CN111694964A - Medicine discovery method, equipment, server and readable storage medium - Google Patents
Medicine discovery method, equipment, server and readable storage medium Download PDFInfo
- Publication number
- CN111694964A CN111694964A CN202010404943.6A CN202010404943A CN111694964A CN 111694964 A CN111694964 A CN 111694964A CN 202010404943 A CN202010404943 A CN 202010404943A CN 111694964 A CN111694964 A CN 111694964A
- Authority
- CN
- China
- Prior art keywords
- medicine
- medicines
- drug
- similarity
- node
- Prior art date
- Legal status (The legal status 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 status listed.)
- Pending
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
Abstract
The invention relates to a block chain technology, is applied to the field of intelligent medical treatment, and discloses a drug discovery method, which comprises the following steps: acquiring a preset knowledge base of medicines and diseases, wherein the knowledge base comprises a medicine set, a disease set and a treatment relation set; calculating a characterization vector of each medicine in the knowledge base, wherein the characterization vector is determined according to semantic information of each medicine; calculating the similarity among the medicines according to the characterization vectors of the medicines, and constructing a medicine relation graph according to the similarity among the medicines; and determining a designated medicine corresponding to the designated disease according to the treatment relation library in the knowledge base, and determining a target medicine set corresponding to the designated medicine according to the medicine relation diagram. The dependence on a knowledge base during drug discovery can be reduced, and the drug discovery efficiency is improved. In addition, the application also relates to a block chain technology, and the medicine set, the disease set and the treatment relation set can be stored in the block chain.
Description
Technical Field
The invention relates to a block chain technology, which is applied to the field of intelligent medical treatment, in particular to a medicine discovery method, equipment, a server and a readable storage medium.
Background
At present, when a new medicine is researched in the traditional pharmaceutical industry, a large amount of substances need to be tested, so that substances which can really treat diseases are screened out, and the medicine is just like a sea fishing needle. Such new drug discovery techniques are highly dependent on complex knowledge bases (such as chemical structures, molecular spatial structures, and targeting relationships with genes of drugs), and the cost of constructing knowledge bases is high.
Disclosure of Invention
The embodiment of the invention provides a medicine discovery method, equipment, a server and a readable storage medium, which can reduce the dependence on a knowledge base during medicine discovery and improve the medicine discovery efficiency.
In a first aspect, an embodiment of the present invention provides a drug discovery method, including:
acquiring a preset knowledge base of medicines and diseases, wherein the knowledge base comprises a medicine set, a disease set and a treatment relation set, and the treatment relation set comprises a plurality of relations between the diseases and the medicines;
calculating a characterization vector of each medicine in the knowledge base, wherein the characterization vector is determined according to semantic information of each medicine;
calculating the similarity among the medicines according to the characterization vectors of the medicines, and constructing a medicine relation graph according to the similarity among the medicines;
and determining a designated medicine corresponding to the designated disease according to the treatment relation library in the knowledge base, and determining a target medicine set corresponding to the designated medicine according to the medicine relation diagram.
Further, the calculating the similarity between the medicines according to the characterization vectors of the medicines includes:
calculating Euclidean distances among the characterization vectors of the medicines according to the characterization vectors of the medicines;
and determining the similarity among the medicines according to the Euclidean distance among the characterization vectors of the medicines.
Further, the calculating the similarity between the medicines according to the characterization vectors of the medicines includes:
calculating included angles among the characteristic vectors of the medicines according to the characteristic vectors of the medicines;
and determining the similarity among the medicines according to the included angle among the characterization vectors of the medicines.
Further, the constructing a drug relationship graph according to the similarity between the drugs includes:
judging whether the similarity between any two medicines is greater than a preset similarity threshold value or not according to the similarity between the medicines;
and if so, determining that the medicines with the similarity larger than the preset similarity threshold are connected pairwise so as to construct and obtain the medicine relation graph.
Further, the determining a target drug set corresponding to the specified drug according to the drug relationship graph includes:
determining a node where the specified drug is located from the drug relationship graph;
determining each child node of the node where the specified medicine is located as an associated medicine set associated with the specified medicine according to the medicine relation graph;
and determining a target medicine set with the weight value larger than a preset weight value threshold according to the weight value of the node where each medicine in the associated medicine set is located.
Further, the determining, according to the weight of the node where each medicine in the associated medicine set is located, the target medicine set where the weight is greater than a preset weight threshold includes:
calculating the weight of the node where each medicine in the associated medicine set is located;
and determining a target medicine set with the weight value larger than a preset weight value threshold according to the weight value of the node where each medicine in the associated medicine set is located, and determining the medicines in the target medicine set as target medicines for treating the specified diseases.
