CN113096725A - Protein target structure optimization method and system - Google Patents
Protein target structure optimization method and system Download PDFInfo
- Publication number
- CN113096725A CN113096725A CN202110436053.8A CN202110436053A CN113096725A CN 113096725 A CN113096725 A CN 113096725A CN 202110436053 A CN202110436053 A CN 202110436053A CN 113096725 A CN113096725 A CN 113096725A
- Authority
- CN
- China
- Prior art keywords
- side chain
- structures
- optimizing
- intercepting
- dihedral angles
- 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 55
- 102000004169 proteins and genes Human genes 0.000 title claims abstract description 37
- 108090000623 proteins and genes Proteins 0.000 title claims abstract description 37
- 238000005457 optimization Methods 0.000 title claims abstract description 34
- 238000000605 extraction Methods 0.000 claims description 3
- 239000000126 substance Substances 0.000 abstract description 8
- 238000005070 sampling Methods 0.000 description 12
- 238000004364 calculation method Methods 0.000 description 10
- 239000003814 drug Substances 0.000 description 7
- 238000002474 experimental method Methods 0.000 description 7
- 229940079593 drug Drugs 0.000 description 6
- 230000003993 interaction Effects 0.000 description 5
- 238000012827 research and development Methods 0.000 description 4
- 230000000694 effects Effects 0.000 description 3
- 238000009509 drug development Methods 0.000 description 2
- 238000005259 measurement Methods 0.000 description 2
- 238000005182 potential energy surface Methods 0.000 description 2
- 125000003275 alpha amino acid group Chemical group 0.000 description 1
- 230000015572 biosynthetic process Effects 0.000 description 1
- 230000036760 body temperature Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 239000000284 extract Substances 0.000 description 1
- 238000010606 normalization Methods 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
- 238000012216 screening Methods 0.000 description 1
- 238000012163 sequencing technique Methods 0.000 description 1
- 238000004088 simulation Methods 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
- 238000003786 synthesis reaction Methods 0.000 description 1
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
- G16B15/30—Drug targeting using structural data; Docking or binding prediction
-
- 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
- G16B50/00—ICT programming tools or database systems specially adapted for bioinformatics
Landscapes
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Spectroscopy & Molecular Physics (AREA)
- Evolutionary Biology (AREA)
- Theoretical Computer Science (AREA)
- Bioinformatics & Computational Biology (AREA)
- Biotechnology (AREA)
- Biophysics (AREA)
- General Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- Chemical & Material Sciences (AREA)
- Bioethics (AREA)
- Databases & Information Systems (AREA)
- Medicinal Chemistry (AREA)
- Pharmacology & Pharmacy (AREA)
- Crystallography & Structural Chemistry (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a protein target structure optimization method and a system. The method comprises the following steps: extracting a target structure from a protein target database; the target structure comprises a main chain structure and a plurality of side chain structures; the main chain structure is fixed; sequentially carrying out three-degree-of-freedom rotation on a plurality of dihedral angles of a plurality of side chain structures according to a set sequence, and judging whether the number of the rotated side chain structures reaches the preset number of structures; if not, continuing to perform three-degree-of-freedom rotation; if so, optimizing and intercepting the rotated side chain structure by adopting a DFTB method; and after intercepting, performing three-degree-of-freedom rotation on the residual dihedral angles, and optimizing and intercepting by adopting a DFTB method after each dihedral angle is rotated once until all the dihedral angles of all the side chain structures are completely searched. The invention provides an accurate and reliable target structure through a reliable conformation search method and structural optimization of quantum chemical computation.
Description
Technical Field
The invention relates to the technical field of protein target structures, in particular to a protein target structure optimization method and system.
Background
Modern drug development must rely on relevant computational software, whose role is reflected in: 1. generating all possible molecular structures by computer; 2. modifying the generated molecules; 3. all molecules are screened through calculation simulation, and a small number of molecules with calculation indexes meeting requirements are selected from a plurality of candidates, so that the next synthesis experiment stage can be carried out. The above three aspects involve millions of molecules, and therefore must be implemented on a computing platform through software. This calculation must be screened by calculating the interaction of the drug molecule with the relevant protein target.
However, the side chain structure information of the target structure extracted from the protein database by the existing method is incomplete. This is because the structure in the protein database is generally obtained by an experimental method, and the measurement accuracy of the experimental method can well reflect the main chain structure, whereas the accuracy requirement of obtaining the side chain structure for the experiment is higher (less than 1.5A), and most cases are difficult to achieve. Therefore, the side chain structure can be obtained only with the help of a calculation method, and the commonly used methods such as a molecular force field and the like have poor precision and universality, so that the reliability of the given side chain structure is low.
The calculation of the interaction between the drug and the target by using the protein target with unreliable side chain structure is an important factor causing the deviation of the calculation result. The poor screening caused by the deviation is a significant reason for the high development cost of the medicine.
The existing method extracts a target structure from a protein database, and the structure in the protein database is mainly obtained by an experimental method. The resolution requirements of the measurement of the main chain and the side chain structure on the experiment are different, the main chain is 4.5-6 angstroms, and the resolution of less than 2.5 angstroms is required for distinguishing the form and the direction of the side chain, so the main chain structure obtained by the experiment is relatively reliable, and the side chain structure is usually obtained by the aid of a calculation method.
The disadvantages of the commonly used calculation methods are represented in two aspects, namely, the calculation accuracy of the energy is not high, and the sampling method is not reliable.
Disclosure of Invention
The invention aims to provide a protein target structure optimization method and a system, which can provide an accurate and reliable target structure through a reliable conformation search method and structural optimization of quantum chemical computation.
In order to achieve the purpose, the invention provides the following scheme:
a protein target structure optimization method comprises the following steps:
extracting a target structure from a protein target database; the target structure comprises a main chain structure and a plurality of side chain structures; the main chain structure is fixed;
sequentially carrying out three-degree-of-freedom rotation on a plurality of dihedral angles of a plurality of side chain structures according to a set sequence;
judging whether the number of the rotated side chain structures reaches the preset number of structures or not;
if not, continuing to perform three-degree-of-freedom rotation;
if so, optimizing and intercepting the rotated side chain structure by adopting a DFTB method;
and after intercepting, performing three-degree-of-freedom rotation on the residual dihedral angles, and optimizing and intercepting by adopting a DFTB method after each dihedral angle is rotated once until all the dihedral angles of all the side chain structures are completely searched.
Further, the structure of the top N of the energy sequence is intercepted.
Further, structures with energy ranges within 8kcal are intercepted.
Further, the number of the preset structures is 6561.
Further, the rotation period is 120 °.
Further, before sequentially performing three-degree-of-freedom rotation on a plurality of dihedral angles of a plurality of side chain structures according to a set sequence, the method further includes:
the side chains are numbered as well as the dihedral angles of the side chains.
The invention also provides a protein target structure optimization system, which comprises:
the target structure extraction module is used for extracting a target structure from a protein target database; the target structure comprises a main chain structure and a plurality of side chain structures; the main chain structure is fixed;
the first rotation module is used for sequentially carrying out three-degree-of-freedom rotation on a plurality of dihedral angles of a plurality of side chain structures according to a set sequence;
the judging module is used for judging whether the number of the rotated side chain structures reaches the preset number of structures;
the optimizing and intercepting module is used for optimizing and intercepting the rotated side chain structure by adopting a DFTB method;
and the second rotation and optimization interception module is used for performing three-degree-of-freedom rotation on the residual dihedral angles, and optimizing and intercepting each dihedral angle by adopting a DFTB method once rotation until all dihedral angles of all side chain structures are completely searched.
