CN108363902A - A kind of accurate prediction technique of pathogenic hereditary variation - Google Patents
A kind of accurate prediction technique of pathogenic hereditary variation Download PDFInfo
- Publication number
- CN108363902A CN108363902A CN201810088147.9A CN201810088147A CN108363902A CN 108363902 A CN108363902 A CN 108363902A CN 201810088147 A CN201810088147 A CN 201810088147A CN 108363902 A CN108363902 A CN 108363902A
- Authority
- CN
- China
- Prior art keywords
- variation
- phenotype
- data
- pathogenic
- patient
- 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
Classifications
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16B—BIOINFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR GENETIC OR PROTEIN-RELATED DATA PROCESSING IN COMPUTATIONAL MOLECULAR BIOLOGY
- G16B20/00—ICT specially adapted for functional genomics or proteomics, e.g. genotype-phenotype associations
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16B—BIOINFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR GENETIC OR PROTEIN-RELATED DATA PROCESSING IN COMPUTATIONAL MOLECULAR BIOLOGY
- G16B5/00—ICT specially adapted for modelling or simulations in systems biology, e.g. gene-regulatory networks, protein interaction networks or metabolic networks
Abstract
The invention discloses a kind of accurate prediction techniques of pathogenic hereditary variation, and known pathogenic variation is divided into two classes:Database makes a variation and the variation of the training set positive, database makes a variation to obtain the half-proof in ACMG guides, the training set positive hereditary variation data of patient and corresponding phenotypic data are simulated by randomly selecting method, calculate the relevant feature of guide, the relevant feature of phenotype is calculated using the computational methods based on ERIC, judge relevant feature with pathogenic in conjunction with existing, using machine learning algorithm, realizes the pathogenic prediction of variation for considering that genotype data and phenotypic data carry out;This method solve there are problems that clinical phenotypes data are imperfect, lead to not into the pathogenic accurate prediction of row variation with noise and description inaccuracy in actual scene.
Description
Technical field
The present invention relates to a kind of prediction techniques, and in particular to a kind of accurate prediction technique of pathogenic hereditary variation.
Background technology
Rare disease genetic prognosis refers to finding to explain that the pathogenic heredity of patient clinical phenotype becomes from patient gene's group
Different process.Genetic prognosis can accurately and quickly be carried out and be related to the anaphase of patient, nursing even life.But it is accurate pre-
The difficult point for surveying hereditary variation of causing a disease is very big, in actual scene, that there are clinical phenotypes data is imperfect, with noise and description not
Accurate a series of problems leads to not into the pathogenic accurate prediction of row variation.
Invention content
For above-mentioned deficiency in the prior art, a kind of accurate prediction technique of pathogenic hereditary variation provided by the invention,
To solve in actual scene that there are clinical phenotypes data imperfect, leads to not into row variation with noise and description inaccuracy
The problem of pathogenic accurate prediction.
In order to reach foregoing invention purpose, the technical solution adopted by the present invention is:
A kind of accurate prediction technique of pathogenic hereditary variation, includes the following steps:
S1:The pathogenic variation it has been reported that with confirmation is collected, and is divided known pathogenic variation according to the priority of discovery time
At two classes:Database makes a variation and the variation of the training set positive;
S2:It is made a variation to obtain the evidence in ACMG guides according to the database obtained in step S1;
S3:According to the training set positive variation obtained in step S1, the heredity that patient is simulated by randomly selecting method becomes
Heteromerism evidence and corresponding phenotypic data;
S4:Evidence calculating simulation hereditary variation data in the ACMG guides obtained according to step S2, obtain ACMG guides
Relevant feature realizes that the relevant feature of guide is refined;
S5:Using the computational methods based on ERIC come the known phenotype collection of calculating simulation patient phenotypic data and each gene
The similitude between data is closed, the relevant feature of phenotype is obtained, realizes that the relevant feature of phenotype is refined;
S6:The relevant feature of phenotype that the relevant feature of guide and step S5 obtained according to step S4 obtains, in conjunction with existing
Some judges relevant feature with pathogenic, and using machine learning algorithm, realization considers genotype data and phenotypic data
The pathogenic prediction of variation.
