Protein screening method, device, electronic equipment and storage medium

Abstract

Embodiments of the present application provide a protein screening method and device, electronic equipment and storage medium. The method comprises obtaining a first protein sequence and a first protein structure of a candidate protein, and a second protein sequence, a second protein structure and first homology information of a target protein; generating a complex simulation structure according to the first protein structure and the second protein structure; generating a complex predicted structure and a predicted confidence according to the first protein sequence, the second protein sequence, the first homology information and the complex simulation structure; determining difference information between the complex simulation structure and the complex predicted structure, and determining a screening result of the candidate protein according to the predicted confidence and the difference information. The method can improve the accuracy of protein screening.

Description

Technical Field

[0001] This application relates to the field of bioinformatics, and more particularly to a protein screening method, apparatus, electronic device, and storage medium. Background Technology

[0002] De novo protein design refers to the process of designing protein structures with specific functions and properties from scratch using computational methods and experimental techniques. In recent years, the field of de novo protein design has significantly improved the efficiency of protein design thanks to the rapid development of deep learning and artificial intelligence technologies.

[0003] Although the designed proteins may theoretically perform well, their success rate in laboratory validation remains low. Therefore, screening the designed proteins can be used to select the most promising proteins from a large number of candidate designs, significantly improving the efficiency and success rate of experimental validation, thereby accelerating the practical application of de novo protein design.

[0004] However, current filters are not very accurate in screening proteins. Summary of the Invention

[0005] The main objective of this application is to provide a protein screening method, apparatus, electronic device, and storage medium to improve the accuracy of protein screening.

[0006] To achieve the above objectives, this application proposes a protein screening method, comprising:

[0007] Obtain the first protein sequence and first protein structure of the candidate protein, and the second protein sequence, second protein structure and first homology information of the target protein;

[0008] A simulated complex structure was generated based on the first and second protein structures.

[0009] Based on the first protein sequence, the second protein sequence, the first homology information, and the simulated structure of the complex, generate the predicted structure and prediction confidence of the complex.

[0010] The discrepancy information between the simulated structure and the predicted structure of the complex is determined, and the screening results of candidate proteins are determined based on the prediction confidence and the discrepancy information.

[0011] Another aspect of this application proposes a protein screening device, comprising:

[0012] The acquisition unit is used to acquire the first protein sequence and first protein structure of the candidate protein, and the second protein sequence, second protein structure and first homology information of the target protein;

[0013] The first generation unit is used to generate a complex-simulated structure based on the first protein structure and the second protein structure.

[0014] The second generation unit is used to generate a predicted structure and prediction confidence of the complex based on the first protein sequence, the second protein sequence, the first homology information and the simulated structure of the complex.

[0015] The determination unit is used to determine the difference information between the simulated structure and the predicted structure of the complex, and to determine the screening results of candidate proteins based on the prediction confidence and the difference information.

[0016] Optionally, in some embodiments, the determining unit includes:

[0017] The first determining subunit is used to determine the first difference between the first protein structure and the first predicted structure corresponding to the candidate protein in the predicted structure of the complex;

[0018] The second determining subunit is used to determine the second difference between the second protein structure and the second predicted structure corresponding to the target protein in the predicted structure of the complex;

[0019] The third determining subunit is used to determine the third difference between the overall simulated structure and the predicted structure of the complex, and to determine difference information based on the first difference, the second difference and the third difference.

[0020] Optionally, in some embodiments, the first determining subunit includes:

[0021] The first spatial alignment module is used to spatially align the first predicted structure with the first protein structure;

[0022] The first determining module is used to determine the fourth difference between the spatially aligned first predicted structure and the first protein structure;

[0023] The second spatial alignment module is used to spatially align the second predicted structure with the second protein structure;

[0024] The second determining module is used to determine the fifth difference between the spatially aligned first predicted structure and the first protein structure;

[0025] The third determining module is used to determine the first difference based on the fourth and fifth differences.

[0026] Optionally, in some embodiments, the first generating unit includes:

[0027] The encoding subunit is used to encode the backbone information in the first protein structure to obtain the first coordinate matrix, and to encode the backbone information in the second protein structure to obtain the second coordinate matrix.

[0028] The fourth determining subunit is used to determine the third coordinate matrix corresponding to the simulated structure of the complex based on the first and second coordinate matrices.

[0029] The second generation unit includes:

[0030] The first generation subunit is used to generate the predicted structure and prediction confidence of the complex based on the first protein sequence, the second protein sequence, the first homology information, and the third coordinate matrix.

[0031] Optionally, in some embodiments, the fourth determining subunit includes:

[0032] The third spatial alignment module is used to spatially align the first coordinate matrix and the second coordinate matrix;

[0033] The merging module is used to merge the spatially aligned first and second coordinate matrices based on the binding sites of the first and second protein structures to obtain a third coordinate matrix.

[0034] Optionally, in some embodiments, the second generation unit includes:

[0035] The second generation subunit is used to generate the predicted structure of the complex based on the first protein sequence, the second protein sequence, the first homology information, and the simulated structure of the complex.

[0036] The segmentation subunit is used to segment the two-dimensional matrix according to the regional positions of candidate proteins and target proteins in the two-dimensional matrix of the complex predicted structure.

[0037] The fifth determining subunit is used to determine the overlap matrix of candidate proteins and target proteins in a two-dimensional matrix based on the block division results, and to determine the prediction confidence based on the value of the overlap matrix.

[0038] Optionally, in some embodiments, the determining unit includes:

[0039] The sixth determination subunit is used to determine whether a candidate protein is a protein to be verified when the prediction confidence and difference information meet the preset index threshold conditions.

[0040] The seventh determination subunit is used to determine the candidate protein as an invalid protein when the prediction confidence and difference information do not meet the preset index threshold conditions.

[0041] Another aspect of this application provides an electronic device, comprising:

[0042] Memory, transceiver, processor, and bus system;

[0043] The memory is used to store programs;

[0044] The processor is used to execute programs in memory, including methods for performing the aspects mentioned above;

[0045] Bus systems are used to connect memory and processor to enable communication between them.

[0046] Another aspect of this application provides a computer-readable storage medium storing instructions that, when executed on a computer, cause the computer to perform the methods described above.

