CN102708269A - Method for predicting inhibiting concentration of inhibitor of cytosolic phospholipase A2alpha based on support vector machine - Google Patents
Method for predicting inhibiting concentration of inhibitor of cytosolic phospholipase A2alpha based on support vector machine Download PDFInfo
- Publication number
- CN102708269A CN102708269A CN201110325636XA CN201110325636A CN102708269A CN 102708269 A CN102708269 A CN 102708269A CN 201110325636X A CN201110325636X A CN 201110325636XA CN 201110325636 A CN201110325636 A CN 201110325636A CN 102708269 A CN102708269 A CN 102708269A
- Authority
- CN
- China
- Prior art keywords
- descriptor
- inhibitor
- value
- inhibitor molecules
- cytosolic phospholipase
- 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
Images
Landscapes
- Measuring Or Testing Involving Enzymes Or Micro-Organisms (AREA)
Abstract
The invention relates to a method for predicting the inhibiting concentration of an inhibitor of cytosolic phospholipase A2alpha based on a support vector machine, and belongs to the cross field of chemometrics and cheminformatics. By establishing a relational model between the molecular structure and the inhibiting concentration of one inhibitor through the support vector machine, the inhibiting concentration corresponding to the inhibitor can be predicted as long as the molecular structure of the inhibitor is known. The prediction accuracy rate of the method can achieve over 90 percent, the model is stable, the risk of inhibitor development in a later period can be reduced, and the cost of research and development can be reduced.
Description
Technical field
The present invention relates to a kind of based on SVM prediction cytosolic phospholipase A
2The method of the inhibition concentration of alpha inhibitor belongs to the crossing domain of Chemical Measurement and Chemoinformatics.
Background technology
Cytosolic phospholipase A
2α is cytosolic phospholipase A
2One of three hypotypes (being respectively α, β, γ), it can limit arachidonic generation, in addition cytosolic phospholipase A
2The activation of α has caused the generation of a large amount of grease mediators, for example leukotrienes, prostaglandin, platelet activating factor etc.Owing to suppress the endochylema phospholipase A
2The activation of α has great significance, so cytosolic phospholipase A
2The exploitation of alpha inhibitor has caused drug research person's interest.The inhibition concentration experimental data test of inhibitor molecules is difficult, expense is higher; Limited obtaining of great amount of samples; And inhibition concentration is to estimate the leading indicator of inhibitor effect, therefore at the suppressant initial stage of development, accurately predicts the inhibition concentration of inhibitor molecules; Can reduce the risk of later stage suppressant exploitation, reduce R&D costs.
SVMs is based on a kind of new machine learning method of Statistical Learning Theory, and purpose is according to the estimation of given training sample to dependence between certain system's input and output, makes it make prediction as far as possible accurately to the unknown output.
Summary of the invention
The objective of the invention is to solve cytosolic phospholipase A in the prior art
2The problem of the inhibition concentration experimental data test difficulty of alpha inhibitor provides a kind of and accurately predicts cytosolic phospholipase A based on SVMs
2The method of the inhibition concentration of alpha inhibitor.
The object of the invention realizes through following technical scheme,
A kind of based on SVM prediction cytosolic phospholipase A
2The method of the inhibition concentration of alpha inhibitor is characterized in that, comprises the steps:
1) foundation of sample set: collect cytosolic phospholipase A
2The molecular structure of alpha inhibitor;
2) structure of inhibitor molecules descriptor set: input cytosolic phospholipase A
2The molecular structure of alpha inhibitor calculates the molecule descriptor value corresponding with it, and this molecule descriptor contains several components;
3) simplify the inhibitor molecules descriptor set;
4) scale again of inhibitor molecules descriptor set: the inhibitor molecules descriptor set after will simplifying is mapped to [1; + 1] interval, the mapping formula is:
Wherein,
xBe the original value of inhibitor molecules descriptor,
x Pre Be again the value after the scale,
x Max With
x MinThe maximal value and the minimum value of the corresponding inhibitor molecules descriptor of difference,
y Max With
y MinInterval maximal value of difference correspondence mappings and minimum value are promptly+1 with-1;
5) will pass through step 2) to 4) sample set after handling at random be divided into training set and test set, utilize training set data, adopt 10 to roll over cross validation method at random, the supporting vector machine model parameter is optimized;
6) with the described training set of step 5) with optimize after the SVMs parameter that obtains set up the relational model of inhibitor molecules structure and inhibition concentration;
7) with the described test set data of step 5) input step 6) relational model set up, the inhibition concentration of prediction suppressant.
