KR102174764B1 - Method, Device and Computer-Readable Medium for Drug Repositioning Using Drug-Disease Vectors Based On an Integrated Network - Google Patents

Abstract

The present invention relates to a method, an apparatus, and a computer-readable medium for recreating a new drug using an integrated network-based drug-disease vector, and more specifically, to derive and derive a drug vector of an investigational drug that can be recreated as a new drug. A new drug re-creation method, device and computer-readable medium using an integrated network-based drug-disease vector that derives drugs that can exert similar efficacy to existing drugs prescribed for the disease based on the drug vector. About.

Description

[Method, Device and Computer-Readable Medium for Drug Repositioning Using Drug-Disease Vectors Based On an Integrated Network}

The present invention relates to a method, an apparatus, and a computer-readable medium for recreating a new drug using an integrated network-based drug-disease vector, and'more specifically, derive a drug vector of an investigational drug that can be recreated as a new drug, Based on the derived drug vector, a new drug re-creation method, device, and computer-readable medium using an integrated network-based drug-disease vector that derives drugs that can exhibit similar efficacy to existing drugs prescribed for the disease. It is about.

Developing a new drug for a disease is a process that takes a very long time and requires a lot of cost for the development, and even if a new drug is developed, it is also necessary to obtain approval for the drug by an agency such as the Food and Drug Administration in the country. Very tricky. In the US, for example, the number of new drugs approved by the FDA has been declining since the 1990s. As described above, research on Computational Biology has been actively conducted as a method for effectively using resources necessary to derive new drugs such as development time and cost.

Computational biology is a field that solves biological problems by using computers, and it is a science that conducts biological research using computers that can process vast amounts of information quickly.In computational biology, in particular, new uses for existing drugs. Research on drug repositioning is being conducted to find out.

In the research related to the creation of new drugs, various methods are currently used in computational biology, and among them, network-based analysis is one of the most widely used methods. In order to build a network in this way, there have been attempts to apply various properties of drugs and diseases to the network.

In previous studies, information on side effects, phenotypes, and pathways were used to build a drug network or disease network, but the network built through such information was clinical compound (Clinical Compound). ) And the inability to include drugs that have failed in clinical trials.

On the other hand, a study of constructing a network using a biomolecular network has also appeared, and this study uses the relationship between drugs and diseases in a biomolecular network, but most networks using the method use genes or proteins. There is a drawback of not considering the kind of interaction between them.

Research on networks using biomolecule networks is to derive similarities between drugs by deriving the shortest route from drugs to diseases through networks, and based on the similarity, various methods including Guilt by Association are used to treat the disease. Drug was derived. Although the process of applying various drugs to a specific disease through such a method has been suggested, it is very important to consider the interaction characteristics between genes in order to discover the relationship between drugs and diseases in terms of treatment.

On the other hand, among the conventional technologies as described above, in Korean Patent Publication No. 10-2017-0141317 ("Method and apparatus for recreating new drugs using biological networks"), in deriving the shortest path between a drug and a disease gene, the path The shortest path is derived based only on the number of genes included in, that is, the number of nodes, and a configuration is disclosed in which the score is calculated by considering only whether the genes of the shortest path are active/inhibited, but considering whether or not the genes are neutral. It has a problem that it is difficult to derive an accurate shortest route because it is not done, and additionally, the technology does not include an element that can verify it based on the calculated score, so it is difficult to verify the drug.
In this way, the establishment of a network that reflects the characteristics of interactions between various genes is an important prerequisite in the field of new drug creation.

Korean Patent Publication No. 10-2017-0141317 (Method and device for re-creation of new drugs using biological networks, published on December 26, 2017)

The present invention relates to a method, an apparatus, and a computer-readable medium for recreating a new drug using an integrated network-based drug-disease vector, and more specifically, to derive and derive a drug vector of an investigational drug that can be recreated as a new drug. Based on the drug vector, a new drug re-creation method, device, and computer-readable medium using an integrated network-based drug-disease vector that derives drugs that can exert similar efficacy to existing drugs prescribed for the disease. To provide.

In order to solve the above problems, the present invention is a method of recreating a new drug for a specific disease using a drug-disease vector implemented as a computing device, and two or more drugs that can be recreated as a new drug for a specific disease A drug information receiving step of receiving irradiated drug information on the irradiated drug; One of drugs, genes, and proteins between the irradiated drug and one or more disease genes for a specific disease, based on the interaction data including the interaction relationship with two or more of genes, proteins, and drugs and the irradiated drug information. Drug-disease vector derivation step of deriving a drug-disease vector for each irradiated drug in the path including the above as a node; And a new drug derivation step of deriving an evaluation model based on the information on the drug-disease vector of the investigational drug, and deriving a new drug for the specific disease from among the investigational drugs based on the evaluation model. Provides a method of re-creating a new drug for a specific disease using a drug-disease vector.

In the present invention, the method of recreating a new drug for a specific disease using the drug-disease vector is to load data including an interaction relationship with two or more of genes, proteins, and drugs from the computing device or reference database. It may further include an interaction data conversion step of converting based on a preset relationship criterion.

In the present invention, in the interaction data conversion step, in the data including the interaction relationship with two or more of the loaded genes, proteins, and drugs, based on the relationship criteria, two relationships among genes, proteins, and drugs are positive type, Converted into one of a voice type and a neutral type to derive transformed interaction data, and the drug-disease vector deriving step may use the transformed interaction data.

In the present invention, the drug-disease vector derivation step includes: a basic path deriving step of deriving a basic path between the irradiated drug and the disease gene based on the irradiated drug information and the interaction data; It may include; a shortest path calculation step of deriving the shortest path between the irradiated drug and the disease gene based on the basic path, and deriving the drug-disease vector based on the shortest path.

In the present invention, the shortest path includes at least one positive or negative type of interaction between one or more drugs, genes, and proteins included as nodes in the shortest path, and the interaction data includes drugs, genes, And the positive type, the negative type, and the neutral type as a correlation of two or more of the proteins, and the neutral type may include a case in which two or more of a drug, a gene, and a protein have a binding relationship.

In the present invention, the shortest path includes one or more nodes, and the step of calculating the shortest path is based on the number of nodes connected to each node included in the shortest path and a correlation type with nodes adjacent to each node. The drug-disease vector can be derived.

In the present invention, the step of deriving a new drug includes information on the drug-disease vector of the reference drug known to be effective against the specific disease among the irradiated drugs, and the drug not known to be effective against the specific disease among the irradiated drugs. An evaluation model can be derived based on the drug-disease vector.

