A method for recommending a plastic-degrading enzyme mutation site, an electronic device, and a medium

Abstract

The application discloses a method for recommending a plastic-degrading enzyme mutation site, an electronic device and a medium, and comprises the following steps: S1, obtaining an amino acid sequence of a plastic-degrading enzyme to be predicted and a substrate thereof; predicting an interaction region of the substrate and the plastic-degrading enzyme; setting a threshold distance, taking the substrate molecule or the active site of the plastic-degrading enzyme as a benchmark, and taking the plastic-degrading enzyme amino acid within the threshold distance as a candidate amino acid mutation site; S2, obtaining a spatial structure of the plastic-degrading enzyme to be predicted, taking an amino acid as a node, a connection between the amino acids as an edge, and predicting a prediction probability of i kinds of amino acids corresponding to each candidate amino acid mutation site through a geometric vector perception machine, taking the amino acid with the highest probability as a recommended amino acid of the candidate amino acid mutation site; comparing the prediction results of each candidate amino acid mutation site, and when the prediction results are inconsistent with an original amino acid sequence, taking the candidate amino acid mutation site as a recommended plastic-degrading enzyme mutation site.

Description

Technical Field

[0001] This invention relates to the field of bioinformatics, and in particular to a method, electronic device, and medium for recommending mutation sites for plastic-degrading enzymes. Background Technology

[0002] Enzymes are proteins or RNA produced by living cells that possess high specificity and catalytic efficiency towards their substrates. The enzymes described in this invention refer to protein-based enzymes. Enzymes are widely used in biochemistry, pharmaceuticals, environmental engineering, and other fields. However, in harsh industrial environments, enzyme catalysis often faces bottlenecks such as poor thermal stability and low catalytic efficiency. Therefore, rational mutation design of enzymes can improve their thermal stability and catalytic activity, overcoming these bottlenecks in industrial applications.

[0003] Enzyme catalysis depends on the sequence structure (primary structure) and spatial structure of the enzyme molecule. Traditional enzyme mutation mainly employs directed evolution technology, which simulates Darwinian evolution in vitro. Through random mutation and recombination, a large number of mutations are artificially created, and selection pressure is applied according to specific needs and purposes to screen for proteins with desired characteristics, achieving molecular-level simulated evolution. Traditional directed evolution and recombination strategies suffer from drawbacks such as low efficiency, large screening workload, and difficulty in achieving global coverage. Therefore, recommending appropriate enzyme mutation sites is crucial.

[0004] In recent years, with the rapid development of deep learning technology, deep learning-based methods have been widely applied in computer vision, natural language processing, and other fields. The outstanding performance of the protein 3D structure prediction model AlphaFold2 in structural biology has shown researchers the greater potential of deep learning models in solving biological problems. Deep learning models have strong feature extraction capabilities, allowing them to predict the impact of mutations at different sequence sites on enzyme function, thereby searching for and recommending effective mutation sites globally within the sequence with very low dry experimental computational cost. However, deep learning models face two main bottlenecks in recommending enzyme mutation sites:

[0005] 1) Cold start problem: The scope of enzyme mutation sites and mutation types to be explored is large, but there is little expert experience and insufficient prior information;

[0006] 2) Insufficient data: Deep learning models are data-driven, and enzyme activity needs to be verified by wet experiments. Wet experiments require a lot of manpower and resources, which is costly. Therefore, there is very little enzyme activity data available for model training. Summary of the Invention

[0007] To overcome the shortcomings of the prior art, embodiments of the present invention provide a method, electronic device, and medium for recommending mutation sites of plastic degrading enzymes.

[0008] According to a first aspect of the present invention, a method for recommending mutation sites for plastic-degrading enzymes is provided, the method comprising:

[0009] Step S1: Obtain the amino acid sequence of the plastic degrading enzyme to be predicted and its substrate; predict the interaction region between the substrate and the plastic degrading enzyme; set a threshold distance, and use the plastic degrading enzyme amino acid within the threshold distance as the reference threshold distance as the candidate amino acid mutation site;

[0010] Step S2: Obtain the spatial structure of the plastic degrading enzyme to be predicted. Using amino acids as nodes and the connections between amino acids as edges, use a geometric vector perceptron to predict and output the predicted probability of i amino acids corresponding to each candidate amino acid mutation site. The amino acid with the highest probability is taken as the recommended amino acid for that candidate amino acid mutation site. Compare the prediction results of each candidate amino acid mutation site. When the prediction result is inconsistent with the original amino acid sequence, the candidate amino acid mutation site is taken as the recommended mutation site for the plastic degrading enzyme.

