Protein de novo reverse design method and system based on spectrum structure-activity relationship

Abstract

The invention discloses a protein de novo reverse design method and system based on a spectrum structure-activity relationship, and the method comprises the steps: obtaining a data set which comprises protein structure feature data, protein simulation spectrum data and protein-ligand interaction data; establishing a multi-task neural network model, training the multi-task neural network model by using the data set, inputting protein simulation spectrum data into the trained multi-task neural network model, and simultaneously obtaining a distance matrix between protein skeleton atoms and the number of protein amino acids; integrating the distance matrix between protein skeleton atoms and the number of protein amino acids to obtain a final protein distance matrix; obtaining an initial protein PDB structure according to the final protein distance matrix; optimizing the initial protein PDB structure by using an SCUBA-D protein structure optimization model to obtain a full-atom protein structure; proteinMPNN is applied, a full-atom protein structure is used as input, and a plurality of amino acid sequences are obtained. The development period of the medicine can be accelerated.

Description

Technical Field

[0001] The present invention relates to the technical field of spectral inversion quantum chemistry theory, and specifically to a method and system for protein de novo reverse design based on spectral structure-activity relationship. Background Art

[0002] In recent years, the field of protein design, especially de novo design, has made significant progress. However, the field still faces many challenges. Traditional protein design methods mainly rely on two types of models: sequence-based models and structure-based models. Sequence-based models design by learning the statistical characteristics and patterns of protein sequences, while structure-based models focus on the three-dimensional structural information of proteins. Although these methods have been successful in certain scenarios, there are still many limitations when dealing with complex protein function design, such as multi-property fusion. The design of protein function usually requires the optimization of multiple objectives, such as stability, catalytic efficiency and specificity.

[0003] How to effectively integrate these properties in a high-dimensional structural space has become a difficult problem, and existing methods have difficulty making breakthroughs in multi-objective optimization. End-to-end design: The hugeness of the sequence space, the complexity of structure prediction, and the challenges of multi-objective optimization make end-to-end protein design very difficult. Existing methods are difficult to meet the multiple requirements of sequence, structure, and function at the same time, and the designed proteins often cannot effectively balance these factors. Dynamic protein design: Current design methods mainly focus on the design of fixed skeletons, ignoring the dynamic behavior of proteins in different states. However, the dynamic changes of proteins are crucial to the realization of their functions. Existing technologies do not adequately consider this dynamic behavior, which limits the flexibility and functional diversity of the design. Therefore, how to overcome the challenges of multi-property fusion, dynamic behavior simulation, and end-to-end design has become an urgent problem to be solved in the current field of protein design. Summary of the invention

[0004] The technical problem to be solved by the present invention is to solve the problem that the prior art does not take into account the dynamic behavior of proteins sufficiently, thus limiting the flexibility of design and the diversity of functions.

[0005] In order to solve the above technical problems, the present invention provides the following technical solutions:

[0006] A protein de novo reverse design method based on spectrum structure-activity relationship, comprising:

[0007] S10, acquiring a data set, wherein the data set includes protein structural feature data, protein simulated spectrum data, and protein-ligand interaction data;

[0008] S20, establishing a multi-task neural network model, training it using the data set, inputting protein simulation spectrum data into the trained multi-task neural network model, and simultaneously obtaining the distance matrix between protein skeleton atoms and the number of protein amino acids;

[0009] S30, integrating the distance matrix between protein backbone atoms and the number of protein amino acids to obtain the final protein distance matrix;

[0010] S40, obtaining the initial protein PDB structure based on the final protein distance matrix;

[0011] S50, using the SCUBA-D protein structure optimization model to optimize the initial protein PDB structure and obtain the all-atom protein structure;

[0012] S60, applying the ProteinMPNN algorithm, takes the all-atom protein structure as input and obtains multiple amino acid sequences.

[0013] In one embodiment of the present invention, before obtaining protein simulation spectrum data, initial protein simulation spectrum data is first obtained, including the following steps:

[0014] Obtain an initial PDB structure file from the RCSB protein PDB database; wherein the initial PDB structure file includes protein three-dimensional structure data;

[0015] Perform molecular dynamics simulation of the protein on the initial PDB structure file to obtain molecular dynamics simulation data;

[0016] AIM was used to calculate the molecular dynamics simulation data to obtain the intermolecular interaction data; NISE was used to convert the intermolecular interaction data into conversion spectral data to obtain the initial protein simulation spectral data.

[0017] In one embodiment of the present invention, protein structural feature data, protein simulated spectral data, and protein-ligand interaction data are obtained by:

[0018] The protein three-dimensional structure data is converted into a protein two-dimensional distance matrix; at the same time, the initial protein simulation spectrum data is formatted to obtain a protein simulation spectrum two-dimensional matrix; and the protein two-dimensional distance matrix and the protein simulation spectrum two-dimensional matrix are normalized;

[0019] According to the topological structure of the protein, the normalized two-dimensional protein distance matrix and the two-dimensional matrix of protein simulated spectrum are classified simultaneously to obtain protein structural feature data and protein simulated spectrum data;

[0020] A mapping relationship is established between protein structural feature data and protein simulated spectral data with the same protein structural features and properties to obtain protein-ligand interaction data.