Beneficial effects of the present invention are:
Feature based on guide improves the interpretation and accuracy of prediction result;Randomly selecting for phenotype is more true
The complexity for simulating clinical phenotypes improves the reliability and Clinical practicability of prediction technique;The table based on ERIC introduced
Type similarity calculation method enables prediction technique preferably to resist, and phenotype is imperfect, inaccurate and there are what noise band was come not to know
Property, further improve the accuracy of prediction technique.
Further, the side of randomly selecting of the hereditary variation data and corresponding phenotypic data of patient is simulated in step S3
Method includes the following steps:
S3-1:W negative variation is randomly selected from the populational variation from non-rare patient, is inserted into and is come from training set
It causes a disease and makes a variation known to 1 in positive variation, W negative variation and 1 positive, which are caused a disease, to make a variation constitutes the simulation heredity of patient
Make a variation data;
S3-2:A phenotype is randomly selected from the positive known phenotype of gene where variation of causing a disease, then randomly selects b
A phenotype simultaneously carries out inaccurateization processing, finally randomly selects c unrelated noise phenotypes, simulates the a+b+c table of patient
Type constitutes the phenotypic data of patient;
S3-3:Step S3-1 to S3-2 is repeated, the hereditary variation data of all patients and corresponding phenotypic data are simulated.
Above-mentioned further scheme has the beneficial effect that:
The randomly selecting of phenotype is inaccurately changed and noise treatment, reduces the authenticity of clinical phenotypes, improves prediction side
The reliability and Clinical practicability of method.
Further, in step S5, between calculating simulation patient phenotypic data and the known phenotype collective data of each gene
Similitude used in calculation formula be:
T in formula1、t2For two kinds of different clinical phenotypes of simulation patient;T1To simulate patient's phenotype set;T2For a gene
Known phenotype set;sim(t1,t2) it is phenotype t1And t2Between similarity.
Further, the similarity sim (t between phenotype are calculated1,t2) used in calculation formula be:
sim(t1,t2)=2IC (tMICA)-min(IC(t1),IC(t2))
T in formulaMICAFor phenotype t1And t2Maximum fault information common ancestor's node;IC(tMICA) it is two phenotype t1And t2Altogether
Same ancestors tMICAInformation content;IC(t1) and IC (t2) it is respectively phenotype t1And t2Information content.
Further, calculation formula used in the information content IC (t) of calculating simulation patient phenotype t is:
IC (t)=log (N/Nt)
N is gene number in formula;NtTo lead to the gene number of phenotype t.
Above-mentioned further scheme has the beneficial effect that:
Phenotype similarity calculation method based on ERIC is more accurate, can effectively resist inaccurate and noise phenotype shadow
It rings, improves the accuracy of prediction technique.
Further, in step S6, using the GBDT models in machine learning algorithm, realization considers genotype data
With the pathogenic prediction of variation of phenotypic data.
Above-mentioned further scheme has the beneficial effect that:
GBDT models are a kind of nonlinear models, and the letter from numerous characteristic variables can be preferably integrated compared to linear model
Breath, improves the accuracy and practicability of prediction technique.
Description of the drawings
Fig. 1 is a kind of accurate prediction technique flow chart of pathogenic hereditary variation.
Fig. 2 is test set variation (2016-2017 new discoveries variation) prediction case figure.
Fig. 3 is the ranking figure of distinct methods under different phenotype Sampling Modes.
Fig. 4 is the ranking figure that distinct methods cause a disease in true clinical data EJHG2017 in variation.
Specific implementation mode
The specific implementation mode of the present invention is described below, in order to facilitate understanding by those skilled in the art this hair
It is bright, it should be apparent that the present invention is not limited to the ranges of specific implementation mode, for those skilled in the art,
As long as various change is in the spirit and scope of the present invention that the attached claims limit and determine, these variations are aobvious and easy
See, all are using the innovation and creation of present inventive concept in the row of protection.
