CN111180005A - Multi-modal protein structure prediction method based on niche resampling - Google Patents

Multi-modal protein structure prediction method based on niche resampling Download PDF

Info

Publication number
CN111180005A
CN111180005A CN201911197605.3A CN201911197605A CN111180005A CN 111180005 A CN111180005 A CN 111180005A CN 201911197605 A CN201911197605 A CN 201911197605A CN 111180005 A CN111180005 A CN 111180005A
Authority
CN
China
Prior art keywords
conformation
energy
niche
resampling
initial
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
Application number
CN201911197605.3A
Other languages
Chinese (zh)
Other versions
CN111180005B (en
Inventor
张贵军
夏瑜豪
赵凯龙
刘俊
彭春祥
周晓根
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Zhejiang University of Technology ZJUT
Original Assignee
Zhejiang University of Technology ZJUT
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Zhejiang University of Technology ZJUT filed Critical Zhejiang University of Technology ZJUT
Priority to CN201911197605.3A priority Critical patent/CN111180005B/en
Publication of CN111180005A publication Critical patent/CN111180005A/en
Application granted granted Critical
Publication of CN111180005B publication Critical patent/CN111180005B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • 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
    • G16B15/20—Protein or domain folding
    • 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

Landscapes

  • Life Sciences & Earth Sciences (AREA)
  • Physics & Mathematics (AREA)
  • Spectroscopy & Molecular Physics (AREA)
  • General Health & Medical Sciences (AREA)
  • Biotechnology (AREA)
  • Biophysics (AREA)
  • Health & Medical Sciences (AREA)
  • Engineering & Computer Science (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Theoretical Computer Science (AREA)
  • Evolutionary Biology (AREA)
  • Chemical & Material Sciences (AREA)
  • Medical Informatics (AREA)
  • Crystallography & Structural Chemistry (AREA)
  • Analytical Chemistry (AREA)
  • Proteomics, Peptides & Aminoacids (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)
  • Investigating Or Analysing Biological Materials (AREA)

Abstract

A multi-modal protein structure prediction method based on niche resampling is characterized in that under a Monte Carlo framework, an initial energy function is used for first round search; secondly, resampling in the current niche by taking the energy minimum conformation obtained after each operation as an initial conformation; thirdly, calculating the radius of the niche according to the conformational information obtained by resampling, and constructing an energy function for the next round of search to avoid the searched conformational from being repeatedly trapped into local optimum; and finally, outputting the conformation with the lowest energy in each resampling process as a final prediction result. The multi-modal protein structure prediction method based on niche resampling can solve the problem that the radius of the sequence niche method is difficult to determine, thereby enhancing the sampling capability, improving the sampling efficiency and improving the prediction precision. The invention provides a multi-modal protein structure prediction method based on niche resampling with high prediction precision.

