Evaluation method, device, equipment, medium and product for effect of traditional Chinese medicine on diseases

By constructing the Barabas PPI network of traditional Chinese medicine and diseases and calculating the similarity, the problem of quantitative evaluation of the effects of traditional Chinese medicine was solved, the quantitative evaluation and standardization of the effects of traditional Chinese medicine were achieved, and the modernization research of traditional Chinese medicine was promoted.

CN120783956AActive Publication Date: 2025-10-14INNOVATION CENTER OF YANGTZE RIVER DELTA ZHEJIANG UNIVERSITY

Patent Information

Application Number
CN202511301473.X
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2025-09-12
Publication Date
2025-10-14
Estimated Expiration
2045-09-12

AI Technical Summary

Technical Problem

Traditional research models make it difficult to systematically analyze the networked regulatory relationship between "ingredients-targets-pathways-diseases and syndromes" of traditional Chinese medicine, especially the dynamic integration mechanism in the "disease-syndrome combination" dimension, which restricts the quantitative evaluation and standardized development of the mechanism of action of traditional Chinese medicine.

Method used

A large language model is used to extract target entities from disease and traditional Chinese medicine datasets, construct a Barabas PPI network, calculate the similarity between the disease gene network and the medicinal material gene network, and achieve quantitative evaluation of the effects of traditional Chinese medicine on diseases.

Benefits of technology

It has achieved quantitative mapping from microscopic interactions to macroscopic efficacy, provided an effective quantitative evaluation method for the effects of traditional Chinese medicine on diseases, and promoted the transformation of modern research on traditional Chinese medicine to a data-driven paradigm.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN120783956A_ABST
    Figure CN120783956A_ABST
Patent Text Reader

Abstract

The invention discloses a method, a device, equipment, a medium and a product for evaluating the effect of traditional Chinese medicine on diseases, and relates to the technical field of pharmacology of traditional Chinese medicine, the method comprises the following steps: acquiring a disease data set and a traditional Chinese medicine data set of a target disease; extracting a disease target entity from the disease data set by adopting a large language model, and extracting a medicinal material entity from the traditional Chinese medicine data set; constructing a disease gene network according to each disease target entity and a Barabas PPI network; constructing a medicinal material gene network according to the target traditional Chinese medicine formula, the medicinal material entities and a Barabas PPI network; the similarity between the disease gene network and the medicinal material gene network is calculated, the similarity is used for representing the effect of the target traditional Chinese medicine formula on the target disease, and quantitative evaluation of the effect of the traditional Chinese medicine on the disease can be achieved.
Need to check novelty before this filing date? Find Prior Art

Description

TECHNICAL FIELD

[0001] The application relates to the technical field of traditional Chinese medicine pharmacology, in particular to a method and device for evaluating the effect of traditional Chinese medicine on diseases, equipment, medium and products. BACKGROUND

[0002] Alcoholic liver disease (ALD) is a chronic liver injury disease caused by long-term excessive alcohol consumption. Its pathogenesis is complex and involves multiple pathological links such as oxidative stress, inflammatory response and metabolic disorder. At present, the western medicine treatment has limitations such as single target and obvious side effects, while the traditional Chinese medicine compound has unique potential in the prevention and treatment of ALD due to the advantages of multiple components, multiple targets and overall regulation. However, the traditional research mode is difficult to systematically analyze the network regulation relationship between the components-target-pathway-disease syndrome of traditional Chinese medicine, especially the dynamic integration mechanism of ligand-receptor interaction in the dimension of disease syndrome combination, which restricts the quantitative evaluation and standardized development of the action principle of traditional Chinese medicine. SUMMARY

[0003] The purpose of the application is to provide a method and device for evaluating the effect of traditional Chinese medicine on diseases, equipment, medium and products, which can realize the quantitative evaluation of the effect of traditional Chinese medicine on diseases.

[0004] To achieve the above purpose, the application provides the following solutions. In a first aspect, the application provides a method for evaluating the effect of traditional Chinese medicine on diseases, comprising: collecting a disease symptom data set and a traditional Chinese medicine data set of a target disease; extracting disease symptom target entities from the disease symptom data set and extracting medicinal material entities from the traditional Chinese medicine data set by using a large language model; constructing a disease symptom gene network according to each disease symptom target entity and a Barabas PPI network, and constructing a medicinal material gene network according to a target traditional Chinese medicine prescription, each medicinal material entity and the Barabas PPI network; calculating the similarity of the disease symptom gene network and the medicinal material gene network, wherein the similarity is used to represent the effect of the target traditional Chinese medicine prescription on the target disease.