[0011] According to a second aspect of the present invention, an electronic device is provided, including a memory and a processor, the memory being coupled to the processor; wherein the memory is used to store program data, and the processor is used to execute the program data to implement the method described above for the recommended plastic degrading enzyme mutation site.

[0012] According to a third aspect of the present invention, a computer-readable storage medium is provided having a computer program stored thereon, which, when executed by a processor, implements the method described above for the recommended plastic degrading enzyme mutation sites.

[0013] The beneficial effects of this invention are as follows: This invention provides a method for recommending mutation sites for plastic degrading enzymes, introducing a geometric vector perceptron to solve the problem of single-point mutation in plastic degrading enzymes, namely, the large number of selectable mutation sites, the large exploration space for possible mutation types, and the lack of prior information. This invention can quickly recommend mutable sites for plastic degrading enzymes, effectively improving the activity of plastic degrading enzymes. Attached Figure Description

[0014] To more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings used in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0015] Figure 1 This is a schematic diagram of the catalytic reaction process of the plastic degrading enzyme PETase provided in an embodiment of the present invention.

[0016] Figure 2A flowchart for recommending enzyme mutation sites provided in embodiments of the present invention.

[0017] Figure 3 This is a schematic diagram illustrating the selection of candidate amino acid mutation sites provided in an embodiment of the present invention.

[0018] Figure 4 This is a schematic diagram illustrating the recommendations based on stable amino acid mutation sites provided in an embodiment of the present invention.

[0019] Figure 5 This is a schematic diagram of an electronic device provided in an embodiment of the present invention. Detailed Implementation

[0020] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0021] It should be noted that, unless otherwise specified, the features in the following embodiments and implementation methods can be combined with each other.

[0022] This invention provides a method for recommending mutation sites for plastic-degrading enzymes. The plastic-degrading enzymes described in this invention are primarily targeted at polyethylene terephthalate (PET) and / or PET. The catalytic reaction process of the plastic-degrading enzymes is described below. Figure 1 The method of this invention has been validated on two different plastic-degrading enzymes: FAST-PETase and Depo-PETase. The nucleotide sequence of FAST-PETase is shown in SEQ ID NO: 1, and the amino acid sequence is shown in SEQ ID NO: 2. The nucleotide sequence of Depo-PETase is shown in SEQ ID NO: 3, and the amino acid sequence is shown in SEQ ID NO: 4.

[0023] The embodiments of this invention are mainly based on FAST-PETase, and Depo-PETase is similar. A flowchart of the recommended enzyme mutation sites is shown below. Figure 2 Specifically, it includes the following steps:

[0024] Step S1: Obtain the amino acid sequence of the plastic degrading enzyme to be predicted and its substrate; predict the interaction region between the substrate and the plastic degrading enzyme; set a threshold distance, and use the plastic degrading enzyme amino acid within the threshold distance as the reference threshold distance as the candidate amino acid mutation site.

[0025] It should be noted that the process of screening candidate amino acid mutation sites in step S1 can reduce the candidate range space and focus the mutation options on the interface between the plastic degrading enzyme and the substrate.

[0026] Specifically, such as Figure 3 As shown, step S1 specifically includes the following steps:

[0027] Step S101: Obtain the amino acid sequence of a plastic-degrading enzyme (single polypeptide chain) with a defined substrate;

[0028] When the 3D structure of the plastic-degrading enzyme to be predicted is unknown, in this example, the AlphaFold model is used to predict the 3D structure of the plastic-degrading enzyme. The AlphaFold model is set to the default parameters.

[0029] The plastic-degrading enzyme is FAST-PETase, and the chemical formula of its substrate is: .

[0030] Step S102: Protein characterization of plastic degrading enzymes using the ESM-2 model.

[0031] In the ESM-2 model, the repr_layers parameter is set to 33, and the other parameters are set to the default values.

[0032] Step S103: Predict the interaction region between the substrate and the plastic-degrading enzyme.

