationship;

[0054] The calculation module is further configured to calculate a second score corresponding to each of the traditional Chinese medicines based on the first attribute label and the second attribute label; the second score is a correlation score between the traditional Chinese medicine and the symptom corresponding to the disease;

[0055] The determination module is further configured to determine a recommended traditional Chinese medicine compound based on the first score and the second score.

[0056] In a third aspect, the present application provides a device for recommending a traditional Chinese medicine compound, where the device includes: a processor and a memory communicatively connected to the processor;

[0057] The memory is used to store computer execution instructions;

[0058] The processor is configured to execute the computer execution instructions stored in the memory to implement the method according to any one of the first aspects.

[0059] In a fourth aspect, the present application provides a computer-readable storage medium, where computer execution instructions are stored in the computer-readable storage medium, and when the computer execution instructions are executed by a processor, they are used to implement the method according to any one of the first aspects.

[0060] In a fifth aspect, the present application provides a computer program product, including a computer program, and when the computer program is executed by a processor, it implements the method according to any one of the first aspects.

[0061] The recommended method, device, equipment, medium and product of the traditional Chinese medicine compound provided by this application, in response to receiving a determination request, queries the target proteins corresponding to the initial traditional Chinese medicine compound-related information included in the determination request from a preset database. The determination request includes the names of each Chinese medicinal material in the initial traditional Chinese medicine compound, the name of the disease corresponding to the initial traditional Chinese medicine compound, and the symptoms corresponding to the disease; calculates the first score corresponding to each target protein and determines at least one candidate target protein from each target protein; the first score is the correlation score between the target protein and the corresponding information; obtains the Chinese medicinal materials related to each candidate target protein; determines the first attribute feature label corresponding to each Chinese medicinal material and the second attribute feature label corresponding to the symptom according to a preset mapping relationship; calculates the second score corresponding to each Chinese medicinal material based on the first attribute label and the second attribute label; the second score is the correlation score between the Chinese medicinal material and the symptoms corresponding to the disease; determines the recommended traditional Chinese medicine compound based on the first score and the second score. By querying the target proteins corresponding to each Chinese medicinal material and the disease name in the initial traditional Chinese medicine compound through a preset database and calculating its first score, the direct interaction relationship between the Chinese medicinal material and the disease target protein can be clarified; traditional traditional Chinese medicine compounds are mostly formulated based on experience, and there may be problems such as "ineffective ingredients" or "unclear targets". Through the screening of the first score, the target proteins with weak correlation with the disease target protein can be eliminated, focusing on the truly effective ingredients; by determining the first attribute feature label (such as "hot", "cold") of the Chinese medicinal material and the second attribute feature label (such as "qi deficiency", "blood stasis") of the symptom according to a preset mapping relationship and calculating the second score, the matching degree between the Chinese medicinal material and the symptom can be quantified; traditional compounds may have scattered curative effects due to too many medicinal materials. Through the screening of the second score, the Chinese medicinal materials with high matching degree with the symptoms can be preferentially selected, reducing redundant ingredients; the first score verifies the correlation between the Chinese medicinal material and the disease target protein, and the second score verifies the matching degree between the Chinese medicinal material and the symptom, forming a double verification of "target mechanism + symptom relief". Based on the first score and the second score, the recommended traditional Chinese medicine compound is determined, avoiding the one-sidedness that may be caused by relying only on the target or symptom score, and improving the adaptability of the traditional Chinese medicine compound to the disease. BRIEF DESCRIPTION OF THE DRAWINGS

[0062] The accompanying drawings herein are incorporated into the specification and constitute a part of this specification, showing embodiments consistent with this application, and are used together with the specification to explain the principles of this application.

[0063] Figure 1 It is an application scenario diagram of the recommended method of the traditional Chinese medicine compound provided by an embodiment of this application;

[0064] Figure 2 It is a flowchart of the recommended method of the traditional Chinese medicine compound provided by an embodiment of this application;

[0065] Figure 3A flowchart of a method for recommending a Chinese herbal compound according to another embodiment of the present application;

[0066] Figure 4 A schematic diagram showing changes in the display screen of a recommended operation interface for a Chinese herbal compound provided in one embodiment of the present application;

[0067] Figure 5 A schematic diagram of the structure of a device for recommending a Chinese herbal compound according to an embodiment of the present application;

[0068] Figure 6 This is a schematic diagram of the structure of the recommended equipment for preparing a Chinese herbal compound according to one embodiment of the present application.

[0069] The above drawings illustrate specific embodiments of the present application, which will be described in more detail below. These drawings and the textual description are not intended to limit the scope of the present application in any way, but rather to illustrate the concepts of the present application to those skilled in the art by reference to specific embodiments. DETAILED DESCRIPTION

[0070] Exemplary embodiments will be described in detail herein, with examples illustrated in the accompanying drawings. In the following description, when referring to the drawings, identical numerals in different figures represent identical or similar elements, unless otherwise indicated. The embodiments described in the following exemplary embodiments are not intended to represent all embodiments consistent with the present application. Rather, they are merely examples of apparatus and methods consistent with certain aspects of the present application, as detailed in the appended claims.

[0071] It should be noted that in the embodiments of the present application, certain software, components, and models may be mentioned, which should be regarded as exemplary. Their purpose is only to illustrate the feasibility of implementing the technical solution of the present application, but it does not mean that the applicant has or will necessarily use the solution.

[0072] In order to clearly understand the technical solution of the present application, the solution of the prior art is first introduced in detail.

[0073] As the core means of traditional Chinese medicine (TCM) for treating diseases, the rationality of the formula compatibility in traditional Chinese medicine compound directly determines the quality of clinical efficacy. TCM emphasizes the core concept of "treatment based on syndrome differentiation", that is, through the comprehensive collection of information such as the patient's symptoms, signs, pulse conditions, and tongue manifestations by combining the four diagnostic methods (inspection, auscultation and olfaction, interrogation, and palpation), and analyzing the causes, pathogenesis, and disease locations in combination with TCM theory, and then formulating an individualized treatment plan for traditional Chinese medicine compound. However, with the complexity of the modern disease spectrum (such as chronic diseases, multi-system co-morbidities, etc.) and the significant increase in individual differences among patients, the formula pattern relying solely on traditional experience or single symptoms gradually exposes limitations, resulting in a decrease in the compatibility between traditional Chinese medicine compound and diseases and an increase in the volatility of clinical efficacy. To break through this bottleneck, modern research has deeply analyzed the pharmacodynamic substance basis and action mechanism of traditional Chinese medicine compound through interdisciplinary technologies, significantly improving the scientificity and precision of the formula. For example, by using high-throughput screening technology combined with clinical phenotype models, the active ingredient groups that play key pharmacodynamic effects in traditional Chinese medicine compound can be quickly identified, and they can be used as screening indicators to optimize the compound composition; chemometric methods (such as principal component analysis, cluster analysis) quantify the correlation between the chemical components and pharmacodynamic effects of Chinese medicinal materials, eliminate redundant components, and streamline the compound structure; machine learning models based on clinical big data can integrate multi-dimensional information of patients (such as genomics, metabolomics data) to achieve dynamic optimization of compound compatibility, making it more suitable for individualized treatment needs. However, the complexity of traditional Chinese medicine compound is far more than the association between components and targets. The attribute characteristics of Chinese medicinal materials have multiple dimensions. Therefore, only focusing on the component-target relationship may fall into the dilemma of "effective in mechanism but ineffective clinically", resulting in a low compatibility between traditional Chinese medicine compound and diseases.

[0074] Therefore, when facing the technical problems in the prior art, in order to establish the association between traditional Chinese medicine materials and diseases, the target proteins corresponding to each traditional Chinese medicine material and disease name in the initial compound prescription are queried from the preset database, and then the first score of the target protein and the corresponding information (traditional Chinese medicine materials, diseases) is calculated to screen out the candidate target proteins highly related to the core pathological mechanism of the disease, ensuring the molecular mechanism effectiveness of the traditional Chinese medicine compound prescription; in order to verify the relevance between the candidate target proteins and traditional Chinese medicine materials bidirectionally, the traditional Chinese medicine materials related to each candidate target protein are obtained, and at the same time, the traditional Chinese medicine materials related to the candidate target proteins can be more comprehensively selected, not limited to the traditional Chinese medicine materials in the initial traditional Chinese medicine compound prescription, improving the accuracy of the traditional Chinese medicine compound prescription; due to the diverse dimensional attributes of traditional Chinese medicine materials, including four natures and five flavors (cold, heat, warm, cool, pungent, sweet, sour, bitter, salty), meridian tropism (such as the zang-fu organs affected), efficacy (such as clearing heat, promoting blood circulation, tonifying, etc.), these attributes need to be highly consistent with the symptom attributes of the disease (such as cold, heat, deficiency, excess, exterior, interior, slow, urgent, etc.), so the first attribute feature labels corresponding to each traditional Chinese medicine material and the second attribute feature labels corresponding to the symptoms are determined according to the preset mapping relationship, and then the second score of each traditional Chinese medicine material is calculated based on the first attribute label and the second attribute label to quantify the matching degree between the attribute features of the traditional Chinese medicine material and the symptoms, screening out the traditional Chinese medicine materials highly matching the symptoms, ensuring the symptom relief effectiveness of the compound prescription; finally, combining the molecular mechanism and symptom adaptability, optimizing the compound prescription composition, and determining the recommended traditional Chinese medicine compound prescription based on the first score and the second score, avoiding the one-sidedness of relying only on the molecular mechanism or symptom adaptability, and improving the overall adaptability of the traditional Chinese medicine compound prescription to the disease.

