CN109935341A - A kind of prediction technique and device of drug new indication - Google Patents
A kind of prediction technique and device of drug new indication Download PDFInfo
- Publication number
- CN109935341A CN109935341A CN201910280839.8A CN201910280839A CN109935341A CN 109935341 A CN109935341 A CN 109935341A CN 201910280839 A CN201910280839 A CN 201910280839A CN 109935341 A CN109935341 A CN 109935341A
- Authority
- CN
- China
- Prior art keywords
- gene
- drug
- drug target
- indication
- pathway
- 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.)
- Granted
Links
Landscapes
- Medical Treatment And Welfare Office Work (AREA)
Abstract
The embodiment of the present application discloses the prediction technique and device of a kind of drug new indication, it is determined for the new curative effect of existing drug target, specifically, marking of the available drug target on gene pathway is as a result, marking result of the drug target on gene pathway characterizes the drug target for the activation of the gene pathway；The marking result is then inputted into machine learning model, obtains the corresponding indication of the drug target.After the indication for determining drug target, in view of may include the known indications of drug target in the indication, so the indication in the corresponding indication of the drug target in addition to the known indications of the drug target is predicted as the new indication of the drug target.It can be seen that the new indication of drug target can be predicted using the method for the embodiment of the present application, it can predict the new curative effect of existing drug.
Description
Technical field
This application involves technical field of biological information more particularly to a kind of method and devices for predicting drug new indication.
Background technique
Currently, the research and development of novel drugs face the problem that the R&D cycle is long and research and development are at high cost, for this problem, to
It is relatively good solution that drug, which recycle,.It is so-called that existing drug is recycled, refer to, by existing drug
For treating new disease.For example, before 60 years, " Thalidomide " is a kind of drug for treating morning sickness and now it is but used to
Treat leukaemia and leprosy；" aspirin " is initially a kind of analgesic-antipyretic, but finds that it had platelet aggregation later
Inhibiting effect can prevent thrombosis, so nowadays " aspirin " is used as prevention transient ischemic attack, cardiac muscle again
The drug of the formation of thrombus after infarct, heart valve prosthesis and venous fistula or other operations.
Therefore, the new curative effect for how determining existing drug is current urgent problem.
Summary of the invention
The prediction technique and device of a kind of drug new indication provided by the embodiments of the present application, can determine existing drug
New curative effect.
In a first aspect, the embodiment of the present application provides a kind of prediction technique of drug new indication, which comprises
Marking of the drug target on gene pathway is obtained as a result, marking result of the drug target on gene pathway
The drug target is characterized for the activation of the gene pathway；
Marking result of the drug target on the gene pathway is inputted into machine learning model, obtains the target
The corresponding indication of drug, marking result and institute of the machine learning model according to training drug on the gene pathway
The known indications training for stating trained drug obtains, and the trained drug is drug known to indication；
The known indications of the drug target are obtained, and the target will be removed in the corresponding indication of the drug target
Indication except the known indications of drug is predicted as the new indication of the drug target.
Optionally, the method also includes:
Obtain the chemical structure of the corresponding known drug of new indication of the drug target；
The chemical structure of the drug target and the chemical structure of the known drug are compared, comparison result is obtained；
If the comparison result meets preset condition, the drug target is determined as to solve the medicine of the new indication
Object.
Optionally, the method also includes:
Obtain marking result of the drug target on the corresponding gene pathway of the new indication；
If marking result of the drug target on the corresponding gene pathway of the new indication is greater than or equal to threshold value,
Then the drug target is determined as to solve the drug of the new indication.
Optionally, the method also includes:
The corresponding multiple drugs of the new indication are obtained respectively on gene pathway corresponding with the new indication
Marking result；
Multiple drugs corresponding to the new indication beating on gene pathway corresponding with the new indication respectively
Point result is ranked up according to sequence from high to low；
If including the drug target in the corresponding drug of the preceding preset number new indication, by the target medicine
Object is determined as solving the drug of the new indication.
Optionally, the marking result for obtaining drug target on gene pathway includes:
Obtain the transcript profile data of control group drug and the transcript profile data of drug target；
According to the transcript profile data of the transcript profile data of the control group drug and the drug target, transcriptional differences are obtained
Express multiple data；
Clustering processing is done to related gene, by the gene clusters of coexpression to same group, obtains multiple gene co-expressing lists
Member；
Gene pathway is obtained, is each in the gene pathway according to gene effect played in the gene pathway
A gene distributes weight coefficient, obtains gene pathway topology coefficient matrix；Effect packet of the gene played in gene pathway
It includes: facilitation, inhibiting effect, phosphorylation and dephosphorylation；
Multiple data, the gene co-expressing unit and gene pathway topology system are expressed according to the transcriptional differences
Matrix number determines marking result of the drug target on every gene pathway.
Optionally, the effect according to gene played in gene pathway is each gene distribution in gene pathway
Weight coefficient, comprising:
+ 1 will be set as to the corresponding weight coefficient of the favorable gene of gene pathway；Gene pathway will be risen and be inhibited
The corresponding weight coefficient of the gene of effect is set as -1；
+ 2 are set by the corresponding weight coefficient of gene for playing phosphorylation to gene pathway；Gene pathway will be gone it
The corresponding weight coefficient of the gene of phosphorylation is set as -2.
Optionally, the acquisition gene pathway topology coefficient matrix, comprising:
According to the corresponding weight coefficient of each gene, R packet KEGG gene pathway figure (Kyoto is utilized
Encyclopedia of Genes and Genomes Graph, KEGGgraph) and R Speech enhancement picture library (R Language
Boost Graph Library, RBGL) calculate topological coefficient of the gene on every gene pathway.
Optionally, described that clustering processing is done to gene, by the gene clusters of coexpression to same group, it is total to obtain multiple genes
Expression unit, comprising:
First time clustering processing is carried out to the gene of coexpression, and second is carried out to the first time cluster result and is gathered
Class processing, obtains gene co-expressing unit.
Optionally, described that clustering processing is done to gene, by the gene clusters of coexpression to same group, it is total to obtain multiple genes
Expression unit, comprising:
Using density clustering method and/or hierarchy clustering method.
Optionally, the density clustering method includes: the noise application space clustering algorithm based on density
(Density-Based Spatial Clustering of Applications with Noise, DBSCAN), and/or, row
Sequence point with identify cluster topology algorithm (Ordering Points to identity the clustering structure,
OPTICS)；
The hierarchy clustering method includes: hierarchical structure equilibrium iteration clustering algorithm (Balance Iterative
Reducing and Clustering using Hierarchies,BIRCH)。
Second aspect, the embodiment of the present application provide a kind of prediction meanss of drug new indication, and described device includes:
First acquisition unit, for obtaining marking of the drug target on gene pathway as a result, the drug target is in base
Because the marking result on access characterizes the drug target for the activation of the gene pathway；
Input unit, for marking result of the drug target on the gene pathway to be inputted machine learning mould
Type obtains the corresponding indication of the drug target, and the machine learning model is according to training drug on the gene pathway
Marking result and the trained drug known indications training obtain, the trained drug be indication known to medicine
Object；
Predicting unit, for obtaining the known indications of the drug target, and by the corresponding adaptation of the drug target
Indication in disease in addition to the known indications of the drug target is predicted as the new indication of the drug target.
Optionally, described device further include:
Second acquisition unit, the chemical structure of the corresponding known drug of new indication for obtaining the drug target；
Comparing unit is obtained for comparing the chemical structure of the drug target and the chemical structure of the known drug
Comparison result；
The drug target is determined as solving by the first determination unit if meeting preset condition for the comparison result
The drug of the certainly described new indication.
Optionally, described device further include:
Third acquiring unit, for obtaining marking of the drug target on the corresponding gene pathway of the new indication
As a result；
Second determination unit, if the marking knot for the drug target on the corresponding gene pathway of the new indication
Fruit is greater than or equal to threshold value, then is determined as the drug target solving the drug of the new indication.
