Recommended methods, devices, equipment, media and products for Chinese herbal compound prescriptions

Abstract

The present application provides a method, device, equipment, medium and product for recommending a Chinese herbal compound, which relates to the field of biomedicine. It includes: in response to receiving a determination request, querying the target protein corresponding to the initial Chinese herbal compound related information included in the determination request from a preset database; calculating the first score corresponding to each target protein and determining at least one candidate target protein from each target protein; obtaining Chinese medicinal materials related to each candidate target protein; determining 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; calculating the second score corresponding to each Chinese medicinal material based on the first attribute label and the second attribute label; and determining the recommended Chinese herbal compound based on the first score and the second score. The present application determines the correlation between Chinese medicinal materials and diseases by associating target proteins, and then determines the correlation between Chinese medicinal materials and symptoms by associating attribute feature labels, so that the recommended Chinese herbal compound has a higher matching degree with the disease.

Description

Technical Field

[0001] The present application relates to the field of biomedical technology, and in particular to a method, device, equipment, medium and product for recommending a traditional Chinese medicine compound. Background Art

[0002] Traditional Chinese medicine (TCM) compound prescriptions are an important tool for treating diseases. The rationality of their composition is directly related to the therapeutic effect. TCM emphasizes syndrome differentiation and treatment. This involves determining the cause, pathogenesis, and location of the disease based on comprehensive information such as the patient's symptoms, physical signs, pulse, and tongue, and then formulating a corresponding TCM compound for treatment. Due to the complexity and variability of diseases, the compatibility of TCM compounds determined simply based on symptoms is gradually decreasing.

[0003] To improve the compatibility of traditional Chinese medicine compounds with diseases, relevant programs analyze the material basis of the efficacy of traditional Chinese medicine compounds through high-throughput screening, molecular biology and network pharmacology. For example, clinical phenotypes are used as screening indicators for efficacy models, combined with chemometric methods to optimize traditional Chinese medicine compounds, and network pharmacology technology is used to predict the relationship between active ingredients and targets. This improves the matching degree between traditional Chinese medicine compounds and diseases and provides a scientific basis for clinical application.

[0004] However, the composition of Chinese herbal compound is complex and its properties are diverse. If only the relationship between the active ingredients of Chinese medicinal materials and the target protein is considered, it is easy to cause the problem of low compatibility between the determined Chinese herbal compound and the disease. Summary of the Invention

[0005] The present application provides a method, device, equipment, medium and product for recommending a Chinese herbal compound, which is used to solve the technical problem of low compatibility between Chinese herbal compound and disease.

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

[0007] 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;

[0008] 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;

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

[0010] 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;

[0011] 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;

[0012] A recommended Chinese herbal compound is determined based on the first score and the second score.

[0013] In one possible design, 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] Obtaining the interaction scores between the target proteins;

[0015] constructing a protein interaction network topology map according to the interaction score;

[0016] 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;

[0017] At least one candidate target protein is determined according to the first score corresponding to each target protein.

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

[0019] 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.

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

[0021] 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;

[0022] A recommended Chinese herbal compound is determined based on the third score.

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

[0024] Arrange and combine the Chinese medicinal materials in the recommended Chinese medicinal compound to obtain multiple drug pairs;

[0025] determining an adjustment coefficient for each of the drug pairs;

[0026] 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.

[0027] In one possible design, determining the adjustment coefficient of each drug pair includes:

[0028] 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;

[0029] and / or determining whether the medicinal properties of the Chinese medicinal materials in the drug 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;

[0030] 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.

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

[0032] Determine directly acting proteins, indirectly acting proteins and uncovered proteins based on the protein interaction network topology map;

[0033] Identifying the side effect proteins in each of the target proteins;

[0034] The output includes a list of directly acting proteins, indirectly acting proteins, uncovered proteins, and side-effecting proteins.

[0035] In a possible design, 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:

[0036] 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.

[0037] In one possible design, 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:

[0038] 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;

[0039] 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;

[0040] 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.

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

[0042] 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.

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

[0044] Querying 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 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:

[0047] 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.

[0048] In a second aspect, the present application provides a device for recommending a Chinese herbal compound, the device comprising:

[0049] 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;

[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, used to acquire Chinese medicinal materials related to each candidate target protein;

[0053] 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;

[0054] 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;

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

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

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

[0058] The processor is used to execute the computer-executable instructions stored in the memory to implement the method as described in any one of the first aspects.

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

[0060] In a fifth aspect, the present application provides a computer program product, comprising a computer program, which, when executed by a processor, implements the method as described in any one of the first aspects.

[0061] The method, apparatus, device, medium and product for recommending a Chinese herbal compound provided in the present application, in response to receiving a determination request, querying a preset database for a target protein corresponding to the initial Chinese herbal compound related information included in the determination request, wherein the determination request includes the name of each Chinese herbal medicine 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 herbal medicines related to each of the candidate target proteins; determining a first attribute feature label corresponding to each of the Chinese herbal medicines and a second attribute feature label corresponding to the symptoms according to a preset mapping relationship; calculating a second score corresponding to each of the Chinese herbal medicines based on the first attribute label and the second attribute label; the second score is a correlation score between the Chinese herbal medicine and the symptoms corresponding to the disease; and determining a recommended Chinese herbal compound based on the first score and the second score. By querying the target proteins corresponding to each Chinese medicinal material and disease name in the initial Chinese medicine compound through the preset database and calculating its first score, the direct interaction relationship between the Chinese medicinal materials and the disease target protein can be clarified; traditional Chinese medicine compounds are mostly based on experience-based combinations, and there may be problems of "ineffective ingredients" or "unclear targets". Through the first score screening, target proteins with weak correlation with disease target proteins can be eliminated, and the focus can be placed on truly effective ingredients; the first attribute feature labels of Chinese medicinal materials (such as "heat" and "cold") and the second attribute feature labels of symptoms (such as "qi deficiency" and "blood deficiency") are determined through the preset mapping relationship. The first score verifies the association between the Chinese herbal medicine and the disease target protein, and the second score verifies the match between the Chinese herbal medicine and the symptoms, forming a double verification of "target mechanism + symptom relief". The recommended Chinese herbal medicine compound is determined based on the first and second scores, avoiding the one-sidedness caused by relying solely on the target or symptom score, thereby improving the adaptability of the Chinese herbal medicine compound to the disease. BRIEF DESCRIPTION OF THE DRAWINGS

[0062] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and, together with the description, serve to explain the principles of the present application.