[0021] In one embodiment of the present invention, the network architecture of the multi-task neural network model includes: an input layer, a convolutional layer, a fully connected layer, a multi-layer feature extraction layer, a feature fusion layer and an output layer; wherein,

[0022] Input layer, used for normalization preprocessing of protein simulation spectral data;

[0023] Convolutional layers, used to extract spatial features in protein simulation spectral data;

[0024] The fully connected layer is used to map the spatial features in the protein simulation spectral data extracted in the convolutional layer to the structural feature space of the protein and obtain the distance matrix between the initial protein skeleton atoms;

[0025] The multi-layer feature extraction layer includes a first-layer feature extraction, a second-layer feature extraction and a third-layer feature extraction; and the extraction scales from the first-layer feature extraction to the third-layer feature extraction are increased in sequence; the three-layer feature extraction is used to extract features of different levels of scales from the distance matrix between the initial protein skeleton atoms;

[0026] The feature fusion layer is used to use the splicing function to splice and fuse the features of different levels extracted from the multiple feature extraction layers to obtain the final distance matrix between the protein skeleton atoms;

[0027] The output layer includes a protein structure output layer and an amino acid number output layer; the protein structure output layer directly outputs the final distance matrix between protein backbone atoms; the protein structure is obtained based on the distance matrix between protein backbone atoms, and the characteristic lengths of all output protein structures are unified. The amino acid number output layer adopts a filling method to fill in the missing amino acids with invalid information, so that the characteristic lengths of all output protein structures are unified, and then the number of amino acids is output.

[0028] In one embodiment of the present invention, obtaining the final protein distance matrix includes: adjusting the dimension of the distance matrix between protein backbone atoms according to the number of protein amino acids, and using the PyRosetta tool to generate the initial protein PDB structure from the distance matrix between protein backbone atoms after the dimension adjustment.

[0029] In one embodiment of the present invention, obtaining the full-atom protein structure includes: establishing a protein index mapping and a configuration of protein structure optimization to ensure that the SCUBA-D protein structure optimization model can process each part of the protein; the SCUBA-D protein structure optimization model is based on energy calculations of molecular dynamics and force fields, and achieves energy minimization by continuously adjusting the main chain and side chain of the protein to optimize the full-atom structure of the protein and obtain the full-atom protein structure.

[0030] In one embodiment of the present invention, obtaining multiple amino acid sequences includes: using ProteinMPNN algorithm to perform global energy calculation on atomic protein structure, and generating multiple amino acid sequences according to the energy minimization principle.

[0031] In one embodiment of the present invention, the protein de novo reverse design method based on spectrum-structure-activity relationship also includes step S100, which is located between step S10 and step S20; wherein step S100 is: establishing a spectral diffusion generation model based on a neural network; using protein simulated spectral data and input custom protein description as inputs of the spectral diffusion generation model for training, and outputting custom diffuse protein spectral data; wherein the input custom protein description is obtained in the following manner: using a script to generate a mapping relationship file between the spectrum and the custom description, the mapping relationship file records the matching relationship between each spectral data and its corresponding protein attribute, function and topological description.

[0032] In one embodiment of the present invention, according to user needs, a custom protein description is input into a trained spectral diffusion generation model to output custom diffuse protein spectral data, and then the custom diffuse protein spectral data is executed from step S20 to step S60.

[0033] The present invention also provides a protein de novo reverse design system based on spectrum structure-activity relationship, which uses the above-mentioned protein de novo reverse design method based on spectrum structure-activity relationship, comprising:

[0034] Dataset module: used to obtain data sets, where the data sets include protein structural feature data, protein simulation spectrum data, and protein-ligand interaction data;

[0035] The multi-task prediction module is used to establish a multi-task neural network model, train it using a data set, input protein simulation spectrum data into the trained multi-task neural network model, and simultaneously obtain the distance matrix between protein skeleton atoms and the number of protein amino acids;

[0036] The protein distance matrix module is used to integrate the distance matrix between protein backbone atoms and the number of protein amino acids to obtain the final protein distance matrix;

[0037] Initial PDB module, used to obtain the initial protein PDB structure based on the final protein distance matrix;

[0038] All-atom protein structure module, which is used to optimize the initial protein PDB structure using the SCUBA-D protein structure optimization model to obtain the all-atom protein structure;

[0039] The amino acid sequence module is used to apply the ProteinMPNN algorithm to obtain multiple amino acid sequences using all-atom protein structures as input.

