An industrial enzyme screening method, apparatus, equipment and medium
By screening industrial enzyme libraries for stability, similarity, and catalytic site specificity, and utilizing protein models and deep learning algorithms, the problem of low enzyme screening efficiency in existing technologies has been solved, achieving efficient and accurate enzyme screening.
Patent Information
- Application Number
- CN202311614934.X
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2023-11-28
- Publication Date
- 2026-11-17
- Estimated Expiration
- 2043-11-28
AI Technical Summary
Existing technologies struggle to effectively address issues such as the thermal stability, catalytic activity enhancement, and specificity improvement of industrial enzymes during enzyme screening, resulting in high screening costs and low efficiency.
By screening industrial enzyme libraries for stability, similarity, and catalytic site specificity, and using protein models, phylogenetic trees, molecular dynamics simulations, and deep learning algorithms, industrial enzymes that meet industrial requirements in terms of stability, similarity, and specificity are selected.
It enables accurate and targeted enzyme screening in complex enzyme libraries, improving enzyme screening efficiency and reducing costs.
Smart Images

Figure CN117612638B_ABST
Abstract
Description
Technical Field
[0001] This invention relates to the field of enzyme screening technology, and in particular to an industrial enzyme screening method, apparatus, equipment and medium. Background Technology
[0002] Enzymes are widely used as highly efficient biocatalysts in various industrial production scenarios. Natural enzymes are widely distributed in nature, originate from diverse species, and have inconsistent and fragmented annotation information in various enzyme libraries. These factors place higher demands on enzyme screening methods adapted to specific industrial production environments.
[0003] Enzyme screening typically uses the catalyzed reaction as a "probe," and then broadly screens enzyme families that match this probe. With the rapid development of synthetic biology and protein engineering, the number and types of existing industrial enzymes have become increasingly diverse. To optimize production processes and improve efficiency, there are often specific requirements for screening existing industrial enzymes: higher thermal stability, stronger catalytic activity, and improved catalytic selectivity. Current technologies often involve broad screening from heat-resistant species within the families of existing industrial enzymes to identify those with thermal stability, but this may result in a lack of heat-resistant species. Another approach is to cluster enzyme families based on similarity, extract representative sequences from each cluster, and explore the enzyme activity of different clusters under the same similarity conditions for broad screening. A further requirement is to improve the specific catalytic activity of enzymes, aiming to mutate specific amino acid sites to obtain specific catalytic selectivity. However, most current enzyme screening methods for catalytic reactions are still in the stage of reverse enzyme discovery based on the catalytic reaction itself, which cannot effectively address the issues of thermal stability, catalytic activity enhancement, and specificity improvement faced by existing industrial enzymes. Screening from scratch would be much more costly.
[0004] In summary, how to accurately and specifically screen industrial enzymes that meet industrial needs from enzyme libraries with complex annotation information, and improve the efficiency of enzyme screening, is a technical problem that needs to be solved in this field. Summary of the Invention
[0005] In view of this, the purpose of this invention is to provide an industrial enzyme screening method, apparatus, equipment, and medium, which can accurately and specifically screen industrial enzymes that meet industrial needs from enzyme libraries with complex annotation information, thereby improving the efficiency of enzyme screening. The specific solution is as follows:
[0006] In a first aspect, this application discloses an industrial enzyme screening method, comprising:
[0007] Stable industrial enzymes are labeled from a pre-defined industrial enzyme library according to pre-defined stability screening criteria;
[0008] Label similar industrial enzymes from the preset industrial enzyme library according to preset similarity screening conditions;
[0009] Specific industrial enzymes are labeled from the preset industrial enzyme library according to preset catalytic site specificity screening conditions;
[0010] Stability analysis, substrate binding affinity prediction, and specific binding affinity prediction of the stable industrial enzyme, the similar industrial enzyme, and the specific industrial enzyme were performed on the stable industrial enzyme, the similar industrial enzyme, and the specific industrial enzyme to different substrates, respectively, to obtain the stable industrial enzyme after stability expression test, the similar industrial enzyme after enzyme activity test, and the specific industrial enzyme after specific catalysis test, respectively.
[0011] According to preset industrial enzyme screening conditions, the stable industrial enzymes after stability expression test, the similar industrial enzymes after enzyme activity test, and the specific industrial enzymes after specific catalysis test are labeled and screened to obtain target industrial enzymes.
[0012] Optionally, stability analysis is performed on the stable industrial enzyme, including:
[0013] A protein model was constructed based on the sequence of the stable industrial enzyme.
[0014] The surface sequence and internal residue sequence of the protein model corresponding to the stable industrial enzyme are distinguished using the protein structure prediction tool of the stable industrial enzyme, so as to evaluate the distribution of hydrophilic / hydrophobic amino acids on the surface of the stable industrial enzyme based on the surface sequence, and obtain the solubility evaluation result of the stable industrial enzyme.
[0015] The structural changes of the protein model under preset temperature conditions are evaluated to obtain the structural thermal stability evaluation results;
[0016] The industrial enzymes corresponding to the solubility assessment results and the structural thermal stability assessment results were expressed and tested to obtain the target stable industrial enzymes.
[0017] Optionally, the step of labeling similar industrial enzymes from the preset industrial enzyme library according to preset similarity screening conditions includes:
[0018] Select industrial enzyme families with similar enzyme catalytic functions from the pre-set industrial enzyme library;
[0019] Sequence alignment was performed on the industrial enzyme family to construct a phylogenetic tree for analyzing sequence evolutionary relationships;
[0020] The phylogenetic tree is used to select and label industrial enzymes with similar sequences to obtain similar industrial enzymes.