[0075] Figure 1 The application scenario diagram of the recommended method for the traditional Chinese medicine compound prescription provided by an embodiment of the present application is as Figure 1 shown. The application scenario diagram of the recommended method for the traditional Chinese medicine compound prescription provided by this embodiment includes: a terminal device 101, a server 102, and a server database 103.

[0076] Specifically, the user can send a determination request to the server 102 through the terminal device 101. The determination request includes the names of each Chinese medicinal material in the initial Chinese medicine compound, the name of the disease corresponding to the initial Chinese medicine compound, and the symptoms corresponding to the disease. After receiving the determination request, the server 102 queries the target proteins corresponding to the relevant information of the initial Chinese medicine compound included in the determination request from the server database 103. The server 102 calculates the first score corresponding to each target protein and determines at least one candidate target protein from each target protein. The first score is the correlation score between the target protein and the corresponding information. Then the server 102 obtains the Chinese medicinal materials related to each candidate target protein from the server database 103, determines the first attribute feature labels corresponding to each Chinese medicinal material and the second attribute feature labels corresponding to the symptoms according to the preset mapping relationship, and then calculates the second score corresponding to each Chinese medicinal material based on the first attribute label and the second attribute label. The second score is the correlation score between the Chinese medicinal material and the symptoms corresponding to the disease. Finally, the server 102 determines the recommended Chinese medicine compound based on the first score and the second score. The server 102 sends the recommended Chinese medicine compound to the terminal device 101 for the user to view.

[0077] Optionally, it can also be that the server establishes a communication connection with an external database by calling an interface or other means to obtain the Chinese medicinal materials related to each candidate target protein. This embodiment does not limit this.

[0078] The following uses specific embodiments to elaborate on the technical solution of the present application and how the technical solution of the present application solves the above technical problems in detail. These specific embodiments below can be combined with each other, and the same or similar concepts or processes may not be repeated in some embodiments. The embodiments of the present application will be described below in conjunction with the accompanying drawings.

[0079] Figure 2 It is a flowchart of a method for recommending a Chinese medicine compound provided by an embodiment of the present application. As Figure 2 shown, the execution subject of this embodiment is a device for recommending a Chinese medicine compound. The device for recommending a Chinese medicine compound can be implemented through a computer program, or through a medium storing relevant computer programs, such as a USB flash drive and / or an optical disc, etc., and can also be integrated in a device for recommending a Chinese medicine compound, such as a server, etc. The method for recommending a Chinese medicine compound provided in this embodiment includes the following steps:

[0080] Step 201, in response to receiving a determination request, query the target proteins corresponding to the relevant information of the initial Chinese medicine compound included in the determination request from a preset database. The determination request includes the names of each Chinese medicinal material in the initial Chinese medicine compound, the name of the disease corresponding to the initial Chinese medicine compound, and the symptoms corresponding to the disease.

[0081] Among them, the preset database refers to the one preconfigured in the traditional Chinese medicine compound recommendation device, including a traditional Chinese medicine small molecule database (such as PubChem, SymMap), a disease gene library (such as OMIM, DisGeNET), etc., which is used to query the target proteins corresponding to traditional Chinese medicinal materials and diseases therefrom.

[0082] Among them, the initial traditional Chinese medicine compound refers to a combination of medicinal materials for a specific disease obtained based on traditional Chinese medicine consultation or clinical experience.

[0083] Specifically, the user can send the names of each traditional Chinese medicinal material in the initial traditional Chinese medicine compound, the name of the disease corresponding to the initial traditional Chinese medicine compound, and the symptoms corresponding to the disease to the traditional Chinese medicine compound recommendation device through the terminal device to initiate a determination request. After receiving the determination request, the traditional Chinese medicine compound recommendation device queries the active ingredients corresponding to the traditional Chinese medicinal materials according to the names of various medicinal materials in the initial traditional Chinese medicine compound in the preset database, then queries the corresponding target proteins according to the active ingredients, and then queries the target proteins corresponding to the disease included in the determination request from the preset database.

[0084] It can be understood that one traditional Chinese medicinal material may correspond to multiple target proteins; a disease may also correspond to multiple target proteins.

[0085] Optionally, the traditional Chinese medicine compound recommendation device can also perform keyword retrieval according to the disease symptoms in the determination request to obtain diseases related to the symptoms, and query the target proteins corresponding to the diseases related to the symptoms from the preset database, and also perform subsequent steps on it. This embodiment does not make a limit on this.

[0086] Step 202, calculate the first score corresponding to each target protein and determine at least one candidate target protein from each target protein; the first score is the relevance score between the target protein and the corresponding information.

[0087] Specifically, after querying the target proteins, obtain various data or features related to the target proteins, such as expression data, protein interaction data, etc. The traditional Chinese medicine compound recommendation device preprocesses the obtained data to ensure the accuracy and consistency of the data, selects a suitable relevance analysis method, such as correlation analysis, regression analysis, network analysis, etc., performs a relevance analysis on each target protein and its corresponding information, calculates the relevance index between the target protein and the corresponding information, and the scoring method can adopt methods such as weighted summation, machine learning model prediction, etc. After calculating the first scores of each target protein, sort all the target proteins according to the level of the first scores, and select the target proteins with higher scores as candidate target proteins.

[0088] Among them, the method for obtaining various data or features related to the target proteins can be to call an interface, query a database, etc. This embodiment does not make a limit on this.

[0089] Exemplarily, call the API interface of the protein interaction database, send a query request containing the list of target proteins to it, and set key parameters: limit the species to human (species number 9606), the interaction confidence threshold (default ≥ 0.4), and specify the interaction type (such as physical binding or functional association). The protein interaction database returns the interaction pairs between target proteins based on multi-source evidence (experimental verification, co-expression analysis, text mining, etc.). Each interaction record contains the names of two target proteins, a comprehensive score, and sub-item evidence scores (such as the number of experimental supports, the number of database records, etc.).

[0090] Optionally, the criteria for determining candidate target proteins can be set according to specific research needs and actual situations. For example, the target proteins ranked top N in terms of score can be selected as candidate target proteins, or a score threshold can be set, etc. This embodiment does not limit this.

[0091] Step 203, obtain the traditional Chinese medicines related to each candidate target protein.

[0092] It can be understood that one target protein may be related to multiple traditional Chinese medicines, that is, the target proteins corresponding to the traditional Chinese medicines in the initial traditional Chinese medicine compound may also be related to other traditional Chinese medicines.

[0093] Specifically, after determining at least one target protein, obtain the traditional Chinese medicines related to each candidate target protein, such as by calling the database for query and receiving the query results, so as to obtain other traditional Chinese medicines related to the candidate target proteins, avoiding being limited only to the traditional Chinese medicines in the initial traditional Chinese medicine compound, and further improving the reliability of the finally recommended traditional Chinese medicine compound.

[0094] Step 204, determine the first attribute feature labels corresponding to each traditional Chinese medicine and the second attribute feature labels corresponding to the symptoms according to the preset mapping relationship.

[0095] Among them, the first attribute feature label refers to the attribute feature label corresponding to the traditional Chinese medicine, such as bitter, cold, pungent, sweet, and the meridian tropism such as spleen, lung, etc.

[0096] Among them, the second attribute feature label refers to the attribute feature label of the traditional Chinese medicine used to treat the symptom, such as bitter, dryness, spleen and stomach, etc.

[0097] Among them, the preset mapping relationship refers to the association relationship between each traditional Chinese medicine and its related attribute feature labels such as its medicinal property, etc., which is pre-configured in the traditional Chinese medicine compound recommendation device, and the association relationship between each symptom and the attribute feature label of the traditional Chinese medicine used to treat the symptom.

[0098] Exemplarily, the first attribute feature labels corresponding to the traditional Chinese medicine Scutellaria baicalensis: bitter, cold, lung, gallbladder, clearing heat, drying dampness; the second attribute feature labels corresponding to the symptom qi deficiency: warm, sweet, spleen, lung.

[0099] Specifically, in addition to the traditional Chinese medicinal materials related to the candidate target protein in the initial traditional Chinese medicine compound, other related traditional Chinese medicinal materials were obtained, and the first attribute feature labels corresponding to these traditional Chinese medicinal materials were determined according to the preset mapping relationship; then, according to the preset mapping relationship, the second attribute feature labels corresponding to the symptoms included in the determination request were determined.

[0100] Optionally, a semantic model can also be pre-configured in the traditional Chinese medicine compound recommendation device to match the symptom description in the determination request with the symptom description in the preset mapping relationship, so as to determine the second attribute feature label corresponding to the symptom.

[0101] It can be understood that a large number of materials have been pre-query and integrated, including "Classification and Determination Standards for Traditional Chinese Medicine Constitution of Chinese Residents", Traditional Chinese Medicine Prescription-Syndrome Database, "Traditional Chinese Medicine Constitution Scale of China", "Great Dictionary of Traditional Chinese Medicine", "Science of Traditional Chinese Medicine Formulas", "Internal Medicine of Traditional Chinese Medicine", etc. The attribute feature labels of traditional Chinese medicinal materials and symptoms are extracted from them, such as the four natures: cold, hot, warm, cool, neutral; the five flavors: pungent, sweet, sour, bitter, salty; ascending, descending, floating, sinking; meridian tropism: heart, liver, spleen, lung, kidney, stomach, large intestine, small intestine, gallbladder, bladder, etc.; therapeutic effects: replenishing qi, nourishing blood, strengthening the spleen, resolving phlegm, promoting diuresis, activating blood circulation, regulating qi, soothing the liver, clearing heat, detoxifying, nourishing yin, warming yang, calming the nerves, dredging collaterals, stopping bleeding, dispelling wind, etc.; respectively establish the association relationship between each traditional Chinese medicinal material and its corresponding first attribute label, and the association relationship between each symptom and the attribute feature label of the traditional Chinese medicinal material used to treat the symptom, that is, the association relationship between the symptom and its corresponding second attribute feature label, and store it in the traditional Chinese medicine compound recommendation device as the preset mapping relationship.