According to the specific embodiment provided by the invention, the invention discloses the following technical effects:
the protein target structure optimization method provided by the invention comprises the following steps: extracting a target structure from a protein target database; the target structure comprises a main chain structure and a plurality of side chain structures; the main chain structure is fixed; sequentially carrying out three-degree-of-freedom rotation on a plurality of dihedral angles of a plurality of side chain structures according to a set sequence, and judging whether the number of the rotated side chain structures reaches the preset number of structures; if not, continuing to perform three-degree-of-freedom rotation; if so, optimizing and intercepting the rotated side chain structure by adopting a DFTB method; and after intercepting, performing three-degree-of-freedom rotation on the residual dihedral angles, and optimizing and intercepting by adopting a DFTB method after each dihedral angle is rotated once until all the dihedral angles of all the side chain structures are completely searched. The invention provides an accurate and reliable target structure through a reliable conformation search method and structural optimization of quantum chemical computation, and better accords with the real situation when the interaction between a drug molecule and a target is computed. Through the mode of improving the productivity effect of the initial link, the research and development cost is reduced, and the research and development speed is accelerated.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings needed to be used in the embodiments will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art to obtain other drawings without inventive exercise.
FIG. 1 is a flow chart of a method for optimizing a protein target structure according to an embodiment of the present invention;
FIG. 2 is a schematic numbering of side chain dihedral angles in accordance with embodiments of the present invention;
fig. 3 is a schematic diagram of structure optimization and structure search (structure sampling).
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
The invention aims to provide a protein target structure optimization method and a system, which can provide an accurate and reliable target structure through a reliable conformation search method and structural optimization of quantum chemical computation.
In order to make the aforementioned objects, features and advantages of the present invention comprehensible, embodiments accompanied with figures are described in further detail below.
As shown in FIG. 1, the method for optimizing the structure of the protein target disclosed by the invention comprises the following steps:
step 101: extracting a target structure from a protein target database; the target structure comprises a main chain structure and a plurality of side chain structures; the main chain structure is fixed.
Step 102: and sequentially carrying out three-degree-of-freedom rotation on a plurality of dihedral angles of a plurality of side chain structures according to a set sequence, wherein the rotation period is 120 degrees.
Step 103: judging whether the number of the rotated side chain structures reaches the preset number of structures or not; if not, go to step 102, and if yes, go to step 104.
Step 104: and optimizing and intercepting the rotated side chain structure by adopting a DFTB method. And intercepting the structure of N before energy sequencing or intercepting the structure with the energy range within 8 kcal.
Step 105: and after intercepting, performing three-degree-of-freedom rotation on the residual dihedral angles, and optimizing and intercepting by adopting a DFTB method after each dihedral angle is rotated once until all the dihedral angles of all the side chain structures are completely searched.
Before three-degree-of-freedom rotation is sequentially performed on a plurality of dihedral angles of a plurality of side chain structures according to a set sequence, the method further comprises the following steps: the side chains are numbered as well as the dihedral angles of the side chains.
The above method will be described in detail below:
1. target structures are extracted from existing protein target databases. (extracting the target structure, i.e., the three-dimensional coordinates of each atom in the target from the target database)
2. The main chain structure is fixed, the main chain structure in a target point database is reliable, and the accuracy of the side chain structure is insufficient, so that the step aims to fix the three-dimensional coordinates of the main chain atoms, and the subsequent sampling and optimization are only carried out aiming at the side chain. The fixed atoms adopt constraint parameters in an input file, and the realization mode is that a Constraintst { } command is used in the input file of the DFTB, and the sequence numbers corresponding to the fixed atoms are filled in brackets.
3. The side chains are numbered with side chain dihedral angles, where the numbering is that in fig. 2, and each dihedral angle is named. First, a rotation of three degrees of freedom is made for the 1 st dihedral angle χ (1,1) of the 1 st side chain as shown in FIG. 2. Then, the chi (2,1) and the chi (3,1) … … are sequentially rotated, so that the target region usually contains dozens of amino acid side chains, and the rotation to the chi (8,1) can obtain 6561 structures. The DFTB method was used for structure optimization for these structures. The interception energy range is within 8kcal, or the energy sequences of the first N structures, and two conditions are satisfied. The numerical value of N is determined by a user, 1000 is recommended to be selected, structural diversity can be guaranteed, and the calculated amount can be controlled within a reasonable range.