[0047] As can be seen from the above technical solutions, the embodiments of this application have the following advantages:

[0048] The first protein structure of a candidate protein and the second protein structure of a target protein are used to synthesize a simulated complex structure. Based on the first protein sequence of the candidate protein, the second protein sequence of the target protein, the simulated complex structure, and the homology information of the target protein, a structure prediction is performed to obtain the predicted complex structure and the corresponding prediction confidence score. Candidate proteins can then be screened based on the difference information between the simulated and predicted complex structures, as well as the prediction confidence score, to obtain the screening results. The prediction confidence score reflects the accuracy of the predicted complex structure, while the difference information quantifies the similarity between the predicted and simulated complex structures. Combining the analysis of prediction accuracy and similarity can improve the screening accuracy of whether the predicted complex structure meets the expected results. Attached Figure Description

[0049] Figure 1 This is a schematic flowchart of a protein screening method provided in an embodiment of this application;

[0050] Figure 2 yes Figure 1 A flowchart illustrating step 104 in the middle section;

[0051] Figure 3 yes Figure 2 A flowchart illustrating step 201;

[0052] Figure 4 yes Figure 1 A flowchart illustrating steps 102 to 103.

[0053] Figure 5 yes Figure 4 A flowchart illustrating step 402 in the middle section;

[0054] Figure 6 yes Figure 1 A flowchart illustrating step 103;

[0055] Figure 7 yes Figure 1A flowchart illustrating step 104 in the middle section;

[0056] Figure 8 This is a schematic diagram illustrating the predicted structure of the complex provided in the embodiments of this application;

[0057] Figure 9 This is a schematic diagram of the protein complex structure prediction and screening process provided in the embodiments of this application;

[0058] Figure 10 This is a structural diagram of a protein screening device provided in an embodiment of this application;

[0059] Figure 11 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application. Detailed Implementation

[0060] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application.

[0061] It should be noted that although functional modules are divided in the device schematic diagram and a logical order is shown in the flowchart, in some cases, the steps shown or described may be performed in a different order than the module division in the device or the order in the flowchart. The terms "first," "second," etc., in the specification, claims, and the aforementioned drawings are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence.

[0062] The term “exemplary” as used herein means “serving as an example, embodiment, or illustration.” Any embodiment illustrated herein as “exemplary” is not necessarily to be construed as superior to or better than other embodiments.

[0063] In this application embodiment, the terms "module" or "unit" refer to a computer program or part of a computer program that has a predetermined function and works with other related parts to achieve a predetermined goal, and can be implemented wholly or partially using software, hardware (such as processing circuitry or memory), or a combination thereof. Similarly, a processor (or multiple processors or memory) can be used to implement one or more modules or units. Furthermore, each module or unit can be part of an overall module or unit that includes the functionality of that module or unit.

[0064] Furthermore, to better illustrate this application, numerous specific details are provided in the following detailed embodiments. Those skilled in the art should understand that this application can be implemented without certain specific details. In some instances, methods, means, components, and circuits well-known to those skilled in the art have not been described in detail in order to highlight the main points of this application.

[0065] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs. The terminology used herein is for the purpose of describing embodiments of this application only and is not intended to limit this application.

[0066] First, let's analyze some of the terms used in this application:

[0067] De novo protein design refers to the process of carefully arranging the amino acid sequence of a protein to enable it to spontaneously fold into a desired three-dimensional structure and acquire a specific function. The core of this technology lies in overcoming the limitations of natural proteins, building and designing proteins with entirely new structures and functions from scratch, creating protein structures and functions that have never existed in nature. For example, scientists can use de novo protein design to develop novel enzymes that can catalyze specific chemical reactions for use in drug synthesis, biofuel production, or other industrial processes.

[0068] Wet experiments refer to experimental procedures conducted in a laboratory by physically manipulating liquids, biological samples, or chemical reagents. This contrasts with "dry experiments," which primarily rely on computer simulations and data analysis.

[0069] The field of de novo protein design has significantly improved efficiency thanks to the rapid development of deep learning and artificial intelligence technologies. Researchers, leveraging increasingly rich protein databases and fully utilizing existing sequence and structural information from nature, have successfully designed novel proteins with specific functions. From initial stability optimization to the realization of complex functions (such as enzyme activity and signal transduction), this field is gradually moving towards multifunctionality. Furthermore, the application of high-throughput screening technologies and automated experimental equipment has greatly shortened the design and validation cycle, while enhancing the feedback mechanism between computation and experiment. Although computationally designed proteins exhibit excellent theoretical performance, their success rate in wet experiments (laboratory validation) remains low. Therefore, screening de novo designed proteins before conducting wet experiments can significantly improve the efficiency and success rate of experimental validation, thereby accelerating the practical application of de novo protein design.

[0070] Currently, Rosetta, a screening tool based on physical energy functions, can predict the energy state and folding probability of proteins by calculating physical energy functions and using intermolecular interaction energies (such as hydrogen bonds and van der Waals forces) and hydrophobic effects, thereby assessing the folding stability and interaction relationships of de novo designed proteins. However, under complex environments (such as solution effects, pH, and temperature), its energy function's prediction accuracy for the folding probability of de novo designed proteins is insufficient, often leading to significant deviations from actual experimental results. It also incurs extremely high computational costs and has a very low success rate in wet experiments. Screening tools combining molecular dynamics simulations, such as GROMACS and AMBER, can simulate conformational changes and stability of proteins under dynamic environments, capturing the dynamic behavior of proteins at the nanosecond to microsecond scale, thereby analyzing the stability of de novo designed proteins and their interaction relationships with target proteins. However, screening tools combining molecular dynamics simulations are computationally very expensive, making it difficult to efficiently process large-scale candidate protein libraries. Furthermore, their simulation timescales are limited (usually at the nanosecond or microsecond level), which may prevent them from capturing important conformational interactions between de novo designed proteins and target proteins. Statistical and data-driven screeners, such as ProGen and dl_binder_design, can leverage deep learning models to capture potential sequence-structure-function relationships from massive datasets. By combining large-scale statistical associations between protein sequences, structures, and functions, they can predict the folding probability of de novo designed proteins and their interactions with target proteins. However, these statistical and data-driven screeners typically use protein monomer structure prediction models as their foundation. When screening large-scale candidate protein libraries, they may not accurately predict the interactions between de novo designed proteins and target proteins, leading to the selection of too many false positive candidate designs.

[0071] To address the aforementioned issues, this application discloses a protein screening method. The method includes obtaining a first protein sequence and a first protein structure of a candidate protein, and a second protein sequence, a second protein structure, and first homology information of a target protein; generating a simulated complex structure based on the first and second protein structures; generating a predicted complex structure and a prediction confidence level based on the first protein sequence, the second protein sequence, the first homology information, and the simulated complex structure; determining the difference information between the simulated complex structure and the predicted complex structure; and determining the screening result of the candidate protein based on the prediction confidence level and the difference information.

