Mutation screening method of cellobiose epimerase and related equipment

Abstract

The invention relates to the technical field of bioinformatics, in particular to a mutation screening method of cellobiose epimerase and related equipment. According to the method provided by the embodiment of the invention, a protein diffusion model is adopted to reconstruct the key catalytic region to obtain a regenerated mutant protein skeleton; performing side chain optimization on the mutant protein skeleton by using a deep learning neural network model to obtain a predicted amino acid sequence of the mutant protein skeleton; obtaining a three-dimensional structure of a cellobiose epimerase mutant-substrate compound according to the predicted amino acid sequence and a molecular structure of a substrate, and screening the three-dimensional structure of the cellobiose epimerase mutant-substrate compound; through the mode, the mutation screening efficiency of the key catalytic region can be improved, the mutant capable of improving the conversion efficiency of lactulose can be rapidly screened, and the screening efficiency of the cellobiose epimerase mutant with the improved conversion efficiency of lactulose is improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of bioinformatics, and in particular to a mutant screening method of cellobiose epimerase and related equipment. BACKGROUND

[0002] Lactulose is a non-digestible disaccharide, and its finished product is a yellow and clear liquid. The sweetness of lactulose is equivalent to that of lactose, but less than that of sucrose, about 48% to 60% of sucrose. Lactulose has a cool and mellow taste, low viscosity, low heat, and high safety and stability. In addition, lactulose can increase the activity of bifidobacterium and is a good bifidobacterium promoting factor. Therefore, lactulose has been widely used in the medical industry, food and animal feed fields. Cellobiose epimerase is an enzyme that exhibits lactose epimerization activity, which can convert lactose into lactulose.

[0003] In the process of converting lactose into lactulose by cellobiose epimerase, byproduct epilactose is generated, which is not conducive to improving the conversion efficiency of lactulose. In addition, the content of epilactose in lactulose solution is strictly limited in pharmacopoeias of various countries, so it is necessary to reduce the content of epilactose in the reaction of synthesizing lactulose. At present, by performing saturated mutation screening on each key site in cellobiose epimerase, a mutant of cellobiose epimerase with improved lactulose conversion efficiency is obtained, which is not conducive to improving the screening efficiency of the mutant of cellobiose epimerase with improved lactulose conversion efficiency. SUMMARY

[0004] In view of the above problems, the embodiments of the present application provide a mutant screening method of cellobiose epimerase and related equipment to solve the technical problem of the above-noted not conducive to improving the screening efficiency of the mutant of cellobiose epimerase with improved lactulose conversion efficiency.

[0005] In a first aspect, the embodiments of the present application provide a mutant screening method of cellobiose epimerase, comprising: obtaining a three-dimensional structure of a cellobiose epimerase-substrate complex according to an amino acid sequence of the cellobiose epimerase and a molecular structure of the substrate; obtaining a key catalytic region according to the three-dimensional structure of the cellobiose epimerase-substrate complex; reconstructing the key catalytic region by using a protein diffusion model to obtain a regenerated mutant protein skeleton; optimizing a side chain of the mutant protein skeleton by using a deep learning neural network model to obtain a predicted amino acid sequence of the mutant protein skeleton; According to the predicted amino acid sequence and the molecular structure of the substrate, a cellobiose epimerase mutant-substrate complex three-dimensional structure is obtained, and the cellobiose epimerase mutant-substrate complex three-dimensional structure is screened.

[0006] In a second aspect, an embodiment of the present application provides a mutation screening device for cellobiose epimerase, comprising: A complex construction module is configured to obtain a cellobiose epimerase-substrate complex three-dimensional structure according to an amino acid sequence of the cellobiose epimerase and a molecular structure of the substrate. An extraction module is configured to obtain a key catalytic region according to the cellobiose epimerase-substrate complex three-dimensional structure. A diffusion module is configured to reconstruct the key catalytic region by using a protein diffusion model to obtain a regenerated mutant protein skeleton. A sequence prediction module is configured to perform side chain optimization on the mutant protein skeleton by using a deep learning neural network model to obtain a predicted amino acid sequence of the mutant protein skeleton. A mutant screening module is configured to obtain a cellobiose epimerase mutant-substrate complex three-dimensional structure according to the predicted amino acid sequence and the molecular structure of the substrate, and screen the cellobiose epimerase mutant-substrate complex three-dimensional structure.

[0007] In a third aspect, an embodiment of the present application provides an electronic device, comprising a processor and a memory coupled to the processor, wherein the memory stores program instructions executable by the processor; and the processor executes the program instructions stored in the memory to implement the mutation screening method for cellobiose epimerase.

[0008] In a fourth aspect, an embodiment of the present application provides a computer readable storage medium, wherein the computer readable storage medium stores program instructions, and the program instructions are executed by a processor to implement the mutation screening method for cellobiose epimerase.

[0009] The method for screening mutations of cellobiose epimerase provided in the embodiments of the present application, the key catalytic region is reconstructed by using a protein diffusion model to obtain a regenerated mutant protein skeleton; the side chain of the mutant protein skeleton is optimized by using a deep learning neural network model to obtain a predicted amino acid sequence of the mutant protein skeleton; a three-dimensional structure of a cellobiose epimerase mutant-substrate complex is obtained according to the predicted amino acid sequence and a molecular structure of a substrate, and the three-dimensional structure of the cellobiose epimerase mutant-substrate complex is screened. In this way, the efficiency of mutation screening of the key catalytic region can be improved, so that a mutant capable of improving the conversion efficiency of lactulose can be quickly screened, and the screening efficiency of the cellobiose epimerase mutant with improved lactulose conversion efficiency is improved.