In the embodiment of the present invention, a kind of accurate prediction technique of pathogenic hereditary variation, as shown in Figure 1, including the following steps:
S1:The pathogenic variation for having been found to and confirming is collected from ClinVar databases, is divided into three further according to discovery time
Class:Database variation (finds) that the training set positive makes a variation (2013 to 2015 years) before 2013, the variation of the test set positive
(in June, -2017 in 2016);
S2:It makes a variation to obtain ACMG guides based on database and obtains the distinguishing rule of each evidence;
S3:According to the training set positive variation obtained in step S1, the something lost of 10,000 patients is simulated by randomly selecting method
Progress of disease heteromerism evidence and corresponding phenotypic data;
Method is randomly selected, is included the following steps:
S3-1:W negative variation is randomly selected from the populational variation from non-rare patient, is inserted into and is come from training set
It causes a disease and makes a variation known to 1 in positive variation, W negative variation and 1 positive, which are caused a disease, to make a variation constitutes the simulation heredity of patient
Make a variation data;
S3-2:A phenotype is randomly selected from the positive known phenotype of gene where variation of causing a disease, then randomly selects b
A phenotype simultaneously carries out inaccurateization processing, finally randomly selects c unrelated noise phenotypes, simulates the a+b+c table of patient
Type constitutes the phenotypic data of patient;
S3-3:Repeat step S3-1 to S3-2, the hereditary variation data of 10,000 patients of simulation and corresponding phenotypic data.
S4:Evidence calculating simulation hereditary variation data in the ACMG guides obtained according to step S2, obtain ACMG guides
Relevant feature realizes that the relevant feature of guide is refined;
S5:Using the computational methods based on ERIC come the known phenotype collection of calculating simulation patient phenotypic data and each gene
The similitude between data is closed, the relevant feature of phenotype is obtained, realizes that the relevant feature of phenotype is refined;
Similitude calculating used between calculating simulation patient phenotypic data and the known phenotype collective data of each gene is public
Formula is:
T in formula1、t2For two kinds of different clinical phenotypes of simulation patient;T1To simulate patient's phenotype set;T2For a gene
Known phenotype set;sim(t1,t2) it is phenotype t1And t2Between similarity.
Calculate the similarity sim (t between phenotype1,t2) used in calculation formula be:
sim(t1,t2)=2IC (tMICA)-min(IC(t1),IC(t2))
T in formulaMICAFor phenotype t1And t2Maximum fault information common ancestor's node;IC(tMICA) it is two phenotype t1And t2Altogether
Same ancestors tMICAInformation content;IC(t1) and IC (t2) it is respectively phenotype t1And t2Information content.
Calculation formula is used in the information content IC (t) of calculating simulation patient's phenotype t:
IC (t)=log (N/Nt)
N is gene number in formula;NtTo lead to the gene number of phenotype t.
S6:The relevant feature of phenotype that the relevant feature of guide and step S5 obtained according to step S4 obtains, in conjunction with existing
What is had is other to predicting cause a disease variation helpful data, such as CADD, PhyloP etc., as complementary features, obtains each mould
Paragenetic makes a variation in the feature of each dimension, and the GBDT models in machine learning algorithm, realization is recycled to consider genotype
The pathogenic prediction of variation of data and phenotypic data;The test set positive is made a variation and carries out step S3 to S6, realization considers base
Because of the pathogenic prediction of the variation of type data and phenotypic data, the effect for evaluating this prediction technique and other methods.