[0072] This method synthesizes a simulated complex structure by combining the first protein structure of a candidate protein with the second protein structure of a target protein. Based on the first protein sequence of the candidate protein, the second protein sequence of the target protein, the simulated complex structure, and the corresponding homology information of the target protein, structural prediction is performed to obtain the predicted complex structure and its corresponding prediction confidence score. Candidate proteins can then be screened based on the difference information between the simulated and predicted complex structures, along with this prediction confidence score, to obtain the screening results. This method considers both the static structural features of proteins and the dynamic interaction features introduced through the simulated complex structure, while also utilizing homology information to enhance prediction accuracy. Furthermore, the prediction confidence score reflects the accuracy of the predicted complex structure, and the difference information quantifies the similarity between the predicted and simulated complex structures. Combining the analysis of prediction accuracy and similarity dimensions can improve the accuracy of screening whether the predicted complex structure meets the expected results.

[0073] The protein screening method provided in the embodiments of this application will be described below.

[0074] Please see Figure 1 In some embodiments, the protein screening method provided in this application includes, but is not limited to, steps 101 to 104.

[0075] Step 101: Obtain the first protein sequence and first protein structure of the candidate protein, and the second protein sequence, second protein structure and first homology information of the target protein;

[0076] Step 102: Generate a simulated complex structure based on the first and second protein structures;

[0077] Step 103: Based on the first protein sequence, the second protein sequence, the first homology information, and the simulated structure of the complex, generate the predicted structure and prediction confidence of the complex;

[0078] Step 104: Determine the difference information between the simulated structure and the predicted structure of the complex, and determine the screening results of candidate proteins based on the prediction confidence and the difference information.

[0079] Steps 101 to 104, as illustrated in the embodiments of this application, generate a simulated complex structure using the first protein structure of the candidate protein and the second protein structure of the target protein. This simulates the complex that the candidate and target proteins may form in the natural environment, providing a representation of protein-protein interactions. Then, combining the protein sequences of the candidate and target proteins, the first homology information of the target protein, and the simulated complex structure, a predicted complex structure is generated. The confidence level of the generated predicted complex structure is used as the prediction confidence level. The difference between the simulated and predicted complex structures, combined with the prediction confidence level, can determine the screening results for candidate proteins. By comparing the similarity between the predicted and simulated structures, and the prediction confidence level, proteins that structurally match the expectations can be identified, thus screening out candidate proteins most likely to succeed in wet experiments.

[0080] In step 101 of some embodiments, candidate proteins may refer to proteins that may interact with a specific target protein. These can be proteins selected from de novo protein design that need to bind to a specific target protein. These candidate proteins can also be screened before wet experiments to improve the efficiency of wet experiments.

[0081] The target protein can be a specific protein that interacts with (specifically binds to) the de novo designed protein.

[0082] A protein sequence is the sequence of amino acids that make up a protein, which determines the protein's structure and function. The protein sequence of a candidate protein can be called the first protein sequence, and the protein sequence of the target protein can be called the second protein sequence.

[0083] The first protein structure can be a three-dimensional structure generated by folding the protein sequence of a de novo designed protein. That is, amino acids are linked together by peptide bonds to form polypeptide chains, and these chains are then folded into specific three-dimensional shapes through various interactions (such as hydrogen bonds, hydrophobic interactions, van der Waals forces, etc.).

[0084] The second protein structure can be the three-dimensional structure of the target protein obtained through experimental methods, including X-ray crystallography, nuclear magnetic resonance (NMR), and cryo-electron microscopy (Cryo-EM). X-ray crystallography analyzes the diffraction pattern of protein crystals using X-rays to determine the three-dimensional structure of the protein; NMR uses nuclear magnetic resonance spectroscopy to study the structure and dynamics of proteins; and cryo-electron microscopy involves observing the structure of a frozen sample using an electron microscope.

[0085] Homology information, which can be genetic information derived from a common ancestor in biology, can provide additional sequence and structural data that helps improve and validate protein structures obtained through experimental methods. The homology information of a target protein can be referred to as primary homology information.

[0086] In step 102 of some embodiments, the simulated complex structure may refer to the three-dimensional structure of the complex formed by the expected interaction between biomolecules such as proteins and proteins and ligands, simulated by computational methods. Here, it refers to the complex structure under the interaction between the three-dimensional structure of the candidate protein to be screened and the laboratory structure of a specific target protein.

[0087] In step 103 of some embodiments, the predicted complex structure may be a three-dimensional structure constructed based on the binding sites and functional regions of the two protein structures indicated by the first and second protein sequences, combined with the sequence and structural information of other proteins similar to the second protein sequence, including the first homology information, and the expected interactions indicated by the complex structure.

[0088] Prediction confidence can be an assessment of the degree of certainty about the predicted structure of the generated complex; for example, it can refer to the degree of confidence the model has in its prediction results.

[0089] In step 104 of some embodiments, the difference information can be a quantitative indicator measuring the magnitude of the difference between two structures. In protein complex structure prediction, the similarity or difference between the simulated complex structure and the predicted complex structure can be compared. This can be achieved by calculating the distance between corresponding atoms in the two structures. The smaller the difference information, the more similar the predicted complex structure is to the simulated complex structure, and the higher the prediction accuracy. The confidence index indicates the model's level of confidence in its prediction results. A high prediction confidence indicates that the predicted complex structure is more consistent with the expected structure, which provides an important positive signal for selecting candidate proteins. Combining the prediction accuracy indicated by the difference information with a more comprehensive assessment of whether candidate proteins meet the expected structural requirements, this assessment result can be used as the screening result. Proteins that meet the expectations can be more accurately screened from multiple proteins to be screened for wet experiments, improving the efficiency of wet experiments.

[0090] Please see Figure 2 In some embodiments, step 104 includes, but is not limited to, steps 201 to 203.

[0091] Step 201: Determine the first difference between the first protein structure and the first predicted structure corresponding to the candidate protein in the predicted structure of the complex;

[0092] Step 202: Determine the second difference between the second protein structure and the second predicted structure corresponding to the target protein in the predicted structure of the complex;

[0093] Step 203: Determine the third difference between the overall simulated structure and the predicted structure of the complex, and determine the difference information based on the first difference, the second difference, and the third difference.

[0094] In this embodiment, the first difference can be the difference between the first protein structure and the first predicted structure corresponding to the candidate protein in the simulated complex structure and the predicted complex structure, which are local differences between them. This can be calculated by measuring the distance between corresponding atoms in the two structures, such as Euclidean distance. The predicted complex structure consists of the predicted candidate protein structure and the predicted target protein structure, and the first predicted structure can specifically refer to the predicted candidate protein structure.

[0095] The second difference can be the difference between the simulated structure and the predicted structure of the complex, specifically the difference between the second protein structure and the second predicted structure corresponding to the target protein in the predicted structure of the complex. It can also be the difference in the straight-line distance between the two structures in three-dimensional space.