[0010] These aspects or other aspects of the present application will be more apparent in the following description of the embodiments. BRIEF DESCRIPTION OF DRAWINGS

[0011] Figure 1 A flowchart of the method for screening mutations of cellobiose epimerase provided in the embodiments of the present application is shown.

[0012] Figure 2 A schematic diagram of the three-dimensional structure of the complex in the embodiments of the present application is shown.

[0013] Figure 3 A comparison diagram of the conversion efficiency of the obtained mutant on lactose in the embodiments of the present application is shown.

[0014] Figure 4 A structural schematic diagram of the device for screening mutations of cellobiose epimerase provided in the embodiments of the present application is shown.

[0015] Figure 5 A structural schematic diagram of the electronic device provided in the embodiments of the present application is shown.

[0016] Figure 6 A structural schematic diagram of the storage medium provided in the embodiments of the present application is shown. DETAILED DESCRIPTION

[0017] The embodiments of the present application are described in detail below, and examples of the embodiments are shown in the drawings, wherein the same or similar reference numerals represent the same or similar elements or elements having the same or similar functions throughout. The embodiments described below are exemplary and are only used to explain the present application, and cannot be understood as a limitation of the present application.

[0018] In the following, the technical solutions in the embodiments of the present application will be described clearly and completely in conjunction with the drawings of the embodiments of the present application, so that those skilled in the art can better understand the solutions of the present application. Obviously, the described embodiments are only some of the embodiments of the present application, but not all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative work fall within the scope of protection of the present application.

[0019] It should be noted that in the embodiments of the present application, in this document, the terms such as first and second are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply that there is any such actual relationship or order between these entities or operations.

[0020] Moreover, the terms "include", "contain" or any other variants thereof are intended to cover non-exclusive inclusion, so that the process, method, article or equipment including a series of elements not only includes those elements, but also includes other elements not explicitly listed or inherent to such process, method, article or equipment. Without more limitations, the element defined by the sentence "includes a" does not exclude the presence of another identical element in the process, method, article or equipment including the element.

[0021] In the description of the embodiments of the present application, the words "example" or "for example" are used to represent example, illustration or description. Any embodiment or design scheme described as "example" or "for example" in the embodiments of the present application is not interpreted as more preferred or having more advantages than another embodiment or design scheme. The use of the words "example" or "for example" is intended to present the relative concept in a clear manner.

[0022] In addition, "multiple" in the embodiments of the present application means two or more, and therefore "multiple" in the embodiments of the present application can also be understood as "at least two". "At least one" can be understood as one or more, for example, as one, two or more. For example, including at least one means including one, two or more, and does not limit which ones are included, for example, including at least one of A, B and C, which can include A, B, C, A and B, A and C, B and C, or A and B and C.

[0023] It should be noted that in the embodiments of the present application, the association relationship of the associated objects described by "and / or" represents that there can be three relationships, for example, A and / or B can represent the existence of A alone, the existence of A and B together, and the existence of B alone. In addition, the character " / ", if not specially specified, generally represents a "or" relationship between the associated objects before and after it.

[0024] It should be noted that the "connection" in the embodiments of the present application can be understood as an electrical connection, and the connection between two electrical elements can be direct or indirect connection between the two electrical elements. For example, A and B are connected, which can be direct connection between A and B, or indirect connection between A and B through one or more other electrical elements.

[0025] An embodiment of the present application provides a mutation screening method of cellobiose epimerase, please refer to Figure 1 The mutation screening method of cellobiose epimerase includes the following steps S11-S15: Step S11: Obtain the three-dimensional structure of the cellobiose epimerase-substrate complex according to the amino acid sequence of the cellobiose epimerase and the molecular structure of the substrate.

[0026] Wherein, the substrate can be lactose, and the three-dimensional structure of the cellobiose epimerase-substrate complex can show the active center and catalytic residues of the enzyme, the active pocket of the enzyme, the binding site of the substrate, the domain of the enzyme, the loop region of the enzyme, etc.

[0027] Step S12: Obtain the key catalytic region according to the three-dimensional structure of the cellobiose epimerase-substrate complex.

[0028] Wherein, the key catalytic region can be at least one loop region, for example, the key catalytic region can be a key active pocket loop region, which is a loop region in the cellobiose epimerase that directly participates in substrate binding and catalytic reaction. Illustratively, the key active pocket loop region is the 148th-181st in the amino acid sequence of the cellobiose epimerase.

[0029] Step S13: Reconstruct the key catalytic region using a protein diffusion model to obtain a newly generated mutant protein skeleton.

[0030] Wherein, the protein diffusion model can gradually introduce noise to the key catalytic region to break the original structure characteristics, and then regenerate the three-dimensional structure of the key catalytic region through a denoising process to generate a new mutant protein skeleton. The amino acid residues in the key catalytic region of the mutant protein skeleton are mutated, and the amino acid residues in other regions are unchanged.

[0031] Step S14: Use a deep learning neural network model to optimize the side chain of the mutant protein skeleton to obtain a predicted amino acid sequence of the mutant protein skeleton.

[0032] The deep learning neural network model learns the relationship between the three-dimensional structure of the protein and the amino acid sequence, such as the interaction and spatial constraint between amino acids, which can map the three-dimensional mutant protein skeleton to the corresponding amino acid sequence.

[0033] Step S15: Obtain the cellobiose mutarotase mutant-substrate complex three-dimensional structure according to the predicted amino acid sequence and the molecular structure of the substrate, and screen the cellobiose mutarotase mutant-substrate complex three-dimensional structure.