Description

Multi-modal protein structure prediction method based on niche resampling
Technical Field
The invention relates to the fields of bioinformatics and computer application, in particular to a multi-modal protein structure prediction method based on niche resampling.
Background
Proteins are the cornerstone of life, and their structure determines their specific biological functions. Obtaining an accurate protein folding structure is crucial to understanding the protein folding mechanism, analyzing protein function, and developing innovative drugs. The journal of Science also lists protein structure prediction as one of the first 125 scientific problems of the 21 st century. Therefore, how to precisely obtain the three-dimensional structure of the protein and elucidate the relationship with the biological function is a serious challenge.
Biological wet experiments are the traditional methods for determining the three-dimensional structure of proteins, such as X-ray diffraction, nuclear magnetic resonance, cryoelectron microscopy, etc. However, there are two major problems with the method of experimentally determining structure: on the one hand, it is difficult to determine the structure of membrane proteins, the main targets of modern drug design; on the other hand, the process of experimental determination is time-consuming, labor-consuming and expensive, and the requirement for efficiently, quickly and simply obtaining the protein structure cannot be met. Therefore, a method for predicting the three-dimensional structure of a protein from its amino acid sequence by computer technology has been proposed. This method stems from the conclusion that the amino acid sequence of a protein determines its spatial arrangement for biological activity as proposed by Anfinsen in 1961. Methods for predicting the three-dimensional structure of a protein based on an amino acid sequence mainly include a homology modeling method and a de novo prediction method. Homology modeling predicts the structure of a new sequence using a template whose structure is known. The de novo prediction method is directly based on a protein physical or knowledge energy model, and utilizes an optimization algorithm to search a global minimum energy conformational solution in a conformational space.
Protein structure prediction is a highly-dimensional complex non-convex multi-modal optimization problem. This problem is very challenging due to the imprecision of the energy model and the extreme vulnerability to local optima. The multi-modal optimization method based on the sequence niche guides the next conformational search by using the information obtained after each algorithm operation through multiple serial operation of the algorithms, and finally obtains a protein structure with diversity. This may alleviate the above problem of protein structure prediction to some extent. However, the sequential niche method still has defects, for example, the radius of the niche is difficult to determine, if the radius is too small, the conformation still has a high probability of trapping in the same potential energy trap, and if the radius is too large, the adjacent potential energy traps are affected, so that a satisfactory result is difficult to search.
Therefore, the existing protein structure prediction method has the problems of inaccurate energy function, insufficient sampling capability, low sampling efficiency, insufficient prediction accuracy and the like, and needs to be improved.
Disclosure of Invention
The invention provides a multi-modal protein structure prediction method based on niche resampling, aiming at solving the problems of inaccurate energy function, insufficient sampling capability, low sampling efficiency, insufficient prediction precision and the like of the existing protein structure prediction method. On the basis of the sequence niche method, the lowest energy conformation in each Monte Carlo track is used as an initial conformation, the track is restarted, and resampling is performed in the explored niche, so that a conformation with lower energy and a more accurate niche radius are obtained, the sampling capacity is enhanced, the sampling efficiency is improved, and the overall prediction accuracy is improved.
The technical scheme adopted by the invention for solving the technical problems is as follows:
a method for multi-modal protein structure prediction based on niche resampling, the method comprising the steps of:
1) inputting sequence information of a target protein;
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) setting parameters: maximum number of iterations G, coefficient of energy function k1Radius coefficient of niche k2A degradation function coefficient m, an energy threshold value T;
4) setting G ═ 1, G ∈ {1, 2.., G };
5) initialization of an energy function: marking P as a target conformation, setting the initial energy function of Rosetta to M1(P)＝score(P)；
6) And (3) conformation initialization: random fragment assembly to generate an initial conformation
Figure BDA0002295056990000021
7) The initial niche conformation generation operation is as follows:
7.1) recording Mg(P) is the energy function of the g-th iteration to
Figure BDA0002295056990000022
As initial conformation, according to an energy function Mg(P) running the first to fourth phases of abinitio protocol in Rosetta, recording
Figure BDA0002295056990000023
The receiving conformation with the highest energy in four stages has an energy value of
Figure BDA0002295056990000024
Figure BDA0002295056990000025
The receiving conformation with the lowest energy, the energy value of which is
Figure BDA0002295056990000026
7.2) if
Figure BDA0002295056990000027
Step 8) is executed, otherwise, step 7) is executed again;
8) and (3) carrying out a niche resampling operation, wherein the process is as follows:
8.1) recording omegagFor the received constellation set of the g-th iteration and setting
Figure BDA0002295056990000028
To be provided with
Figure BDA0002295056990000029
As initial conformation, according to an energy function Mg(P) continuing to operate the first to fourth phases of Rosetta if the received target constellation P isacceptEnergy E ofaccept< T, then Ωg＝Ωg∪{PacceptGet it written together
Figure BDA0002295056990000031
Is a set omegagThe lowest energy conformation;
8.2) note
Figure BDA0002295056990000032
Are respectively set omegagMedium energy minimum conformation
Figure BDA0002295056990000033
The dihedral angle of the ith residue of (1),
Figure BDA0002295056990000034
are respectively set omegagThe dihedral angle of the ith residue of the jth conformation, j ∈ {1,2gL is the sequence length of the target protein, and the niche radius r is calculated according to the following formulag：