In the present invention, in the drug-disease vector extraction step, for each investigational drug, a drug-disease vector including a value for each of one or more disease genes for the specific disease is derived, and the new drug extraction step is the investigation A group classification step of classifying at least one of the drugs into a first set and classifying at least one of the irradiated drugs into a second set; And an evaluation model deriving step of deriving an evaluation model based on the drug-disease vector of the irradiated drug belonging to the first set and the drug-disease vector of the irradiated drug belonging to the second set.

In the present invention, the first set includes one or more of the reference drugs known to be effective against the specific disease among the irradiated drugs, and the second set is not known to be effective against the specific disease among the irradiated drugs. It may contain one or more of the drugs.

In the present invention, in the step of deriving an evaluation model, two or more preliminary evaluation models may be derived using the plurality of second sets, and the evaluation model may be derived based on an evaluation value of the preliminary evaluation model.

In order to solve the above problems, the present invention is an apparatus for re-creating a new drug for a specific disease using a drug-disease vector including at least one memory and at least one processor, which will be recreated as a new drug for a specific disease. A drug information receiving unit for receiving irradiated drug information for two or more irradiated drugs; One of drugs, genes, and proteins between the irradiated drug and one or more disease genes for a specific disease, based on the interaction data including the interaction relationship with two or more of genes, proteins, and drugs and the irradiated drug information. A drug-disease vector extraction unit for deriving a drug-disease vector for each irradiated drug in the path including the above as a node; And a new drug extraction unit for deriving an evaluation model based on the information on the drug-disease vector of the investigational drug, and for deriving a new drug for the specific disease from among the investigational drugs based on the evaluation model. Provides a device for re-creating a new drug for a specific disease using a drug-disease vector.

In order to solve the above problems, the present invention provides a computer-readable recording medium, wherein the computer-readable recording medium stores instructions for causing a computing device to perform the following steps, the steps; A drug information receiving step of receiving irradiated drug information for two or more irradiated drugs that can be recreated as new drugs for a specific disease; One of drugs, genes, and proteins between the irradiated drug and one or more disease genes for a specific disease, based on the interaction data including the interaction relationship with two or more of genes, proteins, and drugs and the irradiated drug information. A drug-disease vector derivation step of deriving a drug-disease vector for each irradiated drug in the path including the above as a node; And a new drug derivation step of deriving an evaluation model based on the information on the drug-disease vector of the investigational drug, and deriving a new drug for the specific disease from among the investigational drugs based on the evaluation model. Computer-readable recording media are provided.

According to an embodiment of the present invention, it is possible to exert an effect of deriving a more accurate new drug re-creation model by applying genes in a binding relationship to a network.

According to an embodiment of the present invention, by deriving the shortest route of the network, deriving a vector value based on the shortest route, and creating a model for deriving a drug by comparing it with a reference drug, it is possible to derive more accurate drugs. Can exert.

According to an embodiment of the present invention, a network leading to a drug and a disease gene is generated to derive a pathway, so that the mechanism by which the drug reaches the disease gene may be identified.

According to an embodiment of the present invention, through the process of generating a plurality of models capable of deriving the derived drug, comparing the plurality of models to derive a final model, and verifying the drug derived through the final model, It can exert an effect that can improve the accuracy of the final model.

1 is a diagram schematically showing a process of deriving a new drug having similar efficacy to a reference drug based on interaction data and drug information according to an embodiment of the present invention.
2 is a diagram schematically showing an apparatus for recreating a new drug using a drug-disease vector based on an integrated network according to an embodiment of the present invention.
3 is a diagram schematically showing the internal components of an apparatus for recreating a new drug using a drug-disease vector based on an integrated network according to an embodiment of the present invention.
4 is a diagram schematically showing interaction data converted by an interaction data conversion unit according to an embodiment of the present invention.
5 is a diagram schematically showing steps performed by a drug-disease vector extraction unit according to an embodiment of the present invention.
6 is a diagram schematically showing the shortest path derived by the drug-disease vector extraction unit according to an embodiment of the present invention.
7 is a diagram schematically illustrating a process of deriving a drug-disease vector by a drug-disease vector deriving unit in the shortest path according to an embodiment of the present invention.
8 is a diagram schematically showing a step of performing a drug delivery unit according to an embodiment of the present invention.
9 is a diagram schematically showing a first set and a second set derived from a group of irradiated drugs according to an embodiment of the present invention.
10 is a block diagram illustrating an example of an internal configuration of a new drug re-creation device using an integrated network-based drug-disease vector according to an embodiment of the present invention.

In the following, various embodiments and/or aspects are now disclosed with reference to the drawings. In the following description, for purposes of explanation, a number of specific details are disclosed to aid in an overall understanding of one or more aspects. However, it will also be appreciated by those of ordinary skill in the art that this aspect(s) may be practiced without these specific details. The following description and the annexed drawings set forth in detail certain illustrative aspects of one or more aspects. However, these aspects are exemplary and some of the various methods in the principles of the various aspects may be used, and the descriptions described are intended to include all such aspects and their equivalents.

Further, various aspects and features will be presented by a system that may include multiple devices, components and/or modules, and the like. It is also noted that various systems may include additional devices, components and/or modules, and/or may not include all of the devices, components, modules, etc. discussed in connection with the figures. It must be understood and recognized.

As used herein, “an embodiment,” “example,” “aspect,” “example,” and the like may not be construed as having any aspect or design described as being better or advantageous than other aspects or designs. . The terms'~part','component','module','system', and'interface' used below generally mean a computer-related entity, for example, hardware, hardware It can mean a combination of software and software, or software.

In addition, the terms "comprising" and/or "comprising" mean that the corresponding feature and/or element is present, but excludes the presence or addition of one or more other features, elements, and/or groups thereof. It should be understood as not.

In addition, terms including ordinal numbers such as first and second may be used to describe various elements, but the elements are not limited by the terms. These terms are used only for the purpose of distinguishing one component from another component. For example, without departing from the scope of the present invention, a first element may be referred to as a second element, and similarly, a second element may be referred to as a first element. The term and/or includes a combination of a plurality of related listed items or any of a plurality of related listed items.

In addition, in the embodiments of the present invention, unless otherwise defined, all terms used herein including technical or scientific terms are commonly understood by those of ordinary skill in the art to which the present invention belongs. It has the same meaning as. Terms as defined in a commonly used dictionary should be interpreted as having a meaning consistent with the meaning in the context of the related technology, and unless explicitly defined in the embodiments of the present invention, an ideal or excessively formal meaning Is not interpreted as.

1 is a diagram schematically showing a process of deriving a new drug having similar efficacy to a reference drug based on interaction data and drug information according to an embodiment of the present invention.

Referring to FIG. 1, the interaction data corresponds to a first element for deriving drug-disease vector data, and specifically, the first element includes the interaction relations included in the interaction data converted based on a relationship criterion. The interaction data is included. On the other hand, drug information corresponds to a second element for deriving drug-disease vector data, and the drug information is information received by a user's direct or indirect input, and two or more corresponding to a candidate group for deriving a new drug. It includes the drug name and chemical formula for the investigational drug, information on the disease improved by the new drug, and information on the reference drug that exerts efficacy against the disease.

