CN102930113B - Building method of two-level fitting quantitative structure-activity relationship (QSAR) model for forecasting compound activity - Google Patents
Building method of two-level fitting quantitative structure-activity relationship (QSAR) model for forecasting compound activity Download PDFInfo
- Publication number
- CN102930113B CN102930113B CN201210455239.9A CN201210455239A CN102930113B CN 102930113 B CN102930113 B CN 102930113B CN 201210455239 A CN201210455239 A CN 201210455239A CN 102930113 B CN102930113 B CN 102930113B
- Authority
- CN
- China
- Prior art keywords
- compound
- model
- training set
- activity
- qsar
- 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.)
- Expired - Fee Related
Links
Landscapes
- Investigating Or Analysing Biological Materials (AREA)
Abstract
The invention discloses a building method of a two-level fitting quantitative structure-activity relationship (QSAR) model for forecasting compound activity. The building method includes following procedures: 1 a plurality of compounds with the same frames are utilized as a training set, and the train set compounds are divided into substituent groups and are coincided; 2 a linear regression method is utilized to calculate local physiological action produced by each substituent group, and a preceding-stage fitting model is built; 3 according to the local physiological action which is obtained in calculating mode in the procedure 2, a neural network method is utilized to calculate the whole biological activity, and a backward-stage fitting model is built; and 4 the preceding-stage fitting model and the backward-stage fitting model are combined to form the front-and-back two-stage QSAR model. According to the building method, the linear regression method and the neural network method are combined to build the model, the neural network method has good fitting performance, and compared with a traditional linear model, the built model can accurately forecast the biological activity of the compounds.
Description
Technical field
The present invention relates to a kind of construction method of OSAR model, especially a kind of construction method of the two-stage matching QSAR model for predictive compound activity, belongs to biological medicine areas of information technology.
Background technology
Quantitative structure activity relationship (Quantitative Structure-Activity Relationship is called for short QSAR) is a kind of technology by mathematical model quantitative forecast compound activity.Result of study due to 3D QSAR has clear and definite directive significance, is extensively adopted by much research at present.But because the modeling process of 3D QSAR performs in the black box of business software, and the process in software black box is difficult to human intervention, this increases the difficulty of its modeling optimization undoubtedly, not yet has a kind of modeling method published, generally acknowledge convenient and swift 3D QSAR so far.Therefore, conveniently 3D QSAR modeling method is significant to set up one.
At present, the 3D QSAR method that publication is recorded is in modeling process, not only compound is superimposed irregular, and use traditional linear regression method (as partial least square method etc.), in the process of model of fit, only consider the complicacy that organic chemistry is theoretical, do not consider biological acceptor, cause not meeting biochemical theory, affecting the final goodness of fit and predictive ability.
Topomer composite technology based on bee-line has neat superimposed result, is a kind of compound folding method with optimistic application prospect.If the complicacy of biological acceptor can be considered, make the QSAR result of study based on Topomer folding method meet biochemical theory, then can improve the goodness of fit and the predictive ability of QSAR model.
Neural network (Neural Networks) is a kind of statistical modeling method that physiological function by simulating mammalian brain carries out data fitting.Neural network model has successfully been applied to the function prediction of biomacromolecule, the toxicity prediction of organic contaminant, the performance prediction etc. of macromolecule polymeric material, and the application in chemicals MOLECULE DESIGN is also by increasingly extensive.Because neural network approaches arbitrarily complicated mapping relations, therefore when the action target of compound is that the biological acceptor more complicated than Small molecular divides the period of the day from 11 p.m. to 1 a.m greatly, the QSAR model based on neural network can than the biologically active of linear model predictive compound more accurately.
QSAR modeling based on neural network generally needs by following three steps: 1) arrange the activity data of compound as dependent variable; 2) selecting suitable descriptor as independent variable calculates; 3) suitable neural net method is selected to build QSAR model.