Figure BDA0002295056990000035
8.3) note
Figure BDA0002295056990000036
φi、ωiDihedral angles of the ith residue of the target conformation P,
Figure BDA0002295056990000037
is the target conformation P and the energy-minimized conformation
Figure BDA0002295056990000038
The distance between the two is calculated according to the following formula:
Figure BDA0002295056990000039
8.4) calculate the degradation function as follows:
Figure BDA00022950569900000310
8.5) calculating the energy function of the next iteration according to the following formula:
Figure BDA00022950569900000311
9) setting G to G +1, and if G > G, executing step 10); otherwise, go to step 6);
10) outputting G energy-lowest constellations in G iterations
Figure BDA00022950569900000312
As a final prediction result, G ∈ {1, 2.
The technical conception of the invention is as follows: under the monte carlo framework, firstly, a first round of search is carried out by using an initial energy function; secondly, resampling in the current niche by taking the energy minimum conformation obtained after each operation as an initial conformation; thirdly, calculating the radius of the niche according to the conformational information obtained by resampling, and constructing an energy function for the next round of search to avoid the searched conformational from being repeatedly trapped into local optimum; and finally, outputting the conformation with the lowest energy in each resampling process as a final prediction result. The multi-modal protein structure prediction method based on niche resampling can solve the problem that the radius of the sequence niche method is difficult to determine, thereby enhancing the sampling capability, improving the sampling efficiency and improving the prediction precision.
The invention has the beneficial effects that: the selection of the radius of the niche is accurate according to the niche resampling strategy; outputting multiple conformations alleviates the drawback of evaluating conformations with only a single energy function, increases conformational diversity, and thus improves overall prediction accuracy.
Drawings
FIG. 1 is a schematic diagram of the conformational update when the structure of the protein 1E2A is predicted by a multi-modal protein structure prediction method based on niche resampling.
FIG. 2 is a schematic diagram of the change of the radius of a niche when the structure of the protein 1E2A is predicted by a multi-modal protein structure prediction method based on niche resampling.
FIG. 3 is a three-dimensional structure diagram of protein 1E2A obtained by structure prediction using a multi-modal protein structure prediction method based on niche resampling.
Detailed Description
The invention is further described below with reference to the accompanying drawings.
Referring to fig. 1 to 3, a multi-modal protein structure prediction method based on niche resampling, the method comprising the steps of:
1) inputting sequence information of a target protein;
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) setting parameters: maximum number of iterations G, coefficient of energy function k1Radius coefficient of niche k2A degradation function coefficient m, an energy threshold value T;
4) setting G ═ 1, G ∈ {1, 2.., G };
5) initialization of an energy function: marking P as a target conformation, setting the initial energy function of Rosetta to M1(P)＝score(P)；
6) And (3) conformation initialization: random fragment assembly to generate an initial conformation
Figure BDA0002295056990000041
7) The initial niche conformation generation operation is as follows:
7.1) recording Mg(P) is the energy function of the g-th iteration to
Figure BDA0002295056990000042
As initial conformation, according to an energy function Mg(P) running the abinitio protocol first to fourth phases in Rosetta,note the book
Figure BDA0002295056990000043
The receiving conformation with the highest energy in four stages has an energy value of
Figure BDA0002295056990000044
Figure BDA0002295056990000045
The receiving conformation with the lowest energy, the energy value of which is
Figure BDA0002295056990000046
7.2) if
Figure BDA0002295056990000051
Step 8) is executed, otherwise, step 7) is executed again;
8) and (3) carrying out a niche resampling operation, wherein the process is as follows:
8.1) recording omegagFor the received constellation set of the g-th iteration and setting
Figure BDA0002295056990000052
To be provided with
Figure BDA0002295056990000053
As initial conformation, according to an energy function Mg(P) continuing to operate the first to fourth phases of Rosetta if the received target constellation P isacceptEnergy E ofaccept< T, then Ωg＝Ωg∪{PacceptGet it written together
Figure BDA0002295056990000054
Is a set omegagThe lowest energy conformation;
8.2) note
Figure BDA0002295056990000055
Are respectively set omegagMedium energy minimum conformation
Figure BDA0002295056990000056
The dihedral angle of the ith residue of (1),
Figure BDA0002295056990000057
are respectively set omegagThe dihedral angle of the ith residue of the jth conformation, j ∈ {1,2gL is the sequence length of the target protein, and the niche radius r is calculated according to the following formulag：
Figure BDA0002295056990000058
8.3) note
Figure BDA0002295056990000059
φi、ωiDihedral angles of the ith residue of the target conformation P,
Figure BDA00022950569900000510
is the target conformation P and the energy-minimized conformation
Figure BDA00022950569900000511
The distance between the two is calculated according to the following formula:
Figure BDA00022950569900000512
8.4) calculate the degradation function as follows:
Figure BDA00022950569900000513
8.5) calculating the energy function of the next iteration according to the following formula:
Figure BDA00022950569900000514
9) setting G to G +1, and if G > G, executing step 10); otherwise, go to step 6);
10) outputting G energy-lowest constellations in G iterations
Figure BDA00022950569900000515
As a final prediction result, G ∈ {1, 2.
The present embodiment takes protein 1E2A with sequence length 102 as an example, and provides a multi-modal protein structure prediction method based on niche resampling, which includes the following steps:
1) inputting sequence information of a target protein;
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) setting parameters: maximum number of iterations G is 5, coefficient of energy function k11, niche radius coefficient k21, the coefficient m of the degradation function is 0.001, and the energy threshold value T is 20;
4) setting G ═ 1, G ∈ {1, 2.., G };
5) initialization of an energy function: marking P as a target conformation, setting the initial energy function of Rosetta to M1(P)＝score(P)；