Further, step 2) conformation of the molecular structure of said suppressant is in the minimum energy state.
Further, the calculating of molecule descriptor is to adopt online drug molecule descriptor computation software MODEL to accomplish step 2).
Further, the described simplification process of step 3) is:
(a) deletion and the little inhibitor molecules descriptor of inhibitor molecules structural dependence;
(b) deleting descriptor value again is 0 inhibitor molecules descriptor, the descriptor that deletion all equates for the pairing molecule descriptor value of all suppressant;
(c) use stepwise regression method that remaining inhibitor molecules descriptor is screened again.
Further, in step 5), sample set is that the ratio random division in 4:1 is training set and test set.
Further, the supporting vector machine model parameter optimisation procedure described in the step 5) is:
Capacity factor measure C is set is fixed as 100; The maximal value of the ε value variation range of ε insensitive loss function is 1, and minimum value is-1, and change step is 0.01; The maximal value of the value variation range of kernel function parameter γ is 1, and minimum value-1, change step are 0.01; Kernel function K selects the radially basic kernel function of Gauss for use;
With training set at random be divided into 10 groups; 9 groups of relational models that are used for setting up inhibitor molecules structure and inhibition concentration wherein; Remaining one group is used for verifying this model; Successively each group is carried out one-time authentication, with the mean value of resultant 10 results' in checking back accuracy rate as estimation accurately;
The value of the ε value of pairing capacity factor measure C, ε insensitive loss function, kernel function parameter γ was the optimal value of supporting vector machine model parameter when accuracy rate was the highest.
The present invention compared with prior art has the following advantages: the present invention effectively utilizes support vector machine method to set up model prediction cytosolic phospholipase A
2The inhibition concentration of alpha inhibitor; It is based on a kind of new machine learning method of Statistical Learning Theory; It is a theoretical foundation with the structural risk minimization principle; Have the Complex Nonlinear System of approaching, stronger study generalization ability and good recurrence performance and the unique advantage of the outside huge data of computing machine fast processing thereof, forecast quality and forecasting efficiency are greatly improved.At the initial stage of suppressant exploitation, through computing machine input inhibitor molecules structure,, accomplish prediction to its inhibition concentration based on support vector machine method, can reduce the risk of later stage suppressant exploitation, reduce R&D costs.Through the model of being set up is estimated, calculating training set and test set correlation coefficient r is 0.9170,0.9667, cross validation coefficient Q
2Be 0.9901,0.9943, predictablity rate of the present invention can reach more than 90%, and model is more stable.
Description of drawings
Fig. 1 utilizes the present invention to realize based on SVM prediction cytosolic phospholipase A
2The method flow diagram of the inhibition concentration of alpha inhibitor.
Fig. 2 based on support vector machine method to the endochylema phospholipase A
2The inhibition concentration of the alpha inhibitor figure that predicts the outcome.
Wherein, the IC among Fig. 2
50Be meant the 503nhibiting concentration of suppressant, pIC
50=-logIC
50
Embodiment
Below in conjunction with embodiment and accompanying drawing the present invention is further specified.
Based on SVM prediction endochylema phospholipase A
2The method of the inhibition concentration of alpha inhibitor, concrete steps are:
1, the foundation of sample set: collected 49 kinds of cytosolic phospholipase A
2Alpha inhibitor molecule and to cytosolic phospholipase A
2The inhibition concentration of α.Utilize the computer software Gaussian view 3.09 every kind of cytosolic phospholipase A that draws
2The structure of alpha inhibitor molecule is carried out conformation optimization with 7 pairs of above-mentioned molecular structures of computer software Hyperchem Release again, seeks out every kind of cytosolic phospholipase A
2The minimum energy state of alpha inhibitor molecule, the semiempirical MP3 method of selecting for use software Hyperchem to be provided when conformation is optimized.