Optionally, described device further include:
4th acquiring unit, for obtain the corresponding multiple drugs of the new indication respectively with the new indication pair
Marking result on the gene pathway answered；
Sequencing unit, for multiple drugs corresponding to the new indication respectively in base corresponding with the new indication
Because the marking result on access is ranked up according to sequence from high to low；
Third determination unit, if for including the target medicine in the corresponding drug of the preceding preset number new indication
The drug target is then determined as solving the drug of the new indication by object.
Optionally, the first acquisition unit, specifically includes:
Subelement is obtained, for obtaining the transcript profile data of control group drug and the transcript profile data of drug target；
Subelement is obtained, for according to the transcript profile data of the control group drug and the transcript profile number of the drug target
According to acquisition transcriptional differences express multiple data；
Subelement is clustered, for doing clustering processing to related gene, by the gene clusters of coexpression to same group, is obtained more
A gene co-expressing unit；
Coefficient distributes subelement for obtaining gene pathway
Each gene in the gene pathway distributes weight coefficient, obtains gene pathway topology coefficient matrix；The gene is in gene
Effect played in access includes: facilitation, inhibiting effect, phosphorylation and dephosphorylation；
Subelement is determined, for expressing multiple data, the gene co-expressing unit and institute according to the transcriptional differences
Gene pathway topology coefficient matrix is stated, determines marking result of the drug target on every gene pathway.
Optionally, the coefficient distributes subelement, is specifically used for:
+ 1 will be set as to the corresponding weight coefficient of the favorable gene of gene pathway；Gene pathway will be risen and be inhibited
The corresponding weight coefficient of the gene of effect is set as -1；
+ 2 are set by the corresponding weight coefficient of gene for playing phosphorylation to gene pathway；Gene pathway will be gone it
The corresponding weight coefficient of the gene of phosphorylation is set as -2.
Optionally, the acquisition gene pathway topology coefficient matrix, comprising:
According to the corresponding weight coefficient of each gene, R packet KEGG gene pathway figure (Kyoto is utilized
Encyclopedia of Genes and Genomes Graph, KEGGgraph) and R Speech enhancement picture library (R Language
Boost Graph Library, RBGL) calculate topological coefficient of the gene on every gene pathway.
Optionally, the cluster subelement, is specifically used for:
First time clustering processing is carried out to the gene of coexpression, and second is carried out to the first time cluster result and is gathered
Class processing, obtains gene co-expressing unit.
Optionally, the cluster subelement, is specifically used for:
Using density clustering device and/or hierarchical clustering device.
Optionally, the density clustering device includes: the noise application space clustering algorithm based on density
(Density-Based Spatial Clustering of Applications with Noise, DBSCAN), and/or, row
Sequence point with identify cluster topology algorithm (Ordering Points to identity the clustering structure,
OPTICS)；
The hierarchical clustering device includes: hierarchical structure equilibrium iteration clustering algorithm (Balance Iterative
Reducing and Clustering using Hierarchies,BIRCH)。
The third aspect, the embodiment of the present application provide a kind of pre- measurement equipment of drug new indication, and the drug newly adapts to
The pre- measurement equipment of disease includes: processor and memory；
The memory is transferred to the processor for storing program code, and by said program code；
The processor, for calling drug described in the above first aspect any one of the instruction execution in memory new
The prediction technique of indication.
The prediction technique and device of drug new indication provided by the embodiments of the present application, are determined for existing target
The new curative effect of drug, specifically, marking of the available drug target on gene pathway as a result, the drug target in gene
Marking result on access characterizes the drug target for the activation of the gene pathway；It is then that the marking result is defeated
Enter machine learning model, obtains the corresponding indication of the drug target.Due to the machine learning model be according to indication
What the known indications training of marking result and the trained drug of the training drug known on the gene pathway obtained,
It therefore, can be according to marking of the drug target on gene pathway as a result, determining the drug target by the machine learning model
Corresponding indication.After the indication for determining drug target, it is contemplated that may include the known of drug target in the indication
Indication, so by the adaptation in the corresponding indication of the drug target in addition to the known indications of the drug target
Disease is predicted as the new indication of the drug target.It can be seen that mesh can be predicted using the method for the embodiment of the present application
Mark the new indication of drug, it can predict the new curative effect of existing drug.
Detailed description of the invention
In order to illustrate the technical solutions in the embodiments of the present application or in the prior art more clearly, to embodiment or will show below
There is attached drawing needed in technical description to be briefly described, it should be apparent that, the accompanying drawings in the following description is only this
The some embodiments recorded in application, for those of ordinary skill in the art, without creative efforts,
It can also be obtained according to these attached drawings other attached drawings.
Fig. 1 is a kind of flow chart of the prediction technique of drug new indication provided by the embodiments of the present application；
Fig. 2 is a kind of flow chart of the prediction technique of drug new indication provided by the embodiments of the present application；
Fig. 3 is whether another determination drug target provided by the embodiments of the present application is the drug for solving the new indication
Method flow diagram；
Fig. 4 is the process of the method for marking result of the acquisition drug target provided by the embodiments of the present application on gene pathway
Schematic diagram；
Fig. 5 is the process of the method for marking result of the acquisition drug target provided by the embodiments of the present application on gene pathway
Schematic diagram.
Specific embodiment
In order to make those skilled in the art more fully understand application scheme, below in conjunction in the embodiment of the present application
Attached drawing, the technical scheme in the embodiment of the application is clearly and completely described, it is clear that described embodiment is only this
Apply for a part of the embodiment, instead of all the embodiments.Based on the embodiment in the application, those of ordinary skill in the art exist
Every other embodiment obtained under the premise of creative work is not made, shall fall in the protection scope of this application.
The description and claims of this application and term " first ", " second ", " third ", " in above-mentioned attached drawing
The (if present)s such as four " are to be used to distinguish similar objects, without being used to describe a particular order or precedence order.It should manage
The data that solution uses in this way are interchangeable under appropriate circumstances, so as to embodiments herein described herein can in addition to
Here the sequence other than those of diagram or description is implemented.In addition, term " includes " and " having " and their any deformation,
Be intended to cover it is non-exclusive include, for example, containing the process, method of a series of steps or units, system, product or setting
It is standby those of to be not necessarily limited to be clearly listed step or unit, but may include be not clearly listed or for these mistakes
The intrinsic other step or units of journey, method, product or equipment.
Currently, the research and development of novel drugs face the problem that the R&D cycle is long and research and development are at high cost, for this problem, to
It is relatively good solution that drug, which recycle,.The embodiment of the present application provides a kind of prediction side of drug new indication
Method and device are determined for the new curative effect of existing drug target, and specifically, available drug target is in gene pathway
On marking as a result, marking result of the drug target on gene pathway to characterize the drug target logical for the gene
The activation on road；The marking result is then inputted into machine learning model, obtains the corresponding indication of the drug target.By
In the machine learning model be marking result of the training drug on the gene pathway according to known to indication and described
What the known indications training of training drug obtained, it therefore, can be according to drug target in gene by the machine learning model
Marking on access is as a result, determine the corresponding indication of the drug target.After the indication for determining drug target, it is contemplated that should
It may include the known indications of drug target in indication, so the mesh will be removed in the corresponding indication of the drug target
The indication except the known indications of drug is marked, the new indication of the drug target is predicted as.It can be seen that utilizing this Shen
Please embodiment method, the new indication of drug target can be predicted, it can the new curative effect for predicting existing drug, is existing
The recycling of drug provides possibility.
It describes in detail below by prediction technique of the embodiment to drug new indication provided by the present application.
Referring to Fig. 1, which is a kind of flow chart of the prediction technique of drug new indication provided by the embodiments of the present application.
