WO2021114830A1 - 一种药品发现方法、设备、服务器及可读存储介质 - Google Patents

一种药品发现方法、设备、服务器及可读存储介质 Download PDF

Info

Publication number
WO2021114830A1
WO2021114830A1 PCT/CN2020/118365 CN2020118365W WO2021114830A1 WO 2021114830 A1 WO2021114830 A1 WO 2021114830A1 CN 2020118365 W CN2020118365 W CN 2020118365W WO 2021114830 A1 WO2021114830 A1 WO 2021114830A1
Authority
WO
WIPO (PCT)
Prior art keywords
drug
similarity
various drugs
node
relationship
Prior art date
Application number
PCT/CN2020/118365
Other languages
English (en)
French (fr)
Inventor
顾大中
Original Assignee
平安科技（深圳）有限公司
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 平安科技（深圳）有限公司 filed Critical 平安科技（深圳）有限公司
Publication of WO2021114830A1 publication Critical patent/WO2021114830A1/zh

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
    • G06F16/36—Creation of semantic tools, e.g. ontology or thesauri
    • G06F16/367—Ontology
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/22—Matching criteria, e.g. proximity measures
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F40/00—Handling natural language data
    • G06F40/30—Semantic analysis
    • G—PHYSICS
    • G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
    • G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
    • G16H20/00—ICT specially adapted for therapies or health-improving plans, e.g. for handling prescriptions, for steering therapy or for monitoring patient compliance
    • G16H20/10—ICT specially adapted for therapies or health-improving plans, e.g. for handling prescriptions, for steering therapy or for monitoring patient compliance relating to drugs or medications, e.g. for ensuring correct administration to patients
    • G—PHYSICS
    • G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
    • G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
    • G16H70/00—ICT specially adapted for the handling or processing of medical references
    • G16H70/40—ICT specially adapted for the handling or processing of medical references relating to drugs, e.g. their side effects or intended usage

