CN109086565A - A kind of Advances in protein structure prediction based on contiguity constraint between residue - Google Patents
A kind of Advances in protein structure prediction based on contiguity constraint between residue Download PDFInfo
- Publication number
- CN109086565A CN109086565A CN201810763135.1A CN201810763135A CN109086565A CN 109086565 A CN109086565 A CN 109086565A CN 201810763135 A CN201810763135 A CN 201810763135A CN 109086565 A CN109086565 A CN 109086565A
- Authority
- CN
- China
- Prior art keywords
- conformation
- residue
- population
- segment
- protein
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Landscapes
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Investigating Or Analysing Biological Materials (AREA)
Abstract
A kind of Advances in protein structure prediction based on contiguity constraint between residue, comprising the following steps: contact information first with distance between the residue of RaptorX-Contact predicted query sequence, construct fragment library；Secondly population conformation is initialized using taboo search method, establishes the evaluation function based on contiguity constraint between residue, design cross and variation strategy；Population recruitment is finally realized according to distance restraint score value between residue, algorithm ability in sampling, search efficiency can be effectively improved using distance restraint between residue, and then obtains that structure is more compact, the lower conformation of energy.The present invention provides a kind of higher Advances in protein structure prediction of precision of prediction.
Description
Technical field
The present invention relates to bioinformatics, Intelligent Information Processing, computer application field, tertiary protein structures to predict,
More particularly to a kind of Advances in protein structure prediction based on contiguity constraint between residue.
Background technique
Protein is the important component of life entity, is the undertaker of vital movement.The basic component units of protein
It is amino acid, common amino acid has more than 20 kinds in nature, and protein is made of carbon, hydrogen, oxygen, nitrogen, and general protein can
It can also contain phosphorus, sulphur, iron, zinc, copper, boron, manganese, iodine, molybdenum etc., amino acid is by central carbon atom and its connected amino, carboxylic
The side chain of base, hydrogen atom and amino acid forms, and amino acid forms peptide bond, the amino connected by peptide bond by dehydrating condensation
Acid forms a long-chain, as protein.
Protein molecule plays a crucial role in biological cell chemical reaction process.Their structural model and
Bioactivity state pair is we have appreciated that have important meaning with a variety of diseases are cured.Protein is only folded into specific three-dimensional knot
Structure could generate its distinctive biological function.It is to be understood that the function of protein, must just obtain its three-D space structure.Cause
This, obtain protein three-dimensional structure be for the mankind it is vital, 1961, Anfinsen proposed amino acid sequence
Determining protein three-dimensional structure, this starts new theory.And three-dimensional structure directly determines the biological sexual function of protein, institute
Great interest is produced with three-dimensional structure of the people to protein and is unfolded to study.Foreign scholar Ken Delu and Perutz are to flesh blood
Albumen and hemoglobin have carried out structural analysis, obtain its protein three-dimensional structure, are that the mankind measure the three of protein for the first time
Structure is tieed up, two people win a year Nobel chemistry Prize whereby.In addition, Britain crystallographer Bernal and proposing protein in 1958
The concept of quaternary structure is defined as the infiltration and development of prlmary structure of protein, secondary structure and tertiary structure.Multidimensional core
Magnetic resonance method and ray-crystallography method are the experiments of the two most important measurement protein structures to grow up in recent years
Method.Multi-dimensional nmr method is to put protein in water, and the method for its three-dimensional structure is directly measured using nuclear magnetic resonance.
And ray-crystallography method is most effective protein three-dimensional structure mensuration means so far.Until before, both sides are used
The protein of method measurement accounts for having surveyed the exhausted large scale in protein.Since the condition using experimental method is limited, limited time,
It needs to spend a large amount of man power and material, and the speed measured does not catch up with the finding speed of sequence much, so being badly in need of one kind
Not only chemical experiment, but also the prediction technique with certain accuracy rate are not depended on.It is how easy in this way, fast and efficiently to unknown egg
White matter carries out three-dimensional structure prediction, becomes the thorny problem of researcher.Under theory study and the dual promotion of application demand, according to
The theory that protein three-dimensional structure is determined according to the prlmary structure of protein of proposition, using Computer Design algorithm appropriate, with sequence
It is classified as starting point, three-dimensional structure is that the protein structure prediction of target flourishes at the end of the 20th century certainly.