[0034] The cellobiose mutarotase can undergo mutarotation and isomerization during the catalysis of the substrate lactose. Specifically, during mutarotation, the galactose in lactose is converted to mannose by changing the chiral carbon configuration at the C-2 position of the galactose, thereby generating lactulose. This mutarotation reaction may involve the opening and closing of the sugar ring, and key residues participate in proton transfer to facilitate configuration inversion. In addition, the mutarotation activity of the cellobiose mutarotase can also cause the chiral carbon at the C-2 position of lactulose to undergo configuration inversion, thereby generating the byproduct epilactose. During isomerization, the glucose in lactose is isomerized to fructose, thereby generating lactulose. This isomerization reaction may involve the isomerization between aldose and ketose.

[0035] The mutant that is beneficial to the isomerization reaction direction can be obtained by screening the cellobiose mutarotase mutant-substrate complex three-dimensional structure, so as to improve the isomerization activity of the mutant, thereby improving the conversion efficiency of lactulose, while avoiding the increase in the content of the byproduct epilactose caused by the increase in mutarotation activity.

[0036] Exemplarily, the cellobiose mutarotase mutant-substrate complex three-dimensional structure can be as shown in Figure 2 .

[0037] In this embodiment, the efficiency of screening mutations in the key catalytic region can be improved to quickly screen the mutant that can improve the conversion efficiency of lactulose, thereby improving the screening efficiency of the cellobiose mutarotase mutant with improved lactulose conversion efficiency.

[0038] As an implementation manner, step S13 can specifically include the following steps: Step S21: Input the three-dimensional structure data of the cellobiose mutarotase and the six-dimensional data of the key catalytic region into the protein diffusion model.

[0039] The amino acid residues in the key catalytic region can be target amino acid residues for diffusion, and the target amino acid residues can be represented in six dimensions, i.e., the six-dimensional data of the target amino acid residues can include three translational degrees of freedom (x, y, and z coordinates) and three rotational degrees of freedom (usually represented by Euler angles a, b, and g) of the residues.

[0040] Step S22: The protein diffusion model diffuses the key catalytic region to generate a plurality of diffusion skeletons, wherein the sequence length of the key catalytic region in the diffusion skeleton is unchanged, and the amino acid residues in other regions are unchanged.

[0041] The protein diffusion model is, for example, RFdiffusion, and the key catalytic region can be, for example, a loop region. By diffusing the target amino acid residues in the loop region while keeping the main chain structure unchanged, a plurality of diffusion skeletons are obtained. In the diffusion skeletons, only the conformations of the target amino acid residues are changed, and the amino acid residues in other regions are unchanged.

[0042] Step S23: Calculate the root mean square deviation value of the diffusion skeleton according to the three-dimensional structure of the diffusion skeleton and the three-dimensional structure of the cellobiose epimerase, and output the diffusion skeleton with a root mean square deviation value less than a first preset threshold as a mutant protein skeleton.

[0043] The generated diffusion skeletons are subjected to main chain root mean square deviation (RMSD) calculation, and structures with a main chain root mean square deviation (RMSD) less than a first preset threshold are selected to ensure the rationality of the structure. Exemplarily, the first preset threshold can be 2.0 Å.

[0044] As an implementation, step S14 can specifically include the following steps: Step S31: Input the three-dimensional data of the mutant protein skeleton into a deep learning neural network model, and the deep learning neural network model predicts the amino acid sequence of the mutant protein skeleton according to the three-dimensional data of the mutant protein skeleton to generate a corresponding predicted amino acid sequence.

[0045] The deep learning neural network model can be, for example, ProteinMPNN. Based on ProteinMPNN, the position of each target amino acid residue in the key catalytic region of the mutant protein skeleton is optimized, and the most matching amino acid sequence is dynamically predicted and generated.

[0046] Step S32: According to the predicted amino acid sequence and the amino acid sequence of the cellobiose epimerase, calculate the sequence recovery degree of the predicted amino acid sequence, and output the predicted amino acid sequence with a sequence recovery degree greater than a second preset threshold.

[0047] The sequence recovery degree is used to represent the accuracy of recovering the three-dimensional structure of the mutant protein skeleton to the predicted amino acid sequence, which can be obtained by comparing the similarity between the recovered sequence (predicted amino acid sequence) and the natural sequence (amino acid sequence of cellobiose mutarotase). For example, the second preset threshold can be 0.6, 0.8, 0.85 or 0.9.

[0048] As an implementation, the screening of the three-dimensional structure of the cellobiose mutarotase mutant-substrate complex in step S15 specifically includes the following steps: Step S41: performing molecular dynamics simulation according to the three-dimensional structure of the cellobiose mutarotase mutant-substrate complex to obtain state change data of the mutant-substrate complex during the molecular dynamics simulation.

[0049] The tool for molecular dynamics simulation is, for example, GROMACS (GROningen MAchine for Chemical Simulations, GROMACS). GROMACS supports various simulation algorithms such as molecular dynamics, energy minimization, conformational search and free energy calculation, and also provides functions such as molecular construction, force field parameterization, simulation setting, post-processing and analysis.

[0050] Specifically, first, the three-dimensional structure of the mutant-substrate complex is established and energy minimization is performed to obtain the initial structure of the mutant-substrate complex.

[0051] The initial structure of the mutant-substrate complex is obtained based on the binding site of the catalytic residue of the mutant and the substrate; and the initial structure of the mutant-substrate complex is subjected to energy minimization to eliminate unreasonable conformations in the initial structure.

