Antigen-antibody affinity prediction methods, systems, and devices

Abstract

The application relates to the technical field of artificial intelligence, in particular to an antigen-antibody affinity prediction method, system and device, which comprises the following steps: performing feature extraction on amino acid sequence data of an antigen and an antibody, and generating a preliminary complex three-dimensional conformation through a prediction model; fusing and screening a plurality of preliminary complex three-dimensional conformations to determine an intermediate complex three-dimensional conformation; optimizing a binding interface of the intermediate complex three-dimensional conformation based on molecular dynamics simulation and a reinforcement learning algorithm to obtain a final optimized conformation; performing energy decomposition based on a molecular force field principle to obtain key energy parameters, and obtaining a binding free energy through an affinity prediction deep neural network based on the key energy parameters and energy characteristics determined by the molecular dynamics simulation; and when the binding free energy is higher than a judgment threshold, re-performing optimization and determining the binding free energy. In this way, the accuracy and reliability of prediction can be significantly improved on the basis of realizing full-process automation.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of artificial intelligence, in particular to an antigen-antibody affinity prediction method, system and device. BACKGROUND

[0002] The binding affinity between antigens and antibodies is a core indicator for evaluating the efficacy of antibody drugs, the protection effect of vaccines, and understanding the mechanism of immune response, which can generally be characterized by binding free energy. Traditional experimental methods, such as surface plasmon resonance technology or isothermal titration calorimetry, can accurately measure the affinity, but generally have problems such as high cost, long cycle, large sample consumption, and are difficult to meet the needs of high-throughput screening and rapid iteration. SUMMARY

[0003] Therefore, the purpose of the present application is to provide an antigen-antibody affinity prediction method, system and device to solve the problems of high cost, long cycle and large sample consumption in the prior art.

[0004] To achieve the above purpose, the technical scheme adopted by the present application is as follows:

[0005] In a first aspect, the present application provides an antigen-antibody affinity prediction method, comprising:

[0006] extracting features from the amino acid sequence data of the antigen and the antibody, and generating a preliminary complex three-dimensional conformation based on the feature extraction result and a preset prediction model;

[0007] fusing and screening a plurality of preliminary complex three-dimensional conformations to determine an intermediate complex three-dimensional conformation;

[0008] optimizing the binding interface of the intermediate complex three-dimensional conformation based on molecular dynamics simulation and reinforcement learning algorithm to obtain a final optimized conformation;

[0009] based on the principle of molecular force field, energy decomposition is performed on the final optimized conformation to obtain key energy parameters, and based on the key energy parameters and energy characteristics determined by molecular dynamics simulation, the binding free energy is obtained through a preset affinity prediction deep neural network;

[0010] comparing the binding free energy with a preset judgment threshold, if the binding free energy is higher than the judgment threshold, re-optimizing the binding interface of the intermediate complex three-dimensional conformation and determining the binding free energy, otherwise outputting the binding free energy.

[0011] Further, in some embodiments of the present application, the feature extraction from the amino acid sequence data of the antigen and the antibody, and the generation of the preliminary complex three-dimensional conformation based on the feature extraction result and the preset prediction model, comprises:

[0012] performing multiple sequence alignment processing on the amino acid sequence data to extract sequence conservation features;

[0013] converting the amino acid sequence data into a high-dimensional feature vector based on a pre-trained language model;

[0014] performing monomer structure prediction on the antigen and the antibody respectively based on the sequence conservation features and the high-dimensional feature vector through a preset monomer prediction model to generate a plurality of candidate structures;

[0015] inputting the candidate structures into a preset complex prediction model to generate the preliminary complex three-dimensional conformation.

[0016] Further, in some embodiments of the present application, the fusing and screening of the plurality of preliminary complex three-dimensional conformations to determine the intermediate complex three-dimensional conformation comprises:

[0017] performing structure comparison on the plurality of preliminary complex three-dimensional conformations, and merging the preliminary complex three-dimensional conformations based on the comparison result to obtain a fusion conformation set; wherein the plurality of preliminary complex three-dimensional conformations are output by a plurality of complex prediction models or output multiple times by one complex prediction model;

[0018] performing clustering screening on the complex three-dimensional conformations in the fusion conformation set to obtain the intermediate complex three-dimensional conformation.