Wherein, selecting suitable descriptor as independent variable is set up the necessary condition with the neural network QSAR model of good predict ability.If the information gain that independent variable contains is not enough, then institute's established model is difficult to have good predictive ability, although but the number increasing independent variable likely improves information gain, there will be over-fitting, not Convergent Phenomenon and cause model performance decline, even modeling failure.Therefore, find a kind of low dimensional vector comprising enough information gain as independent variable, very crucial based on the QSAR model of neural network for structure.
Summary of the invention
Object of the present invention is the defect in order to solve above-mentioned prior art, provides a kind of construction method with good fit goodness, the bioactive two-stage matching QSAR model for predictive compound activity of Accurate Prediction compound.
Object of the present invention can reach by taking following technical scheme:
For the construction method of the two-stage matching QSAR model of predictive compound activity, it is characterized in that comprising the following steps:
1) get several compounds with identical skeleton as training set, training set compound is divided substituting group, and superimposed training set compound;
2) according to the structure and energy of training set compound, adopt linear regression method to calculate the local physiological effect of each substituting group generation, set up prime model of fit;
3) according to activity and the step 2 of training set compound) the local physiological effect that calculates, adopt neural network to calculate the overall biologically active of compound, set up rear class model of fit;
4) prime model of fit and rear class model of fit are combined, be built into front and back stages QSAR model.
As a kind of preferred version, step 2) activity of described training set compound is inhibition concentration or inhibiting rate.
As a kind of preferred version, step 1) is specific as follows:
For existing compound, the data acquisition of biologic activity is carried out for particular test system, data target adopts the negative logarithmic form ［-lg (inhibition concentration) or-lg (1/ inhibiting rate-1) ］ of inhibition concentration or inhibiting rate, in this, as training set sample; Use the two-dimensional structure of Sybyl analysis software inspection compound, its three-dimensional structure is generated to the compound by inspection; Subsequently, the substituting group of Further Division compound, and be optimized; Finally, divide based on substituting group, and adopt Topomer composite technology to carry out superimposed to above compound three-dimensional structure.
As a kind of preferred version, step 2) specific as follows:
With the molecular field around the training set compound that probe scanning is superimposed, calculate MSA, CoMFA or CoMSIA molecular field, after molecular field information is selected, carry out linear regression with the assay activity of training set compound, obtain the prime model of fit of structure-activity relationship.
As a kind of preferred version, step 3) is specific as follows:
By step 2) the local physiological effect that calculates, be normalized with the activity of training set compound, obtain normalized value, go normalization by neural network model, calculate the overall biologically active of compound, obtain rear class model of fit.
As a kind of preferred version, described training set compound is the pyrazole compound with p38 kinase inhibition rate.
As a kind of preferred version, the sample size of described training set compound has 30 at least.
As a kind of preferred version, the substituting group that described training set compound divides has 2 at least, includes the connecting bridge of compound in the substituting group of described division.
As a kind of preferred version, described step 2) linear regression method that adopts is partial least square method or principal component analysis (PCA).
As a kind of preferred version, the neural network that described step 3) adopts is BF neural network or RBF neural method
The present invention has following beneficial effect relative to prior art:
1, modeling method of the present invention have employed the mode Modling model that linear regression method and neural network combine, and because neural network has good capability of fitting, the model of structure can than the biologically active of traditional linear model predictive compound more accurately.
2, modeling method of the present invention adopts linear regression to have two aspect beneficial effects as prime model: 1) linear model is easily explained, contributes to the structural modification of compound; 2) with the result of the prime model independent variable as rear class neural network model, can avoid occurring not restraining, the phenomenon of over-fitting; Thus prevent neural net model establishing failure, improve the predictive ability of rear class model, namely improve the predictive ability of whole front and back stages model of fit.
3, modeling method of the present invention have employed Topomer composite technology and carries out superimposed to training set compound, is conducive to the efficiency of modeling, and simultaneously superimposed result is neat.
4, modeling method of the present invention is without the need to molecular docking, few without the need to the independent variable number of quantum chemistry calculation, neural network, can can build based on the training set of large sample within the identical time like this and obtain model, thus the predictive ability of QSAR model can be improved further.