[0063] Figure 1 This is a diagram of an application scenario of a method for recommending a Chinese herbal compound according to an embodiment of the present application;

[0064] Figure 2 A flowchart of a method for recommending a Chinese herbal compound according to an embodiment of the present 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] Traditional Chinese medicine (TCM) compound prescriptions are a core tool for treating diseases. The rationality of their formulation directly determines the effectiveness of their clinical efficacy. Traditional Chinese medicine emphasizes the core concept of "differentiation and treatment based on syndrome differentiation." This involves comprehensively collecting information on a patient's symptoms, physical signs, pulse, and tongue through the Four Diagnostics (inspection, auscultation, inquiry, and palpation). This information is then analyzed using TCM theory to analyze the etiology, pathogenesis, and location of the disease, ultimately leading to a personalized TCM compound treatment plan. However, with the increasing complexity of modern disease spectrums (e.g., chronic diseases and multi-system comorbidities) and the significant increase in individual patient variability, formulating formulas solely based on traditional experience or single symptoms has gradually exposed its limitations. This has led to a decrease in the suitability of TCM compound prescriptions for specific diseases and increased variability in clinical efficacy. To overcome this bottleneck, modern research is leveraging multidisciplinary approaches to deeply analyze the pharmacological basis and mechanisms of action of TCM compound prescriptions, significantly improving the scientific and precise nature of formula formulations. For example, high-throughput screening technology combined with clinical phenotypic models can quickly identify clusters of active ingredients in traditional Chinese medicine compounds that exert key pharmacological effects and use them as screening indicators to optimize compound composition. Chemometric methods (such as principal component analysis and cluster analysis) quantitatively analyze the correlation between the chemical composition and pharmacodynamics of traditional Chinese medicines, eliminate redundant components, and streamline compound structures. Machine learning models based on clinical big data can integrate multi-dimensional patient information (such as genomic and metabolomics data) to achieve dynamic optimization of compound compatibility, making it more tailored to individualized treatment needs. However, the complexity of traditional Chinese medicine compounds goes far beyond the relationship between ingredients and targets. The properties and characteristics of traditional Chinese medicines have diverse dimensions. Therefore, focusing solely on the ingredient-target relationship may fall into the dilemma of "mechanistic effectiveness but clinical ineffectiveness", resulting in low compatibility between traditional Chinese medicine compounds and diseases.

[0074] Therefore, when facing technical problems in the existing technology, in order to establish the association between Chinese medicinal materials and diseases, the target proteins corresponding to each Chinese medicinal material and disease name in the initial compound are queried from the preset database, and then the first score of the target protein and the corresponding information (Chinese medicinal material, disease) is calculated to screen out candidate target proteins that are highly correlated with the core pathological mechanism of the disease, thereby ensuring the effectiveness of the molecular mechanism of the Chinese medicinal compound; in order to bidirectionally verify the correlation between the candidate target protein and the Chinese medicinal material, the Chinese medicinal materials related to each candidate target protein are obtained, and at the same time, the Chinese medicinal materials related to the candidate target protein can be more comprehensively selected, without being restricted to the Chinese medicinal materials in the initial Chinese medicinal compound, thereby improving the accuracy of the Chinese medicinal compound; because the property characteristics of Chinese medicinal materials have diversified dimensions, including four qi and five flavors (cold, hot, warm, cool, pungent, sweet, sour, bitter, and salty), Meridians (such as the effects on internal organs, etc.), efficacy (such as clearing heat, activating blood circulation, and nourishing), etc., these attributes need to be highly consistent with the symptom attributes of the disease (such as cold and heat, deficiency and excess, exterior and interior, urgency, etc.). Therefore, the first attribute feature label corresponding to each Chinese medicinal material and the second attribute feature label corresponding to the symptom are determined according to the preset mapping relationship, and then the second score corresponding to each Chinese medicinal material is calculated based on the first attribute label and the second attribute label, and the matching degree between the attribute characteristics of the Chinese medicinal material and the symptoms is quantified, and the Chinese medicinal materials that are highly matched with the symptoms are screened out to ensure the effectiveness of the compound in relieving symptoms; finally, the molecular mechanism and symptom adaptability are combined to optimize the composition of the compound, and the recommended Chinese medicine compound is determined based on the first score and the second score to avoid the one-sidedness of relying solely on the molecular mechanism or symptom adaptability, and to improve the overall adaptability of the Chinese medicine compound to the disease.

[0075] Figure 1 This is an application scenario diagram of the method for recommending a Chinese medicine compound provided in one embodiment of the present application, such as Figure 1 As shown, the application scenario diagram of the method for recommending a traditional Chinese medicine compound provided in 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, where the determination request includes the name 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. After receiving the determination request, the server 102 queries the server database 103 for the target protein corresponding to the relevant information of the initial Chinese medicinal compound included in the determination request. The server 102 calculates a first score corresponding to each target protein and determines at least one candidate target protein from each target protein. The first score is a correlation score between the target protein and the corresponding information. The server 102 then obtains Chinese medicinal materials related to each candidate target protein from the server database 103, determines a first attribute feature label corresponding to each Chinese medicinal material and a second attribute feature label corresponding to the symptom according to a preset mapping relationship, and then calculates a second score corresponding to each Chinese medicinal material 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. Finally, the server 102 determines a recommended Chinese medicinal compound based on the first score and the second score. The server 102 sends the recommended Chinese medicinal compound to the terminal device 101 so that the user can view it.

[0077] Optionally, the server may establish a communication connection with an external database by calling an interface or the like to obtain Chinese medicinal materials related to each candidate target protein, which is not limited in this embodiment.

[0078] The following specific embodiments describe in detail the technical solution of the present application and how the technical solution of the present application solves the above-mentioned technical problems. The following specific embodiments 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 This is a flow chart of a method for recommending a Chinese herbal compound according to an embodiment of the present application, as shown in FIG. Figure 2 As shown, the execution subject of this embodiment is a device for recommending a Chinese herbal compound. The device can be implemented by a computer program, or by a medium storing a relevant computer program, such as a USB flash drive and / or a CD, or can be integrated into a device for recommending a Chinese herbal compound, such as a server. The method for recommending a Chinese herbal compound provided in this embodiment includes the following steps:

[0080] Step 201, in response to receiving a determination request, querying a preset database for a target protein corresponding to the initial Chinese medicine compound related information included in the determination request, wherein 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 pre-configured in the recommendation device of the Chinese medicine compound, including the Chinese medicine small molecule database (such as PubChem, SymMap), disease gene library (such as OMIM, DisGeNET), etc., which is used to query the target proteins corresponding to Chinese medicinal materials and diseases.

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

[0083] Specifically, the user can send the names of the Chinese medicinal materials 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 to the Chinese medicinal compound recommendation device through the terminal device to initiate a confirmation request. After receiving the confirmation request, the Chinese medicinal compound recommendation device queries the active ingredients corresponding to the Chinese medicinal materials in the preset database according to the names of the various medicinal materials in the initial Chinese medicinal compound, and then queries the corresponding target proteins based on the active ingredients, and then queries the target proteins corresponding to the diseases included in the confirmation request from the preset database.