[0033] Specifically, molecular docking techniques are used to predict the spatial conformation of the interaction between the protease and the substrate. In this example, the DiffDock model is used to perform molecular docking prediction. The SMILES format file corresponding to the substrate and the 3D structure of the plastic degrading enzyme are input into the DiffDock model, and the interaction region between the substrate and the plastic degrading enzyme is output.

[0034] The SMILES format file corresponding to the substrate includes: a molecular substrate docking file generated using the DiffDock model, where the substrate chemical formula is: Its SMILES format is:

[0035] C1=CC(=CC=C1C(=O)OCCOC(=O)(C1=CC=C(C(=O)OCCOC(=O)(C2=CC=C(C(=O)OCCOC(=O)(C3=CC=C(C(=O)OCCO)C=C3))C=C2))C=C1))C(=O)OCCO.

[0036] In the DiffDock model, the inference_steps parameter is set to 20, samples_per_complex parameter is set to 40, batch_size parameter is set to 10, actual_steps parameter is set to 18, and the no_final_step_noise parameter is added. Other parameters are set to their default values.

[0037] The Diffdock model scores the substrate conformation and selects the top-ranked substrate conformation sdf file.

[0038] Step S104: Set a threshold distance, using the substrate molecule or the active site of the plastic degrading enzyme as the benchmark. The amino acids of the plastic degrading enzyme within the threshold distance are selected as candidate amino acid mutation sites.

[0039] The threshold distance range is 5. -10 In this example, 10 To limit the selection of amino acids at nearby sites.

[0040] Furthermore, excluding known active amino acid sites of plastic degrading enzymes that function in the substrate, the remaining plastic degrading enzyme amino acids are considered as candidate amino acid mutation sites. This example excludes three known amino acid residues (i.e., the catalytic triplet) that simultaneously act on the active site center of FAST-PETase, S134-D180-H211, where S134 represents serine at position 134, and D180 and H211 are similarly excluded.

[0041] Step S2: Obtain the spatial structure of the plastic degrading enzyme to be predicted. Using amino acids as nodes and the connections between amino acids as edges, use a Geometric Vector Perceptron (GVP) to predict the predicted probability of i amino acids corresponding to each candidate amino acid mutation site. The amino acid with the highest probability is taken as the recommended amino acid for that candidate amino acid mutation site. Compare the prediction results of each candidate amino acid mutation site. When the prediction result is inconsistent with the original amino acid sequence, the candidate amino acid mutation site is taken as the recommended plastic degrading enzyme mutation site.

[0042] It should be noted that step S2 predicts the amino acid types with a higher probability of appearing at each candidate site in the protein sequence based on the stability of the amino acid microenvironment. Specifically, as shown... Figure 4 As shown, step S2 includes the following sub-steps:

[0043] Step S201: Obtain the spatial structure of the plastic-degrading enzyme to be predicted.

[0044] Based on the PDB file of the plastic-degrading enzyme to be predicted obtained from AlphaFold, the framework atoms were obtained ( The three-dimensional coordinates of (C, N, O atoms).

[0045] In step S202, with amino acids as nodes and the connections between amino acids as edges, the predicted probability of the i amino acids corresponding to each candidate amino acid mutation site is predicted and output by a Geometric Vector Perceptron (GVP). The amino acid with the highest probability is taken as the recommended amino acid for that candidate amino acid mutation site.

[0046] Among them, the node attribute features in the geometric vector perceptron include: isoelectric point information of amino acids.

[0047] In this example, i is set to 20. The geometric vector perceptron outputs the predicted probabilities of 20 amino acids for each candidate amino acid mutation site, and the amino acid with the highest probability is taken as the recommended amino acid for that candidate amino acid mutation site.

[0048] Step S203: Compare the prediction results of each candidate amino acid mutation site. When the prediction result is inconsistent with the original amino acid sequence, the candidate amino acid mutation site is taken as the recommended plastic degrading enzyme mutation site.

[0049] Step S204, the method further includes:

[0050] Based on the active amino acid site of the plastic degrading enzyme, the recommended plastic degrading enzyme mutation site with the closest spatial distance to the active amino acid site (topN) was selected for wet experimental verification. N is a user-defined positive integer. The enzyme catalytic efficiency was calculated.