Embodiment:In order to show the high accuracy of this method, compares this method and other existing methods were arrived in 2016
The performance that 830 found for 2017 are caused a disease in the test data that variation is constituted, as shown in Figure 2.The common method of industry at present
There is a major class only to use the data information of genotype (Genotype Only) pathogenic to predict merely, such as MCAP,
CADD, MutationTaster.These methods are based primarily upon conservative of the gene order in evolution and to encoding histone amino
The calculating of the function effect degree of acid is pathogenic to predict.Figure it is seen that the accuracy ratio of such methods considers base simultaneously
Because the method (Exomiser) of type and phenotype wants low 20% or more.The result shows that method provided by the invention has than other methods
Apparent raising, than considering that the method (Exomiser) of genotype and phenotype improves 30% or more simultaneously.And it finds single
It is pure all to be had well using phenotypic characteristic (Xrare_phenotype) and simple guide for use evident feature (Xrare_ACMG)
Performance illustrates that the new phenotype measure introduced and the feature based on guide improve model accuracy.It can be sent out from Fig. 3
It is existing, lacked in phenotypic information, it is inaccurate and there are when phenotype noise, the performance of new phenotype method for measuring similarity obviously with
It is good.In order to which further method of evaluation and forecast is analyzed with other methods and expert's guidance type method (Clinically-Driven)
Result between difference, with true clinical case history and gene data come the performance of comparative approach.Use deliver within 2017
Authenticated 54 pathogenic sites of clinical expert as test, Fig. 4 the result shows that GBDT models obviously than expert's guidance type method
(Clinically-Driven) effect is also apparent.
Beneficial effects of the present invention are:
Feature based on guide improves the interpretation and accuracy of prediction result;Phenotype is randomly selected, inaccurately
Change and noise treatment, reduce the authenticity of clinical phenotypes, improve the reliability and Clinical practicability of prediction technique;It introduces
Phenotype similarity calculation method based on ERIC enable prediction technique preferably resist phenotype it is imperfect, it is inaccurate and exist make an uproar
The uncertainty that vocal cores comes, to improve the accuracy of prediction technique;It is further improved using nonlinear GBDT models
The accuracy and practicability of prediction technique.
Claims (6)
1. a kind of accurate prediction technique of pathogenic hereditary variation, which is characterized in that include the following steps:
S1:The pathogenic variation it has been reported that with confirmation is collected, and known pathogenic variation is divided into two according to the priority of discovery time
Class:Database makes a variation and the variation of the training set positive;
S2:It is made a variation to obtain the evidence in ACMG guides according to the database obtained in step S1;
S3:According to the training set positive variation obtained in step S1, the hereditary variation number of patient is simulated by randomly selecting method
According to corresponding phenotypic data;
S4:It is related to obtain ACMG guides for evidence calculating simulation hereditary variation data in the ACMG guides obtained according to step S2
Feature, realize that the relevant feature of guide is refined;
S5:Utilize the known phenotype collective data of computational methods calculating simulation patient phenotypic data and each gene based on ERIC
Between similitude, obtain the relevant feature of phenotype, realize that the relevant feature of phenotype is refined;
S6:The relevant feature of phenotype that the relevant feature of guide and step S5 obtained according to step S4 obtains, in conjunction with existing
Judge relevant feature with pathogenic, using machine learning algorithm, realizes the change for considering genotype data and phenotypic data
Different pathogenic prediction.
2. prediction technique according to claim 1, which is characterized in that simulate the hereditary variation number of patient in the step S3
Method is randomly selected according to corresponding phenotypic data, is included the following steps:
S3-1:W negative variation is randomly selected from the populational variation from non-rare patient, is inserted into positive from training set
It causes a disease and makes a variation known to 1 in variation, W negative variation and 1 positive, which are caused a disease to make a variation, constitutes the simulation hereditary variation of patient
Data;
S3-2:A phenotype is randomly selected from the positive known phenotype of gene where variation of causing a disease, then randomly selects b table
Type simultaneously carries out inaccurateization processing, finally randomly selects c unrelated noise phenotypes, simulates the a+b+c phenotype of patient, structure
At the phenotypic data of patient;
S3-3:Step S3-1 to S3-2 is repeated, the hereditary variation data of all patients and corresponding phenotypic data are simulated.