[0021] Optionally, the step of labeling similar industrial enzymes from the preset industrial enzyme library according to preset similarity screening conditions includes:
[0022] The industrial enzymes in the preset industrial enzyme library are screened for similarity using a preset sequence similarity network, and industrial enzymes with similar sequences are labeled to obtain similar industrial enzymes.
[0023] Optionally, the binding affinity of the similar industrial enzyme to the substrate is predicted, including:
[0024] A binding model of the similar industrial enzyme and its substrate was constructed, and the binding free energy was obtained by performing a kinetic simulation on the binding model.
[0025] The binding free energy is calculated to obtain the binding affinity between the similar industrial enzyme and the substrate.
[0026] Optionally, the industrial enzyme screening method further includes:
[0027] A pre-defined batch affinity prediction model is used to predict the binding affinity between the similar industrial enzymes and substrates in batches within the industrial enzyme family.
[0028] Optionally, after predicting the specific binding affinity of the specific industrial enzyme to different substrates, the method further includes:
[0029] Different specific binding sites were obtained after predicting the specific affinity of the specific industrial enzyme for different substrates.
[0030] Molecular docking and molecular dynamics simulations were used to compare all the specific binding sites with the target specific binding site to verify whether the specific binding sites were consistent with the target specific binding site and to obtain the corresponding target specific binding affinity.
[0031] Secondly, this application discloses an industrial enzyme screening device, comprising:
[0032] The first labeling module is used to label stable industrial enzymes from a preset industrial enzyme library according to preset stability screening conditions;
[0033] The second labeling module is used to label similar industrial enzymes from the preset industrial enzyme library according to preset similarity screening conditions;
[0034] The third labeling module is used to label specific industrial enzymes from the preset industrial enzyme library according to preset catalytic site specificity screening conditions;
[0035] The analysis and prediction module is used to perform stability analysis, prediction of binding affinity between similar industrial enzymes and substrates, and prediction of specific binding affinity between specific industrial enzymes and different substrates on the stable industrial enzyme, the similar industrial enzyme, and the specific industrial enzyme, respectively, so as to obtain the stable industrial enzyme after stability expression test, the similar industrial enzyme after enzyme activity test, and the specific industrial enzyme after specific catalysis test.
[0036] The screening module is used to label and screen the stable industrial enzymes after the stability expression test, the similar industrial enzymes after the enzyme activity test, and the specific industrial enzymes after the specific catalysis test according to preset industrial enzyme screening conditions, so as to obtain the target industrial enzymes.
[0037] Thirdly, this application discloses an electronic device, including:
[0038] Memory, used to store computer programs;
[0039] A processor is used to execute the computer program to implement the steps of the aforementioned disclosed industrial enzyme screening method.
[0040] Fourthly, this application discloses a computer-readable storage medium for storing a computer program; wherein, when the computer program is executed by a processor, it implements the steps of the aforementioned disclosed industrial enzyme screening method.
[0041] As can be seen, this application discloses an industrial enzyme screening method, comprising: labeling stable industrial enzymes from a preset industrial enzyme library according to preset stability screening conditions; labeling similar industrial enzymes from the preset industrial enzyme library according to preset similarity screening conditions; labeling specific industrial enzymes from the preset industrial enzyme library according to preset catalytic site specificity screening conditions; performing stability analysis, prediction of binding affinity between similar industrial enzymes and substrates, and prediction of specific binding affinity between specific industrial enzymes and different substrates on the stable industrial enzymes, the similar industrial enzymes after enzyme activity tests, and the specific industrial enzymes after specific catalytic tests, respectively, to obtain stable industrial enzymes after stability expression tests, similar industrial enzymes after enzyme activity tests, and specific industrial enzymes after specific catalytic tests; and labeling and screening the stable industrial enzymes after stability expression tests, the similar industrial enzymes after enzyme activity tests, and the specific industrial enzymes after specific catalytic tests according to preset industrial enzyme screening conditions to obtain target industrial enzymes. Therefore, by performing stability analysis on the sequence information of industrial enzymes, we can quickly screen industrial enzymes with similar functions and high expression solubility. By identifying the homology of similar sequences, we can screen sequences to achieve similarity analysis of industrial enzymes. Finally, by using hierarchical sequence screening, we can select specific industrial enzymes with better specificity. This enables accurate and targeted enzyme screening of industrial enzymes that meet industrial needs from enzyme libraries with complex annotation information, thereby improving the efficiency of enzyme screening. Attached Figure Description
[0042] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on the provided drawings without creative effort.
[0043] Figure 1 This is a flowchart of an industrial enzyme screening method disclosed in this application;
[0044] Figure 2 This is a flowchart of a method for discovering novel industrial enzymes disclosed in this application;
[0045] Figure 3 This is a flowchart of an industrial enzyme screening method with upgrade requirements disclosed in this application;
[0046] Figure 4 This is a schematic diagram of the structure of an industrial enzyme screening device disclosed in this application;
[0047] Figure 5 This is a structural diagram of an electronic device disclosed in this application. Detailed Implementation
[0048] The technical solutions of the embodiments of this application 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 of ordinary skill in the art without creative effort are within the scope of protection of the present invention.