5, modeling method of the present invention solves and uses conventional linear to return the coarse problem that predicts the outcome caused as not the considering biological acceptor complicacy of modeling method, the two-stage matching QSAR model built is to the p38 kinase inhibiting activity of pyrazole compound, related coefficient square is greater than 0.95, present good good capability of fitting and estimated performance, the biologically active Forecasting Methodology as the pyrazoles immunosuppressive drug being action target spot with p38 kinases, anti-inflammatory agent, antifungal has broad application prospects.
Accompanying drawing explanation
Fig. 1 is the schematic flow sheet of two-stage matching QSAR model building method of the present invention.
Fig. 2 is that pyrazoles p38 inhibitors of kinases training set compound adopts traditional single stage model M
1goodness of fit scatter diagram.
Fig. 3 is that pyrazoles p38 inhibitors of kinases training set compound adopts front and back stages model M
1-M
2goodness of fit scatter diagram.
Fig. 4 is that pyrazoles p38 inhibitors of kinases training set compound adopts traditional single stage model M
1estimated performance scatter diagram.
Fig. 5 is that pyrazoles p38 inhibitors of kinases training set compound adopts front and back stages model M
1-M
2estimated performance scatter diagram.
Embodiment
Embodiment 1:
As shown in Figure 1, the linear regression-neural network front and back stages matching QSAR model of the present embodiment, its construction step is as follows:
1) bioactive arrangement
For ensureing statistics effect, get 35 pyrazole compounds with p38 kinase inhibition rate as training set S
1, its inhibiting rate α is converted into logarithmic form: Y
1=LgBio=-lg (α
-1-1).Y
1=LgBio is follow-up modeling dependent variable used, uses the two-dimensional structure of Sybyl analysis software inspection compound, generates its three-dimensional structure to the compound by inspection.
2) structure of prime model of fit
By training set compound S
1import the molecule list S1.tbl of Sybyl software, in Topomer CoMFA module, to training set S
1compound divide substituting group, substituting group divides and will ensure model coincidence theory on the one hand, to the goodness of fit of model, there is certain influence on the other hand, simultaneously also very relevant to the predictive ability of model, and when connecting bridge only has a few structure, it can be used as a substituting group, be conducive to inquiring into connecting bridge to bioactive impact, so by training set compound S
1be divided into connecting bridge and side chain two substituting groups, and adopt Topomer method these 35 compounds superimposed; With the molecular field around the training set compound that probe scanning is superimposed, calculate MSA, CoMFA or CoMSIA molecular field, after selecting molecular field information, then by Y
1=LgBio is appointed as dependent variable and sets up linear model (called after M
1), institute's established model is prime model of fit.Calculate by Sybyl software the local physiological effect P that compound substituent produces in modeling process
1; Because compound has two substituting groups, therefore P
1for bivector, in molecule list, be expressed as Act_R
1and Act_R
2.
3) structure of rear class model of fit
In SPSS Clementine software, by the above-mentioned local physiological effect P calculated by Sybyl software
1make independent variable, Y
1=LgBio makes dependent variable, is normalized, obtains normalized value, go normalization by neural network model with the activity of training set compound, calculation training collection S
1the overall biologically active of compound, sets up " thoroughly pruning " neural network model (called after M
2), institute's established model is rear class model of fit, in modeling process, sample is set to 100% to improve the predictive ability of model, random seed is set to 0 to ensure the repeatability of testing.
Embodiment 2:
The present embodiment measures the goodness of fit, compares the M that above-described embodiment 1 is built
1-M
2two-level model and M
1the goodness of fit of single-stage model, concrete steps are as follows:
1) variable naming
By model M
1to training set S
1the calculated activity called after Y of compound
2.
By model M
2to training set S
1the calculated activity called after Y of compound
3.
2) electronic form file is derived
By Sybyl molecule list S
1.tbl LgBio and Pre_LgBio two row in export as S
1_ M
1.csv file, then be converted to S
1_ M
1.xls file.Above-mentioned LgBio is Y
1, Pre_LgBio is Y
2.
Adopt identical method, from SPSS Clementine software, derive M2 to training set compound S
1calculated activity, save as S
1_ M
2.xls file; Wherein, S
1_ M
2.xls file comprises variable Y
1and Y
3.
