CN109360597A - A kind of group's Advances in protein structure prediction based on global and local policy cooperation - Google Patents
A kind of group's Advances in protein structure prediction based on global and local policy cooperation Download PDFInfo
- Publication number
- CN109360597A CN109360597A CN201810862181.7A CN201810862181A CN109360597A CN 109360597 A CN109360597 A CN 109360597A CN 201810862181 A CN201810862181 A CN 201810862181A CN 109360597 A CN109360597 A CN 109360597A
- Authority
- CN
- China
- Prior art keywords
- conformation
- segment
- population
- variation
- global
- 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
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
Under differential evolution algorithm frame, for each conformation, global Mutation Strategy is first carried out in a kind of group's Advances in protein structure prediction based on global and local policy cooperation, carries out and detects to the overall situation of conformational space, to obtain potential region；Then local Mutation Strategy is executed, local search is carried out to the region that detection obtains, to obtain preferably conformation.In global detection process, segment exchange is carried out by randomly selected conformation while generating the multiple conformations of test, and selects the test conformation of minimum energy；In local search procedure, selection conformation guidance variation preferably than target conformation generates multiple test conformations, and selects the lower conformation of energy.Reach the relationship between balance diversity and convergence rate by the writing of global policies and local policy.The present invention provides a kind of precision of prediction and the higher group's Advances in protein structure prediction based on global and local policy cooperation of search efficiency.
Description
Technical field
The present invention relates to a kind of biological information, intelligent optimization, computer application field more particularly to a kind of bases
In group's Advances in protein structure prediction of global and local policy cooperation.
Background technique
Nineteen sixty-five, Nirenberg and Khorana etc. have found triplet genetic code (i.e. the first genetic code), and DNA is with three
A nucleotide is that one group of codon translates to protein amino acid sequence (i.e. prlmary structure of protein)；And protein is only rolled over
Its specific biological function could be generated by building up specific three-dimensional structure (i.e. tertiary protein structure).Relative to the first heredity
Password, the corresponding relationship (i.e. the second genetic code or code of folding) between protein sequence primary structure and its tertiary structure
It is still unsolved mystery.In order to solve protein folding this " asking for century ", more and more there is grinding for different discipline backgrounds
The person of studying carefully participates, and especially for terminal-protein structure prediction of protein folding procedure, it is extensive to receive scientific circles
Concern and research.For opposing proteins fold, protein structure prediction has stronger practicability, only acquisition protein
Three-dimensional structure, could really realize gene diagnosis, and be finally reached gene therapy purpose.
Currently, the experimental method of measurement protein three-dimensional structure includes X-ray crystal diffraction, multi-dimensional nmr (NMR)
With electron cryo-microscopy etc..X-ray crystal diffraction is current measurement protein structure most efficient method, and precision achieved is other
What method cannot compare, major defect is that protein crystal is difficult to cultivate and the period of crystal structure determination is longer；NMR method
The conformation of protein in the solution can directly be measured, but it is big to the requirement of sample, purity requirement is high, can only measure at present
Small protein.Secondly, these experimental determining methods are expensive, the three-dimensional structure for measuring a protein needs hundreds of thousands
Dollar, however, the primary amino acid sequences of one protein of measurement only need 1000 dollars or so, so as to cause protein sequence and
Wide gap between three-dimensional structure measurement is increasing.Therefore, such as how computer is tool, with algorithm appropriate, from amino
Acid sequence, which sets out, directly predicts the three-dimensional structure of protein, becomes a kind of important research topic in current biological informatics.
Conformational space optimization (or sampling) method be it is current restrict protein structure ab initio prediction precision most critical because
One of element.Differential evolution algorithm (Differential Evolution, DE) is as algorithm most powerful in evolution algorithm
A kind of randomness algorithm that Price and Storn is proposed in nineteen ninety-five.DE algorithm is since structure is simple, fast convergence rate, robustness
The advantages that strong, has in protein conformation space optimization field and is widely applied.Sudha etc. proposes a kind of based on local policy
Differential evolution Advances in protein structure prediction；Custodio etc. proposes a kind of group albumen of the local based on similarity agent model
Matter structure prediction prediction technique；Shehu research group is based on DE algorithm, proposes a series of effective protein conformation space optimizations
Method, such as multiple dimensioned HYBRID EVOLUTIONARY ALGORITHMS HEA and multiple target conformational space optimization method MOEA.The experimental results showed that above-mentioned
Algorithm can effectively be predicted to obtain some small-scale protein structures.However, with the increase of albumen scale, stable conformation
Space also rises with it, and since DE algorithm overall situation detectivity is stronger, and local search ability is weaker, so as to cause later period search
Efficiency is lower；Secondly, Energy Surface is extremely complex, includes thousands of a local search areas, algorithm is caused to be easily trapped into part most
It is excellent, to influence precision of prediction.
Therefore, there is defects in terms of precision of prediction and search efficiency for existing Advances in protein structure prediction, need
It improves.
Summary of the invention
In order to overcome precision of prediction and the lower deficiency of search efficiency, the present invention of existing Advances in protein structure prediction to mention
A kind of precision of prediction and the higher protein structure prediction side of group based on global and local policy cooperation of search efficiency out
Method.
The technical solution adopted by the present invention to solve the technical problems is:
A kind of group's Advances in protein structure prediction based on global and local policy cooperation, the method includes following steps
It is rapid:
1) sequence information of testing protein is inputted, and from ROBETTA server (http://www.robetta.org/)
On obtain fragment library；
2) parameter setting: population scale NP, crossover probability CR, fragment length l, temperature factor KT, greatest iteration time are set
Number Gmax, and initialize the number of iterations g=0；
3) segment assembling is randomly choosed to the corresponding fragment library in each residue position generates initial configurations population P={ C1,
C2,...,CNP, wherein Ci, i={ 1,2 ..., NP } is i-th of conformation individual in population P；
4) to each conformation C in populationi, i ∈ { 1,2 ..., NP } executes global policies, and process is as follows:
4.1) by conformation CiRegard target conformation as, from current population randomly choose four it is different and with target conformation
Different conformation Ca、Cb、CcAnd Cd；
4.2) respectively from conformation CaAnd CbThe different segment in one residue position of middle random selection replaces conformation CcMiddle corresponding position
Segment, generate first variation conformation
4.3) respectively from Ca、CbAnd CcThe different segment in one residue position of middle random selection replaces target conformation CiMiddle correspondence
The segment of position generates second variation conformation
4.4) respectively from Ca、CbAnd CcThe different segment in one residue position of middle random selection replaces target conformation CdMiddle correspondence
The segment of position generates third variation conformation
4.5) random to generate a decimal R between 0 and 1, if R < CR, from conformation CiIn randomly select a length
Variation conformation is replaced respectively for the segment of lWithThe segment of middle corresponding position, and carry out once with Bigpian
Section assembling, to generate test conformationWithOtherwise variation conformation is directly subjected to a random fragment assembling
Generate test conformationWith
4.6) test conformation calculated separately according to Rosetta score3 energy functionAnd CiEnergy
Magnitude, and willWithThe minimum conformation of middle energy value regards optimal test conformation C astrial；
If 4.7) CtrialEnergy value be less than CiEnergy value, then CtrialReplace Ci, otherwise according to Boltzmann probabilityUse CtrialReplace Ci, wherein Δ E is CtrialEnergy value and CiEnergy value miss absolute value of the difference；
5) each conformation C in the new population obtained to step 4)i, i ∈ { 1,2 ..., NP } execution local policy, process
It is as follows:
5.1) it finds out energy value in population and is lower than conformation CiAll conformationsIf these conformations
Quantity M > 1 then continues step 5.2), otherwise goes to step 5.6)；
5.2) fromOne conformation of middle random selectionAnd three are randomly choosed from entire population
It is mutually different, and withAnd CiAlso different conformation Ce、CfAnd Cg；
5.3) respectively from conformation CeAnd CfThe different segment in one residue position of middle random selection replaces conformationMiddle correspondence position
The segment set generates variation conformation
5.4) respectively from conformation CeWithThe different segment in one residue position of middle random selection replaces conformation CiMiddle correspondence position
The segment set generates variation conformation
5.5) respectively from conformation Ce、CfAnd CgThe different segment in one residue position of middle random selection replaces conformationIn it is right
The segment of position is answered, variation conformation is generated
5.6) according to step 4.1)~4.4) generate variation conformationWith
5.7) willWithRegard as respectivelyWithAccording to step 4.5)~4.7)
Population Regeneration；
6) g=g+1, if g > Gmax, then the final pre- geodesic structure of conformation conduct of minimum energy is exported, otherwise return step
4)。
Technical concept of the invention are as follows: under differential evolution algorithm frame, for each conformation, global variation is first carried out
Strategy is carried out and is detected to the overall situation of conformational space, to obtain potential region；Then local Mutation Strategy is executed, to spy
The region measured carries out local search, to obtain preferably conformation.In global detection process, pass through randomly selected structure
As carrying out segment exchange while generating the multiple conformations of test, and select the test conformation of minimum energy；In local search procedure,
Selection conformation preferably than target conformation carries out segment with randomly selected conformation and exchanges the multiple test conformations of generation, and selects energy
Measure lower conformation.Reach the relationship between balance diversity and convergence rate by the writing of global policies and local policy.
The present invention provides a kind of precision of prediction and the higher group's protein knot based on global and local policy cooperation of search efficiency
Structure prediction technique.
Beneficial effects of the present invention are shown: being instructed to make a variation by global policies, kept population diversity；Pass through local plan
Slightly guidance variation, accelerates convergence rate；Therefore, global policies and local policy cooperation, not only can be improved search efficiency, but also can be with
Improve precision of prediction.
Detailed description of the invention
Fig. 1 is that group's Advances in protein structure prediction based on global and local policy cooperation ties protein 1I6C
Conformation when structure is predicted updates schematic diagram.
Fig. 2 is that group's Advances in protein structure prediction based on global and local policy cooperation ties protein 1I6C
The conformation distribution map that structure obtains when predicting.
Fig. 3 is that group's Advances in protein structure prediction based on global and local policy cooperation ties protein 1I6C
The tomograph that structure is predicted.
Specific embodiment
The invention will be further described below in conjunction with the accompanying drawings.
Referring to Fig.1~Fig. 3, a kind of group's Advances in protein structure prediction based on global and local policy cooperation, including
Following steps:
1) sequence information of testing protein is inputted, and from ROBETTA server (http://www.robetta.org/)
On obtain fragment library；
2) parameter setting: population scale NP, crossover probability CR, fragment length l, temperature factor KT, greatest iteration time are set
Number Gmax, and initialize the number of iterations g=0；
3) segment assembling is randomly choosed to the corresponding fragment library in each residue position generates initial configurations population P={ C1,
C2,...,CNP, wherein Ci, i={ 1,2 ..., NP } is i-th of conformation individual in population P；
4) to each conformation C in populationi, i ∈ { 1,2 ..., NP } executes global policies, and process is as follows:
4.1) by conformation CiRegard target conformation as, from current population randomly choose four it is different and with target conformation
Different conformation Ca、Cb、CcAnd Cd；
4.2) respectively from conformation CaAnd CbThe different segment in one residue position of middle random selection replaces conformation CcMiddle corresponding position
Segment, generate first variation conformation
4.3) respectively from Ca、CbAnd CcThe different segment in one residue position of middle random selection replaces target conformation CiMiddle correspondence
The segment of position generates second variation conformation
4.4) respectively from Ca、CbAnd CcThe different segment in one residue position of middle random selection replaces target conformation CdMiddle correspondence
The segment of position generates third variation conformation
4.5) random to generate a decimal R between 0 and 1, if R < CR, from conformation CiIn randomly select a length
Variation conformation is replaced respectively for the segment of lWithThe segment of middle corresponding position, and carry out once with Bigpian
Section assembling, to generate test conformationWithOtherwise variation conformation is directly subjected to a random fragment assembling
Generate test conformationWith
4.6) test conformation is calculated separately according to Rosetta score3 energy functionAnd CiEnergy
Magnitude, and willWithThe minimum conformation of middle energy value regards optimal test conformation C astrial；
If 4.7) CtrialEnergy value be less than CiEnergy value, then CtrialReplace Ci, otherwise according to Boltzmann probabilityUse CtrialReplace Ci, wherein Δ E is CtrialEnergy value and CiEnergy value miss absolute value of the difference；
5) each conformation C in the new population obtained to step 4)i, i ∈ { 1,2 ..., NP } execution local policy, process
It is as follows:
5.1) it finds out energy value in population and is lower than conformation CiAll conformationsIf these conformations
Quantity M > 1 then continues step 5.2), otherwise goes to step 5.6)；
5.2) fromOne conformation of middle random selectionAnd three are randomly choosed from entire population
It is mutually different, and withAnd CiAlso different conformation Ce、CfAnd Cg；
5.3) respectively from conformation CeAnd CfThe different segment in one residue position of middle random selection replaces conformationMiddle correspondence position
The segment set generates variation conformation
5.4) respectively from conformation CeWithThe different segment in one residue position of middle random selection replaces conformation CiMiddle correspondence position
The segment set generates variation conformation
5.5) respectively from conformation Ce、CfAnd CgThe different segment in one residue position of middle random selection replaces conformationIn it is right
The segment of position is answered, variation conformation is generated
5.6) according to step 4.1)~4.4) generate variation conformationWith
5.7) willWithRegard as respectivelyWithAccording to step 4.5)~4.7)
Population Regeneration；
6) g=g+1, if g > Gmax, then the final pre- geodesic structure of conformation conduct of minimum energy is exported, otherwise return step
4)。
The β-pleated sheet protein 1I6C that the present embodiment sequence length is 39 is embodiment, and one kind being based on global and local strategy
Group's Advances in protein structure prediction of cooperation, wherein comprising the steps of:
1) sequence information of testing protein is inputted, and from ROBETTA server (http://www.robetta.org/)
On obtain fragment library；
2) parameter setting: setting population scale NP=100, crossover probability CR=0.5, fragment length l=9, temperature factor
KT=2, maximum number of iterations Gmax=1000, and initialize the number of iterations g=0；
3) segment assembling is randomly choosed to the corresponding fragment library in each residue position generates initial configurations population P={ C1,
C2,...,CNP, wherein Ci, i={ 1,2 ..., NP } is i-th of conformation individual in population P；
4) to each conformation C in populationi, i ∈ { 1,2 ..., NP } executes global policies, and process is as follows:
4.1) by conformation CiRegard target conformation as, from current population randomly choose four it is different and with target conformation
Different conformation Ca、Cb、CcAnd Cd；
4.2) respectively from conformation CaAnd CbThe different segment in one residue position of middle random selection replaces conformation CcMiddle corresponding position
Segment, generate first variation conformation
4.3) respectively from Ca、CbAnd CcThe different segment in one residue position of middle random selection replaces target conformation CiMiddle correspondence
The segment of position generates second variation conformation
4.4) respectively from Ca、CbAnd CcThe different segment in one residue position of middle random selection replaces target conformation CdMiddle correspondence
The segment of position generates third variation conformation
4.5) random to generate a decimal R between 0 and 1, if R < CR, from conformation CiIn randomly select a length
Variation conformation is replaced respectively for the segment of lWithThe segment of middle corresponding position, and carry out once with Bigpian
Section assembling, to generate test conformationWithOtherwise variation conformation is directly subjected to a random fragment assembling
Generate test conformationWith
4.6) test conformation is calculated separately according to Rosetta score3 energy functionAnd CiEnergy
Magnitude, and willWithThe minimum conformation of middle energy value regards optimal test conformation C astrial；
If 4.7) CtrialEnergy value be less than CiEnergy value, then CtrialReplace Ci, otherwise according to Boltzmann probabilityUse CtrialReplace Ci, wherein Δ E is CtrialEnergy value and CiEnergy value miss absolute value of the difference；
5) each conformation C in the new population obtained to step 4)i, i ∈ { 1,2 ..., NP } execution local policy, process
It is as follows:
5.1) it finds out energy value in population and is lower than conformation CiAll conformationsIf these conformations
Quantity M > 1 then continues step 5.2), otherwise goes to step 5.6)；
5.2) fromOne conformation of middle random selectionAnd three are randomly choosed from entire population
It is mutually different, and withAnd CiAlso different conformation Ce、CfAnd Cg；
5.3) respectively from conformation CeAnd CfThe different segment in one residue position of middle random selection replaces conformationMiddle correspondence position
The segment set generates variation conformation
5.4) respectively from conformation CeWithThe different segment in one residue position of middle random selection replaces conformation CiMiddle correspondence position
The segment set generates variation conformation
5.5) respectively from conformation Ce、CfAnd CgThe different segment in one residue position of middle random selection replaces conformationIn it is right
The segment of position is answered, variation conformation is generated
5.6) according to step 4.1)~4.4) generate variation conformationWith
5.7) willWithRegard as respectivelyWithAccording to step 4.5)~4.7)
Population Regeneration；
6) g=g+1, if g > Gmax, then the final pre- geodesic structure of conformation conduct of minimum energy is exported, otherwise return step
4)。
The β-pleated sheet protein 1I6C for being 39 using sequence length has obtained the protein with above method as embodiment
Nearly native state conformation, lowest mean square root deviation areAverage root-mean-square deviation isPre- geodesic structure is as shown in Figure 3.
Described above is that the present invention is obtained as example using protein 1I6C as a result, and non-limiting implementation model of the invention
It encloses, various changes and improvements is done to it under the premise of without departing from range involved by basic content of the present invention, should not exclude at this
Except the protection scope of invention.
Claims (1)
1. a kind of group's Advances in protein structure prediction based on global and local policy cooperation, it is characterised in that: the method
The following steps are included:
1) sequence information of testing protein is inputted, and obtains fragment library from ROBETTA server；
2) parameter setting: population scale NP, crossover probability CR, fragment length l, temperature factor KT, maximum number of iterations are set
Gmax, and initialize the number of iterations g=0；
3) segment assembling is randomly choosed to the corresponding fragment library in each residue position generates initial configurations population P={ C1,C2,...,
CNP, wherein Ci, i={ 1,2 ..., NP } is i-th of conformation individual in population P；
4) to each conformation C in populationi, i ∈ { 1,2 ..., NP } executes global policies, and process is as follows:
4.1) by conformation CiRegard target conformation as, random selection four is different and different from target conformation from current population
Conformation Ca、Cb、CcAnd Cd；
4.2) respectively from conformation CaAnd CbThe different segment in one residue position of middle random selection replaces conformation CcThe piece of middle corresponding position
Section, generates first variation conformation
4.3) respectively from Ca、CbAnd CcThe different segment in one residue position of middle random selection replaces target conformation CiMiddle corresponding position
Segment generates second variation conformation
4.4) respectively from Ca、CbAnd CcThe different segment in one residue position of middle random selection replaces target conformation CdMiddle corresponding position
Segment generates third variation conformation
4.5) random to generate a decimal R between 0 and 1, if R < CR, from conformation CiIn to randomly select length be l
Segment replaces variation conformation respectivelyWithThe segment of middle corresponding position, and carry out a random fragment group
Dress, to generate test conformationWithOtherwise variation conformation is directly carried out a random fragment assembling to generate
Test conformationWith
4.6) test conformation is calculated separately according to Rosetta score3 energy functionAnd CiEnergy value,
And it willWithThe minimum conformation of middle energy value regards optimal test conformation C astrial；
If 4.7) CtrialEnergy value be less than CiEnergy value, then CtrialReplace Ci, otherwise according to Boltzmann probabilityUse CtrialReplace Ci, wherein Δ E is CtrialEnergy value and CiEnergy value miss absolute value of the difference；
5) each conformation C in the new population obtained to step 4)i, i ∈ { 1,2 ..., NP } executes local policy, and process is as follows:
5.1) it finds out energy value in population and is lower than conformation CiAll conformationsIf the quantity of these conformations
M > 1 then continues step 5.2), otherwise goes to step 5.6)；
5.2) fromOne conformation of middle random selectionAnd from entire population randomly choose three mutually not
It is identical, and withAnd CiAlso different conformation Ce、CfAnd Cg；
5.3) respectively from conformation CeAnd CfThe different segment in one residue position of middle random selection replaces conformationMiddle corresponding position
Segment generates variation conformation
5.4) respectively from conformation CeWithThe different segment in one residue position of middle random selection replaces conformation CiMiddle corresponding position
Segment generates variation conformation
5.5) respectively from conformation Ce、CfAnd CgThe different segment in one residue position of middle random selection replaces conformationMiddle corresponding position
Segment, generate variation conformation
5.6) according to step 4.1)~4.4) generate variation conformationWith
5.7) willWithRegard as respectivelyWithAccording to step 4.5)~4.7) it updates
Population；
6) g=g+1, if g > Gmax, then the final pre- geodesic structure of conformation conduct of minimum energy is exported, otherwise return step 4).
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810862181.7A CN109360597B (en) | 2018-08-01 | 2018-08-01 | Group protein structure prediction method based on global and local strategy cooperation |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810862181.7A CN109360597B (en) | 2018-08-01 | 2018-08-01 | Group protein structure prediction method based on global and local strategy cooperation |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109360597A true CN109360597A (en) | 2019-02-19 |
| CN109360597B CN109360597B (en) | 2020-12-01 |
Family
ID=65349769
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810862181.7A Active CN109360597B (en) | 2018-08-01 | 2018-08-01 | Group protein structure prediction method based on global and local strategy cooperation |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109360597B (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110634531A (en) * | 2019-08-13 | 2019-12-31 | 浙江工业大学 | Protein structure prediction method based on double-layer bias search |
| JP2020140514A (en) * | 2019-02-28 | 2020-09-03 | 富士通株式会社 | Identification method, identification program, and identification apparatus |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105808972A (en) * | 2016-03-11 | 2016-07-27 | 浙江工业大学 | Method for predicting protein structure from local to global on basis of knowledge spectrum |
| CN108334746A (en) * | 2018-01-15 | 2018-07-27 | 浙江工业大学 | A kind of Advances in protein structure prediction based on secondary structure similarity |
-
2018
- 2018-08-01 CN CN201810862181.7A patent/CN109360597B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105808972A (en) * | 2016-03-11 | 2016-07-27 | 浙江工业大学 | Method for predicting protein structure from local to global on basis of knowledge spectrum |
| CN108334746A (en) * | 2018-01-15 | 2018-07-27 | 浙江工业大学 | A kind of Advances in protein structure prediction based on secondary structure similarity |
Non-Patent Citations (2)
| Title |
|---|
| WANPENG029: ""蛋白质二级、三级结构预测"", 《HTTPS://BLOG.CSDN.NET/WEIXIN_43202635/ARTICLE/DETAILS/82907736》 * |
| XIAO-GENZHOU 等: ""A noveldifferentialevolutionalgorithmusinglocalabstractconvex underestimatestrategyforglobaloptimization"", 《COMPUTERS &OPERATIONSRESEARCH》 * |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2020140514A (en) * | 2019-02-28 | 2020-09-03 | 富士通株式会社 | Identification method, identification program, and identification apparatus |
| JP7287005B2 (en) | 2019-02-28 | 2023-06-06 | 富士通株式会社 | Specific method, specific program and specific device |
| CN110634531A (en) * | 2019-08-13 | 2019-12-31 | 浙江工业大学 | Protein structure prediction method based on double-layer bias search |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109360597B (en) | 2020-12-01 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106778059B (en) | A kind of group's Advances in protein structure prediction based on Rosetta local enhancement | |
| Chatterjee et al. | PPI_SVM: Prediction of protein-protein interactions using machine learning, domain-domain affinities and frequency tables | |
| CN106055920B (en) | It is a kind of based on the Advances in protein structure prediction that tactful copy exchanges more than stage | |
| CN106650305B (en) | A kind of more tactful group Advances in protein structure prediction based on local abstract convex supporting surface | |
| Samee et al. | Evaluating thermodynamic models of enhancer activity on cellular resolution gene expression data | |
| CN109360597A (en) | A kind of group's Advances in protein structure prediction based on global and local policy cooperation | |
| CN109524058A (en) | A kind of protein dimer Structure Prediction Methods based on differential evolution | |
| CN106096326B (en) | A kind of differential evolution Advances in protein structure prediction based on barycenter Mutation Strategy | |
| Ziemianowicz et al. | New opportunities in integrative structural modeling | |
| Gao et al. | Balanceali: multiple PPI network alignment with balanced high coverage and consistency | |
| Chen et al. | Domain-based predictive models for protein-protein interaction prediction | |
| CN109147867A (en) | A kind of group's Advances in protein structure prediction based on dynamic fragment length | |
| CN109411013A (en) | A kind of group's Advances in protein structure prediction based on the specific Mutation Strategy of individual | |
| CN108920894A (en) | A kind of protein conformation space optimization method based on the estimation of brief abstract convex | |
| Fan et al. | Predicting RNA solvent accessibility from multi-scale context feature via multi-shot neural network | |
| Ramana et al. | LipocalinPred: a SVM-based method for prediction of lipocalins | |
| Pliego-Pastrana et al. | Effective pair potentials between protein amino acids | |
| CN102609779B (en) | A kind of geographical national conditions aggregative index monitoring method | |
| CN109326318B (en) | Group protein structure prediction method based on Loop region Gaussian disturbance | |
| CN109243526B (en) | Protein structure prediction method based on specific fragment crossing | |
| CN113139334A (en) | Simulation optimization method based on bee colony | |
| CN109300503A (en) | A kind of group's Advances in protein structure prediction of global and local Lower Bound Estimation collaboration | |
| Gómez et al. | Prediction of protein function improving sequence remote alignment search by a fuzzy logic algorithm | |
| Cheng et al. | ReHiC: Enhancing Hi-C data resolution via residual convolutional network | |
| CN110223730A (en) | Protein and small molecule binding site prediction technique, prediction meanss |
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 |