Further, the calculating the weight of the node where each medicine in the associated medicine set is located includes:
assigning a first energy to a node in the drug relationship graph at which each drug in the set of associated drugs associated with the specified drug is located;
assigning a second energy to other nodes in the drug relationship graph except the node where each drug in the associated drug set is located;
and calculating the weight of the node where each medicine in the associated medicine set in the medicine relation graph is located by using a specified algorithm according to the first energy and the second energy of each node in the medicine relation graph.
In a second aspect, embodiments of the present invention provide a drug discovery device comprising means for performing the drug discovery method of the first aspect.
In a third aspect, an embodiment of the present invention provides a server, including a processor, an input device, an output device, and a memory, where the processor, the input device, the output device, and the memory are connected to each other, where the memory is used to store a computer program supporting a drug discovery device to execute the method described above, and the computer program includes a program, and the processor is configured to call the program to execute the method described above in the first aspect.
In a fourth aspect, the present invention provides a computer-readable storage medium, which stores a computer program, where the computer program is executed by a processor to implement the method of the first aspect.
According to the embodiment of the invention, by acquiring the preset knowledge base of the medicines and the diseases, calculating the characteristic vectors of the medicines in the knowledge base, calculating the similarity among the medicines according to the characteristic vectors of the medicines, constructing the medicine relation graph according to the similarity among the medicines, determining the specified medicines corresponding to the specified diseases according to the treatment relation base in the knowledge base, and determining the target medicine set corresponding to the specified medicines according to the medicine relation graph, the dependence on the knowledge base during medicine discovery can be reduced, and the medicine discovery efficiency is improved.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings needed to be used in the description of the embodiments are briefly introduced below, and it is obvious that the drawings in the following description are some embodiments of the present invention, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without creative efforts.
FIG. 1 is a schematic flow chart of a drug discovery method according to an embodiment of the present invention;
FIG. 2 is a schematic diagram of a drug relationship diagram provided by an embodiment of the present invention;
FIG. 3 is a schematic diagram of another drug relationship diagram provided by an embodiment of the present invention;
FIG. 4 is a schematic block diagram of a drug discovery device provided by an embodiment of the present invention;
fig. 5 is a schematic block diagram of a server according to an embodiment of the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are some, not all, embodiments of the present invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
The drug discovery method provided by the embodiment of the invention can be executed by a drug discovery device, wherein the drug discovery device can be arranged on a server. In some embodiments, 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 a component of the server, i.e. the server comprises a drug discovery device.
In the embodiment of the invention, the scheme can be applied to the field of intelligent medical treatment, so that the construction of a smart city is promoted. The drug discovery device can acquire a preset knowledge base of drugs and diseases, calculate the characterization vectors of the drugs in the knowledge base, calculate the similarity between the drugs according to the characterization vectors of the drugs, construct a drug relationship diagram according to the similarity between the drugs, determine the specified drugs corresponding to the specified diseases according to a treatment relationship base in the knowledge base, and determine a target drug set corresponding to the specified drugs according to the drug relationship diagram. By the implementation mode, the dependence on the knowledge base in drug discovery can be reduced, and the drug discovery efficiency is improved.
The drug discovery method according to the embodiment of the present invention will be schematically described below with reference to the drawings.
Referring to fig. 1, fig. 1 is a schematic flow chart of a drug discovery method according to an embodiment of the present invention, and as shown in fig. 1, the method may be executed by a drug discovery device, and the specific explanation of the drug discovery device is as described above and is not repeated here. Specifically, the method of the embodiment of the present invention includes the following steps.
S101: the method comprises the steps of obtaining a preset knowledge base of medicines and diseases, wherein the knowledge base comprises a medicine set, a disease set and a treatment relation set, and the treatment relation set comprises a plurality of relations between the diseases and the medicines.
In the embodiment of the invention, the medicine discovery device can acquire a preset knowledge base of medicines and diseases, wherein the knowledge base comprises a medicine set, a disease set and a treatment relation set, and the treatment relation set comprises a plurality of relations between the diseases and the medicines. In some embodiments, the predetermined knowledge base of drugs and diseases may be obtained from a public database. In certain embodiments, the relationship of a plurality of diseases to drugs included in the set of treatment relationships is used to indicate that one or more drugs are treating a disease.
In one example, the drug set is { captopril, metformin }. In one example, the set of diseases is { hypertension, diabetes }. In one example, the set of therapeutic relationships is { metformin- > diabetes, captopril- > diabetes }, where "metformin- > diabetes" is used to indicate metformin is used to treat diabetes and "captopril- > diabetes" is used to indicate captopril is used to treat diabetes.
S102: and calculating a characterization vector of each medicine in the knowledge base, wherein the characterization vector is determined according to the semantic information of each medicine.