[0005] Optionally, the disease symptom gene network is constructed according to each disease symptom target entity and the Barabas PPI network, and the medicinal material gene network is constructed according to the target traditional Chinese medicine prescription, each medicinal material entity and the Barabas PPI network, specifically comprising: each disease symptom target entity is converted into a disease symptom gene in a preset gene dictionary, each disease symptom gene constitutes a disease symptom gene set, and each medicinal material entity is converted into a medicinal material in a preset medicinal material dictionary, and the converted medicinal material constitutes a medicinal material set; calculate a first frequency of each disease gene in the disease gene set appearing in the disease data set, and a second frequency of each medicinal material in the medicinal material set appearing in the traditional Chinese medicine data set; calculate a first frequency of each disease gene in the disease gene set appearing in the disease data set, and a second frequency of each medicinal material in the medicinal material set appearing in the traditional Chinese medicine data set; According to the component proportion of each medicinal material in the target traditional Chinese medicine prescription and the initial medicinal material weight, the medicinal material gene weight of each medicinal material gene in the target traditional Chinese medicine prescription is calculated. According to the component proportion of each medicinal material in the target traditional Chinese medicine prescription and the initial medicinal material weight, the medicinal material gene weight of each medicinal material gene in the target traditional Chinese medicine prescription is calculated.

[0006] Optionally, each disease target entity is converted into a disease gene in a preset gene dictionary, each disease gene constitutes a disease gene set, and each medicinal material entity is converted into a medicinal material in a preset medicinal material dictionary, and the converted medicinal material constitutes a medicinal material set, which specifically includes: Each disease target entity is matched with a disease gene in a preset gene dictionary with the smallest edit distance by using an edit distance algorithm, and each disease target entity matched with a disease gene constitutes a disease gene set. Each medicinal material entity is matched with a medicinal material in a preset medicinal material dictionary with the smallest edit distance by using an edit distance algorithm, and each medicinal material entity matched with a medicinal material constitutes a medicinal material set.

[0007] Optionally, according to the component proportion of each medicinal material in the target traditional Chinese medicine prescription and the initial medicinal material weight, the medicinal material gene weight of each medicinal material gene in the target traditional Chinese medicine prescription is calculated, which specifically includes: the formula for calculating the medicinal material gene weight is: ; ; Wherein, is the medicinal material weight of medicinal material h in the target traditional Chinese medicine prescription, is the component proportion of medicinal material h, is the initial medicinal material weight of medicinal material h, is the identifier of medicinal material gene s in medicinal material h, =1 indicates that medicinal material gene s exists in medicinal material h, =0 indicates that medicinal material gene s does not exist in medicinal material h, and S is the total number of medicinal material genes in the target traditional Chinese medicine prescription; is the medicinal material gene weight of medicinal material gene s in the target traditional Chinese medicine prescription, and H is the number of types of medicinal materials in the target traditional Chinese medicine prescription.

[0008] Optionally, the Barabas PPI network is used to filter the disease gene set and the medicinal material gene set corresponding to the medicinal material set respectively, and the filtered disease gene set constitutes a disease gene network, and the filtered medicinal material gene set constitutes a medicinal material gene network, specifically including: ; ; in, is the filtered disease gene set, The filtered medicinal material gene set, For the Barabas PPI network, For the disease gene set, A collection of medicinal materials.

[0009] Optionally, calculating the similarity between the disease gene network and the medicinal material gene network specifically includes: ; in, is the similarity between the disease gene network and the medicinal material gene network, For genes The weight of medicinal material genes, For genes The disease gene weight, For genes The weight of medicinal material genes, For genes The disease gene weights.

[0010] In a second aspect, the present application provides a device for evaluating the effect of traditional Chinese medicine on a disease, wherein the device for evaluating the effect of traditional Chinese medicine on a disease applies any of the above-mentioned methods for evaluating the effect of traditional Chinese medicine on a disease, and the device for evaluating the effect of traditional Chinese medicine on a disease comprises: Data collection module, used to collect symptom datasets and traditional Chinese medicine datasets of target diseases; An entity extraction module, configured to extract disease target entities from the disease dataset and extract medicinal material entities from the traditional Chinese medicine dataset using a large language model; Disease gene network and medicinal material gene network construction modules are used to construct disease gene networks based on target entities of each disease and BarabasPPI network; and to construct medicinal material gene networks based on target traditional Chinese medicine formulas, medicinal material entities and BarabasPPI network; The similarity calculation module is used to calculate the similarity between the disease gene network and the medicinal material gene network, and the similarity is used to represent the effect of the target traditional Chinese medicine formula on the target disease.