[0051] Specifically, in this example, based on the active amino acid site of the plastic degrading enzyme, we selected the recommended plastic degrading enzyme mutation sites that are spatially close to the active amino acid site (in this example, the spatial distance is calculated using Euclidean distance) as candidate sites for the first round of experimental verification. Due to the cost of wet experiments, we selected 10 mutable sites as the initial mutation sites. The specific mutation sites are shown in the first column of Table 1.

[0052] The catalytic efficiency of the anchored enzyme was the primary objective, and wet experiments were used to verify the enhancement effect of the mutant site relative to the baseline enzyme. Reaction conditions: Using a PET film (ø=8 mm) as the substrate, 60 μL of crude enzyme solution was added to 1940 μL of phosphate buffer (pH 8.5, 50 mM). All experiments were repeated three times, and the average value was taken.

[0053] This example uses the total yield of products released by PET during substrate degradation—namely, the sum of monoethyl terephthalate (MHET), diethyl terephthalate (BHET), and terephthalic acid (TPA)—as the indicator of enzyme efficiency. Ethylene glycol was used as the solvent, and its content was not measured. Under the same time and substrate amount, a higher yield indicates higher catalytic efficiency. The yield at different temperatures (40℃, 50℃) was also observed; the specific effects are shown in Table 1.

[0054] Table 1: Amount of terminal end products generated in Fast-PETase mutagenesis experiments

[0055]

[0056] G60A means that the glycine (G) at position 60 is replaced with alanine (A), and the same applies below.

[0057] Analyze the wet experiment results and count the number of mutation sites that are increased relative to the wild type.

[0058] As shown in Table 1, two mutations at 40℃ (Y61Q increased by 93.48% and A214L increased by 59.01%) and three mutations at 50℃ (G60A increased by 7.79%, Y61Q increased by 51.90% and I182A increased by 30.79%) are superior to Fast-PETase.

[0059] Based on the above experimental methods, and having also verified them on Depo-PETase, we were able to obtain mutation sites with higher activity, as shown in Table 2.

[0060] Table 2: Amount of terminal end products generated in Depo-PETase mutation experiments

[0061]

[0062] As shown in Table 2, two mutations at 40℃ (Y61Q increased by 99.11% and I182A increased by 59.42%) and two mutations at 50℃ (W159M increased by 59.80% and S181Y increased by 56.21%) are superior to Depo-PETase.

[0063] As shown in the table above, in this example, at reaction temperatures of 40 ℃ and 50 ℃, at least 2 of the 10 mutants showed improved efficacy compared to the original enzyme, with the highest improvement being 99.11%.

[0064] In summary, this invention provides a method for recommending mutation sites for plastic degrading enzymes. It introduces a geometric vector perceptron to address the problem of single-point mutations in plastic degrading enzymes, namely, the large number of selectable mutation sites, the vast exploration space for possible mutation types, and insufficient prior information. This invention can rapidly recommend mutable sites for plastic degrading enzymes, effectively improving their activity.

[0065] like Figure 5 As shown, this application provides an electronic device including a memory 101 for storing one or more programs and a processor 102. When the one or more programs are executed by the processor 102, they implement the method as described in any of the first aspects above.

[0066] The system also includes a communication interface 103. The memory 101, processor 102, and communication interface 103 are electrically connected directly or indirectly to each other to enable data transmission or interaction. For example, these components can be electrically connected to each other via one or more communication buses or signal lines. The memory 101 can be used to store software programs and modules, and the processor 102 executes various functional applications and data processing by executing the software programs and modules stored in the memory 101. The communication interface 103 can be used for signaling or data communication with other node devices.

[0067] The memory 101 may be, but is not limited to, random access memory (RAM), read-only memory (ROM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), etc.

[0068] The processor 102 can be an integrated circuit chip with signal processing capabilities. The processor 102 can be a general-purpose processor 102, including a central processing unit (CPU), a network processor (NP), etc.; it can also be a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components.