[0040] Compared with the prior art, the beneficial effects of the present invention are: by establishing the potential relationship between protein spectral data and protein properties and topological structure, data-driven guidance is provided for efficient and rapid protein design, spectral data is automatically processed and analyzed, the efficiency and accuracy of spectral data analysis are effectively improved, and a spectral diffusion generation model with multiple training and stable effects is provided, which can design proteins that meet the requirements only under the condition that the user provides the design target. The system is used to guide the design and optimization of proteins, can quickly screen and verify proteins with specified requirements, accelerate the drug development cycle, and reduce R&D costs.

[0041] It is easy to operate and can automatically process user needs and design specified protein structures. This automated feature reduces the workload of users in the data processing process and improves processing efficiency. It combines the latest diffusion model to achieve efficient protein de novo design. The results are verified by the most advanced AF2 and AF3, which greatly accelerates drug development and design as well as the discovery and exploration of new functional proteins, and has great potential.

[0042] The initial protein simulation spectral data are based on molecular dynamics simulation to study the dynamic behavior of proteins, and the spectral diffusion generation model is user-defined, enabling flexible protein design. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] Figure 1 The present invention is a flowchart of a method for de novo reverse design of proteins based on spectrum structure-activity relationship.

[0044] Figure 2 4 is a network architecture diagram of a multi-task neural network model according to an embodiment of the present invention.

[0045] Figure 3 This is a graph showing the accuracy of the protein design results according to an embodiment of the present invention.

[0046] Figure 4 A block diagram of a system for de novo reverse design of proteins based on spectrum-structure-activity relationship according to an embodiment of the present invention. DETAILED DESCRIPTION

[0047] In order to facilitate those skilled in the art to understand the technical solution of the present invention, the technical solution of the present invention is further described in conjunction with the accompanying drawings of the specification.

[0048] The terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of the features. In the description of this application, the meaning of "plurality" is two or more, unless otherwise clearly and specifically defined.

[0049] See also Figure 1 As shown, the present invention discloses a method for de novo reverse design of proteins based on spectrum structure-activity relationship, comprising the following steps:

[0050] S10, acquiring a data set, wherein the data set includes protein structural feature data, protein simulation spectrum data, and protein-ligand interaction data.

[0051] In one embodiment of the present invention, before obtaining protein simulation spectrum data, initial protein simulation spectrum data is first obtained, including the following steps:

[0052] S11, obtaining an initial PDB structure file from the RCSB protein PDB database; wherein the initial PDB structure file includes protein three-dimensional structure data.

[0053] In this embodiment, the RCSB protein PDB database is an open source database. As needed, the three-dimensional structure of the required protein can be downloaded from the RCSB protein PDB database and saved in PDB format to provide an initial structure for molecular dynamics simulation.

[0054] In the present embodiment, the pdbfixer package can be used to repair the initial PDB structure file, handle the problems such as the atoms, residues or chains of protein deletions and the residue naming problem, ensure that the PDB structure file is complete and correct, and prepare for subsequent simulation and analysis. This process involves the arrangement and standardization of the PDB structure file to ensure that it meets the requirements of subsequent calculations and simulations. The initial PDB structure file contains the atomic coordinate information of the protein and is the basis for all subsequent calculations. Therefore, in this step, the present invention ensures that the file format is correct, and pre-processes any potential problems to lay a solid foundation for molecular dynamics simulation and spectral calculation.

[0055] S12, performing molecular dynamics simulation of the protein on the initial PDB structure file to obtain molecular dynamics simulation data.

[0056] In the present embodiment, molecular dynamics simulation is performed using GROMACS software to study the dynamic behavior of proteins. Molecular dynamics simulation is a computer simulation technique to study the physical motion of molecular systems over time. Specifically, molecular dynamics simulation predicts the trajectory and behavior of molecules by calculating the interaction forces between molecules according to the motion equations of classical mechanics. The process includes constructing a molecular system, such as a protein-ligand complex, setting initial conditions, such as temperature, pressure, simulated environment, etc., minimizing energy to ensure system stability, and then applying a corresponding integral algorithm, such as the Verlet integral method, to iteratively calculate the displacement and velocity of molecules at different time points. Through long-term simulation, the dynamic changes of the molecular system can be observed, and then the conformational evolution of the protein, the binding mechanism with the ligand, and other information can be obtained. This step provides a verification basis for the dynamic behavior of the protein structure after design optimization, ensuring that the designed protein not only has the expected function under static conditions, but also remains stable in a dynamic environment.

[0057] S13, using AIM to calculate the molecular dynamics simulation data to obtain the intermolecular interaction data; using NISE to convert the intermolecular interaction data into conversion spectral data to obtain the initial protein simulation spectral data.