[0011] In a third aspect, the present application provides a computer device comprising: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the steps of the method for evaluating the effects of traditional Chinese medicine on diseases as described in any one of the above-mentioned methods.

[0012] In a fourth aspect, the present application provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of the method for evaluating the effects of traditional Chinese medicine on diseases as described in any one of the above.

[0013] In a fifth aspect, the present application provides a computer program product, comprising a computer program, which, when executed by a processor, implements the steps of the method for evaluating the effects of traditional Chinese medicine on diseases as described in any one of the above.

[0014] According to the specific embodiments provided in this application, this application discloses the following technical effects: The present application provides a method, apparatus, equipment, medium and product for evaluating the effects of traditional Chinese medicine on diseases. The method comprises constructing a disease gene network based on target entities of each disease and the Barabas PPI network; constructing a medicinal material gene network based on a target traditional Chinese medicine formula, each medicinal material entity and the Barabas PPI network; calculating the similarity between the disease gene network and the medicinal material gene network, and using the similarity to represent the effect of the target traditional Chinese medicine formula on the target disease, thereby achieving quantitative mapping from microscopic interactions to macroscopic efficacy, and further achieving quantitative evaluation of the effects of traditional Chinese medicine on diseases, thereby providing an effective traditional Chinese medicine evaluation method. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0016] Figure 1 A flowchart of a method for evaluating the effects of traditional Chinese medicine on diseases provided in one embodiment of the present application.

[0017] Figure 2 A schematic diagram of the principle of a method for evaluating the effects of traditional Chinese medicine on diseases provided in one embodiment of the present application.

[0018] Figure 3 A schematic diagram of the frequency statistics of Chinese medicinal materials literature provided in one embodiment of the present application.

[0019] Figure 4 A schematic diagram of the Barabas PPI network provided in an embodiment of the present application.

[0020] Figure 5 Quantitative evaluation values ​​of the medicinal material gene network and disease gene network of different traditional Chinese medicine prescriptions provided in one embodiment of the present application.

[0021] Figure 6 This is a schematic diagram of the functional modules of a device for evaluating the effects of traditional Chinese medicine on diseases provided in one embodiment of the present application.

[0022] Figure 7 A schematic diagram of the structure of a computer device provided in one embodiment of the present application. DETAILED DESCRIPTION

[0023] The following will be combined with the drawings in the embodiments of this application to clearly and completely describe the technical solutions in the embodiments of this application. Obviously, the embodiments described are only part of the embodiments of this application, not all of the embodiments. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of this application.

[0024] In order to make the above-mentioned purposes, features and advantages of the present application more obvious and easy to understand, the present application is further described in detail below with reference to the accompanying drawings and specific implementation methods.

[0025] In an exemplary embodiment, the present application provides a method for evaluating the effect of traditional Chinese medicine on a disease, such as Figure 1 and Figure 2 As shown, the method for evaluating the effect of traditional Chinese medicine on a disease includes steps 101 to 104.

[0026] Step 101: Collect a symptom dataset and a traditional Chinese medicine dataset of a target disease.

[0027] Step 102: using a large language model to extract disease target entities from the disease dataset, and extracting medicinal material entities from the traditional Chinese medicine dataset.

[0028] Step 103: construct a disease gene network based on each disease target entity and the Barabas PPI network; construct a medicinal material gene network based on the target Chinese medicine formula, each medicinal material entity and the Barabas PPI network.

[0029] Step 104: Calculate the similarity between the disease gene network and the medicinal material gene network, where the similarity is used to represent the effect of the target traditional Chinese medicine formula on the target disease.

[0030] In practical applications, when there are multiple target TCM prescriptions for a target disease, the similarity between the medicinal material gene network and the disease gene network corresponding to each target TCM prescription is calculated, with each target TCM prescription corresponding to a similarity score. The priority of each target TCM prescription is determined based on the similarity scores, and the target TCM prescription with the highest similarity is selected as the highest priority TCM prescription for the target disease.

[0031] In an exemplary embodiment, the target disease is alcoholic liver disease, and the method for evaluating the effect of traditional Chinese medicine on the disease in the present application is specifically a method for evaluating the integrated regulatory effect of the "disease-syndrome" network of ligand-receptor interaction in alcoholic liver disease.