The interaction data and the drug information are basic data for deriving drug-disease vector data to be described later, and the interaction data and the drug information are inputted by the user, or, such as KEGG, BioCarta, PID, Reactome, and DrugBank. It can also be retrieved from a database containing information.

Based on the interaction data and the drug information, the device for recreating a new drug using a drug-disease vector of the present invention derives a drug-disease vector, and the drug-disease vector first generates a basic path, and the generated The shortest path is derived from the basic path, and the drug-disease vector is derived based on the node forming the shortest path and the interaction relationship.

On the other hand, the meaning of the pathway in the basic route and the shortest route means a network from a specific drug to one or more disease genes that finally affect the efficacy of the drug through one or more target genes that the specific drug first affects. And, the path from the specific drug to the disease gene includes one or more nodes. The node corresponds to genes, proteins, and biomolecules, and thus the pathway corresponds to a network from a specific drug to a target gene and a target gene to a node and a disease gene from the node.

Finally, based on the drug-disease vector data, a new drug that can exhibit similar efficacy to the reference drug prescribed for the disease is derived. Based on the drug-disease vector, the irradiated drug is classified into a plurality of sets, and an evaluation model is generated based on the set, and a new drug can be derived from the irradiated drug through the evaluation model.

Hereinafter, a device for recreating a new drug using the drug-disease vector of the present invention will be described in detail.

2 is a diagram schematically showing an apparatus for recreating a new drug using a drug-disease vector based on an integrated network according to an embodiment of the present invention.

Referring to FIG. 2, a computing device 1000 capable of functioning as a device for recreating a new drug using a drug-disease vector based on an integrated network according to an embodiment of the present invention is connected to an external reference database 2000.

The reference database 2000 may be composed of a plurality of databases, and the reference database 2000 includes a first reference database 2100, a second reference database 2200, and an Nth reference database 2300. I can.

Each reference database contains information on drugs and various interaction data that can be used as drug action pathways. According to an embodiment of the present invention, each reference database including BioCarta, Reactome, PID, KEGG, DrugBank, DisGeNet, and CTD, etc., which have databases for drug-gene interaction data and gene-node interaction data. It can be configured and operated.

The reference database 2000 is connected via a network to a computing device 1000 that can function as a device for recreating a new drug using a drug-disease vector based on an integrated network, and the reference database 2000 ) Data can be accessed.

3 is a diagram schematically showing the internal components of an apparatus for recreating a new drug using a drug-disease vector based on an integrated network according to an embodiment of the present invention.

Referring to FIG. 3, a computing device 1000 capable of functioning as a new drug re-creation device using an integrated network-based drug-disease vector according to an embodiment of the present invention includes a processor 100, a bus (not shown), A network interface 300 and a memory 400 may be included. The memory 400 may store an operating system 410, a service providing routine 420, a reference database 430, a conversion interaction database 440, and a criterion setting unit 450.

The processor 100 may include an interaction data conversion unit 110, a drug information receiving unit 120, a drug-disease vector deriving unit 130, a new drug deriving unit 140, and a new drug verification unit 150. In other embodiments, the device for recreating a new drug using an integrated network-based drug-disease vector may include more components than those of FIG. 3.

The memory 400 is a computer-readable recording medium, and may include a permanent mass storage device such as a random access memory (RAM), read only memory (ROM), and a disk drive. In addition, program codes or data for the operating system 410, the service providing routine 420, the reference database 430, the conversion interaction database 440, and the determination criterion setting unit 450 may be stored in the memory. These software components may be loaded from a computer-readable recording medium separate from the memory 400 using a drive mechanism (not shown). Such a separate computer-readable recording medium may include a computer-readable recording medium (not shown) such as a floppy drive, a disk, a tape, a DVD/CD-ROM drive, or a memory card. In another embodiment, software components may be loaded into the memory 400 through the network interface 300 rather than a computer-readable recording medium.

The bus (not shown) may enable communication and data transmission between device components that control the computing device 1000. The bus (not shown) may be configured using a high-speed serial bus, a parallel bus, a storage area network (SAN), and/or other suitable communication technology.

The network interface 300 may be a computer hardware component for connecting the computing device 1000 functioning as a new drug re-creation device using an integrated network-based drug-disease vector to a computer network. The network interface 300 may connect the computing device 1000 functioning as a new drug re-creation device using an integrated network-based drug-disease vector to a computer network through a wireless or wired connection. Through the network interface 300, the computing device 1000 functioning as a new drug re-creation device using an integrated network-based drug-disease vector may be wirelessly or wiredly connected to the reference database 2000.

The processor 100 may be configured to process instructions of a computer program by performing input/output operations of the computing device 1000, which functions as a device for determining basic arithmetic, logic, and similarity of drugs. Instructions may be provided to the processor 100 by the memory 400 or the network interface 300 and via a bus (not shown). The processor 100 may be configured to execute program codes for the operating system 410, the service providing routine 420, the reference database 430, the conversion interaction database 440, and the determination criterion setting unit 450. Such program codes may be stored in a recording device such as a memory.

The operating system 410, the service providing routine 420, the reference database 430, the conversion interaction database 440, and the determination criterion setting unit 450 perform the operation of the computing device 1000, which will be described below. Can be configured for In the processor 100, some components may be omitted, additional components not shown may be further included, or two or more components may be combined according to a method of controlling the computing device 1000.

Meanwhile, such a computing device preferably corresponds to a personal computer or a server, and in some cases, a smart phone, a tablet, a mobile phone, a video phone, and an e-book reader (e -book reader), desktop PC, laptop PC, netbook PC, personal digital assistant (PDA, hereinafter referred to as'PDA'), portable Multimedia player (portable multimedia player: PMP, hereinafter referred to as'PMP'), mp3 player, mobile medical device, camera, wearable device (for example, head-mounted Device (head-mounted device: HMD, for example, to be referred to as'HMD'), electronic clothing, electronic bracelet, electronic necklace, electronic appcessory, electronic tattoo, or smart watch ), etc.

A method for recreating a new drug for a specific disease using a drug-disease vector, implemented as a computing device according to an embodiment of the present invention, for two or more irradiated drugs that can be recreated as new drugs for a specific disease. A drug information receiving step of receiving irradiated drug information; One of drugs, genes, and proteins between the irradiated drug and one or more disease genes for a specific disease, based on the interaction data including the interaction relationship with two or more of genes, proteins, and drugs and the irradiated drug information. A drug-disease vector derivation step of deriving a drug-disease vector for each irradiated drug in the path including the above as a node; And deriving an evaluation model based on information on the drug-disease vector of the investigational drug, and deriving a new drug for the specific disease from among the investigational drugs based on the evaluation model.