The prediction technique of drug new indication provided in this embodiment, can be as follows
S101-S103 is realized.
S101: obtaining marking of the drug target again on gene pathway as a result, the drug target beating on gene pathway again
Point result characterizes the drug target for the activation of the gene pathway.
It, can also be with it should be noted that the drug target referred in the embodiment of the present application, can be the drug listed
For the compound not listed.The embodiment of the present application does not limit the drug target specifically, which for example can be existing
One or more drug in drug.
About the specific implementation of S101, can not be described in detail herein with reference to the description section below with Fig. 4.
S102: marking result of the drug target on the gene pathway is inputted into machine learning model, obtains institute
State the corresponding indication of drug target.
In the embodiment of the present application, the machine learning model is the marking according to training drug on the gene pathway
As a result and the training of the known indications of the trained drug obtains, and the trained drug is existing drug, also, the instruction
It is known for practicing the indication of drug.
It should be noted that in the embodiment of the present application, the adaptation of a drug such as drug target or training drug
Disease refers to the disease that the drug can be used for treating.For example, drug " Thalidomide " can be used for treating leukaemia and leprosy
Disease, then leukaemia and leprosy are the indication of drug " Thalidomide ".
It is understood that a drug may can treat a variety of diseases, it is also possible to it is only used for treating a kind of disease, because
This, in the embodiment of the present application, when training machine learning model, the indication of training drug can be one, or more
A, the embodiment of the present application is not specifically limited.
The embodiment of the present application does not limit the machine learning model specifically, and the machine learning model for example can be convolution
Neural network (Convolutional Neural Networks, CNN) model；The machine learning model may be depth
Neural network (Deep Neural Networks, DNN) model.
S103: the known indications of the drug target are obtained, and institute will be removed in the corresponding indication of the drug target
The indication except the known indications of drug target is stated, the new indication of the drug target is predicted as.
It is understood that since the machine learning model is that the training drug according to known to indication is logical in the gene
The marking result of road and the training of the known indications of the trained drug obtain, therefore, by the machine learning model,
It can be according to marking of the drug target on gene pathway as a result, determining the corresponding indication of the drug target.Moreover, from theory
From, the corresponding indication of the drug target determined may both include the known indications of the drug target, and also include
The unknown indication of the drug target.
Therefore, in the embodiment of the present application, the known indications of the available drug target, and by the target medicine
Indication in the corresponding indication of object in addition to the known indications of the drug target, is predicted as the new of the drug target
Indication.For example, the indication of 3 with the drug target are determined by the machine mould for drug target,
But two of them indication be it is known, i.e., used drug target to treat the two indications at present, so by another
An outer indication is determined as the new indication of drug target.
The embodiment of the present application does not limit the implementation for obtaining the known indications of drug target specifically, shows as one kind
Example, can inquire drug target in database (such as Mesh) vocabulary for being stored with drug and the corresponding indication of drug
Know indication.
As can be seen from the above description, the prediction technique of drug new indication provided by the embodiments of the present application can be used for really
The new curative effect of fixed existing drug target, specifically, marking of the available drug target on gene pathway is as a result, the mesh
It marks marking result of the drug on gene pathway and characterizes the drug target for the activation of the gene pathway；Then will
The marking result inputs machine learning model, obtains the corresponding indication of the drug target.Since the machine learning model is
The known adaptation of marking result and the trained drug of the training drug on the gene pathway according to known to indication
Disease training obtains, therefore, by the machine learning model, can according to marking of the drug target on gene pathway as a result,
Determine the corresponding indication of the drug target.After the indication for determining drug target, it is contemplated that may include in the indication
The known indications of drug target, so the known adaptation for the drug target being removed in the corresponding indication of the drug target
Indication except disease is predicted as the new indication of the drug target.It can be seen that using the method for the embodiment of the present application,
The new indication of drug target can be predicted, it can predict the new curative effect of existing drug.
In the embodiment of the present application, in order to further determine whether drug target can be used to solve aforementioned new adaptation
Disease can also further verify aforementioned prediction result.Three kinds introduced below aforementioned new suitable for solving to drug target
The implementation for answering the effect of disease to be verified specifically can choose one such or a variety of progress verifying.
In view of in practical application, the chemical structure of multiple drugs for solving an indication be it is similar, therefore,
It is similar with the chemical structure of the known drug of the new indication if the chemical structure of drug target, then it indicates to a certain extent
Drug target can be used to solve aforementioned new indication.
In consideration of it, in one possible implementation, method provided by the embodiments of the present application can also include Fig. 2 institute
The step S201-S203 shown.Fig. 2 is whether a kind of determining drug target provided by the embodiments of the present application is to solve the new adaptation
The flow diagram of the method for the drug of disease.
S201: the chemical structure of the corresponding known drug of new indication of the drug target is obtained.
In the embodiment of the present application, the corresponding known drug of the new indication, refer to have been used to solve it is described new suitable
Answer the drug of disease.
In the embodiment of the present application, it can use in the aforementioned database for being stored with drug and the corresponding indication of drug,
The corresponding known drug of the new indication is inquired, then, determines the chemical structure of the corresponding known drug of the new indication.One
As for, the chemical structure of drug is stored in corresponding drug data base, therefore, can be determined from the drug data base
The chemical structure of the corresponding known drug of the new indication.
It should be noted that is referred in the embodiment of the present application " is stored with the data of drug and the corresponding indication of drug
Library " and " drug data base " can be the same database, be also possible to disparate databases, and the embodiment of the present application does not do specific limit
It is fixed.
S202: the chemical structure of the drug target and the chemical structure of the known drug are compared, comparison result is obtained.
In the embodiment of the present application, the chemical structure of drug target can be determined by foregoing pharmaceutical database.
S202 in specific implementation, can use chemical fingerprint method, compare chemical structure and the institute of the drug target
The similitude between the chemical structure of known drug is stated, comparison result is obtained.
In the embodiment of the present application, can also chemical structure to the drug target and the known drug chemistry knot
Structure carries out similarity score, such as using tanimoto coefficient to the chemical structure of the drug target and the known drug
Chemical structure carries out similarity score, using the marking result as comparison result.It should be noted that the marking result is
Number between 0-1, numerical value is bigger, indicates that similitude is higher, and numerical value is smaller, indicates that similitude is lower.
S203: if the comparison result meets preset condition, the drug target is determined as to solve the new adaptation
The drug of disease.
In the embodiment of the present application, if the comparison result meets preset condition, it can refer to the change of the drug target
The similitude learned between structure and the chemical structure of the known drug is more than or equal to preset threshold.The embodiment of the present application is not
The preset threshold is specifically limited, the specific value of the preset threshold can be determines according to actual conditions.For example, if the ratio
Pair the result is that the marking of aforementioned tanimoto coefficient can refer to aforementioned as a result, the comparison result meets preset condition
Tanimoto coefficient gives a mark result more than or equal to 0.65.
In view of in practical applications, if being used to solve aforementioned new indication for drug target, drug target is for solving
The effect of certainly aforementioned new indication can satisfy certain condition.In a kind of implementation of the embodiment of the present application, in view of mesh
Marking of the drug again on the corresponding gene pathway of the new indication is marked as a result, drug target can be embodied for the new adaptation
The activation of the corresponding gene pathway of disease, it can embody the effect that drug target is used to solve aforementioned new indication.
In consideration of it, can also further be verified by following steps A-B in a kind of implementation of the embodiment of the present application
Whether drug target can be used to solve aforementioned new indication.
Step A: marking result of the drug target on the corresponding gene pathway of the new indication is obtained.
It should be noted that in the embodiment of the present application, step A in specific implementation, can be determined described new suitable first
The corresponding gene pathway of disease is answered, then drug target is extracted in the marking result of multiple gene pathway from drug target and exists
Marking result on the corresponding gene pathway of the new indication.