[0032] Alcohol is a "damp-heat" poison. Long-term excessive drinking will lead to internal accumulation of damp-heat alcohol poison, which will block the circulation of qi and blood. Over time, the liver, spleen, and kidney will be out of balance, resulting in "qi stagnation and blood stasis", "liver depression and spleen deficiency", and "damp-heat phlegm obstruction". It is advisable to treat it with therapies such as "activating blood circulation and removing blood stasis", "soothing the liver and regulating qi", "strengthening the spleen and removing dampness", "diuresis and dampness removal", and "clearing heat and detoxification". This application uses the understanding of the pathogenesis of alcoholic liver disease in traditional Chinese medicine to establish corresponding keywords. The keywords include "qi stagnation and blood stasis", "liver depression and spleen deficiency", "damp-heat phlegm obstruction", "activating blood circulation and removing blood stasis", "soothing the liver and regulating qi", "strengthening the spleen and removing dampness", "diuresis and dampness removal", and "clearing heat and detoxification". Through large language models, text mining, entity extraction, etc., disease target entities related to the occurrence and development of alcoholic liver disease are identified from Chinese literature and patents. Disease target entities are biomarkers or target protein groups.

[0033] By utilizing Western medicine's understanding of the pathology of alcoholic liver disease, such as the Therapeutic Target Database (TTD), the Genecard database, and literature, corresponding keywords were established. Biomarkers or target protein groups related to the occurrence and development of liver ischemia-reperfusion injury were identified from Chinese and English literature through large language models, text mining, and entity extraction.

[0034] Integrate protein-protein interactions and biomarkers or target protein groups to construct a PPI target group combining the traditional Chinese and Western medicine "disease syndrome" of alcoholic liver disease, identify key ligand receptors and their interactions, and establish a weighted ligand receptor interaction communication network based on the frequency of appearance in the literature.

[0035] Literature search for traditional Chinese medicine therapeutic drugs (main treatment methods include "promoting blood circulation and removing blood stasis", "soothing the liver and regulating qi", "strengthening the spleen and removing dampness", "promoting diuresis and removing dampness", "clearing heat and detoxifying", etc.) was carried out. The target group of the Traditional Chinese Medicine Systems Pharmacology Database and Analysis Platform (TCMSP) was integrated with the "disease-syndrome" network of alcoholic liver disease ligand-receptor interaction to design a comprehensive evaluation index of the integrated regulatory effect of traditional Chinese medicine based on weighted network distance (PS, Perturbation Score), that is, the similarity between the disease gene network and the medicinal material gene network, and the accuracy of the perturbation score PS was further verified.

[0036] In an exemplary embodiment, in step 101, the systematic collection of disease datasets, such as alcoholic liver disease-related data, is the basis for constructing a target network for the "disease-syndrome integration" of traditional Chinese and Western medicine, and requires the integration of multi-source heterogeneous data, including Chinese and English literature, patent texts, and biomedical databases.

[0037] First, we collected Chinese medicine literature primarily from HowNet, while disease literature was collected from HowNet and PubMed. We used the Python Selenium framework to crawl literature abstracts and patent data, and stored the crawled data in a MongoDB database. PubMed is a free database that provides searchable biomedical papers and abstracts.

[0038] In one exemplary embodiment, in step 102, TCM research literature is collected from databases such as PubMed and HowNet, or unstructured text such as patents and ancient books is obtained using crawlers. Specifically, the unstructured text in the disease dataset and TCM dataset is preprocessed, including word segmentation and stop word removal.

[0039] Through the prompt project, the preprocessed disease dataset and traditional Chinese medicine dataset are respectively input into the large language model, so that the large language model outputs the disease target entity and the medicinal material entity. The large language model is the DeepSeek large language model.

[0040] In an exemplary embodiment, a disease gene network is constructed based on each disease target entity and the Barabas PPI network; and a medicinal material gene network is constructed based on the target traditional Chinese medicine formula, each medicinal material entity and the Barabas PPI network, specifically including steps 201 to 205.

[0041] Step 201: convert each disease target entity into a disease gene in a preset gene dictionary, and each disease gene constitutes a disease gene set; convert each medicinal material entity into a medicinal material in a preset medicinal material dictionary, and the converted medicinal materials constitute a medicinal material set.

[0042] Each disease target entity is converted into a disease gene in a preset gene dictionary, and each disease gene constitutes a disease gene set; each medicinal material entity is converted into a medicinal material in a preset medicinal material dictionary, and the converted medicinal materials constitute a medicinal material set, specifically including: using an edit distance algorithm to match each disease target entity with a disease gene with the smallest edit distance in the preset gene dictionary, and the disease genes obtained by matching each disease target entity constitute a disease gene set; using an edit distance algorithm to match each medicinal material entity with a medicinal material with the smallest edit distance in the preset medicinal material dictionary, and the medicinal materials obtained by matching each medicinal material entity constitute a medicinal material set.

[0043] The edit distance algorithm specifically uses the Levenshtein distance.

[0044] Among them, step 201 is specifically a process of standardizing the disease gene entity and the medicinal material entity.