The interaction data conversion unit 110 performs a step of converting the interaction data stored in the reference database according to a preset criterion. The predetermined criterion corresponds to a criterion for converting according to an interaction relationship of the interaction data, and the interaction data converted through the corresponding step is separately stored in the conversion interaction database 440 included in the memory unit, or , It may be included in the reference database 2000 configured separately from the computing device 1000 or the reference database 430 included in the memory 400. A detailed operation of the interaction data conversion unit 110 will be described later.

The drug information receiving step is performed by the drug information receiving unit 120, and information on the investigational drug that can be derived as a new drug, information on a specific disease for which a new drug is to be derived, and 1 that is previously prescribed for the disease. Information on the reference drug is received, and such a process may be performed by receiving information input by a user or calling corresponding information included in the reference database.

On the other hand, the drug-disease vector derivation step is performed in the drug-disease vector derivation unit 130, and the interaction data converted by the interaction data conversion unit 110 and the drug information receiving unit 120 A drug-disease vector is derived based on the received information on the investigational drug, information on a specific disease, and information on the reference drug. A detailed operation for the drug-disease vector derivation step will be described later.

The new drug extraction step is performed by the new drug delivery unit 140 and is not known to be effective against a specific disease contained in the at least one investigational drug based on the drug-disease vector derived in the drug-disease vector extraction step. It carries out the process of deriving a new drug that can be effective against the disease. A detailed operation for the new drug extraction step will be described later.

Finally, the new drug verification unit 150 performs a new drug verification step of verifying whether the new drug derived in the new drug extraction step is effective in the corresponding disease compared to the irradiated drug not derived as the new drug. The new drug verification step derives a first degree of similarity for the efficacy of the new drug and the reference drug, and derives a second degree of similarity for the efficacy of the investigational drug and the reference drug not derived as the new drug, and the first similarity and The new drug is verified based on the second similarity.

4 is a diagram schematically showing interaction data converted by the interaction data conversion unit 110 according to an embodiment of the present invention.

The method of recreating a new drug for a specific disease using the drug-disease vector is a preset relationship by loading data including interaction relationships for two or more of genes, proteins, and drugs from the computing device or a reference database. It further includes an interaction data conversion step of converting based on the criterion.

Specifically, the interaction data conversion step is performed by the interaction data conversion unit 110, and the interaction data conversion step includes drugs, genes, proteins, and more specifically, biomolecules included in the interaction data. Including, the interaction data for two or more may be converted based on a preset relationship criterion. The relationship criterion may be directly or indirectly input by the user, and may be separately stored in the determination criterion setting unit 450 included in the memory unit 400.

On the other hand, in the interaction data conversion step, in the data including the interaction relationship with two or more of the loaded genes, proteins, and drugs, based on the relationship criteria, two relationships among genes, proteins and drugs are positive type and negative. Converted to one of type and neutral type and derived as transformed interaction data.

Specifically, the interaction name shown in FIG. 4 refers to an interaction relationship between two or more drugs, genes, proteins, and more specifically, biomolecules included in the interaction data, and is shown below the interaction name. Activation (active relationship), expression (expression relationship), repression (inhibition relationship), inhibition (inactive relationship), binding (binding relationship), etc. correspond to the types of the interaction relationship.

In addition, interaction type in our network corresponds to the transformation interaction data converted based on the relation criteria in the interaction data transformation step, and the positive (positive) shown below the interaction type in our network Type), negative (speech type), and neutral (neutral type) correspond to the types of the transformed interaction data.

Specifically, the relationship criterion is to convert the interaction relationship into the positive type when the interaction relationship of the interaction data is the active relationship and the expression relationship, and the negative when the interaction relationship is the inhibition relationship and the inactive relationship. It is converted into a type, and when the interaction relationship is a binding relationship, it is converted into the neutral type.

The activity relationship and the expression relationship correspond to the same factor in the process of deriving the shortest path for deriving the drug-disease vector, which will be described later, so that the positive type is converted, and the inhibition relationship and the inactive relationship are the shortest path. It corresponds to the same element in the process of deriving a so that it is converted into the speech type. On the other hand, phosphorylation, indirect effect, dissociation, dephosphorylation, ubiquitination, missing interaction, methylation, glycosylation, and state change below the interaction name shown in FIG. 4 do not have a significant effect on deriving the drug-disease vector, so they are not considered. Does not.

On the other hand, when the path is derived by considering only the positive type and the negative type, the number of genes, proteins and biomolecules included in the positive type and the negative type is considerably smaller than the total number of genes, proteins and biomolecules. There are limitations in deriving various basic pathways from drugs to disease genes. On the other hand, in the case of deriving the basic route from the specific drug to the disease gene in consideration of the neutral type as in the present invention, the effect of deriving a more diverse basic route than the case described above can be exhibited.

5 is a diagram schematically showing steps performed by a drug-disease vector extraction unit according to an embodiment of the present invention.

The drug-disease vector derivation step uses the transformed interaction data, and the drug-disease vector derivation step includes a basic path between the irradiated drug and the disease gene based on the irradiated drug information and the interaction data. A step of deriving a basic path (S10); And a shortest path calculation step (S20) of deriving the shortest path between the irradiated drug and the disease gene based on the basic path, and deriving the drug-disease vector based on the shortest path.

Specifically, the drug-disease vector extraction step is performed in the drug-disease vector extraction unit 130, and the drug-disease vector extraction step is the basic path including a mechanism of action between the irradiated drug and the disease gene. The basic path deriving step (S10) to derive; is performed. The basic pathway includes all pathways that can be linked from the drug to the disease gene. In addition, the path from the drug to the disease gene includes a target gene and a node that are primarily affected by the drug, and the node may correspond to a gene, a protein, and a biomolecule. In the basic pathway, two or more connections among components such as the irradiation drug, the target gene, the node, and the disease gene are formed based on the transformation interaction data. The connection of the components is displayed based on a positive type, a negative type, and a neutral type corresponding to the type of the transformation interaction data. The basic path corresponds to a basic path for deriving the shortest path and drug-disease vector to be described later, and the shortest path can be derived through the basic path to derive the drug-disease vector.

On the other hand, the shortest path calculation step (S20) derives the shortest path based on the basic path derived in the basic path extraction step, and derives the drug-disease vector based on the shortest path. The shortest path includes at least one positive type or negative type of transformation interaction data included in each path among a plurality of paths included in the basic path, and corresponds to a path composed of the fewest nodes. An embodiment of the process of deriving the shortest path will be described later in FIG. 6.