In the embodiment of the present invention, the drug discovery device may calculate a characterization vector of each drug in the knowledge base, where the characterization vector is determined according to semantic information of each drug. In some embodiments, the token vector may be a high-dimensional vector, typically between 100 and 1000 dimensions; in some embodiments, each element in the characterization vector may be a real number. In some embodiments, the characterization vector includes, to some extent, semantic information of each corresponding drug for reflecting a description of each drug.
In one embodiment, when calculating the characterization vector of each drug in the knowledge base, the drug discovery device may obtain semantic information of each drug in the knowledge base, and calculate the characterization vector of each drug in the knowledge base according to the semantic information of each drug.
In one embodiment, when calculating the characterization vector of each drug in the knowledge base, the drug discovery device may obtain the composition of each drug in the knowledge base, obtain semantic information of the composition of each drug, and calculate the characterization vector of each drug in the knowledge base according to the semantic information of the composition of each drug.
In one embodiment, the drug discovery device may utilize word2vec technology to calculate a characterization vector for each drug in the knowledge base. In some embodiments, the word2vec is based on a large amount of text, and a characterization vector of a word (or a phrase) in the text is calculated, wherein the characterization vector reflects semantic information of the word.
S103: and calculating the similarity among the medicines according to the characterization vectors of the medicines, and constructing a medicine relation graph according to the similarity among the medicines.
In the embodiment of the invention, the medicine discovery equipment calculates the similarity among the medicines according to the characterization vectors of the medicines, and constructs a medicine relation graph according to the similarity among the medicines.
In one embodiment, when the drug discovery device calculates the similarity between the drugs according to the characterization vectors of the drugs, the drug discovery device may calculate euclidean distances between the characterization vectors of the drugs according to the characterization vectors of the drugs, and determine the similarity between the drugs according to the euclidean distances between the characterization vectors of the drugs.
In an embodiment, when the drug discovery device calculates the similarity between the drugs according to the characterization vectors of the drugs, the drug discovery device may calculate an included angle between the characterization vectors of the drugs according to the characterization vectors of the drugs, and determine the similarity between the drugs according to the included angle between the characterization vectors of the drugs. In other embodiments, the similarity between the medicines may also be calculated in other manners, which is not specifically limited herein.
In an embodiment, when the medicine discovery device constructs the medicine relationship diagram according to the similarity between the medicines, it may determine whether the similarity between any two medicines is greater than a preset similarity threshold according to the similarity between the medicines, and if the determination result is yes, it may determine that the medicines with the similarity greater than the preset similarity threshold are connected in pairs to construct the medicine relationship diagram.
In one embodiment, when determining that the medicines with the similarity greater than the preset similarity threshold are connected two by two, the medicine discovery device may connect the medicines with the similarity greater than the preset similarity threshold through a line segment. In one embodiment, the medicine discovery device may construct the medicine relationship diagram in order from high to low according to the magnitude of the similarity when constructing the medicine relationship diagram.
It is emphasized that, in order to further ensure the privacy and safety of the medicine, disease and treatment relationship sets, the medicine, disease and treatment relationship sets may also be stored in nodes of a blockchain.
Specifically, the description may be given by taking fig. 2 as an example, where fig. 2 is a schematic diagram of a drug relationship graph provided in an embodiment of the present invention, and as shown in fig. 2, a drug with a similarity greater than a preset similarity threshold is used as a node to construct the drug relationship graph shown in fig. 2.
S104: and determining a designated medicine corresponding to the designated disease according to the treatment relation library in the knowledge base, and determining a target medicine set corresponding to the designated medicine according to the medicine relation diagram.
In the embodiment of the present invention, the drug discovery device may determine, according to the treatment relation library in the knowledge base, the specified drug corresponding to the specified disease, and determine, according to the drug relation map, the target drug set corresponding to the specified drug. In one example, the specified disease may be diabetes and the specified medication may be metformin used to treat diabetes.
In an embodiment, when determining, by the drug discovery device, a target drug set corresponding to the specified drug according to the drug relationship graph, the node where the specified drug is located may be determined from the drug relationship graph, and each child node of the node where the specified drug is located is determined to be an associated drug set associated with the specified drug according to the drug relationship graph, and the target drug set where the weight is greater than a preset weight threshold is determined according to the weight of the node where each drug in the associated drug set is located.