The embodiment of the present application does not limit the specific implementation for determining the corresponding gene pathway of new indication specifically, as one
Kind example, can inquire corresponding database and obtain the corresponding gene pathway of new indication.
Step B: if marking result of the drug target on the corresponding gene pathway of the new indication is greater than or waits
In threshold value, then the drug target is determined as solving the drug of the new indication.
The embodiment of the present application does not limit the threshold value specifically, and the threshold value can be an empirical value, for example, according to institute
State the experience that marking result of the corresponding known drug of new indication on the corresponding gene pathway of the new indication determines
Value.When marking result of the drug target on the corresponding gene pathway of the new indication is greater than or equal to threshold value, then
It is considered that the effect that drug target solves the new indication meets condition, so the drug target can be determined as solving
The drug of the certainly described new indication.
It, can be according to the corresponding known medicine of the solution new indication in another implementation of the embodiment of the present application
Object solves the effect of the new indication, to determine drug target for solving the effect of the new indication.It specifically, can be with
By step shown in Fig. 3, the drug target further determined that is used to solve the effect of the new indication.Fig. 3 is the application
Whether another determination drug target that embodiment provides is the flow diagram for solving the method for drug of the new indication.
S301: the corresponding multiple drugs of the new indication are obtained respectively in gene pathway corresponding with the new indication
On marking result.
It is understood that the corresponding multiple drugs of the new indication are respectively in gene corresponding with the new indication
Marking on access as a result, the activation of multiple drug gene pathway corresponding for the new indication can be characterized,
The multiple drug can be characterized for solving the effect of the new indication.
In the embodiment of the present application, S301 in specific implementation, can determine that the new indication is corresponding multiple first
Drug, then, the multiple drug marking result on the corresponding gene pathway of the new indication respectively determined.
It should be noted that the corresponding multiple drugs of the new indication mentioned herein, including the drug target and
The corresponding known drug of the new indication.
S302: multiple drugs corresponding to the new indication are respectively on gene pathway corresponding with the new indication
Marking result be ranked up according to sequence from high to low.
S303:, will be described if including the drug target in the corresponding drug of the preceding preset number new indication
Drug target is determined as solving the drug of the new indication.
About S302 and S303 it should be noted that multiple drugs corresponding to the new indication respectively with it is described new
Marking result on the corresponding gene pathway of indication according to being ranked up from high to low, actually to the solution new adaptation
Multiple drugs of disease are ranked up from high to low according to the effect for solving the new indication.
It is understood that if including the mesh in the corresponding drug of the forward preset number new indication that sorts
Mark drug, then it represents that the effect that the drug target is used to solve the new indication is earlier in the multiple drug,
It may thereby determine that effect of the drug target for solving the new indication is relatively good, it is possible to further by the target
Drug is determined as solving the drug of the new indication.
The embodiment of the present application does not limit the preset number specifically, and the specific value of the preset number can be according to reality
Situation determines.
In above-mentioned three kinds of methods, it is aforementioned new suitable for solving specifically to can choose one such or a variety of pair of drug target
The effect of disease is answered to be verified.For example, can choose step S201-S203 combination step S301-303, so that the medicine filtered out
Object has chemical structure and pharmacological effect double verification.
The prediction technique of drug new indication provided by the embodiments of the present application is described above, below in conjunction with attached drawing
Introduce the specific implementation of S101 in previous embodiment " obtaining marking result of the drug target on gene pathway ".
Referring to fig. 4, Fig. 4 is the side of marking result of the acquisition drug target provided by the embodiments of the present application on gene pathway
The flow diagram of method, as shown in figure 4, method includes the following steps:
S401: the transcript profile data of control group drug and the transcript profile data of drug target are obtained.
Wherein, the transcript profile data of control group drug refer to the transcript profile number for being not affected by compound (such as placebo) effect
According to；The transcript profile data of drug target refer to the transcript profile data by compound effects, the transcript profile number of different drug targets
According to different compound dosage, and/or corresponding different classes of compounds and/or different administration times may be corresponded to, that is, exist
In experimentation, it can be tested using the compound of variety classes same dose, the agent of identical type difference can also be used
The compound of amount is tested, and can also be tested using the compound of variety classes various dose, and then for real every time
It tests and correspondingly generates one group of corresponding transcript profile data.Further, it is also possible to increase variable on the basis of above-mentioned experiment condition and give
Medicine interval carries out experiment and generates transcript profile data, does not do any restriction to the formation condition of transcript profile data herein.
In practical applications, the transcript profile data of one or more groups of control group drugs can be obtained according to actual needs, and
Correspondingly obtain the transcript profile data of one or more groups of drug targets.When specific acquisition, experiment can be passed through and obtain above-mentioned control
The transcript profile data of group drug and the transcript profile data of drug target can also be obtained from transcription group data set online or offline
The transcript profile data of above-mentioned control group drug and the transcript profile data of drug target, the herein not transcription to control group drug is obtained
The implementation of group data and the transcript profile data of drug target is specifically limited.
In practical applications, the transcript profile data of the transcript profile data of acquired control group drug and drug target, tool
Body is as shown in table 1:
Table 1
Wherein, 2 liang of drug target 1, drug target column datas are the transcript profile data of drug target, normally organize 1, is normal
2 this two column data of group are the transcript profile data of corresponding control group drug.
S402: according to the transcript profile data of the transcript profile data of the control group drug and the drug target, turned
Record differential expression multiple data.
It, can be first to acquired after getting the transcript profile data of control group drug and the transcript profile data of drug target
Each transcript profile data carry out preliminary treatment and calculate transcription of the transcript profile data of drug target relative to control group drug in turn
The transcriptional differences of group data express multiple data.
More mature calculatings transcriptional differences existing many at present express the mode of multiple data, can be with when concrete application
Suitable calculation is correspondingly chosen according to actual needs, according to turn of the transcript profile data of control group drug and drug target
Record group data determine that transcriptional differences express multiple data, do not do have to the mode for calculating transcriptional differences expression multiple data herein
Body limits.
S403: doing clustering processing to related gene, by the gene clusters of coexpression to same group, obtains multiple genes and is total to table
Up to unit.
Next, the transcript profile data to control group drug and the related gene in the transcript profile data of drug target carry out
Clustering processing, related gene herein specifically refer under compound effects, the gene that expression quantity can change a lot；Into
And the same expression factor will be controlled by related gene, and/or show significant coordinate expression series of genes cluster arrive
Same group, these genes are the gene co-expressed, are clustered to obtain gene co-expressing unit by the gene to coexpression.
According to synergistic effect, multiple gene co-expressing units are obtained.
When specifically doing clustering processing to the gene of coexpression, a clustering processing directly can be done to the gene of coexpression,
Obtain corresponding gene co-expressing unit；It is more preferable of course for the effect for guaranteeing cluster, two can also be done to the gene of coexpression
Secondary clustering processing carries out first time clustering processing to the gene of coexpression, and carry out again to first time cluster result second
Clustering processing obtains gene co-expressing unit.
It should be noted that when the gene to coexpression does clustering processing, can using density clustering method and/
Or hierarchy clustering method；Specifically, density clustering method includes: the noise application space clustering algorithm based on density
(Density-Based Spatial Clustering of Applications with Noise, DBSCAN), sequence point with
Mark cluster topology algorithm (Ordering Points to identity the clustering structure,
OPTICS)；Hierarchy clustering method includes: hierarchical structure equilibrium iteration clustering algorithm (Balance Iterative Reducing
And Clustering using Hierarchies, BIRCH).
It, can be using any one of the above clustering method to total table when the gene to coexpression only does a clustering processing
The gene reached is clustered, and gene co-expressing unit is obtained；When the gene to coexpression does multiple clustering processing, can only adopt
It is repeatedly clustered with any one of the above clustering method, obtains gene co-expressing unit, it can also will be above-mentioned any a variety of poly-
Class method combines, and is clustered to obtain gene co-expressing unit to the gene of coexpression, for example, using poly- based on density
Class method does first time clustering processing to the gene of coexpression, and then again using hierarchy clustering method to first time clustering processing knot
Fruit carries out second of clustering processing, obtains gene co-expressing unit.