Thereafter, in the shortest path step, the drug-disease vector is derived from the derived shortest path. The drug-disease vector is derived based on the transformation interaction data included in the shortest path and the number of connections between nodes included in the shortest path and adjacent nodes. An embodiment of the process of deriving the drug-disease vector will be described later in FIG. 7.

6 is a diagram schematically showing the shortest path derived by the drug-disease vector extraction unit according to an embodiment of the present invention.

In the shortest path, the correlation between one or more drugs, genes, and proteins included as nodes in the shortest path includes at least one positive type or negative type, and the interaction data is 2 of drugs, genes, and proteins. As described above, the positive type, the negative type, and the neutral type are included, and the neutral type includes a case in which two or more of a drug, a gene, and a protein are in a binding relationship.

Specifically, referring to FIG. 6, FIG. 6 is a diagram showing a part of the shortest path from the target gene to the disease gene through a plurality of nodes, and FIG. 6 (a) is the conversion between the irradiated drug and the target gene. A diagram showing a part of the shortest path when the action data is of a neutral type, and FIG. 6B shows a part of the shortest path when the conversion interaction data between the irradiated drug and the target gene is not a neutral type. It corresponds to one drawing.

When the transformation interaction data is a neutral type, the interaction relationship is a binding relationship, and the neutral type maintains normal actions in the body, and the transformation corresponding to a positive type or a negative type that affects a specific disease by a drug This is interaction data. Therefore, in the case where the shortest route can be, at least one of the pathways from the irradiated drug to the disease gene should include the positive type or the negative type.

6A and 6B include a path from target gene 1 to disease gene through node 3, node 2, and node 1, and two paths through node 3 and a node at the bottom. On the other hand, in the case of (a) of FIG. 6, since it is assumed that the conversion interaction data between the irradiated drug and the target gene 1 is of a neutral type, node 3 and node 3 of the two paths shown in FIG. 6 (a) A path including transformed interaction data in which node 2 is a positive type, node 2 and node 1 is a negative type, and node 1 and a disease gene is a negative type may be derived as the shortest path.

On the other hand, in the case of (b) of FIG. 6, it is assumed that the transformation interaction data between the irradiated drug and the target gene 1 is not a neutral type, and thus transformation interaction data included in the corresponding path in the two paths is Although all are neutral types, the path from target gene 1 with the smallest number of nodes included to node 3 and the node at the bottom to the disease gene can be derived as the shortest path. On the other hand, in the case of the path from target gene 1 to node 3, node 2, and node 1 to the disease gene, the drug corresponds to a path that can affect the gene, but the number of nodes passing through is compared to the derived shortest path. Because there are many, it is not derived as the shortest path.

As shown in Fig. 6, the method of deriving the shortest path by dividing the case of the neutral type and the case of the non-neutral type according to the conversion interaction data with the irradiation drug and the target gene is only one embodiment. Various methods may be used, such as a method of deriving a path including the least node among paths including a positive type or a negative type as the shortest path in which at least one transformation interaction data for the basic path leading to the gene is determined. As shown, the shortest path is not only one path, but two or more paths may be derived.

7 is a diagram schematically illustrating a process of deriving a drug-disease vector by a drug-disease vector deriving unit in the shortest path according to an embodiment of the present invention.

The shortest path includes one or more nodes, and in the shortest path calculation step, the drug-disease is based on the number of nodes connected to each node included in the shortest path and a correlation type with nodes adjacent to each node. Derive a vector.

Specifically, referring to FIG. 7, (a) of FIG. 7 shows transformational interaction data between the irradiated drug and one or more target genes for a plurality of irradiated drugs, and vector values between the target gene and the plurality of disease genes. It is a drawing. The number of target genes forming an interaction relationship with the irradiated drug may be 1 or more, and likewise, the number of disease genes affected by the target gene may also be 1 or more.

On the other hand, in the case of the first irradiated drug in Fig. 7A, it forms a negative type with the target gene 1, and forms a neutral type with the target gene 2. Meanwhile, values between the target gene 1 and the disease gene a or the disease gene b correspond to a basic vector for deriving a drug-disease vector.

The process of deriving the basic vector will be described with reference to FIG. 6 as follows. Factors for deriving the basic vector from the path shown in FIG. 6 include a path type value (T) and a path weight value (W). First, an equation for deriving a path type value (T) is as follows.

E is a set of transformation interaction data of positive type or negative type in the corresponding path, and e _i corresponds to the transformation interaction data between the i-th node and the i+1-th node. If the transformed interaction data is the positive type, +1 is assigned, and if the negative type is the negative type, -1 is assigned. If there is a neutral type in the path, the neutral type is ignored. Therefore, the path type value (T) from the target gene 1 to the disease gene in FIG. 6A has +1 by one positive type and two negative types.

Meanwhile, the equation for deriving the path weight value W is as follows.

을 갖게 된다.d _i corresponds to the number of connections between the i-th node included in the path and the adjacent node. Therefore, in Figure 6 (a), the path weight value (W) from target gene 1 to disease gene is connected to one node adjacent to target gene 1, node 3 is connected to three nodes, and node 2 is It is connected to two adjacent nodes, and node 1 is connected to one disease gene.

Will have.

An equation for deriving the basic vector V based on the path type value T and the path weight W derived above is as follows.

을 갖게 된다.m means the maximum number of target genes that form the shortest path with the disease gene, and the basic vector (V) is formed by the product of the path type value (T) and the path weight value (W). For example, in Fig. 6(a), the disease gene forms the shortest path with a single target gene 1, so the basic vector V is

Will have.

Finally, the formula for deriving the drug-disease vector (DV) based on the basic vector (V) is as follows.

을 갖게 된다.sign(T _i ) corresponds to the transduction interaction data between the irradiated drug and the i-th target gene. In the case of the positive type, +1 is assigned, and in the case of the negative type, -1 is assigned. If there is a neutral type in the path, the neutral type is ignored. Therefore, in Figure 6 (a), the drug-disease vector (DV) is assumed to be a case where the irradiated drug and the target gene 1 are of a neutral type,

Will have.

, 상기 타겟유전자 1과 질병유전자 b 사이의 기초벡터(V)는

, 타겟유전자 2와 상기 질병유전자 b 사이의 기초벡터(V)는

, 상기 타겟유전자 2와 질병유전자 c 사이의 기초벡터(V)는

에 해당한다.Referring to Figure 7 through the above method, in the case of the first irradiated drug of Figure 7 (a), the basic vector (V) between the target gene 1 and the disease gene a is

, The basic vector (V) between the target gene 1 and the disease gene b is

, The basic vector (V) between the target gene 2 and the disease gene b is

, The basic vector (V) between the target gene 2 and the disease gene c is

Corresponds to.