[0102] Step 205, calculate the second score corresponding to each traditional Chinese medicinal material based on the first attribute label and the second attribute label; the second score is the correlation score between the traditional Chinese medicinal material and the symptom corresponding to the disease.

[0103] Specifically, after determining the first attribute label and the second attribute label, calculate the similarity between the first attribute label corresponding to each traditional Chinese medicinal material and the second attribute feature labels corresponding to all symptoms as the second score.

[0104] Exemplarily, the symptoms include qi deficiency and phlegm-dampness, and the corresponding second-attribute characteristic labels are warm, sweet, spleen, lung, replenishing qi, bitter, dryness, spleen, stomach, resolving phlegm, and promoting diuresis, respectively. At this time, to calculate the second score of the Chinese medicinal material turmeric, the corresponding first-attribute characteristic labels of turmeric are bitter, cold, lung, gallbladder, clearing heat, and drying dampness. Then, the second score can be obtained by calculating the similarity between bitter, cold, lung, gallbladder, clearing heat, and drying dampness and all the second-attribute characteristic labels corresponding to the symptoms: warm, sweet, spleen, lung, replenishing qi, bitter, dryness, spleen, stomach, resolving phlegm, and promoting diuresis. For example, there are six first-attribute characteristic labels corresponding to turmeric, among which bitter, lung, and drying dampness overlap with all the second-attribute characteristic labels corresponding to the symptoms. Then, the second score of the Chinese medicinal material turmeric is the intersection number 3 divided by the total number 6 of the first-attribute labels, that is, 0.5. Or the second score can be calculated by other methods, and this embodiment does not limit this.

[0105] Step 206: Determine the recommended traditional Chinese medicine compound based on the first score and the second score.

[0106] It can be understood that the Chinese medicinal materials for which the second score has been calculated all correspond to the candidate target proteins. The first scores of each candidate target protein have been calculated in step 202, that is, the first score of each Chinese medicinal material is the first score of the candidate target protein corresponding to it.

[0107] Specifically, after obtaining the first score and the second score corresponding to each Chinese medicinal material, calculate the final score corresponding to each Chinese medicinal material based on the first score and the second score respectively. For example, calculate by the method of weighted summation, and determine the recommended traditional Chinese medicine compound according to the final score.

[0108] Optionally, a standard for determining the recommended traditional Chinese medicine compound can be pre-configured in the recommended device of the traditional Chinese medicine compound, such as setting a threshold for the final score, and the Chinese medicinal materials with scores exceeding this threshold are used as recommendations; or sort the final scores of all Chinese medicinal materials, and use the top 5 Chinese medicinal materials as recommendations; or other methods, and this embodiment does not limit this.

[0109] Optionally, it is also possible not to calculate the final score and directly determine based on the first score and the second score corresponding to each Chinese medicinal material. For example, pre-configure the thresholds of the first score and the second score in the recommended device of the traditional Chinese medicine compound, and use the Chinese medicinal materials that satisfy both the first score and the second score thresholds as recommendations, or other methods, and this embodiment does not limit this.

[0110] The recommended method for the traditional Chinese medicine compound provided by the embodiments of the present application, in response to receiving a determination request, queries the target proteins corresponding to the initial traditional Chinese medicine compound-related information included in the determination request from a preset database. The determination request includes the names of each Chinese medicinal material in the initial traditional Chinese medicine compound, the name of the disease corresponding to the initial traditional Chinese medicine compound, and the symptoms corresponding to the disease; calculates the first score corresponding to each target protein and determines at least one candidate target protein from each target protein; the first score is the relevance score between the target protein and the corresponding information; obtains the Chinese medicinal materials related to each candidate target protein; determines the first attribute feature label corresponding to each Chinese medicinal material and the second attribute feature label corresponding to the symptom according to the preset mapping relationship; calculates the second score corresponding to each Chinese medicinal material based on the first attribute label and the second attribute label; the second score is the relevance score between the Chinese medicinal material and the symptom corresponding to the disease; determines the recommended traditional Chinese medicine compound based on the first score and the second score. By querying the target proteins corresponding to each Chinese medicinal material and the disease name in the initial traditional Chinese medicine compound through the preset database and calculating its first score, the direct interaction relationship between the Chinese medicinal material and the disease target protein can be clarified; traditional Chinese medicine compounds are mostly formulated based on experience, and there may be problems such as "ineffective ingredients" or "unclear targets". Through the screening of the first score, the target proteins with weak relevance to the disease target protein can be eliminated, focusing on the truly effective ingredients; by determining the first attribute feature label (such as "hot", "cold") of the Chinese medicinal material and the second attribute feature label (such as "qi deficiency", "blood stasis") of the symptom according to the preset mapping relationship and calculating the second score, the matching degree between the Chinese medicinal material and the symptom can be quantified; traditional compounds may have scattered curative effects due to too many medicinal materials. Through the screening of the second score, the Chinese medicinal materials with a high degree of matching with the symptoms can be preferentially selected to reduce redundant ingredients; the first score verifies the relevance between the Chinese medicinal material and the disease target protein, and the second score verifies the matching degree between the Chinese medicinal material and the symptom, forming a double verification of "target mechanism + symptom relief". Based on the first score and the second score, the recommended traditional Chinese medicine compound is determined, avoiding the one-sidedness that may be caused by relying only on the target or symptom score, and improving the adaptability of the traditional Chinese medicine compound to the disease.

[0111] As an optional implementation manner, on the basis of the above embodiment, calculating the first score corresponding to each target protein and determining at least one candidate target protein from each target protein includes:

[0112] Obtaining the interaction scores between each target protein;

[0113] Constructing a protein-protein interaction network topological map according to the interaction scores;

[0114] Calculating the numerical values of various centrality indexes of each target protein based on the protein-protein interaction network topological map, and calculating the first score corresponding to each target protein in a weighted summation manner based on the numerical values of various centrality indexes of each target protein and the weights corresponding to the numerical values of various centrality indexes;

[0115] At least one candidate target protein is determined according to the first score corresponding to each target protein.

[0116] Among them, the protein-protein interaction network topology map is a map reflecting the relationships between target proteins, which is drawn based on interaction scores according to specific rules and includes nodes (target proteins) and edges (interaction relationships). For example, if the interaction score between target protein A and target protein B is 0.999, a high-weight edge is generated between target protein A and target protein B. The topological importance can also be mapped by the size and color of the nodes, and the thickness of the edges reflects the score level, so as to intuitively display the relationships between target proteins.

[0117] Among them, the centrality index value is a value reflecting the importance of a target protein in the protein-protein interaction network topology map. The centrality index can include degree centrality, betweenness centrality, closeness centrality, eigenvector centrality, etc.

[0118] Specifically, after querying the target proteins, all the target proteins are listed in a list, the API interface of the protein interaction database is called, a query request containing the list of target proteins is sent to it, and key parameters are set and the interaction type (such as physical binding or functional association) is specified. The protein interaction database returns the interaction pairs between target proteins and their interaction scores based on multi-source evidence, so as to obtain the interaction scores between each target protein. The recommendation device for traditional Chinese medicine compound analyzes the interaction scores into nodes (target proteins) and edges (interaction relationships), where the weight of the edge is quantified by the interaction score, constructs a protein-protein interaction network topology map, and calculates various centrality index values of each target protein based on the map. For example, the degree centrality is the number of direct connections, the betweenness centrality is the frequency of the node as the bridge of the shortest path, and the closeness centrality is the average distance from other nodes. Then, according to the weights corresponding to the centrality index values configured in advance, the first score of each target protein is calculated by means of weighted summation, and at least one candidate target protein is determined according to the first score corresponding to each target protein.

[0119] Optionally, rules for screening candidate target proteins can be pre-configured in the recommendation device for traditional Chinese medicine compound, such as setting a first score threshold, and the target proteins whose first scores meet the threshold are determined as candidate target proteins. It can also be other rules, which are not limited in this embodiment.

[0120] Optionally, the protein-protein interaction network topology map can be output as a result for the user to view.

[0121] The recommended method for the traditional Chinese medicine compound provided by the embodiment of the present application calculates the first score corresponding to each target protein and determines at least one candidate target protein from each target protein, including: obtaining the interaction scores between each target protein; constructing a protein interaction network topology map according to the interaction scores; calculating the numerical values of various centrality indexes of each target protein based on the protein interaction network topology map, and calculating the first score corresponding to each target protein by using the weighted summation method based on the numerical values of various centrality indexes of each target protein and the weights corresponding to the various centrality index numerical values; determining at least one candidate target protein according to the first score corresponding to each target protein. By obtaining the interaction scores between each target protein, the degree of association between target proteins can be quantified, providing an objective data basis for subsequent analysis. The interaction between target proteins is presented in the form of a network topology map, intuitively showing the complex relationship between target proteins. Calculating the numerical values of various centrality indexes of each target protein based on the protein interaction network topology map, different centrality indexes reflect the importance of target proteins in the network from different perspectives. Considering these indexes comprehensively can more comprehensively evaluate the characteristics of target proteins; calculating the first score corresponding to each target protein by using the weighted summation method according to the numerical values of various centrality indexes and their corresponding weights fully considers the relative importance of different centrality indexes, making the scoring result more scientific and reasonable. By reasonably setting the weights, according to the specific research purposes and requirements, the role of certain key indexes can be highlighted, so as to more accurately evaluate the comprehensive importance of target proteins; the first score comprehensively considers the interaction relationship between target proteins and various centrality indexes, can more effectively identify the target proteins with important positions and potential functions in the network, can reduce the interference of human factors, and improve the reliability and effectiveness of the screening results.