Below by taking the gene to coexpression does clustering processing twice as an example, the process for generating gene co-expressing unit is carried out
It introduces:
Specifically, can first be done at first time cluster using gene of the density clustering method OPTICS to coexpression
Reason, OPTICS method is without being manually entered field radius and field minimal point the two parameters, and the class cluster knot that cluster obtains
Fruit is lower to field radius and field minimal point susceptibility.After obtaining first time cluster result, first time cluster result is determined
In similarity between each gene, and be screened out from it similarity and be used as at second of cluster higher than the gene of preset threshold
Reason further, only retains similarity and is higher than for example, only retaining the gene that similarity is higher than 0.3,0.4,0.5,0.6,0.7
0.5 gene.
Then, second of clustering processing is carried out to first time cluster result using hierarchy clustering method BIRCH, generates gene
Unit is co-expressed, BIRCH is suitable for large-scale data set, the cluster efficiency with higher when handling large-scale data,
And normal operation can be left in any give.
By the efficient combination of both clustering methods, can be obtained in a relatively short period of time with a small amount of computing resource
Accurate gene co-expressing unit.
S404: obtaining gene pathway, is in the gene pathway according to gene effect played in the gene pathway
Each gene distribute weight coefficient, obtain gene pathway topology coefficient matrix；Work of the gene played in gene pathway
With including: facilitation, inhibiting effect, phosphorylation and dephosphorylation.
From gene pathway database (such as KEGG (Kyoto Encyclopedia of Genes and Genomes) data
Library, Reactome database etc.) in obtain gene pathway, according to effect of each gene played in gene pathway, correspondingly
Weight coefficient is distributed for each gene in gene pathway；In turn, according to the corresponding weight coefficient of each gene, correspondingly
Topological coefficient of each gene on every gene pathway is calculated, and determines gene pathway topology coefficient matrix.
It should be noted that the gene of Primary Reference is played in gene pathway when distributing weight coefficient for each gene
Effect include: facilitation, inhibiting effect, phosphorylation and dephosphorylation.
Specifically, if gene-for-gene access plays a driving role, it can be correspondingly by the corresponding weight coefficient of the gene
It is set as+1；If gene-for-gene access plays inhibiting effect, can correspondingly set the corresponding weight coefficient of the gene to-
1；In view of the addition or removal of phosphate group play biological " switch ", i.e. phosphorylation and dephosphorylation mistake to many reactions
Journey played in biology " switch " effect, correspondingly, if gene-for-gene access rise phosphorylation, can correspondingly by
The corresponding weight coefficient of the gene is set as+2；If gene-for-gene access plays dephosphorylation, will can correspondingly be somebody's turn to do
The corresponding weight coefficient of gene is set as -2.
It should be understood that in practical applications, can consider according to actual needs facilitation that gene-for-gene access plays,
Inhibiting effect, phosphorylation and dephosphorylation, and corresponding weight coefficient is set for it, it can correspondingly by weight
Coefficient is set as other numerical value commonly used in the art, does not do any restriction to the specific value of set weight coefficient herein.
Consider effect of the gene played in gene pathway, correspondingly distributes weight system for each gene in gene pathway
After number；R packet KEGG gene pathway figure can be utilized further according to the corresponding weight coefficient of each gene
(KEGGgraph) and R Speech enhancement picture library (R Boost Graph Library, RBGL) calculates each gene in every gene
Topological coefficient on access, in turn, calculated topology coefficient form gene pathway topology coefficient matrix.
Gene pathway topology coefficient matrix specific manifestation obtained is as shown in table 2:
Table 2
It should be noted that in practical applications, the execution sequence of S402, S403 and S404 are not limited to be retouched above
The sequence stated when specific implementation, can first carry out S402, can also first carry out S403, can also first carry out S404, can also be same
Shi Zhihang S402, S403 and S404 are not specifically limited the execution sequence of S402, S403 and S404 herein.
S405: multiple data, the gene co-expressing unit and the gene pathway are expressed according to the transcriptional differences
Topological coefficient matrix determines marking result of the compound on every gene pathway；The marking result is for evaluating the chemical combination
Activation of the object for the gene pathway.
It, can after obtaining transcriptional differences expression multiple data, gene co-expressing unit and gene pathway topology coefficient matrix
To express multiple data, gene co-expressing unit and gene pathway topology coefficient matrix according to transcriptional differences obtained, adopt
Marking of the compound on every gene pathway is calculated as a result, the marking result is used to evaluate compound to base with IPANDA method
The activation risen by access.
Marking of the final specific identified compound on every gene pathway is as a result, as shown in table 3:
Table 3
| Gene pathway | Drug target 1 | Drug target 2 |
| Rap1_signaling_Main_Pathway | -0.622737634 | -0.619785569 |
| VEGF_signaling_Main_Pathway | -0.316897711 | -0.235690687 |
| Ras_signaling_Main_Pathway | -1.218444012 | -1.072584992 |
| Tryptophan_metabolism_Main_Pathway | -0.028747661 | -0.108538395 |
| TNF_signaling_Main_Pathway | -0.232548389 | -0.182675885 |
| PI3K_Akt_signaling_Main_Pathway | -0.377465567 | -0.220240466 |
| AMPK_signaling_Main_Pathway | -0.057748743 | 0.083952757 |
| Apoptosis_Main_Pathway | 0.227476786 | 0.277298624 |
| TGF_beta_signaling_Main_Pathway | -0.6715697 | -0.813821004 |
Wherein, positive value data representation compound has facilitation to corresponding gene pathway, and negative valued data represents chemical combination
Object is inhibited to corresponding gene pathway, and the more big then expression effect of the absolute value of numerical value is stronger.
It should be understood that in practical applications, needing the transcript profile data according to each drug target, correspondingly determining the target
The corresponding marking of drug is as a result, determine that classes of compounds used in the drug target, compound dosage and/or compound are made
With the time, the activation that gene pathway is risen.
It can be seen that in the embodiment of the present application, during determining gene pathway topology coefficient matrix, comprehensively considering
Facilitation, inhibiting effect, phosphorylation and dephosphorylation of the gene played in gene pathway, that is, determining gene
Effect during access topology coefficient matrix to gene played in gene pathway carries out accurate evaluation, in turn, after guarantee
The continuous chemical combination determined based on transcriptional differences expression multiple data, gene co-expressing unit and gene pathway topology coefficient matrix
Marking of the object on gene pathway is as a result, it is possible to the activation that more accurately characterization of compound plays gene pathway.
Prediction technique based on a kind of drug new indication that above embodiments provide, the embodiment of the present application also provides one
Its working principle is described in detail with reference to the accompanying drawing in the prediction meanss of kind of drug new indication.
Referring to Fig. 5, which is a kind of structural representation of the prediction meanss of drug new indication provided by the embodiments of the present application
Figure.The prediction meanss 500 of drug new indication provided by the embodiments of the present application may include first acquisition unit 510, input list
Member 520 and predicting unit 530.
First acquisition unit 510, for obtaining marking of the drug target on gene pathway as a result, the drug target exists
Marking result on gene pathway characterizes the drug target for the activation of the gene pathway；
Input unit 520, for marking result of the drug target on the gene pathway to be inputted machine learning
Model obtains the corresponding indication of the drug target, and the machine learning model is according to training drug in the gene pathway
On marking result and the trained drug known indications training obtain, the trained drug be indication known to medicine
Object；
Predicting unit 530, for obtaining the known indications of the drug target, and the drug target is corresponding suitable
The indication in disease in addition to the known indications of the drug target is answered, the new indication of the drug target is predicted as.