On the other hand, Figure 7 (b) is a table summarizing the process of deriving the basic vector (V) and drug-disease vector (DV) obtained in Figure 7 (a). In the case of the target gene (TG) 1 in the table, since the relationship with the irradiated drug is negative, it is indicated in bold so that it can be distinguished. In addition, in the case of the disease gene (DG) b from the table, it can be seen that target gene 1 and target gene 2 are included in the target gene (TG) forming the path with the disease gene.

에 -1을 곱한 값을 상기 타겟유전자 2와 상기 질병유전자 b 사이의 기초벡터(V) 값인

에 더한 값에 해당하는

가 최종적으로 해당 조사약물과 상기 약물유전자 b 사이의 약물-질병벡터(DV)에 해당한다. 도 7에 도시된 각 조사약물 및 각 질병유전자에 대한 약물-질병벡터들을 도 7의 (c)에 표로 도시하였다.The table at the bottom of Fig. 7(b) corresponds to a table for deriving a drug-disease vector (DV) based on the table at the top of Fig. 7(b). The drug-disease vector (DV) is derived for each disease gene, and thus the drug-disease based on the basic vector (V) corresponding to the disease gene and the conversion interaction data between the irradiated drug and the target gene. Derive a vector (DV). For example, in the case of disease gene b, it is affected by the target gene 1 and the target gene 2, and the target gene 1 has a negative relationship with the irradiated drug, so the corresponding basic vector (V) value is

Multiplied by -1 is the basic vector (V) value between the target gene 2 and the disease gene b

Corresponding to the value added to

Finally corresponds to a drug-disease vector (DV) between the irradiated drug and the drug gene b. Drug-disease vectors for each irradiated drug and each disease gene shown in FIG. 7 are shown in a table in FIG. 7 (c).

Referring to the table shown in (c) of FIG. 7, each drug-disease vector corresponding to the disease gene a, the disease gene b, and the disease gene c for a plurality of irradiated drugs is included. In addition to those shown in the table above, the types of one or more disease genes corresponding to each investigational drug may be different, and thus some investigational drugs may not contain a drug-disease vector with a specific disease gene.

The process of deriving the drug-disease vector shown in FIG. 7 is only an example, and without going through the above steps, one or more shortest routes from the irradiated drug to the one or more disease genes are considered as a whole, and the irradiated drug and one or more Various derivation methods can be used, such as deriving each drug-disease vector between disease genes at once.

8 is a diagram schematically showing a step of performing a drug delivery unit according to an embodiment of the present invention.

The new drug extraction step includes information on the drug-disease vector of a reference drug known to be effective against the specific disease among the irradiated drugs, and the drug-disease of a drug that is not known to be effective against the specific disease among the irradiated drugs. An evaluation model is derived based on the vector.

Specifically, the new drug extraction unit 140 performs the new drug extraction step, and a specific drug to derive a new drug from the drug-disease vector of a plurality of irradiated drug groups derived from the drug-disease vector extraction unit 130 Based on the drug-disease vector of one or more investigational drugs known to be effective against diseases and the drug-disease vector of one or more investigational drugs that are not known to have previously been known to be effective for a specific disease to derive a new drug from the investigational drug group Thus, an evaluation model that can derive a new drug can be derived.

Meanwhile, in the drug-disease vector derivation step, for each irradiated drug, a drug-disease vector including a value for each of one or more disease genes for the specific disease is derived, and the new drug derivation step is performed in the investigational drug. A group classification step (S30) of classifying one or more into a first set and classifying one or more of the irradiated drugs into a second set; And an evaluation model deriving step (S50) of deriving an evaluation model based on the drug-disease vector of the irradiated drug belonging to the first set and the drug-disease vector of the irradiated drug belonging to the second set.

Specifically, the collective classification step (S30) classifies the irradiated drug according to a preset criterion based on the drug-disease vector derived for one or more irradiated drugs. Based on the drug-disease vector of each of the irradiated drugs and the drug-disease vector of the reference drug that has been prescribed for a specific disease contained in the irradiated drug, the first set and the second set of at least one are selected. Classify more than one investigational drug.

On the other hand, based on the first set and the second set classified in the set classification step S30, the preliminary evaluation model derivation step S40 derives two or more preliminary evaluation models that can be derived as the evaluation models. The preliminary evaluation model includes the first set and at least one second set, and the second set is classified into a plurality of the plurality of preliminary evaluation models including each of the second set and the first set. To derive.

The preliminary evaluation model is derived through machine learning, and more specifically, derived using a random forest or artificial neural network algorithm.

Finally, the evaluation module derivation step (S50) compares the plurality of preliminary evaluation models derived in the preliminary evaluation model derivation step to derive one evaluation model with the best performance. Each of the preliminary evaluation models performs K-Fold Cross Validation, and through this, the accuracy of the preliminary evaluation model can be improved.

Meanwhile, in the evaluation model derivation step (S50), two or more preliminary evaluation models are derived using the plurality of second sets, and the evaluation model is derived based on the evaluation values of the preliminary evaluation models.

More specifically, the evaluation value may include the area under the ROC curve (AUC) value of the receiver operating characteristic (ROC) graph of the preliminary evaluation model. Therefore, by comparing the AUC values of each preliminary evaluation model, the preliminary evaluation model including the highest AUC value can be derived as the final evaluation model.

9 is a diagram schematically showing a first set and a second set derived from a group of irradiated drugs according to an embodiment of the present invention.

The first set (a) shown in FIG. 9 includes one or more of the reference drugs known to be effective against the specific disease among the irradiated drugs, and the second set is effective against the specific disease among the irradiated drugs. Contains one or more of the drugs not known to have.

Specifically, the first set (a) includes a drug-disease vector of one or more reference drugs that are previously prescribed for a specific disease to derive a new drug received by the drug information receiving unit 120. The reference drug may be included in the irradiation drug group, and the plurality of second sets include one or more irradiation drugs that are not previously prescribed for a specific disease.

In the process of classifying into the first set and the second set, the user separately receives information on the reference drug and classifies the drug-disease vector for the reference drug, or the user does not separately classify the reference drug. , In the case of receiving information on one or more irradiated drugs, the irradiation drug prescribed for a specific disease by the determination criterion setting unit 450 included in the memory unit 400 is separately determined as a reference drug and the It can also be classified as a set.

On the other hand, one or more preliminary evaluation models including the first set (a) and each of the second sets are derived. For example, a first preliminary evaluation model including the first set (a) and the second set (b), a second preliminary evaluation model including the first set (a) and the second set (c), A third preliminary evaluation model including the first set (a) and the second set (d) and a fourth preliminary evaluation model including the first set (a) and the second set (e) can be derived, and , Each preliminary evaluation model may be derived through the machine learning described above in FIG. 8.