[0058] In one embodiment of the present invention, AIM (Atoms In Molecules) is mainly used to calculate and analyze the atomic interactions in molecular structures. Specifically, AIM analyzes the bonding and non-bonding interactions in molecular systems by calculating the electron density distribution and using the Hamiltonian matrix in quantum chemistry. First, the electron density distribution of the molecule is obtained by quantum chemical calculation, and then AIM uses Bader theory to divide the electron density into atomic regions. By analyzing the boundaries of these regions, i.e., the zero-through points of the electron density and their gradients, the interactions between atoms, including covalent bonds, hydrogen bonds, and van der Waals forces, can be accurately identified. Finally, AIM uses the Hamiltonian matrix to calculate the bond strength, potential energy, and interaction energy of the molecular system, thereby evaluating the stability and structural properties of the molecular system.

[0059] In this real-time example, NISE (Nonlinear Infrared Spectroscopy Estimator) is used to process and analyze the spectral data in molecular dynamics simulation, particularly for calculating two-dimensional infrared spectrum (2DIR). NISE method, by combining molecular dynamics trajectory, first calculates the dynamic behavior of molecules evolving over time. Then, the molecular configuration in each frame trajectory is utilized to simulate the spectral characteristics by calculating the second-order response function of the molecule. NISE uses efficient calculation algorithms to process a large amount of trajectory data, and accurately simulates the influence of intermolecular interactions on the spectrum, particularly energy transfer, coupling effect, etc., by calculating the transition dipole moment of electronic and vibrational states. The method can also simulate the dynamic behavior of molecules on different time scales, thereby obtaining the spectrum simulation results with physical reality. In the present embodiment, AIM and NISE are both prior art, and the present application is not improved.

[0060] In one embodiment of the present invention, Python scripts and professional visualization tools can be used to visualize the results generated by NISE. This process not only helps us gain insight into the displayed data, but also reveals potential scientific discoveries and trends. Through detailed analysis of the results, we can draw important conclusions about protein behavior and provide solid support for further research.

[0061] In one embodiment of the present invention, protein structural feature data, protein simulated spectral data, and protein-ligand interaction data are obtained by:

[0062] S14, converting the protein three-dimensional structure data into a protein two-dimensional distance matrix; at the same time, converting the format of the initial protein simulation spectrum data to obtain a protein simulation spectrum two-dimensional matrix; and normalizing the protein two-dimensional distance matrix and the protein simulation spectrum two-dimensional matrix.

[0063] In this embodiment, the corresponding residue distance matrix is ​​calculated from the data of the initial PDB structure file by a script. Specifically, the residue distance matrix is ​​calculated based on the Euclidean distance between CA atoms, i.e., α-carbon atoms, in the initial PDB structure file. The calculation process is as follows: First, the three-dimensional coordinates of the CA atoms of all residues in the initial PDB structure file are extracted. Then, the distance between any two CA atoms is calculated, i.e., the protein three-dimensional structure data is converted into a protein two-dimensional distance matrix, by the following formula:

[0064]

[0065] Where d(i, j) is the distance between two CA atoms i and j, (x i ,y i, z i ) and (x j ,y j , z j ), are the three-dimensional coordinates of the two CA atoms i and CA atom j respectively. By calculating the distances between all the residues of the protein, a symmetric protein two-dimensional distance matrix can be generated. This protein two-dimensional distance matrix represents the geometric structure of the protein skeleton and can be used to reconstruct the skeleton model of the protein. At the same time, the corresponding initial protein simulation spectral data is converted into a format acceptable to the model, such as a two-dimensional image or matrix, and normalized to ensure that the spectral data matches the structural features of the protein. The purpose of this step is to allow the multi-task neural network model to both receive the structural information of the protein and process its corresponding spectral data.

[0066] S15, according to the topological structure of the protein, the normalized protein two-dimensional distance matrix and the protein simulated spectrum two-dimensional matrix are simultaneously classified to obtain protein structural feature data and protein simulated spectrum data.

[0067] In one embodiment of the present invention, the normalized two-dimensional distance matrix of proteins is classified according to proteins with different topological structures, such as ring-shaped proteins, barrel-shaped proteins, etc., and the two-dimensional matrices of protein simulation spectra corresponding to these structures are processed and mapped together. By combining spectral data with the structural features and properties of proteins, the multi-task neural network model can better learn the relationship between the two.

[0068] S16, establishing a mapping relationship between protein structural feature data and protein simulated spectral data with the same protein structural feature and property, and obtaining protein-ligand interaction data.

[0069] In one embodiment of the present invention, spectral data is obtained based on the initial PDB structure file, and when classified according to the topological structure of the protein, the spectral data is classified synchronously, so that the protein structural characteristics and protein structural characteristic data with the same properties and protein simulation spectral data can establish a mapping relationship. The ligands of the protein are such as atoms, molecules and ions, and the structure of the protein can be understood as including the ligand, and the protein-ligand interaction data also contains the spectral information of the protein and the ligand. For example, by calculating and analyzing the spectral changes of the protein after the ligand binds, it is ensured that the protein-ligand interaction relationship can be reflected in the spectral data. This step enables the spectral data to not only describe a single protein, but also reflect its interaction with the ligand.