[0019] Further, in some embodiments of the present application, the optimization of the binding interface of the intermediate complex three-dimensional conformation based on molecular dynamics simulation and reinforcement learning algorithm to obtain the final optimized conformation comprises:

[0020] performing coarse-grained molecular dynamics simulation on the intermediate complex three-dimensional conformation to obtain coarse-grained simulation results;

[0021] extracting binding interface data of the coarse-grained simulation results;

[0022] performing side chain reconstruction on the binding interface residues, and adjusting the rotation angle and conformation of the residues based on a policy gradient-based reinforcement learning algorithm to obtain an optimization result;

[0023] performing all-atom molecular dynamics refinement on the optimization result to obtain the final optimized conformation.

[0024] Further, in some embodiments of the present application, the energy decomposition is performed on the final optimized conformation based on the principle of molecular force field to obtain key energy parameters, and based on the key energy parameters and energy characteristics determined by molecular dynamics simulation, a binding free energy is obtained through a preset affinity prediction deep neural network, comprising:

[0025] obtaining energy features based on coarse-grained molecular dynamics simulation and all-atom molecular dynamics refinement;

[0026] inputting the key energy parameters and the energy features into the affinity prediction deep neural network to predict the binding free energy.

[0027] Further, in some embodiments of the present application, the key energy parameters include van der Waals energy, electrostatic energy and solvation free energy.

[0028] Further, in some embodiments of the present application, further comprising: performing uncertainty evaluation on the predicted binding free energy to determine a corresponding confidence interval.

[0029] Further, in some embodiments of the present application, further comprising:

[0030] generating single-point and multi-point mutant conformations of the binding interface residues;

[0031] calculating the difference in binding free energy before and after mutation for each mutant conformation, and analyzing the influence of mutation on affinity based on the difference in binding free energy.

[0032] In a second aspect, the present application provides an antigen-antibody affinity prediction system, comprising:

[0033] a data input and structure prediction module for feature extraction on amino acid sequence data of the antigen and the antibody, and generating a preliminary complex three-dimensional conformation based on the feature extraction result and a preset prediction model;

[0034] a conformation fusion and screening module for fusing and screening a plurality of preliminary complex three-dimensional conformations to determine an intermediate complex three-dimensional conformation;

[0035] a binding interface optimization module for optimizing the binding interface of the intermediate complex three-dimensional conformation based on molecular dynamics simulation and reinforcement learning algorithm to obtain a final optimized conformation;

[0036] a cross-scale affinity calculation module for energy decomposition on the final optimized conformation based on molecular force field principle to obtain key energy parameters, and obtaining the binding free energy through a preset affinity prediction deep neural network based on the key energy parameters and energy features determined by molecular dynamics simulation;

[0037] and comparing the binding free energy with a preset judgment threshold, if the binding free energy is higher than the judgment threshold, it is judged that the binding interface of the intermediate complex three-dimensional conformation needs to be optimized and the binding free energy needs to be determined, otherwise the binding free energy is output.

[0038] In a third aspect, the present application provides an antigen-antibody affinity prediction device, characterized in that it comprises a processor and a memory, wherein the processor is connected to the memory.

[0039] The processor is configured to call and execute the program stored in the memory.

[0040] The memory is configured to store the program, and the program is configured to execute the antigen-antibody affinity prediction method.

[0041] The present application relates to the technical field of artificial intelligence, in particular to an antigen-antibody affinity prediction method, system and device, which comprises the following steps: performing feature extraction on amino acid sequence data of an antigen and an antibody, and generating a preliminary complex three-dimensional conformation based on the feature extraction result and a preset prediction model; fusing and screening a plurality of preliminary complex three-dimensional conformations to determine an intermediate complex three-dimensional conformation; optimizing a binding interface of the intermediate complex three-dimensional conformation based on molecular dynamics simulation and reinforcement learning algorithm to obtain a final optimized conformation; decomposing energy of the final optimized conformation based on the principle of molecular force field to obtain key energy parameters, and obtaining binding free energy by a preset affinity prediction deep neural network based on the key energy parameters and energy characteristics determined by the molecular dynamics simulation; and re-optimizing and determining the binding free energy when the binding free energy is higher than a judgment threshold. In this way, the accuracy and reliability of the prediction can be significantly improved on the basis of full-process automation. BRIEF DESCRIPTION OF DRAWINGS

[0042] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the drawings needed in the embodiments or prior art description will be briefly introduced. Obviously, the drawings in the following description are only some embodiments of the present application, and other drawings can be obtained by those skilled in the art without creative labor.

[0043] Figure 1 is a flowchart of the antigen-antibody affinity prediction method provided by the embodiments of the present application.

[0044] Figure 2 is a structural schematic diagram of the antigen-antibody affinity prediction system provided by the embodiments of the present application.

[0045] Figure 3 is a structural schematic diagram of the antigen-antibody affinity prediction device provided by the embodiments of the present application. DETAILED DESCRIPTION

[0046] In order to make the objectives, technical solutions and advantages of the present application clearer, the technical solutions of the present application will be described in detail below. Obviously, the described embodiments are only some of the embodiments of the present application, but not all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative work belong to the scope of protection of the present application.

[0047] Figure 1 is a flowchart of the antigen-antibody affinity prediction method provided by the embodiments of the present application, please refer to Figure 1 The embodiments can include the following steps:

[0048] S101, feature extraction is performed on the amino acid sequence data of the antigen and the antibody, and based on the feature extraction result and a preset prediction model, a preliminary complex three-dimensional conformation is generated.

[0049] Specifically, the amino acid sequence data of the antigen and the antibody can be derived from gene sequencing, public database or artificial design, etc. In the present application, after feature extraction is performed on the amino acid sequence data of the antigen and the antibody, the feature extraction result is taken as the input of the preset prediction model, so as to generate and output the preliminary complex three-dimensional conformation through the prediction model.

[0050] S102, the multiple preliminary complex three-dimensional conformations are fused and screened to determine an intermediate complex three-dimensional conformation.

[0051] Specifically, in the present application, the multiple preliminary complex three-dimensional conformations can be output by multiple complex prediction models or by one complex prediction model multiple times, and then the multiple preliminary complex three-dimensional conformations are fused and screened to determine the intermediate complex three-dimensional conformation.

[0052] S103, based on molecular dynamics simulation and reinforcement learning algorithm, the binding interface of the intermediate complex three-dimensional conformation is optimized to obtain a final optimized conformation.

[0053] Specifically, in the present application, the binding interface data is determined by performing molecular dynamics simulation on the intermediate complex three-dimensional conformation, and on this basis, the final optimization result is obtained by optimizing the binding interface, which is used for subsequent calculation of the binding free energy.

[0054] S104, based on the principle of molecular force field, the energy of the final optimized conformation is decomposed to obtain key energy parameters, and based on the key energy parameters and the energy characteristics determined by the molecular dynamics simulation, the binding free energy is obtained through a preset affinity prediction deep neural network.

[0055] S105, compare the binding free energy with a preset judgment threshold value, if the binding free energy is higher than the judgment threshold value, re-optimize and determine the binding free energy of the binding interface of the intermediate complex three-dimensional conformation, otherwise output the binding free energy.

[0056] The antigen-antibody affinity prediction method provided in the application can significantly improve the accuracy and reliability of the prediction on the basis of realizing full-process automation. The antigen-antibody affinity prediction method provided in the application comprises the following steps: extracting feature data from amino acid sequence data of an antigen and an antibody, and generating a preliminary complex three-dimensional conformation based on the feature extraction result and a preset prediction model; fusing and screening a plurality of preliminary complex three-dimensional conformations to determine an intermediate complex three-dimensional conformation; optimizing a binding interface of the intermediate complex three-dimensional conformation based on molecular dynamics simulation and a reinforcement learning algorithm to obtain a final optimized conformation; decomposing energy for the final optimized conformation based on the principle of a molecular force field to obtain key energy parameters, and obtaining a binding free energy by a preset affinity prediction deep neural network based on the key energy parameters and energy characteristics determined by the molecular dynamics simulation; and re-optimizing and determining the binding free energy when the binding free energy is higher than a judgment threshold value.

[0057] Further, in some embodiments of the application, the feature data of the amino acid sequence data of the antigen and the antibody is extracted, and the preliminary complex three-dimensional conformation is generated based on the feature extraction result and the preset prediction model, which can specifically include the following steps: first, performing multiple sequence alignment processing on the amino acid sequence data to extract sequence conservation features; then converting the amino acid sequence data into a high-dimensional feature vector based on a pre-trained language model; then, based on the sequence conservation features and the high-dimensional feature vector, respectively predicting the monomer structure of the antigen and the antibody by a preset monomer prediction model to generate a plurality of candidate structures; and inputting the candidate structures into a preset complex prediction model to generate the preliminary complex three-dimensional conformation.