[0069] In the embodiments provided in this application, it should be understood that the disclosed methods and systems can also be implemented in other ways. The method and system embodiments described above are merely illustrative. For example, the flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of methods and systems, methods, and computer program products according to various embodiments of this application. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions marked in the blocks may occur in a different order than those marked in the drawings. For example, two consecutive blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in a block diagram and / or flowchart, and combinations of blocks in block diagrams and / or flowcharts, can be implemented using a dedicated hardware-based system that performs the specified function or action, or using a combination of dedicated hardware and computer instructions.

[0070] In addition, the functional modules in the various embodiments of this application can be integrated together to form an independent part, or each module can exist independently, or two or more modules can be integrated to form an independent part.

[0071] On the other hand, embodiments of this application provide a computer-readable storage medium storing a computer program thereon. When executed by processor 102, the computer program implements the methods described in any of the first aspects above. If the functions are implemented as software functional modules and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or a part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as a USB flash drive, a portable hard drive, a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disk.

[0072] The above embodiments are only used to illustrate the design concept and features of the present invention, and their purpose is to enable those skilled in the art to understand the content of the present invention and implement it accordingly. The protection scope of the present invention is not limited to the above embodiments. Therefore, all equivalent changes or modifications made based on the principles and design ideas disclosed in the present invention are within the protection scope of the present invention.

Claims

1. A method for recommending mutation sites for plastic-degrading enzymes, characterized in that, The method includes: Step S1: Obtain the amino acid sequence of the plastic degrading enzyme to be predicted and its substrate; predict the interaction region between the substrate and the plastic degrading enzyme; set a threshold distance, and use the plastic degrading enzyme amino acid within the threshold distance as the reference threshold distance as the candidate amino acid mutation site; Step S2: Obtain the spatial structure of the plastic degrading enzyme to be predicted. Using amino acids as nodes and the connections between amino acids as edges, the predicted probability of i amino acids corresponding to each candidate amino acid mutation site is predicted and output by a geometric vector perceptron. The amino acid with the highest probability is taken as the recommended amino acid for the candidate amino acid mutation site. The prediction results of each candidate amino acid mutation site are compared. When the prediction result is inconsistent with the original amino acid sequence, the candidate amino acid mutation site is taken as the recommended mutation site for the plastic degrading enzyme. The predicted interaction regions between the substrate and the plastic-degrading enzyme include: The DiffDock model was used to predict molecular docking. The SMILES format file corresponding to the substrate and the 3D structure of the plastic degrading enzyme were input into the DiffDock model, and the interaction region between the substrate and the plastic degrading enzyme was output. The predicted interaction regions between the substrate and the plastic-degrading enzyme also include: Before using the DiffDock model to predict molecular docking, the plastic degrading enzymes were characterized as proteins using the ESM-2 model. Among them, the node attribute features in the geometric vector perceptron include: isoelectric point information of amino acids.

2. The method for recommending mutation sites of plastic-degrading enzymes according to claim 1, characterized in that, Step S1 further includes: When the 3D structure of the plastic degrading enzyme to be predicted is unknown, the AlphaFold model is used to predict the 3D structure of the plastic degrading enzyme.

3. The method for recommending mutation sites of plastic-degrading enzymes according to claim 1, characterized in that, The threshold distance ranges from 5 Å to 10 Å.

4. The method for recommending mutation sites of plastic-degrading enzymes according to claim 1, characterized in that, Candidate amino acid mutation sites for plastic-degrading enzymes are selected within a threshold distance from the substrate molecule or the active site of the plastic-degrading enzyme, including: Excluding known active amino acid sites of plastic degrading enzymes that function in the substrate, the remaining amino acids of plastic degrading enzymes were selected as candidate amino acid mutation sites.

5. The method for recommending mutation sites of plastic-degrading enzymes according to claim 1, characterized in that, Step S2 further includes: Based on the active amino acid site of the plastic degrading enzyme, the recommended plastic degrading enzyme mutation site with the closest spatial distance to the active amino acid site (topN) was selected for wet experimental verification. N is a user-defined positive integer. The enzyme catalytic efficiency was calculated.

6. An electronic device comprising a memory and a processor, characterized in that, The memory is coupled to the processor; wherein the memory is used to store program data, and the processor is used to execute the program data to implement the method for the recommended plastic degrading enzyme mutation site as described in any one of claims 1-5.

7. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the program is executed by the processor, it implements the method for the recommended plastic degrading enzyme mutation sites as described in any one of claims 1-5.

Images