[0045] Standardization of disease gene entities and medicinal material entities (e.g., Atractylodes macrocephala extract -> Atractylodes macrocephala) is mainly performed through annotation dictionary files.

[0046] The default gene dictionary is derived from the gene file (Homo_sapiens.gene_info) from the National Center for Biotechnology Information (NCBI). Standard gene symbols are parsed from the gene file to form the standardized dictionary, known as the default gene dictionary. The default herbal medicine dictionary is derived from the open-source databases TCMBANK and HERB2.0. Both gene and herbal medicine standardization processes are first automatically corrected using the standardized dictionary, and then manually optimized to produce the disease gene set and herbal medicine set.

[0047] Step 202: Calculate the first frequency of occurrence of each disease gene in the disease gene set in the disease dataset, and the second frequency of occurrence of each medicinal material in the medicinal material set in the traditional Chinese medicine dataset.

[0048] The frequency of the literature gene, that is, the first frequency, is expressed as: .

[0049] in, is the frequency of the disease gene d, i.e., the first frequency, where d is the disease gene entity (e.g., "TP53"). N1 represents the total amount of data in the disease gene set (e.g., the number of papers or sentences). Indicates the number of times the disease gene d appears in the i-th data.

[0050] The frequency of occurrence of medicinal materials in the literature, that is, the second frequency, is expressed as: .

[0051] in, is the frequency of the medicinal material entity h, that is, the second frequency of the medicinal material h, where h is the medicinal material entity (such as "Huangqi"). N2 represents the total amount of data in the medicinal material set (such as the number of documents or sentences). Indicates the number of times the medicinal material entity h appears in the j-th data in the medicinal material set.

[0052] like Figure 3 As shown, Danshen and Licorice are frequently used in the treatment of alcoholic liver disease. Danshen promotes blood circulation, removes blood stasis, and relieves pain. Licorice replenishes Qi and strengthens the middle stomach, relieves acute pain, and moderates the effects of other drugs, supporting liver health.

[0053] Step 203: Calculate the weight of each disease gene according to the first frequency corresponding to each disease gene in the disease gene set, and calculate the initial medicinal material weight of each medicinal material according to the second frequency corresponding to each medicinal material in the medicinal material set.

[0054] The disease gene weight is expressed as: .

[0055] in, is the disease gene weight of disease gene d, M represents the number of types of disease gene entities, The second frequency of the disease gene m.

[0056] The frequency weight of medicinal materials in the literature, that is, the medicinal material weight, is expressed as: .

[0057] in, is the medicinal material weight of medicinal material h, N is the number of types of medicinal material entities, is the frequency of medicinal material n.

[0058] Step 204: Calculate the medicinal material gene weight of each medicinal material gene in the target Chinese medicine formula according to the component proportion of each medicinal material in the target Chinese medicine formula and the initial medicinal material weight h.

[0059] The proportion of each medicinal material in the target traditional Chinese medicine formula, that is, the proportion in grams, is expressed as: ; in, is the component ratio of medicinal material h, is the number of grams of medicinal material h, is the number of grams of medicinal material s, and S is the type of medicinal material in the target traditional Chinese medicine formula.

[0060] According to the component proportion of each medicinal material in the target traditional Chinese medicine formula and the initial weight of the medicinal material, the medicinal material gene weight of each medicinal material gene in the target traditional Chinese medicine formula is calculated, specifically including: the formula for calculating the medicinal material gene weight is: ; ; in, is the medicinal material weight of the target Chinese medicine formula h, is the component ratio of medicinal material h, is the initial medicinal material weight of medicinal material h, is the identifier of the medicinal material gene s in the medicinal material h, =1 means that the medicinal material gene s exists in the medicinal material h, =0 means that the herbal medicine gene s does not exist in the herbal medicine h, and S is the total number of herbal medicine genes in the target Chinese medicine formula; is the medicinal material gene weight of the target Chinese medicine formula Chinese medicine gene s, and H is the number of Chinese medicinal materials in the target Chinese medicine formula.

[0061] The herb2.0 herb gene database contains targets but no weights. This application uses targets identified in the herb2.0 herb gene database and assigns weights.

[0062] Step 205: using the Barabas PPI network to filter the disease gene set and the medicinal material gene set corresponding to the medicinal material set respectively, the filtered disease gene set constitutes a disease gene network, and the filtered medicinal material gene set constitutes a medicinal material gene network.

[0063] like Figure 4 As shown, Figure 4 Each letter expression in the expression represents a gene. Genes interact with each other. This application can use this relationship to construct sub-network groups for different diseases.