2, the structure of inhibitor molecules descriptor set: each the inhibitor molecules sample in the sample set that step 1 is set up all will be by a descriptor vector representation; This descriptor vector has included the structural information of suppressant; This descriptor vector comprises 3778 kinds of molecule descriptors: specifically can be divided into electronics descriptor, ingredient descriptor, topological index descriptor, physicochemical property descriptor, geometrical molecular descriptor, quantum chemistry descriptor six big classes, the molecule descriptor of all samples has constituted the inhibitor molecules descriptor set.Concrete calculating is with the cytosolic phospholipase A through optimizing
2The conformation of alpha inhibitor molecule imports the software for calculation MODEL (referring to http://jing.cz3.nus.edu.sg/cgi-bin/model/model.cgi) of online drug molecule descriptor; Thereby calculate the molecule descriptor value of above-mentioned every kind of suppressant automatically; Obtain 49 * 3778 molecule descriptor values altogether, this online drug molecule descriptor computation software discloses the computing method (referring to http://jing.cz3.nus.edu.sg/model/) of described various molecule descriptor values.Wherein, Described electronics descriptor comprises that dipole moment, electric density connect index, topological electric charge index; Described ingredient descriptor comprises number of rings, atomicity, hydrogen bond number, atomic weight, hydrogen bond donor, the hydrogen bond receptor of drug molecule; Described topological index descriptor comprises that Schultz Topological Index, Gutman Topological Index, Balaban molecule connection index, Wiener chemical bond index, CHI molecule connect index, kappa shape index, Hosoya Molecular Graphs index, Zagreb Molecular Graphs index, Moreau-Broto topology auto-correlation descriptor, Moran topology auto-correlation descriptor; Described physicochemical property descriptor comprises profit partition factor, polarizability; Described geometrical molecular descriptor comprises principal moments of inertia, drug molecule volume, drug molecule surface area, and described quantum chemistry descriptor comprises high occupied orbital, lowest unoccupied molecular orbital, gross energy.
3, simplify the inhibitor molecules descriptor set: a) deletion and cytosolic phospholipase A
2The inhibitor molecules descriptor that alpha inhibitor molecular structure correlativity is little, b) deleting descriptor value again is 0 inhibitor molecules descriptor, the descriptor that deletion all equates for the pairing molecule descriptor value of all suppressant; After the deletion through a, b two steps, also surplus 1430 the drug molecule descriptors of each sample; C) use stepwise regression method that remaining molecule descriptor is screened; Each sample is finally represented by the descriptor vector that contains 5 drug molecule descriptors; The purpose of simplifying the inhibitor molecules descriptor set be deletion do not have researching value the inhibitor molecules descriptor to reduce redundance, improve the accuracy rate and the stability of prediction.
4, the scale again of inhibitor molecules descriptor set: the inhibitor molecules descriptor set after will simplifying is mapped to [1; + 1] interval, the mapping formula is:
Wherein,
xBe the original value of inhibitor molecules descriptor,
x Pre Be again the value after the scale,
x Max With
x MinThe maximal value and the minimum value of the corresponding inhibitor molecules descriptor of difference,
y Max With
y MinInterval maximal value of difference correspondence mappings and minimum value are promptly+1 with-1.
5, will pass through after step 2 is handled to 4 sample set at random be divided into training set and test set; Utilize training set data; Adopt 10 to roll over cross validation method at random; The supporting vector machine model parameter is optimized, and described parameter comprises ε, the kernel function parameter γ of capacity factor measure C, ε insensitive loss function, and concrete optimizing process is following:
5.1, with 49 kinds of cytosolic phospholipase A in the sample set
2The alpha inhibitor molecule at random be divided into training set and test set, wherein training set comprises 39 samples, test set comprises 10 samples.
5.2, capacity factor measure C be set be fixed as 100; The maximal value of the ε value variation range of ε insensitive loss function is 1, and minimum value is-1, and change step is 0.01; The maximal value of the value variation range of kernel function parameter γ is 1, and minimum value-1, change step are 0.01; Kernel function K selects the radially basic kernel function of Gauss for use.