Using sequence as starting point, it is referred to as using the three-dimensional structure of computer and optimization algorithm prediction protein from the beginning pre-
It surveys.Ab initio prediction method is directly based upon protein physics or Knowledge Energy model, is searched for entirely using optimization algorithm in conformational space
Office's the lowest energy conformation solution.Conformational space optimization (or sampling) method is to restrict protein structure ab initio prediction precision most at present
Crucial one of factor.Optimization algorithm is applied to ab initio prediction sampling process must solve the problems, such as following three aspects first:
(1) complexity of energy model.Protein energy model consider molecular system bonding effect and Van der Waals force, electrostatic, hydrogen bond,
The non-bonding effect such as hydrophobic, causes the Energy Surface formed it into extremely coarse, local minimizers number quantity with sequence length increasing
Add and is exponentially increased；The funnel characteristic of energy model will necessarily also generate localized high energy obstacle, and algorithm is caused easily to fall into office
Portion's solution.(2) energy model higher-dimension characteristic.For now, ab initio prediction method can only cope with the lesser target protein of size, and one
As be no more than 100.It is more than the target protein of 150 residues or more to size, existing optimization method is helpless.This is also just into one
Step illustrates the increase with size scale, necessarily causes dimension calamity problem, completes involved by so immense stable conformation process
And calculation amount be that current state-of-the-art computer is also difficult to bear.(3) inexactness of energy model.For protein this
The large biological molecule of class complexity, other than considering the effect of various physics bondings and knowledge reasoning, it is also contemplated that it and surrounding
The interaction of solvent molecule can not also provide accurate physical description at present.In view of calculating cost problem, grind nearly ten years
The person of studying carefully proposes some field of force simplified models (AMBER, CHARMM etc.) based on physics successively, the Knowledge based engineering field of force simplifies mould
Type (Rosetta, QUARK etc.).However, we, which can not also much build, is able to guide the foot that target sequence is folded towards correct direction
Enough accurate field of forces, the optimal solution for causing mathematically not necessarily correspond to the native state structure of target protein；In addition, model is not
Accuracy, which also inevitably results in, objectively to analyze algorithm performance, to hinder high-performance algorithm in protein knot
Application in structure ab initio prediction field.
Therefore, there is defects in terms of precision of prediction and energy function for present Advances in protein structure prediction, need
It improves.
Summary of the invention
In order to overcome existing Advances in protein structure prediction energy function inaccurate and the lower defect of precision of prediction, this
Invention provides a kind of precision of prediction the higher Advances in protein structure prediction based on contiguity constraint between residue.
The technical solution adopted by the present invention to solve the technical problems is:
A kind of Advances in protein structure prediction based on contiguity constraint between residue, the described method comprises the following steps:
1) input inquiry sequence, and utilization RaptorX-Contact (http://raptorx.uchicago.edu/ ContactMap) predicted query sequence residue between distance contact information；
2) initial population scale NP, maximum number of iterations Gen, crossover probability CR, segment are set and assemble times N, input is looked into
It askes and contacts information, the number of iterations g=0 between sequence, fragment library, residue；
3) the method initialization population for using TABU search, to conformation C each in populationiFollowing operation is done, wherein i ∈
[1, NP] is conformation index value in population, and process is as follows:
3.1) to conformation CiCarry out the assembling of n times segment, and segment used when recorded segment assembling；
3.2) conformation C is setiSegment segment used when assembling is to CjSegment is sampled for taboo, wherein j ∈ [1, NP] and j
≠i；
4) conformation is intersected, and is operated as follows:
4.1) i-th of conformation C is selectediFor target conformation, random number r, r a ∈ [0,1] is generated, if r is less than CR, is jumped
To 4.2), step 5) is otherwise skipped to；
4.2) a conformation C is randomly choosedj, j ≠ i, utilize calculate secondary structure algorithm DSSP obtain conformation CiSecond level knot
Structure information；
4.3) according to CiResi-dues randomly choose a crosspoint p, judge the secondary structure of the corresponding residue of crosspoint p
Type S, S ∈ { H, E, L }, H, E and L respectively represent spiral, lamella, random folding；
4.4) it is directed to CiAnd Cj, dihedral angle is successively exchanged since the p of crosspoint to until the two of another intersection residue
Level structure S ' ≠ S, S ' ∈ { H, E, L } generate a new conformation C 'i；
5) conformation makes a variation, to conformation C 'iWith C 'j, mutation process is as follows:
5.1) to conformation C 'iWith C 'j9 residue segment assemblings are carried out, two conformation C " are generatediWith C "j；
5.2) respectively to conformation C "iWith C "jSeek distance restraint score value E between residueco:
Wherein N is contact residues sum,It is that k-th of residue of search sequence query has been predicted to be contact to p and q
Confidence level,It is the actual distance for testing k residue of conformation to p and q, dconIt is the threshold value for being predicted as contact,
5.3) from conformation C "iWith C "jDistance restraint score value E ' between middle selection residuecoHighest conformation is as the successfully structure that makes a variation
As；
6) it is selected based on contiguity constraint between residue, process is as follows:
6.1) distance restraint score value E seeking residue to each conformation in populationco, and distance is about between finding out the smallest residue
Beam score value E "co；
If 6.2) E 'coGreater than E "co, then E " is usedcoE " is replaced to deserved conformationcoPopulation recruitment is realized to deserved conformation, it is no
Then population remains unchanged；
7) g=g+1 judges whether to reach maximum number of iterations Gen, if being unsatisfactory for condition termination condition, traverses population
Step 4) is executed, last prediction result is otherwise exported.
Technical concept of the invention are as follows: a kind of Advances in protein structure prediction based on contiguity constraint between residue, including with
Lower step: information is contacted first with distance between the residue of RaptorX-Contact predicted query sequence, constructs fragment library；Its
It is secondary that population conformation is initialized using taboo search method, the evaluation function based on contiguity constraint between residue is established, design intersects
Mutation Strategy；Population recruitment is finally realized according to distance restraint score value between residue, it can be effectively using distance restraint between residue
Algorithm ability in sampling, search efficiency are improved, and then obtains that structure is more compact, the lower conformation of energy.
The invention has the benefit that conformational space ability in sampling is relatively strong, can effectively make potential conformation quilt
It preserves and then improves precision of prediction.
Detailed description of the invention
Fig. 1 is to contact distribution map between protein 1AOY residue.
Fig. 2 is three that protein 1AOY is predicted using the Advances in protein structure prediction based on contiguity constraint between residue
Tie up structural schematic diagram.
Specific embodiment
The present invention is described further with reference to the accompanying drawing.
Referring to Figures 1 and 2, a kind of Advances in protein structure prediction based on contiguity constraint between residue, comprising the following steps:
1) input inquiry sequence, and utilization RaptorX-Contact (http://raptorx.uchicago.edu/ ContactMap) predicted query sequence residue between distance contact information；
2) initial population scale NP, maximum number of iterations Gen, crossover probability CR, segment are set and assemble times N, input is looked into
It askes and contacts information, the number of iterations g=0 between sequence, fragment library, residue；
3) the method initialization population for using TABU search, to conformation C each in populationiFollowing operation is done, wherein i ∈
[1, NP] is conformation index value in population, and process is as follows:
6.1) to conformation CiCarry out the assembling of n times segment, and segment used when recorded segment assembling；
6.2) conformation C is setiSegment segment used when assembling is to CjSegment is sampled for taboo, wherein j ∈ [1, NP] and j
≠i；
4) conformation is intersected, and is operated as follows:
4.1) i-th of conformation C is selectediFor target conformation, random number r, r a ∈ [0,1] is generated, if r is less than CR, is jumped
To 4.2), step 5) is otherwise skipped to；
4.2) a conformation C is randomly choosedj, j ≠ i, utilize calculate secondary structure algorithm DSSP obtain conformation CiSecond level knot
Structure information；
4.3) according to CiResi-dues randomly choose a crosspoint p, judge the secondary structure of the corresponding residue of crosspoint p
Type S, S ∈ { H, E, L }, H, E and L respectively represent spiral, lamella, random folding；
4.4) it is directed to CiAnd Cj, dihedral angle is successively exchanged since the p of crosspoint to until the two of another intersection residue
Level structure S ' ≠ S, S ' ∈ { H, E, L } generate a new conformation C 'i；
5) conformation makes a variation, to conformation C 'iWith C 'j, mutation process is as follows:
5.1) to conformation C 'iWith C 'j9 residue segment assemblings are carried out, two conformation C " are generatediWith C "j；
5.2) respectively to conformation C "iWith C "jSeek distance restraint score value E between residueco:
Wherein N is contact residues sum,It is that k-th of residue of search sequence query has been predicted to be contact to p and q
Confidence level,It is the actual distance for testing k residue of conformation to p and q, dconIt is the threshold value for being predicted as contact,
5.3) from conformation C "iWith C "jDistance restraint score value E ' between middle selection residuecoHighest conformation is as the successfully structure that makes a variation
As；
6) it is selected based on contiguity constraint between residue, process is as follows:
6.1) distance restraint score value E seeking residue to each conformation in populationco, and distance is about between finding out the smallest residue
Beam score value E "co；
If 6.2) E 'coGreater than E "co, then E ' is usedcoE " is replaced to deserved conformationcoPopulation recruitment is realized to deserved conformation, it is no
Then population remains unchanged；
7) g=g+1 judges whether to reach maximum number of iterations Gen, if being unsatisfactory for condition termination condition, traverses population
Step 4) is executed, last prediction result is otherwise exported.