3) calculate related coefficient square and draw scatter diagram
By electrical form S
1_ M
1.xls file imports in Origin software, to variable Y
1and Y
2do linear regression, calculate related coefficient square R
1be 0.95.Draw scatter diagram, result as shown in Figure 1.
By electrical form S
1_ M
2.xls file imports in Origin software, to variable Y
1and Y
3do linear regression, calculate related coefficient square R
2be 0.96.Draw scatter diagram, result as shown in Figure 2.
Thus, employing front and back stages model M can be seen
1-M
2compare single-stage model M
1, related coefficient square R
2>R
1=0.95, thus there is good capability of fitting.
Embodiment 3:
The present embodiment measures estimated performance, compares the M that above-described embodiment 1 is built
1-M
2two-level model and M
1the estimated performance of single-stage model, concrete steps are as follows:
1) arrangement of p38 kinase inhibiting activity
Get 35 non-training set S
1the pyrazole compound of element sets up test set S
2, its p38 kinase inhibiting activity is designated as Y
4.By test set S
235 pyrazole compounds be made into Sybyl molecule list S
2.tbl, by Y
4be appointed as dependent variable (being expressed as LgBio in S2.tbl molecule list).
2) estimated performance of single-stage model M1 measures
By in the TopomerCoMFA module of Sybyl software, predictive molecule list S
2.tbl p38 kinase inhibiting activity, result is designated as Y
5(at S
2.tbl Pre_LgBio is expressed as in molecule list).In forecasting process, calculate the substituent local physiological effect P of compound two
2, at S
2.tbl Act_R is expressed as in molecule list
1and Act_R
2.
Y is calculated in Origin software
4with Y
5related coefficient square R
3be 0.95, the scatter diagram that drafting obtains as shown in Figure 3.
3) estimated performance of two-level model M1-M2 measures
By in SPSS Clementine, with P
2for independent variable, Y
4for dependent variable, use rear class model M 2 to predict the p38 kinase inhibiting activity of test set compound S 2, result is designated as Y
6.
Y is calculated in Origin software
4with Y
6related coefficient square R4 be 0.96, draw the scatter diagram that obtains as shown in Figure 4.
Thus, employing front and back stages model M can be seen
1-M
2compare single-stage model M
1, related coefficient square R
4>R
3=0.95, thus there is good estimated performance.
The above; be only the preferred embodiment of the invention; but protection scope of the present invention is not limited thereto; anyly be familiar with those skilled in the art in scope disclosed in this invention; be equal to according to technical scheme of the present invention and inventive concept thereof and replace or change, all belonged to protection scope of the present invention.
Claims (8)
1., for the construction method of the two-stage matching QSAR model of predictive compound activity, it is characterized in that comprising the following steps:
1) get several compounds with identical skeleton as training set, training set compound is divided substituting group, and superimposed training set compound;
2) according to the structure and energy of training set compound, adopt linear regression method to calculate the local physiological effect of each substituting group generation, set up prime model of fit, be specially:
With the molecular field around the training set compound that probe scanning is superimposed, calculate MSA, CoMFA or CoMSIA molecular field, after molecular field information is selected, carry out linear regression with the assay activity of training set compound, obtain the prime model of fit of structure-activity relationship;
3) according to activity and the step 2 of training set compound) the local physiological effect that calculates, adopt neural network to calculate the overall biologically active of compound, set up rear class model of fit, be specially:
By step 2) the local physiological effect that calculates, be normalized with the activity of training set compound, obtain normalized value, go normalization by neural network model, calculate the overall biologically active of compound, obtain rear class model of fit;
4) prime model of fit and rear class model of fit are combined, be built into front and back stages QSAR model.
2. the construction method of the two-stage matching QSAR model for predictive compound activity according to claim 1, is characterized in that: step 2) activity of described training set compound is inhibition concentration or inhibiting rate.