[0070] In this example, the classification results and the matching of protein and spectral data are analyzed in detail to construct a data set for protein design. This data set contains protein structural feature data, protein simulated spectral data, and protein-ligand interaction data, ensuring the accurate association of spectral and protein features and properties in the data set, so as to facilitate the subsequent model learning and training.

[0071] In one embodiment of the present invention, protein simulation spectral data is generated by theoretical calculation methods to avoid the high cost and difficulty of experimental acquisition. The core of this process is to accurately match each spectrum with its corresponding protein structure, ensuring that the spectra in the data set correspond to their associated molecular properties one by one.

[0072] S20, establish a multi-task neural network model, train it using the data set, input protein simulation spectral data into the trained multi-task neural network model, and simultaneously obtain the distance matrix between protein skeleton atoms and the number of protein amino acids.

[0073] See also Figure 1 and Figure 2 As shown, in one embodiment of the present invention, the network architecture of the multi-task neural network model includes: an input layer, a convolutional layer, a fully connected layer, a multi-layer feature extraction layer, a feature fusion layer and an output layer.

[0074] The input layer is used to normalize and preprocess the protein simulation spectrum data. During training, the data in the dataset is input into the input layer.

[0075] Convolutional layers are used to extract spatial features from protein simulation spectral data. The convolutional layers are used to identify local patterns and features in the spectra, helping the model understand the potential relationship between spectral information and protein structure.

[0076] The fully connected layer is used to map the spatial features in the protein simulated spectral data extracted by the convolution layer to the structural feature space of the protein and obtain the distance matrix between the initial protein backbone atoms. The spatial features extracted by the convolution layer are mapped to the structural feature space of the protein, such as the distance matrix between backbone atoms or the three-dimensional structural information. The fully connected layer is responsible for converting high-dimensional spectral features into structure-related outputs.

[0077] In this embodiment, before output, the present invention uses a special fusion method to achieve the best performance. In this model, feature fusion is completed through the torch.cat(concat) operation. Specifically, the model first extracts features from different layers (layer1, layer2, layer3), and then concatenates the features of these layers. The innovation of feature fusion is to combine low-level fine-grained features such as local patterns extracted by convolutional layers with high-level abstract features, so that the final output not only contains local information, but also captures global structural information. The details are as follows:

[0078] The multi-layer feature extraction layer includes a first layer feature extraction, a second layer feature extraction and a third layer feature extraction; and the extraction scales from the first layer feature extraction to the third layer feature extraction increase successively; the three-layer feature extraction is used to extract features of different levels of scales from the distance matrix between the initial protein skeleton atoms.

[0079] In this embodiment, three feature extraction layers propose features at different levels, which represent gradual abstraction from the bottom layer to the high layer.

[0080] The feature fusion layer is used to use the splicing function to splice and fuse the features of different levels and scales extracted from the multiple feature extraction layers to obtain the final distance matrix between the protein skeleton atoms.

[0081] In this embodiment, torch.cat(concat) is used to concatenate and fuse features of different scales extracted from multiple feature extraction layers. Through this combination of features, information from different scales can be integrated to improve the perception of complex features of proteins.

[0082] The output layer includes a protein structure output layer and an amino acid number output layer; the protein structure output layer directly outputs the final distance matrix between protein backbone atoms; the protein structure is obtained based on the distance matrix between protein backbone atoms, and the characteristic lengths of all output protein structures are unified. The amino acid number output layer adopts a filling method to fill in the missing amino acids with invalid information, so that the characteristic lengths of all output protein structures are unified, and then the number of amino acids is output.

[0083] In this embodiment, for the prediction of known proteins, we only need the distance matrix between the protein skeleton atoms to obtain the protein structure. The prediction of unknown proteins lacks protein length (number of amino acids) information, so the output layer needs to additionally predict a single value, which represents the number of amino acids.

[0084] Since the input protein simulation spectral data is fixed as a 3x224x224 image, and the output protein lengths vary, we use the padding method to unify the lengths of all output protein structure features to a fixed size. And during the training process, we use a custom mask loss function (MaskLoss) to ignore the invalid information of the padding part. The working principle of MaskLoss is: first generate a mask to mark the valid parts of the input and target that are not zero. Then, only calculate the loss for these valid parts and ignore the padding part. In this way, the model can focus on learning effective information and improve the accuracy of the prediction. In addition, during the training process, we used a dynamic learning rate strategy, which can automatically change the learning rate size according to the real-time performance of the model to help the model fit and converge faster.

[0085] S30, integrating the distance matrix between protein backbone atoms and the number of protein amino acids to obtain the final protein distance matrix.

[0086] In this example, the integration process includes adjusting the dimension of the distance matrix between protein backbone atoms according to the number of amino acids, ensuring that its size matches the predicted amino acid sequence.

[0087] S40, obtaining the initial protein PDB structure according to the final protein distance matrix.