The α/β unfolded protein 1AOY that the present embodiment is 78 using sequence length is embodiment, based on contiguity constraint between residue
Tertiary protein structure prediction technique, the described method comprises the following steps:
1) input inquiry sequence, and utilization RaptorX-Contact (http://raptorx.uchicago.edu/ ContactMap) predicted query sequence residue between distance contact information；
2) initial population scale 100, maximum number of iterations 1000, crossover probability 0.5, segment are set and assemble number 2000,
Information, the number of iterations g=0 are contacted between input inquiry sequence, fragment library, residue；
3) the method initialization population for using TABU search, to conformation C each in populationiFollowing operation is done, wherein i ∈
[1,100] is conformation index value in population, and process is as follows:
9.1) to conformation CiCarry out 2000 segment assemblings, and segment used when recorded segment assembling；
9.2) conformation C is setiSegment segment used when assembling is to CjSegment is sampled for taboo, wherein j ∈ [1,100] and j
≠i；
4) conformation is intersected, and is operated as follows:
4.1) i-th of conformation C is selectediFor target conformation, generate random number r, r a ∈ [0,1], if r less than 0.5,
It jumps to 4.2), otherwise skips to step 5)；
4.2) a conformation C is randomly choosedj, j ≠ i, utilize calculate secondary structure algorithm DSSP obtain conformation CiSecond level knot
Structure information；
4.3) according to CiResi-dues randomly choose a crosspoint p, judge the secondary structure of the corresponding residue of crosspoint p
Type S, S ∈ { H, E, L }, H, E and L respectively represent spiral, lamella, random folding；
4.4) it is directed to CiAnd Cj, dihedral angle is successively exchanged since the p of crosspoint to until the two of another intersection residue
Level structure S ' ≠ S, S ' ∈ { H, E, L } generate a new conformation Ci′；
5) conformation makes a variation, to conformation C 'iWith C 'j, mutation process is as follows:
5.1) to conformation C 'iWith C 'j9 residue segment assemblings are carried out, two conformation C " are generatediWith C "j；
5.2) respectively to conformation C "iWith C "jSeek distance restraint score value E between residueco:
Wherein N is contact residues sum,It is that k-th of residue of search sequence query has been predicted to be contact to p and q
Confidence level,It is the actual distance for testing k residue of conformation to p and q, dconIt is the threshold value for being predicted as contact,
5.3) from conformation C "iWith C "jDistance restraint score value E ' between middle selection residuecoHighest conformation is as the successfully structure that makes a variation
As；
6) it is selected based on contiguity constraint between residue, process is as follows:
6.1) distance restraint score value E seeking residue to each conformation in populationco, and distance is about between finding out the smallest residue
Beam score value E "co；
If 6.2) E 'coGreater than E 'co, then E ' is usedcoE " is replaced to deserved conformationcoPopulation recruitment is realized to deserved conformation, it is no
Then population remains unchanged；
7) g=g+1 judges whether to reach maximum number of iterations 1000, if being unsatisfactory for condition termination condition, traverses population
Step 4) is executed, last prediction result is otherwise exported.
The α/β unfolded protein 1AOY for being 78 using sequence length has obtained the protein as embodiment, with above method
Nearly native state conformation, lowest mean square root deviation isAverage root-mean-square deviation isPre- geodesic structure is as shown in Figure 2.
Described above is the excellent results that the present invention is obtained using 1AOY protein by example, it is clear that the present invention is not only suitable for
Above-described embodiment does various changes and improvements to it under the premise of without departing from range involved by basic content of the present invention, does not answer
It excludes except protection scope of the present invention.
Claims (1)
1. a kind of Advances in protein structure prediction based on contiguity constraint between residue, it is characterised in that: the method includes following
Step:
1) input inquiry sequence, and information is contacted using distance between the residue of RaptorX-Contact predicted query sequence；
2) initial population scale NP, maximum number of iterations Gen, crossover probability CR, segment are set and assemble times N, input inquiry sequence
Information, the number of iterations g=0 are contacted between column, fragment library, residue；
3) the method initialization population for using TABU search, to conformation C each in populationiFollowing operation is done, wherein [1, NP] i ∈
It is conformation index value in population, process is as follows:
3.1) to conformation CiCarry out the assembling of n times segment, and segment used when recorded segment assembling；
3.2) conformation C is setiSegment segment used when assembling is to CjSegment is sampled for taboo, wherein j ∈ [1, NP] and j ≠ i；
4) conformation is intersected, and is operated as follows:
4.1) i-th of conformation C is selectediFor target conformation, random number r, r a ∈ [0,1] is generated, if r is less than CR, is jumped to
4.2) step 5), is otherwise skipped to；
4.2) a conformation C is randomly choosedj, j ≠ i, utilize calculate secondary structure algorithm DSSP obtain conformation CiSecondary structure letter
Breath；
4.3) according to CiResi-dues randomly choose a crosspoint p, judge the secondary structure types of the corresponding residue of crosspoint p
S, S ∈ { H, E, L }, H, E and L respectively represent spiral, lamella, random folding；
4.4) it is directed to CiAnd Cj, dihedral angle is successively exchanged since the p of crosspoint to the second level knot until another intersection residue
Structure S ' ≠ S, S ' ∈ { H, E, L } generate a new conformation C 'i；
5) conformation makes a variation, to conformation C 'iWith C 'j, mutation process is as follows:
5.1) to conformation C 'iWith C 'j9 residue segment assemblings are carried out, two conformation C " are generatediWith C "j；
5.2) respectively to conformation C "iWith C "jSeek distance restraint score value E between residueco:
Wherein N is contact residues sum,It is the confidence that k-th of residue of search sequence query is predicted to be contact to p and q
Degree,It is the actual distance for testing k residue of conformation to p and q, dconIt is the threshold value for being predicted as contact,
5.3) from conformation C "iWith C "jDistance restraint score value E ' between middle selection residuecoHighest conformation is as the successfully conformation that makes a variation；
6) it is selected based on distance restraint between residue, process is as follows:
6.1) distance restraint score value E seeking residue to each conformation in populationco, and find out distance restraint point between the smallest residue
Value E "co；
If 6.2) E 'coGreater than E "co, then E ' is usedcoE " is replaced to deserved conformationcoPopulation recruitment is realized to deserved conformation, is otherwise planted
Group remains unchanged；
7) g=g+1 judges whether to reach maximum number of iterations Gen, if being unsatisfactory for condition termination condition, traverses population execution
Step 4) otherwise exports last prediction result.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810763135.1A CN109086565B (en) | 2018-07-12 | 2018-07-12 | Protein structure prediction method based on contact constraint between residues |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810763135.1A CN109086565B (en) | 2018-07-12 | 2018-07-12 | Protein structure prediction method based on contact constraint between residues |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109086565A true CN109086565A (en) | 2018-12-25 |
| CN109086565B CN109086565B (en) | 2021-11-23 |
Family
ID=64837595
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810763135.1A Active CN109086565B (en) | 2018-07-12 | 2018-07-12 | Protein structure prediction method based on contact constraint between residues |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109086565B (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109658979A (en) * | 2019-01-09 | 2019-04-19 | 浙江工业大学 | A kind of Advances in protein structure prediction based on fragment library information enhancement |
| CN111815036A (en) * | 2020-06-23 | 2020-10-23 | 浙江工业大学 | Protein structure prediction method based on multi-residue contact map cooperative constraint |
| CN112085246A (en) * | 2020-07-22 | 2020-12-15 | 浙江工业大学 | Protein structure prediction method based on residue-to-distance constraint |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2017079836A1 (en) * | 2015-11-09 | 2017-05-18 | The University Of British Columbia | Systems and methods for predicting misfolded protein epitopes by collective coordinate biasing |
| CN107622182A (en) * | 2017-08-04 | 2018-01-23 | 中南大学 | The Forecasting Methodology and system of protein partial structurtes feature |
| CN107633159A (en) * | 2017-08-21 | 2018-01-26 | 浙江工业大学 | A kind of protein conformation space search method based on Distance conformability degree |