[0122] As an optional implementation manner, on the basis of the above embodiment, calculating the second score corresponding to each traditional Chinese medicine material based on the first attribute label and the second attribute label includes:

[0123] Calculating the similarity between the first attribute label and the second attribute label corresponding to each traditional Chinese medicine material to obtain the second score corresponding to each traditional Chinese medicine material.

[0124] It can be understood that there may be multiple symptoms, and each symptom has its corresponding second attribute feature label. Calculating the second score is to calculate the similarity between the first attribute feature label corresponding to each traditional Chinese medicine material and the second attribute feature labels corresponding to all symptoms respectively.

[0125] Exemplarily, to calculate the cosine similarity, operations such as word segmentation, stop word removal, and stemming are performed on the texts of the first attribute label and the second attribute label. The preprocessed texts are converted into word vectors. Methods such as the bag-of-words model and TF-IDF can be used. The cosine value of the angle between the two word vectors is calculated using the cosine similarity formula. The closer the value is to 1, the higher the similarity; or other methods can be used to calculate the similarity, which is not limited in this embodiment.

[0126] The recommended method for traditional Chinese medicine compound provided by the embodiments of this application calculates the second score corresponding to each traditional Chinese medicine based on the first attribute label and the second attribute label, including: calculating the similarity between the first attribute label and the second attribute label corresponding to each traditional Chinese medicine to obtain the second score corresponding to each traditional Chinese medicine. By calculating the similarity between the first attribute feature label and the second attribute feature label as the second score, the abstract association can be transformed into a quantitative value, reducing the interference of human factors and objectively reflecting their degree of association, laying a reliable data foundation for determining the recommended traditional Chinese medicine compound.

[0127] As an optional implementation manner, based on the above embodiments, determining the recommended traditional Chinese medicine compound includes:

[0128] Based on the first score, the second score corresponding to each traditional Chinese medicine, and the weights corresponding to the first score and the second score, the third score corresponding to each traditional Chinese medicine is calculated by using the weighted summation method;

[0129] The recommended traditional Chinese medicine compound is determined according to the third score.

[0130] Among them, the third score refers to the score calculated based on the comprehensive first score and the second score.

[0131] Specifically, the weights corresponding to the first score and the weights corresponding to the second score are pre-configured in the recommended device for traditional Chinese medicine compound. After obtaining the first score and the second score corresponding to each traditional Chinese medicine, based on the weights corresponding to the first score and the second score, the third score corresponding to each traditional Chinese medicine is calculated by using the weighted summation method, and then the recommended traditional Chinese medicine compound is determined according to the third score.

[0132] Exemplarily, the first score corresponding to traditional Chinese medicine A is 0.85, the second score is 0.92, the weight of the first score is 0.6, and the weight of the second score is 0.4. Then the third score corresponding to traditional Chinese medicine A is .

[0133] Optionally, the rules for determining the recommended traditional Chinese medicine compound can be pre-configured in the recommended device for traditional Chinese medicine compound, such as sorting the third scores corresponding to each traditional Chinese medicine, and taking the top six traditional Chinese medicines as the recommended traditional Chinese medicine compound.

[0134] The recommended method for the traditional Chinese medicine compound provided by the embodiment of the present application determines the recommended traditional Chinese medicine compound based on the first score and the second score, including: calculating the third score corresponding to each Chinese medicinal material by using the weighted summation method based on the first score, the second score corresponding to each Chinese medicinal material, and the weights corresponding to the first score and the second score; determining the recommended traditional Chinese medicine compound according to the third score. The first score and the second score respectively reflect the correlation degrees in different aspects. By comprehensively considering the two-dimensional characteristics through weighted summation, the one-sidedness caused by relying only on a single score is avoided; by setting different weights, different application scenarios can be flexibly responded to.

[0135] As an optional implementation manner, on the basis of the above embodiment, after determining the recommended traditional Chinese medicine compound based on the first score and the second score, the method further includes:

[0136] Performing permutation and combination on each Chinese medicinal material in the recommended traditional Chinese medicine compound to obtain a plurality of medicine pairs;

[0137] Determining the adjustment coefficient of each medicine pair;

[0138] Determining the recommended level of each medicine pair based on the adjustment coefficient and the third score corresponding to each Chinese medicinal material in each medicine pair.

[0139] Among them, a medicine pair refers to a combination including at least two Chinese medicinal materials, such as astragalus membranaceus and codonopsis pilosula.

[0140] Among them, the adjustment coefficient refers to the coefficient used to adjust the third score, such as increasing by 15% or decreasing by 10%, etc.

[0141] Specifically, after determining the recommended traditional Chinese medicine compound, performing permutation and combination on each Chinese medicinal material included therein to obtain a plurality of medicine pairs, respectively determining the adjustment coefficient of each medicine pair, such as determining the specific adjustment coefficient according to whether the medicine pair includes poisonous Chinese medicinal materials, and after determining the adjustment coefficient, calculating the third score to obtain the final score, so as to determine the recommended level of each medicine pair.

[0142] It can be understood that the third score corresponding to a medicine pair is the sum of the third scores corresponding to each Chinese medicinal material included in the medicine pair.

[0143] Exemplarily, if the medicine pair is aconite + ginger + licorice root, and it is determined that aconite in it is a highly poisonous Chinese medicinal material, then the adjustment coefficient is a decrease of 40%. If the third score of the medicine pair is 1.6, the final score calculated through the adjustment coefficient is .

[0144] Optionally, the relationship between each recommended level and the score can be pre-configured in the recommended device for the traditional Chinese medicine compound, such as a first-level recommendation for a score greater than 1.5, a second-level recommendation for a score between 1 and 1.5, etc., or other methods, and this embodiment does not limit this.

[0145] After determining the recommended traditional Chinese medicine (TCM) compound based on the first score and the second score, the method for recommending the TCM compound provided by the embodiment of the present application further includes: arranging and combining each Chinese medicinal material in the recommended TCM compound to obtain multiple pairs of medicinal materials; determining the adjustment coefficient of each pair of medicinal materials; and determining the recommended level of each pair of medicinal materials based on the adjustment coefficient and the third score corresponding to each Chinese medicinal material in each pair of medicinal materials. To further verify the reliability of the recommended TCM compound, the compound is disassembled into pairs of medicinal materials, which can specifically analyze the interaction between medicinal materials. By determining the adjustment coefficient, the degree of synergistic effect or antagonistic effect can be quantitatively reflected. Based on the adjustment coefficient and the third score, the recommended level of each pair of medicinal materials is determined, comprehensively considering the synergistic effect of each pair of medicinal materials, so as to improve the suitability of the recommended prescription for diseases.

[0146] As an optional implementation manner, on the basis of the above embodiment, determining the adjustment coefficient of each pair of medicinal materials includes:

[0147] Determining whether the pair of medicinal materials is a classical pair of medicinal materials. If so, determining that the adjustment coefficient is to increase the third score by the first preset adjustment coefficient; if not, determining that the adjustment coefficient is 0;

[0148] And / or, determining whether the compatibility of the properties of the Chinese medicinal materials in the pair of medicinal materials is opposite. If so, determining that the adjustment coefficient is to decrease the third score by the second preset adjustment coefficient; if not, determining that the adjustment coefficient is 0;

[0149] And / or, determining whether there is a Chinese medicinal material with toxicity in the pair of medicinal materials. If so, determining that the adjustment coefficient is to decrease the third score by the third preset adjustment coefficient; if not, determining that the adjustment coefficient is 0.

[0150] Among them, the first preset adjustment coefficient refers to the coefficient corresponding to the classical pair of medicinal materials index, such as 15%, etc.

[0151] Among them, the second preset adjustment coefficient refers to the coefficient corresponding to the compatibility of the properties of the medicinal materials index, such as 10%, etc.

[0152] Among them, the third preset adjustment coefficient refers to the coefficient corresponding to the toxicity index, such as 30%, etc.

[0153] Specifically, after obtaining the pair of medicinal materials, determine whether the pair of medicinal materials is a classical pair of medicinal materials. For example, query in the TCMID pair of medicinal materials database. If it can be queried, it means that the pair of medicinal materials is a classical pair of medicinal materials, and determine that the adjustment coefficient is to increase the third score by the first preset adjustment coefficient; determine whether the compatibility of the Chinese medicinal materials in the pair of medicinal materials is opposite. For example, cold + heat means that the compatibility of the pair of medicinal materials is opposite, and determine that the adjustment coefficient is to decrease the third score by the second preset adjustment coefficient; determine whether there is a Chinese medicinal material with toxicity in the pair of medicinal materials. If so, determine that the adjustment coefficient is to decrease the third score by the third preset adjustment coefficient.

[0154] It is understandable that to determine whether the compatibility of each traditional Chinese medicine in the medicine pair is opposite, the compatibility can be based on the first attribute characteristic labels corresponding to each traditional Chinese medicine.

[0155] Among them, to determine whether there are toxic traditional Chinese medicines in the medicine pair, a query can be made in the relevant database to determine whether there are toxic traditional Chinese medicines.

[0156] Optionally, the third preset adjustment coefficient can also be configured with different adjustment coefficients according to the level of toxicity. For example, the slightly toxic is down-regulated by 10%, and the highly toxic is down-regulated by 40%, etc. This embodiment does not limit this.