Optionally, described device 500 further include:
Second acquisition unit, the chemical structure of the corresponding known drug of new indication for obtaining the drug target；
Comparing unit is obtained for comparing the chemical structure of the drug target and the chemical structure of the known drug
Comparison result；
The drug target is determined as solving by the first determination unit if meeting preset condition for the comparison result
The drug of the certainly described new indication.
Optionally, described device 500 further include:
Third acquiring unit, for obtaining marking of the drug target on the corresponding gene pathway of the new indication
As a result；
Second determination unit, if the marking knot for the drug target on the corresponding gene pathway of the new indication
Fruit is greater than or equal to threshold value, then is determined as the drug target solving the drug of the new indication.
Optionally, described device 500 further include:
4th acquiring unit, for obtain the corresponding multiple drugs of the new indication respectively with the new indication pair
Marking result on the gene pathway answered；
Sequencing unit, for multiple drugs corresponding to the new indication respectively in base corresponding with the new indication
Because the marking result on access is ranked up according to sequence from high to low；
Third determination unit, if for including the target medicine in the corresponding drug of the preceding preset number new indication
The drug target is then determined as solving the drug of the new indication by object.
Optionally, the first acquisition unit, specifically includes:
Subelement is obtained, for obtaining the transcript profile data of control group drug and the transcript profile data of drug target；
Subelement is obtained, for according to the transcript profile data of the control group drug and the transcript profile number of the drug target
According to acquisition transcriptional differences express multiple data；
Subelement is clustered, for doing clustering processing to related gene, by the gene clusters of coexpression to same group, is obtained more
A gene co-expressing unit；
Coefficient distributes subelement for obtaining gene pathway
Each gene in the gene pathway distributes weight coefficient, obtains gene pathway topology coefficient matrix；The gene is in gene
Effect played in access includes: facilitation, inhibiting effect, phosphorylation and dephosphorylation；
Subelement is determined, for expressing multiple data, the gene co-expressing unit and institute according to the transcriptional differences
Gene pathway topology coefficient matrix is stated, determines marking result of the drug target on every gene pathway.
Optionally, the coefficient distributes subelement, is specifically used for:
+ 1 will be set as to the corresponding weight coefficient of the favorable gene of gene pathway；Gene pathway will be risen and be inhibited
The corresponding weight coefficient of the gene of effect is set as -1；
+ 2 are set by the corresponding weight coefficient of gene for playing phosphorylation to gene pathway；Gene pathway will be gone it
The corresponding weight coefficient of the gene of phosphorylation is set as -2.
Optionally, the acquisition gene pathway topology coefficient matrix, comprising:
According to the corresponding weight coefficient of each gene, R packet KEGG gene pathway figure (Kyoto is utilized
Encyclopedia of Genes and Genomes Graph, KEGGgraph) and R Speech enhancement picture library (R Language
Boost Graph Library, RBGL) calculate topological coefficient of the gene on every gene pathway.
Optionally, the cluster subelement, is specifically used for:
First time clustering processing is carried out to the gene of coexpression, and second is carried out to the first time cluster result and is gathered
Class processing, obtains gene co-expressing unit.
Optionally, the cluster subelement, is specifically used for:
Using density clustering device and/or hierarchical clustering device.
Optionally, the density clustering device includes: the noise application space clustering algorithm based on density
(Density-Based Spatial Clustering of Applications with Noise, DBSCAN), and/or, row
Sequence point with identify cluster topology algorithm (Ordering Points to identity the clustering structure,
OPTICS)；
The hierarchical clustering device includes: hierarchical structure equilibrium iteration clustering algorithm (Balance Iterative
Reducing and Clustering using Hierarchies,BIRCH)。
Since described device 500 is dress corresponding with the prediction technique of drug new indication of above method embodiment offer
It sets, the specific implementation of each unit of described device 500, is same design with above method embodiment, accordingly, with respect to described
The specific implementation of each unit of device 500 can refer to the description section of above method embodiment, and details are not described herein again.
As can be seen from the above description, the prediction meanss of drug new indication provided by the embodiments of the present application can be used for really
The new curative effect of fixed existing drug target, specifically, marking of the available drug target on gene pathway is as a result, the mesh
It marks marking result of the drug on gene pathway and characterizes the drug target for the activation of the gene pathway；Then will
The marking result inputs machine learning model, obtains the corresponding indication of the drug target.Since the machine learning model is
The known adaptation of marking result and the trained drug of the training drug on the gene pathway according to known to indication
Disease training obtains, therefore, by the machine learning model, can according to marking of the drug target on gene pathway as a result,
Determine the corresponding indication of the drug target.After the indication for determining drug target, it is contemplated that may include in the indication
The known indications of drug target, so the known adaptation for the drug target being removed in the corresponding indication of the drug target
Indication except disease is predicted as the new indication of the drug target.It can be seen that using the method for the embodiment of the present application,
The new indication of drug target can be predicted, it can predict the new curative effect of existing drug.
The embodiment of the present application also provides a kind of pre- measurement equipment of drug new indication, the prediction of the drug new indication
Equipment includes: processor and memory；
The memory is transferred to the processor for storing program code, and by said program code；
The processor, the drug new indication for calling the instruction execution above method embodiment in memory to provide
Prediction technique.
When introducing the element of various embodiments of the application, the article " one ", "one", " this " and " described " be intended to
Indicate one or more elements.Word "include", "comprise" and " having " are all inclusive and mean in addition to listing
Except element, there can also be other elements.
It should be noted that those of ordinary skill in the art will appreciate that realizing the whole in above method embodiment or portion
Split flow is relevant hardware can be instructed to complete by computer program, and the program can be stored in a computer
In read/write memory medium, the program is when being executed, it may include such as the process of above-mentioned each method embodiment.Wherein, the storage
Medium can be magnetic disk, CD, read-only memory (Read-Only Memory, ROM) or random access memory (Random
Access Memory, RAM) etc..
All the embodiments in this specification are described in a progressive manner, same and similar portion between each embodiment
Dividing may refer to each other, and each embodiment focuses on the differences from other embodiments.Especially for device reality
For applying example, since it is substantially similar to the method embodiment, so describing fairly simple, related place is referring to embodiment of the method
Part explanation.The apparatus embodiments described above are merely exemplary, wherein described be used as separate part description
Unit and module may or may not be physically separated.Furthermore it is also possible to select it according to the actual needs
In some or all of unit and module achieve the purpose of the solution of this embodiment.Those of ordinary skill in the art are not paying
In the case where creative work, it can understand and implement.
The above is only the specific embodiment of the application, it is noted that for the ordinary skill people of the art
For member, under the premise of not departing from the application principle, several improvements and modifications can also be made, these improvements and modifications are also answered
It is considered as the protection scope of the application.
Claims (21)
1. a kind of prediction technique of drug new indication, which is characterized in that the described method includes:
Marking of the drug target on gene pathway is obtained as a result, marking result characterization of the drug target on gene pathway
Activation of the drug target for the gene pathway；
Marking result of the drug target on the gene pathway is inputted into machine learning model, obtains the drug target
Corresponding indication, marking result and the instruction of the machine learning model according to training drug on the gene pathway
The known indications training for practicing drug obtains, and the trained drug is drug known to indication；
The known indications of the drug target are obtained, and the drug target will be removed in the corresponding indication of the drug target
Known indications except indication, be predicted as the new indication of the drug target.
2. the method according to claim 1, wherein the method also includes:
Obtain the chemical structure of the corresponding known drug of new indication of the drug target；
The chemical structure of the drug target and the chemical structure of the known drug are compared, comparison result is obtained；
If the comparison result meets preset condition, the drug target is determined as to solve the drug of the new indication.
