CN112085244A - Residue contact map-based multi-objective optimization protein structure prediction method - Google Patents
Residue contact map-based multi-objective optimization protein structure prediction method Download PDFInfo
- Publication number
- CN112085244A CN112085244A CN202010704125.8A CN202010704125A CN112085244A CN 112085244 A CN112085244 A CN 112085244A CN 202010704125 A CN202010704125 A CN 202010704125A CN 112085244 A CN112085244 A CN 112085244A
- Authority
- CN
- China
- Prior art keywords
- contact
- population
- residue
- conformation
- server
- 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.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 24
- 238000000455 protein structure prediction Methods 0.000 title claims abstract description 14
- 238000005457 optimization Methods 0.000 title claims abstract description 12
- 102000004169 proteins and genes Human genes 0.000 claims abstract description 42
- 108090000623 proteins and genes Proteins 0.000 claims abstract description 42
- 239000012634 fragment Substances 0.000 claims abstract description 26
- 238000004364 calculation method Methods 0.000 claims abstract description 10
- 238000005215 recombination Methods 0.000 claims abstract description 6
- 230000006798 recombination Effects 0.000 claims abstract description 6
- 230000008569 process Effects 0.000 claims description 4
- 238000012163 sequencing technique Methods 0.000 claims description 4
- 238000005070 sampling Methods 0.000 abstract description 2
- 230000006870 function Effects 0.000 description 12
- 238000010586 diagram Methods 0.000 description 2
- 238000011160 research Methods 0.000 description 2
- 102000004190 Enzymes Human genes 0.000 description 1
- 108090000790 Enzymes Proteins 0.000 description 1
- 239000012190 activator Substances 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004166 bioassay Methods 0.000 description 1
- 230000008827 biological function Effects 0.000 description 1
- 230000003197 catalytic effect Effects 0.000 description 1
- 230000001413 cellular effect Effects 0.000 description 1
- 238000004883 computer application Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 239000003814 drug Substances 0.000 description 1
- 229940079593 drug Drugs 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000002474 experimental method Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 239000003112 inhibitor Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 102000039446 nucleic acids Human genes 0.000 description 1
- 108020004707 nucleic acids Proteins 0.000 description 1
- 150000007523 nucleic acids Chemical class 0.000 description 1
- 230000006916 protein interaction Effects 0.000 description 1
- 230000004850 protein–protein interaction Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/004—Artificial life, i.e. computing arrangements simulating life
- G06N3/006—Artificial life, i.e. computing arrangements simulating life based on simulated virtual individual or collective life forms, e.g. social simulations or particle swarm optimisation [PSO]
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16B—BIOINFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR GENETIC OR PROTEIN-RELATED DATA PROCESSING IN COMPUTATIONAL MOLECULAR BIOLOGY
- G16B15/00—ICT specially adapted for analysing two-dimensional or three-dimensional molecular structures, e.g. structural or functional relations or structure alignment
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16B—BIOINFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR GENETIC OR PROTEIN-RELATED DATA PROCESSING IN COMPUTATIONAL MOLECULAR BIOLOGY
- G16B30/00—ICT specially adapted for sequence analysis involving nucleotides or amino acids
- G16B30/10—Sequence alignment; Homology search
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Theoretical Computer Science (AREA)
- Spectroscopy & Molecular Physics (AREA)
- Business, Economics & Management (AREA)
- General Health & Medical Sciences (AREA)
- Biophysics (AREA)
- Health & Medical Sciences (AREA)
- Chemical & Material Sciences (AREA)
- Human Resources & Organizations (AREA)
- Medical Informatics (AREA)
- Evolutionary Biology (AREA)
- Biotechnology (AREA)
- General Physics & Mathematics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Strategic Management (AREA)
- Economics (AREA)
- Game Theory and Decision Science (AREA)
- Artificial Intelligence (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- Quality & Reliability (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Biomedical Technology (AREA)
- Crystallography & Structural Chemistry (AREA)
- Development Economics (AREA)
- Entrepreneurship & Innovation (AREA)
- Marketing (AREA)
- General Business, Economics & Management (AREA)
- Operations Research (AREA)
- Tourism & Hospitality (AREA)
- Analytical Chemistry (AREA)
- Proteomics, Peptides & Aminoacids (AREA)
Abstract
A multi-objective optimization protein structure prediction method based on a residue contact map comprises the following steps: firstly, predicting a residue Contact map of a target protein sequence by utilizing tripletRNAs, MetaPSICOV, RaptorX and STOP-Contact; secondly, designing a scoring function to initialize the population; then, sampling the population through fragment recombination and assembly; finally, aiming at different prediction servers, four contact energies are obtained through calculation according to the designed contact energy function, and a weighted scoring function E of a harmonic mean and a standard deviation is adoptedtotal(Cn) All conformations in the population are ranked and the first conformation in the last generation is selected as the predicted result. The invention can relieveThe single residue contact map prediction is inaccurate, so that the protein is misfolded, the diversity is increased, and the overall prediction accuracy is improved.
Description
Technical Field
The invention relates to the fields of bioinformatics and computer application, in particular to a residue contact map-based multi-objective optimization protein structure prediction method.
Background
Proteins are the cornerstone of life, almost all cellular activities are involved in proteins, and the three-dimensional structure of proteins determines their specific biological functions. Therefore, structural information of proteins is crucial in protein research. For example, the catalytic function of an enzyme is performed by a portion of the protein chain, i.e., the active sites exposed on the surface of the protein. Protein interactions and protein interactions with nucleic acids, inhibitors, activators are also limited to specific protein surface areas. Therefore, it is only possible to design targeted drugs that interact with the protein surface if the protein structure is known. At present, protein structure is mainly determined by means of biological wet experiments. However, the biological assay method has the disadvantages of complicated operation, long time consumption, high cost and the like. Therefore, based on computer technology, predicting the tertiary structure of a protein directly from the primary or secondary structure of the protein is a major problem in structural bioinformatics research.
Protein structure prediction mainly has the following two problems: (1) the problem of the ability to sample under high-dimensional and complex energy functions. (2) And the energy function model is inaccurate. At present, we are still far from constructing a sufficiently accurate force field that can direct the folding of the target sequence in the correct direction, resulting in a mathematically optimal solution that does not necessarily correspond to the native structure of the target protein. Aiming at the problem of inaccuracy of an energy function, the method helps to improve the prediction accuracy of the protein structure by using residue contact information to assist the energy function, but the currently predicted residue contact information is inaccurate and easily influences the overall prediction accuracy.
Therefore, improvement is needed to solve the problem that the existing inaccurate residue contact information results in insufficient accuracy of protein structure prediction.
Disclosure of Invention
In order to solve the problem that the prediction accuracy of a protein structure is insufficient due to inaccurate contact information of a single residue, the invention provides a multi-objective optimization protein structure prediction method based on a residue contact map.
The technical scheme adopted by the invention for solving the technical problems is as follows:
a method for residue contact map-based multi-objective optimized protein structure prediction, the method comprising the steps of:
1) inputting sequence information of a target protein, and predicting a residue Contact map of the target sequence by using a triplets server (zhanglab, ccmb, med, umich, edu/resttriplet), a metapsiccov server (bioif, cs, ucl, ac, uk/psipled), a RaptorX server (RaptorX, uchicago, edu/ContactMap) and a STOP-Contact server (spark-lab, org/server/shot-Contact);
2) acquiring fragment library files of 3 fragments and 9 fragments from a ROBETTA server (http:// www.robetta.org /) according to a target protein sequence;
3) according to the confidence coefficient between residue pairs in the residue contact map, arranging the confidence coefficient of the residue pairs from large to small, and selecting the first 2L pieces of contact information, wherein L is the sequence length of the target protein;
4) setting parameters: population size NP, maximum number of iterations G, temperature factor beta, omegaT,ωP,ωRAnd ωSRespectively representing the weights corresponding to Contact energies calculated from residue Contact maps predicted by the servers TripletRes, MetaPSICOV, RaptorX and STOP-Contact;
5) setting G ═ 1, G ∈ {1, 2.., G };
6) population initialization, the process is as follows:
6.1) first and second phases using the Rosetta protocolGeneration of 2NP initial conformations Cn,n={1,2,…,2NP};
6.2) calculating the energy of each individual in the population using the Rosetta score3 energy function, Individual CnHas an energy of score3 (C)n) And calculating four contact energies E according to the residue contact maps predicted by the four different contact prediction serversC(Cn) And are respectively denoted as EC1(Cn),EC2(Cn),EC3(Cn) And EC4(Cn) In which EC(Cn) The calculation formula of (a) is as follows:
wherein N is the total number of residue pairs,is the confidence of the contact of the kth residue in the residue contact map to the (i, j),is the distance between the kth residue pair (i, j) in the target protein, dconIs a threshold value of 8, EC1(Cn) Representing contact energy calculated from residue contact maps predicted by the TripletRes server, EC2(Cn) Representing contact energy calculated from residue contact maps predicted by MetaPSICOV servers, EC3(Cn) Representing the calculated contact energy, E, from a residue contact map predicted by a Raptorx serverC4(Cn) Represents the Contact energy calculated from the residue Contact map predicted by the STOP-Contact server;
6.3) according to Etotal(Cn) Sequencing the individuals in the population from low to high, taking the first NP individuals as an initialization population, Etotal(Cn) The calculation formula of (a) is as follows:
7) conformational recombination, assembly, as follows:
7.1)Cnfor the nth individual in the population and selecting two conformations C in the population which are different from the target conformationn1,Cn2Three different fragments were randomly selected in these two conformations, replacing conformation CnFragment of the corresponding position in the sequence to generate a new recombinant conformation C'n;
7.2) according to each conformation C 'in the starting population'nAssembly of fragments 3 and 9 to give a new conformation C ″n;
7.3) if score3 (C'n)>score3(C″n) Then, the conformation C ″, is usednSubstitute for C'nOtherwise, receiving the new conformation by using the Boltzmann probability to generate new NP individuals of the child population, forming a new population together with the NP individuals in the parent population, wherein the new population is 2NP individuals, and realizing the update of the new population;
8) performing population updating operation, repeating the steps 6.2) to 6.3), and selecting front NP individuals as new populations;
9) setting G to G +1, and if G > G, executing step 10); otherwise, go to 7);
10) the first conformation in the G-th generation is output as the final predicted result.
The technical conception of the invention is as follows: a multi-objective optimization protein structure prediction method based on a residue contact map comprises the following steps: firstly, predicting a residue Contact map of a target protein sequence by utilizing tripletRNAs, MetaPSICOV, RaptorX and STOP-Contact; secondly, designing a scoring function to initialize the population; then, sampling the population through fragment recombination and assembly; finally, aiming at different prediction servers, four contact energies are obtained through calculation according to the designed contact energy function, and a weighted scoring function E of a harmonic mean and a standard deviation is adoptedtotal(Cn) All conformations in the population are ranked and the first conformation in the last generation is selected as the predicted result. The multi-objective optimization protein structure prediction method based on the residue contact map can relieve protein misfolding caused by inaccurate prediction of a single residue contact map, thereby increasing diversity and improving overall prediction accuracy.
The invention has the beneficial effects that: according to a multi-objective optimization strategy, the defect that the conformation is evaluated only by a single energy function or a single residue contact map is overcome by using four pieces of residue contact map information, the population diversity is increased, and the overall prediction precision is improved.
Drawings
FIG. 1 is a schematic diagram of conformational update in the structural prediction of protein 1BG8 by a residue contact map-based multi-objective optimization protein structure prediction method.
FIG. 2 is a three-dimensional structure diagram of protein 1BG8 predicted by a residue contact map-based multi-objective optimization protein structure prediction method.
Detailed Description
The invention is further described below with reference to the accompanying drawings.
Referring to fig. 1 and 2, a method for residue contact map-based multi-objective optimized protein structure prediction, the method comprising the steps of:
1) inputting sequence information of a target protein, and predicting a residue Contact map of the target sequence by using a triplets server (zhanglab, ccmb, med, umich, edu/resttriplet), a metapsiccov server (bioif, cs, ucl, ac, uk/psipled), a RaptorX server (RaptorX, uchicago, edu/ContactMap) and a STOP-Contact server (spark-lab, org/server/shot-Contact);
2) acquiring fragment library files of 3 fragments and 9 fragments from a ROBETTA server (http:// www.robetta.org /) according to a target protein sequence;
3) according to the confidence coefficient between residue pairs in the residue contact map, arranging the confidence coefficient of the residue pairs from large to small, and selecting the first 2L pieces of contact information, wherein L is the sequence length of the target protein;
4) setting parameters: population size NP, maximum number of iterations G, temperature factor beta, omegaT,ωP,ωRAnd ωSRespectively representing the weights corresponding to Contact energies calculated from residue Contact maps predicted by the servers TripletRes, MetaPSICOV, RaptorX and STOP-Contact;
5) setting G ═ 1, G ∈ {1, 2.., G };
6) population initialization, the process is as follows:
6.1) generating 2NP initial constellations C by using the first and second stages of the Rosetta protocoln,n={1,2,…,2NP};
6.2) calculating the energy of each individual in the population using the Rosetta score3 energy function, Individual CnHas an energy of score3 (C)n) And calculating four contact energies E according to the residue contact maps predicted by the four different contact prediction serversC(Cn) And are respectively denoted as EC1(Cn),EC2(Cn),EC3(Cn) And EC4(Cn) In which EC(Cn) The calculation formula of (a) is as follows:
wherein N is the total number of residue pairs,is the confidence of the contact of the kth residue in the residue contact map to the (i, j),is the distance between the kth residue pair (i, j) in the target protein, dconIs a threshold value of 8, EC1(Cn) Representing contact energy calculated from residue contact maps predicted by the TripletRes server, EC2(Cn) Representing contact energy calculated from residue contact maps predicted by MetaPSICOV servers, EC3(Cn) Representing the calculated contact energy, E, from a residue contact map predicted by a Raptorx serverC4(Cn) Represents the Contact energy calculated from the residue Contact map predicted by the STOP-Contact server;
6.3) according to Etotal(Cn) Sequencing the individuals in the population from low to high, taking the first NP individuals as an initialization population, Etotal(Cn) The calculation formula of (a) is as follows:
7) conformational recombination, assembly, as follows:
7.1)Cnfor the nth individual in the population and selecting two conformations C in the population which are different from the target conformationn1,Cn2Three different fragments were randomly selected in these two conformations, replacing conformation CnFragment of the corresponding position in the sequence to generate a new recombinant conformation C'n;
7.2) according to each conformation C 'in the starting population'nAssembly of fragments 3 and 9 to give a new conformation C ″n;
7.3) if score3 (C'n)>score3(C″n) Then, the conformation C ″, is usednSubstitute for C'nOtherwise, receiving the new conformation by using the Boltzmann probability to generate new NP individuals of the child population, forming a new population together with the NP individuals in the parent population, wherein the new population is 2NP individuals, and realizing the update of the new population;
8) performing population updating operation, repeating the steps 6.2) to 6.3), and selecting front NP individuals as new populations;
9) setting G to G +1, and if G > G, executing step 10); otherwise, go to 7);
10) the first conformation in the G-th generation is output as the final predicted result.
This example illustrates protein 1BG8 with sequence length 76 as an example, a method for predicting protein structure based on residue contact map for multi-objective optimization, the method comprises the following steps:
1) inputting sequence information of a target protein, and predicting a residue Contact map of the target sequence by using a triplets server (zhanglab, ccmb, med, umich, edu/resttriplet), a metapsiccov server (bioif, cs, ucl, ac, uk/psipled), a RaptorX server (RaptorX, uchicago, edu/ContactMap) and a STOP-Contact server (spark-lab, org/server/shot-Contact);
2) acquiring fragment library files of 3 fragments and 9 fragments from a ROBETTA server (http:// www.robetta.org /) according to a target protein sequence;
3) according to the confidence coefficient between residue pairs in the residue contact map, arranging the confidence coefficient of the residue pairs from large to small, and selecting the first 2L pieces of contact information, wherein L is the sequence length of the target protein;
4) setting parameters: the population size NP is 200, the maximum number of iterations G is 500, the temperature factor β is 2, ωT=0.213,ωP=0.189,ωR0.233 and ωS0.175 represents the weight corresponding to the Contact energy calculated from the residue Contact maps predicted by the servers TripletRes, MetaPSICOV, RaptorX and STOP-Contact, respectively;
5) setting G ═ 1, G ∈ {1, 2.., G };
6) population initialization, the process is as follows:
6.1) generating 2NP initial constellations C by using the first and second stages of the Rosetta protocoln,n={1,2,…,2NP};
6.2) calculating the energy of each individual in the population using the Rosetta score3 energy function, Individual CnHas an energy of score3 (C)n) And calculating four contact energies E according to the residue contact maps predicted by the four different contact prediction serversC(Cn) And are respectively denoted as EC1(Cn),EC2(Cn),EC3(Cn) And EC4(Cn) In which EC(Cn) The calculation formula of (a) is as follows:
wherein N is the total number of residue pairs,is the confidence of the contact of the kth residue in the residue contact map to the (i, j),is the distance between the kth residue pair (i, j) in the target protein, dconIs a threshold value of 8, EC1(Cn) Representing contact energy calculated from residue contact maps predicted by the TripletRes server, EC2(Cn) Representing contact energy calculated from residue contact maps predicted by MetaPSICOV servers, EC3(Cn) Representing the calculated contact energy, E, from a residue contact map predicted by a Raptorx serverC4(Cn) Represents the Contact energy calculated from the residue Contact map predicted by the STOP-Contact server;
6.3) according to Etotal(Cn) Sequencing the individuals in the population from low to high, taking the first NP individuals as an initialization population, Etotal(Cn) The calculation formula of (a) is as follows:
7) conformational recombination, assembly, as follows:
7.1)Cnfor the nth individual in the population and selecting two conformations C in the population which are different from the target conformationn1,Cn2Three different fragments were randomly selected in these two conformations, replacing conformation CnFragment of the corresponding position in the sequence to generate a new recombinant conformation C'n;
7.2) according to each conformation C 'in the starting population'nAssembly of fragments 3 and 9 to give a new conformation C ″n;
7.3) if score3 (C'n)>score3(C″n) Then, the conformation C ″, is usednSubstitute for C'nOtherwise, receiving the new conformation by using the Boltzmann probability to generate new NP individuals of the child population, forming a new population together with the NP individuals in the parent population, wherein the new population is 2NP individuals, and realizing the update of the new population;
8) performing population updating operation, repeating the steps 6.2) to 6.3), and selecting front NP individuals as new populations;
9) setting G to G +1, and if G > G, executing step 10); otherwise, go to 7);
10) the first conformation in the G-th generation is output as the final predicted result.
Using the protein 1C8C with sequence length 76 as an example, the above method can obtain the near-native conformation of the protein, the conformation renewal scheme is shown in FIG. 1, and the root mean square deviation between the structure obtained after 500 generations of operation and the native structure isThe predicted three-dimensional structure is shown in fig. 2.
While the foregoing illustrates one embodiment of the invention showing advantageous results, it will be apparent that the invention is not limited to the above-described embodiment, but is capable of numerous modifications without departing from the basic inventive concepts and without exceeding the scope of the inventive concepts.
Claims (1)
1. A protein structure prediction method based on multi-objective optimization is characterized by comprising the following steps: the method comprises the following steps:
1) inputting sequence information of a target protein, and predicting a residue Contact graph of the target sequence by using a tripleters server, a MetaPSICOV server, a Raptorx server and a STOP-Contact server;
2) acquiring fragment library files of 3 fragments and 9 fragments from a ROBETTA server according to a target protein sequence;
3) according to the confidence coefficient between residue pairs in the residue contact map, arranging the confidence coefficient of the residue pairs from large to small, and selecting the first 2L pieces of contact information, wherein L is the sequence length of the target protein;
4) setting parameters: population size NP, maximum number of iterations G, temperature factor beta, omegaT,ωP,ωRAnd ωSRespectively representing the weights corresponding to Contact energies calculated from residue Contact maps predicted by the servers TripletRes, MetaPSICOV, RaptorX and STOP-Contact;
5) setting G ═ 1, G ∈ {1, 2.., G };
6) population initialization, the process is as follows:
6.1) generating 2NP initial constellations C by using the first and second stages of the Rosetta protocoln,n={1,2,…,2NP};
6.2) calculating the energy of each individual in the population using the Rosetta score3 energy function, Individual CnHas an energy of score3 (C)n) And calculating four contact energies E according to the residue contact maps predicted by the four different contact prediction serversC(Cn) And are respectively denoted as EC1(Cn),EC2(Cn),EC3(Cn) And EC4(Cn) In which EC(Cn) The calculation formula of (a) is as follows:
wherein N is the total number of residue pairs,is the confidence of the contact of the kth residue in the residue contact map to the (i, j),is the distance between the kth residue pair (i, j) in the target protein, dconIs a threshold value of 8, EC1(Cn) Representing contact energy calculated from residue contact maps predicted by the TripletRes server, EC2(Cn) Representing contact energy calculated from residue contact maps predicted by MetaPSICOV servers, EC3(Cn) Representing the calculated contact energy, E, from a residue contact map predicted by a Raptorx serverC4(Cn) Represents the Contact energy calculated from the residue Contact map predicted by the STOP-Contact server;
6.3) according to Etotal(Cn) Sequencing the individuals in the population from low to high, taking the first NP individuals as an initialization population, Etotal(Cn) The calculation formula of (a) is as follows:
7) conformational recombination, assembly, as follows:
7.1)Cnfor the nth individual in the population and selecting two conformations C in the population which are different from the target conformationn1,Cn2Three different fragments were randomly selected in these two conformations, replacing conformation CnFragment of the corresponding position in the sequence to generate a new recombinant conformation C'n;
7.2) according to each conformation C 'in the starting population'nAssembly of fragments 3 and 9 to give a new conformation C ″n;
7.3) if score3 (C'n)>score3(C″n) Then, the conformation C ″, is usednSubstitute for C'nOtherwise, receiving the new conformation by using the Boltzmann probability to generate new NP individuals of the child population, forming a new population together with the NP individuals in the parent population, wherein the new population is 2NP individuals, and realizing the update of the new population;
8) performing population updating operation, repeating the steps 6.2) to 6.3), and selecting front NP individuals as new populations;
9) setting G to G +1, and if G > G, executing step 10); otherwise, go to 7);
10) the first conformation in the G-th generation is output as the final predicted result.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010704125.8A CN112085244A (en) | 2020-07-21 | 2020-07-21 | Residue contact map-based multi-objective optimization protein structure prediction method |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010704125.8A CN112085244A (en) | 2020-07-21 | 2020-07-21 | Residue contact map-based multi-objective optimization protein structure prediction method |
Publications (1)
Publication Number | Publication Date |
---|---|
CN112085244A true CN112085244A (en) | 2020-12-15 |
Family
ID=73735351
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202010704125.8A Pending CN112085244A (en) | 2020-07-21 | 2020-07-21 | Residue contact map-based multi-objective optimization protein structure prediction method |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN112085244A (en) |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108846256A (en) * | 2018-06-07 | 2018-11-20 | 浙江工业大学 | A kind of group's Advances in protein structure prediction based on contact residues information |
CN109033744A (en) * | 2018-06-19 | 2018-12-18 | 浙江工业大学 | A kind of Advances in protein structure prediction based on residue distance and contact information |
CN109346128A (en) * | 2018-08-01 | 2019-02-15 | 浙江工业大学 | A kind of Advances in protein structure prediction based on residue information dynamic select strategy |
CN110148437A (en) * | 2019-04-16 | 2019-08-20 | 浙江工业大学 | A kind of Advances in protein structure prediction that contact residues auxiliary strategy is adaptive |
CN111180004A (en) * | 2019-11-29 | 2020-05-19 | 浙江工业大学 | Multi-contact information sub-population strategy protein structure prediction method |
-
2020
- 2020-07-21 CN CN202010704125.8A patent/CN112085244A/en active Pending
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108846256A (en) * | 2018-06-07 | 2018-11-20 | 浙江工业大学 | A kind of group's Advances in protein structure prediction based on contact residues information |
CN109033744A (en) * | 2018-06-19 | 2018-12-18 | 浙江工业大学 | A kind of Advances in protein structure prediction based on residue distance and contact information |
CN109346128A (en) * | 2018-08-01 | 2019-02-15 | 浙江工业大学 | A kind of Advances in protein structure prediction based on residue information dynamic select strategy |
CN110148437A (en) * | 2019-04-16 | 2019-08-20 | 浙江工业大学 | A kind of Advances in protein structure prediction that contact residues auxiliary strategy is adaptive |
CN111180004A (en) * | 2019-11-29 | 2020-05-19 | 浙江工业大学 | Multi-contact information sub-population strategy protein structure prediction method |
Non-Patent Citations (2)
Title |
---|
李章维;余宝昆;胡俊;周晓根;张贵军;: "接触图辅助的过程重采样蛋白质构象空间优化算法", 小型微型计算机系统, no. 03, 15 March 2020 (2020-03-15) * |
谢腾宇;周晓根;胡俊;张贵军;: "基于接触图残基对距离约束的蛋白质结构预测算法", 计算机科学, no. 01, 19 September 2019 (2019-09-19) * |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
Wang et al. | Analysis of deep learning methods for blind protein contact prediction in CASP12 | |
Purzycka et al. | Automated 3D RNA structure prediction using the RNAComposer method for riboswitches1 | |
CN106503484A (en) | A kind of multistage differential evolution Advances in protein structure prediction that is estimated based on abstract convex | |
CN103473482B (en) | Based on the prediction method for three-dimensional structure of protein that differential evolution and conformational space are annealed | |
CN108846256B (en) | Group protein structure prediction method based on residue contact information | |
Escamilla-Gutiérrez et al. | In silico strategies for modeling RNA aptamers and predicting binding sites of their molecular targets | |
CN109360596B (en) | Protein conformation space optimization method based on differential evolution local disturbance | |
CN109360599B (en) | Protein structure prediction method based on residue contact information cross strategy | |
CN106096326B (en) | A kind of differential evolution Advances in protein structure prediction based on barycenter Mutation Strategy | |
CN109086566B (en) | Group protein structure prediction method based on fragment resampling | |
CN109215732A (en) | A kind of Advances in protein structure prediction based on contact residues information self study | |
Lo et al. | Conformational epitope matching and prediction based on protein surface spiral features | |
CN109872770B (en) | Variable strategy protein structure prediction method combined with displacement degree evaluation | |
CN106503486A (en) | A kind of differential evolution protein structure ab initio prediction method based on multistage subgroup coevolution strategy | |
CN111180004B (en) | Multi-contact information sub-population strategy protein structure prediction method | |
CN112085244A (en) | Residue contact map-based multi-objective optimization protein structure prediction method | |
CN109360597B (en) | Group protein structure prediction method based on global and local strategy cooperation | |
CN109378034B (en) | Protein prediction method based on distance distribution estimation | |
CN109300506B (en) | Protein structure prediction method based on specific distance constraint | |
CN109509510B (en) | Protein structure prediction method based on multi-population ensemble variation strategy | |
CN109346126B (en) | Adaptive protein structure prediction method of lower bound estimation strategy | |
CN109243526B (en) | Protein structure prediction method based on specific fragment crossing | |
CN109147867B (en) | Group protein structure prediction method based on dynamic segment length | |
CN109360600B (en) | Protein structure prediction method based on residue characteristic distance | |
CN109448785B (en) | Protein structure prediction method for enhancing Loop region structure by using Laplace graph |
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 |