[0084] It is understandable that a Chinese medicinal material may correspond to multiple target proteins; a disease may also correspond to multiple target proteins.

[0085] Optionally, the device for recommending Chinese herbal compound prescriptions can also perform keyword retrieval based on the disease symptoms in the determination request to obtain diseases related to the symptoms, and query the target proteins corresponding to the symptom-related diseases from a preset database, and perform subsequent steps on them as well. This embodiment does not limit this.

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

[0087] Specifically, after the target protein is queried, various data or features related to the target protein are obtained, such as expression data, protein interaction data, etc. The recommendation device of the traditional Chinese medicine compound preprocesses the obtained data to ensure the accuracy and consistency of the data, and selects appropriate correlation analysis methods, such as correlation analysis, regression analysis, network analysis, etc., to perform correlation analysis on each target protein and its corresponding information, and calculate the correlation index between the target protein and the corresponding information. The scoring method can adopt weighted summation, machine learning model prediction and other methods. After calculating the first score of each target protein, all target proteins are ranked according to the first score, and target proteins with higher scores are selected as candidate target proteins.

[0088] The method for obtaining various data or features related to the target protein may be calling an interface, querying a database, etc., which is not limited in this embodiment.

[0089] For example, the API interface of the protein interaction database is called, and a query request containing a list of target proteins is sent to it, and key parameters are set: limiting the species to humans (species number 9606), the interaction confidence threshold (default ≥0.4), and specifying 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 two target protein names, a comprehensive score, and a sub-item evidence score (such as the number of experimental support, 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 conditions. For example, the top N target proteins with the highest scores can be selected as candidate target proteins, or a scoring threshold can be set. This embodiment does not limit this.

[0091] Step 203: Acquire Chinese medicinal materials related to each candidate target protein.

[0092] It is understandable that a target protein may be associated with multiple Chinese medicinal materials, that is, the target protein corresponding to the Chinese medicinal materials in the initial Chinese medicinal compound may also be associated with other Chinese medicinal materials.

[0093] Specifically, after determining at least one target protein, Chinese medicinal materials related to each candidate target protein are obtained, such as by calling a database to query and receiving the query results, thereby obtaining other Chinese medicinal materials related to the candidate target protein, avoiding being restricted to the Chinese medicinal materials in the initial Chinese medicine compound, and further improving the reliability of the final recommended Chinese medicine compound.

[0094] Step 204 : determining 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.

[0095] Among them, the first attribute characteristic label refers to the attribute characteristic label corresponding to the Chinese medicinal materials, such as bitter, cold, pungent, sweet, and meridians such as spleen and lung.

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

[0097] Among them, the preset mapping relationship refers to the association relationship between each Chinese medicinal material and its related attribute feature labels such as medicinal properties, as well as the association relationship between each symptom and the attribute feature labels of the Chinese medicinal materials used to treat the symptom, which are pre-configured in the recommendation device of the Chinese herbal compound.

[0098] For example, the first attribute feature label corresponding to the Chinese medicinal material Scutellaria baicalensis is: bitter, cold, lung, gallbladder, heat-clearing, and dampness-drying; the second attribute feature label corresponding to the symptom of Qi deficiency is: warm, sweet, spleen, and lung.

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

[0100] Optionally, a semantic model may be pre-configured in the Chinese herbal compound recommendation device to determine the second attribute feature label corresponding to the symptom by matching the symptom description in the determination request with the symptom description in the preset mapping relationship.

[0101] It is understandable that a large amount of information is pre-queried and integrated, including the "Classification and Determination Standards of Chinese Residents' Constitution in Traditional Chinese Medicine", the Chinese Medicine Prescription and Syndrome Database, the "Chinese Traditional Medicine Body Mass Chart", the "Dictionary of Chinese Materia Medica", "Chinese Medicine Prescriptions", "Chinese Internal Medicine", etc., from which the attribute feature labels of Chinese medicinal materials and symptoms are extracted, such as the four properties: cold, hot, warm, cool, and neutral, the five flavors: pungent, sweet, sour, bitter, and salty, rising and falling: rising, falling, floating, and sinking, meridians: heart, liver, spleen, lung, kidney, stomach, large intestine, small intestine, gallbladder, etc., and therapeutic effects: tonifying qi, tonifying blood, strengthening the spleen, resolving phlegm, promoting dampness, activating blood circulation, regulating qi, soothing the liver, clearing heat, detoxifying, nourishing yin, warming yang, calming the mind, unblocking meridians, stopping bleeding, and dispelling wind, etc.; an association relationship is established between each Chinese medicinal material and its corresponding first attribute label, and an association relationship is established between each symptom and the attribute feature label of the Chinese medicinal material used to treat the symptom, that is, the association relationship between the symptom and its corresponding second attribute feature label, and stored as a preset mapping relationship in the recommendation device of the Chinese medicine compound.

[0102] Step 205 : Calculate a second score corresponding to each Chinese medicinal material 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.

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

[0104] For example, the symptoms include qi deficiency and phlegm and dampness, and the corresponding second attribute feature labels are warm, sweet, spleen, lung, qi tonification and bitter, dry, spleen, stomach, phlegm resolving, and dampness removal, respectively. At this time, the second score of the Chinese medicinal material turmeric is to be calculated. The first attribute feature labels corresponding to turmeric are bitter, cold, lung, gallbladder, heat-clearing, and dampness-drying. The second score can be obtained by calculating the similarity between bitter, cold, lung, gallbladder, heat-clearing, and dampness-drying and the second attribute feature labels corresponding to all symptoms: warm, sweet, spleen, lung, qi tonification, bitter, dry, spleen, stomach, phlegm resolving, and dampness removal; if there are six first attribute feature labels corresponding to turmeric, among which bitter, lung, and dampness-drying overlap with the second attribute feature labels corresponding to all symptoms, then the second score of the Chinese medicinal material turmeric is the number of intersections 3 divided by the total number of first attribute labels 6, that is, 0.5, or the second score can be calculated by other methods, which is not limited in this embodiment.

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

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

[0107] Specifically, after obtaining the first score and the second score corresponding to each Chinese medicinal material, the final score corresponding to each Chinese medicinal material is calculated based on the first score and the second score, respectively. For example, a weighted summation method is used for calculation, and the recommended Chinese herbal compound is determined according to the final score.

[0108] Optionally, the criteria for determining the recommended Chinese herbal compound can be pre-configured in the Chinese herbal compound recommendation device, such as setting a threshold for the final score, and recommending Chinese herbal medicines corresponding to scores exceeding the threshold; or sorting the final scores of all Chinese herbal medicines, and recommending the top 5 Chinese herbal medicines; or other methods, which are not limited in this embodiment.

[0109] Optionally, the final score may not be calculated, and the determination may be made directly based on the first score and the second score corresponding to each Chinese medicinal material. For example, thresholds for the first score and the second score may be pre-configured in the recommendation device for the Chinese herbal compound, and Chinese medicinal materials whose first score and second score both meet the thresholds may be recommended, or other methods may be used. This embodiment does not limit this.