4. Each subsequent selection (here the selection is done by a program, operating on each dihedral angle one by one in the order specified in the previous step) of 1 dihedral angle is rotated with 3 degrees of freedom. The rotation is a sampling of the structure, wherein the concepts and relationships of sampling, optimization, and structure search are detailed in fig. 3. For example, χ (9,1) is selected to rotate with 3 degrees of freedom, the number of structures is expanded by three times, and the obtained 3 × N structures are subjected to DFTB optimization, wherein the interception criterion is the same as that in the step 3. In this way, the χ (1, n) search for all target side chains was completed. )
5. Searching for the 2 nd dihedral angles χ (1, 2) to χ (N,2) of each side chain in the above manner, (according to the relevant chemical theory, the structure is a C-C bond structure, the rotation period is about 120 °, and 120 ° and 240 °, namely x, x +120, and x +240, are respectively added on the basis of the initial angle x of the dihedral angle, namely, three angles of x, x +120, and x +240, namely, "structure sampling", the "search" of the structure is the final result of "structure sampling" and "structure optimization", which is detailed in fig. 3), rotating three degrees of freedom each time, expanding the number of the structure by 3 times, optimizing the structure by using a DFTB method, and selecting a low-energy stable structure with energy within 8kcal or sorted in the top N.
6. Following the above procedure, a series of low energy conformations are obtained by searching all dihedral angles of all side chains (sampling the rotational degrees of freedom of each dihedral angle in turn, i.e. the original angle value x, plus 120 and 240 degrees respectively, the search and optimization meaning being illustrated in fig. 3).
Wherein P isiIs the probability, ε, of a quantum state iiIs the energy of the quantum state i, k is the boltzmann constant, T is the system temperature and M is the number of quantum states the system has. PiThe probability that the structure with the energy sequence i exists at the temperature T in the result output in the step 5 is shown, the environment where the drug molecules act is the body temperature of the human body, and the T is set to be 37 ℃; epsiloniOutputting the energy of the ith structure in the result for the step 5; k is Boltzmann constant (physical constant K is 1.380649 × 10-23J/K); the denominator part of the expression serves as a normalization parameter; the significance of the whole formula is that the result output in the step 5 shows that at any temperature, the probability of each structure is exponentially reduced along with the increase of the energy of the structure, and at the temperature of human body environment (37 ℃), the real molecular structure falls into a structure set with the energy ordering within 8kcal/molThe probability of a sum exceeds 99.9%. Structures other than those resulting from step 5 are likely to be present with negligible probability due to their higher energy.
FIG. 3, the black curve represents the potential energy surface, the real structure of the molecule is at the local minimum point of the potential energy surface, the goal of the invention is to find out all the local minimum values in a certain energy range (the energy upper limit is generally selected between 3-8kcal according to the requirement); the upper black dots represent the numerical value of a certain dihedral angle in the initial structure; the dashed arrow represents a structure optimization process, the optimization process is completed by a DFTB program, and the purpose is to find local minimum values of energy near an initial structure, but the local minimum values of other areas cannot be obtained by the structure optimization, so that sampling operation is required; the solid arrows represent sampling operations, and according to the relevant chemical theory, such dihedral angles typically contain 3 local minima in the range 0-360 °, so that the dihedral angles in the initial structure are added by 120 ° and 240 °, respectively, in order to make the sampling points fall into other regions containing local minima. The operation of finding out the local minimum value through sampling and optimization is the structure search.
Drug development (chemical and biological) must be screened by calculating the interaction of drug molecules with the relevant protein targets. However, the target structure side chain information extracted from the protein database by the existing method is missing, which is an important factor causing the deviation of the calculation result. The target structure obtained by the invention provides an accurate and reliable target structure through a reliable conformation search method and structural optimization of quantum chemical computation, and better accords with the real situation when the interaction between a drug molecule and the target is computed. Through the mode of improving the productivity effect of the initial link, the research and development cost is reduced, and the research and development speed is accelerated.
The invention also provides a protein target structure optimization system, which comprises:
the target structure extraction module is used for extracting a target structure from a protein target database; the target structure comprises a main chain structure and a plurality of side chain structures; the main chain structure is fixed.
The first rotation module is used for sequentially carrying out three-degree-of-freedom rotation on a plurality of dihedral angles of a plurality of side chain structures according to a set sequence;
the judging module is used for judging whether the number of the rotated side chain structures reaches the preset number of structures;
and the optimization interception module is used for optimizing and intercepting the rotated side chain structure by adopting a DFTB method.
And the second rotation and optimization interception module is used for performing three-degree-of-freedom rotation on the residual dihedral angles, and optimizing and intercepting each dihedral angle by adopting a DFTB method once rotation until all dihedral angles of all side chain structures are completely searched.
The embodiments in the present description are described in a progressive manner, each embodiment focuses on differences from other embodiments, and the same and similar parts among the embodiments are referred to each other. For the system disclosed by the embodiment, the description is relatively simple because the system corresponds to the method disclosed by the embodiment, and the relevant points can be referred to the method part for description.
The principles and embodiments of the present invention have been described herein using specific examples, which are provided only to help understand the method and the core concept of the present invention; meanwhile, for a person skilled in the art, according to the idea of the present invention, the specific embodiments and the application range may be changed. In view of the above, the present disclosure should not be construed as limiting the invention.
Claims (7)
1. A protein target structure optimization method is characterized by comprising the following steps:
extracting a target structure from a protein target database; the target structure comprises a main chain structure and a plurality of side chain structures; the main chain structure is fixed;
sequentially carrying out three-degree-of-freedom rotation on a plurality of dihedral angles of a plurality of side chain structures according to a set sequence;
judging whether the number of the rotated side chain structures reaches the preset number of structures or not;
if not, continuing to perform three-degree-of-freedom rotation;
if so, optimizing and intercepting the rotated side chain structure by adopting a DFTB method;
and after intercepting, performing three-degree-of-freedom rotation on the residual dihedral angles, and optimizing and intercepting by adopting a DFTB method after each dihedral angle is rotated once until all the dihedral angles of all the side chain structures are completely searched.
2. The method for optimizing the structure of a protein target according to claim 1, wherein the structure of N before the energy ordering is truncated.
3. The method for structural optimization of a protein target according to claim 1, wherein structures with energy ranging from 8kcal are truncated.
4. The method for optimizing protein target structure according to claim 1, wherein the number of the predetermined structures is 6561.
5. The method for structural optimization of a protein target according to claim 1, wherein the rotation period is 120 °.
6. The method for optimizing the structure of a protein target according to claim 1, wherein before sequentially performing three-degree-of-freedom rotation on a plurality of dihedral angles of a plurality of side chain structures according to a set sequence, the method further comprises:
the side chains are numbered as well as the dihedral angles of the side chains.
7. A protein target structure optimization system, comprising:
the target structure extraction module is used for extracting a target structure from a protein target database; the target structure comprises a main chain structure and a plurality of side chain structures; the main chain structure is fixed;
the first rotation module is used for sequentially carrying out three-degree-of-freedom rotation on a plurality of dihedral angles of a plurality of side chain structures according to a set sequence;
the judging module is used for judging whether the number of the rotated side chain structures reaches the preset number of structures;
the optimizing and intercepting module is used for optimizing and intercepting the rotated side chain structure by adopting a DFTB method;
and the second rotation and optimization interception module is used for performing three-degree-of-freedom rotation on the residual dihedral angles, and optimizing and intercepting each dihedral angle by adopting a DFTB method once rotation until all dihedral angles of all side chain structures are completely searched.
Priority Applications (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110436053.8A CN113096725A (en) | 2021-04-22 | 2021-04-22 | Protein target structure optimization method and system |
| AU2021102886A AU2021102886A4 (en) | 2021-04-22 | 2021-05-27 | Method for Optimizing Protein Target Structure and a System Thereof |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110436053.8A CN113096725A (en) | 2021-04-22 | 2021-04-22 | Protein target structure optimization method and system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113096725A true CN113096725A (en) | 2021-07-09 |
Family
ID=76679498
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110436053.8A Pending CN113096725A (en) | 2021-04-22 | 2021-04-22 | Protein target structure optimization method and system |
Country Status (2)
| Country | Link |
|---|---|
| CN (1) | CN113096725A (en) |
| AU (1) | AU2021102886A4 (en) |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20020072864A1 (en) * | 1999-08-31 | 2002-06-13 | Emmanuel Lacroix | Computer-based method for macromolecular engineering and design |
| US20170329892A1 (en) * | 2016-05-10 | 2017-11-16 | Accutar Biotechnology Inc. | Computational method for classifying and predicting protein side chain conformations |
-
2021
- 2021-04-22 CN CN202110436053.8A patent/CN113096725A/en active Pending
- 2021-05-27 AU AU2021102886A patent/AU2021102886A4/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20020072864A1 (en) * | 1999-08-31 | 2002-06-13 | Emmanuel Lacroix | Computer-based method for macromolecular engineering and design |
| US20170329892A1 (en) * | 2016-05-10 | 2017-11-16 | Accutar Biotechnology Inc. | Computational method for classifying and predicting protein side chain conformations |
Also Published As
| Publication number | Publication date |
|---|---|
| AU2021102886A4 (en) | 2021-07-15 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Igashov et al. | Equivariant 3D-conditional diffusion model for molecular linker design | |
| Faro et al. | The exact online string matching problem: A review of the most recent results | |
| Martin et al. | Assessment of comparative modeling in CASP2 | |
| CN108804869B (en) | Molecular structure and chemical reaction energy function construction method based on neural network | |
| Feng et al. | Computational chemical synthesis analysis and pathway design | |
| Li et al. | Protein loop modeling using deep generative adversarial network | |
| Oliveira et al. | Fitting isochrones to open cluster photometric data-III. Estimating metallicities from UBV photometry | |
| CN115017268B (en) | Heuristic log extraction method and system based on tree structure | |
| CN113223608A (en) | Method and system for predicting three-dimensional structure of protein by double-layer mutual reinforcement | |
| CN110008482A (en) | Text handling method, device, computer readable storage medium and computer equipment | |
| Chakraborty et al. | Codit: Code editing with tree-based neural machine translation | |
| CN114913938A (en) | Small molecule generation method, equipment and medium based on pharmacophore model | |
| Den Hartogh et al. | Barium stars as tracers of s-process nucleosynthesis in AGB stars-II. Using machine learning techniques on 169 stars | |
| CN113096725A (en) | Protein target structure optimization method and system | |
| CN107526939B (en) | Rapid alignment method for small molecular structure | |
| Täubig et al. | PAST: fast structure-based searching in the PDB | |
| Yu et al. | An efficient exact algorithm for the motif stem search problem over large alphabets | |
| CN112699018A (en) | Software defect positioning method based on software defect correlation analysis | |
| Rhalem et al. | An efficient and rapid method for detection of mutations in deoxyribonucleic acid-sequences | |
| CN113628696B (en) | Medicine connection graph score prediction method and device based on double-graph convolution fusion model | |
| CN111124366B (en) | Demand tracking recovery method based on information retrieval | |
| CN114398069A (en) | Method and system for identifying accurate version of public component library based on cross fingerprint analysis | |
| CN116030883A (en) | Protein structure prediction method, device, equipment and storage medium | |
| CN114360637A (en) | Protein-ligand affinity evaluation method based on graph attention network | |
| Hu et al. | Cerebra: a computationally efficient framework for accurate protein structure prediction |
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 |