[0049] Enzymes are widely used as highly efficient biocatalysts in various industrial production scenarios. Natural enzymes are widely distributed in nature, originate from diverse species, and have inconsistent and fragmented annotation information in various enzyme libraries. These factors place higher demands on enzyme screening methods adapted to specific industrial production environments.
[0050] Enzyme screening typically uses the catalyzed reaction as a "probe," and then broadly screens enzyme families that match this probe. With the rapid development of synthetic biology and protein engineering, the number and types of existing industrial enzymes have become increasingly diverse. To optimize production processes and improve efficiency, there are often specific requirements for screening existing industrial enzymes: higher thermal stability, stronger catalytic activity, and improved catalytic selectivity. Current technologies often involve broad screening from heat-resistant species within the families of existing industrial enzymes to identify those with thermal stability, but this may result in a lack of heat-resistant species. Another approach is to cluster enzyme families based on similarity, extract representative sequences from each cluster, and explore the enzyme activity of different clusters under the same similarity conditions for broad screening. A further requirement is to improve the specific catalytic activity of enzymes, aiming to mutate specific amino acid sites to obtain specific catalytic selectivity. However, most current enzyme screening methods for catalytic reactions are still in the stage of reverse enzyme discovery based on the catalytic reaction itself, which cannot effectively address the issues of thermal stability, catalytic activity enhancement, and specificity improvement faced by existing industrial enzymes. Screening from scratch would be much more costly.
[0051] Therefore, this application provides an industrial enzyme screening scheme that can accurately and specifically screen industrial enzymes that meet industrial needs from enzyme libraries with complex annotation information, thereby improving the efficiency of enzyme screening.
[0052] Reference Figure 1 As shown in the figure, an embodiment of the present invention discloses an industrial enzyme screening method, comprising:
[0053] Step S11: Label stable industrial enzymes from a preset industrial enzyme library according to preset stability screening conditions.
[0054] In this embodiment, refer to Figure 2As shown, the internal and external sequences of industrial enzymes are distinguished. Due to the presence of numerous hydrophobic residues in the external sequence, multiple catalytic units (enzyme monomers or dimers) may aggregate and precipitate using this hydrophobic region. The concentrated distribution of hydrophobic residues in the internal sequence helps maintain the overall conformational stability of the protein, while the hydrophobic distribution of the external sequence leads to the aggregation and precipitation of enzyme catalytic units. Without altering the sequence, multiple sequence alignment results are used to determine the hydrophobicity of internal and external sequence segments, with sequences exhibiting lower hydrophobicity having a higher priority for passing the screening. Based on this, corresponding stability screening conditions are set according to the hydrophobicity levels of the internal and external sequences, allowing stable industrial enzymes to be identified from a pre-defined industrial enzyme library. Specifically, the pre-defined industrial enzyme library can be: a publicly available sequence library, such as Uniprot or Alphafold DB; or an artificially constructed library, built using a machine learning (ML) model based on existing advantageous sequence features. Stability screening is performed on all family sequences of enzymes in the entire enzyme sequence library that meet the required enzyme catalytic function conditions, from which the target enzyme sequence is selected. In existing annotated enzyme libraries, the catalytic function of enzymes is labeled using an Enzyme Commission (EC) number. Sequences must first possess this EC number; unlabeled sequences can be screened out based on sequence homology criteria. Further analysis of industrial enzyme sequence information using CAEE (Computer Assisted Enzyme Engineering) and AI (Artificial Intelligence) technologies can rapidly screen for sequences with similar functions and high expression solubility.
[0055] Step S12: Label similar industrial enzymes from the preset industrial enzyme library according to preset similarity screening conditions.
[0056] In this embodiment, an industrial enzyme family with similar catalytic functions is selected from a pre-defined industrial enzyme library; sequence alignment is performed on the industrial enzyme family to construct a phylogenetic tree for analyzing sequence evolutionary relationships; the phylogenetic tree is then used to select and label industrial enzymes with similar sequences to obtain similar industrial enzymes. It is understood that, referring to... Figure 2As shown, when labeling similar industrial enzymes, that is, labeling industrial enzyme families with similar catalytic functions, specifically: a phylogenetic tree is constructed based on the sequences of this industrial enzyme family. Starting from the protein sequence, sequence alignment is performed, and a phylogenetic tree is constructed using commonly used methods such as maximum likelihood (ML), neighbor-joining (NJ), or maximum parsimony (MP). Phylogenetic trees can effectively analyze and understand the evolutionary relationships between different sequences, allowing for the selection or exclusion of sequences based on the closeness of these relationships. For selection purposes, initially, the branches of the phylogenetic tree are analyzed and verified as much as possible according to a certain level of relationship to ensure that the output reflects the overall performance of the sequences in the phylogenetic tree. When the overall screening enters the next stage, it is desirable to analyze and verify sequences with closer relationships to those showing outstanding performance, in order to obtain sequences with even stronger performance. Through multi-level similarity network analysis, the closeness of homology between similar sequences is identified to screen sequences, and the resulting sequences are further screened based on an AI model.
[0057] In this embodiment, a preset sequence similarity network is used to screen industrial enzymes in the preset industrial enzyme library for similarity, and industrial enzymes with similar sequences are labeled to obtain similar industrial enzymes. It can be understood that, referring to... Figure 2 As shown, a Sequence Similarity Network (SSN) is constructed to study the similarity between different sequences. This allows for the extraction of representative sequences from different clusters under different alignment scores for further study. Similarly, similar sequences can be excluded based on the distribution of different sequences within different clusters of the network, maximizing the coverage of the selected sequences within this industrial enzyme family.