Definitions

  • This application relates to blockchain technology, which is applied in the field of smart medical care, and in particular to a drug discovery method, equipment, server and readable storage medium.
  • the embodiments of this application provide a drug discovery method, equipment, server and readable storage medium, which can reduce knowledge during drug discovery. Reliance on the library improves the efficiency of drug discovery.
  • an embodiment of the present application provides a drug discovery method, including: obtaining a predetermined knowledge base of drugs and diseases, the knowledge base including a drug set, a disease set, and a treatment relationship set, and the treatment relationship set includes The relationship between multiple diseases and drugs; calculate the characterization vector of each drug in the knowledge base, and the characterization vector is determined according to the semantic information of each drug; calculate the characterization vector of each drug according to the characterization vector of each drug According to the similarity between each drug, the drug relationship diagram is constructed according to the similarity between the various drugs; the specified drug corresponding to the specified disease is determined according to the treatment relationship database in the knowledge base, and the drug relationship is determined according to the drug relationship diagram. Describe the target drug set corresponding to the specified drug.
  • an embodiment of the present application provides a drug discovery device, which includes a unit for executing the drug discovery method of the first aspect.
  • an embodiment of the present invention provides a server, including a processor, an input device, an output device, and a memory.
  • the processor, the input device, the output device, and the memory are connected to each other, wherein the memory is used for storage and support.
  • a computer program for the drug discovery device to execute the above method includes a program, the processor is configured to call the program, wherein: a preset knowledge base of drugs and diseases is obtained, and the knowledge base includes a collection of drugs A set of diseases and a set of treatment relationships, the set of treatment relationships includes the relationship between multiple diseases and drugs; calculating the characterization vector of each drug in the knowledge base, the characterization vector being determined according to the semantic information of each drug; Calculate the similarity between the various drugs according to the characterization vector of the various drugs, and construct a drug relationship graph according to the similarity between the various drugs; determine the corresponding disease according to the treatment relationship database in the knowledge base And determine the target drug set corresponding to the designated drug according to the drug relationship diagram.
  • an embodiment of the present invention provides a computer-readable storage medium, the computer-readable storage medium stores a computer program, and the computer program is executed by a processor to implement the following steps: Obtain preset medicines and diseases
  • the knowledge base includes a drug set, a disease set, and a treatment relationship set, and the treatment relationship set includes a relationship between multiple diseases and drugs;
  • the characterization vector of each drug in the knowledge base is calculated, and the characterization vector is Determined according to the semantic information of each drug; calculate the similarity between the various drugs according to the characterization vector of the various drugs, and construct a drug relationship graph according to the similarity between the various drugs; according to the knowledge
  • the treatment relationship library in the library determines a designated drug corresponding to a designated disease, and determines a target drug set corresponding to the designated drug according to the drug relationship graph.
  • Fig. 1 is a schematic flowchart of a drug discovery method provided by an embodiment of the present application.
  • Figure 2 is a schematic diagram of a drug relationship diagram provided by an embodiment of the present application.
  • Fig. 3 is a schematic diagram of another drug relationship diagram provided by an embodiment of the present application.
  • Fig. 4 is a schematic block diagram of a drug discovery device provided by an embodiment of the present application.
  • Fig. 5 is a schematic block diagram of a server provided by an embodiment of the present application.
  • the drug discovery method provided by the embodiment of the application can be executed by a drug discovery device, wherein the drug discovery device can be set on a server.
  • the drug discovery device may be installed on a server; in some embodiments, the drug discovery device may be spatially independent of the server; in some embodiments, the drug discovery device may be The discovery device may be a component of the server, that is, the server includes a drug discovery device.
  • the solution can be applied in the field of smart medical care, thereby promoting the construction of smart cities.
  • the drug discovery device can obtain a preset knowledge base of drugs and diseases, and calculate the characterization vector of each drug in the knowledge base, and calculate the similarity between the various drugs according to the characterization vector of each drug, and according to Constructing a drug relationship graph based on the similarity between the various drugs, determining the designated drug corresponding to the specified disease according to the treatment relationship database in the knowledge base, and determining the target corresponding to the designated drug based on the drug relationship graph Medicine collection.
  • the dependence on the knowledge base during drug discovery can be reduced, and the efficiency of drug discovery can be improved.
  • FIG. 1 is a schematic flowchart of a drug discovery method provided by an embodiment of the present application. As shown in FIG. 1, the method can be executed by a drug discovery device. The specific explanation of the drug discovery device is as described above. I will not repeat them here. Specifically, the method of the embodiment of the present application includes the following steps S101-S104.
  • S101 Acquire a preset knowledge base of medicines and diseases, where the knowledge base includes a medicine set, a disease set, and a treatment relationship set, and the treatment relationship set includes a relationship between multiple diseases and drugs.
  • the drug discovery device can obtain a preset knowledge base of drugs and diseases, the knowledge base includes a drug set, a disease set, and a treatment relationship set, and the treatment relationship set includes a relationship between multiple diseases and drugs.
  • the predetermined knowledge base of drugs and diseases may be obtained from a public database.
  • the relationship between multiple diseases and drugs included in the treatment relationship set is used to indicate that one or more drugs treat a certain disease.
  • the drug set is ⁇ captopril, metformin ⁇ .
  • the disease set is ⁇ hypertension, diabetes ⁇ .
  • the treatment relationship set is ⁇ metformin->diabetes, captopril->diabetes ⁇ , in the treatment relationship “metformin->diabetes” is used to indicate that metformin is used to treat diabetes, and the “card Topril -> Diabetes” is used to indicate that Captopril is used to treat diabetes.
  • S102 Calculate the characterization vector of each medicine in the knowledge base, where the characterization vector is determined according to the semantic information of each medicine.
  • the drug discovery device may calculate the characterization vector of each drug in the knowledge base, and the characterization vector is determined according to the semantic information of each drug.
  • the characterization vector may be a high-dimensional vector, generally between 100-1000 dimensions; in some embodiments, each element in the characterization vector may be a real number.
  • the representation vector contains the corresponding semantic information of each medicine to a certain extent, and is used to reflect the description of each medicine.
  • the drug discovery device when the drug discovery device calculates the characterization vector of each drug in the knowledge base, it can obtain the semantic information of each drug in the knowledge base, and calculate the knowledge base based on the semantic information of each drug.
  • the drug discovery device when it calculates the characterization vector of each drug in the knowledge base, it can obtain the constituents of each drug in the knowledge base, and obtain the semantic information of the constituents of each drug, and The characterization vector of each drug in the knowledge base is calculated according to the semantic information of the constituent components of each drug.
  • the drug discovery device may use word2vec technology to calculate the characterization vector of each drug in the knowledge base.
  • the word2vec is based on a large amount of text, and calculates the characterization vector of the word (or phrase) in the text, and the characterization vector reflects the semantic information of the word.
  • S103 Calculate the similarity between the various drugs according to the characterization vector of the various drugs, and construct a drug relationship graph according to the similarity between the various drugs.
  • the drug discovery device calculates the similarity between the various drugs according to the characterization vector of the various drugs, and constructs a drug relationship graph according to the similarity between the various drugs.
  • the drug discovery device when it calculates the similarity between each drug according to the characterization vector of each drug, it may calculate the difference between the characterization vector of each drug according to the characterization vector of each drug. Euclidean distance, and determine the similarity between the respective medicines according to the Euclidean distance between the characterization vectors of the respective medicines.
  • the drug discovery device when it calculates the similarity between each drug according to the characterization vector of each drug, it may calculate the difference between the characterization vector of each drug according to the characterization vector of each drug.
  • the included angle, and the similarity between the respective medicines is determined according to the included angle between the characterization vectors of the respective medicines.
  • the embodiment of the present application may also use other methods to calculate the similarity between the various drugs, which is not specifically limited herein.
  • the drug discovery device when the drug discovery device constructs a drug relationship graph based on the similarity between the various drugs, it can determine whether the similarity between any two drugs is greater than the similarity between the various drugs. A preset similarity threshold, and if the judgment result is yes, it can be determined to connect the medicines with the similarity greater than the preset similarity threshold in pairs to construct the medicine relationship graph.
  • the drug discovery device when the drug discovery device determines that the drugs whose similarity is greater than the preset similarity threshold are connected in pairs, it can pass between the drugs whose similarity is greater than the preset similarity threshold. Line segment connection.
  • the drug discovery device may construct the drug relationship graph in descending order according to the magnitude of the similarity when constructing the drug relationship graph.
  • the above-mentioned drug collection, disease collection, and treatment relationship collection can also be stored in a blockchain node.
  • Figure 2 is used as an example to illustrate.
  • Figure 2 is a schematic diagram of a drug relationship diagram provided by an embodiment of the present application. As shown in Figure 2, drugs with similarity greater than a preset similarity threshold are used as nodes to construct and obtain the following Figure 2 shows the drug relationship diagram.
  • S104 Determine a designated drug corresponding to a designated disease according to the treatment relationship database in the knowledge base, and determine a target drug set corresponding to the designated drug according to the drug relationship graph.
  • the drug discovery device may determine the designated drug corresponding to the designated disease according to the treatment relationship library in the knowledge base, and determine the target drug set corresponding to the designated drug according to the drug relationship graph.
  • the designated disease may be diabetes
  • the designated drug may be metformin for the treatment of diabetes.
  • the drug discovery device when it determines the target drug set corresponding to the specified drug according to the drug relationship graph, it may determine the node where the specified drug is located from the drug relationship graph, and then determine the node where the specified drug is located according to the drug relationship graph.
  • the drug relationship graph determines that each child node of the node where the specified drug is located is an associated drug set associated with the specified drug, and determines the node according to the weight of each drug in the associated drug set.
  • the set of target medicines whose weight is greater than the preset weight threshold.
  • the drug discovery device can determine that the child nodes of the node where the metformin is located are nivolumab, flumethenin, and metformin according to the drug relationship diagram shown in Figure 2.
  • the set of related drugs related to metformin assuming that the weight of the node where nivolumab is located is x1, the weight of the node where flumethene is located is x2, the weight of the node where metformin is located is x3, The weight of the node where captopril is located is x4, the weight of the node where endrozine is located is x5, and the weight of the node where kadrozine is located is x6. If the x1, x2, x3, x4 are greater than the preset The weight threshold y can determine that the nivolumab, flumezine, dimethyltiazine, and captopril are the target drug set.
  • the related drug set associated with the specified drug can be screened from the preset drug and disease knowledge base, which helps to subsequently determine the target drug set with a strong correlation from the related drug set. .
  • the drug discovery device may calculate the related drug set when determining the target drug set whose weight is greater than a preset weight threshold according to the weight of each drug in the related drug set. And determine the target drug set with the weight greater than the preset weight threshold according to the weight of the node where each drug in the associated drug set is located, and determine the target drug set The drug in is the target drug for the treatment of the specified disease. It can be seen that by calculating the weight of each node, the target drug corresponding to the node with a strong correlation can be determined.
  • the drug discovery device when it calculates the weight of the node where each drug in the related drug set is located, it can compare each drug in the related drug set associated with the specified drug in the drug relationship graph.
  • the node where the drug is located is assigned the first energy
  • other nodes in the drug relationship graph except the node where each drug in the associated drug set is located are assigned the second energy, and according to each node in the drug relationship graph
  • the first energy and the second energy of use a specified algorithm to calculate the weight of the node where each drug in the associated drug set in the drug relationship graph is located.
  • the specified algorithm includes, but is not limited to, a graph propagation algorithm.
  • the first energy and the second energy are not the same, and the first energy and the second energy may be represented by characters such as numbers, letters, and colors; in one example, the first energy The energy can be 1, and the second energy can be 0; in another example, the first energy can be green, and the second energy can be red.