6) And (3) conformation initialization: random fragment assembly to generate an initial conformation
Figure BDA0002295056990000061
7) The initial niche conformation generation operation is as follows:
7.1) recording Mg(P) is the energy function of the g-th iteration to
Figure BDA0002295056990000062
As initial conformation, according to an energy function Mg(P) running the first to fourth phases of abinitio protocol in Rosetta, recording
Figure BDA0002295056990000063
The receiving conformation with the highest energy in four stages has an energy value of
Figure BDA0002295056990000064
Figure BDA0002295056990000065
The receiving conformation with the lowest energy, the energy value of which is
Figure BDA0002295056990000066
7.2) if
Figure BDA0002295056990000067
Step 8) is executed, otherwise, step 7) is executed again;
8) and (3) carrying out a niche resampling operation, wherein the process is as follows:
8.1) recording omegagFor the received constellation set of the g-th iteration and setting
Figure BDA0002295056990000068
To be provided with
Figure BDA0002295056990000069
As initial conformation, according to an energy function Mg(P) continuing to operate the first to fourth phases of Rosetta if the received target constellation P isacceptEnergy E ofaccept< T, then Ωg＝Ωg∪{PacceptGet it written together
Figure BDA00022950569900000610
Is a set omegagThe lowest energy conformation;
8.2) note
Figure BDA00022950569900000611
Are respectively set omegagMedium energy minimum conformation
Figure BDA00022950569900000612
The dihedral angle of the ith residue of (1),
Figure BDA00022950569900000613
are respectively set omegagThe dihedral angle of the ith residue of the jth conformation, j ∈ {1,2gL is the sequence length of the target protein, and is calculated as followsRadius of habitat rg：
Figure BDA00022950569900000614
8.3) note
Figure BDA00022950569900000615
φi、ωiDihedral angles of the ith residue of the target conformation P,
Figure BDA00022950569900000616
is the target conformation P and the energy-minimized conformation
Figure BDA0002295056990000071
The distance between the two is calculated according to the following formula:
Figure BDA0002295056990000072
8.4) calculate the degradation function as follows:
Figure BDA0002295056990000073
8.5) calculating the energy function of the next iteration according to the following formula:
Figure BDA0002295056990000074
9) setting G to G +1, and if G > G, executing step 10); otherwise, go to step 6);
10) outputting G energy-lowest constellations in G iterations
Figure BDA0002295056990000075
As a final prediction result, G ∈ {1, 2.
Using protein 1E2A with sequence length 102 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 radius of its niche isThe variation diagram is shown in FIG. 2, and the root mean square deviation between the 5 structures obtained after 5 times of operation and the natural structure is respectively
Figure BDA0002295056990000076
The predicted three-dimensional structure is shown in fig. 3.
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 multi-modal protein structure prediction method based on niche resampling is characterized by comprising the following steps: the method comprises the following steps:
1) inputting sequence information of a target protein;
2) acquiring fragment library files of 3 fragments and 9 fragments from a ROBETTA server according to a target protein sequence;
3) setting parameters: maximum number of iterations G, coefficient of energy function k1Radius coefficient of niche k2A degradation function coefficient m, an energy threshold value T;
4) setting G ═ 1, G ∈ {1, 2.., G };
5) initialization of an energy function: marking P as a target conformation, setting the initial energy function of Rosetta to M1(P)＝score(P)；
6) And (3) conformation initialization: random fragment assembly to generate an initial conformation
Figure FDA0002295056980000011
7) The initial niche conformation generation operation is as follows:
7.1) recording Mg(P) is the energy function of the g-th iteration to
Figure FDA0002295056980000012
As initial conformation, according to an energy function Mg(P) running the abinitio protocol first in RosettaTo the fourth stage, recording
Figure FDA0002295056980000013
The receiving conformation with the highest energy in four stages has an energy value of
Figure FDA0002295056980000014
Figure FDA0002295056980000015
The receiving conformation with the lowest energy, the energy value of which is
Figure FDA0002295056980000016
7.2) if
Figure FDA0002295056980000017
Step 8) is executed, otherwise, step 7) is executed again;
8) and (3) carrying out a niche resampling operation, wherein the process is as follows:
8.1) recording omegagFor the received constellation set of the g-th iteration and setting
Figure FDA0002295056980000018
To be provided with
Figure FDA0002295056980000019
As initial conformation, according to an energy function Mg(P) continuing to operate the first to fourth phases of Rosetta if the received target constellation P isacceptEnergy E ofaccept< T, then Ωg＝Ωg∪{PacceptGet it written together
Figure FDA00022950569800000110
Is a set omegagThe lowest energy conformation;
8.2) note
Figure FDA00022950569800000111
Are respectively set omegagMedium energy minimum conformation
Figure FDA00022950569800000112
The dihedral angle of the ith residue of (1),
Figure FDA00022950569800000113
are respectively set omegagThe dihedral angle of the ith residue of the jth conformation, j ∈ {1,2gL is the sequence length of the target protein, and the niche radius r is calculated according to the following formulag：
Figure FDA0002295056980000021
8.3) note
Figure FDA0002295056980000022
φi、ωiDihedral angles of the ith residue of the target conformation P,
Figure FDA0002295056980000023
is the target conformation P and the energy-minimized conformation
Figure FDA0002295056980000024
The distance between the two is calculated according to the following formula:
Figure FDA0002295056980000025
8.4) calculate the degradation function as follows:
Figure FDA0002295056980000026
8.5) calculating the energy function of the next iteration according to the following formula:
Figure FDA0002295056980000027
9) setting G to G +1, and if G > G, executing step 10); otherwise, go to step 6);
10) outputting G energy-lowest constellations in G iterations
Figure FDA0002295056980000028
As a final prediction result, G ∈ {1, 2.
CN201911197605.3A 2019-11-29 2019-11-29 Multi-modal protein structure prediction method based on niche resampling Active CN111180005B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201911197605.3A CN111180005B (en) 2019-11-29 2019-11-29 Multi-modal protein structure prediction method based on niche resampling

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201911197605.3A CN111180005B (en) 2019-11-29 2019-11-29 Multi-modal protein structure prediction method based on niche resampling

Publications (2)

Publication Number Publication Date
CN111180005A true CN111180005A (en) 2020-05-19
CN111180005B CN111180005B (en) 2021-08-03

Family

ID=70653770

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201911197605.3A Active CN111180005B (en) 2019-11-29 2019-11-29 Multi-modal protein structure prediction method based on niche resampling

Country Status (1)

Country Link
CN (1) CN111180005B (en)

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN114121146A (en) * 2021-11-29 2022-03-01 山东建筑大学 RNA three-level structure prediction method based on parallel and Monte Carlo strategies
CN117497071A (en) * 2023-11-02 2024-02-02 正则量子(北京)技术有限公司 Method and device for determining stable conformation of drug molecule through quantum computation

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20180068054A1 (en) * 2016-09-06 2018-03-08 University Of Washington Hyperstable Constrained Peptides and Their Design
CN109255427A (en) * 2018-08-30 2019-01-22 无锡城市职业技术学院 A kind of molecular docking calculation method based on quantum particle swarm optimization
CN109360601A (en) * 2018-08-29 2019-02-19 浙江工业大学 A kind of multi-modal Advances in protein structure prediction based on exclusion strategy
US20190070314A1 (en) * 2017-03-28 2019-03-07 The Regents Of The University Of California Nano/micromotors for active and dynamic intracellular payload delivery
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

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20180068054A1 (en) * 2016-09-06 2018-03-08 University Of Washington Hyperstable Constrained Peptides and Their Design
US20190070314A1 (en) * 2017-03-28 2019-03-07 The Regents Of The University Of California Nano/micromotors for active and dynamic intracellular payload delivery
CN109360601A (en) * 2018-08-29 2019-02-19 浙江工业大学 A kind of multi-modal Advances in protein structure prediction based on exclusion strategy
CN109255427A (en) * 2018-08-30 2019-01-22 无锡城市职业技术学院 A kind of molecular docking calculation method based on quantum particle swarm optimization
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

Non-Patent Citations (2)

* Cited by examiner, † Cited by third party
Title
LI Z W: ""Loop Enhanced Conformational Resampling Method for Protein Structure Prediction"", 《 IEEE TRANSACTIONS ON NANOBIOSCIENCE》 *
於东军: ""识别蛋白质配体绑定残基的生物计算方法综述"", 《数据采集与处理》 *

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN114121146A (en) * 2021-11-29 2022-03-01 山东建筑大学 RNA three-level structure prediction method based on parallel and Monte Carlo strategies
CN114121146B (en) * 2021-11-29 2023-10-03 山东建筑大学 RNA tertiary structure prediction method based on parallel and Monte Carlo strategies
CN117497071A (en) * 2023-11-02 2024-02-02 正则量子(北京)技术有限公司 Method and device for determining stable conformation of drug molecule through quantum computation

Also Published As

Publication number Publication date
CN111180005B (en) 2021-08-03

Similar Documents

Publication Publication Date Title
JP2022501695A (en) Predicting a protein structure using a geometry neural network that estimates the similarity between the predicted protein structure and the actual protein structure.
Gao et al. Alphadesign: A graph protein design method and benchmark on alphafolddb
CN111180005B (en) Multi-modal protein structure prediction method based on niche resampling
CN109360599B (en) Protein structure prediction method based on residue contact information cross strategy
Djeddi et al. A novel computational approach for global alignment for multiple biological networks
JP2022106287A (en) Affinity prediction method and model training method, equipment, device, and medium
Brunette et al. Guiding conformation space search with an all‐atom energy potential
Nichols et al. On the use of molecular dynamics receptor conformations for virtual screening
US20050177318A1 (en) Methods, systems and computer program products for identifying pharmacophores in molecules using inferred conformations and inferred feature importance
CN110706741B (en) Multi-modal protein structure prediction method based on sequence niche
CN116092576A (en) Protein structure optimization method and device
CN113257338A (en) Protein structure prediction method based on residue contact diagram information game mechanism
Chen et al. An improved graph entropy-based method for identifying protein complexes
Theepalakshmi et al. Freezing firefly algorithm for efficient planted (ℓ, d) motif search
Guo et al. Solving 2D HP protein folding problem by parallel ant colonies
Zhu et al. GMAlign: A new network aligner for revealing large conserved functional components
Yang et al. Fast and accurate algorithms for mapping and aligning long reads
Xun et al. A hybrid search method for accelerating convolutional neural architecture search
CN113362887A (en) Protein conformation sampling method based on local enhancement of niche
Saleh et al. A population-based evolutionary algorithm for sampling minima in the protein energy surface
CN109584954B (en) Protein conformation space optimization method based on multi-population joint search
Nori et al. RNAFlow: RNA Structure & Sequence Design via Inverse Folding-Based Flow Matching
Rashid et al. A parallel framework for multipoint spiral search in ab initio protein structure prediction
CN113257339A (en) Fragment assembly method guided by residue-to-distance constraint
CN116386764A (en) Method for predicting three-dimensional folding and drug molecule binding model of G protein coupled receptor protein

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
EE01 Entry into force of recordation of patent licensing contract

Application publication date: 20200519

Assignee: ZHEJIANG ORIENT GENE BIOTECH CO.,LTD.

Assignor: JIANG University OF TECHNOLOGY

Contract record no.: X2023980053610

Denomination of invention: A multimodal protein structure prediction method based on niche resampling

Granted publication date: 20210803

License type: Common License

Record date: 20231222

EE01 Entry into force of recordation of patent licensing contract