[0058] Step S13: Label specific industrial enzymes from the preset industrial enzyme library according to preset catalytic site specificity screening conditions.
[0059] In this embodiment, the specificity analysis of catalytic function, i.e., labeling specific industrial enzymes, involves expanding the existing In-silico enzyme library with artificial sequences generated by an AI model. Subsequently, the industrial enzyme library is screened, and corresponding specific industrial enzyme tags are added to the library sequences. Based on CAEE and AI model-related technologies, a stereoscopic model analysis is performed on specific residues in the catalytic pocket region. Combined with key sequence fragments, an AI sequence generation algorithm is used to generate a sequence library, and hierarchical sequence screening is performed based on this library.
[0060] Step S14: Perform stability analysis, predict the binding affinity of the similar industrial enzyme to the substrate, and predict the specific binding affinity of the specific industrial enzyme to different substrates on the stable industrial enzyme, the similar industrial enzyme, and the specific industrial enzyme, respectively, to obtain the stable industrial enzyme after stability expression test, the similar industrial enzyme after enzyme activity test, and the specific industrial enzyme after specific catalysis test.
[0061] In this embodiment, stability analysis of the stable industrial enzyme includes: constructing a protein model based on the sequence of the stable industrial enzyme; using a protein structure prediction tool for the stable industrial enzyme to distinguish the surface sequence and internal residue sequence of the protein model corresponding to the stable industrial enzyme, so as to evaluate the distribution of hydrophilic / hydrophobic amino acids on the surface of the stable industrial enzyme based on the surface sequence, and obtain the solubility evaluation result of the stable industrial enzyme; evaluating the structural changes of the protein model under a preset temperature condition to obtain the structural thermal stability evaluation result; and performing expression tests on the industrial enzymes corresponding to the solubility evaluation result and the structural thermal stability evaluation result, respectively, to obtain the target stable industrial enzyme. It can be understood that the In-silico stability analysis of the stable industrial enzyme specifically includes three parallel steps: protein structure-based evaluation, molecular dynamics simulation analysis, and deep learning algorithm analysis. Specifically, the protein structure-based evaluation: with the development of high-precision protein structure prediction tools, many sequences whose structures have not yet been resolved can be used to construct high-precision prediction models. By distinguishing between surface and internal residue sequences, protein surface residues have a significant impact on protein aggregation. The solubility of the sequence structure is predicted and evaluated by assessing the distribution of hydrophilic / hydrophobic amino acids on the surface, combined with the CAEE method. Based on molecular dynamics simulation analysis: Molecular dynamics simulations typically rely on the accuracy of the protein model. By analyzing the structural changes (RMSD, RMSF) of the protein model under explicit / implicit solvent model conditions at different or the same temperature, the thermal stability of the protein structure can be assessed, and corresponding adjustable residues can be identified to improve solubility. Based on deep learning algorithm analysis: Based on the correlation model between amino acid sequences and protein solubility / stability established using deep learning algorithms on a database of proteins from model organisms (e.g., *E. coli*), a database containing massive sequences is rapidly evaluated at the sequence level. Stability analysis is achieved through three steps: protein structure-based evaluation, molecular dynamics simulation analysis, and deep learning algorithm analysis, to obtain stable industrial enzymes after stability analysis. Then, expression tests are conducted on these stable industrial enzymes. Industrial enzymes with good expression performance are identified as target stable industrial enzymes based on the experimental results, i.e., stable industrial enzymes after stability expression testing.
[0062] In this embodiment, a binding model of the similar industrial enzyme and the substrate is constructed, and the binding model is kineticly simulated to obtain the binding free energy. The binding free energy is then calculated to obtain the binding affinity between the similar industrial enzyme and the substrate. It is understood that constructing a binding model between the substrate and enzyme macromolecule using molecular docking, performing kinetic simulations of the binding complex using the molecular dynamics (MD) method, and calculating the binding free energy using MMPB / GBSA based on the MD output results can effectively assess the binding affinity between the substrate and the enzyme macromolecule.
[0063] In this embodiment, a pre-defined batch affinity prediction model is used to predict the binding affinity between similar industrial enzymes and substrates in batches for the industrial enzyme family. It is understood that a DL (Deep Learning) model based on GNN (Graph Neural Network) and CNN (Convolutional Neural Network) is used to perform batch Kcat predictions on the large-scale sequence library obtained from the screening. After prediction, enzyme activity assays and scale-up production tests are performed to obtain similar industrial enzymes after enzyme activity testing. It should be noted that whether the DL model needs to be pre-trained depends on whether the training data of the DL model contains sequences of the target enzyme family. In this embodiment, the DL model is applied in two scenarios: one is to screen enzymes with existing local research to find those with better performance; in this case, local Kcat data can be used to enhance the model's training to improve its reliability. The other scenario is the discovery of new enzymes; in this case, it relies more on the original training data of the DL model, and the results are only for reference. Using a DL model only requires knowing the substrate, products, temperature, and reaction conditions required by the model. For predictions, simply submit the corresponding file (FASTA format file) containing the sequence.