Taking fig. 2 as an example, assuming that the designated drug is metformin, the drug discovery device may determine that each sub-node of the node where metformin is located is nivolumab, flumetrene Chiung, xylazine, captopril, endrazine, and cadrazine according to the drug relationship diagram shown in fig. 2, and thus may determine that { nivolumab, flumetrene Chiung, xylazine, captopril, endrazine } is the associated drug set associated with metformin, assuming that the weight of the node where nivolumab is located is x1, the weight of the node where flumetrene Chiung is x2, the weight of the node where xylazine is located is x3, the weight of the node where captopril is x4, the weight of the node where endrazine is x5, and the weight of the node where cadrazine is x6, and if the weights of the nodes x1, x2, x3, and x4 are greater than a preset niuma threshold value, the drug discovery device may determine that the node is niuma threshold value, Flumetrene Chiung, xylazine and captopril are taken as a target drug set.
Therefore, the method and the device can screen the associated drug set associated with the specified drug from the preset knowledge base of the drug and the disease, and are helpful for determining the target drug set with stronger association from the associated drug set.
In an embodiment, when determining, by the drug discovery device, a target drug set in which the weight is greater than a preset weight threshold according to the weight of the node in which each drug in the associated drug set is located, the drug discovery device may calculate the weight of the node in which each drug in the associated drug set is located, determine, according to the weight of the node in which each drug in the associated drug set is located, the target drug set in which the weight is greater than the preset weight threshold, and determine the drug in the target drug set as the target drug for treating the specified disease. Therefore, by calculating the weight of each node, the target medicine corresponding to the node with strong relevance can be determined.
In one embodiment, when calculating the weight of the node where each drug in the associated drug set is located, the drug discovery device may assign a first energy to the node where each drug in the associated drug set associated with the specified drug in the drug relationship graph is located, assign a second energy to the nodes other than the node where each drug in the associated drug set is located in the drug relationship graph, and calculate the weight of the node where each drug in the associated drug set is located in the drug relationship graph by using a specified algorithm according to the first energy and the second energy of each node in the drug relationship graph. In certain embodiments, the specified algorithm includes, but is not limited to, a graph propagation algorithm.
In some embodiments, the first energy and the second energy are different, and the first energy and the second energy may be represented by characters such as numbers, letters, colors, and the like; in one example, the first energy may be 1, the second energy may be 0; in another example, the first energy may be green, and the second energy may be red, taking fig. 3 as an example, fig. 3 is a schematic diagram of another drug relationship diagram provided by the embodiment of the present invention, and in the drug relationship diagram shown in fig. 3, the first energy is gray, and the second energy is white. In certain embodiments, the same color drug in the drug relationship graph is the associated drug for treatment of the same disease.
Therefore, through the implementation mode, the target medicine set with strong relevance can be determined from the associated medicine sets according to the weight of each medicine in the medicine relation graph, the target medicine set is prevented from being directly inquired from the preset knowledge base of the medicines and the diseases, and the medicine discovery efficiency is improved.
In the embodiment of the invention, the medicine discovery device can acquire a preset knowledge base of medicines and diseases, calculate the representation vectors of the medicines in the knowledge base, calculate the similarity among the medicines according to the representation vectors of the medicines, construct a medicine relation graph according to the similarity among the medicines, determine the specified medicines corresponding to the specified diseases according to a treatment relation base in the knowledge base, and determine the target medicine set corresponding to the specified medicines according to the medicine relation graph. By the implementation mode, the dependence on the knowledge base in drug discovery can be reduced, and the drug discovery efficiency is improved.
Embodiments of the present invention also provide a drug discovery device for performing the units of the method of any one of the preceding claims. Specifically, referring to fig. 4, fig. 4 is a schematic block diagram of a medicine discovery device according to an embodiment of the present invention. The medicine discovery apparatus of the present 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, where the knowledge base includes a medicine set, a disease set, and a treatment relationship set, and the treatment relationship set includes relationships between a plurality of diseases and medicines;
a calculating unit 402, configured to calculate a characterization vector of each drug in the knowledge base, where the characterization vector is determined according to semantic information of each drug;
a constructing unit 403, configured to calculate similarities between the medicines according to the characterization vectors of the medicines, and construct a medicine relation graph according to the similarities between the medicines;
a determining unit 404, configured to determine a specified drug corresponding to a specified disease according to the treatment relation library in the knowledge base, and determine a target drug set corresponding to the specified drug according to the drug relation map.
Further, when the constructing unit 403 calculates the similarity between the medicines according to the characterization vectors of the medicines, it is specifically configured to:
calculating Euclidean distances among the characterization vectors of the medicines according to the characterization vectors of the medicines;
and determining the similarity among the medicines according to the Euclidean distance among the characterization vectors of the medicines.
Further, when the constructing unit 403 calculates the similarity between the medicines according to the characterization vectors of the medicines, it is specifically configured to:
calculating included angles among the characteristic vectors of the medicines according to the characteristic vectors of the medicines;
and determining the similarity among the medicines according to the included angle among the characterization vectors of the medicines.
Further, when the construction unit 403 constructs the medicine relationship graph according to the similarity between the medicines, it is specifically configured to:
judging whether the similarity between any two medicines is greater than a preset similarity threshold value or not according to the similarity between the medicines;
and if so, determining that the medicines with the similarity larger than the preset similarity threshold are connected pairwise so as to construct and obtain the medicine relation graph.
Further, when the determining unit 404 determines the target drug set corresponding to the specified drug according to the drug relationship graph, specifically, the determining unit is configured to:
determining a node where the specified drug is located from the drug relationship graph;
determining each child node of the node where the specified medicine is located as an associated medicine set associated with the specified medicine according to the medicine relation graph;
and determining a target medicine set with the weight value larger than a preset weight value threshold according to the weight value of the node where each medicine in the associated medicine set is located.
Further, when the determining unit 404 determines, according to the weight of the node where each medicine in the associated medicine set is located, that the target medicine set whose weight is greater than a preset weight threshold is specifically configured to:
calculating the weight of the node where each medicine in the associated medicine set is located;
and determining a target medicine set with the weight value larger than a preset weight value threshold according to the weight value of the node where each medicine in the associated medicine set is located, and determining the medicines in the target medicine set as target medicines for treating the specified diseases.
Further, when the determining unit 404 calculates the weight of the node where each medicine in the associated medicine set is located, it is specifically configured to:
assigning a first energy to a node in the drug relationship graph at which each drug in the set of associated drugs associated with the specified drug is located;
assigning a second energy to other nodes in the drug relationship graph except the node where each drug in the associated drug set is located;
and calculating the weight of the node where each medicine in the associated medicine set in the medicine relation graph is located by using a specified algorithm according to the first energy and the second energy of each node in the medicine relation graph.
In the embodiment of the invention, the medicine discovery device can acquire a preset knowledge base of medicines and diseases, calculate the representation vectors of the medicines in the knowledge base, calculate the similarity among the medicines according to the representation vectors of the medicines, construct a medicine relation graph according to the similarity among the medicines, determine the specified medicines corresponding to the specified diseases according to a treatment relation base in the knowledge base, and determine the target medicine set corresponding to the specified medicines according to the medicine relation graph. By the implementation mode, the dependence on the knowledge base in drug discovery can be reduced, and the drug discovery efficiency is improved.
It is emphasized that, in order to further ensure the privacy and safety of the medicine, disease and treatment relationship sets, the medicine, disease and treatment relationship sets may also be stored in nodes of a blockchain.
Referring to fig. 5, fig. 5 is a schematic block diagram of a server according to an embodiment of the present invention. 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 memory 504. The processor 501, the input device 502, the output device 503, and the memory 504 are connected by a bus 505. The memory 504 is used for storing computer programs, including programs, and the processor 501 is used for executing the programs stored in the memory 504. Wherein the processor 501 is configured to invoke the program to perform:
acquiring a preset knowledge base of medicines and diseases, wherein the knowledge base comprises a medicine set, a disease set and a treatment relation set, and the treatment relation set comprises a plurality of relations between the diseases and the medicines;
calculating a characterization vector of each medicine in the knowledge base, wherein the characterization vector is determined according to semantic information of each medicine;
calculating the similarity among the medicines according to the characterization vectors of the medicines, and constructing a medicine relation graph according to the similarity among the medicines;
and determining a designated medicine corresponding to the designated disease according to the treatment relation library in the knowledge base, and determining a target medicine set corresponding to the designated medicine according to the medicine relation diagram.
Further, when the processor 501 calculates the similarity between the medicines according to the characterization vectors of the medicines, it is specifically configured to:
calculating Euclidean distances among the characterization vectors of the medicines according to the characterization vectors of the medicines;
and determining the similarity among the medicines according to the Euclidean distance among the characterization vectors of the medicines.
Further, when the processor 501 calculates the similarity between the medicines according to the characterization vectors of the medicines, it is specifically configured to:
calculating included angles among the characteristic vectors of the medicines according to the characteristic vectors of the medicines;
and determining the similarity among the medicines according to the included angle among the characterization vectors of the medicines.
Further, when the processor 501 constructs a medicine relation graph according to the similarity between the medicines, the processor is specifically configured to:
judging whether the similarity between any two medicines is greater than a preset similarity threshold value or not according to the similarity between the medicines;
and if so, determining that the medicines with the similarity larger than the preset similarity threshold are connected pairwise so as to construct and obtain the medicine relation graph.
Further, when the processor 501 determines the target drug set corresponding to the specified drug according to the drug relationship diagram, it is specifically configured to:
determining a node where the specified drug is located from the drug relationship graph;
determining each child node of the node where the specified medicine is located as an associated medicine set associated with the specified medicine according to the medicine relation graph;
and determining a target medicine set with the weight value larger than a preset weight value threshold according to the weight value of the node where each medicine in the associated medicine set is located.