5.3, with training set at random be divided into 10 groups; Utilize 9 groups of relational models that are used for setting up inhibitor molecules structure and inhibition concentration wherein; Remaining one group is used for verifying this model; And successively each group is carried out one-time authentication, with the mean value of resultant 10 results' in checking back accuracy rate as estimation accurately.
5.4 the value of the ε value of pairing capacity factor measure C, ε insensitive loss function, kernel function parameter γ was an optimal value when accuracy rate was the highest, optimized the C, ε, the γ value that obtain and was respectively 100,0.25,0.03;
6, adopt the described training set of step 5 and optimize supported vector machine model parameter (C, ε, γ), set up the relational model of inhibitor molecules structure and inhibition concentration.
7, the relational model of step 5 described test set data substitution step 6 being set up obtains the predicted value of the inhibition concentration of corresponding inhibitor molecules.Model to being set up is estimated, and calculating training set and test set correlation coefficient r is 0.9170,0.9667, cross validation coefficient Q
2Be 0.9901,0.9943, root-mean-square error RMSE is 0.0085.
Claims (6)
1. one kind based on SVM prediction cytosolic phospholipase A
2The method of the inhibition concentration of alpha inhibitor is characterized in that, comprises the steps:
1) foundation of sample set: collect cytosolic phospholipase A
2The molecular structure of alpha inhibitor;
2) structure of inhibitor molecules descriptor set: input cytosolic phospholipase A
2The molecular structure of alpha inhibitor calculates the molecule descriptor value corresponding with it, and this molecule descriptor contains several components;
3) simplify the inhibitor molecules descriptor set;
4) scale again of inhibitor molecules descriptor set: the inhibitor molecules descriptor set after will simplifying is mapped to [1; + 1] interval, the mapping formula is:
Wherein,
xBe the original value of inhibitor molecules descriptor,
x Pre Be again the value after the scale,
x Max With
x MinThe maximal value and the minimum value of the corresponding inhibitor molecules descriptor of difference,
y Max With
y MinInterval maximal value of difference correspondence mappings and minimum value are promptly+1 with-1;
5) will pass through step 2) to 4) sample set after handling at random be divided into training set and test set, utilize training set data, adopt 10 to roll over cross validation method at random, the supporting vector machine model parameter is optimized;
6) with the described training set of step 5) with optimize after the SVMs parameter that obtains set up the relational model of inhibitor molecules structure and inhibition concentration;
7) with the described test set data of step 5) input step 6) relational model set up, the inhibition concentration of prediction suppressant.
2. according to claim 1 based on SVM prediction cytosolic phospholipase A
2The method of the inhibition concentration of alpha inhibitor is characterized in that: step 2) conformation of the molecular structure of said suppressant is in the minimum energy state.
3. according to claim 1 based on SVM prediction cytosolic phospholipase A
2The method of the inhibition concentration of alpha inhibitor is characterized in that: step 2) in the calculating of molecule descriptor be to adopt online drug molecule descriptor computation software MODEL to accomplish.
4. according to claim 1 based on SVM prediction cytosolic phospholipase A
2The method of the inhibition concentration of alpha inhibitor is characterized in that, the described simplification process of step 3) is:
(a) deletion and the little inhibitor molecules descriptor of inhibitor molecules structural dependence;
(b) deleting descriptor value again is 0 inhibitor molecules descriptor, the descriptor that deletion all equates for the pairing molecule descriptor value of all suppressant;
(c) use stepwise regression method that remaining inhibitor molecules descriptor is screened again.
5. according to claim 1 based on SVM prediction cytosolic phospholipase A
2The method of the inhibition concentration of alpha inhibitor is characterized in that: in step 5), sample set is that the ratio random division in 4:1 is training set and test set.