3. method according to claim 1 or 2, which is characterized in that the method also includes:
Obtain marking result of the drug target on the corresponding gene pathway of the new indication；
It, will if marking result of the drug target on the corresponding gene pathway of the new indication is greater than or equal to threshold value
The drug target is determined as solving the drug of the new indication.
4. method according to claim 1 or 2, which is characterized in that the method also includes:
Obtain the marking on gene pathway corresponding with the new indication respectively of the corresponding multiple drugs of the new indication
As a result；
Multiple drugs corresponding to new indication marking knot on gene pathway corresponding with the new indication respectively
Fruit is ranked up according to sequence from high to low；
It is if including the drug target in the corresponding drug of the preceding preset number new indication, the drug target is true
It is set to the drug for solving the new indication.
5. the method according to claim 1, wherein the marking knot for obtaining drug target on gene pathway
Fruit includes:
Obtain the transcript profile data of control group drug and the transcript profile data of drug target；
According to the transcript profile data of the transcript profile data of the control group drug and the drug target, transcriptional differences expression is obtained
Multiple data；
Clustering processing is done to related gene, by the gene clusters of coexpression to same group, obtains multiple gene co-expressing units；
Gene pathway is obtained, is each base in the gene pathway according to gene effect played in the gene pathway
Because distributing weight coefficient, gene pathway topology coefficient matrix is obtained；Effect of the gene played in gene pathway includes: to promote
Into effect, inhibiting effect, phosphorylation and dephosphorylation；
Multiple data, the gene co-expressing unit and the gene pathway topology coefficient square are expressed according to the transcriptional differences
Battle array, determines marking result of the drug target on every gene pathway.
6. according to the method described in claim 5, it is characterized in that, the effect according to gene played in gene pathway,
Weight coefficient is distributed for each gene in gene pathway, comprising:
+ 1 will be set as to the corresponding weight coefficient of the favorable gene of gene pathway；Inhibiting effect will be played to gene pathway
The corresponding weight coefficient of gene be set as -1；
+ 2 are set by the corresponding weight coefficient of gene for playing phosphorylation to gene pathway；It phosphoric acid will be removed to gene pathway
The corresponding weight coefficient of gene of change effect is set as -2.
7. method according to claim 5 or 6, which is characterized in that the acquisition gene pathway topology coefficient matrix, packet
It includes:
According to the corresponding weight coefficient of each gene, it is logical in every gene that gene is calculated using R packet KEGGgraph and RBGL
The topological coefficient of road.
8. according to the method described in claim 5, it is characterized in that, described do clustering processing to gene, by the gene of coexpression
Same group is clustered, multiple gene co-expressing units are obtained, comprising:
First time clustering processing is carried out to the gene of coexpression, and the first time cluster result is carried out at second of cluster
Reason obtains gene co-expressing unit.
9. according to the method described in claim 5, it is characterized in that, described do clustering processing to gene, by the gene of coexpression
Same group is clustered, multiple gene co-expressing units are obtained, comprising:
Using density clustering method and/or hierarchy clustering method.
10. according to the method described in claim 9, it is characterized in that, the density clustering method includes: DBSCAN,
And/or OPTICS；
The hierarchy clustering method includes: BIRCH.
11. a kind of prediction meanss of drug new indication, which is characterized in that described device includes:
First acquisition unit, for obtaining marking of the drug target on gene pathway as a result, the drug target is logical in gene
The marking result of road characterizes the drug target for the activation of the gene pathway；
Input unit is obtained for marking result of the drug target on the gene pathway to be inputted machine learning model
To the corresponding indication of the drug target, marking of the machine learning model according to training drug on the gene pathway
As a result and the training of the known indications of the trained drug obtains, and the trained drug is drug known to indication；
Predicting unit, for obtaining the known indications of the drug target, and will be in the corresponding indication of the drug target
Indication in addition to the known indications of the drug target is predicted as the new indication of the drug target.
12. the apparatus according to claim 1, which is characterized in that described device further include:
Second acquisition unit, the chemical structure of the corresponding known drug of new indication for obtaining the drug target；
Comparing unit is compared for comparing the chemical structure of the drug target and the chemical structure of the known drug
As a result；
The drug target is determined as solving institute by the first determination unit if meeting preset condition for the comparison result
State the drug of new indication.
13. device according to claim 11 or 12, which is characterized in that described device further include:
Third acquiring unit, for obtaining marking knot of the drug target on the corresponding gene pathway of the new indication
Fruit；
Second determination unit, if big for marking result of the drug target on the corresponding gene pathway of the new indication
In or equal to threshold value, then the drug target is determined as solving the drug of the new indication.
14. device according to claim 11 or 12, which is characterized in that described device further include:
4th acquiring unit, for obtaining the corresponding multiple drugs of the new indication respectively corresponding with the new indication
Marking result on gene pathway；
Sequencing unit is logical in gene corresponding with the new indication respectively for multiple drugs corresponding to the new indication
The marking result of road is ranked up according to sequence from high to low；
Third determination unit, if for including the drug target in the corresponding drug of the preceding preset number new indication,
Then the drug target is determined as to solve the drug of the new indication.
15. device according to claim 11, which is characterized in that the first acquisition unit specifically includes:
Subelement is obtained, for obtaining the transcript profile data of control group drug and the transcript profile data of drug target；
Subelement is obtained, for according to the transcript profile data of the control group drug and the transcript profile data of the drug target,
It obtains transcriptional differences and expresses multiple data；
It clusters subelement and, by the gene clusters of coexpression to same group, obtains multiple bases for doing clustering processing to related gene
Because co-expressing unit；
It, according to gene effect played in the gene pathway, is described that coefficient, which distributes subelement for obtaining gene pathway,
Each gene in gene pathway distributes weight coefficient, obtains gene pathway topology coefficient matrix；The gene is in gene pathway
Played in effect include: facilitation, inhibiting effect, phosphorylation and dephosphorylation；
Subelement is determined, for expressing multiple data, the gene co-expressing unit and the base according to the transcriptional differences
Because of access topology coefficient matrix, marking result of the drug target on every gene pathway is determined.
16. device according to claim 15, which is characterized in that the coefficient distributes subelement, is specifically used for:
+ 1 will be set as to the corresponding weight coefficient of the favorable gene of gene pathway；Inhibiting effect will be played to gene pathway
The corresponding weight coefficient of gene be set as -1；
+ 2 are set by the corresponding weight coefficient of gene for playing phosphorylation to gene pathway；It phosphoric acid will be removed to gene pathway
The corresponding weight coefficient of gene of change effect is set as -2.
17. device according to claim 15 or 16, which is characterized in that the acquisition gene pathway topology coefficient matrix,
Include:
According to the corresponding weight coefficient of each gene, it is logical in every gene that gene is calculated using R packet KEGGgraph RBGL
The topological coefficient of road.
18. device according to claim 15, which is characterized in that the cluster subelement is specifically used for:
First time clustering processing is carried out to the gene of coexpression, and the first time cluster result is carried out at second of cluster
Reason obtains gene co-expressing unit.
19. device according to claim 15, which is characterized in that the cluster subelement is specifically used for:
Using density clustering device and/or hierarchical clustering device.
20. device according to claim 19, which is characterized in that the density clustering device includes: DBSCAN,
And/or OPTICS；
The hierarchical clustering device includes: BIRCH.