[0096] The third difference can be determined by comparing the overall difference between the simulated and predicted structures of the complex. This can be achieved by calculating the overall difference, allowing for a comprehensive evaluation of the predicted complex structure. For example, it can assess the difference between the interaction relationships between two proteins within the structure and the simulated structure, identifying potential structural biases. Therefore, the difference information between the simulated and predicted structures can be determined by both the local differences (first and second differences) and the overall difference (third difference). This approach not only assesses the accuracy of individual protein structures but also evaluates the structure of the protein complex as a whole, improving the accuracy of the difference between the simulated and predicted structures based on the differences in each component and their interactions.

[0097] Please see Figure 3 In some embodiments, step 201 includes, but is not limited to, steps 301 to 305.

[0098] Step 301: Spatially align the first predicted structure with the first protein structure;

[0099] Step 302: Determine the fourth difference between the spatially aligned first predicted structure and the first protein structure;

[0100] Step 303: Spatial alignment of the second predicted structure with the second protein structure;

[0101] Step 304: Determine the fifth difference between the spatially aligned first predicted structure and the first protein structure;

[0102] Step 305: Determine the first difference based on the fourth and fifth differences.

[0103] In this embodiment, spatial alignment can be a process of matching two or more molecular structures in three-dimensional space. Specifically, it can involve finding corresponding parts within the molecules and calculating the rotation and translation operations required to align one molecule with another, ensuring that the two structures are based on the same coordinate system. It is understood that before determining the first difference between the first protein structure and the first predicted structure corresponding to the candidate protein in the predicted complex structure, a difference comparison can be performed based on the spatially aligned structures. The first protein structure can be directly spatially aligned with the first predicted structure corresponding to the candidate protein in the predicted complex structure, ensuring that the corresponding parts of the first protein structure and the first predicted structure are accurately matched in three-dimensional space. This allows the calculation of the difference between the two structures as a fourth difference, making the difference calculation more accurate.

[0104] Before determining the difference between the first predicted structure and the first protein structure, besides focusing solely on the alignment of a single candidate protein structure, one can also consider the candidate protein based on the interactions of the entire complex. For example, the coordinate system of the second predicted structure corresponding to the target protein in the complex's predicted structure can be aligned to the coordinate system of the second protein structure in the complex's simulated structure. In this case, the first protein structure in the complex's simulated structure, based on its interaction with the second protein structure, is in the same coordinate system as the first predicted structure. This difference between the first predicted structure and the first protein structure includes the difference in their interaction relationships and can be referred to as the fifth difference. Therefore, determining the first difference between the first protein structure and the first predicted structure based on the fourth and fifth differences provides more information about protein interactions than simply evaluating whether the candidate protein structure meets expectations. This helps to more comprehensively understand whether the function and stability of the complex meet expectations.

[0105] It is understandable that the first and second predicted structures in the complex prediction structure can be distinguished by identifiers.

[0106] An identifier can be a string of characters or numbers used to uniquely identify a molecule, protein, gene, or other biological entity, serving as a label to identify specific protein structures. When processing large amounts of data, identifiers can be used to quickly and accurately locate corresponding specific protein structures. That is, different identifiers in the simulated complex structure represent the first and second protein structures, respectively, and similarly, different identifiers in the predicted complex structure represent the first and second predicted structures. Therefore, when determining the difference between the first predicted structure and the first protein structure, the first predicted structure can be distinguished first by using the identifiers in the predicted complex structure, and then the first difference between the first protein structure and the first predicted structure can be determined. Identifiers ensure accurate identification and differentiation of different protein structures in the simulated and predicted complex structures, simplifying data retrieval and processing.

[0107] Please see Figure 4 In some embodiments, steps 102 and 103 include, but are not limited to, steps 401 to 403.

[0108] Step 401: Encode the backbone information in the first protein structure to obtain the first coordinate matrix; encode the backbone information in the second protein structure to obtain the second coordinate matrix.

[0109] Step 402: Determine the third coordinate matrix corresponding to the simulated structure of the complex based on the first and second coordinate matrices;

[0110] Step 403: Generate the predicted structure and prediction confidence of the complex based on the first protein sequence, the second protein sequence, the first homology information, and the third coordinate matrix.

[0111] In this embodiment, the backbone information refers to the atomic coordinates that constitute the basic structure of the protein. This information describes the position of each atom in the protein in three-dimensional space. The position of each atom in three-dimensional space can be represented in the form of X, Y, and Z coordinates.

[0112] The first coordinate matrix can be a matrix obtained by converting the backbone information in the first protein structure into a numerical form. It can contain the spatial coordinate information of all atoms that make up the protein backbone, and usually includes coordinate values ​​in three dimensions: X, Y, and Z.

[0113] The second coordinate matrix can be obtained by converting the backbone information in the second protein structure into a numerical form, thus providing structural information about the target protein.

[0114] The third coordinate matrix can be a matrix that integrates information from the first and second coordinate matrices. It is used to describe the predicted complex structure. This matrix contains the spatial coordinates of all atoms in the complex. The interaction relationships between the first and second coordinate matrices can guide the adjustment of atomic coordinates in these matrices to find a stable structure as the third coordinate matrix. Therefore, the structural information of the simulated complex structure can be used to participate in the prediction of the complex structure. With a precise coordinate matrix, the interactions and binding patterns between proteins can be simulated more accurately, thereby improving the accuracy of the predicted complex structure.

[0115] Please see Figure 5 In some embodiments, step 402 includes, but is not limited to, steps 501 to 502.

[0116] Step 501: Spatially align the first coordinate matrix and the second coordinate matrix;

[0117] Step 502: Based on the binding sites of the first and second protein structures, merge the spatially aligned first and second coordinate matrices to obtain the third coordinate matrix.

[0118] In this embodiment, a specific algorithm (such as the least squares method) is used to perform translation, rotation and other operations on the two coordinate matrices to achieve spatial alignment, so that the two protein structures overlap as much as possible in space, thereby placing them in a unified spatial reference frame.

[0119] Protein binding sites are key regions where proteins interact with other molecules (such as another protein, ligands, etc.). After spatial alignment, the two coordinate matrices are integrated based on the binding site information of the first and second proteins. Specifically, the coordinate information of atoms in the two protein structures is combined according to the binding site priority rule to form a new coordinate matrix, which can be called the third coordinate matrix. The third coordinate matrix contains all the atomic coordinate information of the two protein structures and considers the binding sites, reflecting the overall spatial structural characteristics of the two proteins in their interaction state.

[0120] Please see Figure 6 In some embodiments, step 103 includes, but is not limited to, steps 601 to 603.