[0088] In this embodiment, the dimension of the distance matrix between protein backbone atoms is adjusted according to the number of protein amino acids, and the PyRosetta tool is used to generate the initial protein PDB structure from the distance matrix between protein backbone atoms after the adjusted dimension, ensuring that the dimension size of the distance matrix between protein backbone atoms matches the predicted amino acid sequence.

[0089] S50, the initial protein PDB structure was optimized using the SCUBA-D protein structure optimization model to obtain the all-atom protein structure.

[0090] In one embodiment of the present invention, the SCUBA-D protein structure optimization model is used to optimize the initial low-resolution protein structure. The low-resolution initial protein PDB structure is input, and the main chain and side chain conformations of the protein are gradually adjusted using the known protein energy function and force field, and a higher-resolution all-atom protein structure is output. This process is based on molecular dynamics simulation and energy minimization algorithm to convert the low-resolution rough structure into a full-atom model with more accurate atomic coordinates. Specifically, it includes:

[0091] S51, establish the protein index mapping and protein structure optimization configuration to ensure that the SCUBA-D protein structure optimization model can process every part of the protein. The core of this step is to ensure that the information of each residue, atom, etc. of the protein can be consistent with its optimization results.

[0092] S52, SCUBA-D protein structure optimization model is based on the energy calculation of molecular dynamics and force field. It minimizes the energy by continuously adjusting the main chain and side chain of the protein to optimize the protein's all-atom structure and obtain the all-atom protein structure. Finally, it outputs a high-resolution all-atom protein structure, whose conformation is more consistent with the actual biological function.

[0093] In this embodiment, the SCUBA-D protein structure optimization model further optimizes the folding state of the protein by analyzing the global topological structure and local interactions of the protein. The PDB structure file of the protein is input, and the model can predict the foldable high-resolution protein structure to ensure that the generated protein structure is physically stable and biologically feasible. Among them, the SCUBA-D protein structure optimization model is an existing open source model.

[0094] S60, applying ProteinMPNN, takes the all-atom protein structure as input and obtains multiple amino acid sequences.

[0095] In one embodiment of the present invention, ProteinMPNN performs global energy calculation on the atomic protein structure and generates multiple amino acid sequences according to the energy minimization principle. The required amino acid sequence can be selected from the multiple amino acid sequences according to the requirements. Specifically, the ProteinMPNN algorithm is an open source model.

[0096] In one embodiment of the present invention, the protein de novo reverse design method based on spectrum structure-activity relationship also includes step S100, which is located between step S10 and step S20; wherein step S100 is: establishing a spectrum diffusion generation model based on neural network; using protein simulation spectrum data and input custom protein description as input of the spectrum diffusion generation model for training, and outputting custom diffusion protein spectrum data. According to user needs, input the custom protein description into the trained spectrum diffusion generation model to output the custom diffusion protein spectrum data, and then execute steps S20 to S60 on the custom diffusion protein spectrum data.

[0097] In one embodiment of the present invention, a custom protein description is input and obtained in the following manner: a mapping relationship file between a spectrum and a custom description is generated using a script, and the mapping relationship file records the matching relationship between each spectral data and its corresponding protein attribute, function, and topological description. For example, the custom description corresponding to the spectrum may include information such as the hydrophobicity, amino acid sequence, and structural morphology of the protein. Through this mapping relationship, the model can associate the spectrum with the description one by one, which helps to learn the intrinsic connection between the spectrum and the functional and structural characteristics of the protein.

[0098] In this embodiment, the spectral diffusion generation model generates a log file during the training process, which records the detailed parameters of the training process. The log file is loaded and visualized through TensorBoard to monitor the changes in the loss function in real time so as to select the checkpoint with the lowest loss in the training. Visualization can help monitor the performance of the spectral diffusion generation model and ensure the stability of the spectral diffusion generation model during the training process.

[0099] In this embodiment, the user can input specific requirement descriptions, such as the characteristics, shape, and function of the target protein, and the spectral diffusion generation model can generate protein spectrum data that meets the requirements based on these descriptions. Through this process, the user can generate diverse protein spectra with specific functional characteristics based on specific requirements, providing a basis for further protein design.

[0100] See also Figure 1 As shown, in one embodiment of the present invention, the verification step is: the amino acid sequence of the designed protein is structurally verified by AF2 (AlphaFold2) or AF3 (AlphaFold3). AF2 and AF3 are advanced protein structure prediction algorithms developed by DeepMind. They are based on deep learning technology and can predict the three-dimensional structure of a protein by inputting its amino acid sequence.