| WO2018081289A2 (en) * | 2016-10-25 | 2018-05-03 | The United States Of America, As Represented By The Secretary, Department Of Health And Human Services | Prefusion piv f immunogens and their use |
-
2018
- 2018-07-12 CN CN201810763135.1A patent/CN109086565B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2017079836A1 (en) * | 2015-11-09 | 2017-05-18 | The University Of British Columbia | Systems and methods for predicting misfolded protein epitopes by collective coordinate biasing |
| WO2018081289A2 (en) * | 2016-10-25 | 2018-05-03 | The United States Of America, As Represented By The Secretary, Department Of Health And Human Services | Prefusion piv f immunogens and their use |
| CN107622182A (en) * | 2017-08-04 | 2018-01-23 | 中南大学 | The Forecasting Methodology and system of protein partial structurtes feature |
| CN107633159A (en) * | 2017-08-21 | 2018-01-26 | 浙江工业大学 | A kind of protein conformation space search method based on Distance conformability degree |
Non-Patent Citations (2)
| Title |
|---|
| JING X: "" Improved protein residue-residue contacts prediction using learning-to-rank"", 《2016 IEEE INTERNATIONAL CONFERENCE ON BIOINFORMATICS AND BIOMEDICINE》 * |
| 王超: ""蛋白质三级结构预测算法综述"", 《计算机学报》 * |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109658979A (en) * | 2019-01-09 | 2019-04-19 | 浙江工业大学 | A kind of Advances in protein structure prediction based on fragment library information enhancement |
| CN109658979B (en) * | 2019-01-09 | 2021-06-18 | 浙江工业大学 | Protein structure prediction method based on fragment library information enhancement |
| CN111815036A (en) * | 2020-06-23 | 2020-10-23 | 浙江工业大学 | Protein structure prediction method based on multi-residue contact map cooperative constraint |
| CN111815036B (en) * | 2020-06-23 | 2022-04-08 | 浙江工业大学 | Protein structure prediction method based on multi-residue contact map cooperative constraint |
| CN112085246A (en) * | 2020-07-22 | 2020-12-15 | 浙江工业大学 | Protein structure prediction method based on residue-to-distance constraint |
| CN112085246B (en) * | 2020-07-22 | 2024-06-21 | 浙江工业大学 | Protein structure prediction method based on residue pair distance constraint |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109086565B (en) | 2021-11-23 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109086565A (en) | A kind of Advances in protein structure prediction based on contiguity constraint between residue | |
| CN111063389A (en) | Ligand binding residue prediction method based on deep convolutional neural network | |
| CN105740626A (en) | Drug activity prediction method based on machine learning | |
| CN109101785A (en) | A kind of Advances in protein structure prediction based on secondary structure similarity selection strategy | |
| CN116438601A (en) | Predicting protein structure by sharing information between multiple sequence alignments and alignment embeddings | |
| CN109920473A (en) | A kind of metabolism group marker weight analysis universal method | |
| CN109360599A (en) | A kind of Advances in protein structure prediction based on contact residues information Crossover Strategy | |
| CN109300506A (en) | A kind of Advances in protein structure prediction based on specific range constraint | |
| US20240087686A1 (en) | Predicting complete protein representations from masked protein representations | |
| CN108647486A (en) | A kind of prediction method for three-dimensional structure of protein based on conformational diversity strategy | |
| CN112085245B (en) | Protein residue contact prediction method based on depth residual neural network | |
| Chen et al. | Evaluation of fast sample entropy algorithms on fpgas: from performance to energy efficiency | |
| CN109378035A (en) | A kind of Advances in protein structure prediction based on secondary structure dynamic select strategy | |
| CN109326320A (en) | A kind of Advances in protein structure prediction that assemblage conformation selection strategy is adaptive | |
| CN116635940A (en) | Training protein structure prediction neural networks using simplified multi-sequence alignment | |
| CN105260626B (en) | The full information Forecasting Methodology of protein structure space conformation | |
| CN109002691A (en) | A kind of Advances in protein structure prediction based on Boltzmann more new strategy | |
| Rains et al. | A Bayesian method for construction of Markov models to describe dynamics on various time-scales | |
| CN109243526B (en) | Protein structure prediction method based on specific fragment crossing | |
| CN109346128A (en) | A kind of Advances in protein structure prediction based on residue information dynamic select strategy | |
| CN116325002A (en) | Prediction of protein structure using assisted folding networks | |
| CN112686912A (en) | Acute stroke lesion segmentation method based on gradual learning and mixed samples | |
| Wu et al. | OPUS-Dom: applying the folding-based method VECFOLD to determine protein domain boundaries | |
| Geethu et al. | Improved protein real-valued distance prediction using deep residual dense network (DRDN) | |
| US20230410938A1 (en) | Predicting protein structures using protein graphs |
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 |