3. the construction method of the two-stage matching QSAR model for predictive compound activity according to claim 2, is characterized in that: step 1) specific as follows:
For existing compound, carry out the data acquisition of biologic activity for particular test system, data target adopts the negative logarithmic form of inhibition concentration or inhibiting rate, in this, as training set sample; Use the two-dimensional structure of Sybyl analysis software inspection compound, its three-dimensional structure is generated to the compound by inspection; Subsequently, the substituting group of Further Division compound, and be optimized; Finally, divide based on substituting group, and adopt Topomer composite technology to carry out superimposed to above compound three-dimensional structure.
4. the construction method of the two-stage matching QSAR model for predictive compound activity according to any one of claim 1-3, is characterized in that: described training set compound is the pyrazole compound with p38 kinase inhibition rate.
5. the construction method of the two-stage matching QSAR model for predictive compound activity according to any one of claim 1-3, is characterized in that: the sample size of described training set compound has 30 at least.
6. the construction method of the two-stage matching QSAR model for predictive compound activity according to any one of claim 1-3, it is characterized in that: the substituting group that described training set compound divides has 2 at least, includes the connecting bridge of compound in the substituting group of described division.
7. the construction method of the two-stage matching QSAR model for predictive compound activity according to any one of claim 1-3, is characterized in that: described step 2) linear regression method that adopts is partial least square method or principal component analysis (PCA).
8. the construction method of the two-stage matching QSAR model for predictive compound activity according to any one of claim 1-3, is characterized in that: described step 3) neural network that adopts is BF neural network or RBF neural method.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201210455239.9A CN102930113B (en) | 2012-11-14 | 2012-11-14 | Building method of two-level fitting quantitative structure-activity relationship (QSAR) model for forecasting compound activity |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201210455239.9A CN102930113B (en) | 2012-11-14 | 2012-11-14 | Building method of two-level fitting quantitative structure-activity relationship (QSAR) model for forecasting compound activity |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN102930113A CN102930113A (en) | 2013-02-13 |
| CN102930113B true CN102930113B (en) | 2015-06-17 |
Family
ID=47644910
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201210455239.9A Expired - Fee Related CN102930113B (en) | 2012-11-14 | 2012-11-14 | Building method of two-level fitting quantitative structure-activity relationship (QSAR) model for forecasting compound activity |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN102930113B (en) |
Families Citing this family (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103646180A (en) * | 2013-12-19 | 2014-03-19 | 山东大学 | Method for forecasting acute toxicity of organic compounds by building quantitative structure-activity relationship model with quantum chemistry method |
| CN104636619B (en) * | 2015-02-10 | 2017-11-14 | 青岛农业大学 | A kind of method that quick virtual screening human small intestine easily absorbs the drug |
| CN104834831B (en) * | 2015-04-08 | 2017-06-16 | 北京工业大学 | A kind of consistency model construction method based on three-dimensional quantitative structure-activity relationship model |
| CN104866710B (en) * | 2015-05-08 | 2017-11-10 | 西北师范大学 | The method for predicting Cytochrome P450 1A2 inhibitor inhibition concentrations |
| CN105787297A (en) * | 2016-03-12 | 2016-07-20 | 云南圣清环境监测科技有限公司 | Microbial remediation system activity evaluating method |
| CN108416184B (en) * | 2017-02-09 | 2020-06-16 | 清华大学深圳研究生院 | 3D display method and system of compound |
| JP7201981B2 (en) * | 2017-06-30 | 2023-01-11 | 学校法人 明治薬科大学 | Prediction device, prediction method and prediction program |
| CN109360610B (en) * | 2018-11-26 | 2019-11-15 | 西南石油大学 | A method of the chemical molecular toxicity prediction model based on fuzzy neural network |
| US11798655B2 (en) * | 2019-05-15 | 2023-10-24 | International Business Machines Corporation | Feature vector feasibility estimation |