  • FIG. 3 as an example, which is an implementation of this application.
  • the example provides a schematic diagram of another drug relationship diagram. In the drug relationship diagram shown in FIG. 3, the first energy is gray and the second energy is white.
  • the drugs with the same color in the drug relationship diagram are related drugs for treating the same disease.
  • the drug discovery device can obtain a preset knowledge base of drugs and diseases, and calculate the characterization vector of each drug in the knowledge base, and calculate the relationship between each drug according to the characterization vector of each drug.
  • a drug relationship diagram is constructed according to the similarity between the various drugs, and the specified drug corresponding to the specified disease is determined according to the treatment relationship database in the knowledge base, and the drug relationship is determined according to the drug relationship diagram. Describe the target drug set corresponding to the specified drug.
  • Fig. 4 is a schematic block diagram of a drug discovery device provided by an embodiment of the present application.
  • the drug discovery device of this embodiment includes: an acquisition unit 401, a calculation unit 402, a construction unit 403, and a determination unit 404.
  • the acquiring unit 401 is configured to acquire a preset knowledge base of medicines and diseases.
  • the knowledge base includes a medicine set, a disease set, and a treatment relationship set, and the treatment relationship set includes a relationship between multiple diseases and medicines.
  • the calculation unit 402 is configured to calculate a characterization vector of each medicine in the knowledge base, and the characterization vector is determined according to the semantic information of each medicine.
  • the constructing unit 403 is configured to calculate the similarity between the respective medicines according to the characterization vector of the respective medicines, and construct a medicine relationship graph according to the similarity between the respective medicines.
  • the determining unit 404 is configured to determine a designated drug corresponding to a designated disease according to the treatment relationship library in the knowledge base, and determine a target drug set corresponding to the designated drug according to the drug relationship graph.
  • the construction unit 403 calculates the similarity between the respective medicines according to the characterization vectors of the respective medicines, it is specifically configured to: calculate the difference between the characterization vectors of the respective medicines according to the characterization vectors of the respective medicines.
  • the Euclidean distance; the degree of similarity between the various drugs is determined according to the Euclidean distance between the characterization vectors of the various drugs.
  • the construction unit 403 calculates the similarity between the respective medicines according to the characterization vectors of the respective medicines, it is specifically configured to: calculate the difference between the characterization vectors of the respective medicines according to the characterization vectors of the respective medicines.
  • the included angle of each drug is determined according to the included angle between the characterization vectors of each drug.
  • the constructing unit 403 constructs the drug relationship graph according to the similarity between the various drugs, it is specifically used to determine whether the similarity between any two drugs is based on the similarity between the various drugs. Greater than the preset similarity threshold; if the judgment result is yes, it is determined to connect the drugs with the similarity greater than the preset similarity threshold pairwise to construct the drug relationship graph.
  • the determining unit 404 determines the target drug set corresponding to the designated drug according to the drug relationship graph, it is specifically configured to: determine the node where the designated drug is located from the drug relationship graph; The drug relationship graph determines that each child node of the node where the specified drug is located is an associated drug set associated with the specified drug; determines the right according to the weight of the node where each drug in the associated drug set is located.
  • the set of target medicines whose value is greater than the preset weight threshold.
  • the determining unit 404 determines the target drug set whose weight is greater than a preset weight threshold according to the weight of the node where each drug in the associated drug set is located, it is specifically used to: calculate the associated drug The weight of the node where each drug in the set is located; according to the weight of the node where each drug in the associated drug set is located, determine the target drug set whose weight is greater than a preset weight threshold, and determine the target drug set The drug in is the target drug for the treatment of the specified disease.
  • the determining unit 404 calculates the weight of the node where each drug in the associated drug set is located, it is specifically used to: compare each of the associated drug sets in the drug relationship graph that is associated with the specified drug.
  • the node where the drug is located is assigned the first energy; the node in the drug relationship graph except the node where each drug in the associated drug set is located is assigned the second energy; according to the value of each node in the drug relationship graph
  • the first energy and the second energy are calculated by using a specified algorithm to calculate the weight of the node where each drug in the associated drug set in the drug relationship graph is located.
  • the drug discovery device can obtain a preset knowledge base of drugs and diseases, and calculate the characterization vector of each drug in the knowledge base, and calculate the relationship between each drug according to the characterization vector of each drug.
  • a drug relationship diagram is constructed according to the similarity between the various drugs, and the specified drug corresponding to the specified disease is determined according to the treatment relationship database in the knowledge base, and the drug relationship is determined according to the drug relationship diagram. Describe the target drug set corresponding to the specified drug.
  • the above-mentioned drug collection, disease collection, and treatment relationship collection can also be stored in a blockchain node.
  • FIG. 5 is a schematic block diagram of a server according to an embodiment of the present application.
  • the server in this embodiment as shown in the figure may include: one or more processors 501; one or more input devices 502, one or more output devices 503, and a memory 504.
  • the aforementioned processor 501, input device 502, output device 503, and memory 504 are connected via a bus 505.
  • the memory 504 is configured to store a computer program, and the computer program includes a program, and the processor 501 is configured to execute the program stored in the memory 504.
  • the processor 501 is configured to call the program to execute: obtain a preset knowledge base of medicines and diseases, the knowledge base including a medicine set, a disease set, and a treatment relationship set, and the treatment relationship set includes multiple diseases.
  • Relationship with drugs calculate the characterization vector of each drug in the knowledge base, the characterization vector is determined according to the semantic information of each drug; calculate the similarity between each drug according to the characterization vector of each drug And construct a drug relationship diagram according to the similarity between the various drugs; determine the specified drug corresponding to the specified disease according to the treatment relationship database in the knowledge base, and determine the drug relationship with the specified drug according to the drug relationship diagram The corresponding target drug collection.
  • the processor 501 calculates the similarity between the respective medicines according to the characterization vectors of the respective medicines, it is specifically configured to: calculate the difference between the characterization vectors of the respective medicines according to the characterization vectors of the respective medicines.
  • the Euclidean distance; the degree of similarity between the various drugs is determined according to the Euclidean distance between the characterization vectors of the various drugs.
  • the processor 501 calculates the similarity between the respective medicines according to the characterization vectors of the respective medicines, it is specifically configured to: calculate the difference between the characterization vectors of the respective medicines according to the characterization vectors of the respective medicines.
  • the included angle of each drug is determined according to the included angle between the characterization vectors of each drug.
  • the processor 501 constructs a drug relationship graph according to the similarity between the various drugs, it is specifically used to determine whether the similarity between any two drugs is based on the similarity between the various drugs. Greater than the preset similarity threshold; if the judgment result is yes, it is determined to connect the drugs with the similarity greater than the preset similarity threshold pairwise to construct the drug relationship graph.
  • the processor 501 determines the target drug set corresponding to the designated drug according to the drug relationship graph, it is specifically configured to: determine the node where the designated drug is located from the drug relationship graph; The drug relationship graph determines that each child node of the node where the specified drug is located is an associated drug set associated with the specified drug; determines the right according to the weight of the node where each drug in the associated drug set is located.
  • the set of target medicines whose value is greater than the preset weight threshold.
  • the processor 501 determines the target drug set whose weight is greater than a preset weight threshold according to the weight of the node where each drug in the associated drug set is located, it is specifically configured to: calculate the associated drug The weight of the node where each drug in the set is located; according to the weight of the node where each drug in the associated drug set is located, determine the target drug set whose weight is greater than a preset weight threshold, and determine the target drug set The drug in is the target drug for the treatment of the specified disease.
  • the processor 501 calculates the weight of the node where each drug in the associated drug set is located, it is specifically used to: compare each of the associated drug sets in the drug relationship graph that is associated with the specified drug.
  • the node where the drug is located is assigned the first energy; the node in the drug relationship graph except the node where each drug in the associated drug set is located is assigned the second energy; according to the value of each node in the drug relationship graph
  • the first energy and the second energy are calculated by using a specified algorithm to calculate the weight of the node where each drug in the associated drug set in the drug relationship graph is located.
  • the server can obtain a preset knowledge base of medicines and diseases, and calculate the characterization vector of each medicine in the knowledge base, and calculate the similarity between each medicine according to the characterization vector of each medicine.
  • a drug relationship diagram is constructed, and the specified drug corresponding to the specified disease is determined according to the treatment relationship database in the knowledge base, and the drug relationship with the specified drug is determined according to the drug relationship diagram.
  • the target drug collection corresponding to the drug can be improved.
  • the processor 501 may be a central processing unit (CenSral Processing UniS, CPU), and the processor may also be other general-purpose processors or digital signal processors (DigiSal Signal Processor, DSP). , Application-specific integrated circuits (ApplicaSion Specific InSegraSed Circuits, ASIC), ready-made programmable gate arrays (Field-Programmable GaSe Array, FPGA) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components, etc.
  • the general-purpose processor may be a microprocessor or the processor may also be any conventional processor or the like.
  • the input device 502 may include a touch panel, a microphone, etc.
  • the output device 503 may include a display (LCD, etc.), a speaker, and the like.
  • the memory 504 may include a read-only memory and a random access memory, and provides instructions and data to the processor 501. A part of the memory 504 may also include a non-volatile random access memory. For example, the memory 504 may also store device type information.
  • processor 501, input device 502, and output device 503 described in the embodiment of this application can execute the implementation described in the method embodiment shown in FIG.
  • the implementation of the drug discovery device described in FIG. 4 of the application embodiment will not be repeated here.
  • the embodiment of the present application also provides a computer-readable storage medium, the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the drug discovery method described in the embodiment corresponding to FIG. 1 is implemented , The drug discovery device of the embodiment corresponding to FIG. 4 of the present application can also be implemented, which will not be repeated here.
  • the computer-readable storage medium may be non-volatile or volatile.
  • the computer-readable storage medium may be the internal storage unit of the drug discovery device described in any of the foregoing embodiments, such as the hard disk or memory of the drug discovery device.
  • the computer-readable storage medium may also be an external storage device of the drug discovery device, such as a plug-in hard disk equipped on the drug discovery device, a smart memory card (SmarS Media Card, SMC), and a secure digital (Secure DigiSal) ,SD) card, flash card (Flash Card), etc.
  • the computer-readable storage medium may also include both an internal storage unit of the drug discovery device and an external storage device.
  • the computer-readable storage medium is used to store the computer program and other programs and data required by the drug discovery device.
  • the computer-readable storage medium can also be used to temporarily store data that has been output or will be output.
  • the computer-readable storage medium may mainly include a storage program area and a storage data area, where the storage program area may store an operating system, an application program required by at least one function, etc.; the storage data area may store Data created by the use of nodes, etc.
  • the blockchain referred to in this application is a new application mode of computer technology such as distributed data storage, point-to-point transmission, consensus mechanism, and encryption algorithm.
  • Blockchain essentially a decentralized database, is a series of data blocks associated with cryptographic methods. Each data block contains a batch of network transaction information for verification. The validity of the information (anti-counterfeiting) and the generation of the next block.
  • the blockchain can include the underlying platform of the blockchain, the platform product service layer, and the application service layer.
  • the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer readable storage medium.
  • the read storage medium includes several instructions to enable a computer device (which may be a personal computer, a terminal, or a network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present application.
  • the aforementioned computer-readable storage media include: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), magnetic disks or optical disks and other various programs that can store programs The medium of the code.