[0101] In current protein design and research, AF2 and AF3 are widely used for structure verification because of their high accuracy. Compared with traditional experimental methods such as X-ray crystallography and nuclear magnetic resonance (NMR), AF2 and AF3 can not only significantly speed up the prediction of protein structure, but also their prediction accuracy is close to the experimental level in some cases. Although their prediction results cannot completely replace experimental verification, the root mean square deviation (RMSD) analysis shows that the structure predictions of AF2 and AF3 in most proteins are very close to the actual structures determined experimentally, with an error of several angstroms. By inputting the amino acid sequence of the designed protein, the predicted structure generated by AF2 / AF3 can be compared with the designed protein, and the RMSD value of the two can be calculated to evaluate the closeness of the designed protein to the real physical structure. This process can verify whether the designed protein meets the expected conformation and function.

[0102] In this example, the model used in the protein de novo reverse design method based on spectrum structure-activity relationship is integrated into an AI system to establish a fully automated process from user requirements directly to the final design of a high-confidence protein structure. Through this system, users can input target functions or structural requirements, and the system will automatically generate and optimize the protein design, such as Figure 3 As shown, the structure was verified by AF2 / AF3 to ensure that the generated protein met the expected requirements.

[0103] See also Figures 1 to 4 As shown, the present invention also provides a protein de novo reverse design system based on spectrum structure-activity relationship, which uses the above-mentioned protein de novo reverse design method based on spectrum structure-activity relationship, including:

[0104] Dataset module 10: used to obtain a data set, wherein the data set includes protein structural feature data, protein simulation spectrum data, and protein-ligand interaction data;

[0105] The multi-task prediction module 20 is used to establish a multi-task neural network model, train it using a data set, input protein simulation spectrum data into the trained multi-task neural network model, and simultaneously obtain the distance matrix between protein skeleton atoms and the number of protein amino acids;

[0106] The protein distance matrix module 30 is used to integrate the distance matrix between protein backbone atoms and the number of protein amino acids to obtain the final protein distance matrix;

[0107] An initial PDB module 40, used to obtain an initial protein PDB structure according to the final protein distance matrix;

[0108] The all-atom protein structure module 50 is used to optimize the initial protein PDB structure using the SCUBA-D protein structure optimization model to obtain the all-atom protein structure;

[0109] The amino acid sequence module 60 is used to apply ProteinMPNN to obtain multiple amino acid sequences by taking the all-atom protein structure as input.

[0110] It is obvious to those skilled in the art that the present invention is not limited to the details of the exemplary embodiments described above, and that the present invention can be implemented in other specific forms without departing from the spirit or essential features of the present invention. Therefore, the embodiments should be regarded as exemplary and non-limiting from any point of view, and the scope of the present invention is defined by the appended claims rather than the above description, and it is intended that all changes falling within the meaning and scope of the equivalent elements of the claims are included in the present invention, and any reference numerals in the claims should not be regarded as limiting the claims involved.

[0111] The above-described embodiments merely represent implementation methods of the invention. The protection scope of the present invention is not limited to the above-described embodiments. For those skilled in the art, several modifications and improvements may be made without departing from the concept of the present invention, which all belong to the protection scope of the present invention.

Claims

1. A method for protein de novo reverse design based on spectrum structure-activity relationship, characterized in that: include: S10, acquiring a data set, wherein the data set includes protein structural feature data, protein simulated spectrum data, and protein-ligand interaction data; S20, establishing a multi-task neural network model, training it using the data set, inputting protein simulation spectrum data into the trained multi-task neural network model, and simultaneously obtaining the distance matrix between protein skeleton atoms and the number of protein amino acids; S30, integrating the distance matrix between protein backbone atoms and the number of protein amino acids to obtain the final protein distance matrix; S40, obtaining the initial protein PDB structure based on the final protein distance matrix; S50, using the SCUBA-D protein structure optimization model to optimize the initial protein PDB structure and obtain the all-atom protein structure; S60, applying ProteinMPNN, takes the all-atom protein structure as input and obtains multiple amino acid sequences.

2. The method for protein de novo reverse design based on spectrum structure-activity relationship according to claim 1, characterized in that: Before obtaining protein simulation spectrum data, initial protein simulation spectrum data is first obtained, including the following steps: Obtain an initial PDB structure file from the RCSB protein PDB database; wherein the initial PDB structure file includes protein three-dimensional structure data; Perform molecular dynamics simulation of the protein on the initial PDB structure file to obtain molecular dynamics simulation data; AIM was used to calculate the molecular dynamics simulation data to obtain the intermolecular interaction data; NISE was used to convert the intermolecular interaction data into conversion spectral data to obtain the initial protein simulation spectral data.

3. The method for protein de novo reverse design based on spectrum structure-activity relationship according to claim 2, characterized in that: Obtain protein structural feature data, protein simulation spectral data, and protein-ligand interaction data through the following methods: The protein three-dimensional structure data is converted into a protein two-dimensional distance matrix; at the same time, the initial protein simulation spectrum data is formatted to obtain a protein simulation spectrum two-dimensional matrix; and the protein two-dimensional distance matrix and the protein simulation spectrum two-dimensional matrix are normalized; According to the topological structure of the protein, the normalized two-dimensional protein distance matrix and the two-dimensional matrix of protein simulated spectrum are classified simultaneously to obtain protein structural feature data and protein simulated spectrum data; A mapping relationship is established between protein structural feature data and protein simulated spectral data with the same protein structural features and properties to obtain protein-ligand interaction data.

