CN109448784B - A protein structure prediction method based on dihedral angle information-assisted energy function selection - Google Patents
A protein structure prediction method based on dihedral angle information-assisted energy function selection Download PDFInfo
- Publication number
- CN109448784B CN109448784B CN201810994128.2A CN201810994128A CN109448784B CN 109448784 B CN109448784 B CN 109448784B CN 201810994128 A CN201810994128 A CN 201810994128A CN 109448784 B CN109448784 B CN 109448784B
- Authority
- CN
- China
- Prior art keywords
- conformation
- score
- energy
- protein
- dihedral angle
- 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.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 45
- 238000000455 protein structure prediction Methods 0.000 title claims abstract description 17
- 102000004169 proteins and genes Human genes 0.000 claims abstract description 49
- 108090000623 proteins and genes Proteins 0.000 claims abstract description 49
- 239000012634 fragment Substances 0.000 claims abstract description 31
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 11
- 230000008569 process Effects 0.000 claims description 17
- 238000011156 evaluation Methods 0.000 claims description 7
- 238000000367 ab initio method Methods 0.000 claims description 4
- 238000007781 pre-processing Methods 0.000 claims description 4
- 238000005070 sampling Methods 0.000 abstract description 6
- 230000006870 function Effects 0.000 description 36
- 229920001184 polypeptide Polymers 0.000 description 3
- 102000004196 processed proteins & peptides Human genes 0.000 description 3
- 108090000765 processed proteins & peptides Proteins 0.000 description 3
- 102000029797 Prion Human genes 0.000 description 2
- 108091000054 Prion Proteins 0.000 description 2
- 230000007547 defect Effects 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000002474 experimental method Methods 0.000 description 2
- 238000005481 NMR spectroscopy Methods 0.000 description 1
- 230000002776 aggregation Effects 0.000 description 1
- 238000004220 aggregation Methods 0.000 description 1
- 125000003275 alpha amino acid group Chemical group 0.000 description 1
- 150000001413 amino acids Chemical class 0.000 description 1
- 238000013459 approach Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000008827 biological function Effects 0.000 description 1
- 230000033228 biological regulation Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 210000003169 central nervous system Anatomy 0.000 description 1
- 239000003795 chemical substances by application Substances 0.000 description 1
- 238000000205 computational method Methods 0.000 description 1
- 238000004883 computer application Methods 0.000 description 1
- 238000002884 conformational search Methods 0.000 description 1
- 230000007123 defense Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000000386 microscopy Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000000329 molecular dynamics simulation Methods 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 230000001717 pathogenic effect Effects 0.000 description 1
- 238000000547 structure data Methods 0.000 description 1
- 230000032258 transport Effects 0.000 description 1
- 238000002424 x-ray crystallography Methods 0.000 description 1
Images
Landscapes
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
一种基于二面角信息辅助能量函数选择的蛋白质结构预测方法，首先，根据蛋白质残基对应的拉氏图Ramachandran plot中提取二面角信息；其次，使用Rosetta算法中的能量函数以及二面角信息对构象进行评估；然后，分别给予两个分数以不同的权重，设计一个新的打分函数，使用这个打分函数对片段组装后的构象进行选择，从而减小能量函数不精确对蛋白质三维结构产生的影响；最后，对构象进行全局搜索以及局部搜索，在保证构象全局拓扑结构的基础上，对局部的结构进行增强，从而获得更多的近天然态的结构。本发明提供一种采样能力较好、预测精度较高的基于二面角信息辅助能量函数选择的蛋白质结构预测方法。
A protein structure prediction method based on dihedral angle information to assist energy function selection. First, the dihedral angle information is extracted from the Ramachandran plot corresponding to the protein residues; secondly, the energy function and dihedral angle in the Rosetta algorithm are used. The information is used to evaluate the conformation; then, two scores are given different weights, a new scoring function is designed, and the conformation after fragment assembly is selected using this scoring function, thereby reducing the energy function inaccuracy. Finally, a global search and a local search are performed on the conformation, and the local structure is enhanced on the basis of ensuring the global topological structure of the conformation, so as to obtain more near-native structures. The invention provides a protein structure prediction method based on dihedral angle information-assisted energy function selection with better sampling ability and higher prediction accuracy.
Description
Technical Field
The invention relates to the fields of biological informatics, molecular dynamics simulation, statistical learning and combination optimization and computer application, in particular to a protein structure prediction method based on dihedral angle information auxiliary energy function selection.
Background
Proteins are the most widely distributed and complex proteins in organisms and play a crucial role in various life-related processes, such as transport, regulation and defense processes.
The structure of proteins can be divided into three levels:
1) the primary structure of a protein refers to the sequence of amino acids in a polypeptide chain.
2) Secondary structure refers to highly regular local structures on the actual polypeptide backbone. There are two main types of secondary structures, alpha-helices and beta-strands.
3) Tertiary structure refers to the three-dimensional structure of monomeric and multimeric protein molecules. The alpha-helices and beta-pleated sheets are folded into a dense globular structure.
4) The fourth structure is a three-dimensional structure composed of an aggregation of two or more separate polypeptide chains (subunits) that operate as a single functional unit.
Proteins can only exert certain biological functions after folding into a specific structure, and therefore understanding the structure of a protein is very important for understanding that it is the central nervous system, the source of which is a specific type of misfolded protein known as a prion. Normally, prions are alpha-helical structures, but in certain cases, they distort to beta-strand structures, which are pathogenic agents. Experimental methods for obtaining the three-dimensional structure of proteins include X-ray crystallography, nuclear magnetic resonance spectroscopy, cryoelectron microscopy, and the like. Data in protein sequence databases (UniProt) and protein structure databases (PDB) have grown exponentially over the past few decades. However, obtaining protein sequence data is much easier than obtaining protein structure data. More importantly, the experimental approach is always time consuming, large and expensive. By 2 months 2018, less than 0.127% of the protein sequence has been experimentally determined to be three-dimensional. Therefore, computational methods for predicting structures from protein sequences are very important tasks. Furthermore, Anfinsen's experiments show that the native structure is determined only by the amino acid sequence of the protein. In other words, structural information of a protein is contained in its sequence, which indicates that a structure can be predicted from the sequence using a calculation method. Since similar protein sequences generally have similar three-dimensional structures, there are homology modeling methods that use known structures in PDB as templates, which are by far the most accurate methods for protein structure prediction. As databases grow, more and more proteins can acquire precise protein structures through homologous templates. Homology modeling can effectively predict protein structure, but its prediction accuracy depends on the sequence identity between the protein of interest and the structural template. Homology modeling methods can generally predict protein tertiary structure with greater accuracy when sequence identity is relatively high (greater than 30%), and fail when sequence identity is low. Unlike template-based structure prediction methods (e.g., homology modeling), de novo prediction methods do not rely on any known structure and search for the native structure of the target protein by conformational search methods. Among them, the fragment assembly technique is widely used, which uses a plurality of fragments of a protein structure to splice a target protein structure into a protein structure. In the process of de novo prediction, two main bottlenecks exist at present, one is deceptiveness of energy landscape, so that the obtained energy low conformation is not a natural conformation, and is specifically represented as inaccurate energy function, and a good conformation cannot be selected; another is the lack of ability of the prior art to sample conformational space, which is manifested by a lack of diversity in the conformations.
Therefore, the current protein structure prediction method has defects in prediction accuracy and sampling capability, and needs to be improved.
Disclosure of Invention
In order to overcome the defects of insufficient sampling capability and prediction accuracy of the conventional protein structure prediction method, the invention provides a protein structure prediction method based on dihedral angle information assisted energy function selection, which has better sampling capability and higher prediction accuracy. The method can effectively reduce the conformational sampling space and improve the problem of low accuracy of protein structure prediction caused by inaccuracy of an energy function.
The technical scheme adopted by the invention for solving the technical problems is as follows:
a protein structure prediction method based on dihedral angle information assisted energy function selection, the method comprising the steps of:
1) setting parameters: length of protein sequence L, number of initialization iterations IiThe number of global search iterations is IgThe number of local search iterations is Il；
2) Information preprocessing, first of all, given an initial protein sequence from which a stretch chain with the largest free energy is formed, in which the dihedral angle phi,
omega is respectively set to be-150 degrees, -150 degrees and 180 degrees, and a Ramachandran plot corresponding to different residue types of different secondary structures of the protein is obtained;
3) conformation initialization, using stage1 in the Rosetta ab initio method to initialize the initial conformation, and replacing residues at each residue position of the initial conformation at least more than one time or reaching the maximum initialization iteration number IiThe initialization is regarded as successful;
4) the constellations are scored through an intermediate Energy function of a Rosetta algorithm, and the Energy fraction of the constellations is Energyscore；
5) And calculating a conformational Rama score, and evaluating the dihedral angle of each residue position of the conformation through Ramachandran plot, wherein the evaluation formula is as follows:
wherein phi isa,
Is the two dihedral angles of residue a, res (a) is the residue type of residue a, ss (a) is the secondary structure type of residue aIn the method, the secondary structure type is obtained by a DSSP algorithm, and the estimation result of each residue position is summed to obtain the Rama fraction Rama of the conformationscore；
6) Designing a scoring function, and obtaining an Energy score Energy through step 4)scoreAnd the Rama fraction Rama obtained in step 5)scoreThe scoring function is designed as follows:
E(C)＝weEnergyscore+wrRamascore
wherein, weAnd wrRespectively corresponding weights of the energy fractions Rama fractions, C is a scored conformation, and the conformation is scored by the scoring function;
7) performing conformational global search, performing 9 fragment assembly on the conformation C to obtain conformation C ', then scoring the individuals before and after the fragment assembly by using the scoring function designed in the step 6) to obtain E (C) and E (C '), if E (C) is less than E (C '), receiving the individual C ', if E (C) is more than E (C '), according to Boltzmann probability
Receiving individuals, wherein, E (E) E (C') is the energy difference of two individuals after the fragments are assembled, kT is a temperature coefficient, and carrying out I on the received conformationgThe second search, the search process, as described above, reaches IgPerforming conformational local search after the secondary search;
8) performing conformation local search, performing 3-segment fragment assembly on the conformation C to obtain conformation C ', then scoring the individuals before and after the fragment assembly by using the scoring function designed in the step 6) to obtain E (C) and E (C '), if E (C) is less than E (C '), receiving the individual C ', if E (C) is more than E (C '), according to Boltzmann probability
Receiving individuals, wherein, E (E) E (C') is the energy difference of two individuals after the fragments are assembled, kT is a temperature coefficient, and carrying out I on the received conformationlThe second search, the search process, as described above, reaches IlCompleting the whole search process of the conformation after the secondary search;
9) the final conformation is saved and the output conformation information is recorded.
The technical conception of the invention is as follows: the invention provides a protein structure prediction method based on dihedral angle information auxiliary energy function selection under the framework of a group algorithm. Firstly, extracting dihedral angle information from a Ramachandran plot corresponding to protein residues; secondly, evaluating the conformation by using an energy function and dihedral angle information in a Rosetta algorithm; then, respectively giving different weights to the two scores, designing a new scoring function, and selecting the conformation after fragment assembly by using the scoring function, thereby reducing the influence of inaccuracy of an energy function on the three-dimensional structure of the protein; and finally, global search and local search are carried out on the conformation, and the local structure is enhanced on the basis of ensuring the conformation global topological structure, so that more structures close to the natural state are obtained.
The beneficial effects of the invention are as follows: on one hand, the energy function in Rosetta and dihedral angle information in a Ramachandran plot corresponding to protein residues are adopted to score the conformation, and a new scoring function is designed on the basis of the two indexes to score the conformation after fragment assembly so as to know and select, so that the accuracy of prediction is improved, and the influence caused by inaccurate energy function is reduced. On the other hand, in the search process of the conformation sampling space, on the basis of using the global search to form the whole topological structure of the conformation, the conformation local search process is added to strengthen the local structure of the conformation, so that the structural diversity of the conformation is increased, and the conformation which is closer to the natural state is sampled.
Drawings
FIG. 1 is a conformational distribution diagram obtained when protein 1AIL is subjected to structure prediction by a protein structure prediction method based on dihedral angle information assisted energy function selection.
FIG. 2 is a three-dimensional structure diagram obtained by predicting the structure of protein 1AIL by a protein structure prediction method using dihedral angle information as an auxiliary energy function.
Detailed Description
The invention is further described below with reference to the accompanying drawings.
Referring to fig. 1 and 2, a protein structure prediction method for assisting energy function selection based on dihedral angle information, the method comprising the steps of:
1) setting parameters: length of protein sequence L, number of initialization iterations IiThe number of global search iterations is IgThe number of local search iterations is Il；
2) Information preprocessing, first of all, given an initial protein sequence from which a stretch chain with the largest free energy is formed, in which the dihedral angle phi,
omega is respectively set to be-150 degrees, -150 degrees and 180 degrees, and a Ramachandran plot corresponding to different residue types of different secondary structures of the protein is obtained;
3) conformation initialization, using stage1 in the Rosetta ab initio method to initialize the initial conformation, and replacing residues at each residue position of the initial conformation at least more than one time or reaching the maximum initialization iteration number IiThe initialization is regarded as successful;
4) the constellations are scored through an intermediate Energy function of a Rosetta algorithm, and the Energy fraction of the constellations is Energyscore；
5) And calculating a conformational Rama score, and evaluating the dihedral angle of each residue position of the conformation through Ramachandran plot, wherein the evaluation formula is as follows:
wherein phi isa,
Two dihedral angles of residue a, res (a) residue type of residue a, ss (a) secondary structure type of residue a, wherein secondary structure type is obtained by DSSP algorithm, and the evaluation results for each residue position are summed to obtain the conformational Rama score Ramascore；
6) Designing a scoring function, and obtaining an Energy score Energy through step 4)scoreAnd the Rama fraction Rama obtained in step 5)scoreThe scoring function is designed as follows:
E(C)＝weEnergyscore+wrRamascore
wherein, weAnd wrRespectively corresponding weights of the energy fractions Rama fractions, C is a scored conformation, and the conformation is scored by the scoring function;
7) performing conformational global search, performing 9 fragment assembly on the conformation C to obtain conformation C ', then scoring the individuals before and after the fragment assembly by using the scoring function designed in the step 6) to obtain E (C) and E (C '), if E (C) is less than E (C '), receiving the individual C ', if E (C) is more than E (C '), according to Boltzmann probability
Receiving individuals, wherein, E (E) E (C') is the energy difference of two individuals after the fragments are assembled, kT is a temperature coefficient, and carrying out I on the received conformationgThe second search, the search process, as described above, reaches IgPerforming conformational local search after the secondary search;
8) performing conformation local search, performing 3-segment fragment assembly on the conformation C to obtain conformation C ', then scoring the individuals before and after the fragment assembly by using the scoring function designed in the step 6) to obtain E (C) and E (C '), if E (C) is less than E (C '), receiving the individual C ', if E (C) is more than E (C '), according to Boltzmann probability
Receiving individuals, wherein, E (E) E (C') is the energy difference of two individuals after the fragments are assembled, kT is a temperature coefficient, and carrying out I on the received conformationlThe second search, the search process, as described above, reaches IlCompleting the whole search process of the conformation after the secondary search;
9) the final conformation is saved and the output conformation information is recorded.
In this embodiment, an α -sheet protein 1AIL with a sequence length of 73 is taken as an example, and a protein structure prediction method based on dihedral angle information assisted energy function selection includes the following steps:
1) setting parameters: the length of the protein sequence L is 73, and the number of initialization iterations is Ii1000, the global search iteration number is Ig12000, local search iteration number Il＝20000；
2) Information preprocessing, first of all, given an initial protein sequence from which a stretch chain with the largest free energy is formed, in which the dihedral angle phi,
omega is respectively set to be-150 degrees, -150 degrees and 180 degrees, and a Ramachandran plot corresponding to different residue types of different secondary structures of the protein is obtained;
3) initializing the conformation, and initializing the initial conformation by using stage1 in a Rosetta ab initio method, wherein residues at each residue position of the initial conformation are replaced at least one time or the initialization is successful up to the maximum initialization iteration number of 1000;
4) the constellations are scored through an intermediate Energy function of a Rosetta algorithm, and the Energy fraction of the constellations is Energyscore；
5) And calculating a conformational Rama score, and evaluating the dihedral angle of each residue position of the conformation through Ramachandran plot, wherein the evaluation formula is as follows:
wherein phi isa,
Two dihedral angles of residue a, res (a) residue type of residue a, ss (a) secondary structure type of residue a, wherein secondary structure type is obtained by DSSP algorithm, and the evaluation results for each residue position are summed to obtain the conformational Rama score Ramascore；
6) Designing a scoring function, and obtaining an Energy score Energy through step 4)scoreAnd the Rama fraction Rama obtained in step 5)scoreThe scoring function is designed as follows:
E(C)＝weEnergyscore+wrRamascore
wherein, we0.5 and wrThe weights respectively corresponding to the energy fractions Rama and C are respectively 0.5, and the scored conformations are scored by the scoring function;
7) performing conformational global search, performing 9 fragment assembly on the conformation C to obtain conformation C ', then scoring the individuals before and after the fragment assembly by using the scoring function designed in the step 6) to obtain E (C) and E (C '), if E (C) is less than E (C '), receiving the individual C ', if E (C) is more than E (C '), according to Boltzmann probability
Receiving individuals, wherein Δ E ═ E (C) — E (C') is the energy difference between the two individuals after the fragments are assembled, kT ═ 2 is a temperature coefficient, 12000 searches are performed on the received constellations, and the search process enters the local search of the constellations after 12000 searches are performed as described above;
8) performing conformation local search, performing 3-segment fragment assembly on the conformation C to obtain conformation C ', then scoring the individuals before and after the fragment assembly by using the scoring function designed in the step 6) to obtain E (C) and E (C '), if E (C) is less than E (C '), receiving the individual C ', if E (C) is more than E (C '), according to Boltzmann probability
Receiving individuals, wherein Δ E ═ E (C) — E (C') is the energy difference between the two individuals after the fragments are assembled, kT ═ 2 is the temperature coefficient, 20000 searches are performed on the received conformations, and the search process is as described above, and the whole search process of the conformations is completed after 20000 searches are achieved;
9) the final conformation is saved and the output conformation information is recorded.
Taking alpha-folded protein 1AIL with sequence length of 73 as an exampleThe above method can obtain the near-native conformation of the protein with minimum root mean square deviation of
Mean root mean square deviation of
The prediction structure is shown in fig. 2.
The above description is of the effect of the present invention using 1AIL protein as an example, and is not intended to limit the scope of the present invention, and various modifications and improvements can be made without departing from the scope of the present invention.
Claims (1)
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810994128.2A CN109448784B (en) | 2018-08-29 | 2018-08-29 | A protein structure prediction method based on dihedral angle information-assisted energy function selection |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810994128.2A CN109448784B (en) | 2018-08-29 | 2018-08-29 | A protein structure prediction method based on dihedral angle information-assisted energy function selection |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109448784A CN109448784A (en) | 2019-03-08 |
| CN109448784B true CN109448784B (en) | 2021-05-18 |
Family
ID=65530260
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810994128.2A Active CN109448784B (en) | 2018-08-29 | 2018-08-29 | A protein structure prediction method based on dihedral angle information-assisted energy function selection |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109448784B (en) |
Families Citing this family (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110729024B (en) * | 2019-08-27 | 2021-12-17 | 浙江工业大学 | Protein structure model quality evaluation method based on topological structure similarity |
| CN110706741B (en) * | 2019-08-27 | 2021-08-03 | 浙江工业大学 | A multimodal protein structure prediction method based on sequence niche |
| CN110853704B (en) * | 2019-11-11 | 2020-11-06 | 腾讯科技（深圳）有限公司 | Protein data acquisition method, protein data acquisition device, computer equipment and storage medium |
| CN111863140B (en) * | 2020-06-15 | 2022-04-15 | 深圳晶泰科技有限公司 | Method for testing and fitting force field dihedral angle parameters |
| CN114121146B (en) * | 2021-11-29 | 2023-10-03 | 山东建筑大学 | A RNA tertiary structure prediction method based on parallel and Monte Carlo strategies |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1328601A (en) * | 1998-08-25 | 2001-12-26 | 斯克利普斯研究院 | Methods and systems for predicting protein function |
| CN1602487A (en) * | 2001-12-10 | 2005-03-30 | 富士通株式会社 | Device and method for predicting protein stereostructure |
| CN107220520A (en) * | 2017-07-11 | 2017-09-29 | 苏州国利倍康软件科技有限公司 | A kind of g protein coupled receptor drug target bag structure Forecasting Methodology |
-
2018
- 2018-08-29 CN CN201810994128.2A patent/CN109448784B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1328601A (en) * | 1998-08-25 | 2001-12-26 | 斯克利普斯研究院 | Methods and systems for predicting protein function |
| CN1602487A (en) * | 2001-12-10 | 2005-03-30 | 富士通株式会社 | Device and method for predicting protein stereostructure |
| CN107220520A (en) * | 2017-07-11 | 2017-09-29 | 苏州国利倍康软件科技有限公司 | A kind of g protein coupled receptor drug target bag structure Forecasting Methodology |
Non-Patent Citations (4)
| Title |
|---|
| 《A fresh look at the Ramachandran plot and the occurrence of standard structures in proteins》;Scott A. Hollingsworth等;《Biomol Concepts》;20101031;全文 * |
| 《From Ramachandran Maps to Tertiary Structures of Proteins》;Debarati DasGupta等;《The Journal of Physical Chemistry B》;20150622;全文 * |
| 《Protein Structure Idealization How accurately is it possible to model protein structures with dihedral angles？》;Xuefeng Cui等;《Algorithms for Molecular Biology》;20130225;全文 * |
| 《动态步长蛋白质构象空间搜索方法》;张贵军等;《吉林大学学报（工学版）》;20160331;第46卷(第2期);全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109448784A (en) | 2019-03-08 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109448784B (en) | A protein structure prediction method based on dihedral angle information-assisted energy function selection | |
| CN112585684B (en) | Iterative protein structure prediction using gradient of quality scores | |
| Khan et al. | pSSbond-PseAAC: Prediction of disulfide bonding sites by integration of PseAAC and statistical moments | |
| Vreven et al. | Updates to the integrated protein–protein interaction benchmarks: docking benchmark version 5 and affinity benchmark version 2 | |
| Yang et al. | High-accuracy prediction of transmembrane inter-helix contacts and application to GPCR 3D structure modeling | |
| Esquivel-Rodriguez et al. | Pairwise and multimeric protein–protein docking using the LZerD program suite | |
| CN106503484A (en) | A kind of multistage differential evolution Advances in protein structure prediction that is estimated based on abstract convex | |
| CN109215732B (en) | A self-learning method for protein structure prediction based on residue contact information | |
| CN105808973B (en) | One kind is based on interim shifty group's conformational space method of sampling | |
| CN108846256B (en) | Group protein structure prediction method based on residue contact information | |
| CN109086566B (en) | A Fragment Resampling-Based Population Protein Structure Prediction Method | |
| WO2020123302A1 (en) | Predicting affinity using structural and physical modeling | |
| Zhang et al. | SPIN-CGNN: Improved fixed backbone protein design with contact map-based graph construction and contact graph neural network | |
| Oda | Improving protein structure prediction with extended sequence similarity searches and deep‐learning‐based refinement in CASP15 | |
| CN109101785B (en) | A Protein Structure Prediction Method Based on Secondary Structure Similarity Selection Strategy | |
| Kuzu et al. | Modeling protein assemblies in the proteome | |
| CN111161792A (en) | Disulfide bond prediction method based on protein space structure | |
| CN108763860B (en) | A Population Protein Conformation Space Optimization Method Based on Loop Information Sampling | |
| Deng et al. | PredCSO: an ensemble method for the prediction of S-sulfenylation sites in proteins | |
| Dayalan et al. | Dihedral angle and secondary structure database of short amino acid fragments | |
| Piątkowski et al. | SupeRNAlign: a new tool for flexible superposition of homologous RNA structures and inference of accurate structure-based sequence alignments | |
| CN109448785B (en) | Protein structure prediction method for enhancing Loop region structure by using Laplace graph | |
| CN109346128B (en) | A protein structure prediction method based on dynamic selection strategy of residue information | |
| Li et al. | ctP 2 ISP: Protein–Protein Interaction Sites Prediction Using Convolution and Transformer With Data Augmentation | |
| CN101710365B (en) | Method for calculating and identifying protein kinase phosphorylation specific sites |
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 | ||
| TR01 | Transfer of patent right |
Effective date of registration: 20221228 Address after: N2248, Floor 3, Xingguang Yingjing, No. 117, Shuiyin Road, Yuexiu District, Guangzhou, Guangdong 510,000 Patentee after: GUANGZHOU ZHAOJI BIOTECHNOLOGY CO.,LTD. Address before: The city Zhaohui six districts Chao Wang Road Hangzhou City, Zhejiang province 310014 18 Patentee before: JIANG University OF TECHNOLOGY Effective date of registration: 20221228 Address after: D1101, Building 4, Software Industry Base, No. 19, 17, 18, Haitian 1st Road, Binhai Community, Yuehai Street, Nanshan District, Shenzhen, Guangdong, 518000 Patentee after: Shenzhen Xinrui Gene Technology Co.,Ltd. Address before: N2248, Floor 3, Xingguang Yingjing, No. 117, Shuiyin Road, Yuexiu District, Guangzhou, Guangdong 510,000 Patentee before: GUANGZHOU ZHAOJI BIOTECHNOLOGY CO.,LTD. |
|
| TR01 | Transfer of patent right |