[0064] In this embodiment, different specific binding sites were obtained after predicting the specific affinity of the specific industrial enzyme with different substrates. Molecular docking and molecular dynamics simulations were used to compare all the specific binding sites with the target specific binding site to verify whether the specific binding sites were consistent with the target specific binding site, and to obtain the corresponding target specific binding affinity. It is understood that the binding affinity of specific industrial enzymes with specific catalytic functions with different substrates is evaluated to obtain different combinations of binding affinity. Specifically, the specificity of the catalytic site usually depends on the difference in affinity (non-covalent / covalent interaction, solvent bridge, etc.) of specific amino acids at the catalytic site for different substrates. This affinity difference is evaluated by calculating the binding affinity between the catalytic substrate and the control substrate and the enzyme macromolecule using molecular docking and MD simulations, and then relabeled to obtain a specific industrial enzyme after specific catalytic testing with a label.
[0065] In this embodiment, the expression test, enzyme activity assay, scale-up production test, and specific catalysis test fall within the scope of actual experiments. The sequence demonstrated good performance through local expression, cultivation, and activity assays. However, in actual industrial production environments, the overall reaction environment in the activity assay system, such as 96-well plates, shake flasks, and fermenter scale-up, will vary significantly, and the same enzyme may exhibit different performance characteristics during scale-up production. Therefore, after activity assays, whether the enzyme can become a qualified industrial-scale enzyme requires scale-up testing and repeated studies to determine its most suitable production environment (temperature, pH, cofactors, etc.).
[0066] Step S15: According to the preset industrial enzyme screening conditions, the stable industrial enzyme after the stability expression test, the similar industrial enzyme after the enzyme activity test, and the specific industrial enzyme after the specific catalysis test are labeled and screened to obtain the target industrial enzyme.
[0067] In this embodiment, since the stable industrial enzymes after stability expression testing, the similar industrial enzymes after enzyme activity testing, and the specific industrial enzymes after specific catalysis testing represent industrial enzymes that excel in different aspects, industrial enzymes with balanced expression in all aspects are further screened and labeled from these three groups using preset industrial enzyme screening conditions to obtain the target industrial enzyme. For sequences, there is no discarding; more precisely, if a sequence performs well in a certain step, it will be labeled accordingly, while unlabeled sequences are retained in the In-silico library for further analysis. This approach eliminates the bias in output evaluation results caused by the bias of different evaluation indicators in different steps. It can be seen that by using CAEE technology to model the enzyme's three-dimensional structure, and using AI algorithms to find enzyme families with similar structures and certain sequence similarities in the enzyme library based on structural and sequence similarity, combined with AI-generated sequences to construct an enzyme sequence library, enzyme screening methods are used to select enzyme sequences with a basis for modification.
[0068] As can be seen, this application discloses an industrial enzyme screening method, comprising: labeling stable industrial enzymes from a preset industrial enzyme library according to preset stability screening conditions; labeling similar industrial enzymes from the preset industrial enzyme library according to preset similarity screening conditions; labeling specific industrial enzymes from the preset industrial enzyme library according to preset catalytic site specificity screening conditions; performing stability analysis, prediction of binding affinity between similar industrial enzymes and substrates, and prediction of specific binding affinity between specific industrial enzymes and different substrates on the stable industrial enzymes, the similar industrial enzymes after enzyme activity tests, and the specific industrial enzymes after specific catalytic tests, respectively, to obtain stable industrial enzymes after stability expression tests, similar industrial enzymes after enzyme activity tests, and specific industrial enzymes after specific catalytic tests; and labeling and screening the stable industrial enzymes after stability expression tests, the similar industrial enzymes after enzyme activity tests, and the specific industrial enzymes after specific catalytic tests according to preset industrial enzyme screening conditions to obtain target industrial enzymes. Therefore, by performing stability analysis on the sequence information of industrial enzymes, we can quickly screen industrial enzymes with similar functions and high expression solubility. By identifying the homology of similar sequences, we can screen sequences to achieve similarity analysis of industrial enzymes. Finally, by using hierarchical sequence screening, we can select specific industrial enzymes with better specificity. This enables accurate and targeted enzyme screening of industrial enzymes that meet industrial needs from enzyme libraries with complex annotation information, thereby improving the efficiency of enzyme screening.
[0069] Reference Figure 3 As shown, this embodiment of the invention discloses an industrial enzyme screening method with upgrade requirements. Compared to the previous embodiment, this embodiment further explains and optimizes the technical solution. Specifically:
[0070] For industrial enzymes requiring upgrades, stability screening involves: analyzing the distribution of hydrophobic amino acid regions based on sequence analysis, establishing a model using the CAEE method, and labeling hydrophobic sites on the surface. By reducing the weight of hydrophobic residues at these sites, the probability of surface hydrophobic amino acids appearing is reduced during AI-generated sequence screening. Highly flexible regions within the protein are identified through molecular docking and kinetic simulations; these regions are likely to be the first to unfold during thermal denaturation. Rigidifying flexible sites (RSFs) are predicted and strengthened using the CAEE method. By analyzing the residue properties and spatial distribution characteristics of these flexible regions, AI sequence generation algorithms are used to increase the proportion of residues in the generated sequence that contribute to structural stability, such as hydrogen bonds, aromatic ring interactions, disulfide bonds, and salt bridges. Disordered end structures (N- and C-termini) and flexible loops in the protein sequence are also factors leading to instability. Structural and sequence alignment analysis reduces the probability of disordered end sequences or flexible loops appearing in the candidate sequence library. Then, in parallel with stability screening, hierarchical similarity screening and catalytic site specificity screening are conducted. After the expression tests of the three screenings are completed, the relevant test results are summarized to form the corresponding industrial enzymes, which are then used as upgraded industrial enzymes.