3. prediction technique according to claim 1, which is characterized in that in the step S5, calculating simulation patient's Phenotype Number
It is according to calculation formula used in the similitude between the known phenotype collective data of each gene:
T in formula1、t2For two kinds of different clinical phenotypes of simulation patient;T1To simulate patient's phenotype set;T2For known to a gene
Phenotype set;sim(t1,t2) it is phenotype t1And t2Between similarity.
4. prediction technique according to claim 3, which is characterized in that calculate the similarity sim (t between phenotype1,t2) used
Calculation formula is:
sim(t1,t2)=2IC (tMICA)-min(IC(t1),IC(t2))
T in formulaMICAFor phenotype t1And t2Maximum fault information common ancestor's node;IC(tMICA) it is two phenotype t1And t2Common
Ancestors tMICAInformation content;IC(t1) and IC (t2) it is respectively phenotype t1And t2Information content.
5. prediction technique according to claim 4, which is characterized in that information content IC (t) institutes of calculating simulation patient's phenotype t
It is with calculation formula:
IC (t)=log (N/Nt)
N is gene number in formula;NtTo lead to the gene number of phenotype t.
6. prediction technique according to claim 1, which is characterized in that in the step S6, using in machine learning algorithm
GBDT models, realize and consider the pathogenic prediction of variation of genotype data and phenotypic data.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810088147.9A CN108363902B (en) | 2018-01-30 | 2018-01-30 | Accurate prediction method for pathogenic genetic variation |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810088147.9A CN108363902B (en) | 2018-01-30 | 2018-01-30 | Accurate prediction method for pathogenic genetic variation |
Publications (2)
Publication Number | Publication Date |
---|---|
CN108363902A true CN108363902A (en) | 2018-08-03 |
CN108363902B CN108363902B (en) | 2022-02-25 |
Family
ID=63007672
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201810088147.9A Active CN108363902B (en) | 2018-01-30 | 2018-01-30 | Accurate prediction method for pathogenic genetic variation |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN108363902B (en) |
Cited By (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109493917A (en) * | 2018-09-02 | 2019-03-19 | 上海市儿童医院 | A kind of evil component level calculation method of gene mutation harmfulness predicted value |
CN111862091A (en) * | 2020-08-05 | 2020-10-30 | 昆山杜克大学 | Early syndrome discovery system based on phenotype measurement |
CN112863605A (en) * | 2021-02-03 | 2021-05-28 | 中国人民解放军总医院第七医学中心 | Platform, method, computer device and medium for determining dysnoesia genes |
CN112951324A (en) * | 2021-02-05 | 2021-06-11 | 广州医科大学 | Pathogenic synonymous mutation prediction method based on undersampling |
CN113241118A (en) * | 2021-07-12 | 2021-08-10 | 法玛门多(常州)生物科技有限公司 | Method for predicting harmfulness of gene mutation |
CN116343913A (en) * | 2023-03-15 | 2023-06-27 | 昆明市延安医院 | Analysis method for predicting potential pathogenic mechanism of single-gene genetic disease based on phenotype semantic association gene cluster regulation network |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2016123692A1 (en) * | 2015-02-04 | 2016-08-11 | The University Of British Columbia | Methods and devices for analyzing particles |
CN106980749A (en) * | 2017-02-21 | 2017-07-25 | 成都奇恩生物科技有限公司 | The quick assisted location method of disease |
CN107169310A (en) * | 2017-03-20 | 2017-09-15 | 上海基银生物科技有限公司 | A kind of genetic test construction of knowledge base method and system |
CN107341366A (en) * | 2017-07-19 | 2017-11-10 | 西安交通大学 | A kind of method that complex disease susceptibility loci is predicted using machine learning |
-
2018
- 2018-01-30 CN CN201810088147.9A patent/CN108363902B/en active Active
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2016123692A1 (en) * | 2015-02-04 | 2016-08-11 | The University Of British Columbia | Methods and devices for analyzing particles |
CN106980749A (en) * | 2017-02-21 | 2017-07-25 | 成都奇恩生物科技有限公司 | The quick assisted location method of disease |
CN107169310A (en) * | 2017-03-20 | 2017-09-15 | 上海基银生物科技有限公司 | A kind of genetic test construction of knowledge base method and system |
