Mutant protein screening method and device and related equipment

Abstract

The invention discloses a mutant protein screening method and device and related equipment thereof, and relates to the technical field of material determination and analysis. The method comprises the following steps: respectively carrying out simulated single mutation on a plurality of amino acid sites in a protein sequence of a target protein to obtain a plurality of simulated mutant proteins, and determining adaptability evaluation values F of the plurality of simulated mutant proteins based on a target protein language model; determining structural stability values S of the plurality of simulated mutant proteins based on a protein folding energy calculation tool; performing normalization processing on the adaptability evaluation value F and the structural stability value S, and performing single-index sorting and comprehensive-index sorting on normalization processing results; and screening the plurality of simulated mutant proteins according to the target screening number, the single index sorting result and the comprehensive index sorting result to obtain a target mutant protein. According to the method, the protein design transformation difficulty can be reduced, the mutant protein screening effect is improved, the calculation amount required by protein transformation and screening is reduced, and the consumption cost is reduced.

Description

Technical Field

[0001] The present invention relates to the technical field of material determination and analysis, and in particular to a mutant protein screening method, device and related equipment. Background Art

[0002] Protein is one of the most diverse and important macromolecules in organisms, playing a vital role in the environment, industrial production, medicine, materials and other fields. However, in actual applications, natural proteins often cannot meet complex application requirements, so some methods and means are needed to carry out specific mutation modification design on proteins. In view of many problems such as high experimental design cost, long experimental cycle and difficulty in analyzing physical and chemical properties, protein mutation optimization modification methods designed by simulation calculation are considered to have great potential in the field of protein engineering.

[0003] However, there are a large number of mutant proteins obtained through simulation calculations, and how to screen out mutant proteins with potential improved properties is an urgent problem to be solved. The mutant protein screening schemes in related technologies have problems such as high difficulty in mutant protein design and modification, poor mutant protein screening effect, large amount of calculation required for protein modification and screening, long experimental cycle and high cost.

[0004] With respect to the above-mentioned problems in the related technologies, no effective solutions have been proposed yet. Summary of the invention

[0005] A mutant protein screening method and related equipment provided in an embodiment of the present invention at least solve the problems in the related art of high difficulty in mutant protein design and modification, poor mutant protein screening effect, large amount of calculation required for protein modification and screening, long test cycle and high cost.

[0006] In order to solve the above problems, one aspect of an embodiment of the present invention provides a method for screening mutant proteins, comprising: Simulating single mutations at multiple amino acid sites in the protein sequence of the target protein to obtain multiple simulated mutant proteins, and performing adaptability prediction on the simulated single mutant sequences corresponding to the multiple simulated mutant proteins based on the target protein language model to obtain the adaptability evaluation value F of each simulated single mutant sequence; wherein any simulated single mutant sequence includes a single mutant protein sequence at the corresponding amino acid site; Determine the simulated single mutant structures corresponding to the multiple simulated mutant proteins, respectively calculate the folding energy change values ​​of the multiple simulated single mutant structures before and after the protein mutation based on the protein folding energy calculation tool, and determine the structural stability value S of each simulated single mutant structure based on the folding energy change value; The adaptability evaluation value F and the structural stability value S are normalized respectively, and the normalized results are sorted by single index and comprehensive index respectively; According to the target screening quantity, single index ranking results and comprehensive index ranking results, multiple simulated mutant proteins are screened to obtain the target mutant protein.

[0007] In some embodiments, the steps of normalizing the adaptability evaluation value F and the structural stability value S respectively, and performing single index ranking and comprehensive index ranking on the normalized results respectively include: Based on the minimum-maximum normalization method, the adaptability evaluation value F and the structural stability value S are respectively normalized to obtain a first adaptability evaluation normalized value F' and a first structural stability normalized value S'; The first adaptability evaluation normalized value F' and the first structural stability normalized value S' are sorted respectively to obtain a single index sorting result including the first adaptability sorting value RF and the first structural stability sorting value RS; The ranking averages of the first adaptability ranking values ​​RF and the first structural stability ranking values ​​RS corresponding to each simulated mutant protein are calculated, and the ranking averages of multiple simulated mutant proteins are ranked to obtain the first comprehensive index ranking result R.

[0008] In some of these embodiments, the method further comprises: Based on the Z-Score standardization method, the adaptability evaluation value F and the structural stability value S are normalized respectively to obtain the second adaptability evaluation normalized value F'' and the second structural stability normalized value S''; According to the second adaptability evaluation normalized value F'', the second structural stability normalized value S'', the adaptability index weight coefficient, and the structural stability index weight coefficient, the comprehensive index value of each simulated mutant protein is calculated; The comprehensive indicator values ​​are sorted to obtain a second comprehensive indicator sorting result K.

[0009] In some embodiments, the number of protein folding energy calculation tools is N, and the number of structural stability values ​​S calculated by the simulated mutant proteins based on the protein folding energy calculation tools is N; the step of normalizing the structural stability values ​​S corresponding to the multiple simulated mutant proteins comprises: The N groups of structural stability values ​​Sn calculated by N protein folding energy calculation tools are normalized, n∈[1,N]; The N structural stability normalized values ​​Sn' corresponding to any simulated mutant protein are averaged to obtain the structural stability normalized result corresponding to the simulated mutant protein.

[0010] In some embodiments, the target screening number includes a single index screening number and a comprehensive index screening number; the step of screening multiple simulated mutant proteins according to the target screening number, the single index ranking result and the comprehensive index ranking result to obtain the target mutant protein includes: Determine the first target mutant protein according to the single index screening quantity, the first adaptability ranking value RF, and the first structural stability ranking value RS; After the first target mutant protein is eliminated from the comprehensive index ranking result, the second target mutant protein is determined according to the comprehensive index screening quantity and the comprehensive index ranking result, and the set of the first target mutant protein and the second target mutant protein is the target mutant protein; wherein the comprehensive index ranking result includes the first comprehensive index ranking result R and / or the second comprehensive index ranking result K.

[0011] In some embodiments, before the step of determining the target mutant protein, the method further comprises: In the comprehensive index ranking results, simulated mutant proteins with adaptability evaluation values ​​F less than 0 and structural stability values ​​S greater than 0 were eliminated.

[0012] In some embodiments, the method further includes the steps of building a target protein language model and tuning parameters: A basic protein language model is obtained, the position encoding layer of the basic protein language model is replaced by a learnable embedding code, and a fully connected neural network layer is constructed in the basic protein language model to obtain a target protein language model; wherein the learnable embedding code is used to capture the distance information in the amino acid sequence; and the fully connected neural network layer is used to perform weighted calculation on the type and corresponding position of each amino acid; The target protein language model is trained unsupervisedly to achieve model parameter tuning of the target protein model.

[0013] In order to solve the above problems, one aspect of an embodiment of the present invention provides a mutant protein screening device, comprising: The fitness evaluation value calculation module is used to simulate single mutations at multiple amino acid sites in the protein sequence of the target protein to obtain multiple simulated mutant proteins, and to perform fitness prediction on the simulated single mutant sequences corresponding to the multiple simulated mutant proteins based on the target protein language model to obtain the fitness evaluation value F of each simulated single mutant sequence; wherein any simulated single mutant sequence includes a single mutant protein sequence at the corresponding amino acid site; A structural stability value calculation module is used to determine the simulated single mutant structures corresponding to the multiple simulated mutant proteins, respectively calculate the folding energy change values ​​of the multiple simulated single mutant structures before and after the protein mutation based on the protein folding energy calculation tool, and determine the structural stability value S of each simulated single mutant structure based on the folding energy change value; The data processing module is used to normalize the adaptability evaluation value F and the structural stability value S respectively, and to sort the normalized results by single index and comprehensive index respectively; The screening module is used to screen multiple simulated mutant proteins according to the target screening quantity, single indicator ranking results and comprehensive indicator ranking results to obtain the target mutant protein.

[0014] In order to solve the above problems, one aspect of an embodiment of the present invention provides an electronic device, including: a processor, and a memory storing a program, wherein the program includes instructions, and when the instructions are executed by the processor, the processor executes any of the above mutant protein screening methods.

[0015] In order to solve the above problems, one aspect of an embodiment of the present invention provides a non-transitory machine-readable medium storing computer instructions, where the computer instructions are used to enable a computer to execute any of the above mutant protein screening methods.

[0016] The beneficial effects of the embodiments of the present invention are as follows: by performing simulated single mutations on multiple amino acid sites in a protein sequence of a target protein, multiple simulated mutant proteins are obtained, and adaptability prediction is performed on simulated single mutant sequences corresponding to the multiple simulated mutant proteins based on a target protein language model to obtain an adaptability evaluation value F of each simulated single mutant sequence; wherein any simulated single mutant sequence includes a single mutant protein sequence at a corresponding amino acid site; the simulated single mutant structures corresponding to the multiple simulated mutant proteins are determined, and the folding energy change values ​​of the multiple simulated single mutant structures before and after the protein mutation are calculated based on a protein folding energy calculation tool, and the structural stability value S of each simulated single mutant structure is determined based on the folding energy change value; the adaptability evaluation value F is calculated based on the adaptability evaluation value F of each simulated single mutant sequence; and the adaptability evaluation value F is calculated based on the adaptability evaluation value F of each simulated single mutant sequence. The value F and the structural stability value S are normalized respectively, and the normalized results are sorted by single index and comprehensive index respectively; multiple simulated mutant proteins are screened according to the target screening quantity, the single index sorting results and the comprehensive index sorting results, and the technical means of obtaining the target mutant protein are obtained, by determining the adaptability evaluation value of the simulated protein sequence based on the protein language model, determining the structural stability value of the simulated mutant protein structure based on the protein folding energy calculation tool, and then combining the protein multi-scale evaluation index normalization screening method to screen out mutant proteins with potential functional improvements, thereby achieving the technical effects of reducing the difficulty of protein design and modification, improving the screening effect of mutant proteins, reducing the amount of calculation required for protein modification and screening, shortening the experimental cycle and reducing the cost.

[0017] The details of one or more embodiments of the invention are set forth in the following drawings and description so that other features, objects, and advantages of the invention are more readily apparent. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the prior art descriptions. Obviously, the drawings described below are only some embodiments of the present invention, and for ordinary technicians in this field, other embodiments can be obtained based on these drawings without creative work.

[0019] Figure 1 It is a schematic diagram of the main process of a mutant protein screening method according to an embodiment of the present invention; Figure 2 It is a schematic diagram of the main process of a mutant protein screening method according to another embodiment of the present invention; Figure 3 is a schematic diagram of performing data processing based on a minimum-maximum normalization method according to an embodiment of the present invention; Figure 4 is a schematic diagram of performing data processing based on a Z-Score standardization method according to an embodiment of the present invention; Figure 5 is a schematic diagram of performing target mutant protein screening based on determined data in an embodiment of the present invention; Figure 6 It is a schematic diagram of the main framework of a mutant protein screening device according to an embodiment of the present invention; Figure 7 It is a structural schematic diagram of the electronic device of the present invention. DETAILED DESCRIPTION

[0020] Embodiments of the present invention will be described in more detail below with reference to the accompanying drawings. Although certain embodiments of the present invention are shown in the accompanying drawings, it should be understood that the present invention can be implemented in various forms and should not be construed as being limited to the embodiments described herein, which are instead provided for a more thorough and complete understanding of the present invention. It should be understood that the drawings and embodiments of the present invention are only for exemplary purposes and are not intended to limit the scope of protection of the present invention.

[0021] Related studies have shown that the function of a protein is determined by its structure, and the protein structure is formed by the folding of its amino acid sequence. Therefore, when designing protein mutation improvements, the design is often based on the protein structure or the protein sequence. However, in the related art, if the mutation modification design is only carried out from the perspective of protein structure or protein sequence, the complete protein properties are often not fully considered. For example, the mutation modification design is based only on the protein structure. Due to the high computational cost and long time-consuming process of its complete structural simulation optimization process, most studies can only consider certain key local areas. Although the mutation modification design based only on the protein sequence can quickly consider the characteristics of all amino acid sites in the global range, it lacks the key structural information that leads to the final function of the protein to a certain extent. If both protein structure information and protein sequence information are taken into consideration, the design factors that need to be considered are very complex. Most of the solutions provided by the related technology require designers to have rich prior knowledge of the physicochemical properties of the protein to be designed, and also need to have rich practical experience in protein design methods. Moreover, due to the variety of designed proteins, it is difficult to have a full understanding of the properties of each designed protein. Therefore, how to combine the key important protein structural feature information obtained by calculation with the protein sequence design method that can consider the global situation is of great research significance for computer-aided protein engineering design and modification.

[0022] In order to solve the above problems, the present invention provides a method for screening mutant proteins. Figure 1 As shown, the mutant protein screening method mainly includes: Step S101, simulate single mutations at multiple amino acid sites in the protein sequence of the target protein to obtain multiple simulated mutant proteins, and perform adaptability prediction on the simulated single mutant sequences corresponding to the multiple simulated mutant proteins based on the target protein language model to obtain the adaptability evaluation value F of each simulated single mutant sequence; wherein any simulated single mutant sequence includes a single mutant protein sequence at the corresponding amino acid site.

[0023] The present invention firstly regards the protein performance optimization problem (screening out suitable mutant proteins) as a protein adaptability search problem, that is, protein mutants with high adaptability (i.e. the mutant proteins mentioned above) are assumed to be mutants with potential functional improvements.

[0024] By simulating single mutations at multiple amino acid sites in the protein sequence of the target protein (the target protein is the object of protein modification engineering research, and the simulated mutant protein is a mutant of the target protein that may appear during the evolution process), all possible single mutants can be systematically generated and evaluated, and then the impact of mutations at each amino acid site on protein function and stability can be fully understood. The adaptability of the simulated single mutant sequence is then predicted through the protein language model to obtain the adaptability evaluation value S, based on which mutations that are more likely to be retained during the evolution process can be identified (the higher the value of the adaptability evaluation value S, the higher the possibility that the simulated mutant will be retained during the evolution process), thereby providing valuable candidate mutant proteins for protein engineering.

[0025] The target protein provided in the embodiment of the present invention is a DNA polymerase, preferably Phi29 DNA polymerase or any other DNA polymerase with similar structure and function.

[0026] This is because the functional optimization of DNA polymerase is an important goal in biotechnology and molecular biology research, and through single-site mutations, mutants with higher activity, higher fidelity or longer read length can be screened. At the same time, DNA polymerase also has high stability under extreme conditions such as high temperature and high salt concentration. Single-site mutations can help screen mutants that are more stable under these conditions, thereby expanding its scope of application.

[0027] According to a specific embodiment of an embodiment of the present invention, Phi29 DNA polymerase is known for its high fidelity and long read length (referring to the ability of Phi29 DNA polymerase to continuously synthesize longer DNA fragments during DNA synthesis without frequent termination or errors). It has high fidelity during DNA replication and can continuously synthesize thousands of bases without errors. This property makes it very useful in applications such as genome sequencing, cloning, and amplification. Through single-site mutations, precise changes can be made at specific amino acid sites to study the effects of these changes on enzyme activity, stability, and other functions. The precise mutation method provided by the embodiment of the present invention helps to deeply understand the structure-function relationship of the enzyme.

[0028] The mutant protein screening method provided in the embodiment of the present invention is applied to the screening of mutants of DNA polymerase, especially to the screening of mutants of Phi29 DNA polymerase or DNA polymerase with similar structure and function, so that Phi29 DNA polymerase mutants with higher fidelity can be screened out, thereby reducing the error rate in the sequencing and cloning process, and based on the stability of DNA polymerase under high temperature conditions, mutants that can still maintain high activity and stability at high temperature can be screened out; based on the high fidelity and long read length characteristics of Phi29 DNA polymerase, Phi29 DNA polymerase mutants with longer read length can be screened out, thereby improving the coverage and accuracy of genome sequencing.

[0029] According to a specific implementation of an embodiment of the present invention, all amino acid sites of the target protein can be subjected to separate replacement mutations of the remaining 19 natural amino acids except the amino acids themselves, so as to obtain 19*L (L is the length of the target protein sequence) single mutant protein sequences as input for subsequent predictions. Among them, the amino acid itself refers to the original amino acid at a specific position in the target protein sequence. Eliminating the amino acid itself helps to avoid redundancy, reduce the amount of simulation calculations, and simplify subsequent data analysis. It should be noted that there are many types of amino acids in proteins. The number of amino acids involved in the mutation in the above specific implementation is not a limitation of the present invention. The types of amino acids required for simulated mutations can be adjusted according to the mutation design and modification requirements of actual protein engineering. For example, according to a specific implementation of an embodiment of the present invention, all amino acid sites of the target protein are simulated for single mutations, so as to consider the mutation effects of all sites from a global perspective and provide a comprehensive adaptive prediction.

[0030] In some of the embodiments, the method further includes the steps of building a target protein language model and tuning parameters: obtaining a basic protein language model, replacing the position encoding layer of the basic protein language model with a learnable embedding code, and constructing a fully connected neural network layer in the basic protein language model to obtain a target protein language model; wherein the learnable embedding code is used to capture distance information in the amino acid sequence; the fully connected neural network layer is used to perform weighted calculations on the type and corresponding site of each amino acid; and performing unsupervised training on the target protein language model to achieve model parameter tuning of the target protein model.

[0031] According to a specific implementation of an embodiment of the present invention, the Tranception model is selected as the basic protein language model, and the basic protein language model uses Transformer as the underlying architecture. Compared with other large-scale protein language models, the Tranception model focuses on protein adaptability prediction tasks, which helps to improve the accuracy of the calculated adaptability value. At the same time, in order to further improve the adaptability prediction effect of the model, in the construction of the target protein language model: in addition to using the Tranception model itself, the learnable embedding code is used in the position encoding layer of the basic model to replace the "Grouped ALiBi" mechanism of the basic model itself. The learnable embedding code can better capture the distance information in the amino acid sequence. In order to fully consider the distance information of all amino acid sites, a layer of fully connected neural network is also constructed to perform weighted calculation on the type code and corresponding site of each amino acid (specific steps: input the type code of each amino acid (for example, one-hot code of 20 natural amino acids) and its position information in the sequence; these inputs are weighted through the fully connected layer to generate a new embedding vector; the generated embedding vector will be used as the input of the Transformer model), further enhancing the expression ability of the model. For the parameter tuning step: by obtaining a basic data set, which includes functional labels of multiple proteins (suitable for evaluating the performance of protein language models), the target protein language model is trained and optimized based on the zero-shot data set and the partial-shot data set, where the prediction results of the zero-shot data set and the partial-shot data set are configured with different weight coefficients. For example, "ProteinGym" can be selected as the benchmark data set, and the target protein language model is used for training and prediction in multiple rounds of zero-shot cases (in the zero-shot case, the model has not seen any data of a specific protein and only relies on pre-trained knowledge. A larger weight coefficient can be set to maximize the prediction effect under unsupervised conditions) and partial-shot cases (in the partial-shot case, the model can access a small amount of data of a specific protein for fine-tuning the model, and a smaller weight coefficient can be set to supplement the prediction results in the zero-shot case). The optimal parameters are obtained based on the prediction results, where the weight of the prediction results obtained in the zero-shot case can be set to 0.8, in order to maximize the prediction effect of the target protein language model under unsupervised conditions.

[0032] Step S102, determine the simulated single mutant structures corresponding to the multiple simulated mutant proteins, calculate the folding energy change values ​​of the multiple simulated single mutant structures before and after the protein mutation based on the protein folding energy calculation tool, and determine the structural stability value S of each simulated single mutant structure based on the folding energy change value.

[0033] By calculating the change in folding energy of simulated single mutant structures before and after mutation using protein folding energy calculation tools (such as molecular modeling software Discovery Studio and FoldX), the effect of each mutation on the stability of the protein structure can be quantitatively evaluated. The structural stability value S can be used to screen out mutants that still maintain or improve structural stability after mutation, which helps to quickly screen out candidate mutants with stable structures, reduce the workload of experimental verification, and improve the efficiency and accuracy of mutant protein screening.

[0034] According to a specific implementation of an embodiment of the present invention, the virtual amino acid mutation function of Discovery Studio can be used to specify single mutations at all amino acid sites, and then the structural stability value S (i.e., the following formula in the formula) of each simulated single mutant structure can be calculated based on the calculation formula designed in Discovery Studio software. ) is calculated. The calculation formula is as follows: in, In the above formula is the free energy of the protein in the folded state, is the free energy of protein unfolding (or folding being disrupted), wild type represents the wild-type structure of the target protein, and mut represents the mutant structure of the simulated mutant protein. As the structural stability value S, a negative value indicates that the mutant is more stable than the wild type, that is, the mutation has a stabilizing effect; a positive value indicates that the mutant is more unstable than the wild type, that is, the mutation has a destabilizing effect.

[0035] In some of the embodiments, the step of determining the simulated single mutant structures corresponding to the multiple simulated mutant proteins is: using the molecular modeling software Discovery Studio to simulate single mutations at all amino acid sites of the target protein to generate multiple simulated single mutant structures.

[0036] In some of the embodiments, before the step of determining the simulated single mutant structures corresponding to the multiple simulated mutant proteins, the method further includes: obtaining a wild-type protein structure file of the target protein, and preliminarily screening the protein structure file based on the structural evaluation factors to obtain the target protein structure file; wherein the wild-type protein structure file includes the three-dimensional structure of the target protein in its natural state (the three-dimensional structure of the target protein can also be obtained first through existing experimental methods (such as X-ray crystallography or NMR). If the structure observed by the experimental method is not available, a high-quality protein structure prediction model (such as AlphaFold) is used to generate the wild-type protein structure file); preprocessing the target protein structure file; wherein the preprocessing includes simulating the removal of crystal water and simulating the assignment of force field parameters.

[0037] According to a specific implementation of an embodiment of the present invention, when a protein structure file is preliminarily screened based on structural evaluation factors, the following structural evaluation factors are mainly considered: resolution (resolution is an important indicator for measuring the accuracy of protein structure, and high resolution means more accurate atomic position information), RMSD value (RMSD (root mean square deviation) is used to measure the similarity between two structures. A lower RMSD value indicates that the difference between the two structures is smaller, and a structure with a lower RMSD is usually selected to ensure the consistency and reliability of the structure), the presence or absence of a ligand (the function of some proteins is closely related to the ligand to which it binds. If the modification target involves the binding of a specific ligand, it is necessary to select a structure file containing the correct ligand) and ligand quality assessment (even if the structure contains a ligand, it is necessary to evaluate whether the position and conformation of the ligand are reasonable. The wrong position or conformation of the ligand may affect subsequent calculations and analysis results), etc. After determining a suitable protein structure file (i.e., the above-mentioned target protein structure file), Discovery Studio can be used to preprocess the target protein file, including the removal of crystal water and the assignment of the CHARMm force field (referring to the use of the CHARMm force field to parameterize the protein structure to ensure the accuracy of subsequent calculations) and other operations.

[0038] In some of the embodiments, due to different calculation methods of folding energy for simulated mutant proteins, the structural stability values ​​S calculated by different protein folding energy calculation tools are slightly different. In order to further ensure the accuracy of the calculated structural stability value, another protein folding energy calculation tool FolfX is selected in a specific embodiment of the embodiment of the present invention to calculate the structural stability value of the mutant (i.e., in the following formula: ), the expression is as follows: in, : The sum of the van der Waals interaction contributions of all atoms relative to the solvent; Energy term The corresponding weight coefficient. and : are the solubility energy differences of nonpolar and polar groups from unfolded to folded states, respectively; and The energy terms are and The corresponding weight coefficient. : Refers to the additional stabilizing free energy provided by a water molecule forming multiple hydrogen bonds (called water bridges) with proteins. : Refers to the free energy difference between intramolecular hydrogen bond formation and intermolecular hydrogen bond formation (with solvent). : Refers to the electrostatic contribution of charged groups, including the helical dipole moment. : refers to the entropy cost of fixing the main chain in the folded state, Energy term The corresponding weight coefficient. : refers to the entropic cost of fixing the side chain in a specific conformation, Energy term The corresponding weight coefficient.

[0039] Discovery Studio and FoldX software, two professional molecular modeling software, are used to simulate and calculate the structural stability of the target protein, thereby providing high-precision structural information, which helps to more accurately evaluate the mutation effect. Specifically, based on the above molecular modeling software, the wild-type structure of the target protein is first changed to a mutant type, and the change in the folding free energy of the protein structure before and after the mutation is calculated to determine the change in the stability of the mutant and obtain the structural stability value S (which represents the structural stability effect of the mutant and serves as a reference for screening mutation sites with improved stability). Through structural simulation, the effect of mutations on the three-dimensional structure and stability of the protein can be more accurately evaluated.

[0040] It is understandable that in order to further improve the calculated structural stability value S of the simulated mutant, other more accurate protein folding energy calculation tools can be used, or the number of protein folding energy calculation tools can be increased.

[0041] Step S103, normalizing the adaptability evaluation value F and the structural stability value S respectively, and performing single index sorting and comprehensive index sorting on the normalized results respectively.

[0042] The adaptability evaluation value F and the structural stability value S usually have different dimensions and numerical ranges. Through normalization, these indicators of different scales can be unified into the same interval (such as 0 to 1), making the weights between different indicators more balanced, avoiding a certain indicator from having too much influence on the comprehensive score due to its large value, thus facilitating comparison and comprehensive evaluation. The normalization results are sorted by single indicator and comprehensive indicator, respectively. Single indicator sorting can help researchers quickly identify mutants that perform well in a specific indicator, while comprehensive indicator sorting combines information from multiple aspects, providing a more comprehensive evaluation standard, and helping to screen out mutants that perform well in multiple aspects.

[0043] At the same time, normalization and sorting methods can automatically process large amounts of data, reduce the workload of manual analysis, and improve screening efficiency. Through systematic sorting methods, the optimal mutants can be quickly screened out, accelerating the progress of protein engineering projects. Combining multiple indicators for comprehensive evaluation can reduce the deviation caused by a single indicator and improve the robustness and reliability of screening results. Multi-indicator comprehensive evaluation can better reflect the performance of mutants in practical applications and improve the practicality and credibility of screening results.

[0044] In some of the embodiments, the steps of normalizing the adaptability evaluation value F and the structural stability value S, respectively, and performing single index ranking and comprehensive index ranking on the normalized results, respectively, include: normalizing the adaptability evaluation value F and the structural stability value S, respectively, based on the minimum-maximum normalization method, to obtain a first adaptability evaluation normalized value F' and a first structural stability normalized value S'; sorting the first adaptability evaluation normalized value F' and the first structural stability normalized value S', respectively, to obtain a single index ranking result including a first adaptability ranking value RF and a first structural stability ranking value RS; calculating the ranking average of the first adaptability ranking value RF and the first structural stability ranking value RS corresponding to each simulated mutant protein, sorting the ranking averages of multiple simulated mutant proteins, and obtaining a first comprehensive index ranking result R.

[0045] For the fitness evaluation value F corresponding to multiple simulated mutant proteins under the fitness index, or the structural stability value S corresponding to multiple simulated mutant proteins under the structural stability index. Taking X (referring to the fitness index or structural stability index) as an example, when the minimum-maximum normalization method is applied, the minimum value Xmin and the maximum value Xmax of the index are first found, and then normalized using the following formula: in, is the normalized value.

[0046] The above steps are a specific implementation method of the embodiment of the present invention for normalizing the adaptability evaluation index and the structural stability evaluation index, and sorting the normalized results by single index and comprehensive index. Among them, the maximum and minimum normalization method is a data preprocessing method that uses the maximum and minimum values ​​in the data column to scale the data to between [0,1].

[0047] By using the minimum-maximum normalization method, the fitness evaluation value F and the structural stability value S are normalized to between 0 and 1, so that the numerical ranges of different indicators (i.e., sequence fitness evaluation index and structural stability index) are consistent, so as to compare the performance of different indicators on the same scale. By sorting the first fitness evaluation value F' and the first structural stability value S' obtained after normalization, the single index sorting results (i.e., the first fitness ranking value RF and the first structural stability ranking value RS) are obtained, which can intuitively show the performance of each mutant in fitness evaluation and structural stability. Further, the ranking average of multiple single index ranking results corresponding to each simulated mutant protein is re-sorted to obtain the first comprehensive index ranking result R. This method combines the information of multiple indicators, provides a more comprehensive evaluation standard, reduces the deviation caused by a single indicator, can better reflect the performance of mutants in practical applications, improve the practicality and credibility of screening results, improve the robustness and reliability of screening results, and can help researchers screen out mutants with good performance in both adaptability and stability.

[0048] In some embodiments, the method further includes: normalizing the adaptability evaluation value F and the structural stability value S based on the Z-Score standardization method to obtain a second adaptability evaluation normalized value F'' and a second structural stability normalized value S''; calculating the comprehensive index value of each simulated mutant protein according to the second adaptability evaluation normalized value F'', the second structural stability normalized value S'', the adaptability index weight coefficient, and the structural stability index weight coefficient; and sorting the comprehensive index values ​​to obtain a second comprehensive index sorting result K.

[0049] According to a specific implementation of an embodiment of the present invention, the specific formula for Z-Score standardization calculation is as follows: in, is the mean value of each indicator, is the standard deviation of each index, and X is the index value of each simulated mutant.

[0050] The above steps are another specific implementation method of the embodiment of the present invention for normalizing the adaptability evaluation index and the structural stability evaluation index, and ranking the normalized results by comprehensive index. Among them, the Z-Score standardization method is also a data normalization processing method, which converts two or more groups of data into unitless Z-Score scores to unify the data standards and improve the data comparability.

[0051] By performing Z-Score normalization on the fitness evaluation value F and the structural stability value S, and calculating the comprehensive index value based on the normalized value, the fitness index weight coefficient and the structural stability index weight coefficient, and then sorting the comprehensive index value to obtain the second comprehensive index sorting result K, the comparability between different indicators can be improved and a comprehensive comprehensive evaluation can be performed. Among them, Z-Score normalization not only unifies the scale, but also takes into account the distribution characteristics of the data. The normalized value reflects the relative position of each mutant in each indicator, which helps to more accurately evaluate its performance. This method not only helps to screen mutants with potential functional improvements and stable structures, but also provides an important reference for subsequent experimental design, improving the efficiency and success rate of protein engineering research.

[0052] In some of the embodiments, the number of the above-mentioned protein folding energy calculation tools is N, and the number of structural stability values ​​S calculated by the above-mentioned simulated mutant proteins based on the protein folding energy calculation tools is N; the step of normalizing the structural stability values ​​S corresponding to multiple simulated mutant proteins includes: normalizing the N groups of structural stability values ​​Sn respectively calculated by the N protein folding energy calculation tools, n∈[1,N]; averaging the N structural stability normalized values ​​Sn' corresponding to any simulated mutant protein to obtain the structural stability normalization result corresponding to the simulated mutant protein.

[0053] Different protein folding energy calculation tools may be based on different algorithms and models, so they may have different advantages and limitations when calculating structural stability. By using multiple tools, their respective shortcomings can be complemented, the robustness and reliability of the calculation results can be improved, and a more accurate stability assessment can be provided. The structural stability value of each simulated mutant protein is calculated separately by N tools, which is equivalent to multiple verifications, which helps to identify mutants that perform consistently in different tools, thereby improving the credibility of the results.

[0054] The average of the N normalized structural stability values ​​Sn' of each simulated mutant protein was calculated to obtain the final structural stability normalization result, which integrated the calculation results of multiple tools, reduced the random noise in the calculation of a single tool, and improved the stability and accuracy of the evaluation results.

[0055] Step S104, screening multiple simulated mutant proteins according to the target screening quantity, single index ranking results and comprehensive index ranking results to obtain the target mutant protein.

[0056] By setting a specific target screening number, we can ensure that the number of mutants finally screened meets the research needs, which helps to control the scale of the experiment and avoid waste of resources. Based on the ranking results of a single indicator, we can quickly identify mutants that perform well in a specific aspect. Combining the comprehensive ranking results of multiple indicators, we can comprehensively evaluate the overall performance of each mutant and screen out mutants that perform well in multiple aspects.

[0057] In some of the embodiments, the target screening quantity includes a single index screening quantity and a comprehensive index screening quantity; the step of screening multiple simulated mutant proteins according to the target screening quantity, the single index ranking result and the comprehensive index ranking result to obtain the target mutant protein includes: determining the first target mutant protein according to the single index screening quantity, the first adaptability ranking value RF, and the first structural stability ranking value RS; after eliminating the first target mutant protein in the comprehensive index ranking result, determining the second target mutant protein according to the comprehensive index screening quantity and the comprehensive index ranking result, and the collection of the first target mutant protein and the second target mutant protein is the target mutant protein; wherein the comprehensive index ranking result includes the first comprehensive index ranking result R and / or the second comprehensive index ranking result K.

[0058] The above steps provide a specific embodiment of screening out target mutant proteins based on target screening quantity, single index ranking results, and comprehensive index ranking results. Through the two screening methods of single index screening and comprehensive index screening, it is achieved to evaluate mutants from different angles, improve the precision and accuracy of screening, and simultaneously obtain mutants that perform well in a single index and mutants that perform well in comprehensive indicators, thereby achieving diversified screening. Specifically, single index screening may miss mutants that perform well in comprehensive performance, while comprehensive index screening may ignore some mutants that are particularly prominent in specific attributes. Through two-step screening, the possibility of omission can be reduced.

[0059] On the other hand, based on different choices of data processing methods (normalization processing method, sorting method), multiple comprehensive ranking results may be obtained in the end (such as the first comprehensive indicator ranking result R and the second comprehensive indicator ranking result K mentioned above). After the single indicator screening, the ranking results of each comprehensive indicator can be screened again. It is only necessary to remove duplicates of the same target mutant protein after the screening is completed.

[0060] In some embodiments, before the step of determining the target mutant protein, the method further comprises: eliminating simulated mutant proteins whose adaptability evaluation value F is less than 0 and whose structural stability value S is greater than 0 in the comprehensive index ranking results.

[0061] The fitness evaluation value F obtained based on the prediction of the protein language model represents the possibility that the mutation of the protein can be retained during the evolution process. The higher the value, the more likely the mutation makes the protein more adaptable to the biological environment. A fitness evaluation value F less than 0 usually indicates that the mutant is unfavorable in the evolution process and may reduce the function or stability of the protein. The structural stability value S obtained by simulation calculation based on the protein folding energy effect represents the effect of the protein on the structural stability after mutation. Generally, a negative value indicates that the mutation makes the structure stable, that is, the energy required for folding is less than the energy for deconstruction. The smaller the value, the smaller the energy required for protein folding, that is, the more stable the protein structure in theory. The structural stability value S greater than 0 indicates that the structure of the protein becomes unstable after mutation. Therefore, it can be determined that the simulated mutant protein with a fitness evaluation value F less than 0 and a structural stability value S greater than 0 is a defective mutant. Studies have shown that mutants that show defects in any indicator will most likely not have good characterization results in actual experiments.

[0062] Therefore, by eliminating simulated mutants that present positive values ​​in protein stability calculation results and mutants that present negative values ​​in fitness prediction, it helps to improve the quality of screening (eliminating bad mutants), increase the reliability of screening results, optimize resource allocation, improve guidance of experimental design and increase the success rate.

[0063] Based on the above steps, the embodiment of the present invention also achieves the following technical effects: 1. A protein mutation effect evaluation method that combines the calculation of protein folding energy effect (protein structure stability index) with protein adaptability prediction (protein sequence adaptability index) is proposed, which provides an effective tool for judging the possible impact of protein mutations and also provides a basis for basic research on protein mutations; 2. It is proposed to use protein stability and protein adaptability for protein mutation screening, and to achieve protein mutant screening by integrating protein structure information, protein sequence and evolution information, solving the problem that the existing method cannot fully utilize the existing information of the target protein; 3. A protein multi-scale evaluation index normalization screening method is proposed, and through the maximum-minimum value normalization method and Z-score standardization method and the means of first selecting specialties and then eliminating, a comprehensive screening of protein mutants with potential functional improvements in multiple dimensions and multiple systems is achieved. 4. Through multiple protein stability calculation tools, the problem of insufficient robustness of a single method at this stage is solved, and the problem of insufficient consideration of the folding energy term is compensated by using different calculation methods, thereby improving the screening accuracy.

[0064] The mutant protein screening method provided by the embodiment of the present invention adopts the method of performing simulated single mutations on multiple amino acid sites in the protein sequence of the target protein to obtain multiple simulated mutant proteins, and performs adaptability prediction on the simulated single mutant sequences corresponding to the multiple simulated mutant proteins based on the target protein language model to obtain the adaptability evaluation value F of each simulated single mutant sequence; wherein any simulated single mutant sequence includes the single mutant protein sequence of the corresponding amino acid site; the simulated single mutant structures corresponding to the multiple simulated mutant proteins are determined, and the folding energy change values ​​of the multiple simulated single mutant structures before and after the protein mutation are calculated based on the protein folding energy calculation tool, and the structural stability value S of each simulated single mutant structure is determined based on the folding energy change value; The adaptability evaluation value F and the structural stability value S are normalized respectively, and the normalized results are sorted by single index and comprehensive index respectively; multiple simulated mutant proteins are screened according to the target screening quantity, the single index sorting results and the comprehensive index sorting results to obtain the technical means of the target mutant protein, by determining the adaptability evaluation value of the simulated protein sequence based on the protein language model, determining the structural stability value of the simulated mutant protein structure based on the protein folding energy calculation tool, and then combining the protein multi-scale evaluation index normalization screening method to screen out mutant proteins with potential functional improvements, thereby achieving the technical effects of reducing the difficulty of protein design and modification, improving the screening effect of mutant proteins, reducing the amount of calculation required for protein modification and screening, shortening the test cycle and reducing costs.

[0065] The present invention also provides a method for screening mutant proteins. Figure 2As shown, mutant protein screening mainly includes: First, all amino acid sites in the protein sequence of the target protein are simulated for single mutations, and the protein sequences and protein structures corresponding to multiple simulated mutant proteins are obtained. For the protein sequence of the simulated mutant protein, the adaptability prediction is performed based on the unsupervised protein language model to obtain the adaptability evaluation value F. For the protein sequence of the simulated mutant protein, the molecular modeling software Discovery Studio and FoldX are used to perform stability calculations of the protein folding energy effect, respectively, to obtain the structural stability values ​​S1 and S2. Then two numerical normalization algorithms (minimum-maximum normalization method and Z-Score normalization method) are used for numerical processing. Finally, the demand (target screening quantity) is determined, and the specialty value (i.e., screening for the single index ranking results) is first selected to obtain the first target mutant protein; then the comprehensive index ranking results are screened to obtain the second target mutant protein, and the first target mutant protein and the second target mutant protein constitute the mutant library finally screened.

[0066] According to a specific implementation of an embodiment of the present invention, the data processing steps performed based on the minimum-maximum normalization method are as follows: Figure 3 As shown. First, the adaptability evaluation value F (also known as the adaptability prediction value F) obtained based on the protein language model, the structural stability value S1 (also known as the stability value calculation value S1) calculated based on Discovery Studio, and the structural stability value S2 (also known as the stability value calculation value S2) calculated based on FoldX are normalized by the minimum-maximum normalization method to obtain the first adaptability evaluation normalized value F', the first structural stability normalized values ​​S1' and S2', wherein, since S1' and S2' are both structural stability indicators, the two values ​​are arithmetic averaged to obtain S'. The first adaptability evaluation normalized value F' and the first structural stability normalized value S' are sorted respectively to obtain a single index sorting result including the first adaptability ranking value RF and the first structural stability ranking value RS. Then, the sorting average of the first adaptability ranking value RF and the first structural stability ranking value RS corresponding to each simulated mutant protein is calculated, and the sorting average of multiple simulated mutant proteins is sorted to obtain the first comprehensive index sorting result R.

[0067] According to a specific implementation of an embodiment of the present invention, the data processing steps performed based on the Z-Score standardization method are as follows: Figure 4As shown. First, the adaptability evaluation value F (also called adaptability prediction value F) obtained based on the protein language model, the structural stability value S1 (also called stability value calculation value S1) calculated based on Discovery Studio, and the structural stability value S2 (also called stability value calculation value S2) calculated based on FoldX are normalized by the Z-Score normalization method to obtain the second adaptability evaluation normalized value F'', the second structural stability normalized value S1'' and S2'', and then the comprehensive index value FS of each simulated mutant protein is calculated according to the second adaptability evaluation normalized value F'', the second structural stability normalized value S'', the adaptability index weight coefficient, and the structural stability index weight coefficient, and the comprehensive index value is sorted to obtain the second comprehensive index sorting result K. Among them, the expression for calculating the comprehensive index value FS is as follows: Among them, the weight coefficient of the adaptability index is set to 0.6, and the structural index is set to 0.2. However, it should be noted that the specific numerical setting of the weight coefficient is not a limitation of the present invention, and can be adaptively adjusted according to actual experimental conditions and protein modification requirements.

[0068] like Figure 5 As shown, the present invention also provides a specific method for screening and obtaining a target mutant protein, comprising: first determining the target screening number (i.e., Figure 5The total demand S in the total demand S), and then first screen from the single index sorting results, that is, screen from the specialty. Specifically, the mutants that rank the highest in each index and are not much different from the next mutant in the index can be regarded as mutants with "specialties". This part of the mutants will only consider a single index, and about 20% of the total screening amount S will be selected. Then screen from the comprehensive sorting index, such as 30% of the total screening amount S can be screened from the first comprehensive sorting result R, and 30% of the total screening amount S can be screened from the second comprehensive sorting result K. At the same time, considering that the target mutant proteins screened from the first comprehensive sorting result R and the second comprehensive sorting result K will be repeated, after deduplication, the total number of target mutant proteins screened does not meet the target screening number (that is, does not meet the total demand). At this time, the simulated mutant proteins with an adaptability evaluation value F less than 0 and a structural stability value S greater than 0 in the remaining simulated mutant proteins can be eliminated, and then about 10% of the total screening amount S can be screened again from the first comprehensive sorting result R and the second comprehensive sorting result K. It should be noted that the above numerical values ​​are only examples and are not intended to limit the present invention.

[0069] Based on the mutant protein screening method provided in the embodiment of the present invention, the embodiment of the present invention also provides a mutant protein screening device, such as Figure 6 As shown, the mutant protein screening device 600 includes: The fitness evaluation value calculation module 601 is used to simulate single mutations at multiple amino acid sites in the protein sequence of the target protein to obtain multiple simulated mutant proteins, and to perform fitness prediction on the simulated single mutant sequences corresponding to the multiple simulated mutant proteins based on the target protein language model to obtain the fitness evaluation value F of each simulated single mutant sequence; wherein any simulated single mutant sequence includes a single mutant protein sequence at the corresponding amino acid site.

[0070] By simulating single mutations at multiple amino acid sites in the protein sequence of the target protein (the target protein is the object of protein modification engineering research, and the simulated mutant protein is a mutant of the target protein that may appear during the evolution process), all possible single mutants can be systematically generated and evaluated, and then the impact of mutations at each amino acid site on protein function and stability can be fully understood. The adaptability of the simulated single mutant sequence is then predicted through the protein language model to obtain the adaptability evaluation value S, based on which mutations that are more likely to be retained during the evolution process can be identified (the higher the value of the adaptability evaluation value S, the higher the possibility that the simulated mutant will be retained during the evolution process), thereby providing valuable candidate mutant proteins for protein engineering.

[0071] In some of the embodiments, the mutant protein screening device 600 further includes a model building and parameter tuning module, which is used to: obtain a basic protein language model, replace the position encoding layer of the basic protein language model with a learnable embedded code, and construct a fully connected neural network layer in the basic protein language model to obtain a target protein language model; wherein the learnable embedded code is used to capture the distance information in the amino acid sequence; the fully connected neural network layer is used to perform weighted calculation on the type and corresponding site of each amino acid; and perform unsupervised training on the target protein language model to achieve model parameter tuning processing for the target protein model.

[0072] The structural stability value calculation module 602 is used to determine the simulated single mutant structures corresponding to the multiple simulated mutant proteins, calculate the folding energy change values ​​of the multiple simulated single mutant structures before and after the protein mutation based on the protein folding energy calculation tool, and determine the structural stability value S of each simulated single mutant structure based on the folding energy change value.

[0073] By calculating the change in folding energy of simulated single mutant structures before and after mutation using protein folding energy calculation tools (such as molecular modeling software Discovery Studio and FoldX), the effect of each mutation on the stability of the protein structure can be quantitatively evaluated. The structural stability value S can be used to screen out mutants that still maintain or improve structural stability after mutation, which helps to quickly screen out candidate mutants with stable structures, reduce the workload of experimental verification, and improve the efficiency and accuracy of mutant protein screening.

[0074] It is understandable that in order to further improve the calculated structural stability value S of the simulated mutant, other more accurate protein folding energy calculation tools can be used, or the number of protein folding energy calculation tools can be increased.

[0075] The data processing module 603 is used to perform normalization processing on the adaptability evaluation value F and the structural stability value S respectively, and to perform single index sorting and comprehensive index sorting on the normalization processing results respectively.

[0076] The adaptability evaluation value F and the structural stability value S usually have different dimensions and numerical ranges. Through normalization, these indicators of different scales can be unified into the same interval (such as 0 to 1), making the weights between different indicators more balanced, avoiding a certain indicator from having too much influence on the comprehensive score due to its large value, thus facilitating comparison and comprehensive evaluation. The normalization results are sorted by single indicator and comprehensive indicator, respectively. Single indicator sorting can help researchers quickly identify mutants that perform well in a specific indicator, while comprehensive indicator sorting combines information from multiple aspects, providing a more comprehensive evaluation standard, and helping to screen out mutants that perform well in multiple aspects.

[0077] Among them, the normalization processing method provided by the embodiment of the present invention may include a minimum-maximum normalization method, a Z-Score standardization method, and other types of data scale unification methods.

[0078] In some of the embodiments, the data processing module 603 is used to: normalize the adaptability evaluation value F and the structural stability value S based on the minimum-maximum normalization method, respectively, to obtain a first adaptability evaluation normalized value F' and a first structural stability normalized value S'; sort the first adaptability evaluation normalized value F' and the first structural stability normalized value S', respectively, to obtain a single index ranking result including a first adaptability ranking value RF and a first structural stability ranking value RS; calculate the ranking average of the first adaptability ranking value RF and the first structural stability ranking value RS corresponding to each simulated mutant protein, sort the ranking averages of multiple simulated mutant proteins, and obtain a first comprehensive index ranking result R.

[0079] By using the minimum-maximum normalization method, the fitness evaluation value F and the structural stability value S are normalized to between 0 and 1, so that the numerical ranges of different indicators (i.e., sequence fitness evaluation index and structural stability index) are consistent, so as to compare the performance of different indicators on the same scale. By sorting the first fitness evaluation value F' and the first structural stability value S' obtained after normalization, the single index sorting results (i.e., the first fitness ranking value RF and the first structural stability ranking value RS) are obtained, which can intuitively show the performance of each mutant in fitness evaluation and structural stability. Further, the ranking average of multiple single index ranking results corresponding to each simulated mutant protein is re-sorted to obtain the first comprehensive index ranking result R. This method combines the information of multiple indicators, provides a more comprehensive evaluation standard, reduces the deviation caused by a single indicator, can better reflect the performance of mutants in practical applications, improve the practicality and credibility of screening results, improve the robustness and reliability of screening results, and can help researchers screen out mutants with good performance in both adaptability and stability.

[0080] In some of the embodiments, the data processing module 603 is also used to: normalize the adaptability evaluation value F and the structural stability value S based on the Z-Score standardization method, respectively, to obtain a second adaptability evaluation normalized value F'' and a second structural stability normalized value S''; calculate the comprehensive index value of each simulated mutant protein according to the second adaptability evaluation normalized value F'', the second structural stability normalized value S'', the adaptability index weight coefficient, and the structural stability index weight coefficient; and sort the comprehensive index values ​​to obtain a second comprehensive index sorting result K.

[0081] By performing Z-Score normalization on the fitness evaluation value F and the structural stability value S, and calculating the comprehensive index value based on the normalized value, the fitness index weight coefficient and the structural stability index weight coefficient, and then sorting the comprehensive index value to obtain the second comprehensive index sorting result K, the comparability between different indicators can be improved and a comprehensive comprehensive evaluation can be performed. Among them, Z-Score normalization not only unifies the scale, but also takes into account the distribution characteristics of the data. The normalized value reflects the relative position of each mutant in each indicator, which helps to more accurately evaluate its performance. This method not only helps to screen mutants with potential functional improvements and stable structures, but also provides an important reference for subsequent experimental design, improving the efficiency and success rate of protein engineering research.

[0082] The screening module 604 is used to screen multiple simulated mutant proteins according to the target screening quantity, the single index ranking results and the comprehensive index ranking results to obtain the target mutant protein.

[0083] By setting a specific target screening number, we can ensure that the number of mutants finally screened meets the research needs, which helps to control the scale of the experiment and avoid waste of resources. Based on the ranking results of a single indicator, we can quickly identify mutants that perform well in a specific aspect. Combining the comprehensive ranking results of multiple indicators, we can comprehensively evaluate the overall performance of each mutant and screen out mutants that perform well in multiple aspects.

[0084] In some of the embodiments, the screening module 604 is also used to: determine a first target mutant protein based on the number of single-index screening, a first adaptability ranking value RF, and a first structural stability ranking value RS; after eliminating the first target mutant protein in the comprehensive index ranking result, determine the second target mutant protein based on the number of comprehensive index screening and the comprehensive index ranking result, and the set of the first target mutant protein and the second target mutant protein is the target mutant protein; wherein the comprehensive index ranking result includes the first comprehensive index ranking result R and / or the second comprehensive index ranking result K.

[0085] Through the two screening methods of single index screening and comprehensive index screening, it is possible to evaluate mutants from different angles, improve the precision and accuracy of screening, and simultaneously obtain mutants that perform well in a single index and mutants that perform well in comprehensive indexes, thereby achieving diversified screening. Specifically, single index screening may miss mutants that perform well in comprehensive performance, while comprehensive index screening may ignore certain mutants that are particularly outstanding in specific properties. Through two-step screening, the possibility of omissions can be reduced.

[0086] In some of the embodiments, the mutant protein screening device further includes an elimination module. Before the step of determining the target mutant protein, the elimination module is used to eliminate simulated mutant proteins whose adaptability evaluation value F is less than 0 and whose structural stability value S is greater than 0 in the comprehensive index ranking results.

[0087] Eliminating simulated mutants with positive values ​​in protein stability calculation results and mutants with negative values ​​in fitness prediction helps to improve screening quality (eliminating bad mutants), increase the reliability of screening results, optimize resource allocation, improve guidance of experimental design and increase success rate.

[0088] The mutant protein screening device provided by the embodiment of the present invention adopts an adaptability evaluation value calculation module, which is used to simulate single mutations at multiple amino acid sites in the protein sequence of the target protein to obtain multiple simulated mutant proteins, and to perform adaptability prediction on the simulated single mutant sequences corresponding to the multiple simulated mutant proteins based on the target protein language model to obtain the adaptability evaluation value F of each simulated single mutant sequence; wherein any simulated single mutant sequence includes a single mutant protein sequence at the corresponding amino acid site; a structural stability value calculation module, which is used to determine the simulated single mutant structures corresponding to the multiple simulated mutant proteins, and to calculate the folding energy change values ​​of the multiple simulated single mutant structures before and after the protein mutation based on the protein folding energy calculation tool, and to determine the structural stability value S of each simulated single mutant structure based on the folding energy change value; a data processing module, which is used to normalize the adaptability evaluation value F and the structural stability value S, respectively, and to perform single index sorting and comprehensive index sorting on the normalized results; a screening module, which is used to screen the multiple simulated mutant proteins according to the target screening quantity, the single index sorting result and the comprehensive index sorting result to obtain the target mutant protein. It was achieved by determining the adaptability evaluation value of the simulated protein sequence based on the protein language model, determining the structural stability value of the simulated mutant protein structure based on the protein folding energy calculation tool, and then combining the normalized screening method of protein multi-scale evaluation indicators to screen out mutant proteins with potential functional improvements. This achieved the technical effects of reducing the difficulty of protein design and modification, improving the screening effect of mutant proteins, reducing the amount of calculation required for protein modification and screening, shortening the experimental cycle and reducing costs.

[0089] An embodiment of the present invention further provides a non-transitory machine-readable medium storing a computer program, wherein the computer program, when executed by a processor of a computer, is used to cause the computer to execute the method of the embodiment of the present invention.

[0090] The embodiment of the present invention further provides a computer program product, including a computer program, wherein the computer program is used to make the computer perform the method of the embodiment of the present invention when executed by a processor of the computer. The computer program product should be understood as a software product that mainly implements the above method of the present invention through a computer program.

[0091] An embodiment of the present invention further provides an electronic device, comprising: at least one processor; and a memory in communication with the at least one processor. The memory stores a computer program executable by the at least one processor, and when the computer program is executed by the at least one processor, the electronic device executes the method of the embodiment of the present invention.

[0092] refer to Figure 7, a block diagram of an electronic device that can be used as a server or client of an embodiment of the present invention will now be described, which is an example of a hardware device that can be applied to various aspects of the present invention. The electronic device is intended to represent various forms of digital electronic computer devices, such as laptop computers, desktop computers, workbenches, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present invention described and / or required herein.

[0093] like Figure 7 As shown, the electronic device includes a computing unit 701, which can perform various appropriate actions and processes according to a computer program stored in a read-only memory (ROM) 702 or a computer program loaded from a storage unit 708 to a random access memory (RAM) 703. In the RAM 703, various programs and data required for the operation of the electronic device can also be stored. The computing unit 701, the ROM 702, and the RAM 703 are connected to each other via a bus 704. An input / output (I / O) interface 705 is also connected to the bus 704.

[0094] Multiple components in the electronic device are connected to the I / O interface 705, including: an input unit 706, an output unit 707, a storage unit 708, and a communication unit 709. The input unit 706 can be any type of device that can input information to the electronic device, and the input unit 706 can receive input digital or character information, and generate key signal input related to user settings and / or function control of the electronic device. The output unit 707 can be any type of device that can present information, and can include but is not limited to a display, a speaker, a video / audio output terminal, a vibrator, and / or a printer. The storage unit 708 can include but is not limited to a disk, an optical disk. The communication unit 709 allows the electronic device to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks, and can include but is not limited to a modem, a network card, an infrared communication device, and / or a wireless communication transceiver, such as a Bluetooth device, a WiFi device, a WiMax device, a cellular communication device, and / or the like.

[0095] The computing unit 701 may be a variety of general and / or special processing components with processing and computing capabilities. Some examples of the computing unit 701 include, but are not limited to, a CPU, a graphics processing unit (GPU), various special artificial intelligence (AI) computing units, various computing units running machine learning model algorithms, digital signal processors (DSPs), and any appropriate processors, controllers, microcontrollers, etc. The computing unit 701 performs the various methods and processes described above. For example, in some embodiments, the method embodiments of the present invention may be implemented as a computer program, which is tangibly contained in a machine-readable medium, such as a storage unit 708. In some embodiments, part or all of the computer program may be loaded and / or installed on an electronic device via a ROM 702 and / or a communication unit 709. In some embodiments, the computing unit 701 may be configured to perform the above-described method in any other appropriate manner (e.g., by means of firmware).

[0096] The computer programs for implementing the methods of the embodiments of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor or controller of a general-purpose computer, a special-purpose computer, or other programmable data processing device, so that when the computer programs are executed by the processor or controller, the functions / operations specified in the flow chart and / or block diagram are implemented. The computer programs may be executed entirely on the machine, partially on the machine, partially on the machine as a stand-alone software package and partially on a remote machine, or entirely on a remote machine or server.

[0097] In the context of an embodiment of the present invention, a machine-readable medium may be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, device, or apparatus. A machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. A machine-readable signal medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, or infrared systems, devices, or devices, or any suitable combination of the foregoing. More specific examples of machine-readable storage media may include electrical connections based on one or more lines, portable computer disks, hard disks, random access memories (RAM), read-only memories (ROM), erasable programmable read-only memories (EPROM or flash memory), optical fibers, portable compact disk read-only memories (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.

[0098] It should be noted that the term "including" and its variations used in the embodiments of the present invention are open inclusions, that is, "including but not limited to". The term "based on" means "based at least in part on". The term "one embodiment" means "at least one embodiment"; the term "another embodiment" means "at least one other embodiment"; the term "some embodiments" means "at least some embodiments". The modifications of "one" and "multiple" mentioned in the embodiments of the present invention are illustrative rather than restrictive. Those skilled in the art should understand that unless the context clearly indicates otherwise, it should be understood as "one or more".

[0099] The information and data involved in the embodiments of the present invention (including but not limited to data used for analysis, data stored, data displayed, etc.) are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with relevant laws, regulations and standards of relevant countries and regions, and corresponding operation entrances are provided for users to choose to authorize or refuse.

[0100] The various steps described in the method implementation methods provided in the embodiments of the present invention may be performed in different orders and / or in parallel. In addition, the method implementation methods may include additional steps and / or omit the steps shown. The scope of protection of the present invention is not limited in this respect.

[0101] The term "embodiment" in this specification refers to specific features, structures or characteristics described in conjunction with the embodiment that can be included in at least one embodiment of the present invention. The appearance of this phrase in various places in the specification does not necessarily mean the same embodiment, nor does it mean that it is mutually exclusive with other embodiments and is independent or optional. The various embodiments in this specification are described in a related manner, and the same or similar parts between the various embodiments refer to each other. In particular, for the device, equipment, and system embodiments, since they are basically similar to the method embodiments, the description is relatively simple, and the relevant parts refer to the partial description of the method embodiment.

[0102] The above-mentioned embodiments only express several implementation methods of the present invention, and the description thereof is relatively specific and detailed, but it cannot be understood as limiting the scope of protection. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present invention, and these all belong to the scope of protection of the present invention. Therefore, the scope of protection of the present invention shall be subject to the attached claims.

Claims

1. A method for screening mutant proteins, characterized in that: Includes steps: Simulating single mutations at multiple amino acid sites in the protein sequence of the target protein to obtain multiple simulated mutant proteins, and performing adaptability prediction on the simulated single mutant sequences corresponding to the multiple simulated mutant proteins based on the target protein language model to obtain the adaptability evaluation value F of each of the simulated single mutant sequences; wherein any of the simulated single mutant sequences includes a single mutant protein sequence at the corresponding amino acid site; Determine the simulated single mutant structures corresponding to the multiple simulated mutant proteins respectively, calculate the folding energy change values ​​of the multiple simulated single mutant structures before and after the protein mutation based on the protein folding energy calculation tool, and determine the structural stability value S of each simulated single mutant structure based on the folding energy change value; The adaptability evaluation value F and the structural stability value S are respectively normalized, and the normalized results are respectively sorted by single index and comprehensive index; The plurality of simulated mutant proteins are screened according to the target screening quantity, the single index ranking results and the comprehensive index ranking results to obtain the target mutant protein; It also includes the steps of building the target protein language model and tuning parameters: Obtaining a basic protein language model, replacing the position encoding layer of the basic protein language model with a learnable embedding code, and constructing a fully connected neural network layer in the basic protein language model to obtain the target protein language model; wherein the learnable embedding code is used to capture distance information in the amino acid sequence; and the fully connected neural network layer is used to perform weighted calculation on the type and corresponding site of each amino acid; The target protein language model is subjected to unsupervised training to achieve model parameter tuning processing for the target protein model.

2. The screening method according to claim 1, characterized in that The steps of normalizing the adaptability evaluation value F and the structural stability value S respectively, and performing single index sorting and comprehensive index sorting on the normalized processing results respectively include: Based on the minimum-maximum normalization method, the adaptability evaluation value F and the structural stability value S are respectively normalized to obtain a first adaptability evaluation normalized value F' and a first structural stability normalized value S'; The first adaptability evaluation normalized value F' and the first structural stability normalized value S' are sorted respectively to obtain a single index sorting result including a first adaptability sorting value RF and a first structural stability sorting value RS; The ranking average values ​​of the first adaptability ranking values ​​RF and the first structural stability ranking values ​​RS corresponding to each of the simulated mutant proteins are calculated, and the ranking average values ​​of the multiple simulated mutant proteins are ranked to obtain a first comprehensive index ranking result R.

3. The screening method according to claim 2, characterized in that Also includes the steps: Based on the Z-Score standardization method, the adaptability evaluation value F and the structural stability value S are respectively normalized to obtain a second adaptability evaluation normalized value F'' and a second structural stability normalized value S''; According to the second adaptability evaluation normalized value F'', the second structural stability normalized value S'', the adaptability index weight coefficient, and the structural stability index weight coefficient, the comprehensive index value of each simulated mutant protein is calculated; The comprehensive indicator values ​​are sorted to obtain a second comprehensive indicator sorting result K.

4. The screening method according to claim 2, characterized in that The number of the protein folding energy calculation tools is N, and the number of structural stability values ​​S calculated by the simulated mutant proteins based on the protein folding energy calculation tools is N; The step of normalizing the structural stability values ​​S corresponding to the plurality of simulated mutant proteins comprises: The N groups of structural stability values ​​Sn calculated by N protein folding energy calculation tools are normalized, n∈[1,N]; The N structural stability normalized values ​​Sn' corresponding to any simulated mutant protein are averaged to obtain the structural stability normalized processing result corresponding to the simulated mutant protein.

5. The screening method according to claim 1, characterized in that The target screening number includes a single index screening number and a comprehensive index screening number; the step of screening the multiple simulated mutant proteins according to the target screening number, the single index ranking result and the comprehensive index ranking result to obtain the target mutant protein includes: Determine the first target mutant protein according to the single index screening quantity, the first adaptability ranking value RF, and the first structural stability ranking value RS; After the first target mutant protein is eliminated from the comprehensive index ranking result, the second target mutant protein is determined according to the comprehensive index screening quantity and the comprehensive index ranking result, and the set of the first target mutant protein and the second target mutant protein is the target mutant protein; wherein the comprehensive index ranking result includes the first comprehensive index ranking result R and / or the second comprehensive index ranking result K.

6. The screening method according to claim 5, characterized in that Before the step of determining the target mutant protein, the following steps are also included: In the comprehensive index ranking results, simulated mutant proteins with adaptability evaluation values ​​F less than 0 and structural stability values ​​S greater than 0 are eliminated.

7. A mutant protein screening device, characterized in that: include: A fitness evaluation value calculation module is used to simulate single mutations at multiple amino acid sites in the protein sequence of the target protein to obtain multiple simulated mutant proteins, and to perform fitness prediction on the simulated single mutant sequences corresponding to the multiple simulated mutant proteins based on the target protein language model to obtain the fitness evaluation value F of each of the simulated single mutant sequences; wherein any of the simulated single mutant sequences includes a single mutant protein sequence at the corresponding amino acid site; A structural stability value calculation module, used to determine the simulated single mutant structures corresponding to the multiple simulated mutant proteins, respectively calculate the folding energy change values ​​of the multiple simulated single mutant structures before and after the protein mutation based on the protein folding energy calculation tool, and determine the structural stability value S of each simulated single mutant structure based on the folding energy change value; A data processing module, used to normalize the adaptability evaluation value F and the structural stability value S, and to sort the normalized results by single index and comprehensive index; A screening module, used to screen the multiple simulated mutant proteins according to the target screening quantity, the single index ranking results and the comprehensive index ranking results to obtain the target mutant protein; The steps of building the target protein language model and tuning parameters include: Obtaining a basic protein language model, replacing the position encoding layer of the basic protein language model with a learnable embedding code, and constructing a fully connected neural network layer in the basic protein language model to obtain the target protein language model; wherein the learnable embedding code is used to capture distance information in the amino acid sequence; and the fully connected neural network layer is used to perform weighted calculation on the type and corresponding site of each amino acid; The target protein language model is subjected to unsupervised training to achieve model parameter tuning processing for the target protein model.

8. An electronic device, comprising: A processor and a memory storing a program, wherein the program comprises instructions, which, when executed by the processor, cause the processor to perform the screening method according to any one of claims 1 to 6.

9. A non-transitory machine-readable medium storing computer instructions, characterized in that: The computer instructions are used to cause the computer to execute the screening method according to any one of claims 1-6.

Images