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Health & Medical Sciences (AREA)
  • Physics & Mathematics (AREA)
  • Data Mining & Analysis (AREA)
  • General Health & Medical Sciences (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • General Physics & Mathematics (AREA)
  • General Engineering & Computer Science (AREA)
  • Primary Health Care (AREA)
  • Epidemiology (AREA)
  • Computational Linguistics (AREA)
  • Public Health (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Chemical & Material Sciences (AREA)
  • Medicinal Chemistry (AREA)
  • Medical Informatics (AREA)
  • Artificial Intelligence (AREA)
  • Evolutionary Computation (AREA)
  • Toxicology (AREA)
  • Pharmacology & Pharmacy (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Animal Behavior & Ethology (AREA)
  • Evolutionary Biology (AREA)
  • Databases & Information Systems (AREA)
  • Audiology, Speech & Language Pathology (AREA)
  • Medical Treatment And Welfare Office Work (AREA)

Abstract

一种药品发现方法，该方法包括：获取预设的药品与疾病的知识库，所述知识库包括药品集合、疾病集合、治疗关系集合，所述治疗关系集合包括多个疾病与药品的关系（S101）；计算所述知识库中各个药品的表征向量，所述表征向量是根据所述各个药品的语义信息确定的（S102）；根据所述各个药品的表征向量计算所述各个药品之间的相似度，并根据所述各个药品之间的相似度构建药品关系图（S103）；根据所述知识库中的治疗关系库确定与指定疾病对应的指定药品，并根据所述药品关系图确定与所述指定药品对应的目标药品集合（（S104））。该方法可以降低药品发现时对知识库的依赖，提高药品发现的效率，还可以将所述药品集合、疾病集合、治疗关系集合存储于区块链中。

Description

一种药品发现方法、设备、服务器及可读存储介质
本申请要求于2020年05月13日提交中国专利局、申请号为202010404943.6、申请名称为“一种药品发现方法、设备、服务器及可读存储介质”的中国专利申请的优先权，其全部内容通过引用结合在本申请中。
技术领域
本申请涉及区块链技术，应用于智慧医疗领域中，尤其涉及一种药品发现方法、设备、服务器及可读存储介质。
背景技术
目前，发明人发现，传统的制药业在研究新药的时候，需要对大量的物质做实验，从而筛选出真正能治病的物质，犹如大海捞针。这样的新药发现技术高度依赖复杂的知识库(如药物的化学结构、分子空间结构、与基因的靶向关系等)，且构建知识库的成本很高。
发明内容
基于现有的新药发现技术高度依赖复杂的知识库，且药品发现的效率低的问题，本申请实施方式提供一种药品发现方法、设备、服务器及可读存储介质，可以降低药品发现时对知识库的依赖，提高药品发现的效率。
第一方面，本申请实施例提供了一种药品发现方法，包括：获取预设的药品与疾病的知识库，所述知识库包括药品集合、疾病集合、治疗关系集合，所述治疗关系集合包括多个疾病与药品的关系；计算所述知识库中各个药品的表征向量，所述表征向量是根据所述各个药品的语义信息确定的；根据所述各个药品的表征向量计算所述各个药品之间的相似度，并根据所述各个药品之间的相似度构建药品关系图；根据所述知识库中的治疗关系库确定与指定疾病对应的指定药品，并根据所述药品关系图确定与所述指定药品对应的目标药品集合。
第二方面，本申请实施例提供了一种药品发现设备，该药品发现设备包括用于执行上述第一方面的药品发现方法的单元。
第三方面，本发明实施例提供了一种服务器，包括处理器、输入设备、输出设备和存储器，所述处理器、输入设备、输出设备和存储器相互连接，其中，所述存储器用于存储支持药品发现设备执行上述方法的计算机程序，所述计算机程序包括程序，所述处理器被配置用于调用所述程序，其中：获取预设的药品与疾病的知识库，所述知识库包括药品集合、疾病集合、治疗关系集合，所述治疗关系集合包括多个疾病与药品的关系；计算所述知识库中各个药品的表征向量，所述表征向量是根据所述各个药品的语义信息确定的；根据所述各个药品的表征向量计算所述各个药品之间的相似度，并根据所述各个药品之间的相似度构建药品关系图；根据所述知识库中的治疗关系库确定与指定疾病对应的指定药品，并根据所述药品关系图确定与所述指定药品对应的目标药品集合。
第四方面，本发明实施例提供了一种计算机可读存储介质，所述计算机可读存储介质存储有计算机程序，所述计算机程序被处理器执行以实现以下步骤：获取预设的药品与疾病的知识库，所述知识库包括药品集合、疾病集合、治疗关系集合，所述治疗关系集合包 括多个疾病与药品的关系；计算所述知识库中各个药品的表征向量，所述表征向量是根据所述各个药品的语义信息确定的；根据所述各个药品的表征向量计算所述各个药品之间的相似度，并根据所述各个药品之间的相似度构建药品关系图；根据所述知识库中的治疗关系库确定与指定疾病对应的指定药品，并根据所述药品关系图确定与所述指定药品对应的目标药品集合。
本申请实施例，通过获取预设的药品与疾病的知识库，并计算所述知识库中各个药品的表征向量，以及根据所述各个药品的表征向量计算所述各个药品之间的相似度，并根据所述各个药品之间的相似度构建药品关系图，以及根据所述知识库中的治疗关系库确定与指定疾病对应的指定药品，并根据所述药品关系图确定与所述指定药品对应的目标药品集合，可以降低药品发现时对知识库的依赖，提高药品发现的效率。
附图说明
图1是本申请实施例提供的一种药品发现方法的示意流程图。
图2是本申请实施例提供的一种药品关系图的示意图。
图3是本申请实施例提供的另一种药品关系图的示意图。
图4是本申请实施例提供的一种药品发现设备的示意框图。
图5是本申请实施例提供的一种服务器的示意框图。
具体实施方式
本申请实施例提供的药品发现方法可以由一种药品发现设备执行，其中，所述药品发现设备可以设置在服务器上。在某些实施例中，所述药品发现设备可以安装在服务器上；在某些实施例中，所述药品发现设备可以在空间上独立于所述服务器；在某些实施例中，所述药品发现设备可以是所述服务器的部件，即所述服务器包括药品发现设备。
本申请实施例中，本方案可应用于智慧医疗领域中，从而推动智慧城市的建设。药品发现设备可以获取预设的药品与疾病的知识库，并计算所述知识库中各个药品的表征向量，以及根据所述各个药品的表征向量计算所述各个药品之间的相似度，并根据所述各个药品之间的相似度构建药品关系图，以及根据所述知识库中的治疗关系库确定与指定疾病对应的指定药品，并根据所述药品关系图确定与所述指定药品对应的目标药品集合。通过这种实施方式可以降低药品发现时对知识库的依赖，提高药品发现的效率。
下面结合附图对本申请实施例的药品发现方法进行示意性说明。
请参见图1，图1是本申请实施例提供的一种药品发现方法的示意流程图，如图1所示，该方法可以由药品发现设备执行，所述药品发现设备的具体解释如前所述，此处不再赘述。具体地，本申请实施例的所述方法包括如下步骤S101-S104。
S101：获取预设的药品与疾病的知识库，所述知识库包括药品集合、疾病集合、治疗关系集合，所述治疗关系集合包括多个疾病与药品的关系。
本申请实施例中，药品发现设备可以获取预设的药品与疾病的知识库，所述知识库包括药品集合、疾病集合、治疗关系集合，所述治疗关系集合包括多个疾病与药品的关系。在某些实施例中，所述预设的药品与疾病的知识库可以是从公开的数据库中获取到的。在 某些实施例中，所述治疗关系集合中包括的多个疾病与药品的关系用于指示一种或多种药品治疗某种疾病。
在一个示例中，所述药品集合为{卡托普利、二甲双胍}。在一个示例中，所述疾病集合为{高血压、糖尿病}。在一个示例中，所述治疗关系集合为{二甲双胍->糖尿病，卡托普利->糖尿病}，所述治疗关系中“二甲双胍->糖尿病”用于指示二甲双胍用于治疗糖尿病，所述“卡托普利->糖尿病”用于指示卡托普利用于治疗糖尿病。
S102：计算所述知识库中各个药品的表征向量，所述表征向量是根据所述各个药品的语义信息确定的。
本申请实施例中，药品发现设备可以计算所述知识库中各个药品的表征向量，所述表征向量是根据所述各个药品的语义信息确定的。在某些实施例中，所述表征向量可以是一个高维向量，一般100-1000维之间；在某些实施例中，所述表征向量中的每个元素可以是实数。在某些实施例中，所述表征向量在一定程度上包含了对应的各个药品的语义信息，用于反映对各个药品的描述。
在一个实施例中，药品发现设备在计算所述知识库中各个药品的表征向量时，可以获取所述知识库中各个药品的语义信息，并根据所述各个药品的语义信息计算所述知识库中各个药品的表征向量。
在一个实施例中，药品发现设备在计算所述知识库中各个药品的表征向量时，可以获取所述知识库中各个药品的组成成分，并获取所述各个药品的组成成分的语义信息，并根据所述各个药品的组成成分的语义信息计算所述知识库中各个药品的表征向量。
在一个实施例中，药品发现设备可以利用word2vec技术计算所述知识库中各个药品的表征向量。在某些实施例中，所述word2vec是基于大量文本，计算文本中单词(或词组)的表征向量，所述表征向量反映了单词的语义信息。
S103：根据所述各个药品的表征向量计算所述各个药品之间的相似度，并根据所述各个药品之间的相似度构建药品关系图。
本申请实施例中，药品发现设备根据所述各个药品的表征向量计算所述各个药品之间的相似度，并根据所述各个药品之间的相似度构建药品关系图。
在一个实施例中，药品发现设备在根据所述各个药品的表征向量计算所述各个药品之间的相似度时，可以根据所述各个药品的表征向量计算所述各个药品的表征向量之间的欧式距离，并根据所述各个药品的表征向量之间的欧式距离确定所述各个药品之间的相似度。
在一个实施例中，药品发现设备在根据所述各个药品的表征向量计算所述各个药品之间的相似度时，可以根据所述各个药品的表征向量计算所述各个药品的表征向量之间的夹角，并根据所述各个药品的表征向量之间的夹角确定所述各个药品之间的相似度。在其他实施例中，本申请实施例还可以采用其他方式计算所述各个药品之间的相似度，在此不做具体限定。
在一个实施例中，药品发现设备在根据所述各个药品之间的相似度构建药品关系图时，可以根据所述各个药品之间的相似度，判断任意两个药品之间的相似度是否大于预设相似 度阈值，如果判断结果为是，则可以确定将所述相似度大于所述预设相似度阈值的药品两两连接，以构建得到所述药品关系图。
在一个实施例中，所述药品发现设备在确定将所述相似度大于所述预设相似度阈值的药品两两连接时，可以在相似度大于所述预设相似度阈值的药品之间通过线段连接。在一个实施例中，药品发现设备在构建药品关系图时可以根据所述相似度的大小，以从高到低的顺序构建药品关系图。
需要强调的是，为进一步保证上述药品集合、疾病集合、治疗关系集合的私密和安全性，上述药品集合、疾病集合、治疗关系集合还可以存储于一区块链的节点中。
具体可以图2为例进行说明，图2是本申请实施例提供的一种药品关系图的示意图，如图2所示，以相似度大于预设相似度阈值的药品为节点，以构建得到如图2所示的药品关系图。
S104：根据所述知识库中的治疗关系库确定与指定疾病对应的指定药品，并根据所述药品关系图确定与所述指定药品对应的目标药品集合。
本申请实施例中，药品发现设备可以根据所述知识库中的治疗关系库确定与指定疾病对应的指定药品，并根据所述药品关系图确定与所述指定药品对应的目标药品集合。在一个示例中，所述指定疾病可以为糖尿病，所述指定药品可以为用于治疗糖尿病的二甲双胍。
在一个实施例中，药品发现设备在根据所述药品关系图确定与所述指定药品对应的目标药品集合时，可以从所述药品关系图中确定所述指定药品所处的节点，并根据所述药品关系图确定所述指定药品所处的节点的各个子节点为与所述指定药品相关联的关联药品集合，以及根据所述关联药品集合中各个药品所处节点的权值，确定所述权值大于预设权值阈值的目标药品集合。
以图2为例，假设指定药品为二甲双胍，则药品发现设备可以根据如图2所示的药品关系图确定二甲双胍所处的节点的各个子节点为纳武单抗、氟美烯烔、二甲替嗪、卡托普利、恩屈嗪、卡屈嗪，从而可以确定{纳武单抗、氟美烯烔、二甲替嗪、卡托普利、恩屈嗪、卡屈嗪}为与二甲双胍相关联的关联药品集合，假设所述纳武单抗所处节点的权值为x1、氟美烯烔所处节点的权值为x2、二甲替嗪所处节点的权值为x3、卡托普利所处节点的权值为x4、恩屈嗪所处节点的权值为x5、卡屈嗪所处节点的权值为x6，如果所述x1、x2、x3、x4大于预设权值阈值y，则可以确定所述纳武单抗、氟美烯烔、二甲替嗪、卡托普利为目标药品集合。
可见，通过这种实施方式可以从预设的药品与疾病的知识库中筛选出与指定药品相关联的关联药品集合，有助于后续从关联药品集合中确定出关联性较强的目标药品集合。
在一个实施例中，药品发现设备在根据所述关联药品集合中各个药品所处节点的权值，确定所述权值大于预设权值阈值的目标药品集合时，可以计算所述关联药品集合中各个药品所处节点的权值，并根据所述关联药品集合中各个药品所处节点的权值，确定所述权值大于预设权值阈值的目标药品集合，并确定所述目标药品集合中的药品为用于治疗所述指定疾病的目标药品。可见，通过计算各个节点的权值，可以确定出关联性较强的节点对应 的目标药品。
在一个实施例中，药品发现设备在计算所述关联药品集合中各个药品所处节点的权值时，可以将所述药品关系图中与所述指定药品相关联的关联药品集合中的各个药品所处的节点赋予第一能量，并将所述药品关系图中除所述关联药品集合中的各个药品所处的节点以外的其他节点赋予第二能量，以及根据所述药品关系图中各个节点的第一能量和第二能量，利用指定算法计算所述药品关系图中所述关联药品集合中各个药品所处节点的权值。在某些实施例中，所述指定算法包括但不限于图传播算法。
在某些实施例中，所述第一能量和所述第二能量不相同，所述第一能量和第二能量可以用数字、字母、颜色等字符表示；在一个示例中，所述第一能量可以为1，所述第二能量可以为0；在另一个示例中，所述第一能量可以为绿色，所述第二能量可以为红色，以图3为例，图3是本申请实施例提供的另一种药品关系图的示意图，如图3所示的药品关系图中，第一能量为灰色、第二能量为白色。在某些实施例中，所述药品关系图中相同颜色的药品为治疗相同疾病的关联药物。
可见，通过这种实施方式，可以根据药品关系图中各个药品的权值，从关联药品集合中确定出关联性较强的目标药品集合，避免直接从预设的药品与疾病的知识库中查询目标药品集合，提高了药品发现的效率。
本申请实施例中，药品发现设备可以获取预设的药品与疾病的知识库，并计算所述知识库中各个药品的表征向量，以及根据所述各个药品的表征向量计算所述各个药品之间的相似度，并根据所述各个药品之间的相似度构建药品关系图，以及根据所述知识库中的治疗关系库确定与指定疾病对应的指定药品，并根据所述药品关系图确定与所述指定药品对应的目标药品集合。通过这种实施方式可以降低药品发现时对知识库的依赖，提高药品发现的效率。
本申请实施例还提供了一种药品发现设备，该药品发现设备用于执行前述任一项所述的方法的单元。具体地，参见图4，图4是本申请实施例提供的一种药品发现设备的示意框图。本实施例的药品发现设备包括：获取单元401、计算单元402、构建单元403、确定单元404。
获取单元401，用于获取预设的药品与疾病的知识库，所述知识库包括药品集合、疾病集合、治疗关系集合，所述治疗关系集合包括多个疾病与药品的关系。
计算单元402，用于计算所述知识库中各个药品的表征向量，所述表征向量是根据所述各个药品的语义信息确定的。
构建单元403，用于根据所述各个药品的表征向量计算所述各个药品之间的相似度，并根据所述各个药品之间的相似度构建药品关系图。
确定单元404，用于根据所述知识库中的治疗关系库确定与指定疾病对应的指定药品，并根据所述药品关系图确定与所述指定药品对应的目标药品集合。
进一步地，所述构建单元403根据所述各个药品的表征向量计算所述各个药品之间的相似度时，具体用于：根据所述各个药品的表征向量计算所述各个药品的表征向量之间的 欧式距离；根据所述各个药品的表征向量之间的欧式距离确定所述各个药品之间的相似度。
进一步地，所述构建单元403根据所述各个药品的表征向量计算所述各个药品之间的相似度时，具体用于：根据所述各个药品的表征向量计算所述各个药品的表征向量之间的夹角；根据所述各个药品的表征向量之间的夹角确定所述各个药品之间的相似度。
进一步地，所述构建单元403根据所述各个药品之间的相似度构建药品关系图时，具体用于：根据所述各个药品之间的相似度，判断任意两个药品之间的相似度是否大于预设相似度阈值；如果判断结果为是，则确定将所述相似度大于所述预设相似度阈值的药品两两连接，以构建得到所述药品关系图。
进一步地，所述确定单元404根据所述药品关系图确定与所述指定药品对应的目标药品集合时，具体用于：从所述药品关系图中确定所述指定药品所处的节点；根据所述药品关系图确定所述指定药品所处的节点的各个子节点为与所述指定药品相关联的关联药品集合；根据所述关联药品集合中各个药品所处节点的权值，确定所述权值大于预设权值阈值的目标药品集合。
进一步地，所述确定单元404根据所述关联药品集合中各个药品所处节点的权值，确定所述权值大于预设权值阈值的目标药品集合时，具体用于：计算所述关联药品集合中各个药品所处节点的权值；根据所述关联药品集合中各个药品所处节点的权值，确定所述权值大于预设权值阈值的目标药品集合，并确定所述目标药品集合中的药品为用于治疗所述指定疾病的目标药品。
进一步地，所述确定单元404计算所述关联药品集合中各个药品所处节点的权值时，具体用于：将所述药品关系图中与所述指定药品相关联的关联药品集合中的各个药品所处的节点赋予第一能量；将所述药品关系图中除所述关联药品集合中的各个药品所处的节点以外的其他节点赋予第二能量；根据所述药品关系图中各个节点的第一能量和第二能量，利用指定算法计算所述药品关系图中所述关联药品集合中各个药品所处节点的权值。
本申请实施例中，药品发现设备可以获取预设的药品与疾病的知识库，并计算所述知识库中各个药品的表征向量，以及根据所述各个药品的表征向量计算所述各个药品之间的相似度，并根据所述各个药品之间的相似度构建药品关系图，以及根据所述知识库中的治疗关系库确定与指定疾病对应的指定药品，并根据所述药品关系图确定与所述指定药品对应的目标药品集合。通过这种实施方式可以降低药品发现时对知识库的依赖，提高药品发现的效率。
需要强调的是，为进一步保证上述药品集合、疾病集合、治疗关系集合的私密和安全性，上述药品集合、疾病集合、治疗关系集合还可以存储于一区块链的节点中。
参见图5，图5是本申请实施例提供的一种服务器的示意框图。如图所示的本实施例中的服务器可以包括：一个或多个处理器501；一个或多个输入设备502，一个或多个输出设备503和存储器504。上述处理器501、输入设备502、输出设备503和存储器504通过总线505连接。存储器504用于存储计算机程序，所述计算机程序包括程序，处理器501用于执行存储器504存储的程序。其中，处理器501被配置用于调用所述程序执行：获取预 设的药品与疾病的知识库，所述知识库包括药品集合、疾病集合、治疗关系集合，所述治疗关系集合包括多个疾病与药品的关系；计算所述知识库中各个药品的表征向量，所述表征向量是根据所述各个药品的语义信息确定的；根据所述各个药品的表征向量计算所述各个药品之间的相似度，并根据所述各个药品之间的相似度构建药品关系图；根据所述知识库中的治疗关系库确定与指定疾病对应的指定药品，并根据所述药品关系图确定与所述指定药品对应的目标药品集合。
进一步地，所述处理器501根据所述各个药品的表征向量计算所述各个药品之间的相似度时，具体用于：根据所述各个药品的表征向量计算所述各个药品的表征向量之间的欧式距离；根据所述各个药品的表征向量之间的欧式距离确定所述各个药品之间的相似度。
进一步地，所述处理器501根据所述各个药品的表征向量计算所述各个药品之间的相似度时，具体用于：根据所述各个药品的表征向量计算所述各个药品的表征向量之间的夹角；根据所述各个药品的表征向量之间的夹角确定所述各个药品之间的相似度。
进一步地，所述处理器501根据所述各个药品之间的相似度构建药品关系图时，具体用于：根据所述各个药品之间的相似度，判断任意两个药品之间的相似度是否大于预设相似度阈值；如果判断结果为是，则确定将所述相似度大于所述预设相似度阈值的药品两两连接，以构建得到所述药品关系图。
进一步地，所述处理器501根据所述药品关系图确定与所述指定药品对应的目标药品集合时，具体用于：从所述药品关系图中确定所述指定药品所处的节点；根据所述药品关系图确定所述指定药品所处的节点的各个子节点为与所述指定药品相关联的关联药品集合；根据所述关联药品集合中各个药品所处节点的权值，确定所述权值大于预设权值阈值的目标药品集合。
进一步地，所述处理器501根据所述关联药品集合中各个药品所处节点的权值，确定所述权值大于预设权值阈值的目标药品集合时，具体用于：计算所述关联药品集合中各个药品所处节点的权值；根据所述关联药品集合中各个药品所处节点的权值，确定所述权值大于预设权值阈值的目标药品集合，并确定所述目标药品集合中的药品为用于治疗所述指定疾病的目标药品。
进一步地，所述处理器501计算所述关联药品集合中各个药品所处节点的权值时，具体用于：将所述药品关系图中与所述指定药品相关联的关联药品集合中的各个药品所处的节点赋予第一能量；将所述药品关系图中除所述关联药品集合中的各个药品所处的节点以外的其他节点赋予第二能量；根据所述药品关系图中各个节点的第一能量和第二能量，利用指定算法计算所述药品关系图中所述关联药品集合中各个药品所处节点的权值。
本申请实施例中，服务器可以获取预设的药品与疾病的知识库，并计算所述知识库中各个药品的表征向量，以及根据所述各个药品的表征向量计算所述各个药品之间的相似度，并根据所述各个药品之间的相似度构建药品关系图，以及根据所述知识库中的治疗关系库确定与指定疾病对应的指定药品，并根据所述药品关系图确定与所述指定药品对应的目标药品集合。通过这种实施方式可以降低药品发现时对知识库的依赖，提高药品发现的效率。
应当理解，在本申请实施例中，所称处理器501可以是中央处理单元(CenSral Processing UniS，CPU)，该处理器还可以是其他通用处理器、数字信号处理器(DigiSal Signal Processor，DSP)、专用集成电路(ApplicaSion Specific InSegraSed CircuiS，ASIC)、现成可编程门阵列(Field-Programmable GaSe Array，FPGA)或者其他可编程逻辑器件、分立门或者晶体管逻辑器件、分立硬件组件等。通用处理器可以是微处理器或者该处理器也可以是任何常规的处理器等。
输入设备502可以包括触控板、麦克风等，输出设备503可以包括显示器(LCD等)、扬声器等。
该存储器504可以包括只读存储器和随机存取存储器，并向处理器501提供指令和数据。存储器504的一部分还可以包括非易失性随机存取存储器。例如，存储器504还可以存储设备类型的信息。
具体实现中，本申请实施例中所描述的处理器501、输入设备502、输出设备503可执行本申请实施例提供的图1所述的方法实施例中所描述的实现方式，也可执行本申请实施例图4所描述的药品发现设备的实现方式，在此不再赘述。
本申请实施例中还提供了一种计算机可读存储介质，所述计算机可读存储介质存储有计算机程序，所述计算机程序被处理器执行时实现图1所对应实施例中描述的药品发现方法，也可实现本申请图4所对应实施例的药品发现设备，在此不再赘述。所述计算机可读存储介质可以是非易失性，也可以是易失性。
所述计算机可读存储介质可以是前述任一实施例所述的药品发现设备的内部存储单元，例如药品发现设备的硬盘或内存。所述计算机可读存储介质也可以是所述药品发现设备的外部存储设备，例如所述药品发现设备上配备的插接式硬盘，智能存储卡(SmarS Media Card,SMC)，安全数字(Secure DigiSal,SD)卡，闪存卡(Flash Card)等。进一步地，所述计算机可读存储介质还可以既包括所述药品发现设备的内部存储单元也包括外部存储设备。所述计算机可读存储介质用于存储所述计算机程序以及所述药品发现设备所需的其他程序和数据。所述计算机可读存储介质还可以用于暂时地存储已经输出或者将要输出的数据。
进一步地，所述计算机可读存储介质可主要包括存储程序区和存储数据区，其中，存储程序区可存储操作系统、至少一个功能所需的应用程序等；存储数据区可存储根据区块链节点的使用所创建的数据等。
本申请所指区块链是分布式数据存储、点对点传输、共识机制、加密算法等计算机技术的新型应用模式。区块链(Blockchain)，本质上是一个去中心化的数据库，是一串使用密码学方法相关联产生的数据块，每一个数据块中包含了一批次网络交易的信息，用于验证其信息的有效性(防伪)和生成下一个区块。区块链可以包括区块链底层平台、平台产品服务层以及应用服务层等。
所述集成的单元如果以软件功能单元的形式实现并作为独立的产品销售或使用时，可以存储在一个计算机可读取存储介质中。基于这样的理解，本申请的技术方案本质上或者 说对现有技术做出贡献的部分，或者该技术方案的全部或部分可以以软件产品的形式体现出来，该计算机软件产品存储在一个计算机可读存储介质中，包括若干指令用以使得一台计算机设备(可以是个人计算机，终端，或者网络设备等)执行本申请各个实施例所述方法的全部或部分步骤。而前述的计算机可读存储介质包括：U盘、移动硬盘、只读存储器(ROM，Read-Only Memory)、随机存取存储器(RAM，Random Access Memory)、磁碟或者光盘等各种可以存储程序代码的介质。
以上所述，仅为本申请的具体实施方式，但本申请的保护范围并不局限于此，任何熟悉本技术领域的技术人员在本申请揭露的技术范围内，可轻易想到变化或替换，都应涵盖在本申请的保护范围之内。因此，本申请的保护范围应以所述权利要求的保护范围为准。

Claims (20)

  1. 一种药品发现方法，其中，包括：
    获取预设的药品与疾病的知识库，所述知识库包括药品集合、疾病集合、治疗关系集合，所述治疗关系集合包括多个疾病与药品的关系；
    计算所述知识库中各个药品的表征向量，所述表征向量是根据所述各个药品的语义信息确定的；
    根据所述各个药品的表征向量计算所述各个药品之间的相似度，并根据所述各个药品之间的相似度构建药品关系图；
    根据所述知识库中的治疗关系库确定与指定疾病对应的指定药品，并根据所述药品关系图确定与所述指定药品对应的目标药品集合。
  2. 根据权利要求1所述的方法，其中，所述根据所述各个药品的表征向量计算所述各个药品之间的相似度，包括：
    根据所述各个药品的表征向量计算所述各个药品的表征向量之间的欧式距离；
    根据所述各个药品的表征向量之间的欧式距离确定所述各个药品之间的相似度。
  3. 根据权利要求1所述的方法，其中，所述根据所述各个药品的表征向量计算所述各个药品之间的相似度，包括：
    根据所述各个药品的表征向量计算所述各个药品的表征向量之间的夹角；
    根据所述各个药品的表征向量之间的夹角确定所述各个药品之间的相似度。
  4. 根据权利要求1-3任一项所述的方法，其中，所述根据所述各个药品之间的相似度构建药品关系图，包括：
    根据所述各个药品之间的相似度，判断任意两个药品之间的相似度是否大于预设相似度阈值；
    如果判断结果为是，则确定将所述相似度大于所述预设相似度阈值的药品两两连接，以构建得到所述药品关系图。
  5. 根据权利要求4所述的方法，其中，所述根据所述药品关系图确定与所述指定药品对应的目标药品集合，包括：
    从所述药品关系图中确定所述指定药品所处的节点；
    根据所述药品关系图确定所述指定药品所处的节点的各个子节点为与所述指定药品相关联的关联药品集合；
    根据所述关联药品集合中各个药品所处节点的权值，确定所述权值大于预设权值阈值的目标药品集合。
  6. 根据权利要求5所述的方法，其中，所述根据所述关联药品集合中各个药品所处节点的权值，确定所述权值大于预设权值阈值的目标药品集合，包括：
    计算所述关联药品集合中各个药品所处节点的权值；
    根据所述关联药品集合中各个药品所处节点的权值，确定所述权值大于预设权值阈值的目标药品集合，并确定所述目标药品集合中的药品为用于治疗所述指定疾病的目标药品。
  7. 根据权利要求6所述的方法，其中，所述计算所述关联药品集合中各个药品所处节点的权值，包括：
    将所述药品关系图中与所述指定药品相关联的关联药品集合中的各个药品所处的节点赋予第一能量；
    将所述药品关系图中除所述关联药品集合中的各个药品所处的节点以外的其他节点赋予第二能量；
    根据所述药品关系图中各个节点的第一能量和第二能量，利用指定算法计算所述药品关系图中所述关联药品集合中各个药品所处节点的权值。
  8. 一种药品发现设备，其中，包括用于执行如权利要求1-7任一项权利要求所述的方法的单元。
  9. 一种服务器，其中，包括处理器、输入设备、输出设备和存储器，所述处理器、输入设备、输出设备和存储器相互连接，其中，所述存储器用于存储计算机程序，所述计算机程序包括程序，所述处理器被配置用于调用所述程序，其中：
    获取预设的药品与疾病的知识库，所述知识库包括药品集合、疾病集合、治疗关系集合，所述治疗关系集合包括多个疾病与药品的关系；
    计算所述知识库中各个药品的表征向量，所述表征向量是根据所述各个药品的语义信息确定的；
    根据所述各个药品的表征向量计算所述各个药品之间的相似度，并根据所述各个药品之间的相似度构建药品关系图；
    根据所述知识库中的治疗关系库确定与指定疾病对应的指定药品，并根据所述药品关系图确定与所述指定药品对应的目标药品集合。
  10. 根据权利要求9所述的服务器，其中，所述处理器用于：
    根据所述各个药品的表征向量计算所述各个药品的表征向量之间的欧式距离；
    根据所述各个药品的表征向量之间的欧式距离确定所述各个药品之间的相似度。
  11. 根据权利要求9所述的服务器，其中，所述处理器用于：
    根据所述各个药品的表征向量计算所述各个药品的表征向量之间的夹角；
    根据所述各个药品的表征向量之间的夹角确定所述各个药品之间的相似度。
  12. 根据权利要求9-11所述的服务器，其中，所述处理器用于：
    根据所述各个药品之间的相似度，判断任意两个药品之间的相似度是否大于预设相似度阈值；
    如果判断结果为是，则确定将所述相似度大于所述预设相似度阈值的药品两两连接，以构建得到所述药品关系图。
  13. 根据权利要求12所述的服务器，其中，所述处理器用于：
    从所述药品关系图中确定所述指定药品所处的节点；
    根据所述药品关系图确定所述指定药品所处的节点的各个子节点为与所述指定药品相关联的关联药品集合；
    根据所述关联药品集合中各个药品所处节点的权值，确定所述权值大于预设权值阈值的目标药品集合。
  14. 根据权利要求13所述的服务器，其中，所述处理器用于：
    计算所述关联药品集合中各个药品所处节点的权值；
    根据所述关联药品集合中各个药品所处节点的权值，确定所述权值大于预设权值阈值的目标药品集合，并确定所述目标药品集合中的药品为用于治疗所述指定疾病的目标药品。
  15. 根据权利要求14所述的服务器，其中，所述处理器用于：
    将所述药品关系图中与所述指定药品相关联的关联药品集合中的各个药品所处的节点赋予第一能量；
    将所述药品关系图中除所述关联药品集合中的各个药品所处的节点以外的其他节点赋予第二能量；
    根据所述药品关系图中各个节点的第一能量和第二能量，利用指定算法计算所述药品关系图中所述关联药品集合中各个药品所处节点的权值。
  16. 一种计算机可读存储介质，其特征在于，所述计算机可读存储介质存储有计算机程序，所述计算机程序被处理器执行以实现以下步骤：
    获取预设的药品与疾病的知识库，所述知识库包括药品集合、疾病集合、治疗关系集合，所述治疗关系集合包括多个疾病与药品的关系；
    计算所述知识库中各个药品的表征向量，所述表征向量是根据所述各个药品的语义信息确定的；
    根据所述各个药品的表征向量计算所述各个药品之间的相似度，并根据所述各个药品之间的相似度构建药品关系图；
    根据所述知识库中的治疗关系库确定与指定疾病对应的指定药品，并根据所述药品关系图确定与所述指定药品对应的目标药品集合。
  17. 根据权利要16所述的计算机可读存储介质，其中，所述计算机程序还被处理器执行以实现以下步骤：
    根据所述各个药品的表征向量计算所述各个药品的表征向量之间的欧式距离；
    根据所述各个药品的表征向量之间的欧式距离确定所述各个药品之间的相似度。
  18. 根据权利要16所述的计算机可读存储介质，其中，所述计算机程序还被处理器执行以实现以下步骤：
    根据所述各个药品的表征向量计算所述各个药品的表征向量之间的夹角；
    根据所述各个药品的表征向量之间的夹角确定所述各个药品之间的相似度。
  19. 根据权利要16-18所述的计算机可读存储介质，其中，所述计算机程序还被处理器执行以实现以下步骤：
    根据所述各个药品之间的相似度，判断任意两个药品之间的相似度是否大于预设相似度阈值；
    如果判断结果为是，则确定将所述相似度大于所述预设相似度阈值的药品两两连接， 以构建得到所述药品关系图。
  20. 根据权利要19所述的计算机可读存储介质，其中，所述计算机程序还被处理器执行以实现以下步骤：
    从所述药品关系图中确定所述指定药品所处的节点；
    根据所述药品关系图确定所述指定药品所处的节点的各个子节点为与所述指定药品相关联的关联药品集合；
    根据所述关联药品集合中各个药品所处节点的权值，确定所述权值大于预设权值阈值的目标药品集合。
PCT/CN2020/118365 2020-05-13 2020-09-28 一种药品发现方法、设备、服务器及可读存储介质 WO2021114830A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202010404943.6 2020-05-13
CN202010404943.6A CN111694964A (zh) 2020-05-13 2020-05-13 一种药品发现方法、设备、服务器及可读存储介质

Publications (1)

Publication Number Publication Date
WO2021114830A1 true WO2021114830A1 (zh) 2021-06-17

Family

ID=72477320

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2020/118365 WO2021114830A1 (zh) 2020-05-13 2020-09-28 一种药品发现方法、设备、服务器及可读存储介质

Country Status (2)

Country Link
CN (1) CN111694964A (zh)
WO (1) WO2021114830A1 (zh)

Families Citing this family (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111694964A (zh) * 2020-05-13 2020-09-22 平安科技（深圳）有限公司 一种药品发现方法、设备、服务器及可读存储介质
CN112509652B (zh) * 2021-02-03 2021-06-18 南京可信区块链与算法经济研究院有限公司 基于区块链的多方联合寻找创新药潜在靶点的方法及系统

Citations (10)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN105653846A (zh) * 2015-12-25 2016-06-08 中南大学 基于集成的相似性度量和双向随机游走的药物重定位方法
US20190035494A1 (en) * 2017-07-31 2019-01-31 Boe Technology Group Co., Ltd. Method and terminal for analyzing drug-disease relevance relation, non-transitory computer-readable storage medium
CN109801705A (zh) * 2018-12-12 2019-05-24 平安科技（深圳）有限公司 治疗推荐方法、系统、装置及存储介质
CN109902233A (zh) * 2019-02-28 2019-06-18 百度在线网络技术（北京）有限公司 智能对象推荐方法、装置、设备和存储介质
CN109934684A (zh) * 2019-03-20 2019-06-25 上海证大喜马拉雅网络科技有限公司 一种商品推荐方法、装置、终端及存储介质
CN110019531A (zh) * 2017-12-29 2019-07-16 北京京东尚科信息技术有限公司 一种获取相似对象集合的方法和装置
CN110020124A (zh) * 2017-10-20 2019-07-16 北京京东尚科信息技术有限公司 用于相关产品挖掘的方法及装置
CN110517785A (zh) * 2019-08-28 2019-11-29 北京百度网讯科技有限公司 相似病例的查找方法、装置及设备
CN110782996A (zh) * 2019-09-18 2020-02-11 平安科技（深圳）有限公司 医疗数据库的构建方法、装置、计算机设备和存储介质
CN111694964A (zh) * 2020-05-13 2020-09-22 平安科技（深圳）有限公司 一种药品发现方法、设备、服务器及可读存储介质

Patent Citations (10)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN105653846A (zh) * 2015-12-25 2016-06-08 中南大学 基于集成的相似性度量和双向随机游走的药物重定位方法
US20190035494A1 (en) * 2017-07-31 2019-01-31 Boe Technology Group Co., Ltd. Method and terminal for analyzing drug-disease relevance relation, non-transitory computer-readable storage medium
CN110020124A (zh) * 2017-10-20 2019-07-16 北京京东尚科信息技术有限公司 用于相关产品挖掘的方法及装置
CN110019531A (zh) * 2017-12-29 2019-07-16 北京京东尚科信息技术有限公司 一种获取相似对象集合的方法和装置
CN109801705A (zh) * 2018-12-12 2019-05-24 平安科技（深圳）有限公司 治疗推荐方法、系统、装置及存储介质
CN109902233A (zh) * 2019-02-28 2019-06-18 百度在线网络技术（北京）有限公司 智能对象推荐方法、装置、设备和存储介质
CN109934684A (zh) * 2019-03-20 2019-06-25 上海证大喜马拉雅网络科技有限公司 一种商品推荐方法、装置、终端及存储介质
CN110517785A (zh) * 2019-08-28 2019-11-29 北京百度网讯科技有限公司 相似病例的查找方法、装置及设备
CN110782996A (zh) * 2019-09-18 2020-02-11 平安科技（深圳）有限公司 医疗数据库的构建方法、装置、计算机设备和存储介质
CN111694964A (zh) * 2020-05-13 2020-09-22 平安科技（深圳）有限公司 一种药品发现方法、设备、服务器及可读存储介质

Also Published As

Publication number Publication date
CN111694964A (zh) 2020-09-22

Similar Documents

Publication Publication Date Title
CA3042660A1 (en) Systems and methods for managing data privacy
US10340038B2 (en) Healthcare transaction validation via blockchain, systems and methods
EP2767951B1 (en) Information processing device, method and program
US11562812B2 (en) Computer implemented method for secure management of data generated in an EHR during an episode of care and a system therefor
CN111949890B (zh) 基于医学领域的数据推荐方法、设备、服务器及存储介质
WO2021114830A1 (zh) 一种药品发现方法、设备、服务器及可读存储介质
CN112700838A (zh) 基于大数据的用药方案推荐方法、装置及相关设备
KR102310227B1 (ko) 블록체인을 이용한 의료 정보 조회 시스템과 방법 및 이를 위한 컴퓨터 프로그램
US20130297333A1 (en) Systems and methods for electronic prescribing
US20140096195A1 (en) Secure Information Release
Krittanawong et al. Artificial intelligence-powered blockchains for cardiovascular medicine
US11705231B2 (en) System and method for computerized synthesis of simulated health data
CN110535958B (zh) 一种健康信息存储方法及相关设备
US20190354721A1 (en) Techniques For Limiting Risks In Electronically Communicating Patient Information
US20210248621A1 (en) Methods and systems for tracking the transfer of a cannabis article
Wadud et al. A decentralized secure blockchain-based privacy-preserving healthcare clouds and applications
Kamal et al. Care4U: Integrated healthcare systems based on blockchain
US11501861B2 (en) System and method to access casualty health information in an emergency situation
Lophatananon et al. The association of herpes zoster and influenza vaccinations with the risk of developing dementia: a population-based cohort study within the UK Clinical Practice Research Datalink
Cai et al. Assessing the transition of COVID-19 burden towards the young population while vaccines are rolled out in China
Usharani et al. Blockchain Technology Use Cases in Healthcare Management: State-of-the-Art Framework and Performance Evaluation
Munshi et al. The effect of Florida Medicaid’s state-mandated formulary provision on prescription drug use and health plan costs in a Medicaid managed care plan
Miya et al. Healthcare Transformation Using Blockchain Technology in the Era of Society 5.0
WO2020158842A1 (ja) 端末装置、データ処理方法、及びプログラム
US10943684B2 (en) Methods and systems for electronic prescription based ETASU enforcement

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 20898143

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 20898143

Country of ref document: EP

Kind code of ref document: A1