4. The method for de novo protein reverse design based on spectrum structure-activity relationship according to claim 1, characterized in that: The network architecture of the multi-task neural network model includes: input layer, convolution layer, fully connected layer, multi-layer feature extraction layer, feature fusion layer and output layer; among them, Input layer, used for normalization preprocessing of protein simulation spectral data; Convolutional layers, used to extract spatial features in protein simulation spectral data; The fully connected layer is used to map the spatial features in the protein simulation spectral data extracted in the convolutional layer to the structural feature space of the protein and obtain the distance matrix between the initial protein skeleton atoms; The multi-layer feature extraction layer includes a first-layer feature extraction, a second-layer feature extraction and a third-layer feature extraction; and the extraction scales from the first-layer feature extraction to the third-layer feature extraction are increased successively; the three-layer feature extraction is used to extract features of different levels of scales from the distance matrix between the initial protein skeleton atoms; The feature fusion layer is used to use the splicing function to splice and fuse the features of different levels extracted from the multiple feature extraction layers to obtain the final distance matrix between the protein skeleton atoms; The output layer includes a protein structure output layer and an amino acid number output layer; the protein structure output layer directly outputs the final distance matrix between protein backbone atoms; the protein structure is obtained based on the distance matrix between protein backbone atoms, and the characteristic lengths of all output protein structures are unified. The amino acid number output layer adopts a filling method to fill in the missing amino acids with invalid information, so that the characteristic lengths of all output protein structures are unified, and then the number of amino acids is output.

5. The method for de novo protein reverse design based on spectrum structure-activity relationship according to claim 1, characterized in that: The final protein distance matrix is ​​obtained, including: adjusting the dimension of the distance matrix between protein backbone atoms according to the number of protein amino acids, and using the PyRosetta tool to generate the initial protein PDB structure from the distance matrix between protein backbone atoms after the dimension adjustment.

6. The method for protein de novo reverse design based on spectrum structure-activity relationship according to claim 1, characterized in that: Obtaining the full-atom protein structure includes: establishing the index mapping of the protein and the configuration of protein structure optimization to ensure that the SCUBA-D protein structure optimization model can process every part of the protein; the SCUBA-D protein structure optimization model is based on the energy calculation of molecular dynamics and force fields, and achieves energy minimization by continuously adjusting the main chain and side chain of the protein to optimize the full-atom structure of the protein and obtain the full-atom protein structure.

7. The method for de novo protein reverse design based on spectrum structure-activity relationship according to claim 1, characterized in that: Obtain multiple amino acid sequences, including: ProteinMPNN performs global energy calculations on atomic protein structures and generates multiple amino acid sequences based on the energy minimization principle.

8. The method for protein de novo reverse design based on spectrum structure-activity relationship according to claim 1, characterized in that: The protein de novo reverse design method based on spectrum structure-activity relationship also includes step S100, which is located between step S10 and step S20; wherein step S100 is: establishing a spectral diffusion generation model based on a neural network; using protein simulated spectral data and input custom protein description as inputs of the spectral diffusion generation model for training, and outputting custom diffuse protein spectral data; wherein the input custom protein description is obtained in the following manner: using a script to generate a mapping relationship file between the spectrum and the custom description, the mapping relationship file records the matching relationship between each spectral data and its corresponding protein attribute, function and topological description.

9. The method for de novo protein reverse design based on spectrum structure-activity relationship according to claim 8, characterized in that: According to user needs, a custom protein description is input into the trained spectral diffusion generation model to output custom diffuse protein spectral data, and then the custom diffuse protein spectral data is executed from step S20 to step S60.

10. A protein de novo reverse design system based on spectrum structure-activity relationship, characterized in that: The method for de novo reverse design of a protein based on spectrum structure-activity relationship according to any one of claims 1 to 9 comprises: Dataset module: used to obtain data sets, where the data sets include protein structural feature data, protein simulation spectrum data, and protein-ligand interaction data; The multi-task prediction module is used to establish a multi-task neural network model, train it using a data set, input protein simulation spectrum data into the trained multi-task neural network model, and simultaneously obtain the distance matrix between protein skeleton atoms and the number of protein amino acids; The protein distance matrix module is used to integrate the distance matrix between protein backbone atoms and the number of protein amino acids to obtain the final protein distance matrix; Initial PDB module, used to obtain the initial protein PDB structure based on the final protein distance matrix; All-atom protein structure module, which is used to optimize the initial protein PDB structure using the SCUBA-D protein structure optimization model to obtain the all-atom protein structure; The amino acid sequence module is used to apply ProteinMPNN to obtain multiple amino acid sequences using all-atom protein structures as input.

Images