[0052] Then, the initial structure of the mutant-substrate complex is subjected to equilibrium simulation to obtain the mutant-substrate complex in the equilibrium state. The molecular dynamics simulation parameters are set, including temperature, pressure, solvent environment, etc., to ensure that the experimental conditions match the physiological environment, and the initial structure of the mutant-substrate complex is subjected to equilibrium simulation, and the parameters are gradually adjusted to make the system reach a thermodynamic equilibrium state. After energy minimization and equilibrium simulation, the system reaches a stable state, reducing the energy deviation of the initial structure of the initial structure of the mutant-substrate complex.

[0053] Finally, the mutant-substrate complex in the equilibrium state is subjected to production phase simulation for structure stability and energy change analysis, and the results of the structure stability and energy change analysis are used as the state change data during the molecular dynamics simulation.

[0054] In the production simulation stage, the mutant-substrate interaction trajectory and conformational change are recorded, and the structural stability and energy change are analyzed according to the simulation trajectory and conformational change, to obtain state change data of the production simulation. The state change data can include a plurality of target indicators, which can include but are not limited to binding energy, number of hydrogen bonds, root mean square deviation, or root mean square fluctuation. Exemplarily, the production simulation time is less than or equal to 100 nanoseconds, for example, the production simulation process can last for 10 nanoseconds to 100 nanoseconds.

[0055] Step S42: First screening of the cellobiose epimerase mutant-substrate complex three-dimensional structure according to the state change data.

[0056] The state change data can include, for example, atomic coordinate changes over time, structural changes of the complex (secondary structure changes, conformational changes, etc.), kinetic parameters (atomic speed, kinetic energy, potential energy, and temperature, etc.), viscosity, and diffusion coefficient, etc. In some embodiments, the state change data can include the binding energy of the mutant and the substrate, the number of hydrogen bonds, the root mean square deviation, or the root mean square fluctuation. Exemplarily, the first screening can be performed according to the binding energy of the mutant and the substrate in the state change data. When the binding energy of the mutant and the substrate is greater than the binding energy of the wild-type cellobiose epimerase and the substrate, the corresponding cellobiose epimerase mutant-substrate complex three-dimensional structure is retained.

[0057] Step S43: Substrate orientation analysis of the first screened cellobiose epimerase mutant-substrate complex three-dimensional structure, and obtaining a cellobiose epimerase mutant-substrate complex three-dimensional structure that is beneficial to the isomerization reaction according to the analysis result.

[0058] The substrate orientation represents the positional relationship between the mutant and the substrate. The substrate orientation analysis can be performed on each first screened cellobiose epimerase mutant-substrate complex three-dimensional structure for the isomerization reaction. For example, at least one of the following substrate orientation analysis indicators can be analyzed: the distance between the reaction site of the isomerization reaction in the substrate and the key residue of the isomerization reaction, the dihedral angle between the substrate and the main chain, the included angle between the substrate and the key residue of the isomerization reaction, the relative position between the substrate and the key residue of the isomerization reaction, the orientation vector between the substrate and the key residue of the isomerization reaction, the repulsion / attraction interaction between the substrate and the key residue of the isomerization reaction, or the binding free energy between the substrate and the key residue of the isomerization reaction. The cellobiose epimerase mutant-substrate complex three-dimensional structure screened according to the analysis result is beneficial to the isomerization reaction.

[0059] In some embodiments, step S43 specifically includes the following steps: Step S51: performing substrate orientation analysis on the first screened cellobiose epimerase mutant-substrate complex three-dimensional structure by using a molecular dynamics visualization tool to obtain an analysis result, the analysis result at least including a reaction site distance between a key residue of the isomerization reaction in the mutant and a reaction site of the isomerization reaction in the substrate and / or a binding free energy of the substrate and the key residue of the isomerization reaction.

[0060] Step S52: obtaining the cellobiose epimerase mutant-substrate complex three-dimensional structure with the reaction site distance less than a third preset threshold value, or the binding free energy less than a fourth preset threshold value, or both the reaction site distance less than the third preset threshold value and the binding free energy less than the fourth preset threshold value.

[0061] The molecular dynamics visualization tool can be VMD (Visual Molecular Dynamics), PyMOL or GROMACS. The reaction site distance between the key residue of the isomerization reaction in the mutant and the reaction site of the isomerization reaction in the substrate and the binding free energy of the substrate and the key residue of the isomerization reaction are respectively related to the isomerization activity.

[0062] The third preset threshold value and the fourth preset threshold value can be determined according to empirical values respectively. Alternatively, the reaction site distances can be arranged in ascending order, and the reaction site distance at the mth position in the arrangement is taken as the third preset threshold value; the binding free energies can be arranged in ascending order, and the binding free energy at the nth position in the arrangement is taken as the fourth preset threshold value, m and n are natural numbers greater than 1, and m and n can be the same or different.

[0063] In some embodiments, the step S15 further includes the following steps: Step S161: calculating at least one enzyme kinetic parameter of the mutant according to the predicted amino acid sequence and the molecular structure of the substrate based on an enzyme kinetic parameter prediction tool.

[0064] Step S162: performing second screening on the cellobiose epimerase mutant-substrate complex three-dimensional structure according to the at least one enzyme kinetic parameter.

[0065] The enzyme kinetic parameter prediction tool can be, for example, UniKP, and the enzyme kinetic parameters can include but are not limited to kcat (turnover number), km (Michaelis constant) or kcat / km (catalytic efficiency constant). kcat (turnover number), km (Michaelis constant) or kcat / km (catalytic efficiency constant) can be selected. The higher the kcat value, the higher the catalytic efficiency of the enzyme; the lower the km value, the higher the affinity of the enzyme to the substrate; the higher the kcat / km value, the higher the catalytic efficiency of the enzyme to the substrate.

[0066] As an implementation, step S11 specifically includes the following steps: Step S61: input the amino acid sequence of the cellobiose epimerase and the molecular structure of the substrate into the pre-trained protein structure prediction model, and output a first candidate enzyme-substrate complex three-dimensional structure.

[0067] The amino acid sequence of the enzyme can be provided in FASTA format, and the molecular structure of the substrate can be provided in the form of a SMILES string or a molecular graph. The protein structure prediction model is used to predict and generate the three-dimensional structure of the cellobiose epimerase-substrate complex, and the three-dimensional structure of the cellobiose epimerase-substrate complex with a plddt (Predicted Local Distance Difference Test) score greater than a score threshold can be selected as the first candidate enzyme-substrate complex three-dimensional structure. Illustratively, the protein structure prediction model can employ an AlphaFold 3 model or a Protenix deep learning model.

[0068] Step S62: extract the three-dimensional structure of the cellobiose epimerase and the three-dimensional structure of the substrate from the first candidate enzyme-substrate complex three-dimensional structure, respectively, and use a molecular docking tool to simulate the binding of the three-dimensional structure of the cellobiose epimerase and the three-dimensional structure of the substrate, to screen the first candidate enzyme-substrate complex three-dimensional structure, to obtain a second candidate enzyme-substrate complex three-dimensional structure.

[0069] The molecular docking tool is used to simulate the binding process of the three-dimensional structure of the enzyme and the three-dimensional structure of the substrate, and the binding data is calculated according to the binding process. The binding data can include the binding energy of the enzyme and the substrate and / or the reaction site distance between the key catalytic residues of the enzyme and the reaction sites of the substrate. The molecular docking tool can be, for example, AutoDock, Glide, or other molecular docking software. Illustratively, the reaction site distance can include the reaction site distance of the epimerization reaction and / or the reaction site distance of the isomerization reaction. Illustratively, the distance between the active site of the enzyme and the binding site of the substrate in the three-dimensional structure of the complex can be directly measured based on the three-dimensional structure of the complex. According to the binding data, the first candidate enzyme-substrate complex three-dimensional structure with smaller binding energy and / or smaller reaction site distance is selected as the second candidate enzyme-substrate complex three-dimensional structure; for example, the first candidate enzyme-substrate complex three-dimensional structure with binding energy less than or equal to a preset binding energy threshold and reaction site distance less than or equal to a preset distance threshold is selected as the second candidate enzyme-substrate complex three-dimensional structure.

[0070] Step S63: performing molecular dynamics simulation on the second candidate enzyme-substrate complex three-dimensional structure to screen the second candidate enzyme-substrate complex three-dimensional structure, to obtain a cellobiose epimerase-substrate complex three-dimensional structure.

[0071] The tool for molecular dynamics simulation is, for example, GROMACS (GROningen MAchine for Chemical Simulations). GROMACS supports various simulation algorithms such as molecular dynamics, energy minimization, conformational search, and free energy calculation, and also provides functions such as molecular construction, force field parameterization, simulation setting, post-processing, and analysis.

[0072] The second candidate enzyme-substrate complex three-dimensional structure can be screened according to the state change data. The state change data may, for example, include changes in atomic coordinates over time, structural changes of the complex (changes in secondary structure, changes in conformation, etc.), kinetic parameters (speed, kinetic energy, potential energy, and temperature of atoms, etc.), viscosity, and diffusion coefficient, etc. In some embodiments, the state change data can include binding energy of the enzyme and the substrate, number of hydrogen bonds, root mean square deviation, or root mean square fluctuation. Exemplarily, screening can be performed according to the binding energy of the enzyme and the substrate in the state change data, and when the binding energy of the enzyme and the substrate is greater than the binding energy of the wild-type cellobiose epimerase and the substrate, the corresponding second candidate enzyme-substrate complex three-dimensional structure is retained.

[0073] Specifically, first, a three-dimensional structure of the enzyme-substrate complex is established and energy minimization is performed to obtain an initial structure of the enzyme-substrate complex.

[0074] The initial structure of the enzyme-substrate complex is obtained based on the binding of the catalytic residues of the enzyme and the binding site of the substrate, and energy minimization is performed on the initial structure of the enzyme-substrate complex to eliminate unreasonable conformations in the initial structure.

[0075] Then, the initial structure of the enzyme-substrate complex is subjected to equilibrium simulation to obtain an enzyme-substrate complex in an equilibrium state. The molecular dynamics simulation parameters are set, including temperature, pressure, solvent environment, etc., to ensure that the experimental conditions match the physiological environment, and the initial structure of the enzyme-substrate complex is subjected to equilibrium simulation, and the parameters are gradually adjusted to make the system reach a thermodynamic equilibrium state. After energy minimization and equilibrium simulation, the system reaches a stable state, and the energy deviation of the initial structure of the initial structure of the enzyme-substrate complex is reduced.

[0076] Finally, the enzyme-substrate complex in the equilibrium state is simulated in the production phase to analyze the structural stability and energy change, and the results of the structural stability and energy change are used as state change data in the molecular dynamics simulation process.

[0077] In the production simulation phase, the enzyme-substrate interaction trajectory and conformation change are recorded, the structural stability and energy change are analyzed according to the simulation trajectory and conformation change, and the state change data of the production simulation phase is obtained. The state change data can include multiple target indicators, which can include but are not limited to binding energy, number of hydrogen bonds, root mean square deviation, or root mean square fluctuation. Exemplarily, the time of the production simulation phase is less than or equal to 100 nanoseconds, for example, the production simulation process can last for 10 nanoseconds to 100 nanoseconds.

[0078] In some embodiments, in step S15, the cellobiose epimerase mutant-substrate complex three-dimensional structure is obtained according to the predicted amino acid sequence and the molecular structure of the substrate, which can include the following steps: Step S71: input the predicted amino acid sequence and the molecular structure of the substrate into the pre-trained protein structure prediction model, and output the candidate mutant-substrate complex three-dimensional structure.

[0079] The predicted amino acid sequence can be provided in FASTA format; the molecular structure of the substrate can be provided in the form of a SMILES string or a molecular graph. The protein structure prediction model is used to predict and generate the three-dimensional structure of the cellobiose epimerase mutant-substrate complex. The three-dimensional structure of the cellobiose epimerase mutant-substrate complex with a plddt (Predicted Local Distance Difference Test) score greater than a score threshold can be selected as the candidate mutant-substrate complex three-dimensional structure. Exemplarily, the protein structure prediction model can use the AlphaFold 3 model or the Protenix deep learning model.

[0080] Step S72: extract the three-dimensional structure of the cellobiose epimerase mutant and the three-dimensional structure of the substrate from the candidate mutant-substrate complex three-dimensional structure, respectively, and use a molecular docking tool to simulate the binding of the three-dimensional structure of the cellobiose epimerase mutant and the three-dimensional structure of the substrate to screen the candidate mutant-substrate complex three-dimensional structure, and obtain the screened mutant-substrate complex three-dimensional structure.

[0081] The binding process of the three-dimensional structure of the mutant and the three-dimensional structure of the substrate is simulated by using a molecular docking tool, and the binding data is calculated according to the binding process. The binding data can include the binding energy of the mutant and the substrate and / or the reaction site distance between the key catalytic residues of the mutant and the reaction site of the substrate. The molecular docking tool can be, for example, AutoDock, Glide, or other molecular docking software. Illustratively, the reaction site distance described above can include the reaction site distance of the isomerization reaction. Illustratively, the distance between the active site of the mutant and the binding site of the substrate in the three-dimensional structure of the complex can be directly measured based on the three-dimensional structure of the complex. According to the binding data, the candidate mutant-substrate complex three-dimensional structure with smaller binding energy and smaller reaction site distance is selected as the screened mutant-substrate complex three-dimensional structure; for example, the candidate mutant-substrate complex three-dimensional structure with binding energy less than or equal to a preset binding energy threshold and reaction site distance less than or equal to a preset distance threshold is selected as the screened mutant-substrate complex three-dimensional structure.

[0082] The nine cellobiose epimerase mutants screened are constructed in the pET-28a plasmid according to the nucleotide sequence corresponding to the amino acid sequence of the cellobiose epimerase mutant in the prior art CN202411312103.1 to obtain the pET-28a-CsCE plasmid. Then, the pET-28a-CsCE plasmid is transformed into Bacillus subtilis for expression. The obtained mutant is fermented with lactose, and the results are shown in Table 1. Figure 3

[0083] An embodiment of the present application provides a mutant screening device for cellobiose epimerase. Referring to Figure 4 ​As shown, the mutation screening device 20 of the cellobiose epimerase comprises a complex construction module 21, an extraction module 22, a diffusion module 23, a sequence prediction module 24, and a mutant screening module 25. The complex construction module 21 is configured to obtain a three-dimensional structure of a cellobiose epimerase-substrate complex according to an amino acid sequence of the cellobiose epimerase and a molecular structure of the substrate. The extraction module 22 is configured to obtain a key catalytic region according to the three-dimensional structure of the cellobiose epimerase-substrate complex. The diffusion module 23 is configured to reconstruct the key catalytic region by using a protein diffusion model to obtain a regenerated mutant protein skeleton. The sequence prediction module 24 is configured to perform side chain optimization on the mutant protein skeleton by using a deep learning neural network model to obtain a predicted amino acid sequence of the mutant protein skeleton. The mutant screening module 25 is configured to obtain a three-dimensional structure of a cellobiose epimerase mutant-substrate complex according to the predicted amino acid sequence and the molecular structure of the substrate, and to screen the three-dimensional structure of the cellobiose epimerase mutant-substrate complex.

[0084] As an implementation form, the extraction module 22 is further configured to determine a loop region of the cellobiose epimerase according to the three-dimensional structure of the cellobiose epimerase-substrate complex, and to take the loop region as the key catalytic region.

[0085] As an implementation form, the diffusion module 23 is further configured to: input three-dimensional structure data of the cellobiose epimerase and six-dimensional data of the key catalytic region into a protein diffusion model; perform diffusion processing on the key catalytic region by using the protein diffusion model to generate a plurality of diffusion skeletons, wherein the sequence length of the key catalytic region in the diffusion skeleton is unchanged and the amino acid residues of other regions are unchanged; calculate a root mean square deviation value of the diffusion skeleton according to the three-dimensional structure of the diffusion skeleton and the three-dimensional structure of the cellobiose epimerase, and output the diffusion skeleton with a root mean square deviation value less than a first preset threshold as the mutant protein skeleton.

[0086] As an implementation form, the sequence prediction module 24 is further configured to: input three-dimensional data of the mutant protein skeleton into a deep learning neural network model, the deep learning neural network model is configured to predict an amino acid sequence of the mutant protein skeleton according to the three-dimensional data of the mutant protein skeleton to generate a corresponding predicted amino acid sequence; calculate a sequence recovery degree of the predicted amino acid sequence according to the predicted amino acid sequence and the amino acid sequence of the cellobiose epimerase, and output the predicted amino acid sequence with a sequence recovery degree greater than a second preset threshold.

[0087] As an implementation form, the mutant screening module 25 is further configured to: perform a molecular dynamics simulation on the cellobiose epimerase mutant-substrate complex three-dimensional structure to obtain state change data of the mutant-substrate complex during the molecular dynamics simulation; perform a first screening on the cellobiose epimerase mutant-substrate complex three-dimensional structure according to the state change data; and perform a substrate orientation analysis on the first screened cellobiose epimerase mutant-substrate complex three-dimensional structure to obtain a cellobiose epimerase mutant-substrate complex three-dimensional structure that is beneficial to the isomerization reaction according to an analysis result.

[0088] As an implementation form, the mutant screening module 25 is further configured to: perform a substrate orientation analysis on the first screened cellobiose epimerase mutant-substrate complex three-dimensional structure by using a molecular dynamics visualization tool to obtain an analysis result, the analysis result at least including a reaction site distance between a key residue of the isomerization reaction in the mutant and a reaction site of the isomerization reaction in the substrate and / or a binding free energy of the substrate and the key residue of the isomerization reaction.

[0089] As an implementation form, the mutant screening module 25 is further configured to: perform a calculation on at least one enzyme kinetics parameter of the mutant according to the predicted amino acid sequence and the molecular structure of the substrate based on an enzyme kinetics parameter prediction tool; and perform a second screening on the cellobiose epimerase mutant-substrate complex three-dimensional structure according to the at least one enzyme kinetics parameter.

[0090] As an implementation form, the complex construction module 21 is further configured to: input the amino acid sequence of the cellobiose epimerase and the molecular structure of the substrate into a pre-trained protein structure prediction model to output a first candidate enzyme-substrate complex three-dimensional structure; extract the three-dimensional structure of the cellobiose epimerase and the three-dimensional structure of the substrate from the first candidate enzyme-substrate complex three-dimensional structure respectively, and simulate the combination of the three-dimensional structure of the cellobiose epimerase and the three-dimensional structure of the substrate by using a molecular docking tool to screen the first candidate enzyme-substrate complex three-dimensional structure to obtain a second candidate enzyme-substrate complex three-dimensional structure; and perform a molecular dynamics simulation on the second candidate enzyme-substrate complex three-dimensional structure to screen the second candidate enzyme-substrate complex three-dimensional structure to obtain the cellobiose epimerase-substrate complex three-dimensional structure.

[0091] Figure 5 is a structural schematic diagram of an electronic device according to an embodiment of the present application. As shown in Figure 5 the electronic device 30 includes a processor 31 and a memory 32 coupled to the processor 31.

[0092] The memory 32 stores program instructions for implementing the mutation screening method of cellobiose epimerase of any of the above embodiments.

[0093] The processor 31 is configured to execute the program instructions stored in the memory 32 to perform the mutation screening of cellobiose epimerase.

[0094] The processor 31 can also be referred to as a CPU (Central Processing Unit). The processor 31 can be an integrated circuit chip having a processing capability of signals. The processor 31 can also be a general-purpose processor, a DSP (Digital Signal Processor), an ASIC (Application-Specific Integrated Circuit), an FPGA (Field Programmable Gate Array) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components. The general-purpose processor can be a microprocessor or the processor can also be any conventional processor.

[0095] Referring to Figure 6 , Figure 6 FIG. 1 is a structural schematic diagram of a computer readable storage medium according to an embodiment of the present application. The storage medium according to the embodiment of the present application stores program instructions 41 capable of implementing all the above methods. The storage medium can be non-volatile or volatile. The program instructions 41 can be stored in the above storage medium in the form of a software product, including a plurality of instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) or a processor to execute all or part of the steps of the methods described in the various embodiments of the present application. The above storage medium includes a U disk, a mobile hard disk, a ROM (Read-Only Memory), a RAM (Random Access Memory), a magnetic disk or an optical disk, etc. various media capable of storing program codes, or a computer, a server, a mobile phone, a tablet, etc. terminal device.

[0096] In the several embodiments provided in the present application, it should be understood that the disclosed system, device and method can be implemented in other ways. For example, the device embodiments described above are only schematic. The division of the units is only a logical function division. There can be another division manner in actual implementation. For example, a plurality of units or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the coupling or direct coupling or communication connection between the units shown or discussed can be indirect coupling or communication connection through some interfaces, devices or units, and can be electrical, mechanical or other forms.

[0097] Furthermore, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated units described above can be implemented in hardware or as software functional units. The above are merely embodiments of this application and do not limit the patent scope of this application. Any equivalent structural or procedural transformations made based on the description and drawings of this application, or direct or indirect applications in other related technical fields, are similarly included within the patent protection scope of this application.

[0098] The above description is merely an embodiment of this application. It should be noted that those skilled in the art can make improvements without departing from the inventive concept of this application, but these improvements all fall within the protection scope of this application.

Claims

1. A method for screening cellobiose epimerases through mutation, characterized in that, include: The three-dimensional structure of the cellobiose epimerase-substrate complex was obtained based on the amino acid sequence of the cellobiose epimerase and the molecular structure of the substrate. The key catalytic region was obtained based on the three-dimensional structure of the cellobiose epimerase-substrate complex. The key catalytic region was reconstructed using a protein diffusion model to obtain a regenerated mutant protein backbone. The side chain of the mutant protein backbone was optimized using a deep learning neural network model to obtain the predicted amino acid sequence of the mutant protein backbone. The three-dimensional structure of the cellobiose epimerase mutant-substrate complex was obtained based on the predicted amino acid sequence and the molecular structure of the substrate, and the three-dimensional structure of the cellobiose epimerase mutant-substrate complex was screened.

2. The mutation screening method for cellobiose epimerase according to claim 1, characterized in that, The process of obtaining the key catalytic region based on the three-dimensional structure of the cellobiose epimerase-substrate complex includes: The loop region of the cellobiose epimerase was determined based on the three-dimensional structure of the cellobiose epimerase-substrate complex, and the loop region was designated as the key catalytic region.

3. The mutation screening method for cellobiose epimerase according to claim 1, characterized in that, The reconstruction of the key catalytic region using a protein diffusion model to obtain the regenerated mutant protein backbone includes: The three-dimensional structural data of the cellobiose epimerase and the six-dimensional data of the key catalytic region were input into the protein diffusion model. The protein diffusion model performs diffusion processing on the key catalytic region to generate multiple diffusion backbones, wherein the sequence length of the key catalytic region in the diffusion backbone remains unchanged and the amino acid residues in other regions remain unchanged. The root mean square deviation (RMSD) of the diffusion backbone is calculated based on the three-dimensional structure of the diffusion backbone and the three-dimensional structure of the cellobiose epimerase. Diffusion backbones with an RMS deviation less than a first preset threshold are output as the mutant protein backbone.

4. The mutation screening method for cellobiose epimerase according to claim 1, characterized in that, The step of optimizing the side chains of the mutant protein backbone using a deep learning neural network model to obtain the predicted amino acid sequence of the mutant protein backbone includes: The three-dimensional data of the mutant protein backbone is input into a deep learning neural network model. The deep learning neural network model predicts the amino acid sequence of the mutant protein backbone based on the three-dimensional data of the mutant protein backbone and generates the corresponding predicted amino acid sequence. Based on the predicted amino acid sequence and the amino acid sequence of the cellobiose epimerase, the sequence recovery of the predicted amino acid sequence is calculated, and the predicted amino acid sequences with a sequence recovery greater than a second preset threshold are output.

5. The mutation screening method for cellobiose epimerase according to claim 1, characterized in that, The screening of the three-dimensional structure of the cellobiose epimerase mutant-substrate complex includes: Molecular dynamics simulations were performed based on the three-dimensional structure of the cellobiose epimerase mutant-substrate complex to obtain data on the state changes of the mutant-substrate complex during the molecular dynamics simulation process. The three-dimensional structure of the cellobiose epimerase mutant-substrate complex was first screened based on the state change data. Substrate orientation analysis was performed on the three-dimensional structure of the cellobiose epimerase mutant-substrate complex after the first screening. Based on the analysis results, the three-dimensional structure of the cellobiose epimerase mutant-substrate complex that is conducive to the isomerization reaction was obtained.

6. The mutation screening method for cellobiose epimerase according to claim 5, characterized in that, The step of performing substrate orientation analysis on the three-dimensional structure of the cellobiose epimerase mutant-substrate complex after the first screening includes: The three-dimensional structure of the cellobiose epimerase mutant-substrate complex after the first screening was analyzed by a molecular dynamics visualization tool to obtain the analysis results. The analysis results include at least the reaction site distance between the key residues of the isomerization reaction in the mutant and the reaction site of the isomerization reaction in the substrate and / or the binding free energy of the substrate and the key residues of the isomerization reaction. And / or, after screening the three-dimensional structure of the cellobiose epimerase mutant-substrate complex, the method further includes: Based on the enzyme kinetic parameter prediction tool, at least one enzyme kinetic parameter of the mutant is calculated according to the predicted amino acid sequence and the molecular structure of the substrate; The three-dimensional structure of the cellobiose epimerase mutant-substrate complex was second-screened based on at least one enzyme kinetic parameter.

7. The mutation screening method for cellobiose epimerase according to claim 1, characterized in that, The process of obtaining the three-dimensional structure of the cellobiose epimerase-substrate complex based on the amino acid sequence of the cellobiose epimerase and the molecular structure of the substrate includes: The amino acid sequence of cellobiose epimerase and the molecular structure of the substrate are input into a pre-trained protein structure prediction model, and the three-dimensional structure of the first candidate enzyme-substrate complex is output. The three-dimensional structures of cellobiose epimerase and substrate were extracted from the three-dimensional structure of the first candidate enzyme-substrate complex. Molecular docking tools were used to simulate the binding of the three-dimensional structures of cellobiose epimerase and substrate to screen the three-dimensional structures of the first candidate enzyme-substrate complex and obtain the three-dimensional structure of the second candidate enzyme-substrate complex. Molecular dynamics simulations were performed on the three-dimensional structure of the second candidate enzyme-substrate complex to screen for the three-dimensional structure of the second candidate enzyme-substrate complex, thereby obtaining the three-dimensional structure of the cellobiose epimerase-substrate complex.

8. A mutation screening device for cellobiose epimerase, characterized in that, include: The complex construction module is used to obtain the three-dimensional structure of the cellobiose epimerase-substrate complex based on the amino acid sequence of the cellobiose epimerase and the molecular structure of the substrate. The extraction module is used to obtain key catalytic regions based on the three-dimensional structure of the cellobiose epimerase-substrate complex; The diffusion module is used to reconstruct the key catalytic region using a protein diffusion model to obtain a regenerated mutant protein backbone. The sequence prediction module is used to optimize the side chains of the mutant protein backbone using a deep learning neural network model to obtain the predicted amino acid sequence of the mutant protein backbone. The mutant screening module is used to obtain the three-dimensional structure of the cellobiose epimerase mutant-substrate complex based on the predicted amino acid sequence and the molecular structure of the substrate, and to screen the three-dimensional structure of the cellobiose epimerase mutant-substrate complex.

9. An electronic device, characterized in that, The method includes a processor and a memory coupled to the processor, the memory storing program instructions executable by the processor; when the processor executes the program instructions stored in the memory, it implements the mutation screening method for cellobiose epimerase as described in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores program instructions that, when executed by a processor, implement a mutation screening method for cellobiose epimerase as described in any one of claims 1 to 7.

Images