[0071] Therefore, it is evident that targeted acquisition of upgraded industrial enzymes for different actual industrial needs can comprehensively screen upgraded industrial enzymes from various aspects. Using CAEE and AI technologies, sequences with similar functions and high expression solubility can be quickly screened.
[0072] Reference Figure 4 As shown, this embodiment of the invention also discloses an industrial enzyme screening device, comprising:
[0073] The first labeling module 11 is used to label stable industrial enzymes from a preset industrial enzyme library according to preset stability screening conditions;
[0074] The second labeling module 12 is used to label similar industrial enzymes from the preset industrial enzyme library according to preset similarity screening conditions;
[0075] The third labeling module 13 is used to label specific industrial enzymes from the preset industrial enzyme library according to preset catalytic site specific screening conditions;
[0076] The analysis and prediction module 14 is used to perform stability analysis, prediction of binding affinity between similar industrial enzymes and substrates, and prediction of specific binding affinity between specific industrial enzymes and different substrates on the stable industrial enzyme, the similar industrial enzyme, and the specific industrial enzyme, respectively, so as to obtain the stable industrial enzyme after stability expression test, the similar industrial enzyme after enzyme activity test, and the specific industrial enzyme after specific catalysis test.
[0077] The screening module 15 is used to label and screen the stable industrial enzymes after the stability expression test, the similar industrial enzymes after the enzyme activity test, and the specific industrial enzymes after the specific catalysis test according to the preset industrial enzyme screening conditions, so as to obtain the target industrial enzyme.
[0078] As can be seen, this application discloses the following methods: labeling stable industrial enzymes from a preset industrial enzyme library according to preset stability screening conditions; labeling similar industrial enzymes from the preset industrial enzyme library according to preset similarity screening conditions; labeling specific industrial enzymes from the preset industrial enzyme library according to preset catalytic site specificity screening conditions; performing stability analysis, predicting the binding affinity of similar industrial enzymes to substrates, and predicting the specific binding affinity of specific industrial enzymes to different substrates on the stable industrial enzymes, similar industrial enzymes after enzyme activity tests, and specific industrial enzymes after specific catalytic tests, respectively, to obtain stable industrial enzymes after stability expression tests, similar industrial enzymes after enzyme activity tests, and specific industrial enzymes after specific catalytic tests, respectively; and labeling and screening the stable industrial enzymes after stability expression tests, similar industrial enzymes after enzyme activity tests, and specific industrial enzymes after specific catalytic tests according to preset industrial enzyme screening conditions to obtain target industrial enzymes. Therefore, by performing stability analysis on the sequence information of industrial enzymes, we can quickly screen industrial enzymes with similar functions and high expression solubility. By identifying the homology of similar sequences, we can screen sequences to achieve similarity analysis of industrial enzymes. Finally, by using hierarchical sequence screening, we can select specific industrial enzymes with better specificity. This enables accurate and targeted enzyme screening of industrial enzymes that meet industrial needs from enzyme libraries with complex annotation information, thereby improving the efficiency of enzyme screening.
[0079] Furthermore, embodiments of this application also disclose an electronic device, Figure 5 This is a structural diagram of an electronic device 20 according to an exemplary embodiment. The content of the diagram should not be construed as limiting the scope of this application.
[0080] Figure 5This is a schematic diagram of the structure of an electronic device 20 provided in an embodiment of this application. Specifically, the electronic device 20 may include: at least one processor 21, at least one memory 22, a power supply 23, a communication interface 24, an input / output interface 25, and a communication bus 26. The memory 22 stores a computer program, which is loaded and executed by the processor 21 to implement the relevant steps in the industrial enzyme screening method disclosed in any of the foregoing embodiments. Alternatively, the electronic device 20 in this embodiment may specifically be an electronic computer.
[0081] In this embodiment, the power supply 23 is used to provide operating voltage for each hardware device on the electronic device 20; the communication interface 24 can create a data transmission channel between the electronic device 20 and external devices, and the communication protocol it follows can be any communication protocol applicable to the technical solution of this application, and is not specifically limited here; the input / output interface 25 is used to acquire external input data or output data to the outside world, and its specific interface type can be selected according to specific application needs, and is not specifically limited here.
[0082] The processor 21 may include one or more processing cores, such as a quad-core processor or an octa-core processor. The processor 21 may be implemented using at least one hardware form selected from DSP (Digital Signal Processing), FPGA (Field-Programmable Gate Array), and PLA (Programmable Logic Array). The processor 21 may also include a main processor and a coprocessor. The main processor, also known as a CPU (Central Processing Unit), is used to process data in the wake-up state; the coprocessor is a low-power processor used to process data in the standby state. In some embodiments, the processor 21 may integrate a GPU (Graphics Processing Unit), which is responsible for rendering and drawing the content to be displayed on the screen. In some embodiments, the processor 21 may also include an AI (Artificial Intelligence) processor, which is used to handle computational operations related to machine learning.
[0083] In addition, the memory 22, as a carrier for resource storage, can be a read-only memory, random access memory, disk or optical disk, etc. The resources stored thereon can include operating system 221, computer program 222, etc., and the storage method can be temporary storage or permanent storage.
[0084] The operating system 221 manages and controls the various hardware devices and computer programs 222 on the electronic device 20 to enable the processor 21 to perform calculations and processing on the massive amounts of data 223 in the memory 22. The operating system 221 can be Windows Server, Netware, Unix, Linux, etc. The computer program 222, in addition to including a computer program capable of performing the industrial enzyme screening method executed by the electronic device 20 as disclosed in any of the foregoing embodiments, may further include computer programs capable of performing other specific tasks. The data 223 may include data received by the electronic device from external devices, as well as data collected by its own input / output interface 25.