[0064] Barabas PPI network refers to a method for constructing protein-protein interaction (PPI) networks based on the Barabási-Albert model (BA model). This network construction method utilizes the scale-free network characteristics in complex network theory. The open source Barabas PPI protein interaction network contains a large number of target genes. , these are groups of gene networks that have been shown to have specific functions, is the w-th gene in the BarabasPPI network, W is the number of genes in the BarabasPPI network, and the value of w ranges from 1 to W.

[0065] The disease gene set is represented as: , is the mth gene in the disease gene set, m ranges from 1 to M, and M is the number of disease genes in the disease gene set.

[0066] The medicinal material gene set is represented as: , is the t-th medicinal gene in the medicinal gene set, the value of t ranges from 1 to T, and T is the number of medicinal genes in the medicinal gene set.

[0067] In an exemplary embodiment, the Barabas PPI network is used to filter the disease gene set and the medicinal material gene set corresponding to the medicinal material set, respectively. The filtered disease gene set constitutes a disease gene network, and the filtered medicinal material gene set constitutes a medicinal material gene network, which specifically includes: ; ; in, is the filtered disease gene set, The filtered medicinal material gene set, For the Barabas PPI network, For the disease gene set, A collection of medicinal materials.

[0068] In an exemplary embodiment, calculating the similarity between the disease gene network and the medicinal material gene network specifically includes: .

[0069] in, is the similarity between the disease gene network and the medicinal material gene network, For genes The weight of medicinal material genes, For genes The disease gene weight, For genes The weight of medicinal material genes, For genes The disease gene weights.

[0070] Longdan Xiegan Decoction and Yinzhihuang Granules each correspond to a target Chinese medicine formula. The method of this application is used to calculate a similarity for Longdan Xiegan Decoction and Yinzhihuang Granules, such as Figure 5 As shown, the scores of Longdan Xiegan Decoction and Yinzhihuang Granules, that is, the similarity is relatively high. The main effects of these two medicines are to clear away the excess fire of the liver and gallbladder and to promote dampness and reduce jaundice. They are the main medicines for treating alcoholic liver disease. This proves that the method of this application is indeed effective. The score of Xuefu Zhuyu Decoction is also relatively high. Its effect is to promote blood circulation and remove blood stasis, which is also in line with the treatment principles of alcoholic liver disease.

[0071] This application is a quantitative evaluation method for the integrated regulatory effect of traditional Chinese medicine on "disease and syndrome" based on the ligand-receptor interaction network. By constructing a biological network associated with "alcoholic liver disease-TCM syndrome", combining text mining and the binding efficacy of active ingredients of traditional Chinese medicine with key receptor targets, and introducing a network pharmacology model, the regulatory intensity and path weight of the multi-target synergistic intervention of traditional Chinese medicine in the ALD pathological network are analyzed. This technology incorporates the "syndrome target-molecular target" data into a unified computing framework for the first time, realizing quantitative mapping from microscopic interactions to macroscopic efficacy, providing standardized tools for the accurate evaluation of traditional Chinese medicine compound treatment of ALD, and promoting the transformation of modern research on traditional Chinese medicine to a data-driven paradigm.

[0072] Based on the same inventive concept, the embodiments of the present application also provide a device for evaluating the effects of traditional Chinese medicine on diseases for implementing the aforementioned method for evaluating the effects of traditional Chinese medicine on diseases. The implementation solution provided by the device is similar to the implementation solution described in the aforementioned method. Therefore, the specific limitations in the embodiments of one or more devices for evaluating the effects of traditional Chinese medicine on diseases provided below can be found in the limitations of the method for evaluating the effects of traditional Chinese medicine on diseases described above and will not be repeated here.

[0073] In an exemplary embodiment, Figure 6 As shown, a device for evaluating the effect of traditional Chinese medicine on diseases is provided, comprising: The data collection module is used to collect the symptom dataset and traditional Chinese medicine dataset of the target disease.

[0074] The entity extraction module is used to extract the disease target entity from the disease dataset and extract the medicinal material entity from the traditional Chinese medicine dataset using a large language model.

[0075] The disease gene network and medicinal material gene network construction modules are used to construct the disease gene network based on the target entities of each disease and the BarabasPPI network; and to construct the medicinal material gene network based on the target Chinese medicine formula, each medicinal material entity and the BarabasPPI network.

[0076] The similarity calculation module is used to calculate the similarity between the disease gene network and the medicinal material gene network, and the similarity is used to represent the effect of the target traditional Chinese medicine formula on the target disease.