[0121] Step 601: Generate the predicted structure of the complex based on the first protein sequence, the second protein sequence, the first homology information, and the simulated structure of the complex;

[0122] Step 602: Divide the two-dimensional matrix into blocks based on the regional positions of candidate proteins and target proteins in the two-dimensional matrix of the complex predicted structure;

[0123] Step 603: Determine the overlap matrix of candidate proteins and target proteins in the two-dimensional matrix based on the block division results, and determine the prediction confidence based on the value of the overlap matrix.

[0124] In this embodiment, the predicted structure of the complex can be represented as a two-dimensional matrix. Each element in the matrix can represent a specific attribute of a location in the protein structure, such as interatomic distance or interaction energy. In the two-dimensional matrix, the candidate protein and the target protein each occupy a certain region, and the positions of these regions can be obtained through analysis of the predicted structure of the complex. For example, the row and column ranges corresponding to the protein in the two-dimensional matrix can be determined based on the amino acid residue numbers or domain information of the protein.

[0125] Block partitioning can be used to divide a two-dimensional matrix into different submatrices based on the determined regional locations of candidate and target proteins.

[0126] An overlap matrix is ​​the overlapping portion of the candidate and target protein regions within a segmented two-dimensional matrix. The elements in the overlap matrix reflect the interaction information between the candidate and target proteins within the overlapping regions. Values ​​in the overlap matrix can represent various information, such as the strength and probability of the interaction. Statistical analysis and evaluation of the values ​​in the overlap matrix can determine the confidence level of the predicted complex structure. For example, if most elements in the overlap matrix indicate strong interactions, the predicted complex structure can be considered to have high confidence; conversely, if the values ​​show weak or unstable interactions, the prediction confidence is low. Segmentation allows for more targeted analysis of the interaction relationships between candidate and target proteins, as well as their structural characteristics within the complex, quantifying prediction quality and improving analytical efficiency.

[0127] In some embodiments, step 103 may be performed as follows: determining the complex sequence and pairing result based on the first protein sequence and the second protein sequence; generating alignment result representation information based on multiple sequence alignment in the complex sequence and the first homology information; generating pairing representation information based on the pairing result, the simulated structure of the complex, and the homology template in the first homology information; and generating the predicted structure and prediction confidence of the complex based on the alignment result representation information and the pairing representation information.

[0128] The complex sequence can refer to the set of amino acid sequences of all protein chains that make up a protein complex. That is, in a protein complex, multiple protein molecules may interact to form a stable complex structure. Each protein molecule has its own amino acid sequence, and these sequences together determine the overall structure and function of the complex.

[0129] Pairing results can be the analysis of possible interactions and binding patterns between two molecules. By comparing the first and second protein sequences, their similarities and differences can be identified, indicating the possible interaction regions between the two proteins.

[0130] Multiple sequence alignment (MSA) is the alignment of three or more biological sequences (such as protein, DNA, or RNA sequences). Its purpose is to align identical bases or amino acids from different sequences in the same column as possible without altering the sequence order, assuming that sequences in the same column are evolutionarily homologous and share a common ancestor. Here, we see the similarities and differences between the second protein sequence and its homologous sequences.

[0131] The alignment results can represent information that, after homology alignment of the second protein sequence in the complex, the alignment results are associated with other parts of the complex sequence (i.e., the first protein sequence). It can provide complete information on the structure and function of the complex and present it in a standardized, visualized, or computable form.

[0132] Homologous templates can refer to the three-dimensional structure of a protein that is homologous (sequence similarity) to the target protein sequence and whose three-dimensional structure is known.

[0133] Pairing representation information refers to a detailed description of the interaction relationships between individual protein monomers in a protein complex. It can include not only which residues interact, but also the type, strength, and spatial location of these interactions. In other words, pairing representation information is generated based on pairing results, simulated complex structures, and homologous templates to describe the interaction patterns between monomers in the complex. Alignment result representation information and pairing representation information provide rich sequence and structural details, enabling more accurate capture of the interaction patterns between monomers in the protein complex, generating predicted complex structures and prediction confidence levels. The representation information format is typically a simplified and abstract data representation method that highlights key information, removes unnecessary details, and allows for more efficient data processing and reduced computational complexity.

[0134] In some embodiments, step 103 can also be performed by predicting the structure of the first protein sequence, the second protein sequence, homology information, and the simulated structure of the complex based on a protein structure prediction model, thereby obtaining the predicted structure of the complex and the prediction confidence level corresponding to the predicted structure of the complex; the model parameters of the protein structure prediction model are updated using the following method:

[0135] Obtain the second homology information corresponding to the protein sequence of the sample, and predict the second homology information based on the protein structure prediction model to obtain the predicted structure of the sample;

[0136] Determine the comparison value between the predicted structure of the sample and the structure of the reference complex;

[0137] The parameters of the protein structure prediction model are updated based on the difference between the comparison value and the reference local distance difference test score and the reference alignment error.

[0138] Among them, protein structure prediction models can be tools for inferring the three-dimensional spatial structure of proteins from amino acid sequences. They can integrate evolutionary information (such as homologous information) and physicochemical laws (such as interatomic interactions indicated by protein sequences and complex simulated structures) and use machine learning algorithms to predict the conformation of proteins after folding.

[0139] Sample protein sequences can refer to specific amino acid sequences used to validate or adjust model performance during the training or optimization of protein structure prediction models. They can be known experimentally resolved structures (such as reference structures obtained by X-ray crystallography or cryo-electron microscopy) or proteins pre-labeled as having a specific function.

[0140] The reference complex structure can refer to the three-dimensional structure of a protein complex that has been resolved by known experiments and serves as a benchmark or validation standard during protein structure prediction or model training.

[0141] The comparison value can be an indicator that quantifies the similarity or difference between the predicted structure and the reference structure. It can be determined by calculating the geometric deviation or local residue matching degree between the predicted structure and the reference structure.

[0142] The Local Distance Difference Test score (LDDT-score) is a non-additive score used to evaluate the local distance differences among all atoms in the model. It does not rely on global alignment but directly compares the distance differences between corresponding atoms in the predicted and reference structures. The LDDT-score ranges from 0 to 1; a value closer to 1 indicates better local consistency between the predicted and reference structures.

[0143] Predicted Alignment Error (PAE) measures the relative position and orientation error between two residues in a predicted structure. A higher PAE value indicates a higher prediction error and therefore lower confidence. PAE can be represented as a matrix, where each element corresponds to the prediction error between two residues. During parameter updates in protein structure prediction models, LDDT-score and PAE can be used to assess the accuracy of the predicted structure and adjust model parameters accordingly. For example, if the predicted structure's local distance difference test score is lower than the reference score or its alignment error is higher, it indicates a significant difference between the predicted and reference structures, and the model parameters may require further optimization. By comparing the LDDT-score and PAE of the predicted structure with the reference values, the model can accurately pinpoint the sources of error in the prediction, allowing for targeted parameter adjustments to reduce errors and improve the overall accuracy of the predicted structure.

[0144] Please see Figure 7 In some embodiments, step 104 includes, but is not limited to, steps 701 to 702.

[0145] Step 701: When the prediction confidence and difference information meet the preset index threshold conditions, the candidate protein is determined as the protein to be verified.

[0146] Step 702: When the prediction confidence and difference information do not meet the preset index threshold conditions, the candidate protein is determined to be an invalid protein.

[0147] In this implementation, the preset threshold conditions can be a set of judgment criteria set based on prediction confidence and difference information. When the prediction confidence reaches the preset confidence level and the difference information reaches the preset difference information, the candidate protein can be determined to be a protein that meets the expected structure, and can be further processed through laboratory verification, thus becoming a protein to be verified. For example, if the prediction confidence of a candidate protein is 95 and the root mean square deviation (RMSD) is... If the threshold condition is met, it is identified as a protein to be verified and further experimental verification is carried out.

[0148] If the prediction confidence level does not reach the preset confidence level or the difference information does not reach the preset difference information, the candidate protein can be considered as not meeting expectations and can be removed from the protein set of the laboratory validation process, thus becoming an invalid protein. By setting reasonable prediction confidence and difference information thresholds, candidate proteins with high confidence and low difference can be screened out, thereby improving the reliability of the prediction results.

[0149] The protein screening method provided in this application will be described in detail below with reference to a specific embodiment.

[0150] 1. Training the filter: Taking the AlphaFold-Multimer prediction model as an example, the homology information of the sample protein sequence is used as input, and the three-dimensional coordinates of the experimental structure of the complex and the local distance difference test score (LDDT-score) and alignment error (AE) between the predicted structure and the experimental structure are used as labels to train AlphaFold-Multimer to obtain the target filter.

[0151] 2. Obtaining the predicted complex structure based on the target screener: Based on the target screener, the structure of the complex designed with the de novo protein in the test protein set, including the test protein sequence, the target protein sequence of the target protein to be bound, the homology information of the target protein, and the designed framework structure of the de novo protein combined with the experimental structure of the target protein, is predicted to obtain the predicted complex structure. For details, please refer to... Figure 8 The schematic diagram of the predicted structure of the complex shown illustrates that, based on the input of the de novo protein design sequence 801 (test protein sequence), 802 (target protein sequence), 803 (design backbone structure), and 804 (experimental structure), the input can be processed first. The processing flow can be as follows: generate the complex sequence 805 based on the test protein sequence 801 and the target protein sequence 802; perform a gene database search based on the target protein sequence 802 to obtain multiple sequence alignment (MSA) 806 from the homology information; pair the test protein sequence 801 and the target protein sequence 802 to obtain the pairing result 807; determine the complex design structure 808 based on the design backbone structure 803 and the experimental structure 804, which can be based on the interface information of the complex design structure constructed from the coordinate matrices corresponding to the design backbone structure 803 and the experimental structure 804, or directly from the distance matrix extracted from the complex design structure; and perform a structure database search based on the target protein sequence 802 to obtain the homology template 809 from the homology information.

[0152] The target filter can determine multiple sequence alignment expression information 810 based on the complex sequence 805 and multiple sequence alignment 806, and determine the first paired expression information 811 based on the pairing result 807, the complex designed structure 805, and the homologous template 809. The evolution module 812 can extract evolutionary and conservation information from the multiple sequence alignment expression information 810 based on a self-attention mechanism to obtain single expression information 813, and update the intrastructural relationships in the paired expression information 811 based on a self-attention mechanism to obtain the second paired expression information 814. The structure module 815 can predict the three-dimensional structure of the protein complex based on the single expression information 813 and the second paired expression information 814. To improve the accuracy of the prediction, multiple cyclic predictions (e.g., three cycles) can be performed based on the single expression information 813, the second paired expression information 814, and the predicted three-dimensional structure obtained each time. The structural representation information is continuously updated and optimized to obtain the final predicted structure of the complex 816.

[0153] Once the filter predicts the structure of the complex of the de novo designed protein and the target protein, the following steps can be performed sequentially:

[0154] Calculate the root mean square deviation between the predicted target protein structure and the experimental target protein structure after alignment in the predicted target protein structure of the complex, and denote this value as target_aligned_target_r.msd;

[0155] Calculate the root mean square deviation between the predicted de novo protein structure and the designed backbone structure of the de novo protein after alignment in the predicted structure of the complex, and denote this value as binder_aligned_binder_r.msd;

[0156] Calculate the root mean square deviation between the predicted structure of the target protein and the designed backbone structure of the de novo designed protein after aligning the predicted structure of the target protein with the experimental structure of the target protein in the predicted structure of the complex, and denote this value as target_aligned_binder_r.msd;

[0157] Calculate the root mean square deviation between the predicted and designed structures of the complex after aligning them, and denote this value as all_aligned_complex_r.msd;

[0158] In the output feature file generated along with the filter's prediction of the complex predicted structure of the de novo designed protein and the target protein, the predicted alignment error of interaction (pAE_interaction), the predicted local distance difference test of complex (plddt_complex), and the predicted docking quality (pDockQ) are extracted. plddt_complex and pDockQ can be obtained directly from the AlphaFold-Multimer output file. pAE_interaction is obtained indirectly from the AlphaFold-Multimer output file, whose original file is a two-dimensional matrix. This two-dimensional matrix can be divided into blocks based on the interval positions of the target protein prediction structure and the de novo designed protein prediction structure within the entire two-dimensional matrix, thus obtaining the values ​​of the overlapping block matrix of the target protein prediction structure and the de novo designed protein prediction structure. pAE_interaction represents the error of the interaction between the predicted structure of the target protein and the predicted structure of the de novo designed protein. The smaller this difference, the stronger the interaction between the two parts. plddt_complex represents the confidence level of the predicted complex structure. The higher this value, the more reliable the predicted complex result is, indirectly reflecting that both the predicted structure of the target protein and the predicted structure of the de novo designed protein are correct. pDockQ represents the correctness of the interface (interaction contact surface) between the predicted structure of the target protein and the predicted structure of the de novo designed protein. The higher this value, the more correct the interface between the predicted structure of the target protein and the predicted structure of the de novo designed protein is.

[0159] A protein designed de novo is considered to meet the design requirements and can be considered as a candidate protein for wet experiments when all the following values ​​are met simultaneously:

[0160]

[0161] plddt_complex>90.0;

[0162] pDockQ>0.8.

[0163] In one example, the process for predicting and screening protein complex structures can also be referenced. Figure 9As shown, the process begins with three different input sources: the test protein sequence 901 of the de novo designed protein, the target protein sequence 902 of the target protein to be bound, and the complex design structure 903 consisting of the designed backbone structure of the de novo designed protein and the experimental structure of the target protein. The target filter 904 processes these inputs and performs structure prediction to obtain the complex prediction structure 905. Simultaneously, it obtains three prediction values ​​906 (pAE_interaction, plddt_complex, and pDockQ) from the output file. Using the complex prediction structure and the complex design structure, it calculates four root mean square deviation values ​​907 (target_aligned_target_r.msd, binder_aligned_binder_r.msd, target_aligned_binder_r.msd, and all_aligned_complex_r.msd). Then, based on pre-defined threshold values, de novo designed proteins that meet the thresholds are selected as candidate proteins for wet experiments 908.

[0164] Reference Figure 10 In some embodiments, this application also provides a protein screening device 1000, which includes:

[0165] The acquisition unit 1001 is used to acquire the first protein sequence and first protein structure of the candidate protein, and the second protein sequence, second protein structure and first homology information of the target protein;

[0166] The first generation unit 1002 is used to generate a complex simulated structure based on the first protein structure and the second protein structure.

[0167] The second generation unit 1003 is used to generate a predicted structure and prediction confidence of the complex based on the first protein sequence, the second protein sequence, the first homology information and the simulated structure of the complex.

[0168] The determination unit 1004 is used to determine the difference information between the simulated structure and the predicted structure of the complex, and to determine the screening results of candidate proteins based on the prediction confidence and the difference information.

[0169] Optionally, in some embodiments, the determining unit 1004 includes:

[0170] The first determining subunit is used to determine the first difference between the first protein structure and the first predicted structure corresponding to the candidate protein in the predicted structure of the complex;

[0171] The second determining subunit is used to determine the second difference between the second protein structure and the second predicted structure corresponding to the target protein in the predicted structure of the complex;

[0172] The third determining subunit is used to determine the third difference between the overall simulated structure and the predicted structure of the complex, and to determine difference information based on the first difference, the second difference and the third difference.

[0173] Optionally, in some embodiments, the first determining subunit includes:

[0174] The first spatial alignment module is used to spatially align the first predicted structure with the first protein structure;

[0175] The first determining module is used to determine the fourth difference between the spatially aligned first predicted structure and the first protein structure;

[0176] The second spatial alignment module is used to spatially align the second predicted structure with the second protein structure;

[0177] The second determining module is used to determine the fifth difference between the spatially aligned first predicted structure and the first protein structure;

[0178] The third determining module is used to determine the first difference based on the fourth and fifth differences.

[0179] Optionally, in some embodiments, the first generation unit 1002 includes:

[0180] The encoding subunit is used to encode the backbone information in the first protein structure to obtain the first coordinate matrix, and to encode the backbone information in the second protein structure to obtain the second coordinate matrix.

[0181] The fourth determining subunit is used to determine the third coordinate matrix corresponding to the simulated structure of the complex based on the first and second coordinate matrices.

[0182] The second generation unit includes:

[0183] The first generation subunit is used to generate the predicted structure and prediction confidence of the complex based on the first protein sequence, the second protein sequence, the first homology information, and the third coordinate matrix.

[0184] Optionally, in some embodiments, the fourth determining subunit includes:

[0185] The third spatial alignment module is used to spatially align the first coordinate matrix and the second coordinate matrix;

[0186] The merging module is used to merge the spatially aligned first and second coordinate matrices based on the binding sites of the first and second protein structures to obtain a third coordinate matrix.

[0187] Optionally, in some embodiments, the second generation unit 1003 includes:

[0188] The second generation subunit is used to generate the predicted structure of the complex based on the first protein sequence, the second protein sequence, the first homology information, and the simulated structure of the complex.

[0189] The segmentation subunit is used to segment the two-dimensional matrix according to the regional positions of candidate proteins and target proteins in the two-dimensional matrix of the complex predicted structure.

[0190] The fifth determining subunit is used to determine the overlap matrix of candidate proteins and target proteins in a two-dimensional matrix based on the block division results, and to determine the prediction confidence based on the value of the overlap matrix.

[0191] Optionally, in some embodiments, the determining unit 1004 includes:

[0192] The sixth determination subunit is used to determine whether a candidate protein is a protein to be verified when the prediction confidence and difference information meet the preset index threshold conditions.

[0193] The seventh determination subunit is used to determine the candidate protein as an invalid protein when the prediction confidence and difference information do not meet the preset index threshold conditions.

[0194] This application also provides an electronic device, which includes a memory and a processor. The memory stores a computer program, and the processor executes the computer program to implement the protein screening method described above. This electronic device can be any smart terminal, including tablet computers, in-vehicle computers, etc.

[0195] Please see Figure 11 , Figure 11 The hardware structure of an electronic device according to another embodiment is illustrated. The electronic device includes:

[0196] The processor 1101 can be implemented using a general-purpose CPU (Central Processing Unit), microprocessor, application-specific integrated circuit (ASIC), or one or more integrated circuits, and is used to execute relevant programs to implement the technical solutions provided in the embodiments of this application.

[0197] The memory 1102 can be implemented as a read-only memory (ROM), a static storage device, a dynamic storage device, or a random access memory (RAM). The memory 1102 can store the operating system and other applications. When the technical solutions provided in the embodiments of this specification are implemented through software or firmware, the relevant program code is stored in the memory 1102 and is called and executed by the processor 1101 using the protein screening method of the embodiments of this application.

[0198] Input / output interface 1103 is used to implement information input and output;

[0199] The communication interface 1104 is used to enable communication and interaction between this device and other devices. Communication can be achieved through wired means (such as USB, network cable, etc.) or wireless means (such as mobile network, WIFI, Bluetooth, etc.).

[0200] Bus 1105 transmits information between various components of the device (e.g., processor 1101, memory 1102, input / output interface 1103, and communication interface 1104);

[0201] The processor 1101, memory 1102, input / output interface 1103 and communication interface 1104 are connected to each other within the device via bus 1105.

[0202] This application also provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the protein screening method described above.

[0203] Memory, as a non-transitory computer-readable storage medium, can be used to store non-transitory software programs and non-transitory computer-executable programs. Furthermore, memory may include high-speed random access memory, and may also include non-transitory memory, such as at least one disk storage device, flash memory device, or other non-transitory solid-state storage device. In some embodiments, memory may optionally include memory remotely located relative to the processor, and these remote memories can be connected to the processor via a network. Examples of such networks include, but are not limited to, the Internet, intranets, local area networks, mobile communication networks, and combinations thereof.

[0204] The embodiments described in this application are for the purpose of more clearly illustrating the technical solutions of the embodiments of this application, and do not constitute a limitation on the technical solutions provided by the embodiments of this application. As those skilled in the art will know, with the evolution of technology and the emergence of new application scenarios, the technical solutions provided by the embodiments of this application are also applicable to similar technical problems.

[0205] Those skilled in the art will understand that the technical solutions shown in the figures do not constitute a limitation on the embodiments of this application, and may include more or fewer steps than shown, or combine certain steps, or different steps.

[0206] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs.

[0207] Those skilled in the art will understand that all or some of the steps in the methods disclosed above, as well as the functional modules / units in the systems and devices, can be implemented as software, firmware, hardware, or suitable combinations thereof.

[0208] The terms “first,” “second,” “third,” “fourth,” etc. (if present) in the specification and accompanying drawings of this application are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of this application described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms “comprising” and “having,” and any variations thereof, are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0209] It should be understood that in this application, "at least one (item)" means one or more, and "more than" means two or more. "And / or" is used to describe the relationship between related objects, indicating that three relationships can exist. For example, "A and / or B" can represent three cases: only A exists, only B exists, and both A and B exist simultaneously, where A and B can be singular or plural. The character " / " generally indicates that the preceding and following related objects are in an "or" relationship. "At least one (item) of the following" or similar expressions refer to any combination of these items, including any combination of single or plural items. For example, at least one (item) of a, b, or c can represent: a, b, c, "a and b", "a and c", "b and c", or "a and b and c", where a, b, and c can be single or multiple.

[0210] In the several embodiments provided in this application, it should be understood that the disclosed apparatus and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of the units described above is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between apparatuses or units may be electrical, mechanical, or other forms.

[0211] The units described above as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0212] Furthermore, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0213] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes multiple instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods of the various embodiments of this application. The aforementioned storage medium includes various media capable of storing programs, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0214] The preferred embodiments of the present application have been described above with reference to the accompanying drawings, but this does not limit the scope of the claims of the present application. Any modifications, equivalent substitutions, and improvements made by those skilled in the art without departing from the scope and substance of the embodiments of the present application shall be within the scope of the claims of the present application.

Claims

1. A protein screening method, characterized in that, include: Obtain the first protein sequence and first protein structure of the candidate protein, and the second protein sequence, second protein structure and first homology information of the target protein; A simulated complex structure is generated based on the first protein structure and the second protein structure; Based on the first protein sequence, the second protein sequence, the first homology information, and the simulated structure of the complex, a predicted structure and prediction confidence of the complex are generated. The difference information between the simulated structure of the complex and the predicted structure of the complex is determined, and the screening result of the candidate protein is determined based on the prediction confidence and the difference information.

2. The method according to claim 1, characterized in that, The determination of the difference information between the simulated structure and the predicted structure of the complex includes: Determine a first difference between the first protein structure and the first predicted structure corresponding to the candidate protein in the predicted structure of the complex; Determine a second difference between the second protein structure and the second predicted structure corresponding to the target protein in the predicted structure of the complex; A third difference is determined between the overall simulated structure of the complex and the predicted structure of the complex, and the difference information is determined based on the first difference, the second difference, and the third difference.

3. The method according to claim 2, characterized in that, Determining the first difference between the first protein structure and the first predicted structure corresponding to the candidate protein in the predicted structure of the complex includes: Spatially align the first predicted structure with the first protein structure; Determine the fourth difference between the spatially aligned first predicted structure and the first protein structure; Spatially align the second predicted structure with the second protein structure; Determine the fifth difference between the spatially aligned first predicted structure and the first protein structure; The first difference is determined based on the fourth difference and the fifth difference.

4. The method according to claim 1, characterized in that, The step of generating a complex-mimicking structure based on the first protein structure and the second protein structure includes: The backbone information in the first protein structure is encoded to obtain a first coordinate matrix, and the backbone information in the second protein structure is encoded to obtain a second coordinate matrix; The third coordinate matrix corresponding to the simulated structure of the complex is determined based on the first coordinate matrix and the second coordinate matrix; The step of generating a predicted complex structure and prediction confidence based on the first protein sequence, the second protein sequence, the first homology information, and the simulated complex structure includes: Based on the first protein sequence, the second protein sequence, the first homology information, and the third coordinate matrix, a predicted structure and prediction confidence of the complex are generated.

5. The method according to claim 4, characterized in that, Determining the third coordinate matrix corresponding to the simulated structure of the complex based on the first coordinate matrix and the second coordinate matrix includes: Spatially align the first coordinate matrix and the second coordinate matrix; Based on the binding sites of the first and second protein structures, the spatially aligned first and second coordinate matrices are merged to obtain the third coordinate matrix.

6. The method according to claim 1, characterized in that, The step of generating a predicted complex structure and prediction confidence based on the first protein sequence, the second protein sequence, the first homology information, and the simulated complex structure includes: Based on the first protein sequence, the second protein sequence, the first homology information, and the simulated structure of the complex, a predicted structure of the complex is generated; The two-dimensional matrix is ​​divided into blocks based on the regional locations of the candidate protein and the target protein in the two-dimensional matrix of the predicted structure of the complex. Based on the block division results, the overlap matrix of the candidate protein and the target protein in the two-dimensional matrix is ​​determined, and the prediction confidence is determined based on the value of the overlap matrix.

7. The method according to any one of claims 1-6, characterized in that, The step of determining the screening results of the candidate proteins based on the predicted confidence level and the difference information includes: When the prediction confidence and the difference information meet the preset index threshold conditions, the candidate protein is determined to be the protein to be verified. When the prediction confidence and the difference information do not meet the preset index threshold conditions, the candidate protein is determined to be an invalid protein.

8. A protein screening device, characterized in that, include: The acquisition unit is used to acquire the first protein sequence and first protein structure of the candidate protein, and the second protein sequence, second protein structure and first homology information of the target protein; The first generation unit is used to generate a complex-simulated structure based on the first protein structure and the second protein structure; The second generation unit is used to generate a predicted structure and prediction confidence of the complex based on the first protein sequence, the second protein sequence, the first homology information and the simulated structure of the complex. A determining unit is configured to determine the difference information between the simulated structure of the complex and the predicted structure of the complex, and to determine the screening result of the candidate protein based on the prediction confidence and the difference information.

9. An electronic device, characterized in that, include: Memory, transceiver, processor, and bus system; The memory is used to store programs; The processor is configured to execute a program in the memory, including performing the method as described in any one of claims 1 to 7; The bus system is used to connect the memory and the processor to enable communication between the memory and the processor.

10. A computer-readable storage medium, characterized in that, Includes instructions that, when run on a computer, cause the computer to perform the method as described in any one of claims 1 to 7.

Images