Further, when the processor 501 determines, according to the weight of the node where each medicine in the associated medicine set is located, that the weight is greater than a preset weight threshold, the target medicine set is specifically configured to:
calculating the weight of the node where each medicine in the associated medicine set is located;
and determining a target medicine set with the weight value larger than a preset weight value threshold according to the weight value of the node where each medicine in the associated medicine set is located, and determining the medicines in the target medicine set as target medicines for treating the specified diseases.
Further, when the processor 501 calculates the weight of the node where each medicine in the associated medicine set is located, it is specifically configured to:
assigning a first energy to a node in the drug relationship graph at which each drug in the set of associated drugs associated with the specified drug is located;
assigning a second energy to other nodes in the drug relationship graph except the node where each drug in the associated drug set is located;
and calculating the weight of the node where each medicine in the associated medicine set in the medicine relation graph is located by using a specified algorithm according to the first energy and the second energy of each node in the medicine relation graph.
In the embodiment of the invention, a server can obtain a preset knowledge base of medicines and diseases, calculate the representation vectors of the medicines in the knowledge base, calculate the similarity among the medicines according to the representation vectors of the medicines, construct a medicine relation graph according to the similarity among the medicines, determine the specified medicines corresponding to the specified diseases according to a treatment relation base in the knowledge base, and determine a target medicine set corresponding to the specified medicines according to the medicine relation graph. By the implementation mode, the dependence on the knowledge base in drug discovery can be reduced, and the drug discovery efficiency is improved.
It should be understood that, in the embodiment of the present invention, the Processor 501 may be a Central Processing Unit (CPU), and the Processor may also be other general processors, Digital Signal Processors (DSPs), Application Specific Integrated Circuits (ASICs), Field-Programmable gate arrays (FPGAs) or other Programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, and the like. A general purpose processor may be a microprocessor or the processor may be any conventional processor or 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 portion of the memory 504 may also include non-volatile random access memory. For example, the memory 504 may also store device type information.
In specific implementation, the processor 501, the input device 502, and the output device 503 described in this embodiment of the present invention may execute the implementation described in the method embodiment shown in fig. 1 provided in this embodiment of the present invention, and may also execute the implementation of the drug discovery device described in fig. 4 in this embodiment of the present invention, which is not described again here.
The embodiment of the present invention further provides a computer-readable storage medium, where a computer program is stored, and when the computer program is executed by a processor, the method for discovering a drug described in the embodiment corresponding to fig. 1 may be implemented, or the device for discovering a drug according to the embodiment corresponding to fig. 4 of the present invention may also be implemented, which is not described herein again.
The computer readable storage medium may be an internal storage unit of the medicine discovery device according to any of the foregoing embodiments, for example, a hard disk or a memory of the medicine discovery device. The computer readable storage medium may also be an external storage device of the medicine discovery device, such as a plug-in hard disk, a Smart Memory Card (SMC), a Secure Digital (SD) Card, a Flash memory Card (Flash Card), and the like provided on the medicine discovery device. Further, the computer readable storage medium may also include both an internal storage unit and an external storage device of the drug discovery device. The computer readable storage medium is for storing the computer program and other programs and data required by the drug discovery device. The computer readable storage medium may also be used to temporarily store data that has been output or is to be output.
Further, the computer-readable storage medium may mainly include a storage program area and a storage data area, wherein the storage program area may store an operating system, an application program required for at least one function, and the like; the storage data area may store data created according to the use of the blockchain node, and the like.
The block chain is a novel application mode of computer technologies such as distributed data storage, point-to-point transmission, a consensus mechanism, an encryption algorithm and the like. A block chain (Blockchain), which is essentially a decentralized database, is a series of data blocks associated by using a cryptographic method, and each data block contains information of a batch of network transactions, so as to verify the validity (anti-counterfeiting) of the information and generate a next block. The blockchain may include a blockchain underlying platform, a platform product service layer, an application service layer, and the like.
The integrated unit, if implemented in the form of a software functional unit and sold or used as a stand-alone product, may be stored in a computer readable storage medium. Based on such understanding, the technical solution of the present invention essentially or partially contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product stored in a computer-readable storage medium, which includes several instructions for causing a computer device (which may be a personal computer, a terminal, or a network device) to execute all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned computer-readable storage media comprise: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, and other various media capable of storing program codes.
The above description is only a part of the embodiments of the present invention, but the scope of the present invention is not limited thereto, and any person skilled in the art can easily conceive various equivalent modifications or substitutions within the technical scope of the present invention, and these modifications or substitutions should be covered within the scope of the present invention.
Claims (10)
1. A method for drug discovery, comprising:
acquiring a preset knowledge base of medicines and diseases, wherein the knowledge base comprises a medicine set, a disease set and a treatment relation set, and the treatment relation set comprises a plurality of relations between the diseases and the medicines;
calculating a characterization vector of each medicine in the knowledge base, wherein the characterization vector is determined according to semantic information of each medicine;
calculating the similarity among the medicines according to the characterization vectors of the medicines, and constructing a medicine relation graph according to the similarity among the medicines;
and determining a designated medicine corresponding to the designated disease according to the treatment relation library in the knowledge base, and determining a target medicine set corresponding to the designated medicine according to the medicine relation diagram.
2. The method of claim 1, wherein the calculating the similarity between the drugs according to the characterization vectors of the drugs comprises:
calculating Euclidean distances among the characterization vectors of the medicines according to the characterization vectors of the medicines;
and determining the similarity among the medicines according to the Euclidean distance among the characterization vectors of the medicines.
3. The method of claim 1, wherein the calculating the similarity between the drugs according to the characterization vectors of the drugs comprises:
calculating included angles among the characteristic vectors of the medicines according to the characteristic vectors of the medicines;
and determining the similarity among the medicines according to the included angle among the characterization vectors of the medicines.
4. The method according to any one of claims 1-3, wherein the constructing a drug relationship graph according to the similarity between the drugs comprises:
judging whether the similarity between any two medicines is greater than a preset similarity threshold value or not according to the similarity between the medicines;
and if so, determining that the medicines with the similarity larger than the preset similarity threshold are connected pairwise so as to construct and obtain the medicine relation graph.
5. The method of claim 4, wherein determining the set of target drugs corresponding to the specified drugs according to the drug relationship graph comprises:
determining a node where the specified drug is located from the drug relationship graph;
determining each child node of the node where the specified medicine is located as an associated medicine set associated with the specified medicine according to the medicine relation graph;
and determining a target medicine set with the weight value larger than a preset weight value threshold according to the weight value of the node where each medicine in the associated medicine set is located.
6. The method according to claim 5, wherein the determining, according to the weight of the node where each medicine in the associated medicine set is located, the target medicine set whose weight is greater than a preset weight threshold includes:
calculating the weight of the node where each medicine in the associated medicine set is located;
and determining a target medicine set with the weight value larger than a preset weight value threshold according to the weight value of the node where each medicine in the associated medicine set is located, and determining the medicines in the target medicine set as target medicines for treating the specified diseases.
7. The method of claim 6, wherein the calculating the weight of the node where each medicine in the associated medicine set is located comprises:
assigning a first energy to a node in the drug relationship graph at which each drug in the set of associated drugs associated with the specified drug is located;
assigning a second energy to other nodes in the drug relationship graph except the node where each drug in the associated drug set is located;
and calculating the weight of the node where each medicine in the associated medicine set in the medicine relation graph is located by using a specified algorithm according to the first energy and the second energy of each node in the medicine relation graph.
8. A drug discovery device comprising means for performing the method of any one of claims 1 to 7.
9. A server comprising a processor, an input device, an output device and a memory, the processor, the input device, the output device and the memory being interconnected, wherein the memory is configured to store a computer program, the computer program comprising a program, the processor being configured to invoke the program to perform the method according to any one of claims 1-7.
10. A computer-readable storage medium, characterized in that the computer-readable storage medium stores a computer program which is executed by a processor to implement the method of any one of claims 1-7.