[0077] In an exemplary embodiment, a computer device is provided. The computer device may be a server or a terminal. The internal structure diagram thereof may be as follows: Figure 7As shown. The computer device includes a processor, a memory, an input / output interface (I / O) and a communication interface. The processor, memory and input / output interface are connected via a system bus, and the communication interface is connected to the system bus via the input / output interface. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and computer program in the non-volatile storage medium. The database of the computer device is used to store evaluation data on the effects of traditional Chinese medicine on diseases. The input / output interface of the computer device is used to exchange information between the processor and an external device. The communication interface of the computer device is used to communicate with an external terminal via a network connection. When the computer program is executed by the processor, a method for evaluating the effects of traditional Chinese medicine on diseases is implemented.

[0078] Those skilled in the art will understand that Figure 7 The structure shown in the figure is merely a block diagram of a portion of the structure related to the solution of the present application and does not constitute a limitation on the computer device to which the solution of the present application is applied. A specific computer device may include more or fewer components than shown in the figure, or combine certain components, or have a different component arrangement. In an exemplary embodiment, a computer device is provided, including a memory and a processor. The memory stores a computer program, and the processor implements the steps of the above-mentioned method embodiments when executing the computer program.

[0079] In an exemplary embodiment, a computer-readable storage medium is provided, storing a computer program. When the computer program is executed by a processor, the steps in the above-mentioned method embodiments are implemented.

[0080] In an exemplary embodiment, a computer program product is provided, including a computer program. When the computer program is executed by a processor, the steps in the above method embodiments are implemented.

[0081] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with relevant regulations.

[0082] Those skilled in the art will appreciate that all or part of the processes in the above-mentioned embodiments can be implemented by instructing the relevant hardware through a computer program. The computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the above-mentioned embodiments. In particular, any reference to memory, database, or other media used in the embodiments provided in this application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM may be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM).

[0083] The databases involved in the various embodiments provided herein may include at least one of a relational database and a non-relational database. Non-relational databases may include, but are not limited to, distributed databases based on blockchains. The processors involved in the various embodiments provided herein may be, but are not limited to, general-purpose processors, central processing units, graphics processing units, digital signal processors, data processing logic of programmable logic devices, and the like.

[0084] The technical features of the above embodiments can be combined arbitrarily. To make 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.

[0085] This document uses specific examples to illustrate the principles and implementation methods of this application. The description of the above examples is only intended to help understand the method and core concept of this application. At the same time, for those skilled in the art, based on the concept of this application, there may be changes in the specific implementation methods and application scope. In summary, the content of this specification should not be understood as limiting this application.

Claims

1. A method for evaluating the effect of traditional Chinese medicine on a disease, characterized in that: The evaluation method of the effect of the traditional Chinese medicine on the disease includes: Collect disease symptom datasets and traditional Chinese medicine datasets for target diseases; A large language model is used to extract disease target entities from the disease dataset and medicinal material entities from the traditional Chinese medicine dataset; The disease gene network was constructed based on the target entities of each disease and the Barabas PPI network; the medicinal material gene network was constructed based on the target traditional Chinese medicine formula, each medicinal material entity and the Barabas PPI network; The similarity between the disease gene network and the medicinal material gene network is calculated, and the similarity is used to represent the effect of the target traditional Chinese medicine formula on the target disease.

2. The method for evaluating the effect of traditional Chinese medicine on a disease according to claim 1, wherein The disease gene network was constructed based on the target entities of each disease and the Barabas PPI network; the medicinal material gene network was constructed based on the target Chinese medicine formula, each medicinal material entity and the Barabas PPI network, specifically including: Each disease target entity is converted into a disease gene in a preset gene dictionary, and each disease gene constitutes a disease gene set; each medicinal material entity is converted into a medicinal material in a preset medicinal material dictionary, and the converted medicinal materials constitute a medicinal material set; Calculating a first frequency of occurrence of each disease gene in the disease gene set in the disease dataset, and a second frequency of occurrence of each medicinal material in the medicinal material set in the traditional Chinese medicine dataset; Calculating the weight of each disease gene according to the first frequency corresponding to each disease gene in the disease gene set, and calculating the initial medicinal material weight of each medicinal material according to the second frequency corresponding to each medicinal material in the medicinal material set; Calculating the medicinal material gene weight of each medicinal material gene in the target traditional Chinese medicine formula according to the component proportion of each medicinal material in the target traditional Chinese medicine formula and the initial weight of the medicinal material; The Barabas PPI network is used to filter the disease gene set and the medicinal material gene set corresponding to the medicinal material set respectively. The filtered disease gene set constitutes a disease gene network, and the filtered medicinal material gene set constitutes a medicinal material gene network.