21. a kind of pre- measurement equipment of drug new indication, which is characterized in that the pre- measurement equipment of the drug new indication includes:
Processor and memory；
The memory is transferred to the processor for storing program code, and by said program code；
The processor, for calling drug described in the instruction execution claim 1-10 any one in memory newly to adapt to
The prediction technique of disease.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910280839.8A CN109935341B (en) | 2019-04-09 | 2019-04-09 | Method and device for predicting new drug indication |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910280839.8A CN109935341B (en) | 2019-04-09 | 2019-04-09 | Method and device for predicting new drug indication |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109935341A true CN109935341A (en) | 2019-06-25 |
| CN109935341B CN109935341B (en) | 2021-04-13 |
Family
ID=66989600
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910280839.8A Active CN109935341B (en) | 2019-04-09 | 2019-04-09 | Method and device for predicting new drug indication |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109935341B (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110782998A (en) * | 2019-10-12 | 2020-02-11 | 平安医疗健康管理股份有限公司 | Data auditing method and device, computer equipment and storage medium |
| CN114358202A (en) * | 2022-01-11 | 2022-04-15 | 平安科技（深圳）有限公司 | Information pushing method and device based on drug molecule image classification |
| CN114496302A (en) * | 2021-12-29 | 2022-05-13 | 深圳云天励飞技术股份有限公司 | Method for predicting pharmaceutical indications and related device |
Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1309722A (en) * | 1998-05-12 | 2001-08-22 | 罗斯塔英法美蒂克斯公司 | Quantitative methods, systems and apparatuses for gene expression analysis |
| CN104021316A (en) * | 2014-06-27 | 2014-09-03 | 中国科学院自动化研究所 | Method for predicting novel adaptation disease of older medicine based on gene space fusion matrix decomposition |
| CN105138862A (en) * | 2015-07-31 | 2015-12-09 | 同济大学 | Collaborative anti-cancer pharmaceutical combination prediction method and pharmaceutical composition |
| CN105224823A (en) * | 2015-09-02 | 2016-01-06 | 苏州协云和创生物科技有限公司 | A kind of drug gene target spot Forecasting Methodology |
| CN105740626A (en) * | 2016-02-01 | 2016-07-06 | 华中农业大学 | Drug activity prediction method based on machine learning |
| CN105740651A (en) * | 2016-03-07 | 2016-07-06 | 吉林大学 | Construction method for specific cancer differential expression gene regulation and control network |
| CN107731309A (en) * | 2017-08-31 | 2018-02-23 | 武汉百药联科科技有限公司 | A kind of Forecasting Methodology of pharmaceutical activity and its application |
| CN108559778A (en) * | 2018-04-28 | 2018-09-21 | 北京师范大学 | Huppert's disease molecule parting and its application on medication guide |
| CN109192252A (en) * | 2018-08-23 | 2019-01-11 | 南开大学 | Co-express purposes of the transcription group of period circadian rhythm in mechanism of drug action discovery |
| CN109256213A (en) * | 2018-08-21 | 2019-01-22 | 四川靠谱健康管理有限公司 | A kind of health control method of combination genetic risk and environmental risk factors |
| CN109411033A (en) * | 2018-11-05 | 2019-03-01 | 杭州师范大学 | A kind of curative effect of medication screening technique based on complex network |
-
2019
- 2019-04-09 CN CN201910280839.8A patent/CN109935341B/en active Active
Patent Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1309722A (en) * | 1998-05-12 | 2001-08-22 | 罗斯塔英法美蒂克斯公司 | Quantitative methods, systems and apparatuses for gene expression analysis |
| CN104021316A (en) * | 2014-06-27 | 2014-09-03 | 中国科学院自动化研究所 | Method for predicting novel adaptation disease of older medicine based on gene space fusion matrix decomposition |
| CN105138862A (en) * | 2015-07-31 | 2015-12-09 | 同济大学 | Collaborative anti-cancer pharmaceutical combination prediction method and pharmaceutical composition |
| CN105224823A (en) * | 2015-09-02 | 2016-01-06 | 苏州协云和创生物科技有限公司 | A kind of drug gene target spot Forecasting Methodology |
| CN105740626A (en) * | 2016-02-01 | 2016-07-06 | 华中农业大学 | Drug activity prediction method based on machine learning |
| CN105740651A (en) * | 2016-03-07 | 2016-07-06 | 吉林大学 | Construction method for specific cancer differential expression gene regulation and control network |
| CN107731309A (en) * | 2017-08-31 | 2018-02-23 | 武汉百药联科科技有限公司 | A kind of Forecasting Methodology of pharmaceutical activity and its application |
| CN108559778A (en) * | 2018-04-28 | 2018-09-21 | 北京师范大学 | Huppert's disease molecule parting and its application on medication guide |
| CN109256213A (en) * | 2018-08-21 | 2019-01-22 | 四川靠谱健康管理有限公司 | A kind of health control method of combination genetic risk and environmental risk factors |
| CN109192252A (en) * | 2018-08-23 | 2019-01-11 | 南开大学 | Co-express purposes of the transcription group of period circadian rhythm in mechanism of drug action discovery |
| CN109411033A (en) * | 2018-11-05 | 2019-03-01 | 杭州师范大学 | A kind of curative effect of medication screening technique based on complex network |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110782998A (en) * | 2019-10-12 | 2020-02-11 | 平安医疗健康管理股份有限公司 | Data auditing method and device, computer equipment and storage medium |
| CN114496302A (en) * | 2021-12-29 | 2022-05-13 | 深圳云天励飞技术股份有限公司 | Method for predicting pharmaceutical indications and related device |
| CN114358202A (en) * | 2022-01-11 | 2022-04-15 | 平安科技（深圳）有限公司 | Information pushing method and device based on drug molecule image classification |
| CN114358202B (en) * | 2022-01-11 | 2024-10-15 | 平安科技（深圳）有限公司 | Information pushing method and device based on medicine molecular image classification |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109935341B (en) | 2021-04-13 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109935341A (en) | A kind of prediction technique and device of drug new indication | |
| AU2016280074B2 (en) | Systems and methods for patient-specific prediction of drug responses from cell line genomics | |
| Markowetz et al. | Nested effects models for high-dimensional phenotyping screens | |
| CN108681660A (en) | A kind of non-coding RNA based on association rule mining and disease relationship prediction technique | |
| CN111613297A (en) | Method, system and device for establishing traditional Chinese medicine action mechanism model based on network pharmacology | |
| Nikolova | On stochastic models in biology and medicine | |
| US8355874B2 (en) | Method for identifying predictive biomarkers from patient data | |
| Gupta et al. | Identification of gene network motifs for cancer disease diagnosis | |
| Liu et al. | Combination of neuro-fuzzy network models with biological knowledge for reconstructing gene regulatory networks | |
| CN115376649B (en) | Dose prediction method and device for intrathecal opioid analgesic | |
| CN109801676A (en) | A kind of method and device acted on for evaluating compound on gene signal pathway activated | |
| CN113450881B (en) | Scoring method for three-dimensional similarity of molecules for virtual screening of drugs | |
| Wu et al. | Traditional Chinese Medicine studies for Alzheimer’s disease via network pharmacology based on entropy and random walk | |
| CN116153527A (en) | Attention mechanism-based method and system for predicting side effects of combination of psychotropic drugs | |
| Binkheder et al. | Analyzing patterns of literature-based phenotyping definitions for text mining applications | |
| Jiang et al. | MOASL: Predicting drug mechanism of actions through similarity learning with transcriptomic signature | |
| Ghose et al. | Genome wide association neural networks (GWANN) identify genes linked to family history of Alzheimer’s disease | |
| KR20170017231A (en) | METHOD OF ACCESS TO IDENTIFYING GENE-microRNA MODULES IN CANCER | |
| Joshi et al. | A software framework integrating gene expression patterns, binding site analysis and gene ontology to hypothesize gene regulation relationships | |
| Kyle et al. | Bio-inspired growth: introducing emergence into computational design | |
| IL292291A (en) | Health-journey based computer automated patients' health risks stratification and interventions | |
| US20230170044A1 (en) | System and method for screening phenotypic targets associated with a disease using in-silico techniques | |
| Kwon et al. | Integrated network-based computational analysis for drug development | |
| Rainio | Stochastic process of social contacts | |
| Chiu et al. | Application of Fuzzy c-Means and Self-organizing maps for genes clustering in mouse brain microarray data analysis |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |