Method and device for generating antibody sequence based on deep learning diffusion generation

Through deep learning diffusion generation method and detailed data preprocessing, the problems of high computational cost, strong data dependence and insufficient sequence diversity in antibody design are solved, efficient and accurate antibody sequence generation are achieved, and the generalization ability of the model is improved and evaluation systems to generate higher quality antibody sequences.

CN118942533AActive Publication Date: 2024-11-12NANJING INST OF INTELLIGENT TECH INST OF MICROELECTRONICS OF THE CHINESE ACAD OF

Patent Information

Application Number
CN202411426755.8
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-10-14
Publication Date
2024-11-12
Estimated Expiration
2044-10-14

AI Technical Summary

Technical Problem

The existing antibody design technology has problems such as high computational cost, strong data dependence, insufficient sequence diversity and limited model generalization capabilities. It lacks a comprehensive evaluation system and makes it difficult to effectively evaluate the function and stability of the designed antibody.

Method used

Using the antibody sequence generation method based on deep learning diffusion generation, the efficient and accurate antibody sequence is generated through diffusion deep learning, complete data preprocessing process and modular design, and the diffusion process is used to remove noise, combine protein structure prediction and antigen antibody binding. Sex evaluation, the optimal antibody sequence was screened out.

Benefits of technology

It improves the efficiency and accuracy of antibody sequence generation, generates higher quality sequences, steadily optimizes model parameters, ensures the quality and consistency of input data, and improves the model training effect and the accuracy of generating sequences.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118942533A_ABST
    Figure CN118942533A_ABST
Patent Text Reader

Abstract

The invention discloses an antibody sequence generation method and device based on deep learning diffusion generation in the technical field of biological medicine. The method comprises the following steps: initializing to generate an initial antibody CDR sequence; the method comprises the following steps: acquiring antibody-antigen complex data for training, performing preprocessing of analysis, repair, classification and feature construction, and performing antibody sequence generator training after preprocessing; gradually denoising the initial antibody CDR sequence after training, generating a target antibody CDR sequence in each step, and respectively splicing the target antibody CDR sequence with the template antibody sequence to generate a target antibody sequence; obtaining a protein structure corresponding to each target antibody sequence, and physically splicing the protein structure with a protein structure of an antigen in antibody-antigen complex data input by a user to generate a target antigen-antibody complex; and screening out an optimal target antigen-antibody compound by adopting an antigen-antibody binding evaluation method to obtain an optimal target antibody sequence. The target antibody sequence can be efficiently and accurately generated.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the field of biomedicine technology, and in particular to a method and device for generating an antibody sequence based on deep learning diffusion generation. Background Art

[0002] Antibody design is one of the important research directions in the field of biomedicine. Antibodies are key defense tools in the immune system, and their main function is to identify and neutralize antigens such as foreign pathogens. Through precise design and optimization of antibody sequences, efficient treatments targeting specific antigens can be developed. Therefore, antibody design has great application potential in the treatment of cancer, infectious diseases, autoimmune diseases, etc.

[0003] The technologies in the field of antibody design mainly include traditional experimental methods and modern computational methods. Traditional antibody design mainly relies on laboratory screening techniques, such as phage display technology and monoclonal antibody preparation. These methods use a large number of experimental cultivation and screening to find antibodies that efficiently bind to the target antigen. However, experimental methods are time-consuming, labor-intensive, costly, and have low efficiency and success rates.

[0004] In recent years, with the improvement of computing power and the development of bioinformatics, computational methods have been widely used in antibody design. The main computational methods include molecular dynamics simulation, computer-aided antibody engineering, and deep learning methods. Molecular dynamics simulation simulates the interaction between antibodies and antigens, predicts the binding force and stability of antibodies, and thus screens suitable antibodies. This method requires high-performance computing resources, takes a long time to simulate, and cannot optimize and design unknown antigens. It belongs to the accelerated screening process. In order to overcome the problems of low antibody performance and poor resistance of unknown antibodies, computer-aided antibody engineering uses algorithms and databases combined with experimental data to design and optimize antibody sequences. This method can improve the efficiency of antibody design, but it depends on the quality of existing data and the degree of optimization of the algorithm. The development of deep learning methods has brought new progress to computer-aided antibody engineering. In recent years, deep learning has made significant progress in protein structure prediction and design. For example, the success of AlphaFold demonstrates the great potential of deep learning in protein structure prediction. This type of method can quickly predict the binding mode of antibodies and antigens and generate optimized antibody sequences by training neural network models. Compared with the past annealing algorithms, genetic algorithms, etc., deep learning methods can often design more effective antibody sequences.

[0005] Although existing technologies have made important progress in antibody design, there are still several major problems: High computing cost: Both molecular dynamics simulation and deep learning model training require a large amount of computing resources, which limits large-scale application and popularization, and requires professional computing centers to provide services and support.

[0006] Strong data dependence: The effectiveness of the computational method depends largely on the quality and quantity of sample data. The antibody-antigen complex data in the existing database may be biased or insufficient, affecting the effectiveness of the model design.

[0007] Insufficient sequence diversity: The antibody sequences generated by traditional and some computational methods are limited in diversity and may not be able to design antibodies that effectively target antigen binding sites, resulting in poor performance of the designed antibodies in practical applications.

[0008] The generalization ability of the model is limited: Deep learning models often perform better on sample data than on new data. How to improve the generalization ability of the model on new antigens is an important research direction.

[0009] Lack of a comprehensive evaluation system: Currently, the evaluation of antibody design mainly relies on computational simulation and a small amount of experimental verification. There is a lack of a systematic and comprehensive evaluation system, making it difficult to effectively evaluate the function and stability of designed antibodies. Summary of the invention

[0010] The purpose of the present invention is to overcome the shortcomings of the prior art and provide a method and device for generating antibody sequences based on deep learning diffusion generation. By introducing diffusion deep learning, a complete data preprocessing process and modular design, the invention aims to improve the efficiency and accuracy of antibody sequence generation and solve some bottleneck problems in the prior art.

[0011] To achieve the above object, the present invention is implemented by adopting the following technical solutions: In a first aspect, the present invention provides a method for generating an antibody sequence based on deep learning diffusion generation, comprising: Initializing and generating an initial antibody CDR sequence; the initial antibody CDR sequence is a completely random noise data; The initial antibody CDR sequence is gradually denoised by a trained antibody sequence generator, and a target antibody CDR sequence is generated at each step; Separately combining each of the target antibody CDR sequences with the template antibody sequence to generate a target antibody sequence; Performing protein structure prediction on each of the target antibody sequences using a protein structure prediction model to generate a corresponding protein structure; Physically splicing the predicted protein structures and the protein structure of the antigen in the antibody-antigen complex data input by the user to generate a target antigen-antibody complex; The target antigen-antibody complexes are evaluated by using an antigen-antibody binding evaluation method, the optimal target antigen-antibody complex is screened out, and the corresponding target antibody sequence is output.

[0012] Optionally, the training of the antibody sequence generator includes: Constructing a deep learning diffusion generation model, wherein the deep learning diffusion generation model includes a diffusion model, a residue embedding module and a residue sequence prediction module; the residue embedding module and the residue sequence prediction module constitute the antibody sequence generator; Obtaining antibody-antigen complex data for training, and performing preprocessing to generate antibody-antigen complex sample data; The diffusion model includes a diffusion process and a reverse diffusion process. In the diffusion process, the antibody CDR sequence in the antibody-antigen complex sample data is subjected to a step-by-step random noise addition operation. In the reverse diffusion process, the antibody CDR sequence finally obtained by the diffusion process is subjected to a step-by-step denoising operation by the antibody sequence generator. The model loss is calculated by the antibody CDR sequence generated by the noise addition operation and the antibody CDR sequence generated by the antibody sequence generator, and the model parameters of the antibody sequence generator are optimized through back propagation to complete the training.

[0013] Optionally, the preprocessing of the training antibody-antigen complex data includes: Selecting a target antigen type from the antibody-antigen complex data file; Parse the antibody sequence corresponding to the target antigen type to determine whether there is an antibody Fab region, whether there are missing values, whether there are multi-protein structural conformations, and whether there are unconventional amino acids, and perform repair processing; The repaired antibody sequence is adjusted to generate antibody-antigen complex sample data, wherein the adjustment process includes amino acid sequence rearrangement, antibody sequence floating point vectorization, continuity check, and CDR region marking; The antibody-antigen complex sample data is classified by a sequence classifier, and a training set and a test set are constructed based on the classification results.

[0014] Optionally, the pre-processed antibody-antigen complex data file also needs to undergo feature construction, which includes generating a mask for the marked CDR region, antigen region labeling, random mutation of the antibody, and calculation of binding site features.

[0015] Optionally, the residue embedding module includes a first feature extraction unit, a second feature extraction unit and a third feature extraction unit; The first feature extraction unit includes a first linear layer, a first Than layer, an identity mapping layer, a second linear layer and a second Than layer connected in sequence; dihedral angle information and position encoding are obtained from the antibody-antigen complex sample data, and are fused to obtain dihedral angle structural features; the dihedral angle structural features are input into the first feature extraction unit to generate a structural feature embedding vector; The second feature extraction unit includes a first embedding layer; obtaining atomic species and position codes from the antibody-antigen complex sample data, and fusing them to obtain atomic species features; inputting the atomic species features into the second feature extraction unit to generate an atomic species embedding vector; The third feature extraction unit includes a second embedding layer; obtaining residue types and position codes from the antigen-antibody complex sample data, and fusing them to obtain residue type features; inputting the residue type features into the third feature extraction unit to generate a residue type embedding vector; The dimensions of the structural feature embedding vector, the atomic type embedding vector, and the residue type embedding vector are aligned through a broadcast mechanism, and are added to generate a sequence feature embedding vector.

[0016] Optionally, the residue sequence prediction module comprises a plurality of Transformer decoders and predictors connected in sequence; The Transformer decoder includes a multi-head attention layer, a first normalization layer, a feedforward neural network layer, and a second normalization layer connected in sequence, and the input of the multi-head attention layer is additively connected to the output of the first normalization layer, and the input of the feedforward neural network is additively connected to the input of the second normalization layer; the feedforward neural network layer includes an amplification linear layer, a first ReLU layer, and a contraction linear layer connected in sequence; The predictor includes a fifth linear layer, a second ReLU layer, a sixth linear layer, and a third ReLU layer connected in sequence; The sequence feature embedding vector obtained by the residue embedding module is input into the residue sequence prediction module to generate an antibody CDR sequence.

[0017] Optionally, the random noise addition operation in the diffusion process is a predefined Markov chain process, and its transition probability is , In the diffusion process, The operation of removing noise in the reverse diffusion process is a parameterized Markov chain process, and its transition probability is , are the first The antibody CDR sequence of the step are the model parameters of the antibody sequence generator.

[0018] Optionally, the antibody sequence generator minimizes the model loss by maximizing the variational lower bound; The variational lower bound for: ; In the formula, is the antibody CDR sequence at step 0 in the diffusion process The approximate posterior distribution The probability distribution of the antibody CDR sequence in the antibody-antigen complex sample data is used as the approximate posterior distribution ; is the antibody CDR sequence in step 1 of the diffusion process Given the antibody CDR sequence at step 0 The conditional probability distribution expectation under ; is the antibody CDR sequence at step 0 in the reverse diffusion process Given the antibody CDR sequence in step 1 The log-likelihood of the conditional probability distribution under ; is the KL divergence function, In the diffusion process T Antibody CDR sequences In a given antibody CDR sequence The conditional probability distribution under T is the total number of steps in the diffusion process or reverse diffusion process; The probability distribution of the antibody CDR sequence finally obtained by the diffusion process is used as the prior distribution ; In the diffusion process Antibody CDR sequences In a given antibody CDR sequence The conditional probability distribution expectation under ; In the diffusion process Antibody CDR sequences In a given antibody CDR sequence The conditional probability distribution under ; In the reverse diffusion process Antibody CDR sequences In the given Antibody CDR sequences The conditional probability distribution under ; Based on the variational lower bound Constructing the loss function of the model loss : ; In the formula, is a hyperparameter, is the antibody CDR sequence in the reverse diffusion process In a given antibody CDR sequence The log-likelihood of the conditional probability distribution under .

[0019] In a second aspect, the present invention provides an antibody sequence generation device based on deep learning diffusion generation, comprising: An initialization module is configured to initialize and generate an initial antibody CDR sequence; the initial antibody CDR sequence is a completely random noise data; The target generation module is configured to gradually denoise the initial antibody CDR sequence through a trained antibody sequence generator, and generate a target antibody CDR sequence at each step; each of the target antibody CDR sequences is respectively combined with a template antibody sequence to generate a target antibody sequence; A structure prediction module is configured to perform protein structure prediction on each of the target antibody sequences using a protein structure prediction model to generate a corresponding protein structure; A physical splicing module is configured to physically splice the protein structures generated by the predictions and the protein structure of the antigen in the antibody-antigen complex data input by the user to generate a target antigen-antibody complex; The antibody screening module is configured to evaluate each of the target antigen-antibody complexes using an antigen-antibody binding evaluation method, screen out the optimal target antigen-antibody complex, and output its corresponding target antibody sequence.

[0020] In a third aspect, the present invention provides an electronic device, including a processor and a storage medium; The storage medium is used to store instructions; The processor is used to operate according to the instructions to execute the steps according to the above method.

[0021] Compared with the prior art, the present invention has the following beneficial effects: The present invention provides a method and device for generating antibody sequences based on deep learning diffusion generation. 1) The antibody CDR sequence is generated by an antibody sequence generator based on diffusion deep learning, and then the target antibody sequence is generated by splicing with the template antibody sequence. The sequence generation process is efficient and accurate; then the target antigen-antibody complex is generated based on the target antibody sequence, and the antigen-antibody binding evaluation method is used to screen and obtain the final target antibody sequence. 2) In the diffusion deep learning process, the noise can be gradually removed through the forward and reverse diffusion processes, so as to generate an antibody CDR sequence that matches the input data distribution. This method can generate higher quality sequences, and the training process can optimize the model parameters more stably. 3) Through the residue embedding module and the residue sequence prediction module, the antibody sequence can be accurately predicted. The residue embedding module uses the protein molecular structure and type characteristics to embed residues, and combines the Transformer Decoder multi-layer stacking process to enable the predictor to work better. 4) Through detailed data preprocessing and feature extraction steps, the quality and consistency of the input data are ensured, thereby improving the effect of model training and the accuracy of the generated sequence. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] Figure 1 is a flow chart of a method for generating an antibody sequence based on deep learning diffusion generation provided in an embodiment of the present invention; Figure 2 is a schematic diagram of the structure of an antibody sequence generator provided by an embodiment of the present invention; Figure 3 is a schematic diagram of the structure of a residue embedding module provided in an embodiment of the present invention; Figure 4 is a schematic diagram of the structure of a residue sequence prediction module provided by the present invention; Figure 5 It is a schematic diagram of the diffusion process and the reverse diffusion process of the antibody sequence generator provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0023] The present invention will be further described below in conjunction with the accompanying drawings. The following embodiments are only used to more clearly illustrate the technical solution of the present invention, and cannot be used to limit the protection scope of the present invention.

[0024] Embodiment 1:

[0025] like Figure 1 As shown, the present invention provides a method for generating antibody sequences based on deep learning diffusion generation, comprising the following steps: Step S1, initializing and generating an initial antibody CDR sequence; the initial antibody CDR sequence is a completely random noise data.

[0026] The initial antibody CDR sequence is the starting point of the process of generating the target antibody CDR sequence.

[0027] Step S2: The initial antibody CDR sequence is gradually denoised using a trained antibody sequence generator, and a target antibody CDR sequence is generated in each step.

[0028] To train the antibody sequence generator, it is necessary to first collect the original antibody-antigen complex data files from the database, data set or user input. The file format of the antibody-antigen complex data file is generally a Protein Data Bank (PDB) file. The antibody-antigen complex in the PDB file is specifically the product of the physical combination of the antibody and the antigen.

[0029] The antibody in the antibody-antigen complex is specifically the Fab region (Fragment antigen-binding region) of the human antibody, including the variable regions (VH and VL) of the antibody and their binding sites. The antigen in the antibody-antigen complex is specifically the receptor binding domain (RBD) region fragment on the selected antigen protein.

[0030] Specifically in this embodiment, the training of the antibody sequence generator includes: Step S2.1, constructing a deep learning diffusion generation model, the deep learning diffusion generation model includes a diffusion model, a residue embedding module and a residue sequence prediction module; Figure 2 As shown, the residue embedding module and the residue sequence prediction module constitute the antibody sequence generator.

[0031] like Figure 3 As shown, the residue embedding module includes a first feature extraction unit, a second feature extraction unit and a third feature extraction unit.

[0032] The first feature extraction unit includes a first linear layer, a first Than layer, an identity mapping layer, a second linear layer and a second Than layer connected in sequence; dihedral angle information and position encoding are obtained from the antibody-antigen complex sample data, and the dihedral angle structural features are obtained by fusion; the dihedral angle structural features are input into the first feature extraction unit to generate a structural feature embedding vector; In the molecular structure characteristics, the angle between two planes formed by four consecutive atoms in a protein molecule is called a dihedral angle. This feature is very important for the dynamic properties and structural stability of the protein. Therefore, the dihedral angle is added to the position code as the protein molecular structure feature.

[0033] The second feature extraction unit includes a first embedding layer; obtaining atomic species and position codes from the antibody-antigen complex sample data, and fusing them to obtain atomic species features; inputting the atomic species features into the second feature extraction unit to generate an atomic species embedding vector; The third feature extraction unit includes a second embedding layer; obtaining residue type and position codes from the antigen-antibody complex sample data, and fusing them to obtain residue type features; inputting the residue type features into the third feature extraction unit to generate a residue type embedding vector; The dimensions of the structural feature embedding vector, atom species embedding vector, and residue species embedding vector are aligned through a broadcasting mechanism and added together to generate a sequence feature embedding vector.

[0034] like Figure 4 As shown, the residue sequence prediction module includes multiple Transformer decoders and predictors connected in sequence; the residue sequence prediction module is used to predict and generate an antibody sequence based on a sequence feature embedding vector.

[0035] The Transformer decoder includes a multi-head attention layer, a first normalization layer, a feedforward neural network layer, and a second normalization layer connected in sequence, and the input of the multi-head attention layer is added to the output of the first normalization layer, and the input of the feedforward neural network is added to the input of the second normalization layer; the feedforward neural network layer includes an amplification linear layer, a first ReLU layer, and a contraction linear layer connected in sequence; The predictor includes a fifth linear layer, a second ReLU layer, a sixth linear layer, and a third ReLU layer connected in sequence; The sequence feature embedding vector obtained by the residue embedding module is input into the residue sequence prediction module to generate the antibody CDR sequence.

[0036] The output after the multi-head self-attention mechanism is processed by layer normalization to standardize the activation values ​​of each layer to stabilize the training process. The normalized output is further processed by a feedforward neural network. This network usually contains two linear transformations and a ReLU activation function, which increases the information expression ability of the model by performing non-high-dimensional linear transformation on the input. The output of the feedforward neural network is processed again by layer normalization to further stabilize and standardize the output. Residual connections are introduced between the input and output of the multi-head self-attention mechanism and the feedforward neural network to alleviate the gradient vanishing problem and improve the training effect of the model. Each decoder layer repeats the above structure. By stacking multiple such layers, the Transformer Decoder can gradually build more complex feature representations and achieve efficient sequence feature to sequence feature conversion, so that the predictor can work better. The stacking layer number parameter of the Transformer Decoder module is 7, the multi-head parameter is 8, the dimension of the hidden layer in the multi-head self-attention layer is 336; the scaling factor of the residual connection is 1; the predictor dimension parameter is 128.

[0037] Step S2.2: Obtain antibody-antigen complex data for training, and perform preprocessing to generate antibody-antigen complex sample data.

[0038] The preprocessing process specifically includes: Step S2.2.1, selecting the target antigen type from the antibody-antigen complex data file.

[0039] Step S2.2.2: Analyze the antibody sequence corresponding to the target antigen type to determine whether there is an antibody Fab region, whether there are missing values, whether there are multiple protein structure conformations, and whether there are unconventional amino acids, and perform repair processing. If repair is not possible, the calculation is terminated and a link problem is prompted.

[0040] Step S2.2.3, the repaired antibody sequence is adjusted to generate antibody-antigen complex sample data, and the adjustment process includes amino acid sequence rearrangement, antibody sequence floating point vectorization, continuity check and CDR region marking.

[0041] Step S2.2.4: Classify the antibody-antigen complex sample data using a sequence classifier, and construct a training set and a test set based on the classification results. When training for the first time or when no classifier exists, use MMseqs2 to construct an unsupervised classifier and perform similarity clustering training on the sequences.

[0042] Step S2.2.5: The pre-processed antibody-antigen complex data file also needs to undergo feature construction, which includes generating a mask for the marked CDR region, antigen region labeling, random mutation of the antibody, and calculation of binding site features.

[0043] Step S2.3, the diffusion model includes the diffusion process and the reverse diffusion process, such as Figure 5 As shown, during the diffusion process, the antibody CDR sequence in the antibody-antigen complex sample data is subjected to a step-by-step random noise addition operation, and during the reverse diffusion process, the antibody CDR sequence finally obtained by the diffusion process is subjected to a step-by-step denoising operation through the antibody sequence generator.

[0044] The random noise addition operation in the diffusion process is a predefined Markov chain process with a transition probability of , In the diffusion process, The noise removal operation in the reverse diffusion process is a parameterized Markov chain process with a transition probability of , are the first The antibody CDR sequence of the step are the model parameters of the antibody sequence generator.

[0045] Step S2.4, the antibody CDR sequence generated by the noise addition operation and the antibody CDR sequence generated by the antibody sequence generator are used to calculate the model loss and back-propagate to optimize the model parameters of the antibody sequence generator to complete the training.

[0046] The antibody sequence generator minimizes the model loss by maximizing the variational lower bound; Variational lower bound for: ; In the formula, is the antibody CDR sequence at step 0 in the diffusion process The approximate posterior distribution The probability distribution of the antibody CDR sequence in the antibody-antigen complex sample data is used as the approximate posterior distribution ; is the antibody CDR sequence in step 1 of the diffusion process Given the antibody CDR sequence at step 0 The conditional probability distribution expectation under ; is the antibody CDR sequence at step 0 in the reverse diffusion process Given the antibody CDR sequence in step 1 The log-likelihood of the conditional probability distribution under ; is the KL divergence function, In the diffusion process T Antibody CDR sequences In a given antibody CDR sequence The conditional probability distribution underT is the total number of steps in the diffusion process or reverse diffusion process; The probability distribution of the antibody CDR sequence finally obtained by the diffusion process is used as the prior distribution ; In the diffusion process Antibody CDR sequences In a given antibody CDR sequence The conditional probability distribution expectation under ; In the diffusion process Antibody CDR sequences In a given antibody CDR sequence The conditional probability distribution under ; In the reverse diffusion process Antibody CDR sequences In the given Antibody CDR sequences The conditional probability distribution under ; ; In the formula, , , is the matrix transpose, is element-wise multiplication, For the parameter Specified description The distribution of classification categories; For the The transition probability matrix of the step, is the transition probability matrix Middle Line Elements of a column; ; is the number of classification categories of antibody sequences, For the A sequence of steps, with the number of steps decreasing.

[0047] Based on variational lower bound Constructing the loss function of the model loss : ; In the formula, is a hyperparameter, is the antibody CDR sequence in the reverse diffusion process In a given antibody CDR sequence The log-likelihood of the conditional probability distribution under .

[0048] Step S3: Each target antibody CDR sequence is combined with the template antibody sequence to generate a target antibody sequence.

[0049] Step S4: using a protein structure prediction model (Alphafold) to predict the protein structure of each target antibody sequence to generate a corresponding protein structure.

[0050] Step S5: Physically splice (ZDOCK) each predicted protein structure and the protein structure of the antigen in the antibody-antigen complex data input by the user to generate a target antigen-antibody complex.

[0051] Step S6: using the antigen-antibody binding evaluation method (ROSETTA) to evaluate each target antigen-antibody complex, screen out the optimal target antigen-antibody complex, and output its corresponding target antibody sequence.

[0052] Embodiment 2:

[0053] Based on the antibody sequence generation method provided in Example 1, the embodiment of the present invention further provides an antibody sequence generation device based on deep learning diffusion generation, including: An initialization module is configured to initialize and generate an initial antibody CDR sequence; the initial antibody CDR sequence is a completely random noise data; The target generation module is configured to gradually denoise the initial antibody CDR sequence through a trained antibody sequence generator, and generate a target antibody CDR sequence at each step; each of the target antibody CDR sequences is respectively combined with a template antibody sequence to generate a target antibody sequence; A structure prediction module is configured to perform protein structure prediction on each of the target antibody sequences using a protein structure prediction model to generate a corresponding protein structure; A physical splicing module is configured to physically splice the protein structures generated by the predictions and the protein structure of the antigen in the antibody-antigen complex data input by the user to generate a target antigen-antibody complex; The antibody screening module is configured to evaluate each of the target antigen-antibody complexes using an antigen-antibody binding evaluation method, screen out the optimal target antigen-antibody complex, and output its corresponding target antibody sequence.

[0054] Embodiment three:

[0055] Based on the antibody sequence generation method provided in Example 1, an embodiment of the present invention further provides an electronic device, characterized in that it includes a processor and a storage medium; The storage medium is used to store instructions; The processor is used to operate according to the instructions to execute the steps according to the above method.

[0056] It will be appreciated by those skilled in the art that embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Furthermore, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0057] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0058] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0059] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.

[0060] The above is only a preferred embodiment of the present invention. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the technical principles of the present invention. These improvements and modifications should also be regarded as the scope of protection of the present invention.

Claims

1. A method for generating antibody sequences based on deep learning diffusion generation, It is characterized in that include: Initializing and generating an initial antibody CDR sequence; the initial antibody CDR sequence is a completely random noise data; The initial antibody CDR sequence is gradually denoised by a trained antibody sequence generator, and a target antibody CDR sequence is generated at each step; Separately combining each of the target antibody CDR sequences with the template antibody sequence to generate a target antibody sequence; Performing protein structure prediction on each of the target antibody sequences using a protein structure prediction model to generate a corresponding protein structure; Physically splicing the predicted protein structures and the protein structure of the antigen in the antibody-antigen complex data input by the user to generate a target antigen-antibody complex; The target antigen-antibody complexes are evaluated by using an antigen-antibody binding evaluation method, the optimal target antigen-antibody complex is screened out, and the corresponding target antibody sequence is output.

2. The method for generating antibody sequences based on deep learning diffusion generation according to claim 1, It is characterized in that The training of the antibody sequence generator comprises: Constructing a deep learning diffusion generation model, wherein the deep learning diffusion generation model includes a diffusion model, a residue embedding module and a residue sequence prediction module; the residue embedding module and the residue sequence prediction module constitute the antibody sequence generator; Obtaining antibody-antigen complex data for training, and performing preprocessing to generate antibody-antigen complex sample data; The diffusion model includes a diffusion process and a reverse diffusion process. In the diffusion process, the antibody CDR sequence in the antibody-antigen complex sample data is subjected to a step-by-step random noise addition operation. In the reverse diffusion process, the antibody CDR sequence finally obtained in the diffusion process is subjected to a step-by-step denoising operation by the antibody sequence generator. The model loss is calculated by the antibody CDR sequence generated by the noise addition operation and the antibody CDR sequence generated by the antibody sequence generator, and the model parameters of the antibody sequence generator are optimized through back propagation to complete the training.

3. The method for generating antibody sequences based on deep learning diffusion generation according to claim 2, It is characterized in that The preprocessing of the training antibody-antigen complex data includes: Selecting a target antigen type from the antibody-antigen complex data file; Parse the antibody sequence corresponding to the target antigen type to determine whether there is an antibody Fab region, whether there are missing values, whether there are multi-protein structural conformations, and whether there are unconventional amino acids, and perform repair processing; Adjusting the repaired antibody sequence to generate antibody-antigen complex sample data, wherein the adjustment process includes amino acid sequence rearrangement, antibody sequence floating point vectorization, continuity check, and CDR region marking; The antibody-antigen complex sample data is classified by a sequence classifier, and a training set and a test set are constructed based on the classification results.

4. The method for generating antibody sequences based on deep learning diffusion generation according to claim 2, It is characterized in that The pre-processed antibody-antigen complex data file also needs to undergo feature construction, which includes generating a mask for the marked CDR region, antigen region marking, random mutation of the antibody, and calculation of binding site features.

5. The method for generating antibody sequences based on deep learning diffusion generation according to claim 2, It is characterized in that The residue embedding module includes a first feature extraction unit, a second feature extraction unit and a third feature extraction unit; The first feature extraction unit includes a first linear layer, a first Than layer, an identity mapping layer, a second linear layer and a second Than layer connected in sequence; dihedral angle information and position encoding are obtained from the antibody-antigen complex sample data, and are fused to obtain dihedral angle structural features; the dihedral angle structural features are input into the first feature extraction unit to generate a structural feature embedding vector; The second feature extraction unit includes a first embedding layer; obtaining atomic species and position codes from the antibody-antigen complex sample data, and fusing them to obtain atomic species features; Inputting the atomic species feature into a second feature extraction unit to generate an atomic species embedding vector; The third feature extraction unit includes a second embedding layer; obtaining residue types and position codes from the antigen-antibody complex sample data, and fusing them to obtain residue type features; inputting the residue type features into the third feature extraction unit to generate a residue type embedding vector; The dimensions of the structural feature embedding vector, the atomic type embedding vector, and the residue type embedding vector are aligned through a broadcast mechanism, and are added to generate a sequence feature embedding vector.

6. The method for generating antibody sequences based on deep learning diffusion generation according to claim 2, It is characterized in that The residue sequence prediction module includes a plurality of Transformer decoders and predictors connected in sequence; The Transformer decoder includes a multi-head attention layer, a first normalization layer, a feedforward neural network layer, and a second normalization layer connected in sequence, and the input of the multi-head attention layer is additively connected to the output of the first normalization layer, and the input of the feedforward neural network is additively connected to the input of the second normalization layer; the feedforward neural network layer includes an amplification linear layer, a first ReLU layer, and a contraction linear layer connected in sequence; The predictor includes a fifth linear layer, a second ReLU layer, a sixth linear layer, and a third ReLU layer connected in sequence; The sequence feature embedding vector obtained by the residue embedding module is input into the residue sequence prediction module to generate an antibody CDR sequence.

7. The method for generating antibody sequences based on deep learning diffusion generation according to claim 2, It is characterized in that The random noise addition operation in the diffusion process is a predefined Markov chain process, and its transition probability is , In the diffusion process, The operation of removing noise in the reverse diffusion process is a parameterized Markov chain process, and its transition probability is , are the first The antibody CDR sequence of the step are the model parameters of the antibody sequence generator.

8. The method for generating antibody sequences based on deep learning diffusion generation according to claim 2, It is characterized in that The antibody sequence generator minimizes the model loss by maximizing the variational lower bound; The variational lower bound for: ; In the formula, is the antibody CDR sequence at step 0 in the diffusion process The approximate posterior distribution The probability distribution of the antibody CDR sequence in the antibody-antigen complex sample data is used as the approximate posterior distribution ; is the antibody CDR sequence in step 1 of the diffusion process Given the antibody CDR sequence at step 0 The conditional probability distribution expectation under ; is the antibody CDR sequence at step 0 in the reverse diffusion process Given the antibody CDR sequence in step 1 The log-likelihood of the conditional probability distribution under ; is the KL divergence function, In the diffusion process T Antibody CDR sequences In a given antibody CDR sequence The conditional probability distribution under T is the total number of steps in the diffusion process or reverse diffusion process; The probability distribution of the antibody CDR sequence finally obtained by the diffusion process is used as the prior distribution ; In the diffusion process Antibody CDR sequences In a given antibody CDR sequence The conditional probability distribution expectation under ; In the diffusion process Antibody CDR sequences In a given antibody CDR sequence The conditional probability distribution under ; In the reverse diffusion process Antibody CDR sequences In the given Antibody CDR sequences The conditional probability score under ; Based on the variational lower bound Constructing the loss function of the model loss : ; In the formula, is a hyperparameter, is the antibody CDR sequence in the reverse diffusion process In a given antibody CDR sequence The log-likelihood of the conditional probability distribution under . 9.An antibody sequence generation device based on deep learning diffusion generation, It is characterized in that include: An initialization module is configured to initialize and generate an initial antibody CDR sequence; the initial antibody CDR sequence is a completely random noise data; The target generation module is configured to gradually denoise the initial antibody CDR sequence through a trained antibody sequence generator, and generate a target antibody CDR sequence at each step; each of the target antibody CDR sequences is respectively combined with a template antibody sequence to generate a target antibody sequence; A structure prediction module is configured to perform protein structure prediction on each of the target antibody sequences using a protein structure prediction model to generate a corresponding protein structure; A physical splicing module is configured to physically splice the protein structures generated by the predictions and the protein structure of the antigen in the antibody-antigen complex data input by the user to generate a target antigen-antibody complex; The antibody screening module is configured to evaluate each of the target antigen-antibody complexes using an antigen-antibody binding evaluation method, screen out the optimal target antigen-antibody complex, and output its corresponding target antibody sequence.

10. An electronic device, It is characterized in that including processor and storage medium; The storage medium is used to store instructions; The processor is configured to operate according to the instructions to execute the steps of the method according to any one of claims 1-8.

Citation Information

Patent Citations

  • Virus structural protein-based bioactive component screening system

    CN114300039A

  • Deep learning model-based antibody structure optimization method and device

    CN116741260A

  • Method and equipment for determining sequence structure of antibody

    CN116844632A

  • Deep learning model-based antibody developability prediction method and device

    CN117637029A

  • Method for designing antibody structure and sequence based on generative neural network model

    CN118335202A

Cited By

  • Nanometer antibody and antigen interaction prediction method, device, equipment and medium

    CN121747702A

  • Method, apparatus, and medium for predicting nanobody-antigen interaction

    CN121747702B