Priority Applications (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010404943.6A CN111694964A (en) | 2020-05-13 | 2020-05-13 | Medicine discovery method, equipment, server and readable storage medium |
| PCT/CN2020/118365 WO2021114830A1 (en) | 2020-05-13 | 2020-09-28 | Drug discovery method, device, server, and readable storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010404943.6A CN111694964A (en) | 2020-05-13 | 2020-05-13 | Medicine discovery method, equipment, server and readable storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111694964A true CN111694964A (en) | 2020-09-22 |
Family
ID=72477320
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010404943.6A Pending CN111694964A (en) | 2020-05-13 | 2020-05-13 | Medicine discovery method, equipment, server and readable storage medium |
Country Status (2)
| Country | Link |
|---|---|
| CN (1) | CN111694964A (en) |
| WO (1) | WO2021114830A1 (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112509652A (en) * | 2021-02-03 | 2021-03-16 | 南京可信区块链与算法经济研究院有限公司 | Method and system for searching potential target points of innovative drugs by combining multiple parties based on block chain |
| WO2021114830A1 (en) * | 2020-05-13 | 2021-06-17 | 平安科技（深圳）有限公司 | Drug discovery method, device, server, and readable storage medium |
Family Cites Families (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105653846B (en) * | 2015-12-25 | 2018-08-31 | 中南大学 | Drug method for relocating based on integrated similarity measurement and random two-way migration |
| CN107403069B (en) * | 2017-07-31 | 2020-05-12 | 京东方科技集团股份有限公司 | System and method for analyzing drug-disease association relationship |
| CN110020124B (en) * | 2017-10-20 | 2021-09-07 | 北京京东尚科信息技术有限公司 | Method and device for related product mining |
| CN110019531B (en) * | 2017-12-29 | 2021-11-02 | 北京京东尚科信息技术有限公司 | Method and device for acquiring similar object set |
| CN109801705A (en) * | 2018-12-12 | 2019-05-24 | 平安科技（深圳）有限公司 | Treat recommended method, system, device and storage medium |
| CN109902233A (en) * | 2019-02-28 | 2019-06-18 | 百度在线网络技术（北京）有限公司 | Smart object recommended method, device, equipment and storage medium |
| CN109934684A (en) * | 2019-03-20 | 2019-06-25 | 上海证大喜马拉雅网络科技有限公司 | A kind of Method of Commodity Recommendation, device, terminal and storage medium |
| CN110517785B (en) * | 2019-08-28 | 2022-05-10 | 北京百度网讯科技有限公司 | Similar case searching method, device and equipment |
| CN110782996A (en) * | 2019-09-18 | 2020-02-11 | 平安科技（深圳）有限公司 | Construction method and device of medical database, computer equipment and storage medium |
| CN111694964A (en) * | 2020-05-13 | 2020-09-22 | 平安科技（深圳）有限公司 | Medicine discovery method, equipment, server and readable storage medium |
-
2020
- 2020-05-13 CN CN202010404943.6A patent/CN111694964A/en active Pending
- 2020-09-28 WO PCT/CN2020/118365 patent/WO2021114830A1/en active Application Filing
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2021114830A1 (en) * | 2020-05-13 | 2021-06-17 | 平安科技（深圳）有限公司 | Drug discovery method, device, server, and readable storage medium |
| CN112509652A (en) * | 2021-02-03 | 2021-03-16 | 南京可信区块链与算法经济研究院有限公司 | Method and system for searching potential target points of innovative drugs by combining multiple parties based on block chain |
| CN112509652B (en) * | 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 | Method and system for searching potential target points of innovative drugs by combining multiple parties based on block chain |
Also Published As
| Publication number | Publication date |
|---|---|
| WO2021114830A1 (en) | 2021-06-17 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| JP7220702B2 (en) | Pseudorandom Number Generation in Blockchain | |
| Mantel | Ranking procedures for arbitrarily restricted observation | |
| CN112700838A (en) | Big data-based medication scheme recommendation method and device and related equipment | |
| US10672514B2 (en) | Systems and methods for clinical decision support | |
| CN109637615B (en) | Method, device and equipment for judging abnormal medical prescription and readable storage medium | |
| Silversides et al. | Fluid management and deresuscitation practices: a survey of critical care physicians | |
| US10496793B1 (en) | Systems and methods for determining eligibility in a prescription safety network program | |
| US20140157382A1 (en) | Observable authentication methods and apparatus | |
| CN111694964A (en) | Medicine discovery method, equipment, server and readable storage medium | |
| KR102327062B1 (en) | Apparatus and method for predicting result of clinical trial | |
| US10318710B2 (en) | System and method for identifying healthcare fraud | |
| Wang et al. | The secular trends in the incidence rate and outcomes of out-of-hospital cardiac arrest in Taiwan—a nationwide population-based study | |
| CN113409078A (en) | Point issuing method, device, equipment and storage medium | |
| CN112214588A (en) | Multi-intention recognition method and device, electronic equipment and storage medium | |
| CN110535958B (en) | Health information storage method and related equipment | |
| KR20180100995A (en) | Method and system for processing user authentication | |
| CN112017776B (en) | Disease prediction method based on dynamic graph and medical knowledge map and related equipment | |
| Dubovitskaya et al. | Intelligent health care data management using blockchain: current limitation and future research agenda | |
| Jafri et al. | Blockchain applications for the healthcare sector: Uses beyond Bitcoin | |
| Herrin et al. | An empiric approach to identifying physician peer groups from claims data: an example from breast cancer care | |
| CN109862006A (en) | A kind of block catenary system cut-in method, apparatus and system | |
| Litvin et al. | The possibilities of blockchain technology in medicine | |
| CN113051622B (en) | Index construction method, device, equipment and storage medium | |
| CN115204914A (en) | Data storage method, device, equipment and medium for drug anti-counterfeiting tracing source block chain | |
| CN112435745B (en) | Method and device for recommending treatment strategy, electronic equipment and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |