Protein-protein docking method and device, intelligent equipment and storage medium

Abstract

The invention is suitable for the technical field of biological information, and provides a protein-protein docking method and device, intelligent equipment and a storage medium, and the method comprises the following steps: carrying out global search on a surface space of a receptor protein, and determining a plurality of candidate docking postures of the receptor protein and a ligand protein; optimizing the plurality of candidate docking postures according to a preset optimization algorithm, and determining a target docking posture; the target docking postures are clustered; and based on the clustering result, determining the optimal docking posture of the receptor protein and the ligand protein. According to the method, the binding conformation can be efficiently searched, and the protein-protein docking efficiency and success rate are improved.

Description

Technical Field

[0001] The present application relates to the field of bioinformatics, and in particular to a protein-protein docking method, apparatus, intelligent device and storage medium. Background Art

[0002] Protein-protein interactions play an important role in biological processes such as cell signaling, metabolic regulation, gene expression regulation, and immune response. In addition to obtaining the structure of protein complexes through traditional experimental methods (such as X-ray crystallography and nuclear magnetic resonance), protein-protein docking technology can also be used. Protein-protein docking is a key research method in computational biology, which aims to explore the interactions between proteins and their complex structures. With the continuous development of technology, it has become possible to use computers to perform molecular simulations of protein docking and thus predict the structure of protein complexes.

[0003] However, protein-protein docking is a challenging task. The main difficulty lies in the extremely large conformational space of proteins. Searching for possible binding conformations requires traversing a huge space. Therefore, how to efficiently search for binding conformations and improve the efficiency and success rate of protein-protein docking is a problem that needs to be solved. Summary of the invention

[0004] The embodiments of the present application provide a protein-protein docking method, apparatus, intelligent device and storage medium, which can efficiently search for binding conformations, thereby improving the efficiency and success rate of protein-protein docking.

[0005] In a first aspect, the present invention provides a protein-protein docking method, the method comprising:

[0006] Performing a global search on the surface space of the receptor protein to determine several candidate docking poses of the receptor protein and the ligand protein;

[0007] Optimizing the candidate docking postures according to a preset optimization algorithm to determine a target docking posture;

[0008] Clustering the target docking postures;

[0009] Based on the clustering results, the optimal docking posture of the receptor protein and the ligand protein is determined.

[0010] In a possible implementation of the first aspect, the step of performing a global search on the surface space of the receptor protein to determine several candidate docking postures of the receptor protein and the ligand protein includes:

[0011] The FFT algorithm is used to perform a global search of the receptor protein surface space to generate multiple binding conformations;

[0012] The binding conformations are screened according to preset screening conditions to determine several candidate docking postures.

[0013] In a possible implementation manner of the first aspect, the step of optimizing the plurality of candidate docking postures by the preset optimization algorithm to determine a target docking posture includes:

[0014] Based on the several candidate docking poses, dividing the surface space of the receptor protein into regions;

[0015] According to the preset optimization algorithm, a local search is performed on the candidate docking postures in each divided area to determine the target docking posture.

[0016] In a possible implementation of the first aspect, the candidate docking postures include ligand protein conformations, and the step of dividing the surface space of the receptor protein into regions based on the candidate docking postures includes:

[0017] Clustering the plurality of candidate docking postures based on the position of the ligand protein conformation to obtain a plurality of classes of candidate docking postures;

[0018] According to the number of classes of the candidate docking poses, the surface space of the receptor protein is divided into regions, wherein each region contains one class of the candidate docking poses.

[0019] In a possible implementation manner of the first aspect, the step of performing a local search on candidate docking postures in each divided area according to the preset optimization algorithm to determine a target docking posture includes:

[0020] The candidate docking postures in each region are iteratively optimized through the differential evolution algorithm;

[0021] Based on the result of the iterative optimization, a target docking posture in each region is determined.

[0022] In a possible implementation manner of the first aspect, the step of iteratively optimizing the candidate docking postures in each region by using a differential evolution algorithm includes:

[0023] It is beneficial to use a preset evaluation function to evaluate the fitness of the candidate docking postures in the area and determine the fitness value of the candidate docking postures in the area;

[0024] The candidate docking posture is iteratively optimized based on the fitness value and a preset iterative strategy until a preset termination condition is met, and the iterative optimization ends. The preset iterative strategy includes crossover, mutation and selection.

[0025] In a possible implementation manner of the first aspect, the step of clustering the target docking postures includes:

[0026] A hierarchical clustering algorithm is used to merge and cluster the target docking postures to obtain several clusters of target docking postures.

[0027] In a second aspect, an embodiment of the present application provides a protein-protein docking device, the device comprising:

[0028] A first determination unit is used to perform a global search on the surface space of the receptor protein to determine a number of candidate docking postures of the receptor protein and the ligand protein;

[0029] A second determination unit is used to optimize the plurality of candidate docking postures according to a preset optimization algorithm to determine a target docking posture;

[0030] A cluster analysis unit, used for clustering the target docking postures;

[0031] A docking posture determination unit is used to determine the optimal docking posture of the receptor protein and the ligand protein based on the clustering result.

[0032] In a third aspect, an embodiment of the present application provides an intelligent device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, the protein-protein docking method as described in the first aspect above is implemented.

[0033] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the protein-protein docking method as described in the first aspect above is implemented.

[0034] In a fifth aspect, an embodiment of the present application provides a computer program product. When the computer program product is run on a smart device, the smart device executes the protein-protein docking method as described in the first aspect above.

[0035] In an embodiment of the present application, a global search is performed on the surface space of the receptor protein to determine several candidate docking postures of the receptor protein and the ligand protein, that is, several potential binding sites are determined, and then the several candidate docking postures are optimized according to a preset optimization algorithm, and the potential binding sites are further optimized and screened based on the results of the global search to determine the target docking posture, which can effectively improve the search efficiency, and then the target docking postures are clustered, and based on the results of the clustering, the optimal docking posture of the receptor protein and the ligand protein is determined, which can effectively improve the success rate of protein-protein docking. BRIEF DESCRIPTION OF THE DRAWINGS

[0036] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative labor.

[0037] Figure 1 is a flowchart of the protein-protein docking method provided in the embodiments of the present application;

[0038] Figure 2 is a specific implementation flow chart of step S101 of the protein-protein docking method provided in an embodiment of the present application;

[0039] Figure 3 is a schematic diagram of candidate docking postures obtained by global search in the protein-protein docking method provided in an embodiment of the present application;

[0040] Figure 4 is a specific implementation flow chart of step S102 in the protein-protein docking method provided in an embodiment of the present application;

[0041] Figure 5 It is a specific implementation flow chart of iteratively optimizing the candidate docking postures in each region in the protein-protein docking method provided in the embodiment of the present application;

[0042] Figure 6 is a schematic diagram of the predicted complex structure in the protein-protein docking method provided in the examples of the present application;

[0043] Figure 7 is a structural block diagram of a protein-protein docking device provided in an embodiment of the present application;

[0044] Figure 8 It is a schematic diagram of a smart device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0045] In the following description, specific details such as specific system structures, technologies, etc. are provided for the purpose of illustration rather than limitation, so as to provide a thorough understanding of the embodiments of the present application. However, it should be clear to those skilled in the art that the present application may also be implemented in other embodiments without these specific details. In other cases, detailed descriptions of well-known systems, devices, circuits, and methods are omitted to prevent unnecessary details from obstructing the description of the present application.

[0046] It should be understood that when used in the present specification and the appended claims, the term "comprising" indicates the presence of described features, wholes, steps, operations, elements and / or components, but does not exclude the presence or addition of one or more other features, wholes, steps, operations, elements, components and / or combinations thereof.

[0047] It should also be understood that the term “and / or” used in the specification and appended claims refers to any and all possible combinations of one or more of the associated listed items, and includes these combinations.

[0048] As used in the specification and appended claims of this application, the term "if" can be interpreted as "when" or "uponce" or "in response to determining" or "in response to detecting", depending on the context. Similarly, the phrase "if it is determined" or "if [described condition or event] is detected" can be interpreted as meaning "uponce it is determined" or "in response to determining" or "uponce [described condition or event] is detected" or "in response to detecting [described condition or event]", depending on the context.

[0049] In addition, in the description of the present application specification and the appended claims, the terms "first", "second", "third", etc. are only used to distinguish the descriptions and cannot be understood as indicating or implying relative importance.

[0050] References to "one embodiment" or "some embodiments" etc. described in the specification of this application mean that one or more embodiments of the present application include specific features, structures or characteristics described in conjunction with the embodiment. Therefore, the statements "in one embodiment", "in some embodiments", "in some other embodiments", "in some other embodiments", etc. that appear in different places in this specification do not necessarily refer to the same embodiment, but mean "one or more but not all embodiments", unless otherwise specifically emphasized in other ways. The terms "including", "comprising", "having" and their variations all mean "including but not limited to", unless otherwise specifically emphasized in other ways.

[0051] It should be understood that the protein-protein docking method provided in the embodiments of the present application is applicable to various types of smart devices that need to simulate the docking between proteins, which may specifically include smart devices such as mobile phones, tablet computers, wearable devices, laptop computers, and desktop computers. The embodiments of the present application do not impose any restrictions on the specific types of smart devices.

[0052] Figure 1 The implementation process of the protein-protein docking method provided in the embodiment of the present application is shown, and the method flow includes steps S101 to S104. The specific implementation principle of each step is as follows:

[0053] Step S101: performing a global search on the surface space of the receptor protein to determine several candidate docking postures of the receptor protein and the ligand protein.

[0054] Before protein-protein docking, the fixed protein and the mobile protein are determined, where the fixed protein is marked as the receptor protein and the mobile protein is marked as the ligand protein. The docking posture refers to the relative position and direction of the receptor protein and the ligand protein when they bind to each other. The ligand protein moves in the surface space of the receptor protein to search for the best docking posture.

[0055] In protein-protein docking, the conformational space of proteins is usually very large, and it is difficult to achieve global coverage by directly sampling the conformational space through evolutionary algorithms. In this implementation, a global search is first performed on the surface space of the receptor protein to determine potential binding sites.

[0056] As a possible implementation of this application, Figure 2 The specific implementation process of step S101 in the protein-protein docking method provided in the embodiment of the present application is shown, and is described in detail as follows:

[0057] A1: Use the FFT algorithm to perform a global search of the surface space of the receptor protein to generate multiple binding conformations.

[0058] FFT (Fast Fourier Transformation) is an efficient algorithm for calculating discrete Fourier transform (DFT) and its inverse transform. The FFT-based search method can quickly search for potential binding conformations (up to 10^10) on a global scale, avoiding falling into local optimal solutions, making the potential binding sites searched more comprehensive, and helping to improve the accuracy of docking. In the FFT-based global search algorithm, the receptor protein and the ligand protein are regarded as rigid bodies, and the degrees of freedom are limited to 6 degrees of freedom, including three-dimensional translation and three-dimensional rotation. In this embodiment, three-dimensional translation refers to the movement of all atomic coordinates of the ligand protein, and three-dimensional rotation refers to the rotation of the ligand protein as a whole.

[0059] In this embodiment, the receptor protein molecule remains fixed and projected into a three-dimensional grid of N×N×N size, and the grid is discretized according to the geometry, electrostatic and hydrophobic properties of the receptor protein molecule; the ligand protein molecule rotates around the receptor protein molecule, and after each rotation, the ligand protein molecule will be reprojected into the three-dimensional grid, and the ligand protein molecule is also discretized according to its geometry, electrostatic and hydrophobic properties. After the grid discretization, the three-dimensional grid data of the receptor protein molecule and the ligand protein molecule are obtained, and the three-dimensional grid data includes information on geometry, electrostatic and hydrophobic properties. Specifically, after discretization, each grid point will represent the characteristics of the molecule at that point, such as whether it is occupied by an atom, the size of the electrostatic potential and hydrophobicity. These discretized data will be used for subsequent fast Fourier transform (FFT) calculations to efficiently evaluate different docking postures in global searches. Grid discretization can simplify the calculation of complex molecular geometries and their interactions, which is convenient for intelligent device processing.

[0060] A2: Screening the binding conformations according to preset screening conditions to determine several candidate docking postures.

[0061] In some embodiments, conformations can be preliminarily screened by conditions such as geometric matching and surface contact, a preset number of binding conformations can be retained, the retained binding conformations after screening can be converted to Cartesian coordinate space, and the retained binding conformations after screening can be scored by using site constraint information and a fast lookup atom pair scoring function. The retained binding conformations can be sorted by an accurate distance-related atom pair scoring function, and candidate docking postures can be determined based on the sorting results.

[0062] In one possible embodiment, unreasonable binding conformations are filtered out by the interaction energy between proteins to determine candidate docking postures, and one binding conformation corresponds to one candidate docking posture. The lower the interaction energy, the more stable the binding conformation. The binding conformations retained after screening are sorted based on the size of the interaction energy, and a certain number of binding conformations are retained, for example, the top 1000 binding conformations are retained to obtain a number of candidate docking postures.

[0063] The interaction energy between proteins is represented by the comprehensive correlation function, and FFT is used to accelerate the calculation of the correlation function. The correlation function is represented by the following calculation formula (1):

[0064] S(t)=∑ v∈V R(v)L(v+o)=IFFT[FFT[R(v)]*FFT[L(v)]] (1)

[0065] Among them, R represents the discrete function of the receptor protein, L represents the discrete function of the ligand protein, v represents the coordinate in the three-dimensional grid, o represents the translation of the ligand protein relative to the receptor protein, V represents the entire three-dimensional grid, * represents the complex conjugate operator, and IFFT represents the inverse FFT.

[0066] The complex conjugate operator refers to taking the conjugate complex number of a complex number, that is, the real part is the same and the imaginary part is opposite. In the above formula (1), R and L are transformed by FFT respectively to obtain their frequency domain representations, and then the frequency domain signal of R is conjugated to obtain the conjugate frequency domain signal. By taking the conjugate of one signal when multiplying in the frequency domain, we can efficiently calculate the correlation in the time domain in the frequency domain, and finally obtain the correlation in the time domain, that is, S(t), through IFFT transformation.

[0067] Direct calculation of the correlation function requires considering all possible relative displacements, a total of N 3 Each relative displacement requires N 3 multiplication and addition operations, so the total computational complexity is O(N 6 After FFT transformation, the correlation function S(t) can be obtained by simply multiplying the two functions and then performing inverse FFT, and the amount of calculation can be reduced to O(N 3 ln 3 ), thereby achieving efficient search.

[0068] In the examples of the present application, a global search of the surface space of the receptor protein is performed based on the FFT algorithm to obtain a large number of binding conformations, and unreasonable binding conformations are filtered out through the interaction capabilities between proteins. Finally, a certain number of binding conformations are retained for subsequent optimization steps.

[0069] Step S102: Optimizing the plurality of candidate docking postures according to a preset optimization algorithm to determine a target docking posture.

[0070] The target docking posture is the docking posture after the candidate docking posture is optimized.

[0071] In this embodiment, based on the global search in step S101, a set of candidate docking postures can be obtained. Figure 3 As shown in the figure, area ① represents the receptor protein, and the particles around it represent the center of mass of the ligand protein, which can be regarded as a docking posture.

[0072] like Figure 3 As shown in Figure 1, the binding sites are mainly distributed in several areas on the receptor surface, and also include some scattered points. In view of this, in order to improve the efficiency of subsequent local optimization operations, the surface space of the receptor protein can be divided into regions.

[0073] As a possible implementation of this application, Figure 4 A specific implementation process of step S102 in the protein-protein docking method provided in the embodiment of the present application is shown, and is described in detail as follows:

[0074] B1: Based on the several candidate docking poses, the surface space of the receptor protein is divided into regions.

[0075] In one possible embodiment, the candidate docking posture includes a ligand protein conformation, and based on the position of the ligand protein conformation, the several candidate docking postures are clustered to obtain several classes of candidate docking postures; according to the number of classes of the candidate docking postures, the surface space of the receptor protein is divided into regions, wherein each region contains one class of the candidate docking postures.

[0076] The above clustering can adopt the first clustering algorithm. The position of the candidate docking posture is specifically the position of the ligand protein in the candidate docking posture. The first clustering algorithm is a clustering algorithm based on partitioning. For example, the K-means algorithm can be used to cluster the positions of the candidate docking postures into 10 categories. That is, the positions of the ligand proteins in the three-dimensional space are clustered, and the center of mass of the ligand proteins is used to represent their positions in the three-dimensional space. Based on the clustering results, the surface space of the receptor protein is divided into regions. For example, if it is clustered into 10 categories, the surface space of the receptor protein is divided into 10 regions. The specific process of using the K-means algorithm is not repeated here.

[0077] B2: According to the preset optimization algorithm, a local search is performed on the candidate docking postures in each divided area to determine a target docking posture, which is the optimal docking posture in the area.

[0078] In this embodiment, the surface space of the receptor protein is divided into regions based on the position of the ligand protein conformation in the candidate docking posture, and then a local search is performed on the candidate docking posture in each divided region according to a preset optimization algorithm. The global search and local optimization are combined to ensure the comprehensiveness of the search and improve the efficiency of the search, while also improving the accuracy of protein-protein docking predictions.

[0079] In a possible implementation, the preset optimization algorithm includes a differential evolution algorithm (DE), and the candidate docking postures in each region are iteratively optimized through the differential evolution algorithm, and the optimal docking posture in each region is determined based on the result of the iterative optimization.

[0080] As a possible implementation of this application, Figure 5A specific implementation process of the step of iteratively optimizing the candidate docking postures in each region by using a differential evolution algorithm in the protein-protein docking method provided in an embodiment of the present application is shown, and is described in detail as follows:

[0081] C1: It is beneficial for the preset evaluation function to perform fitness evaluation on the candidate docking postures in the region and determine the fitness value of the candidate docking postures in the region. The preset evaluation function can be a DFIRE function. The preset evaluation function is used to calculate the fitness value of each individual (the binding conformation corresponding to the candidate docking posture), which reflects the degree of pros and cons of the individual as a solution. The fitness value is also used to identify the docking energy. The lower the fitness value, the lower the docking energy, and the lower the docking energy, the stronger the stability of the docking posture.

[0082] C2: Iteratively optimize the candidate docking posture based on the fitness value and a preset iterative strategy until a preset termination condition is met, and the iterative optimization ends. The preset iterative strategy includes crossover, mutation, and selection.

[0083] Based on the DE algorithm to simulate the evolutionary process in nature, through crossover, mutation and selection strategies, the individuals in the population are continuously evolved to obtain the optimal solution. In general, the DE algorithm will randomly generate an initial population and iteratively optimize the individuals in the initial population. It is worth emphasizing that the initial population in this application is not randomly generated, but is obtained based on the global search in step S101, which can ensure that the initial state of the population is closer to the optimal solution, which is conducive to improving the efficiency of local search and the accuracy of search results. In this embodiment, the candidate docking postures in each region constitute the initial population in the region, and the individuals in the initial population are the binding conformations corresponding to the candidate docking postures.

[0084] Individual X in the population = (X1, X2, ...X d )(d is the dimension of the individual vector) can be regarded as an N-dimensional space vector. If the flexibility of the protein is not considered, the individual dimension N is 6, which is composed of translation and rotation vectors (x, y, z, θ, α, β). Among them, (x, y, z) represents the movement of all atoms in the ligand, and (θ, α, β) represents the rotation of the ligand as a whole.

[0085] In the embodiments of the present application, the anisotropic network model ANM is introduced to consider the structural movement of proteins, and the conformational changes between proteins in the unbound state and the bound state are described by a linear combination of normal modes (only the first ten normal modes are considered). Therefore, the dimension of individuals in the population is changed from 6 dimensions to 26 dimensions, and the last 20 dimensions represent the degree of deformation of the receptor protein and the ligand protein along each mode. The overall movement of the protein structure can be regarded as the superposition of different low-frequency vibration modes. ANM calculates the vibration mode based on the protein structure, and the last 20 dimensions in DE are used to represent the amplitude corresponding to each mode. The anisotropic network model is used to simulate protein conformational changes and further optimize the protein skeleton.

[0086] The mutation strategy is one of the cores of the differential evolution algorithm. For each individual in the population, the algorithm randomly selects three different individuals and generates a mutant individual through the mutation strategy. The mutation strategy usually multiplies the difference vector between two randomly selected individuals by a scaling factor and then adds it to the third individual to generate a mutant individual.

[0087] In a possible implementation, the mutation strategy is as follows (2):

[0088]

[0089] in, represents the i-th mutant individual generated in the t-th iteration, where X represents the individual in the population, F represents the scaling factor (mutation rate), t represents the t-th iteration, and r1, r2, and r3 are random numbers, which are integers randomly generated in [0, NP-1] (where r1, r2, and r3 are different, NP is the population size, and NP ≥ 4). The difference vector of two randomly selected individuals in the population is scaled and combined with the vector of another random individual to generate a mutant individual The value of F is related to the performance of the algorithm. A mutation rate that is too large can increase the search space of the algorithm, but will lead to low search efficiency, while a mutation rate that is too small may reduce population diversity and easily lead to "premature" phenomenon. In this embodiment, an adaptive F value method is adopted, as shown in the following calculation formula (3):

[0090]

[0091] Among them, T m represents the maximum number of iterations, t represents the current number of iterations, and F0 = 0.45.

[0092] The crossover strategy aims to increase the diversity of the population. During the crossover process, the algorithm will exchange some genes of the mutant individual with the target individual (i.e. the individual currently being processed) according to a certain probability.

[0093] In a possible implementation, the crossover strategy is as follows (4):

[0094]

[0095] in, represents the j-th dimension information of the i-th trial individual in the t-th iteration, represents the j-th dimension information of the i-th variant individual generated in the t-th iteration, Represents the j-th dimension information of individual i in the t-th iteration.

[0096] Based on the above calculation formula (4), as long as one of the following two conditions is met, The value comes from

[0097] (1) The randomly generated number ≤ CR;

[0098] (2) The current dimension j is equal to j rand , j rand It is a pre-randomly generated index.

[0099] When both (1) and (2) above are not satisfied, The value comes from

[0100] The purpose of the above crossover strategy is to transform the parent vector and variant individuals Perform crossover recombination to generate test individuals Where CR represents the crossover rate, and its value range is [0,1]. rand is a randomly generated index from [1, d] (d = 26), where d represents the dimension of the individual to ensure At least one gene can come from CR controls the degree of cross-recombination between variant individuals and parental information. When the CR value is too large, Most of the information of comes from the mutant individuals, which is beneficial to increase the diversity of the population; if it is too small, the information of the test individuals comes more from the parents, which affects the search for the global optimal solution of the population. CR is based on the following formula (5):

[0101] CR=0.5×[1+rand(0,1)](5)

[0102] In this embodiment, the average value of the crossover rate is maintained at about 0.75, which helps to maintain the diversity of the population and avoid falling into a local optimal solution.

[0103] The selection operation is used to compare the fitness values ​​of the test individual (i.e., the individual generated after the crossover strategy) and the target individual. If the fitness value of the test individual is better than the fitness value of the target individual (for minimization problems) or worse (for maximization problems), the test individual will replace the target individual and become a member of the new generation population. Otherwise, the target individual will remain in the population.

[0104] In one possible implementation, the selection strategy is as follows: With the parent vector Selecting the individuals with the best fitness and passing them on to the next generation helps retain excellent individuals and gradually improve the overall fitness level of the population.

[0105]

[0106] Based on the above calculation formula (6), when The value comes from the experimental individual otherwise, The value comes from the parent individual

[0107] Step S103: clustering the target docking postures.

[0108] In this embodiment, the target docking posture is the docking posture after DE optimization, and the target docking posture includes the optimized ligand protein conformation. The target docking posture is clustered according to the optimized ligand protein conformation.

[0109] There are often a large number of similar structures in the population after DE optimization, and the existence of these structures will increase the redundancy of the data and reduce the accuracy of the prediction. Therefore, in order to reduce the impact of redundant information, in this embodiment, the docking postures after DE optimization are clustered, and some similar structures are eliminated by clustering.

[0110] In the embodiment of the present application, a second clustering algorithm is used to cluster the docking posture of the target. The second clustering algorithm and the first clustering algorithm are different types of clustering algorithms. The second clustering algorithm is a hierarchical clustering algorithm.

[0111] In this embodiment, a hierarchical clustering algorithm is used to merge and cluster the target docking postures to obtain several clusters of target docking postures. The hierarchical clustering algorithm can be specifically a clustering algorithm based on a tree structure. It does not need to pre-specify the number of clusters, but calculates the similarity or distance between data points, gradually merges them into larger and larger clusters, or gradually splits from one cluster into smaller clusters until a certain stop condition is met. The result of this algorithm is a tree structure, and different numbers of clusters can be obtained by pruning.

[0112] In this embodiment, the root mean square deviation (rmsd) of the ligand is used as an indicator to measure structural similarity. Wherein a smaller Lrmsd value indicates a higher structural similarity. Then, the cluster tree is cut according to a set threshold (4 angstroms) to divide the structure into different clusters. For example, structures with rmsd less than 4 angstroms are classified into the same cluster. By aggregating structures with high similarity together, a large amount of redundant information can be reduced, thereby improving the accuracy and efficiency of protein-protein docking.

[0113] Step S104: Based on the clustering result, the optimal docking posture of the receptor protein and the ligand protein is determined.

[0114] Sort the target docking postures from low to high according to their corresponding docking energies. Select the top-ranked ones as the best docking postures. The lower the energy, the better the docking posture.

[0115] In this implementation, the binding conformation with the lowest docking energy in the cluster retained after clustering is taken as the representative binding conformation in the cluster, and the final predicted docking posture is obtained based on the representative binding conformation. The docking energy can be determined according to the aforementioned evaluation function. Figure 6 The structure of the complex predicted by docking simulation using the protein-protein docking method of the present application is shown. Figure 6 1B6C, 1JTG, 1WDE, 2HRK, 1R6Q, and 1WQ1 are the protein numbers in the database.

[0116] In an experimental scenario, the present application scheme was used for docking simulation on a benchmark data set (containing 230 proteins) and compared with seven other widely used protein-protein docking programs (including Zdock, Pydock, Megadock, Cluspro, Hdocklite, Lightdock and Patchdock). This experiment mainly focused on the success rate performance of the eight docking programs on top1, top5 and top10. Top10 means that if one of the top 10 predicted structures meets the DockQ value requirement, the docking is considered successful, and Top1 and Top5 are similar. The present invention is the only docking program among the eight docking programs with a top1 success rate close to 30%, while the success rates of the other seven docking programs are all less than 15% when only the optimal energy structure is considered. Moreover, for the predictions of top5 and top10, the present application scheme maintained the highest success rate, which were 45.7% and 49.1% respectively. Therefore, compared with other docking programs, the present application scheme has the best docking performance.

[0117] In an embodiment of the present application, a global search is performed on the surface space of the receptor protein to determine candidate docking postures, that is, potential binding sites. The ligand protein conformation is then optimized based on the candidate docking postures and a preset optimization algorithm. Based on the results of the global search, potential binding sites are further optimized and screened to determine the target docking posture, which can effectively improve the search efficiency. The target docking postures are then clustered, and based on the results of the clustering, the optimal docking posture of the ligand protein docked to the receptor protein is determined, which can effectively improve the success rate of protein-protein docking.

[0118] It should be understood that the size of the serial numbers of the steps in the above embodiments does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0119] Corresponding to the protein-protein docking method described in the above examples, Figure 7 A structural block diagram of a protein-protein docking device provided in an embodiment of the present application is shown. For ease of explanation, only the parts related to the embodiment of the present application are shown.

[0120] Reference Figure 7 The protein-protein docking device comprises: a first determination unit 71, a second determination unit 72, a cluster analysis unit 73, and a docking posture determination unit 74, wherein:

[0121] A first determination unit 71 is used to perform a global search on the surface space of the receptor protein to determine several candidate docking postures of the receptor protein and the ligand protein;

[0122] A second determination unit 72, configured to optimize the plurality of candidate docking postures according to a preset optimization algorithm to determine a target docking posture;

[0123] A cluster analysis unit 73, used for clustering the target docking postures;

[0124] The docking posture determination unit 74 is used to determine the optimal docking posture of the receptor protein and the ligand protein based on the clustering result.

[0125] As a possible implementation manner of the present application, the first determining unit 71 includes:

[0126] The binding conformation generation module is used to perform a global search of the surface space of the receptor protein using the FFT algorithm to generate multiple binding conformations;

[0127] The first determination module is used to screen the binding conformation according to preset screening conditions to determine a number of candidate docking postures.

[0128] As a possible implementation manner of the present application, the second determining unit 72 includes:

[0129] A region division module, used for dividing the surface space of the receptor protein into regions based on the plurality of candidate docking postures;

[0130] The second determination module is used to perform a local search on the candidate docking postures in each divided area according to the preset optimization algorithm to determine the target docking posture.

[0131] As a possible implementation of the present application, the candidate docking posture includes a ligand protein conformation, and the above-mentioned region division module is specifically used for:

[0132] Clustering the plurality of candidate docking postures based on the position of the ligand protein conformation to obtain a plurality of classes of candidate docking postures;

[0133] According to the number of classes of the candidate docking poses, the surface space of the receptor protein is divided into regions, wherein each region contains one class of the candidate docking poses.

[0134] As a possible implementation manner of the present application, the second determination module is specifically used for:

[0135] The candidate docking postures in each region are iteratively optimized through the differential evolution algorithm;

[0136] Based on the result of the iterative optimization, a target docking posture in each region is determined.

[0137] As a possible implementation of the present application, the step of iteratively optimizing the candidate docking postures in each region by using a differential evolution algorithm includes:

[0138] It is beneficial to use a preset evaluation function to evaluate the fitness of the candidate docking postures in the area and determine the fitness value of the candidate docking postures in the area;

[0139] The candidate docking posture is iteratively optimized based on the fitness value and a preset iterative strategy until a preset termination condition is met, and the iterative optimization ends. The preset iterative strategy includes crossover, mutation and selection.

[0140] As a possible implementation of the present application, the cluster analysis unit 73 is specifically used for:

[0141] A hierarchical clustering algorithm is used to merge and cluster the target docking postures to obtain several clusters of target docking postures.

[0142] In an embodiment of the present application, a global search is performed on the surface space of the receptor protein to determine several candidate docking postures of the receptor protein and the ligand protein, that is, several potential binding sites are determined, and then the several candidate docking postures are optimized according to a preset optimization algorithm, and the potential binding sites are further optimized and screened based on the results of the global search to determine the target docking posture, which can effectively improve the search efficiency, and then the target docking postures are clustered, and based on the results of the clustering, the optimal docking posture of the receptor protein and the ligand protein is determined, which can effectively improve the success rate of protein-protein docking.

[0143] It should be noted that the information interaction, execution process, etc. between the above-mentioned devices / units are based on the same concept as the method embodiment of the present application. Their specific functions and technical effects can be found in the method embodiment part and will not be repeated here.

[0144] The present application also provides a computer-readable storage medium storing a computer program, wherein when the computer program is executed by a processor, Figures 1 to 6 The steps of any protein-protein docking method represented.

[0145] The embodiment of the present application also provides an intelligent device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, Figures 1 to 6 The steps of any protein-protein docking method represented.

[0146] The present application also provides a computer program product, which, when executed on a server, enables the server to execute the following Figures 1 to 6 The steps of any protein-protein docking method represented.

[0147] Figure 8 Schematic diagram of a smart device provided by an embodiment of the present application. Figure 8 As shown, the smart device 8 of this embodiment includes: a processor 80, a memory 81, and a computer program 82 stored in the memory 81 and executable on the processor 80. When the processor 80 executes the computer program 82, the steps in the above-mentioned protein-protein docking method embodiments are implemented, for example Figure 1 Alternatively, when the processor 80 executes the computer program 82, the functions of each module / unit in the above-mentioned device embodiments are realized, for example Figure 7 The functions of units 71 to 74 are shown.

[0148] Exemplarily, the computer program 82 may be divided into one or more modules / units, which are stored in the memory 81 and executed by the processor 80 to complete the present application. The one or more modules / units may be a series of computer-readable instruction segments capable of completing specific functions, which are used to describe the execution process of the computer program 82 in the smart device 8.

[0149] The smart device 8 may include, but is not limited to, a processor 80 and a memory 81. Those skilled in the art will appreciate that Figure 8 It is only an example of the smart device 8 and does not constitute a limitation of the smart device 8. It may include more or fewer components than shown in the figure, or a combination of certain components, or different components. For example, the smart device 8 may also include input and output devices, network access devices, buses, etc.

[0150] The processor 80 may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or any conventional processor, etc.

[0151] The memory 81 may be an internal storage unit of the smart device 8, such as a hard disk or memory of the smart device 8. The memory 81 may also be an external storage device of the smart device 8, such as a plug-in hard disk, a smart media card (SMC), a secure digital (SD) card, a flash card, etc. equipped on the smart device 8. Further, the memory 81 may also include both an internal storage unit and an external storage device of the smart device 8. The memory 81 is used to store the computer program and other programs and data required by the smart device. The memory 81 may also be used to temporarily store data that has been output or is to be output.

[0152] It should be noted that the information interaction, execution process, etc. between the above-mentioned devices / units are based on the same concept as the method embodiment of the present application. Their specific functions and technical effects can be found in the method embodiment part and will not be repeated here.

[0153] The technicians in the relevant field can clearly understand that for the convenience and simplicity of description, only the division of the above-mentioned functional units and modules is used as an example for illustration. In practical applications, the above-mentioned function allocation can be completed by different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above. The functional units and modules in the embodiment can be integrated in a processing unit, or each unit can exist physically separately, or two or more units can be integrated in one unit. The above-mentioned integrated unit can be implemented in the form of hardware or in the form of software functional units. In addition, the specific names of the functional units and modules are only for the convenience of distinguishing each other, and are not used to limit the scope of protection of this application. The specific working process of the units and modules in the above-mentioned system can refer to the corresponding process in the aforementioned method embodiment, which will not be repeated here.

[0154] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the present application implements all or part of the processes in the above-mentioned embodiment method, which can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a computer-readable storage medium, and the computer program can implement the steps of the above-mentioned various method embodiments when executed by the processor. Among them, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form. The computer-readable medium may at least include: any entity or device that can carry the computer program code to the device / terminal device, a recording medium, a computer memory, a read-only memory (ROM, Read-Only Memory), a random access memory (RAM, Random Access Memory), an electric carrier signal, a telecommunication signal, and a software distribution medium. For example, a USB flash drive, a mobile hard disk, a magnetic disk or an optical disk. In some jurisdictions, according to legislation and patent practice, computer-readable media cannot be electric carrier signals and telecommunication signals.

[0155] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described or recorded in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0156] The embodiments described above are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned embodiments, a person skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features may be replaced by equivalents. Such modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present application, and should all be included in the protection scope of the present application.

Claims

1. A protein-protein docking method, characterized in that: The method comprises: Performing a global search on the surface space of the receptor protein to determine several candidate docking poses of the receptor protein and the ligand protein; Optimizing the candidate docking postures according to a preset optimization algorithm to determine a target docking posture; Clustering the target docking postures; Based on the clustering results, the optimal docking posture of the receptor protein and the ligand protein is determined.

2. The protein-protein docking method according to claim 1, characterized in that: The step of globally searching the surface space of the receptor protein to determine several candidate docking postures of the receptor protein and the ligand protein comprises: The FFT algorithm is used to perform a global search of the receptor protein surface space to generate multiple binding conformations; The binding conformations are screened according to preset screening conditions to determine several candidate docking postures.

3. The protein-protein docking method according to claim 1, characterized in that: The step of optimizing the plurality of candidate docking postures according to a preset optimization algorithm to determine a target docking posture comprises: Based on the several candidate docking poses, dividing the surface space of the receptor protein into regions; According to the preset optimization algorithm, a local search is performed on the candidate docking postures in each divided area to determine the target docking posture.

4. The protein-protein docking method according to claim 3, characterized in that: The candidate docking postures include ligand protein conformations, and the step of dividing the surface space of the receptor protein into regions based on the candidate docking postures includes: Clustering the plurality of candidate docking postures based on the position of the ligand protein conformation to obtain a plurality of classes of candidate docking postures; According to the number of classes of the candidate docking poses, the surface space of the receptor protein is divided into regions, wherein each region contains one class of the candidate docking poses.

5. The protein-protein docking method according to claim 3, characterized in that: The step of performing a local search on the candidate docking postures in each divided area according to the preset optimization algorithm to determine the target docking posture comprises: The candidate docking postures in each region are iteratively optimized through the differential evolution algorithm; Based on the result of the iterative optimization, a target docking posture in each region is determined.

6. The protein-protein docking method according to claim 5, characterized in that: The step of iteratively optimizing the candidate docking postures in each region by using a differential evolution algorithm comprises: It is beneficial to use a preset evaluation function to evaluate the fitness of the candidate docking postures in the area and determine the fitness value of the candidate docking postures in the area; The candidate docking posture is iteratively optimized based on the fitness value and a preset iterative strategy until a preset termination condition is met, and the iterative optimization ends. The preset iterative strategy includes crossover, mutation and selection.

7. The protein-protein docking method according to any one of claims 1 to 6, characterized in that: The step of clustering the target docking postures comprises: A hierarchical clustering algorithm is used to merge and cluster the target docking postures to obtain several clusters of target docking postures.

8. A protein-protein docking device, characterized in that: The device comprises: A first determination unit is used to perform a global search on the surface space of the receptor protein to determine a number of candidate docking postures of the receptor protein and the ligand protein; A second determination unit is used to optimize the plurality of candidate docking postures according to a preset optimization algorithm to determine a target docking posture; A cluster analysis unit, used for clustering the target docking postures; A docking posture determination unit is used to determine the optimal docking posture of the receptor protein and the ligand protein based on the clustering result.

9. An intelligent device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the protein-protein docking method according to any one of claims 1 to 7 is implemented.

10. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the protein-protein docking method according to any one of claims 1 to 7 is implemented.

Images