[0058] In actual application, the monomer prediction model can be constructed by a deep generative modeling network to respectively predict the monomer structure of the antigen and the antibody to generate a plurality of candidate structures to obtain a candidate structure set. Then, the predicted structures of the antigen and the antibody in the candidate structure set are input into the complex prediction model to generate a plurality of preliminary complex three-dimensional conformations (which can be output by a plurality of complex prediction models or by one complex prediction model multiple times) to obtain a preliminary complex three-dimensional conformation set. It should be noted that the confidence score corresponding to the preliminary complex three-dimensional conformation can also be obtained by the complex prediction model.

[0059] On this basis, the structures of a plurality of preliminary complex three-dimensional conformations are compared, and the preliminary complex three-dimensional conformations are merged based on the comparison result to obtain a fusion conformation set; and the complex three-dimensional conformations in the fusion conformation set are clustered and screened to obtain an intermediate complex three-dimensional conformation.

[0060] Specifically, first, the three-dimensional conformations of the plurality of preliminary complexes are subjected to structure alignment, and similar conformations are merged to obtain a set of fused conformations. Then, based on the confidence score or conformation clustering center information obtained by the above prediction model, an intermediate complex three-dimensional conformation can be screened out as an input for subsequent optimization.

[0061] Further, in some embodiments of the present application, based on molecular dynamics simulation and reinforcement learning algorithm, the binding interface of the intermediate complex three-dimensional conformation is optimized to obtain the final optimized conformation, which can specifically include:

[0062] First, coarse-grained molecular dynamics simulation is performed on the intermediate complex three-dimensional conformation to obtain coarse-grained simulation results, so as to realize rapid relaxation of the global conformation.

[0063] Then, the binding interface data of the coarse-grained simulation results is extracted.

[0064] Then, side chain reconstruction is performed on the binding interface residues, and the rotation angle and conformation of the residues are adjusted based on the policy gradient reinforcement learning algorithm to obtain the optimization result. In actual application, the optimization can be performed with the goal of maximizing the interface electrostatic and hydrophobic complementarity score.

[0065] Finally, the optimization result is subjected to all-atom molecular dynamics refinement to obtain the final optimized conformation.

[0066] Further, in some embodiments of the present application, based on the principle of molecular force field, the energy of the final optimized conformation is decomposed to obtain key energy parameters, and based on the key energy parameters and the energy characteristics determined by the molecular dynamics simulation, the binding free energy is obtained through a preset affinity prediction deep neural network, which can specifically include: obtaining the energy characteristics obtained based on the coarse-grained molecular dynamics simulation and the all-atom molecular dynamics refinement; and inputting the key energy parameters and the energy characteristics into the affinity prediction deep neural network to predict the binding free energy.

[0067] Specifically, for the final optimized conformation, molecular force field can be used for energy decomposition to obtain key energy parameters such as van der Waals energy, electrostatic energy and solvation free energy; then the energy characteristics determined by the above coarse-grained molecular dynamics simulation and all-atom molecular dynamics refinement are input into the preset affinity prediction deep neural network, and the network outputs the binding free energy. In addition, the uncertainty of the binding free energy can be evaluated by methods such as Monte Carlo Dropout and Bootstrap sampling, and the confidence interval is output.

[0068] Based on this, after obtaining the binding free energy, it is compared with a preset judgment threshold. If the binding free energy is higher than the judgment threshold, it indicates insufficient affinity. Then, the binding interface of the three-dimensional conformation of the intermediate complex is re-optimized and the binding free energy is determined (this process is the same as the process principle and steps in the above embodiment, and will not be repeated here). Otherwise, the binding free energy is output to ensure the reliability of the final binding free energy.

[0069] In addition, in some embodiments of this application, the antigen-antibody affinity prediction method provided in this application further includes: generating single-point and multi-point mutated conformations of binding interface residues; calculating the difference in binding free energy before and after the mutation for each mutated conformation; and analyzing the effect of the mutation on affinity based on the difference in binding free energy.

[0070] For example, a pre-set system can automatically generate single-point and multi-point mutant conformations of binding interface residues (such as amino acid scans and immune escape mutant sets). Each mutant conformation is then processed using the aforementioned binding interface optimization and free binding energy calculation methods to obtain the binding free energy before and after the mutation, and the difference in binding free energy before and after the mutation can be calculated. This difference can then be used to analyze the effect of the mutation on affinity, such as generating a mutation sensitivity heatmap to analyze the sensitivity of binding affinity to mutations of different residues.

[0071] Based on the same inventive concept, this application also provides an antigen-antibody affinity prediction system. Figure 2 This is a schematic diagram of the antigen-antibody affinity prediction system provided in an embodiment of the present invention, as shown below. Figure 2 As shown, the system includes:

[0072] The data input and structure prediction module 11 is used to extract features from the amino acid sequence data of antigens and antibodies, and generate a preliminary three-dimensional conformation of the complex based on the feature extraction results and a preset prediction model.

[0073] In practical applications, this module can include a sequence input and feature extraction submodule and a three-dimensional structure prediction submodule. The sequence input and feature extraction submodule can input the amino acid sequence data of the antigen and antibody, and then use this module to perform feature extraction and encoding using multiple sequence alignment and a pre-trained language model. The three-dimensional structure prediction submodule can predict the three-dimensional structure of the complex and output the prediction confidence.

[0074] The conformation fusion and screening module 12 is used to fuse and screen multiple preliminary complex three-dimensional conformations to determine the intermediate complex three-dimensional conformation. In practical applications, this module can use RMSD clustering or energy functions to screen out the intermediate complex three-dimensional conformation from multiple preliminary complex three-dimensional conformations.

[0075] The binding interface optimization module 13 is configured to optimize the binding interface of the intermediate complex three-dimensional conformation based on molecular dynamics simulation and reinforcement learning algorithm, to obtain a final optimized conformation, including the coarse-grained molecular dynamics simulation, side chain reconstruction of the binding interface residues, reinforcement learning guided optimization of the residue rotation angle and conformation, and all-atom molecular dynamics refinement mentioned in the method embodiments.

[0076] The cross-scale affinity calculation module 14 is configured to perform energy decomposition on the final optimized conformation based on the principle of molecular force field, to obtain key energy parameters, and based on the key energy parameters and energy characteristics determined by the molecular dynamics simulation, to obtain the binding free energy through a preset affinity prediction deep neural network; and compare the binding free energy with a preset judgment threshold, if the binding free energy is higher than the judgment threshold, it is determined that the binding interface of the intermediate complex three-dimensional conformation needs to be optimized and the binding free energy needs to be determined, otherwise the binding free energy is output. Of course, this module can also be used only to obtain the binding free energy, and other separate modules are used to compare the binding free energy with the judgment threshold, etc., and connected with other modules to realize the feedback loop.

[0077] In addition, in some embodiments of the present application, the system further comprises a mutation sensitivity analysis module configured to trigger automatic generation of a mutant conformation based on the antibody or antigen mutant sequence, and to calculate the change value of the binding free energy before and after the mutation, to generate a mutation site sensitivity heat map.

[0078] In actual application, the above system can also set specific input content according to demand, for example, in addition to outputting the affinity prediction result, i.e. the binding free energy, it can also output related three-dimensional structure files, confidence interval information and mutation sensitivity heat map, etc. for relevant personnel to check and analyze.

[0079] In addition, it should be noted that the above-mentioned three-dimensional structure prediction sub-module and mutation sensitivity analysis module can be run in parallel on different computing nodes to improve large-scale prediction efficiency, and the system can be deployed on a high-performance computing cluster or a GPU-accelerated workstation, etc.

[0080] As to the device in the above embodiments, the specific manner in which each module performs operations has been described in detail in the embodiments related to the method, and will not be described in detail here.

[0081] The antigen antibody affinity prediction system provided in the application can realize complete automation from sequence data input to affinity prediction, without manual docking and energy calculation configuration, greatly reducing labor cost and operation time; meanwhile, by fusing the prediction results of multiple prediction models and screening the uncertainty clusters, the stability and robustness of structure prediction are improved; and by using reinforcement learning, the binding interface conformation can be actively optimized, improving the accuracy of prediction; and by using the data of coarse-grained and all-atom simulation, the binding free energy prediction is performed by using deep neural network, achieving the balance between accuracy and calculation speed; and by mutation sensitivity analysis, the influence of mutation on affinity can be quickly evaluated, thereby providing support for immune escape risk assessment and antibody resistance research.

[0082] Based on the same inventive concept, the application further provides an antigen antibody affinity prediction device for implementing the above method embodiments. Figure 3 is a structural schematic diagram of the antigen antibody affinity prediction device provided by the embodiment of the application, as Figure 3 shown, the antigen antibody affinity prediction device of the embodiment includes a processor 21 and a memory 22, and the processor 21 is connected with the memory 22. Among them, the processor 21 is used to call and execute the program stored in the memory 22; the memory 22 is used to store the program, which is at least used to execute the antigen antibody affinity prediction method in the above embodiments.

[0083] The specific implementation of the antigen antibody affinity prediction device provided in the embodiments of the application can refer to the implementation of the antigen antibody affinity prediction method of any of the above embodiments, which will not be repeated here.

[0084] It can be understood that the same or similar parts in the above embodiments can be mutually referred to, and the contents not described in detail in some embodiments can be referred to the same or similar contents in other embodiments.

[0085] It should be noted that in the description of the application, the terms "first", "second", etc. are only used for descriptive purposes and should not be understood as indicating or implying relative importance. In addition, in the description of the application, unless otherwise specified, "a plurality of" means at least two.

[0086] Any process or method descriptions in flow charts or otherwise described herein can be understood as representing code modules, segments, or portions of code that include one or more executable instructions for implementing specific logic functions or other processes, and the scope of preferred embodiments of the application includes additional implementation in which the functions described with reference to a described process are implemented by hardware, by software stored and executed on hardware, or by combinations thereof, as will be apparent to those skilled in the art of the application.

[0087] It should be understood that aspects of the application can be implemented in hardware, software, firmware or a combination of them. In the above embodiments, multiple steps or methods can be implemented in software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented in hardware, and in another embodiment, any of the following technologies, known in the art, or a combination thereof, can be used: discrete logic circuitry having logic gates for implementing logic functions on data signals, application specific integrated circuits having appropriate combinational logic gates, programmable gate arrays (PGA), field programmable gate arrays (FPGA), etc.

[0088] Those skilled in the art can understand that all or part of the steps carried out by the above-mentioned embodiment method can be completed by a program instructing the relevant hardware, and the program can be stored in a computer readable storage medium. When the program is executed, it includes one of the steps of the method embodiment or a combination thereof.

[0089] In addition, each functional unit in each embodiment of the present application can be integrated into one processing module, or each unit can exist physically, or two or more units can be integrated into one module. The above integrated module can be realized in the form of hardware or in the form of a software function module. The integrated module, if realized in the form of a software function module and sold or used as an independent product, can also be stored in a computer readable storage medium.

[0090] The storage medium mentioned above can be a read-only memory, a magnetic disk or an optical disk, etc.

[0091] In the description of the present specification, the description of the terms "one embodiment", "some embodiments", "an example", "a specific example" or "some examples" means that the specific features, structures, materials or characteristics described in connection with the embodiment or example are included in at least one embodiment or example of the present application. In the present specification, the illustrative description of the above terms does not necessarily mean the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described can be combined in any one or more embodiments or examples in a suitable manner.

[0092] Although the embodiments of the present application have been shown and described above, it should be understood that the above embodiments are exemplary and cannot be understood as limiting the present application, and those skilled in the art can make changes, modifications, replacements and variations to the above embodiments within the scope of the present application.

Claims

1. An antigen-antibody affinity prediction method characterized by, The application relates to a method for predicting the binding free energy of an antigen-antibody complex, comprising the following steps: performing feature extraction on amino acid sequence data of the antigen and the antibody, and generating a preliminary complex three-dimensional conformation based on the feature extraction result and a preset prediction model; fusing and screening a plurality of preliminary complex three-dimensional conformations to determine an intermediate complex three-dimensional conformation; optimizing a binding interface of the intermediate complex three-dimensional conformation based on molecular dynamics simulation and a reinforcement learning algorithm to obtain a final optimized conformation; decomposing energy of the final optimized conformation based on a molecular force field principle to obtain key energy parameters, and obtaining a binding free energy by a preset affinity prediction deep neural network based on the key energy parameters and energy characteristics determined by the molecular dynamics simulation; and comparing the binding free energy with a preset judgment threshold, and if the binding free energy is higher than the judgment threshold, re-optimizing the binding interface of the intermediate complex three-dimensional conformation and determining the binding free energy, otherwise outputting the binding free energy. The method for predicting the binding free energy of an antigen-antibody complex comprises the following steps: performing multiple sequence alignment processing on the amino acid sequence data to extract sequence conservation features; converting the amino acid sequence data into a high-dimensional feature vector based on a pre-trained language model; performing monomer structure prediction on the antigen and the antibody respectively by a preset monomer prediction model based on the sequence conservation features and the high-dimensional feature vector to generate a plurality of candidate structures; and inputting the candidate structures into a preset complex prediction model to generate the preliminary complex three-dimensional conformation. The method for predicting the binding free energy of an antigen-antibody complex comprises the following steps: performing structure comparison on a plurality of preliminary complex three-dimensional conformations, and merging the preliminary complex three-dimensional conformations based on the comparison result to obtain a fusion conformation set; wherein the plurality of preliminary complex three-dimensional conformations are output by a plurality of complex prediction models or are output multiple times by one complex prediction model; and performing clustering screening on the complex three-dimensional conformations in the fusion conformation set to obtain the intermediate complex three-dimensional conformation. The method for predicting the binding free energy of an antigen-antibody complex comprises the following steps: performing coarse-grained molecular dynamics simulation on the intermediate complex three-dimensional conformation to obtain coarse-grained simulation results; extracting binding interface data of the coarse-grained simulation results; performing side chain reconstruction on the binding interface residues, and adjusting the rotation angle and conformation of the residues based on a policy gradient reinforcement learning algorithm to obtain an optimization result; and performing all-atom molecular dynamics refinement on the optimization result to obtain the final optimized conformation. The method for predicting the binding free energy of an antigen-antibody complex comprises the following steps: obtaining energy characteristics based on coarse-grained molecular dynamics simulation and all-atom molecular dynamics refinement; decomposing energy of the final optimized conformation based on a molecular force field principle to obtain key energy parameters; and obtaining a binding free energy by a preset affinity prediction deep neural network based on the key energy parameters and the energy characteristics. ​ 2. The antigen-antibody affinity prediction method according to claim 1, wherein, ​ ​ ​ ​ ​ 3. The antigen-antibody affinity prediction method according to claim 2, wherein ​ ​ ​ 4. The antigen-antibody affinity prediction method according to claim 3, wherein, ​ ​ ​ ​ ​ 5. The antigen-antibody affinity prediction method according to claim 4, wherein ​ ​ inputting the key energy parameters and the energy features into the affinity prediction deep neural network to predict the binding free energy.

6. The antigen-antibody affinity prediction method according to claim 1, wherein, The key energy parameters include van der Waals energy, electrostatic energy and solvation free energy.

7. The antigen-antibody affinity prediction method according to claim 5, wherein Further comprising: performing uncertainty evaluation on the predicted binding free energy to determine a corresponding confidence interval.

8. The antigen-antibody affinity prediction method according to claim 5, wherein, Further comprising: generating single-point and multi-point mutant conformations of the binding interface residues; calculating the difference in binding free energy before and after mutation for each mutant conformation, and analyzing the influence of mutation on affinity based on the difference in binding free energy.

9. An antigen-antibody affinity prediction system, characterized by, Comprising: a data input and structure prediction module for feature extraction on amino acid sequence data of the antigen and the antibody, and generating a preliminary complex three-dimensional conformation based on the feature extraction result and a preset prediction model; a conformation fusion and screening module for fusing and screening a plurality of preliminary complex three-dimensional conformations to determine an intermediate complex three-dimensional conformation; a binding interface optimization module for optimizing the binding interface of the intermediate complex three-dimensional conformation based on molecular dynamics simulation and reinforcement learning algorithm to obtain a final optimized conformation; a cross-scale affinity calculation module for energy decomposition on the final optimized conformation based on the principle of molecular force field, obtaining key energy parameters, and obtaining the binding free energy through a preset affinity prediction deep neural network based on the key energy parameters and energy features determined by molecular dynamics simulation; and comparing the binding free energy with a preset judgment threshold, if the binding free energy is higher than the judgment threshold, it is judged that the binding interface of the intermediate complex three-dimensional conformation needs to be optimized and the binding free energy needs to be determined, otherwise the binding free energy is output.

10. An antigen-antibody affinity prediction device characterized by comprising: Comprising a processor and a memory, the processor being connected with the memory: wherein the processor is used to call and execute a program stored in the memory; the memory is used to store the program, and the program is used to execute at least the antigen-antibody affinity prediction method of any one of claims 1-8.

Images