[0157] Exemplarily, for the medicine pair Pinellia ternata + dried ginger + Chinese date, its corresponding third score is , this medicine pair is a classic medicine pair, then the third score is up-regulated by 15%. The compatibility of each traditional Chinese medicine in this medicine pair is the same, so the adjustment coefficient is 0. Pinellia ternata in the medicine pair is a slightly toxic medicinal material, then the third score is down-regulated by 10%. In summary, the final score of this medicine pair is .

[0158] The recommended method for the traditional Chinese medicine compound provided by the embodiment of the present application to determine the adjustment coefficient of each medicine pair includes: determining whether the medicine pair is a classic medicine pair. If so, determining that the adjustment coefficient is to up-regulate the third score by the first preset adjustment coefficient. If not, determining that the adjustment coefficient is 0; and / or, determining whether the medicinal property compatibility of each traditional Chinese medicine in the medicine pair is opposite. If so, determining that the adjustment coefficient is to down-regulate the third score by the second preset adjustment coefficient. If not, determining that the adjustment coefficient is 0; and / or, determining whether there are toxic traditional Chinese medicines in the medicine pair. If so, determining that the adjustment coefficient is to down-regulate the third score by the third preset adjustment coefficient. If not, determining that the adjustment coefficient is 0. The classic medicine pair has been clinically verified, and its synergistic effect is clear. The up-regulation coefficient can ensure that the compound retains the traditional advantages, and at the same time enhances the modern interpretability through quantitative scoring; reduces the efficacy offset or adverse reactions caused by the conflict of medicinal properties through quantitative constraints, and improves the safety of the compound; intuitively reflects the toxicity risk through quantitative scoring, which is convenient for weighing the efficacy and safety; the first, second, and third preset adjustment coefficients can be dynamically adjusted according to clinical needs to improve flexibility.

[0159] As an optional implementation manner, on the basis of the above embodiment, after constructing the protein-protein interaction network topology map according to the interaction score, the method further includes:

[0160] Determining the directly acting proteins, indirectly acting proteins, and uncovered proteins based on the protein-protein interaction network topology map;

[0161] Determining the side effect proteins in each target protein;

[0162] Outputting a list including directly acting proteins, indirectly acting proteins, uncovered proteins, and side effect proteins.

[0163] Among them, the directly acting protein refers to the protein whose target protein corresponding to the traditional Chinese medicine coincides with the target protein corresponding to the disease, that is, in the protein interaction network topology map, this protein is directly connected to both the traditional Chinese medicine and the disease.

[0164] Among them, the indirectly acting protein refers to the protein directly connected to the disease and indirectly connected to the traditional Chinese medicine in the protein interaction network topology map.

[0165] Among them, the uncovered protein refers to the protein directly connected to the disease, but neither directly connected nor indirectly connected to the traditional Chinese medicine in the protein interaction network topology map.

[0166] Among them, the side-effect protein refers to the protein related to the toxicity, adverse reactions, or inhibition of key physiological functions of known drugs.

[0167] Specifically, after constructing the protein interaction network topology map, find the protein that is directly connected to both the traditional Chinese medicine and the disease in the map and determine it as the directly acting protein; find the protein that is directly connected to the disease and indirectly connected to the traditional Chinese medicine and determine it as the indirectly acting protein; find the protein that is directly connected to the disease but neither directly connected nor indirectly connected to the traditional Chinese medicine and determine it as the uncovered protein; then query the side-effect property of all target proteins obtained by querying in the preset database to determine the side-effect protein, and finally output a list including the directly acting protein, indirectly acting protein, uncovered protein, and side-effect protein, and each type of protein is listed separately in the list.

[0168] The recommended method for the traditional Chinese medicine compound provided by the embodiment of the present application, after constructing the protein interaction network topology map according to the interaction score, the method further includes: determining the directly acting protein, indirectly acting protein, and uncovered protein based on the protein interaction network topology map; determining the side-effect protein in each target protein; outputting a list including the directly acting protein, indirectly acting protein, uncovered protein, and side-effect protein. By classifying and outputting the directly acting protein, indirectly acting protein, uncovered protein, and side-effect protein, the interaction relationship is systematically analyzed, the side-effect risk is quantified, and a precise basis is provided for risk assessment.

[0169] As an optional implementation manner, on the basis of the above embodiment, after querying and determining the target proteins corresponding to the initial traditional Chinese medicine compound related information included in the request from the preset database, the method further includes:

[0170] Query the functional analysis data and signal pathway data corresponding to each target protein, and label the functional analysis data and signal pathway data for each target protein.

[0171] Among them, the functional analysis data may include the classification information of proteins in biological processes (BP), molecular functions (MF), and cellular components (CC), such as querying data by calling the interface of the Gene Ontology database (GO).

[0172] Among them, the signal pathway data may include the key signal pathways involved in diseases, potential regulatory pathways, etc., such as querying data by calling the corresponding interface of the Kyoto Encyclopedia of Genes and Genomes (KEGG).

[0173] Specifically, after querying and determining the target proteins corresponding to the traditional Chinese medicinal materials and diseases included in the request from the preset database, call the corresponding interface to query the functional analysis data and signal pathway data corresponding to each target protein, and label the queried data to the corresponding target proteins in sequence.

[0174] The recommended method for the traditional Chinese medicine compound provided by the embodiments of the present application, after querying and determining the target proteins corresponding to the initial traditional Chinese medicine compound related information included in the request from the preset database, the method further includes: querying the functional analysis data and signal pathway data corresponding to each target protein, and labeling the functional analysis data and signal pathway data to each target protein. By querying and labeling the functional analysis data and signal pathway data corresponding to each target protein, the molecular function of the target protein can be clarified, and the key pathways involved in the target can be clarified, so that users can more comprehensively understand the characteristics of the target protein and provide further data support for the traditional Chinese medicine compound.

[0175] As an optional implementation manner, on the basis of the above embodiments, in response to receiving a determination request, querying and determining the target proteins corresponding to the initial traditional Chinese medicine compound related information included in the request from the preset database includes:

[0176] In response to receiving a determination operation triggered by the user through the operation interface, display a disease name input component, a traditional Chinese medicine compound input component, and a symptom input component on the operation interface;

[0177] In response to receiving the disease name corresponding to the initial traditional Chinese medicine compound input by the user through the disease name input component, the names of each traditional Chinese medicinal material in the initial traditional Chinese medicine compound input through the traditional Chinese medicine compound input component, and the symptoms corresponding to the disease input through the symptom input component, display a confirmation component on the operation interface;

[0178] In response to receiving the determination request input by the user through the confirmation component, query and determine the target proteins corresponding to the initial traditional Chinese medicine compound related information included in the request from the preset database.

[0179] Among them, the determination operation may be that the user clicks on the traditional Chinese medicine compound recommendation icon or creates a new project, etc., and this embodiment does not limit this.

[0180] Specifically, when a traditional Chinese medicine compound recommendation is required, the user triggers a confirmation operation on the operation interface. The operation interface will display a disease name input component, a traditional Chinese medicine compound input component, and a symptom input component for the user to input the corresponding content. After receiving the content input by the user, a confirmation component is displayed on the operation interface. After the user clicks the confirmation component, a confirmation request can be triggered. At this time, the traditional Chinese medicine compound recommendation device queries the target proteins corresponding to the Chinese medicinal materials and diseases included in the confirmation request from the preset database.

[0181] The traditional Chinese medicine compound recommendation method provided by the embodiment of the present application, in response to receiving a confirmation request, queries the target proteins corresponding to the initial traditional Chinese medicine compound related information included in the confirmation request from the preset database, including: in response to receiving a confirmation operation triggered by the user through the operation interface, displaying a disease name input component, a traditional Chinese medicine compound input component, and a symptom input component on the operation interface; in response to receiving the disease name corresponding to the initial traditional Chinese medicine compound input by the user through the disease name input component, the names of each Chinese medicinal material in the initial traditional Chinese medicine compound input through the traditional Chinese medicine compound input component, and the symptoms corresponding to the disease input through the symptom input component, displaying a confirmation component on the operation interface; in response to receiving the confirmation request input by the user through the confirmation component, querying the target proteins corresponding to the initial traditional Chinese medicine compound related information included in the confirmation request from the preset database. Through the step-by-step guidance of the disease name input component, the traditional Chinese medicine compound input component, the symptom input component, and the confirmation component, the user can complete the submission of the confirmation request without understanding the underlying algorithm or code; the step-by-step process allows the user to check whether the input data or operation is correct at each step, reducing the probability of error propagation.

[0182] As an optional implementation manner, based on the first score and the second score, after determining the recommended traditional Chinese medicine compound, the method further includes:

[0183] Displaying the determination result through the operation interface, where the determination result includes the names of each Chinese medicinal material in the recommended traditional Chinese medicine compound, the total number of target proteins corresponding to the recommended traditional Chinese medicine compound, the number of directly acting proteins, the number of indirectly acting proteins, the number of uncovered proteins, the number of side effect proteins, and the recommended grades of each medicine pair.

[0184] Specifically, after the recommended traditional Chinese medicine (TCM) compound recommendation device determines the recommended TCM compound, it displays the determination result on the operation interface. The determination result may include the names of each Chinese medicinal material in the recommended TCM compound, the total number of target proteins corresponding to the recommended TCM compound, the number of directly acting proteins, the number of indirectly acting proteins, the number of uncovered proteins, the number of side effect proteins, and the recommended grades of each herb pair. After determining the recommended TCM compound based on the first score and the second score, the TCM compound recommendation method provided in the embodiments of the present application further includes: displaying the determination result through the operation interface, and the determination result includes the names of each Chinese medicinal material in the recommended TCM compound, the total number of target proteins corresponding to the recommended TCM compound, the number of directly acting proteins, the number of indirectly acting proteins, the number of uncovered proteins, the number of side effect proteins, and the recommended grades of each herb pair. Displaying the determination result through the operation interface can visually present the determination result, enabling the user to quickly understand the names of each Chinese medicinal material in the determined recommended TCM compound, the total number of target proteins corresponding to the recommended TCM compound, the number of directly acting proteins, the number of indirectly acting proteins, the number of uncovered proteins, the number of side effect proteins, and the recommended grades of each herb pair.