In addition, the number of irradiation drugs included in each of the second set may be set to be greater than the number of reference drugs included in the first set. Basically, the number of irradiated drugs included in a single second set is classified to be three times greater than the number of reference drugs included in the first set, and the first set and the first set by the determination criterion setting unit 450 The size of the drugs included in the two sets may be determined.

10 is a block diagram illustrating an example of an internal configuration of a new drug re-creation device using an integrated network-based drug-disease vector according to an embodiment of the present invention.

As shown in FIG. 10, the computing device 11000 includes at least one processor 11100, a memory 11200, a peripheral interface 11300, and an input/output subsystem ( I/Osubsystem) 11400, a power circuit 11500, and a communication circuit 11600 may be included at least. In this case, the computing device 11000 may correspond to a user terminal or a system for providing a currency exchange service.

The memory 11200 may include, for example, high-speed random access memory, magnetic disk, SRAM, DRAM, ROM, flash memory, or nonvolatile memory. have. The memory 11200 may include a software module, an instruction set, or other various data necessary for the operation of the computing device 11000.

In this case, accessing the memory 11200 from another component such as the processor 11100 or the peripheral device interface 11300 may be controlled by the processor 11100.

The peripheral device interface 11300 may couple input and/or output peripheral devices of the computing device 11000 to the processor 11100 and the memory 11200. The processor 11100 may execute various functions for the computing device 11000 and process data by executing a software module or instruction set stored in the memory 11200.

The input/output subsystem 11400 may couple various input/output peripherals to the peripherals interface 11300. For example, the input/output subsystem 11400 may include a monitor, a keyboard, a mouse, a printer, or a controller for coupling a peripheral device such as a touch screen or a sensor to the peripheral device interface 11300 as needed. According to another aspect, the input/output peripheral devices may be coupled to the peripheral device interface 11300 without going through the input/output subsystem 11400.

The power circuit 11500 may supply power to all or part of the components of the terminal. For example, the power circuit 11500 may include a power management system, one or more power sources such as batteries or alternating current (AC), a charging system, a power failure detection circuit, a power converter or inverter, a power status indicator or power. It may contain any other components for creation, management, and distribution.

The communication circuit 11600 may enable communication with another computing device using at least one external port.

Alternatively, as described above, the communication circuit 11600 may enable communication with other computing devices by transmitting and receiving an RF signal, also known as an electromagnetic signal, including an RF circuit, if necessary.

The embodiment of FIG. 10 is only an example of the computing device 11000, and the computing device 11000 omits some of the components shown in FIG. 10, further includes additional components not shown in FIG. 10, or 2 It can have a configuration or arrangement that combines two or more components. For example, a computing device for a communication terminal in a mobile environment may further include a touch screen or a sensor, in addition to the components shown in FIG. 10, and various communication methods (WiFi, 3G, LTE) in the communication circuit 1160 , Bluetooth, NFC, Zigbee, etc.) may include a circuit for RF communication. Components that can be included in the computing device 11000 may be implemented as hardware, software, or a combination of hardware and software including one or more signal processing or application-specific integrated circuits.

Methods according to an embodiment of the present invention may be implemented in the form of program instructions that can be executed through various computing devices and recorded in a computer-readable medium. In particular, the program according to the present embodiment may be composed of a PC-based program or an application dedicated to a mobile terminal. An application to which the present invention is applied may be installed on a user terminal through a file provided by the file distribution system. For example, the file distribution system may include a file transmission unit (not shown) that transmits the file according to the request of the user terminal.

The apparatus described above may be implemented as a hardware component, a software component, and/or a combination of a hardware component and a software component. For example, the devices and components described in the embodiments are, for example, a processor, a controller, an arithmetic logic unit (ALU), a digital signal processor, a microcomputer, a field programmable gate array (FPGA). , A programmable logic unit (PLU), a microprocessor, or any other device capable of executing and responding to instructions, such as one or more general purpose computers or special purpose computers. The processing device may execute an operating system (OS) and one or more software applications executed on the operating system. In addition, the processing device may access, store, manipulate, process, and generate data in response to the execution of software. For the convenience of understanding, although it is sometimes described that one processing device is used, one of ordinary skill in the art, the processing device is a plurality of processing elements and/or a plurality of types of processing elements. It can be seen that it may include. For example, the processing device may include a plurality of processors or one processor and one controller. In addition, other processing configurations are possible, such as a parallel processor.

The software may include a computer program, code, instructions, or a combination of one or more of these, configuring the processing unit to operate as desired or processed independently or collectively. You can command the device. Software and/or data may be interpreted by a processing device or to provide instructions or data to a processing device, of any type of machine, component, physical device, virtual equipment, computer storage medium or device. , Or may be permanently or temporarily embodyed in a transmitted signal wave. The software may be distributed over networked computing devices and stored or executed in a distributed manner. Software and data may be stored on one or more computer-readable recording media.

The method according to the embodiment may be implemented in the form of program instructions that can be executed through various computer means and recorded in a computer-readable medium. The computer-readable medium may include program instructions, data files, data structures, and the like alone or in combination. The program instructions recorded on the medium may be specially designed and configured for the embodiment, or may be known and usable to those skilled in computer software. Examples of computer-readable recording media include magnetic media such as hard disks, floppy disks, and magnetic tapes, optical media such as CD-ROMs and DVDs, and magnetic media such as floptical disks. -A hardware device specially configured to store and execute program instructions such as magneto-optical media, and ROM, RAM, flash memory, and the like. Examples of the program instructions include not only machine language codes such as those produced by a compiler, but also high-level language codes that can be executed by a computer using an interpreter or the like. The hardware device described above may be configured to operate as one or more software modules to perform the operation of the embodiment, and vice versa.

According to an embodiment of the present invention, it is possible to exert an effect of deriving a more accurate new drug re-creation model by applying genes in a binding relationship to a network.

According to an embodiment of the present invention, by deriving the shortest route of the network, deriving a vector value based on the shortest route, and creating a model for deriving a drug by comparing it with a reference drug, it is possible to derive more accurate drugs. Can exert.

According to an embodiment of the present invention, a network leading to a drug and a disease gene is generated to derive a pathway, so that the mechanism by which the drug reaches the disease gene may be identified.

According to an embodiment of the present invention, a final model is generated through the process of generating a plurality of models for deriving the derived drug, comparing the plurality of models to derive a final model, and verifying the drug derived through the final model. It can exert an effect that can improve the accuracy of.

As described above, although the embodiments have been described by the limited embodiments and drawings, various modifications and variations are possible from the above description by those of ordinary skill in the art. For example, the described techniques are performed in a different order from the described method, and/or components such as a system, structure, device, circuit, etc. described are combined or combined in a form different from the described method, or other components Alternatively, even if substituted or substituted by an equivalent, an appropriate result can be achieved.