CN107341366A (en) * | 2017-07-19 | 2017-11-10 | 西安交通大学 | A kind of method that complex disease susceptibility loci is predicted using machine learning |
Cited By (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109493917A (en) * | 2018-09-02 | 2019-03-19 | 上海市儿童医院 | A kind of evil component level calculation method of gene mutation harmfulness predicted value |
CN111862091A (en) * | 2020-08-05 | 2020-10-30 | 昆山杜克大学 | Early syndrome discovery system based on phenotype measurement |
CN112863605A (en) * | 2021-02-03 | 2021-05-28 | 中国人民解放军总医院第七医学中心 | Platform, method, computer device and medium for determining dysnoesia genes |
CN112951324A (en) * | 2021-02-05 | 2021-06-11 | 广州医科大学 | Pathogenic synonymous mutation prediction method based on undersampling |
CN113241118A (en) * | 2021-07-12 | 2021-08-10 | 法玛门多(常州)生物科技有限公司 | Method for predicting harmfulness of gene mutation |
CN116343913A (en) * | 2023-03-15 | 2023-06-27 | 昆明市延安医院 | Analysis method for predicting potential pathogenic mechanism of single-gene genetic disease based on phenotype semantic association gene cluster regulation network |
CN116343913B (en) * | 2023-03-15 | 2023-11-14 | 昆明市延安医院 | Analysis method for predicting potential pathogenic mechanism of single-gene genetic disease based on phenotype semantic association gene cluster regulation network |
Also Published As
Publication number | Publication date |
---|---|
CN108363902B (en) | 2022-02-25 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN108363902A (en) | A kind of accurate prediction technique of pathogenic hereditary variation | |
CN106572493B (en) | Rejecting outliers method and system in LTE network | |
CN108777873A (en) | The wireless sensor network abnormal deviation data examination method of forest is isolated based on weighted blend | |
CN105279397B (en) | A kind of method of key protein matter in identification of protein interactive network | |
CN111785328B (en) | Coronavirus sequence identification method based on gated cyclic unit neural network | |
CN110491441A (en) | A kind of gene sequencing data simulation system and method for simulation crowd background information | |
CN106919957A (en) | The method and device of processing data | |
CN105786898B (en) | A kind of construction method and device of domain body | |
CN110263934A (en) | A kind of artificial intelligence data mask method and device | |
CN115631789B (en) | Group joint variation detection method based on pan genome | |
CN109979531A (en) | A kind of genetic mutation recognition methods, device and storage medium | |
CN115798022A (en) | Artificial intelligence identification method based on feature extraction | |
CN109856494A (en) | A kind of Diagnosis Method of Transformer Faults based on support vector machines | |
CN113889252A (en) | Remote internet big data intelligent medical system based on vital sign big data clustering core algorithm and block chain | |
CN111144462A (en) | Unknown individual identification method and device for radar signals | |
CN111863135B (en) | False positive structure variation filtering method, storage medium and computing device | |
CN110489602B (en) | Knowledge point capability value estimation method, system, device and medium | |
CN114048320B (en) | Multi-label international disease classification training method based on course learning | |
CN113889274B (en) | Method and device for constructing risk prediction model of autism spectrum disorder | |
CN109145554A (en) | A kind of recognition methods of keystroke characteristic abnormal user and system based on support vector machines | |
CN110309727A (en) | A kind of foundation of Building recognition model, Building recognition method and apparatus | |
CN115081515A (en) | Energy efficiency evaluation model construction method and device, terminal and storage medium | |
CN108921434A (en) | A method of user capability prediction is completed by human-computer interaction | |
Yang et al. | Model selection between the fixed-effects model and the random-effects model in meta-analysis | |
CN107871141A (en) | A kind of classification Forecasting Methodology and classification fallout predictor for non-equilibrium data collection |
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 |