[0110] The method for recommending a Chinese herbal compound provided in an embodiment of the present application, in response to receiving a determination request, queries 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 name of each Chinese herbal medicine 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; calculates a first score corresponding to each target protein and determines at least one candidate target protein from each target protein; the first score is a correlation score between the target protein and the corresponding information; obtains Chinese herbal medicines related to each candidate target protein; determines a first attribute feature label corresponding to each Chinese herbal medicine and a second attribute feature label corresponding to the symptom according to a preset mapping relationship; calculates a second score corresponding to each Chinese herbal medicine based on the first attribute label and the second attribute label; the second score is a correlation score between the Chinese herbal medicine and the symptoms corresponding to the disease; and determines a recommended Chinese herbal compound based on the first score and the second score. By querying the target proteins corresponding to each Chinese medicinal material and disease name in the initial Chinese medicine compound through the preset database and calculating its first score, the direct interaction relationship between the Chinese medicinal materials and the disease target protein can be clarified; traditional Chinese medicine compounds are mostly based on experience-based combinations, and there may be problems of "ineffective ingredients" or "unclear targets". Through the first score screening, target proteins with weak correlation with disease target proteins can be eliminated, and the focus can be placed on truly effective ingredients; the first attribute feature labels of Chinese medicinal materials (such as "heat" and "cold") and the second attribute feature labels of symptoms (such as "qi deficiency" and "blood deficiency") are determined through the preset mapping relationship. The first score verifies the association between the Chinese herbal medicine and the disease target protein, and the second score verifies the match between the Chinese herbal medicine and the symptoms, forming a double verification of "target mechanism + symptom relief". The recommended Chinese herbal medicine compound is determined based on the first and second scores, avoiding the one-sidedness caused by relying solely on the target or symptom score, thereby improving the adaptability of the Chinese herbal medicine compound to the disease.

[0111] As an optional implementation, based on 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] Obtain the interaction scores between target proteins;

[0113] Construct protein interaction network topology map based on interaction scores;

[0114] Based on the protein interaction network topology map, multiple centrality index values ​​of each target protein are calculated, and based on the multiple centrality index values ​​of each target protein and the weights corresponding to the multiple centrality index values, the first score corresponding to each target protein is calculated by weighted summation;

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

[0116] Among them, the protein interaction network topology map is a map that reflects the relationship between target proteins. It is drawn based on the interaction score according to specific rules, including nodes (target proteins) and edges (interaction relationships); for example, if the interaction score between target protein A and target protein B is 0.999, then a high-weight edge is generated between target protein A and target protein B. The topological importance of the node can also be mapped by node size and color, and the thickness of the edge reflects the score, thereby intuitively displaying the relationship between target proteins.

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

[0118] Specifically, after the target proteins are found, all target proteins are listed in a list, and the API interface of the protein interaction database is called to send a query request containing the target protein list 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 the target proteins and the interaction scores between them based on multi-source evidence, thereby obtaining the interaction scores between each target protein; the recommendation device of the traditional Chinese medicine compound parses the interaction scores into nodes (target proteins) and edges (interaction relationships), where the weights of the edges are quantified by the interaction scores, and a protein interaction network topology map is constructed. Based on the map, multiple centrality index values ​​of each target protein are calculated respectively, such as degree centrality (the number of direct connections), betweenness centrality (the frequency of a node as a shortest path bridge), and closeness centrality (the average distance to other nodes). Then, according to the pre-configured weights corresponding to the centrality index values, a first score of each target protein is calculated by 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 TCM compound recommendation device, such as setting a first score threshold and determining target proteins whose first scores meet the threshold as candidate target proteins. Other rules can also be used, which are not limited in this embodiment.

[0120] Optionally, a protein interaction network topology map can be output as a result for user viewing.

[0121] The method for recommending a traditional Chinese medicine compound provided in an embodiment of the present application calculates a first score corresponding to each target protein and determines at least one candidate target protein from each target protein, including: obtaining an interaction score between each target protein; constructing a protein interaction network topology map based on the interaction score; calculating multiple centrality index values ​​of each target protein based on the protein interaction network topology map, and calculating the 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; and determining at least one candidate target protein based on the first score corresponding to each target protein. By obtaining the interaction scores between target proteins, the degree of association between target proteins can be quantified, providing an objective data basis for subsequent analysis. The interactions between target proteins are presented in the form of a network topology map, which intuitively demonstrates the complex relationships between target proteins. Based on the protein interaction network topology map, multiple centrality index values ​​are calculated for each target protein. Different centrality indexes reflect the importance of the target protein in the network from different perspectives. Comprehensive consideration of these indicators can more comprehensively evaluate the characteristics of the target protein. Based on the values ​​of multiple centrality indexes and their corresponding weights, a weighted summation method is used to calculate the first score corresponding to each target protein. This fully considers the relative importance of different centrality indexes, making the scoring results more scientific and reasonable. By setting reasonable weights, the role of certain key indicators can be highlighted according to specific research objectives and needs, thereby more accurately evaluating the comprehensive importance of target proteins. The first score comprehensively considers the interaction relationships between target proteins and multiple centrality indexes, which can more effectively identify target proteins with important positions and potential functions in the network, reduce interference from human factors, and improve the reliability and effectiveness of screening results.

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

[0123] The similarity between the first attribute label and the second attribute label corresponding to each Chinese medicinal material is calculated to obtain a second score corresponding to each Chinese medicinal material.

[0124] It is understandable that there may be multiple symptoms, each of which has its corresponding second attribute feature label. The second score is calculated by respectively calculating the similarity between the first attribute feature label corresponding to each medicinal material and the second attribute feature label corresponding to all symptoms.

[0125] Exemplarily, the cosine similarity is calculated, and the text of the first attribute label and the second attribute label is segmented, stop words are removed, stems are extracted, and the preprocessed text is converted into a word vector. The bag-of-words model, TF-IDF, and other methods can be used to calculate the cosine value of the angle between the two word vectors using the cosine similarity formula. The closer the value is to 1, the higher the similarity. Alternatively, other methods can be used to calculate the similarity, which is not limited in this embodiment.

[0126] The method for recommending a Chinese herbal compound provided in an embodiment of the present application calculates a second score corresponding to each Chinese herbal medicine based on a first attribute tag and a second attribute tag, including calculating the similarity between the first attribute tag and the second attribute tag corresponding to each Chinese herbal medicine to obtain the second score corresponding to each Chinese herbal medicine. By calculating the similarity between the first attribute feature tag and the second attribute feature tag as the second score, abstract associations can be converted into quantitative values, reducing interference from human factors and objectively reflecting the degree of association, thereby laying a reliable data foundation for determining recommended Chinese herbal compound prescriptions.