[0085] Furthermore, this application also discloses a computer-readable storage medium for storing a computer program; wherein, when the computer program is executed by a processor, it implements the aforementioned disclosed industrial enzyme screening method. Specific steps of this method can be found in the corresponding content disclosed in the foregoing embodiments, and will not be repeated here.
[0086] The various embodiments in this specification are described in a progressive manner, with each embodiment focusing on its differences from other embodiments. Similar or identical parts between embodiments can be referred to interchangeably. For the apparatus disclosed in the embodiments, since it corresponds to the method disclosed in the embodiments, the description is relatively simple; relevant parts can be referred to in the method section.
[0087] Those skilled in the art will further recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of both. To clearly illustrate the interchangeability of hardware and software, the components and steps of the various examples have been generally described in terms of functionality in the foregoing description. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application. The steps of the methods or algorithms described in conjunction with the embodiments disclosed herein can be implemented directly in hardware, software modules executed by a processor, or a combination of both. The software module can be located in random access memory (RAM), memory, read-only memory (ROM), electrically programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), registers, hard disks, removable disks, CD-ROMs (Compact Disc-Read Only Memory), or any other form of storage medium known in the art.
[0088] Finally, it should be noted that in this document, relational terms such as "first" and "second" are used only to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.
[0089] The above provides a detailed description of the industrial enzyme screening method, apparatus, equipment, and medium provided by the present invention. Specific examples have been used to illustrate the principles and implementation methods of the present invention. The descriptions of the above embodiments are only for the purpose of helping to understand the method and core ideas of the present invention. At the same time, for those skilled in the art, there will be changes in the specific implementation methods and application scope based on the ideas of the present invention. Therefore, the content of this specification should not be construed as a limitation of the present invention.
Claims
1. A method of screening for industrial enzymes, characterized in that, include: Obtain the amino acid sequence of an industrial enzyme with upgrade requirements, establish a protein model based on the amino acid sequence, and mark hydrophobic sites on the surface of the protein model according to the distribution of hydrophobic regions of the amino acid sequence. The highly flexible regions in the protein model were determined through molecular docking and molecular dynamics simulations. Multiple candidate sequences are generated using an artificial intelligence sequence generation algorithm. When generating these candidate sequences, the weight used by the algorithm in generating hydrophobic residues at hydrophobic sites on the surface is reduced to decrease the probability of hydrophobic amino acids appearing at corresponding sites in the candidate sequences. Based on the properties and spatial distribution characteristics of residues in the highly flexible region, the proportion of residues that contribute to the formation of hydrogen bonds, aromatic ring interactions, disulfide bonds, or salt bridges in the candidate sequences is increased, while the probability of disordered end sequences or flexible rings appearing in the candidate sequences is reduced. The multiple candidate sequences are written into an existing computer-simulated industrial enzyme library to obtain a preset industrial enzyme library; Stable industrial enzymes are labeled from a pre-defined industrial enzyme library according to pre-defined stability screening criteria; Label similar industrial enzymes from the preset industrial enzyme library according to preset similarity screening conditions; Specific industrial enzymes are labeled from the preset industrial enzyme library according to preset catalytic site specificity screening conditions; Stability analysis, substrate binding affinity prediction, and specific binding affinity prediction of the stable industrial enzyme, the similar industrial enzyme, and the specific industrial enzyme were performed on the stable industrial enzyme, the similar industrial enzyme, and the specific industrial enzyme to different substrates, respectively, to obtain the stable industrial enzyme after stability expression test, the similar industrial enzyme after enzyme activity test, and the specific industrial enzyme after specific catalysis test, respectively. According to preset industrial enzyme screening conditions, the stable industrial enzymes after stability expression test, the similar industrial enzymes after enzyme activity test, and the specific industrial enzymes after specific catalysis test are labeled and screened to obtain target industrial enzymes. For candidate sequences that do not obtain a corresponding tag in any screening process, the candidate sequences are retained in the preset industrial enzyme library before the remaining screening and corresponding tests are completed, for use in the remaining screening and corresponding tests; Summarize the tags and test results corresponding to the same candidate sequence, and screen the target industrial enzymes based on the summarized results; Stability analysis of the industrial enzyme includes: A protein model was constructed based on the sequence of the stable industrial enzyme. The surface sequence and internal residue sequence of the protein model corresponding to the stable industrial enzyme are distinguished using the protein structure prediction tool of the stable industrial enzyme, so as to evaluate the distribution of hydrophilic / hydrophobic amino acids on the surface of the stable industrial enzyme based on the surface sequence, and obtain the solubility evaluation result of the stable industrial enzyme. The structural changes of the protein model under preset temperature conditions are evaluated to obtain the structural thermal stability evaluation results; The industrial enzymes corresponding to the solubility assessment results and the structural thermal stability assessment results were expressed and tested to obtain the target stable industrial enzymes. After predicting the specific binding affinity of the specific industrial enzyme to different substrates, the method further includes: Different specific binding sites were obtained after predicting the specific affinity of the specific industrial enzyme for different substrates. Molecular docking and molecular dynamics simulations were used to compare all the specific binding sites with the target specific binding site to verify whether the specific binding sites were consistent with the target specific binding site and to obtain the corresponding target specific binding affinity.