| CN112151111B (en) * | 2020-08-27 | 2022-10-11 | 上海大学 | QSAR method for rapidly predicting xanthine derivative inhibitory activity based on multiple linear regression |
| CN112102900B (en) * | 2020-10-12 | 2024-02-23 | 北京晶泰科技有限公司 | Drug design method based on TopoMA quantitative structure-activity relationship model |
Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2000079263A2 (en) * | 1999-06-18 | 2000-12-28 | Synt:Em S.A. | Identifying active molecules using physico-chemical parameters |
-
2012
- 2012-11-14 CN CN201210455239.9A patent/CN102930113B/en not_active Expired - Fee Related
Patent Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2000079263A2 (en) * | 1999-06-18 | 2000-12-28 | Synt:Em S.A. | Identifying active molecules using physico-chemical parameters |
Non-Patent Citations (4)
| Title |
|---|
| HIV_1逆转录酶抑制剂的定量构效关系及分子设计研究;闫宁;《中国优秀硕士学位论文全文数据库医药卫生科技辑》;20120115;第12-14，65-74页 * |
| 几种QSAR建模方法在化学中的应用与研究进展;周喜斌等;《计算机与应用化学》;20110628;第28卷(第6期);第761-764页 * |
| 基于主成分分析_人工神经网络对氯苯酚毒性QSAR研究;肖方竹;《毒理学杂志》;20121025;第26卷(第5期);第336-340页 * |
| 基于交叉验证的逐步回归结合RBF神经网络在QSAR中的应用;王威等;《南京化工大学学报》;20011030;第23卷(第5期);第25-27,40页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN102930113A (en) | 2013-02-13 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN102930113B (en) | Building method of two-level fitting quantitative structure-activity relationship (QSAR) model for forecasting compound activity | |
| Le Bagousse-Pinguet et al. | Phylogenetic, functional, and taxonomic richness have both positive and negative effects on ecosystem multifunctionality | |
| Tabak et al. | Directed clustering coefficient as a measure of systemic risk in complex banking networks | |
| Long et al. | Socio-economic development and land-use change: Analysis of rural housing land transition in the Transect of the Yangtse River, China | |
| Wang et al. | Scenario simulation of the tradeoff between ecological land and farmland in black soil region of Northeast China | |
| He et al. | Probability density forecasting of wind power based on multi-core parallel quantile regression neural network | |
| EP2558969A2 (en) | Methods of using generalized order differentiation and integration of input variables to forecast trends | |
| Yuan et al. | Efficiency estimation and reduction potential of the Chinese construction industry via SE-DEA and artificial neural network | |
| CN103150476B (en) | A kind of system efficiency evaluation method based on data station field | |
| Chen et al. | A two-stage method for model parameter identification based on the maximum power matching and improved flow direction algorithm | |
| Zhang et al. | HOMER-based multi-scenario collaborative planning for grid-connected PV-storage microgrids with electric vehicles | |
| CN110543499A (en) | Anti-electricity-stealing location tracking equipment based on multi-source data fusion | |
| CN105279388A (en) | Multilayer cloud computing framework coordinated integrated reduction method for gestational-age newborn brain medical records | |
| CN109859087A (en) | A kind of intelligent Community soft environment configuration system and method surpassing brain using city | |
| Zhang et al. | A projection pursuit dynamic cluster model based on a memetic algorithm | |
| Meng et al. | The integration of marine biodiversity information resources based on big data technology | |
| Uttej et al. | Prominent Technique for Rainfall Prediction using CatBoost over Light GBM for improving the Accuracy of Prediction | |
| Coccia | Measurement of the evolution of technology: A new perspective | |
| Lu et al. | Application of GA optimized wavelet neural networks for carrying capacity of water resources prediction | |
| Engdaw et al. | The impact of urbanization on food (in) security in Amhara Regional State Metropolitan cities: Monitoring income generating capacity limitation as a mediating variable | |
| Xiang et al. | HDFS efficiency storage strategy for big data in smart city | |
| CN110728403A (en) | Rural medium-long term power grid load prediction method | |
| Xu et al. | Measurement methods and application research of triple Helix model in collaborative innovation management | |
| Liu et al. | The Spatial and Temporal Evolution Pattern and Influencing Factors of Urban Human Settlement Resilience in Three Provinces of Northeast China | |
| Orlov | Theoretical Optimization of Enzymatic Biomass Processes |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| C14 | Grant of patent or utility model | ||
| GR01 | Patent grant | ||
| CF01 | Termination of patent right due to non-payment of annual fee | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20150617 Termination date: 20201114 |