[0185] As an optional implementation manner, based on the above embodiment, after determining at least one candidate target protein, the method further includes:

[0186] Querying the matching relationship between each candidate target protein and known drugs;

[0187] The operation interface includes a determination process display component, and the method further includes:

[0188] In response to receiving a determination process information display request triggered by the user through the determination process display component, displaying the determination process information, where the determination process information includes at least one of the following:

[0189] Functional analysis data and signaling pathway data corresponding to each target protein, protein-protein interaction network topology maps, lists of directly acting proteins, lists of indirectly acting proteins, lists of uncovered proteins, lists of side effect proteins, and analysis results of each herb pair.

[0190] Among them, querying the matching relationship between each candidate target protein and known drugs may be by querying in public databases such as the DrugBank database, organic small molecule bioactivity data, target and bioactive drug database, binding database, etc., or by other means, and this embodiment does not limit this.

[0191] Specifically, after determining at least one candidate target protein, the matching relationship between each candidate target protein and known drugs can also be queried, that is, to determine whether the candidate target protein is already the target of some known drugs; the operation interface can also display a determination process display component. If the user needs to view the determination process information, a determination process information display request can be triggered by clicking on the determination process display component, so as to view the information related to the determination process.

[0192] Optionally, both the determination result and the determination process information can be exported, and the supported formats include CSV, Excel, PDF, etc.

[0193] The recommended method for traditional Chinese medicine compound provided by the embodiment of the present application, after determining at least one candidate target protein, the method further includes: querying the matching relationship between each candidate target protein and known drugs; the operation interface includes a determination process display component, and the method further includes: in response to receiving a determination process information display request triggered by the user through the determination process display component, displaying the determination process information, and the determination process information includes at least one of the following: functional analysis data and signal pathway data corresponding to each target protein, protein interaction network topology map, list of directly acting proteins, list of indirectly acting proteins, list of uncovered proteins, list of side effect proteins, and analysis results of each drug pair. By querying the matching relationship between each candidate target protein and known drugs, drugs or drug candidates that may act on these targets can be quickly located, which helps to more accurately design or optimize the drug molecular structure; through various chart forms, the key data and analysis results in the determination process are intuitively displayed, which not only increases the credibility of the determination result, but also enables the user to understand how the traditional Chinese medicine compound is recommended.

[0194] Figure 3 It is a flowchart of the recommended method for traditional Chinese medicine compound provided by another embodiment of the present application. As Figure 3 shown, the specific steps of the recommended method for traditional Chinese medicine compound provided by this embodiment including calculating the first score and the second score are as follows: The recommended method for traditional Chinese medicine compound provided by this embodiment includes the following steps:

[0195] Step 301, in response to receiving a determination request, query the target proteins corresponding to the Chinese medicinal materials and diseases included in the determination request from a preset database. The determination request includes the names of each Chinese medicinal material in the initial traditional Chinese medicine compound, the name of the disease corresponding to the initial traditional Chinese medicine compound, and the symptoms corresponding to the disease.

[0196] Step 302, obtain the interaction scores between each target protein.

[0197] Step 303, construct a protein interaction network topology map according to the interaction scores.

[0198] Step 304: Determine the directly acting proteins, indirectly acting proteins, and uncovered proteins based on the protein-protein interaction network topological map, and determine the side effect proteins among each target protein.

[0199] Step 305: Calculate the numerical values of various centrality indexes for each target protein based on the protein-protein interaction network topological map, and calculate the first score corresponding to each target protein by using the weighted summation method based on the numerical values of various centrality indexes of each target protein and the weights corresponding to the numerical values of various centrality indexes.

[0200] Step 306: Determine at least one candidate target protein according to the first score corresponding to each target protein.

[0201] Step 307: Obtain the traditional Chinese medicinal materials related to each candidate target protein.

[0202] Step 308: Determine the first attribute feature labels corresponding to each traditional Chinese medicinal material and the second attribute feature labels corresponding to the symptoms according to the preset mapping relationship.

[0203] Step 309: Calculate the similarity between the first attribute label corresponding to each traditional Chinese medicinal material and the second attribute label to obtain the second score corresponding to each traditional Chinese medicinal material.

[0204] Step 310: Calculate the third score corresponding to each traditional Chinese medicinal material by using the weighted summation method based on the first score, the second score corresponding to each traditional Chinese medicinal material, and the weights corresponding to the first score and the second score.

[0205] Step 311: Determine the recommended traditional Chinese medicine compound according to the third score.

[0206] Step 312: Arrange and combine each traditional Chinese medicinal material in the recommended traditional Chinese medicine compound to obtain multiple pairs of traditional Chinese medicinal materials.

[0207] Step 313: Determine the adjustment coefficient for each pair of traditional Chinese medicinal materials.

[0208] Step 314: Determine the recommended level for each pair of traditional Chinese medicinal materials based on the adjustment coefficient and the third score corresponding to each traditional Chinese medicinal material in each pair of traditional Chinese medicinal materials.

[0209] Step 315: Display the determination result through the operation interface. The determination result includes the names of each traditional Chinese medicinal material in the recommended traditional Chinese medicine compound, the total number of target proteins corresponding to the recommended traditional Chinese medicine compound, the number of directly acting proteins, the number of indirectly acting proteins, the number of uncovered proteins, the number of side effect proteins, and the recommended level for each pair of traditional Chinese medicinal materials.

[0210] In this embodiment, the implementation manners and technical effects of Steps 301 - 315 are similar to those of the corresponding solutions in the above embodiments, and will not be elaborated here.

[0211] Figure 4Schematic diagram of the display screen change of the recommended operation interface of the traditional Chinese medicine compound provided by an embodiment of the present application, as Figure 4 shown, when the user needs to recommend a traditional Chinese medicine compound, as shown in the first screen 401, a determination operation can be triggered by clicking on the traditional Chinese medicine compound recommendation icon on the operation interface; in response to receiving the determination operation triggered by the user through the operation interface, as shown in the second screen 402, a disease name input component, a traditional Chinese medicine compound input component, and a symptom input component are displayed on the operation interface; in response to receiving the disease name corresponding to the initial traditional Chinese medicine compound input by the user through the disease name input component, the names of each Chinese medicinal material in the initial traditional Chinese medicine compound input through the traditional Chinese medicine compound input component, and the symptoms corresponding to the disease input through the symptom input component, as shown in the third screen 403, a confirmation component is displayed on the operation interface; in response to receiving the determination request input by the user through the confirmation component, as shown in the fourth screen 404, a waiting determination identification message is displayed on the operation interface. At this time, the recommended device of the traditional Chinese medicine compound determines the recommended traditional Chinese medicine compound according to the recommended method of the traditional Chinese medicine compound provided by itself; in response to determining the traditional Chinese medicine compound, as shown in the fifth screen 405, a traditional Chinese medicine compound determination result component and a determination process display component are displayed on the operation interface, and the user can view specific matters by clicking on the corresponding components; in response to receiving the determination result viewing request triggered by the user through the traditional Chinese medicine compound determination result component, as shown in the sixth screen 406, the names of each Chinese medicinal material in the recommended traditional Chinese medicine compound, the recommended grades of each medicine pair, etc. are displayed on the operation interface; in response to receiving the determination process information display request triggered by the user through the determination process display component, as shown in the seventh screen 407, the determination process information, such as the protein-protein interaction network topological map, the list of directly acting proteins, etc., is displayed on the operation interface.

[0212] Figure 5 Schematic diagram of the structure of the recommended device of the traditional Chinese medicine compound provided by an embodiment of the present application, as Figure 5 shown, the recommended device of the traditional Chinese medicine compound provided by this embodiment is located in the recommended device of the traditional Chinese medicine compound. Then, the recommended device 50 of the traditional Chinese medicine compound provided by this embodiment includes: a query module 51, a calculation module 52, a determination module 53, and an acquisition module 54.

[0213] Among them, the query module 51, in response to receiving a determination request, queries the target proteins corresponding to each piece of information included in the determination request from a preset database. Each piece of information includes the names of each Chinese medicinal material in the initial Chinese medicinal compound, the name of the disease corresponding to the initial Chinese medicinal compound, and the symptoms corresponding to the disease. The calculation module 52 is used to calculate the first score corresponding to each target protein. The first score is the correlation score between the target protein and the corresponding information. The determination module 53 is used to determine at least one candidate target protein from each target protein. The acquisition module 54 is used to acquire the Chinese medicinal materials related to each candidate target protein. The determination module 54 is further used to determine the first attribute feature label corresponding to each Chinese medicinal material and the second attribute feature label corresponding to the symptom according to a preset mapping relationship. The calculation module 52 is further used to calculate the second score corresponding to each Chinese medicinal material based on the first attribute label and the second attribute label. The second score is the correlation score between the Chinese medicinal material and the symptoms corresponding to the disease. The determination module 53 is further used to determine the recommended Chinese medicinal compound based on the first score and the second score.

[0214] The recommended device for Chinese medicinal compounds provided in this embodiment can execute Figure 2 the method provided in the embodiment. The specific implementation principle and technical effect are similar, and will not be elaborated here.

[0215] Optionally, when calculating the first score corresponding to each target protein, the calculation module 52 is specifically used to: obtain the interaction scores between each target protein; construct a protein-protein interaction network topology map according to the interaction scores; calculate various centrality index values of each target protein based on the protein-protein interaction network topology map, and based on the various centrality index values of each target protein and the weights corresponding to the various centrality index values, calculate the first score corresponding to each target protein by means of weighted summation. When determining at least one candidate target protein from each target protein, the determination module 53 is specifically used to: determine at least one candidate target protein according to the first score corresponding to each target protein.

[0216] Optionally, when calculating the second score corresponding to each Chinese medicinal material based on the first attribute label and the second attribute label, the calculation module 52 is specifically used to: calculate the similarity between the first attribute label and the second attribute label corresponding to each Chinese medicinal material to obtain the second score corresponding to each Chinese medicinal material.

[0217] Optionally, when determining the recommended Chinese medicinal compound based on the first score and the second score, the determination module 53 is specifically used to: calculate the third score corresponding to each Chinese medicinal material by means of weighted summation based on the first score, the second score corresponding to each Chinese medicinal material, and the weights corresponding to the first score and the second score; determine the recommended Chinese medicinal compound according to the third score.

[0218] Optionally, the recommended device for Chinese medicinal compounds provided in this embodiment further includes a combination module.

[0219] Correspondingly, a combination module is used to permute and combine each Chinese medicinal material in the recommended traditional Chinese medicine compound to obtain multiple pairs of medicinal materials; the determination module 53 is further used to determine the adjustment coefficient of each pair of medicinal materials; and based on the adjustment coefficient and the third score corresponding to each Chinese medicinal material in each pair of medicinal materials, determine the recommendation level of each pair of medicinal materials.

[0220] Optionally, when determining the adjustment coefficient of each pair of medicinal materials, the determination module 53 is specifically used for: determining whether the pair of medicinal materials is a classical pair of medicinal materials, if so, determining that the adjustment coefficient is to increase the third score by a first preset adjustment coefficient, if not, determining that the adjustment coefficient is 0; and / or, determining whether the medicinal property compatibility of each Chinese medicinal material in the pair of medicinal materials is opposite, if so, determining that the adjustment coefficient is to decrease the third score by a second preset adjustment coefficient, if not, determining that the adjustment coefficient is 0; and / or, determining whether there is a toxic Chinese medicinal material in the pair of medicinal materials, if so, determining that the adjustment coefficient is to decrease the third score by a third preset adjustment coefficient, if not, determining that the adjustment coefficient is 0.

[0221] Optionally, the recommended device for traditional Chinese medicine compound provided in this embodiment further includes an output module.

[0222] Correspondingly, the determination module 53 is further used to determine the directly acting proteins, indirectly acting proteins and uncovered proteins based on the protein-protein interaction network topology map; determine the side effect proteins among each target protein; the output module is used to output a list including the directly acting proteins, indirectly acting proteins, uncovered proteins and side effect proteins.

[0223] Optionally, the recommended device for traditional Chinese medicine compound provided in this embodiment further includes a labeling module.

[0224] Correspondingly, the query module 51 is further used to query the functional analysis data and signal pathway data corresponding to each target protein; the labeling module is used to label the functional analysis data and signal pathway data for each target protein.

[0225] Optionally, when the query module 51 queries the corresponding target protein from the preset database in response to receiving a determination request, it is specifically used for: in response to receiving a determination operation triggered by the user through the operation interface, displaying a disease name input component, a traditional Chinese medicine compound input component and a symptom input component on the operation interface; in response to receiving the disease name corresponding to the initial traditional Chinese medicine compound input by the user through the disease name input component, the names of each Chinese medicinal material in the initial traditional Chinese medicine compound input through the traditional Chinese medicine compound input component, and the symptoms corresponding to the disease input through the symptom input component, displaying a confirmation component on the operation interface; in response to receiving the determination request input by the user through the confirmation component, querying the corresponding target protein from the preset database according to the determination request.

[0226] Optionally, the recommended device for traditional Chinese medicine compound provided in this embodiment further includes a display module.

[0227] Correspondingly, a display module is configured to display the determination result through an operation interface. The determination result includes the names of each Chinese medicinal material in the recommended Chinese medicinal compound, the total number of target proteins corresponding to the recommended Chinese medicinal compound, the number of directly acting proteins, the number of indirectly acting proteins, the number of uncovered proteins, and the number of side-effect proteins.

[0228] Optionally, a query module is further configured to query the matching relationship between each candidate target protein and known drugs; the operation interface includes a determination process display component, and the display module is further configured to display determination process information in response to receiving a determination process information display request triggered by the user through the determination process display component. The determination process information includes at least one of the following: functional analysis data and signal pathway data corresponding to each target protein, a protein interaction network topology map, a list of directly acting proteins, a list of indirectly acting proteins, a list of uncovered proteins, and a list of side-effect proteins.

[0229] Figure 6 The following is a schematic structural diagram of a recommended device for a Chinese medicinal compound provided in an embodiment of the present application. As Figure 6 shown, the recommended device 60 for a Chinese medicinal compound provided in this embodiment includes: a processor 61 and a memory 62 communicatively connected to the processor.

[0230] Among them, the memory 62 is used to store computer execution instructions; the processor 61 executes the computer execution instructions stored in the memory 62 to implement the recommended method for a Chinese medicinal compound provided in the above embodiment. For relevant descriptions, reference can be made to the relevant descriptions and effects corresponding to the steps in the accompanying drawings, and details are not elaborated here.

[0231] Among them, the program may include program codes, and the program codes include computer execution instructions. The memory 62 may include a high-speed RAM memory, and may also include non-volatile memory, such as at least one disk memory.

[0232] In this embodiment, the processor 61 and the memory 62 are connected through a bus. The bus may be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, or an Extended Industry Standard Architecture (EISA) bus, etc. The bus can be divided into an address bus, a data bus, a control bus, etc. For the sake of simplicity of representation, Figure 6 only a thick line is used to represent it in the figure, but it does not mean that there is only one bus or one type of bus.

[0233] The embodiments of the present application further provide a computer-readable storage medium, in which computer-executable instructions are stored. When the controller executes the computer-executable instructions, each step in the method in the above embodiments is implemented.

[0234] The embodiments of the present application further provide a computer program product, including a computer program, which implements each step in the method in the above embodiments when executed by the controller.

[0235] The various embodiments described above in the present application can be implemented in digital electronic circuit systems, integrated circuit systems, field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), systems on chip (SOCs), complex programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments can include: being implemented in one or more computer programs, which can be executed and / or interpreted on a programmable system including at least one programmable processor. The programmable processor can be a dedicated or general-purpose programmable processor, and can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit the data and instructions to the storage system, the at least one input device, and the at least one output device.

[0236] The computer-executable instructions for implementing the method of the present application can be written in any combination of one or more programming languages. These computer-executable instructions can be provided to a processor or controller of a general-purpose computer, a dedicated computer, or other programmable data processing devices, such that when the computer-executable instructions are executed by the processor or controller, the functions / operations specified in the flowchart and / or block diagram are implemented. The computer-executable instructions can be executed entirely on the machine, partially on the machine, executed partially on the machine as an independent software package and partially on a remote machine, or executed entirely on a remote machine or an electronic device.

[0237] In the context of the present application, a computer-readable storage medium may be a tangible medium that can contain or store a program for use by or in connection with an instruction execution system, apparatus, or device. A computer-readable storage medium may be a machine-readable signal medium or a machine-readable storage medium. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing. More specific examples of a computer-readable storage medium include electrical connections based on one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. Alternatively, a computer-readable storage medium may include: resistive random access memory (RRAM), dynamic random access memory (DRAM), static random access memory (SRAM), enhanced dynamic random access memory (EDRAM), high-bandwidth memory (HBM), hybrid memory cube (HMC), and so on.

[0238] The systems and techniques described herein can be implemented in a computing system that includes backend components (e.g., as a data electronic device), or a computing system that includes middleware components (e.g., an application electronic device), or a computing system that includes frontend components (e.g., a user computer having a graphical user interface or a web browser through which a user can interact with an implementation of the systems and techniques described herein), or a computing system that includes any combination of such backend components, middleware components, or frontend components. The components of the system can be interconnected to each other by digital data communication in any form or medium (e.g., a communication network). Examples of a communication network include: a local area network (LAN), a wide area network (WAN), and the Internet.

[0239] It should be noted that, for the foregoing method embodiments, for the sake of simple description, they are all expressed as a series of action combinations. However, those skilled in the art should know that this application is not limited by the described action sequence, because according to this application, certain steps can be carried out in other sequences or simultaneously. Secondly, those skilled in the art should also know that the embodiments described in the specification are all optional embodiments, and the actions and modules involved are not necessarily essential to this application. In other words, the various forms of processes shown above can be used, with steps reordered, added or deleted. For example, the steps described in the disclosure of this application can be executed in parallel, sequentially or in different orders, as long as the desired results of the technical solutions disclosed in this application can be achieved, and this is not limited herein.

[0240] It is further noted that although the steps in the flowchart are shown sequentially in the direction of the arrows, these steps are not necessarily executed sequentially in the direction of the arrows. Unless there is a clear indication in this article, the execution of these steps has no strict order restriction, and these steps can be executed in other orders. Moreover, at least some of the steps in the flowchart may include multiple sub-steps or multiple stages. These sub-steps or stages are not necessarily executed at the same moment, but can be executed at different moments, and the execution order of these sub-steps or stages is not necessarily sequential, but can be executed alternately or in turn with at least a part of other steps or sub-steps or stages of other steps.