[0127] As an optional implementation, based on the above embodiment, the recommended Chinese herbal compound is determined based on the first score and the second score, including:

[0128] 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 weighted sum method is used to calculate the third score corresponding to each Chinese medicinal material;

[0129] The recommended Chinese herbal compound is determined based on the third score.

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

[0131] Specifically, the recommendation device for the Chinese herbal compound is pre-configured with weights corresponding to the first score and the second score. After obtaining the first score and the second score corresponding to each Chinese medicinal material, the third score corresponding to each Chinese medicinal material is calculated by weighted summation based on the weights corresponding to the first score and the second score, and then the recommended Chinese herbal compound is determined based on the third score.

[0132] For example, the first score of Chinese herbal 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 of Chinese herbal medicine A is .

[0133] Optionally, the rules for determining the recommended Chinese herbal compound can be pre-configured in the Chinese herbal compound recommendation device, such as sorting the third scores corresponding to the Chinese medicinal materials and using the top six Chinese medicinal materials as the recommended Chinese herbal compound.

[0134] The method for recommending a Chinese herbal compound provided in an embodiment of the present application determines a recommended Chinese herbal compound based on a first score and a second score, including: calculating a third score corresponding to each Chinese herbal medicine using a weighted summation method based on the first score, the second score, and the weights corresponding to the first and second scores; and determining a recommended Chinese herbal compound based on the third score. The first score and the second score respectively reflect the degree of correlation in different aspects, and the weighted summation comprehensively considers the dual-dimensional characteristics to avoid the one-sidedness caused by relying solely on a single score. By setting different weights, different application scenarios can be flexibly addressed.

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

[0136] Arrange and combine the Chinese medicinal materials in the recommended Chinese herbal compound to obtain multiple drug pairs;

[0137] Determine the adjustment coefficient for each drug pair;

[0138] The recommendation level of each drug pair is determined based on the adjustment coefficient and the third score corresponding to each Chinese medicinal material in each drug pair.

[0139] Among them, a medicinal pair refers to a combination of at least two Chinese medicinal materials, such as Astragalus and Codonopsis.

[0140] Among them, the adjustment coefficient refers to the coefficient used to adjust the third score, such as an increase of 15%, a decrease of 10%, etc.

[0141] Specifically, after determining the recommended Chinese herbal compound, the Chinese medicinal materials included therein are arranged and combined to obtain multiple medicine pairs, and the adjustment coefficient of each medicine pair is determined separately. For example, the specific adjustment coefficient is determined based on whether the medicine pair includes toxic medicinal materials. After determining the adjustment coefficient, the third score is calculated to obtain the final score, thereby determining the recommendation level of each medicine pair.

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

[0143] For example, the drug pair is aconite + ginger + liquorice. If aconite is determined to be a highly toxic drug, the adjustment coefficient is reduced by 40%. The third score of the drug pair is 1.6. The final score after calculating the adjustment coefficient is .

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

[0145] The method for recommending a Chinese herbal compound provided in an embodiment of the present application, after determining the recommended Chinese herbal compound based on the first score and the second score, further comprises: arranging and combining the Chinese medicinal materials in the recommended Chinese herbal compound to obtain a plurality of drug pairs; determining an adjustment coefficient for each drug pair; and determining the recommendation level of each drug pair based on the adjustment coefficient and the third score corresponding to each Chinese medicinal material in each drug pair. To further verify the reliability of the recommended Chinese herbal compound, the compound is decomposed into drug pairs, and the interaction between the medicinal materials can be analyzed in a targeted manner. By determining the adjustment coefficient, the degree of synergistic enhancement or reduction can be quantitatively reflected. The recommendation level of each drug pair is determined based on the adjustment coefficient and the third score, and the synergistic effect of each drug pair is comprehensively considered, thereby improving the compatibility of the recommended prescription with the disease.

[0146] As an optional implementation, based on the above embodiment, the adjustment coefficient of each drug pair is determined, including:

[0147] Determine whether the drug pair is a classic drug pair, and if so, determine the adjustment coefficient to be adjusted upward by the first preset adjustment coefficient for the third score; if not, determine the adjustment coefficient to be 0;

[0148] 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;

[0149] And / or, determine whether there is a toxic Chinese medicinal material in the drug pair, if so, determine the adjustment coefficient to reduce the third score by a third preset adjustment coefficient, if not, determine the adjustment coefficient to be 0.

[0150] Among them, the first preset adjustment coefficient refers to the coefficient corresponding to the classic drug pair indicator, such as 15%.

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

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

[0153] Specifically, after obtaining the drug pair, determine whether the drug pair is a classic drug pair, such as by querying the TCMID drug pair database. If it can be found, it means that the drug pair is a classic drug pair, and the adjustment coefficient is determined to be to increase the third score by the first preset adjustment coefficient; determine whether the compatibility of the Chinese medicinal materials in the drug pair is opposite, such as cold + hot, which means that the compatibility of the drug pair is opposite, and the adjustment coefficient is determined to be to decrease the third score by the second preset adjustment coefficient; determine whether there are toxic Chinese medicinal materials in the drug pair. If so, the adjustment coefficient is determined to be to decrease the third score by the third preset adjustment coefficient.

[0154] It is understandable that to determine whether the compatibility of each Chinese medicinal material in the medicine pair is opposite, the compatibility can be performed based on the first attribute feature label corresponding to each Chinese medicinal material.

[0155] Among them, to determine whether there are toxic Chinese medicinal materials in the drug pair, a query can be performed in a relevant database to determine whether there are toxic Chinese medicinal materials.

[0156] Optionally, the third preset adjustment coefficient can also be configured with different adjustment coefficients according to the level of toxicity, such as reducing the toxicity by 10% for slightly toxic substances and reducing the toxicity by 40%, etc. This embodiment does not limit this.

[0157] For example, the third score of the drug pair of Pinellia tuber + dried ginger + jujube is , if this drug pair is a classic drug pair, the third score will be increased by 15%. If the compatibility of each Chinese herbal medicine in this drug pair is the same, the adjustment coefficient is 0. If Pinellia ternata is a slightly toxic herbal medicine in the drug pair, the third score will be reduced by 10%. In summary, the final score of this drug pair is .