3. The method for evaluating the effect of Chinese medicine on disease according to claim 2, wherein: Each disease target entity is converted into a disease gene in a preset gene dictionary, and each disease gene constitutes a disease gene set. Each medicinal material entity is converted into a medicinal material in a preset medicinal material dictionary, and the converted medicinal materials constitute a medicinal material set, specifically including: Using the edit distance algorithm, each disease target entity is matched with the disease gene with the smallest edit distance in the preset gene dictionary. The disease genes obtained by matching each disease target entity constitute the disease gene set; The edit distance algorithm is used to match each medicinal material entity with the medicinal material with the smallest edit distance in the preset medicinal material dictionary. The medicinal materials obtained by matching each medicinal material entity constitute the medicinal material set.

4. The method for evaluating the effect of Chinese medicine on diseases according to claim 2, wherein According to the component proportion of each medicinal material in the target traditional Chinese medicine formula and the initial weight of the medicinal material, the medicinal material gene weight of each medicinal material gene in the target traditional Chinese medicine formula is calculated, specifically including: the formula for calculating the medicinal material gene weight is: ; ; in, is the medicinal material weight of the target Chinese medicine formula h, is the component ratio of medicinal material h, is the initial medicinal material weight of medicinal material h, is the identifier of the medicinal material gene s in the medicinal material h, =1 means that the medicinal material gene s exists in the medicinal material h, =0 means that the herbal medicine gene s does not exist in the herbal medicine h, and S is the total number of herbal medicine genes in the target Chinese medicine formula; is the medicinal material gene weight of the target Chinese medicine formula Chinese medicine gene s, and H is the number of Chinese medicinal materials in the target Chinese medicine formula.

5. The method for evaluating the effect of Chinese medicine on diseases according to claim 2, wherein: The Barabas PPI network is used to filter the disease gene set and the medicinal material gene set corresponding to the medicinal material set. The filtered disease gene set constitutes a disease gene network, and the filtered medicinal material gene set constitutes a medicinal material gene network, which specifically includes: ; ; in, is the filtered disease gene set, The filtered medicinal material gene set, For the Barabas PPI network, For the disease gene set, A collection of medicinal materials.

6. The method for evaluating the effect of traditional Chinese medicine on diseases according to claim 5, characterized in that: Calculating the similarity between the disease gene network and the medicinal material gene network specifically includes: ; in, is the similarity between the disease gene network and the medicinal material gene network, For genes The weight of medicinal material genes, For genes The disease gene weight, For genes The weight of medicinal material genes, For genes The disease gene weights.

7. A device for evaluating the effect of traditional Chinese medicine on diseases, characterized in that: The device for evaluating the effect of traditional Chinese medicine on a disease applies the method for evaluating the effect of traditional Chinese medicine on a disease according to any one of claims 1 to 6, and the device for evaluating the effect of traditional Chinese medicine on a disease comprises: Data collection module, used to collect symptom datasets and traditional Chinese medicine datasets of target diseases; An entity extraction module, configured to extract disease target entities from the disease dataset and extract medicinal material entities from the traditional Chinese medicine dataset using a large language model; Disease gene network and medicinal material gene network construction modules are used to construct disease gene networks based on target entities of each disease and Barabas PPI network; and to construct medicinal material gene networks based on target traditional Chinese medicine formulas, medicinal material entities and Barabas PPI network; The similarity calculation module is used to calculate the similarity between the disease gene network and the medicinal material gene network, and the similarity is used to represent the effect of the target traditional Chinese medicine formula on the target disease.

8. A computer device comprising: A memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the method for evaluating the effect of traditional Chinese medicine on a disease according to any one of claims 1 to 6.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the method for evaluating the effect of a traditional Chinese medicine on a disease according to any one of claims 1 to 6 is implemented.

10. A computer program product comprising a computer program, characterized in that When the computer program is executed by a processor, the method for evaluating the effect of a traditional Chinese medicine on a disease according to any one of claims 1 to 6 is implemented.

Citation Information

Patent Citations

  • Chinese herbal medicine pharmacology evaluation and analysis system utilizing data evaluation

    CN112885486A

  • Prescription recognition method, device and equipment and storage medium

    CN116364232A

  • Drug combination prediction method and device, electronic equipment and medium

    CN116386760A

  • Disease and gene relationship prediction method and device, electronic equipment and medium

    CN116504317A

  • Traditional Chinese medicine question and answer method, device and equipment based on large language model and medium

    CN119092157A

Cited By

  • Traditional Chinese medicine curative effect evaluation method and device based on node weighted network, equipment and storage medium

    CN121545787A

  • Traditional Chinese medicine efficacy evaluation method and device based on node weighted network, equipment and storage medium

    CN121545787B