Therefore, other implementations, other embodiments, and claims and equivalents fall within the scope of the claims to be described later.

Claims (12)

A method of recreating a new drug for a specific disease using a drug-disease vector implemented as a computing device,
A drug information receiving step of receiving irradiated drug information for two or more irradiated drugs that can be recreated as new drugs for a specific disease;
One of drugs, genes, and proteins between the irradiated drug and one or more disease genes for a specific disease, based on the interaction data including the interaction relationship with two or more of genes, proteins, and drugs and the irradiated drug information. A drug-disease vector derivation step of deriving a drug-disease vector for each irradiated drug in the path including the above as a node; And
Including; a new drug extraction step of deriving an evaluation model based on the information on the drug-disease vector of the investigational drug, and deriving a new drug for the specific disease from the investigational drug based on the evaluation model, and
In the step of deriving the drug-disease vector, for each investigational drug, a drug-disease vector including a value for each of one or more disease genes for the specific disease is derived,
The new drug extraction step includes a group classification step of classifying at least one of the irradiated drugs into a first set and classifying at least one of the irradiated drugs into a second set; And
Including; an evaluation model derivation step of deriving an evaluation model based on the drug-disease vector of the irradiated drug belonging to the first set and the drug-disease vector of the irradiated drug belonging to the second set; and
The step of deriving the evaluation model,
Re-creating a new drug for a specific disease using a drug-disease vector, which derives two or more preliminary evaluation models using the plurality of second sets and derives the evaluation model based on the evaluation values of the preliminary evaluation model How to.
The method according to claim 1,
The method of recreating a new drug for a specific disease using the drug-disease vector,
An interaction data conversion step of loading data including interaction relationships for two or more of genes, proteins, and drugs from the computing device or a reference database and converting them based on a preset relationship criterion; further comprising, drug-disease A method of recreating new drugs for specific diseases using vectors.
The method according to claim 2,
In the interaction data conversion step, in the data including the interaction relationship with two or more of the loaded genes, proteins, and drugs, based on the relationship criteria, two relationships among genes, proteins, and drugs are positive type, negative type and Convert it to one of the neutral types and derive transformed interaction data,
The drug-disease vector derivation step is a method of re-creating a new drug for a specific disease using the drug-disease vector using the transformation interaction data.
The method according to claim 1,
The drug-disease vector extraction step,
A basic path derivation step of deriving a basic path between the irradiated drug and the disease gene based on the irradiated drug information and the interaction data;
Using a drug-disease vector comprising; a shortest path calculation step of deriving the shortest path between the irradiated drug and the disease gene based on the basic path, and deriving the drug-disease vector based on the shortest path. To reinvent a new drug for a specific disease.
The method of claim 4,
The shortest path is,
The correlation between one or more drugs, genes, and proteins included as nodes in the shortest path includes at least one positive type or negative type,
The interaction data includes two or more interactions among drugs, genes, and proteins, and includes the positive type, the negative type, and the neutral type,
The neutral type is a method for recreating a new drug for a specific disease using a drug-disease vector, including a case in which two or more of a drug, a gene, and a protein have a binding relationship.
The method of claim 5,
The shortest path includes one or more nodes,
The shortest path calculation step uses a drug-disease vector to derive the drug-disease vector based on the number of nodes connected to each node included in the shortest path and a correlation type with nodes adjacent to each node. To reinvent a new drug for a specific disease.
The method according to claim 1,
The new drug extraction step includes information on the drug-disease vector of a reference drug known to be effective against the specific disease among the irradiated drugs, and the drug-disease of a drug that is not known to be effective against the specific disease among the irradiated drugs. A method of re-creating a new drug for a specific disease using a drug-disease vector that derives an evaluation model based on a vector.
delete The method according to claim 1,
The first set includes one or more of the reference drugs known to be effective against the specific disease among the investigational drugs,
The second set includes one or more of the drugs that are not known to be effective against the specific disease among the investigational drugs, a drug-disease vector to recreate a new drug for a specific disease.
delete A device for re-creating a new drug for a specific disease using a drug-disease vector including at least one memory and at least one processor,
A drug information receiver for receiving information on irradiated drugs for two or more irradiated drugs that can be recreated as new drugs for a specific disease;
One of drugs, genes, and proteins between the irradiated drug and one or more disease genes for a specific disease, based on the interaction data including the interaction relationship with two or more of genes, proteins, and drugs and the irradiated drug information. A drug-disease vector extraction unit for deriving a drug-disease vector for each irradiated drug in the path including the above as a node; And
Including; a new drug extraction unit for deriving an evaluation model based on the information on the drug-disease vector of the investigational drug and for deriving a new drug for the specific disease from the investigational drug based on the evaluation model, and
The drug-disease vector derivation unit derives a drug-disease vector including a value for each of one or more disease genes for the specific disease, for each investigational drug,
The new drug extraction unit classifying unit for classifying at least one of the irradiated drugs into a first set, and classifying at least one of the irradiated drugs into a second set; And
Including; an evaluation model derivation unit for deriving an evaluation model based on the drug-disease vector of the irradiated drug belonging to the first set and the drug-disease vector of the irradiated drug belonging to the second set; and
The evaluation model extraction unit,
Re-creating a new drug for a specific disease using a drug-disease vector, which derives two or more preliminary evaluation models using the plurality of second sets and derives the evaluation model based on the evaluation values of the preliminary evaluation model Device.
As a computer-readable recording medium,
The computer-readable recording medium stores instructions for causing a computing device to perform the following steps, the steps comprising;
A drug information receiving step of receiving irradiated drug information for two or more irradiated drugs that can be recreated as new drugs for a specific disease;
One of drugs, genes, and proteins between the irradiated drug and one or more disease genes for a specific disease, based on the interaction data including the interaction relationship with two or more of genes, proteins, and drugs and the irradiated drug information. A drug-disease vector derivation step of deriving a drug-disease vector for each irradiated drug in the path including the above as a node; And
And a new drug extraction step of deriving an evaluation model based on the information on the drug-disease vector of the investigational drug, and deriving a new drug for the specific disease from the investigational drugs based on the evaluation model.
In the step of deriving the drug-disease vector, for each investigational drug, a drug-disease vector including a value for each of one or more disease genes for the specific disease is derived,
The new drug extraction step includes a group classification step of classifying at least one of the irradiated drugs into a first set and classifying at least one of the irradiated drugs into a second set; And
Including; an evaluation model derivation step of deriving an evaluation model based on the drug-disease vector of the irradiated drug belonging to the first set and the drug-disease vector of the irradiated drug belonging to the second set; and
The step of deriving the evaluation model,
A computer-readable recording medium for deriving two or more preliminary evaluation models using the plurality of second sets, and deriving the evaluation models based on evaluation values of the preliminary evaluation models.

Images