[0158] The method for recommending a Chinese herbal compound provided in the embodiment of the present application determines the adjustment coefficient of each drug pair, including: determining whether the drug pair is a classic drug pair, if so, determining the adjustment coefficient to increase the third score by the first preset adjustment coefficient, if not, determining the adjustment coefficient to be 0; and / or, determining whether the medicinal properties of each Chinese herbal medicine in the drug pair are opposite, if so, determining the adjustment coefficient to decrease the third score by the second preset adjustment coefficient, if not, determining the adjustment coefficient to be 0; and / or, determining whether there are toxic Chinese herbal medicines in the drug pair, if so, determining the adjustment coefficient to decrease the third score by the third preset adjustment coefficient, if not, determining the adjustment coefficient to be 0. Classic drug pairs have been clinically verified, and their synergistic effects are clear. The upward adjustment coefficient can ensure that the compound retains its traditional advantages, while enhancing modern interpretability through quantitative scoring; reducing the efficacy offset or adverse reactions caused by the conflict of medicinal properties through quantitative constraints, and improving the safety of the compound; intuitively reflecting the toxicity risk through quantitative scoring, facilitating the balance between 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 embodiment, based on the above embodiment, after constructing the protein interaction network topology map according to the interaction score, the method further includes:

[0160] Determine direct-acting proteins, indirect-acting proteins, and uncovered proteins based on the protein interaction network topology map;

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

[0162] The output includes a list of directly acting proteins, indirectly acting proteins, uncovered proteins, and side-effecting proteins.

[0163] Among them, direct-acting proteins refer to proteins whose target proteins corresponding to Chinese medicinal materials overlap with those corresponding to diseases, that is, in the topological map of the protein interaction network, the protein is directly connected to both Chinese medicinal materials and diseases.

[0164] Among them, indirect-acting proteins refer to proteins that are directly connected to diseases and indirectly connected to Chinese medicinal materials in the protein interaction network topology map.

[0165] Among them, uncovered proteins refer to proteins that are directly connected to the disease, but are neither directly nor indirectly connected to Chinese medicinal materials in the protein interaction network topology map.

[0166] Among them, side effect proteins refer to proteins that are associated with known drug toxicity, adverse reactions, or inhibition of key physiological functions.

[0167] Specifically, after constructing the topological map of the protein interaction network, proteins that are directly connected to both Chinese medicinal materials and diseases are found from the map and determined as direct-acting proteins; proteins that are directly connected to diseases and indirectly connected to Chinese medicinal materials are found and determined as indirect-acting proteins; proteins that are directly connected to diseases but are neither directly nor indirectly connected to Chinese medicinal materials are found and determined as uncovered proteins; then, all target proteins obtained by querying the preset database are queried for their side effects to determine the side effect proteins, and finally a list including direct-acting proteins, indirect-acting proteins, uncovered proteins and side effect proteins is output, in which each type of protein is listed separately.

[0168] The method for recommending a traditional Chinese medicine compound provided in the embodiments of the present application, after constructing a protein interaction network topology map based on the interaction scores, further comprises: determining directly acting proteins, indirectly acting proteins, and uncovered proteins based on the protein interaction network topology map; determining side effect proteins in each target protein; and outputting a list of directly acting proteins, indirect acting proteins, uncovered proteins, and side effect proteins. By categorizing and outputting the direct acting proteins, indirect acting proteins, uncovered proteins, and side effect proteins, the interaction relationships are systematically analyzed, the side effect risks are quantified, and a precise basis for risk assessment is provided.

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

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

[0171] Among them, functional analysis data can include 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, signal pathway data can include 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 Chinese medicinal materials and diseases included in the request from the preset database, the corresponding interface is called to query the functional analysis data and signal pathway data corresponding to each target protein, and the queried data is annotated to the corresponding target protein in turn.

[0174] The method for recommending a traditional Chinese medicine compound provided in an embodiment of the present application, after querying and determining the target protein corresponding to the initial traditional Chinese medicine compound related information included in the request from a preset database, further includes: querying the functional analysis data and signal pathway data corresponding to each target protein, and annotating the functional analysis data and signal pathway data for each target protein. By querying the functional analysis data and signal pathway data corresponding to each target protein and annotating them, the molecular function of the target protein can be clarified, and the key pathways involved in the target protein can be clarified, so that the user can have a more comprehensive understanding of the characteristics of the target protein, and further provide data support for the traditional Chinese medicine compound.

[0175] As an optional implementation manner, based on the above embodiment, in response to receiving the determination request, querying the target protein corresponding to the initial Chinese herbal compound related information included in the determination request from a preset database includes:

[0176] 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;

[0177] 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;

[0178] In response to receiving a determination request input by the user through the confirmation component, a target protein corresponding to the initial Chinese herbal compound related information included in the determination request is queried from a preset database.

[0179] The confirmation operation may be a user clicking on a Chinese herbal compound recommendation icon or creating a new project, etc., which is not limited in this embodiment.

[0180] Specifically, when a Chinese herbal compound prescription is required, the user triggers a confirmation operation on the operation interface, and the operation interface will display a disease name input component, a Chinese herbal compound prescription 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 will be displayed on the operation interface. The user clicks the confirmation component to trigger the confirmation request. At this time, the Chinese herbal compound prescription recommendation device queries the preset database for the target proteins corresponding to the Chinese medicinal materials and diseases included in the confirmation request.

[0181] The method for recommending a Chinese herbal formula provided in an embodiment of the present application, in response to receiving a confirmation request, queries a preset database for a target protein corresponding to the initial Chinese herbal formula related information included in the confirmation request, including: in response to receiving a confirmation operation triggered by a user through an operation interface, displaying a disease name input component, a Chinese herbal formula input component, and a symptom input component on the operation interface; in response to receiving the disease name corresponding to the initial Chinese herbal formula input by the user through the disease name input component, the names of each Chinese medicinal material in the initial Chinese herbal formula input by the Chinese herbal formula input component, and the symptoms corresponding to the disease input by 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, querying a preset database for a target protein corresponding to the initial Chinese herbal formula related information included in the confirmation request. Through the step-by-step guidance of the disease name input component, the Chinese herbal formula 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, based on the above embodiment, after determining the recommended Chinese herbal compound based on the first score and the second score, the method further includes:

[0183] 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 herbal compound, the total number of target proteins corresponding to the recommended Chinese herbal 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 recommendation level of each drug pair.

[0184] Specifically, after the Chinese medicine compound recommendation device determines the recommended Chinese medicine compound, the determination result is displayed on the operation interface. The determination result may include the name 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 direct-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. The Chinese medicine compound recommendation method provided in the embodiment of the present application, after determining the recommended Chinese medicine compound based on the first score and the second score, the method further includes: displaying the determination result through the operation interface, the determination result includes the name 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 direct-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. Displaying the determination result through the operation interface can intuitively display the determination result, allowing the user to quickly understand the determined name 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 direct-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.

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

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

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

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

[0189] 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.

[0190] Among them, querying the matching relationship between each candidate target protein and known drugs can be done by querying in public databases such as drug bank database, organic small molecule biological activity data, target and bioactive drug database, combination database, etc., or by querying in other ways, which is not limited in this embodiment.

[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, whether the candidate target protein is already a target of certain known drugs; the operation interface can also display a determination process display component. If the user needs to view the determination process information, he can trigger a determination process information display request by clicking the determination process display component, so as to view the determination process related information.

[0192] Optionally, the determination results and determination process information can be exported in formats including CSV, Excel, PDF, etc.

[0193] The method for recommending a traditional Chinese medicine compound provided in an 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 a known drug; 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, 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. By querying the matching relationship between each candidate target protein and a known drug, 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 a variety of graphical forms, the key data and analysis results in the determination process are intuitively displayed, which not only increases the credibility of the determination results, but also enables users to understand how the traditional Chinese medicine compound is recommended.

[0194] Figure 3 A flowchart of a method for recommending a Chinese herbal compound according to another embodiment of the present application is shown below. Figure 3 As shown, the method for recommending a Chinese herbal compound provided in this embodiment includes the specific steps of calculating a first score and a second score. The method for recommending a Chinese herbal compound provided in this embodiment includes the following steps:

[0195] Step 301, in response to receiving a determination request, querying the target proteins corresponding to the Chinese medicinal materials and diseases included in the determination request from a preset database, wherein the determination request includes the names of the Chinese medicinal materials 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.

[0196] Step 302: Obtain the interaction scores between target proteins.

[0197] Step 303: construct a protein interaction network topology map based on the interaction scores.

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

[0199] Step 305 , based on the protein interaction network topology map, multiple centrality index values ​​of each target protein are calculated, and based on the multiple centrality index values ​​of each target protein and the weights corresponding to the multiple centrality index values, a first score corresponding to each target protein is calculated by weighted summation.

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

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

[0202] Step 308: Determine 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.

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

[0204] Step 310 , 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 weighted sum method is used to calculate the third score corresponding to each Chinese medicinal material.

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

[0206] Step 312: Arrange and combine the Chinese medicinal materials in the recommended Chinese medicinal compound to obtain a plurality of medicinal pairs.

[0207] Step 313: Determine the adjustment coefficient of each drug pair.

[0208] Step 314 : determining the recommendation level of each medicinal pair based on the adjustment coefficient and the third score corresponding to each Chinese medicinal material in each medicinal pair.

[0209] Step 315, the determination result is displayed through the operation interface, and the determination result includes the name of each Chinese medicinal material in the recommended Chinese herbal medicine compound, the total number of target proteins corresponding to the recommended Chinese herbal 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.

[0210] In this embodiment, the implementation method and technical effects of steps 301 to 315 are similar to the implementation method of the corresponding solutions in the above embodiments, and will not be repeated here.

[0211] Figure 4This is a schematic diagram of the display screen changes of the recommended operation interface of the traditional Chinese medicine compound provided in one embodiment of the present application, such as Figure 4 As shown, when the user needs to recommend a Chinese medicine compound, as shown in the first screen 401, a confirmation operation can be triggered by clicking the Chinese medicine compound recommendation icon on the operation interface; in response to receiving the confirmation operation triggered by the user through the operation interface, the disease name input component, the Chinese medicine compound input component and the symptom input component are displayed on the operation interface as shown in the second screen 402; in response to receiving the disease name corresponding to the initial Chinese medicine compound input by the user through the disease name input component, the name of each Chinese medicinal material in the initial Chinese medicine compound input through the Chinese medicine compound input component and the symptoms corresponding to the disease input through the symptom input component, the confirmation component is displayed on the operation interface as shown in the third screen 403; in response to receiving the confirmation request input by the user through the confirmation component, the waiting for confirmation button is displayed on the operation interface as shown in the fourth screen 404. The Chinese medicine compound recommendation device determines the recommended Chinese medicine compound according to the Chinese medicine compound recommendation method provided by itself; in response to the determination of the Chinese medicine compound, the Chinese medicine compound determination result component and the determination process display component are displayed on the operation interface as shown in the fifth screen 405, 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 Chinese medicine compound determination result component, the name of each Chinese medicinal material in the recommended Chinese medicine compound, the recommendation level of each medicine pair, etc. are displayed on the operation interface as shown in the sixth screen 406; in response to receiving the determination process information display request triggered by the user through the determination process display component, the determination process information, such as the protein interaction network topology map, the direct acting protein list, etc., are displayed on the operation interface as shown in the seventh screen 407.

[0212] Figure 5 This is a schematic diagram of the structure of a device for recommending a Chinese herbal compound according to an embodiment of the present application, as shown in FIG. Figure 5 As shown, the Chinese herbal compound recommendation device provided in this embodiment is located in the Chinese herbal compound recommendation device. The Chinese herbal compound recommendation device 50 provided in 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 protein corresponding to each information included in the determination request from a preset database, and each information includes the name 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; the calculation module 52 is used to calculate the first score corresponding to each target protein, and 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 obtain Chinese medicinal materials related to each candidate target protein; the determination module 54 is also 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 also 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 also used to determine the recommended Chinese medicinal compound based on the first score and the second score.

[0214] The Chinese medicine compound recommendation device provided in this embodiment can perform Figure 2 The specific implementation principles and technical effects of the methods provided in the embodiments are similar and will not be repeated here.

[0215] Optionally, the calculation module 52, when calculating the first score corresponding to each target protein, is specifically used to: obtain the interaction score between each target protein; construct a protein interaction network topology map based on the interaction score; calculate multiple centrality index values ​​of each target protein based on the protein interaction network topology map, and calculate the 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; the determination module 53, when determining at least one candidate target protein from each target protein, 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 herbal 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 herbal medicine by weighted summation based on the first score, the second score corresponding to each Chinese herbal medicine and the weights corresponding to the first score and the second score; and determine the recommended Chinese herbal compound based on the third score.

[0218] Optionally, the device for recommending a Chinese herbal compound provided in this embodiment further includes a combination module.

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

[0220] Optionally, when determining the adjustment coefficient of each drug pair, the determination module 53 is specifically used to: determine whether the drug pair is a classic drug pair, if so, determine the adjustment coefficient to increase the third score by the first preset adjustment coefficient, if not, determine the adjustment coefficient to be 0; and / or, determine whether the medicinal properties of the Chinese medicinal materials in the drug pair are opposite, if so, determine the adjustment coefficient to reduce the third score by the second preset adjustment coefficient, if not, determine the adjustment coefficient to be 0; and / or, determine whether there are toxic Chinese medicinal materials in the drug pair, if so, determine the adjustment coefficient to reduce the third score by the third preset adjustment coefficient, if not, determine the adjustment coefficient to be 0.

[0221] Optionally, the device for recommending a Chinese herbal compound provided in this embodiment further includes an output module.

[0222] Accordingly, the determination module 53 is also used to determine the direct-acting proteins, indirect-acting proteins and uncovered proteins based on the protein interaction network topology map; determine the side effect proteins in each target protein; and the output module is used to output a list including direct-acting proteins, indirect-acting proteins, uncovered proteins and side effect proteins.

[0223] Optionally, the device for recommending a Chinese herbal compound provided in this embodiment further includes a marking module.

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

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

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

[0227] Correspondingly, the display module is used to display the determination results through the operation interface, and the determination results include the names of each Chinese medicinal material in the recommended Chinese herbal compound, the total number of target proteins corresponding to the recommended Chinese herbal compound, the number of directly acting proteins, the number of indirect acting proteins, the number of uncovered proteins, and the number of side effect proteins.

[0228] Optionally, the query module is also used 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 also used to display the determination process information in response to receiving a determination process information display request triggered by the user through the determination process display component, 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, direct acting protein list, indirect acting protein list, uncovered protein list and side effect protein list.

[0229] Figure 6 A schematic diagram of the structure of a recommended device for preparing a Chinese herbal compound according to an embodiment of the present application is shown in FIG. Figure 6 As shown, the Chinese medicine compound recommendation device 60 provided in this embodiment includes: a processor 61 and a memory 62 communicatively connected to the processor.

[0230] The memory 62 is used to store computer-executable instructions; the processor 61 executes the computer-executable instructions stored in the memory 62 to implement the method for recommending a Chinese herbal compound provided in the above embodiment. The relevant descriptions can be understood by referring to the corresponding descriptions and effects of the steps in the accompanying drawings, and will not be elaborated on here.

[0231] The program may include program code, which includes computer-executable instructions. The memory 62 may include a high-speed RAM memory, or may also include a non-volatile memory, such as at least one disk memory.

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

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

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

[0235] The various embodiments described above in this 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 parts (ASSPs), systems on chips (SOCs), complex programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may 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, which can be a special-purpose or general-purpose programmable processor, which can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit 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 methods of the present application may be written in any combination of one or more programming languages. These computer-executable instructions may be provided to a processor or controller of a general-purpose computer, a special-purpose computer, or other programmable data processing device, such that when the computer-executable instructions are executed by the processor or controller, the functions / operations specified in the flowcharts and / or block diagrams are implemented. The computer-executable instructions may be executed entirely on the machine, partially on the machine, as a stand-alone software package, partially on the machine and partially on a remote machine, or entirely on a remote machine or electronic device.

[0237] In the context of this application, a computer-readable storage medium may be a tangible medium that may contain or store a program for use by or in conjunction 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, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. More specific examples of computer-readable storage media include an electrical connection 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, the 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), etc.

[0238] The systems and techniques described herein can be implemented in a computing system that includes back-end components (e.g., as data electronics), or a computing system that includes middleware components (e.g., application electronics), or a computing system that includes front-end components (e.g., a user computer with a graphical user interface or web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such back-end components, middleware components, or front-end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include a local area network (LAN), a wide area network (WAN), and the Internet.

[0239] It should be noted that, for the aforementioned method embodiments, for the sake of simplicity of description, they are all expressed as a series of action combinations, but those skilled in the art should be aware that the present application is not limited by the order of the actions described, because according to the present application, certain steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also be aware that the embodiments described in the specification are all optional embodiments, and the actions and modules involved are not necessarily required by the present application. In other words, the various forms of processes shown above can be used to reorder, add or delete steps. For example, the steps disclosed in the present application can be executed in parallel, can be executed sequentially, or can be executed in different orders. As long as the desired results of the technical solutions disclosed in the present application can be achieved, this document does not limit them here.

[0240] It should be further noted that, although the various steps in the flowchart are shown in sequence as indicated by the arrows, these steps are not necessarily performed in the order indicated by the arrows. Unless otherwise specified herein, there is no strict order restriction on the execution of these steps, and these steps may be performed in other orders. Moreover, at least a portion of the steps in the flowchart may include multiple sub-steps or multiple stages, and these sub-steps or stages are not necessarily performed at the same time, but may be performed at different times. The execution order of these sub-steps or stages is not necessarily to be performed in sequence, but may be performed in turn or alternately with other steps or at least a portion of the sub-steps or stages of other steps.

[0241] It should be understood that the above-described device embodiments are merely illustrative, and the device of the present application may also be implemented in other ways. For example, the division of units / modules in the above-described embodiments is merely a logical functional division, and actual implementations may employ other division methods. For example, multiple units, modules, or components may be combined or integrated into another system, or some features may be omitted or not implemented.

[0242] In addition, unless otherwise specified, the functional units / modules in the various embodiments of the present application may be integrated into a single unit / module, each unit / module may exist physically separately, or two or more units / modules may be integrated together. The aforementioned integrated units / modules may be implemented in the form of hardware or software program modules.

[0243] If the integrated unit / module is implemented in the form of hardware, the hardware may 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] If the integrated unit / module is implemented as 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, or the portion that contributes to the relevant technology, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a memory and includes a number of instructions for enabling a computer device (which can be a personal computer, server, or network device, etc.) to execute all or part of the steps of the various embodiments of the method of this application. The aforementioned memory includes various media that can store computer-executable instructions, such as USB flash drives, read-only memories (ROMs), random access memories (RAMs), mobile hard drives, magnetic disks, or optical disks.

[0245] In the above embodiments, the description of each embodiment has its own emphasis. For parts not described in detail in a particular embodiment, please refer to the relevant description of other embodiments. The technical features of the above embodiments can be combined in any way. To keep the description concise, 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, they should be considered to be within the scope of this specification.

[0246] Those skilled in the art will readily appreciate other embodiments of the present application after considering the specification and practicing the invention disclosed herein. This application is intended to cover any variations, uses, or adaptations of the present application that follow the general principles of the present application and include common knowledge or customary techniques in the art not disclosed herein. The description and examples are to be considered as exemplary only.

[0247] It should be understood that the present application is not limited to the precise structure described above and shown in the accompanying drawings, and various modifications and changes can be made without departing from the scope thereof. Therefore, the above specific embodiments do not constitute a limitation on the scope of protection of the present application. It should be understood by those skilled in the art 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 the present application should be included in the scope of protection of the present 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; 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; Determining at least one candidate target protein according to the first score corresponding to each target protein; 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 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.

3. The method according to claim 1, characterized in that 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.

4. The method according to claim 3, 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.

5. The method according to claim 4, 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 drug 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.

6. The method according to claim 1, 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.

7. 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.

8. 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.

9. The method according to claim 8, 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.

10. The method according to claim 8, 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.

11. A device for recommending a Chinese herbal compound, characterized in that: The device comprises: a query module configured to, in response to receiving a determination request, query 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; An acquisition module, used to obtain the interaction scores between the target proteins; A construction module, used to construct a protein interaction network topology map based on the interaction score; a calculation module, configured to calculate multiple centrality index values ​​of each target protein based on the protein interaction network topology map, and calculate 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; a determination module, configured to determine at least one candidate target protein according to the first score corresponding to each of the target proteins; The acquisition module is further 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.

12. 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 10.

13. 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 10 when executed by a processor.

14. 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 10 is implemented.

Images