[0241] It should be understood that the above device embodiments are merely illustrative, and the devices of this application can also be implemented in other ways. For example, the division of units / modules in the above embodiments is only a logical function division, and there can be other division methods in actual implementation. For example, multiple units, modules or components can be combined, or can be integrated into another system, or some features can be ignored or not executed. [[ID=IO]]

[0242] In addition, unless otherwise specified, in each embodiment of this application, each functional unit / module can be integrated in one unit / module, or each unit / module can exist physically alone, or two or more units / modules can be integrated together. The above integrated unit / module can be implemented in the form of hardware or in the form of a software program module.

[0243] When the integrated unit / module is implemented in the form of hardware, the hardware can be a digital circuit, an analog circuit, etc. The physical implementation of the hardware structure includes but is not limited to transistors, memristors, etc.

[0244] When an integrated unit / module is implemented in the form of a software program module and sold or used as an independent product, it can be stored in a computer-readable memory. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the related technology, or all or part of this technical solution, can be embodied in the form of a software product. This computer software product is stored in a memory and includes several instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods of various embodiments of this application. And the aforementioned memory includes: various media such as USB flash drives, read-only memory ROM, random access memory RAM, mobile hard disks, magnetic disks, or optical discs that can store computer-executable instructions.

[0245] In the above embodiments, the descriptions of each embodiment have their own focuses. For the parts not detailed in a certain embodiment, reference can be made to the relevant descriptions of other embodiments. The technical features of the above embodiments can be combined arbitrarily. For the sake of brevity of description, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, it should be considered as within the scope described in this specification.

[0246] Those skilled in the art will easily think of other implementation schemes of this application after considering the specification and practicing the invention disclosed herein. This application aims to cover any variations, uses, or adaptive changes of this application, which follow the general principles of this application and include the common knowledge or conventional technical means in this technical field not disclosed in this application. The specification and embodiments are only regarded as exemplary.

[0247] It should be understood that this application is not limited to the exact structure already described and shown in the drawings, and various modifications and changes can be made without departing from its scope. Therefore, the above specific implementation manners do not constitute a limitation to the protection scope of this application. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the principles of this application shall be included within the protection scope of this application.

Claims

1. A method for recommending a Chinese herbal compound, characterized in that: The method comprises: In response to receiving a determination request, querying a preset database for a target protein corresponding to information related to an initial Chinese herbal compound included in the determination request, wherein the determination request includes the names of each Chinese medicinal material in the initial Chinese herbal compound, the name of the disease corresponding to the initial Chinese herbal compound, and the symptoms corresponding to the disease; Calculating a first score corresponding to each of the target proteins and determining at least one candidate target protein from each of the target proteins; the first score is a correlation score between the target protein and the corresponding information; Obtaining Chinese medicinal materials related to each of the candidate target proteins; Determine the first attribute feature label corresponding to each of the Chinese medicinal materials and the second attribute feature label corresponding to the symptoms according to a preset mapping relationship; Calculating a second score corresponding to each of the Chinese medicinal materials based on the first attribute label and the second attribute label; the second score is a correlation score between the Chinese medicinal material and the symptoms corresponding to the disease; A recommended Chinese herbal compound is determined based on the first score and the second score.

2. The method according to claim 1, characterized in that Calculating the first score corresponding to each target protein and determining at least one candidate target protein from each target protein includes: Obtaining the interaction scores between the target proteins; constructing a protein interaction network topology map according to the interaction score; Calculating multiple centrality index values of each target protein based on the protein interaction network topology map, and calculating a first score corresponding to each target protein by weighted summation based on the multiple centrality index values of each target protein and the weights corresponding to the multiple centrality index values; At least one candidate target protein is determined according to the first score corresponding to each target protein.

3. The method according to claim 1, characterized in that The calculating the second score corresponding to each of the Chinese medicinal materials based on the first attribute label and the second attribute label includes: The similarity between the first attribute label and the second attribute label corresponding to each of the Chinese medicinal materials is calculated to obtain a second score corresponding to each of the Chinese medicinal materials.

4. The method according to claim 1, wherein Determining the recommended Chinese herbal compound based on the first score and the second score includes: Calculating a third score corresponding to each Chinese medicinal material using a weighted summation method based on the first score and the second score corresponding to each Chinese medicinal material and the weights corresponding to the first score and the second score; A recommended Chinese herbal compound is determined based on the third score.

5. The method according to claim 4, characterized in that After determining the recommended Chinese herbal compound based on the first score and the second score, the method further includes: Arrange and combine the Chinese medicinal materials in the recommended Chinese medicinal compound to obtain multiple drug pairs; determining an adjustment coefficient for each of the drug pairs; The recommendation level of each of the drug pairs is determined based on the adjustment coefficient and the third score corresponding to each Chinese medicinal material in each of the drug pairs.

6. The method according to claim 5, characterized in that Determining the adjustment coefficient of each drug pair includes: determining whether the drug pair is a classic drug pair, and if so, determining an adjustment coefficient to increase the third score by a first preset adjustment coefficient; if not, determining the adjustment coefficient to be 0; and / or determining whether the medicinal properties of the Chinese medicinal materials in the medicine pair are opposite; if so, determining an adjustment coefficient to reduce the third score by a second preset adjustment coefficient; if not, determining the adjustment coefficient to be 0; And / or, determining whether there is a toxic Chinese medicinal material in the drug pair; if so, determining an adjustment coefficient to reduce the third score by a third preset adjustment coefficient; if not, determining the adjustment coefficient to be 0.

7. The method according to claim 2, characterized in that After constructing the protein interaction network topology map according to the interaction score, the method further comprises: Determine directly acting proteins, indirectly acting proteins and uncovered proteins based on the protein interaction network topology map; Identifying the side effect proteins in each of the target proteins; The output includes a list of directly acting proteins, indirectly acting proteins, uncovered proteins, and side-effecting proteins.

8. The method according to claim 1, characterized in that After querying the preset database for the target protein corresponding to the initial Chinese medicine compound related information included in the determination request, the method further includes: The functional analysis data and signal pathway data corresponding to each of the target proteins are queried, and the functional analysis data and signal pathway data are annotated for each of the target proteins.

9. The method according to claim 1, characterized in that In response to receiving the determination request, querying a preset database for a target protein corresponding to the initial Chinese herbal compound related information included in the determination request includes: In response to receiving a confirmation operation triggered by the user through the operation interface, displaying a disease name input component, a Chinese herbal compound prescription input component, and a symptom input component on the operation interface; In response to receiving the disease name corresponding to the initial Chinese herbal medicine compound input by the user through the disease name input component, the names of the Chinese medicinal materials in the initial Chinese herbal medicine compound input through the Chinese herbal medicine compound input component, and the symptoms corresponding to the disease input through the symptom input component, displaying a confirmation component on the operation interface; In response to receiving a confirmation request input by the user through the confirmation component, a target protein corresponding to the initial Chinese herbal compound related information included in the confirmation request is queried from a preset database.

10. The method according to claim 9, characterized in that After determining the recommended Chinese herbal compound based on the first score and the second score, the method further includes: The determination results are displayed through the operation interface, and the determination results include the names of each Chinese medicinal material in the recommended Chinese medicine compound, the total number of target proteins corresponding to the recommended Chinese medicine compound, the number of directly acting proteins, the number of indirect acting proteins, the number of uncovered proteins, the number of side effect proteins, and the recommendation level of each drug pair.

11. The method according to claim 9, characterized in that After determining at least one candidate target protein, the method further comprises: Querying the matching relationship between each candidate target protein and known drugs; The operation interface includes a determination process display component, and the method further includes: In response to receiving a determination process information display request triggered by a user through the determination process display component, determination process information is displayed, where the determination process information includes at least one of the following: Functional analysis data and signal pathway data corresponding to each target protein, protein interaction network topology map, direct-acting protein list, indirect-acting protein list, uncovered protein list, side effect protein list, and analysis results of each drug pair.

12. A device for recommending a Chinese herbal compound, characterized in that: The device comprises: a query module, in response to receiving a determination request, querying a preset database for a target protein corresponding to information related to an initial Chinese herbal compound included in the determination request, wherein the determination request includes the names of the Chinese medicinal materials in the initial Chinese herbal compound, the name of the disease corresponding to the initial Chinese herbal compound, and the symptoms corresponding to the disease; a calculation module, configured to calculate a first score corresponding to each of the target proteins, where the first score is a correlation score between the target protein and the corresponding information; A determination module, configured to determine at least one candidate target protein from each of the target proteins; An acquisition module, used to acquire Chinese medicinal materials related to each candidate target protein; The determining module is further configured to determine the first attribute feature label corresponding to each of the Chinese medicinal materials and the second attribute feature label corresponding to the symptoms according to a preset mapping relationship; The calculation module is further configured to calculate a second score corresponding to each of the Chinese medicinal materials based on the first attribute label and the second attribute label; the second score is a correlation score between the Chinese medicinal material and the symptoms corresponding to the disease; The determination module is further configured to determine a recommended Chinese herbal compound based on the first score and the second score.

13. A device for recommending a Chinese herbal compound, characterized in that: The device includes: a processor, and a memory communicatively connected to the processor; The memory is used to store computer-executable instructions; The processor is configured to execute the computer-executable instructions stored in the memory to implement the method according to any one of claims 1 to 11.

14. A computer-readable storage medium, characterized in that The computer-readable storage medium stores computer-executable instructions, which are used to implement the method according to any one of claims 1 to 11 when executed by a processor.

15. A computer program product, comprising a computer program, wherein when the computer program is executed by a processor, the method according to any one of claims 1 to 11 is implemented.

Images