6. according to claim 1 based on SVM prediction cytosolic phospholipase A
2The method of the inhibition concentration of alpha inhibitor is characterized in that, the supporting vector machine model parameter optimisation procedure described in the step 5) is:
Capacity factor measure C is set is fixed as 100; The maximal value of the ε value variation range of ε insensitive loss function is 1, and minimum value is-1, and change step is 0.01; The maximal value of the value variation range of kernel function parameter γ is 1, and minimum value-1, change step are 0.01; Kernel function K selects the radially basic kernel function of Gauss for use;
With training set at random be divided into 10 groups; 9 groups of relational models that are used for setting up inhibitor molecules structure and inhibition concentration wherein; Remaining one group is used for verifying this model; Successively each group is carried out one-time authentication, with the mean value of resultant 10 results' in checking back accuracy rate as estimation accurately;
The value of the ε value of pairing capacity factor measure C, ε insensitive loss function, kernel function parameter γ was the optimal value of supporting vector machine model parameter when accuracy rate was the highest.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201110325636.XA CN102708269B (en) | 2011-10-24 | 2011-10-24 | Based on SVM prediction cytosolic phospholipase A2The method of the inhibition concentration of alpha inhibitor |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201110325636.XA CN102708269B (en) | 2011-10-24 | 2011-10-24 | Based on SVM prediction cytosolic phospholipase A2The method of the inhibition concentration of alpha inhibitor |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN102708269A true CN102708269A (en) | 2012-10-03 |
| CN102708269B CN102708269B (en) | 2016-05-25 |
Family
ID=46901032
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201110325636.XA Expired - Fee Related CN102708269B (en) | 2011-10-24 | 2011-10-24 | Based on SVM prediction cytosolic phospholipase A2The method of the inhibition concentration of alpha inhibitor |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN102708269B (en) |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103258244A (en) * | 2013-04-28 | 2013-08-21 | 西北师范大学 | Method for predicting inhibiting concentration of pyridazine HCV NS5B polymerase inhibitor based on particle swarm optimization support vector machine |
| CN104866710A (en) * | 2015-05-08 | 2015-08-26 | 西北师范大学 | Method for predicting inhibition concentration of cytochrome P450 enzyme CYP1A2 inhibitor by utilizing simplified partial least squares |
| CN109524064A (en) * | 2018-11-12 | 2019-03-26 | 云南省烟草农业科学研究院 | A kind of virtual screening method of polyphenol oxidase enzyme inhibitor |
| CN109927675A (en) * | 2019-04-09 | 2019-06-25 | 深圳创维汽车智能有限公司 | A kind of rain brush control method, device, equipment and storage medium |
| CN114783506A (en) * | 2022-03-17 | 2022-07-22 | 大连理工大学 | Method for predicting half-inhibitory concentration of inhibitor on coronavirus main protease |
| WO2022166129A1 (en) * | 2021-02-08 | 2022-08-11 | 江西煌上煌集团食品股份有限公司 | Screening method for heterologous competitive antigen for use in improvement of immunodetection sensitivity |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101339180A (en) * | 2008-08-14 | 2009-01-07 | 南京工业大学 | Organic compound combustion and explosion characteristic prediction method based on support vector machine |
| CN101630346A (en) * | 2009-06-26 | 2010-01-20 | 上海大学 | Method based on support vector machine for on-line prediction of interaction of protein and nucleic acid |
-
2011
- 2011-10-24 CN CN201110325636.XA patent/CN102708269B/en not_active Expired - Fee Related
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101339180A (en) * | 2008-08-14 | 2009-01-07 | 南京工业大学 | Organic compound combustion and explosion characteristic prediction method based on support vector machine |
| CN101630346A (en) * | 2009-06-26 | 2010-01-20 | 上海大学 | Method based on support vector machine for on-line prediction of interaction of protein and nucleic acid |
Non-Patent Citations (1)
| Title |
|---|
| 陈俏等: "支持向量机应用于大气污染物浓度预测", 《计算机技术与发展》 * |
Cited By (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103258244A (en) * | 2013-04-28 | 2013-08-21 | 西北师范大学 | Method for predicting inhibiting concentration of pyridazine HCV NS5B polymerase inhibitor based on particle swarm optimization support vector machine |
| CN104866710A (en) * | 2015-05-08 | 2015-08-26 | 西北师范大学 | Method for predicting inhibition concentration of cytochrome P450 enzyme CYP1A2 inhibitor by utilizing simplified partial least squares |
| CN104866710B (en) * | 2015-05-08 | 2017-11-10 | 西北师范大学 | The method for predicting Cytochrome P450 1A2 inhibitor inhibition concentrations |
| CN109524064A (en) * | 2018-11-12 | 2019-03-26 | 云南省烟草农业科学研究院 | A kind of virtual screening method of polyphenol oxidase enzyme inhibitor |
| CN109524064B (en) * | 2018-11-12 | 2020-10-20 | 云南省烟草农业科学研究院 | Virtual screening method of polyphenol oxidase inhibitor |
| CN109927675A (en) * | 2019-04-09 | 2019-06-25 | 深圳创维汽车智能有限公司 | A kind of rain brush control method, device, equipment and storage medium |
| CN109927675B (en) * | 2019-04-09 | 2022-02-08 | 深圳创维汽车智能有限公司 | Windshield wiper control method, device, equipment and storage medium |
| WO2022166129A1 (en) * | 2021-02-08 | 2022-08-11 | 江西煌上煌集团食品股份有限公司 | Screening method for heterologous competitive antigen for use in improvement of immunodetection sensitivity |
| CN114783506A (en) * | 2022-03-17 | 2022-07-22 | 大连理工大学 | Method for predicting half-inhibitory concentration of inhibitor on coronavirus main protease |
Also Published As
| Publication number | Publication date |
|---|---|
| CN102708269B (en) | 2016-05-25 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Jiang et al. | Dl-traff: Survey and benchmark of deep learning models for urban traffic prediction | |
| CN102708269A (en) | Method for predicting inhibiting concentration of inhibitor of cytosolic phospholipase A2alpha based on support vector machine | |
| Torabi et al. | A hybrid machine learning approach for daily prediction of solar radiation | |
| CN108090652A (en) | The method for building the electricity transaction index system based on big data technology | |
| Northrop et al. | Efficient simulation and reformulation of lithium-ion battery models for enabling electric transportation | |
| Tang et al. | Parallelization strategies for rapid and robust evolutionary multiobjective optimization in water resources applications | |
| Qin et al. | Machine learning K-means clustering algorithm for interpolative separable density fitting to accelerate hybrid functional calculations with numerical atomic orbitals | |
| Jardak et al. | Parallel processing of data from very large-scale wireless sensor networks | |
| Zhang et al. | Study on spiral source models revealing groundwater transfusion effects on pile foundation ground heat exchangers | |
| Molaeimanesh et al. | Agglomerate modeling of cathode catalyst layer of a PEM fuel cell by the lattice Boltzmann method | |
| Kiss et al. | Efficient handling of Gaussian charge distributions: An application to polarizable molecular models | |
| CN102542131A (en) | Method for predicting medicament pharmacokinetic properties and toxicity on basis of genetic algorithm and artificial neural network | |
| CN104112167B (en) | Can power generating wind resource distribution acquisition methods | |
| Psaltis et al. | Comparing charge transport predictions for a ternary electrolyte using the Maxwell–Stefan and Nernst–Planck equations | |
| Zhang et al. | Improved particle swarm optimization-extreme learning machine modeling strategies for the accurate lithium-ion battery state of health estimation and high-adaptability remaining useful life prediction | |
| CN104199870A (en) | Method for building LS-SVM prediction model based on chaotic search | |
| CN107807961A (en) | A kind of power distribution network big data multidomain treat-ment method based on Spark computing engines | |
| Feng et al. | Molecular design and performance improvement in organic solar cells guided by high‐throughput screening and machine learning | |
| Szarek et al. | Most probable distance between the nucleus and HOMO electron: the latent meaning of atomic radius from the product of chemical hardness and polarizability | |
| CN109447512B (en) | Large power grid reliability assessment method based on uniform design | |
| CN101839946A (en) | Resistor-capacitor decoupling soft sensing method based on magnitude-phase characteristics | |
| CN104751253B (en) | Distribution power flow Forecasting Methodology based on B- spline Basis bottom developed curve cluster | |
| Li et al. | Research on the method of traffic organization and optimization based on dynamic traffic flow model | |
| Liang et al. | HSMA: An O (N) electrostatics package implemented in LAMMPS | |
| CN116316617B (en) | Multi-station intelligent fusion new energy generation power region prediction method and system |
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: 20160525 Termination date: 20161024 |