2. The industrial enzyme screening method according to claim 1, characterized in that, The step of labeling similar industrial enzymes from the preset industrial enzyme library according to preset similarity screening conditions includes: Select industrial enzyme families with similar enzyme catalytic functions from the pre-set industrial enzyme library; Sequence alignment was performed on the industrial enzyme family to construct a phylogenetic tree for analyzing sequence evolutionary relationships; The phylogenetic tree is used to select and label industrial enzymes with similar sequences to obtain similar industrial enzymes.
3. The industrial enzyme screening method according to claim 1, characterized in that, The step of labeling similar industrial enzymes from the preset industrial enzyme library according to preset similarity screening conditions includes: The industrial enzymes in the preset industrial enzyme library are screened for similarity using a preset sequence similarity network, and industrial enzymes with similar sequences are labeled to obtain similar industrial enzymes.
4. The industrial enzyme screening method according to claim 2 or 3, characterized in that, Predicting the binding affinity between the similar industrial enzymes and their substrates includes: A binding model of the similar industrial enzyme and its substrate was constructed, and the binding free energy was obtained by performing a kinetic simulation on the binding model. The binding free energy is calculated to obtain the binding affinity between the similar industrial enzyme and the substrate.
5. The industrial enzyme screening method according to claim 4, characterized in that, Also includes: A pre-defined batch affinity prediction model is used to predict the binding affinity between the similar industrial enzymes and substrates in batches within the industrial enzyme family.
6. An industrial enzyme screening device, characterized in that, include: The industrial enzyme screening device is also used to obtain the amino acid sequence of industrial enzymes with upgrade requirements, establish a protein model based on the amino acid sequence, and mark hydrophobic sites located on the surface of the protein model according to the distribution of hydrophobic regions of the amino acid sequence. The highly flexible regions in the protein model were determined through molecular docking and molecular dynamics simulations. Multiple candidate sequences are generated using an artificial intelligence sequence generation algorithm. When generating these candidate sequences, the weight used by the algorithm in generating hydrophobic residues at hydrophobic sites on the surface is reduced to decrease the probability of hydrophobic amino acids appearing at corresponding sites in the candidate sequences. Based on the properties and spatial distribution characteristics of residues in the highly flexible region, the proportion of residues that contribute to the formation of hydrogen bonds, aromatic ring interactions, disulfide bonds, or salt bridges in the candidate sequences is increased, while the probability of disordered end sequences or flexible rings appearing in the candidate sequences is reduced. The multiple candidate sequences are written into an existing computer-simulated industrial enzyme library to obtain a preset industrial enzyme library; The first labeling module is used to label stable industrial enzymes from a preset industrial enzyme library according to preset stability screening conditions; The second labeling module is used to label similar industrial enzymes from the preset industrial enzyme library according to preset similarity screening conditions; The third labeling module is used to label specific industrial enzymes from the preset industrial enzyme library according to preset catalytic site specificity screening conditions; The analysis and prediction module is used to perform stability analysis, prediction of binding affinity between similar industrial enzymes and substrates, and prediction of specific binding affinity between specific industrial enzymes and different substrates on the stable industrial enzyme, the similar industrial enzyme, and the specific industrial enzyme, respectively, so as to obtain the stable industrial enzyme after stability expression test, the similar industrial enzyme after enzyme activity test, and the specific industrial enzyme after specific catalysis test. The screening module is used to label and screen stable industrial enzymes after stability expression testing, similar industrial enzymes after enzyme activity testing, and specific industrial enzymes after specific catalysis testing according to preset industrial enzyme screening conditions, in order to obtain target industrial enzymes. For candidate sequences that do not obtain corresponding tags in any screening process, the candidate sequences are retained in the preset industrial enzyme library before the remaining screening and corresponding tests are completed, for use in the remaining screening and corresponding tests. The modules summarize the tags and test results corresponding to the same candidate sequence and screen target industrial enzymes based on the summarized results. The analysis and prediction module is specifically used to construct a protein model based on the sequence of the stable industrial enzyme; to distinguish the surface sequence and internal residue sequence of the protein model corresponding to the stable industrial enzyme using a protein structure prediction tool for the stable industrial enzyme, so as to evaluate the distribution of hydrophilic / hydrophobic amino acids on the surface of the stable industrial enzyme based on the surface sequence, and obtain the solubility evaluation result of the stable industrial enzyme; to evaluate the structural changes of the protein model under a preset temperature condition, so as to obtain the structural thermal stability evaluation result; and to perform expression tests on the industrial enzymes corresponding to the solubility evaluation result and the structural thermal stability evaluation result, respectively, to obtain the target stable industrial enzyme. The industrial enzyme screening device is further used to obtain different specific binding sites after predicting the specific affinity of the specific industrial enzyme for different substrates; and to compare all the specific binding sites with the target specific binding site using molecular docking and molecular dynamics simulation methods to verify whether the specific binding sites are consistent with the target specific binding site and to obtain the corresponding target specific binding affinity.
7. An electronic device, characterized in that, include: Memory, used to store computer programs; A processor for executing the computer program to implement the steps of the industrial enzyme screening method as described in any one of claims 1 to 5.
8. A computer-readable storage medium, characterized in that, Used to store a computer program; wherein, when executed by a processor, the computer program implements the steps of the industrial enzyme screening method as described in any one of claims 1 to 5.
Citation Information
Patent Citations
Design and application of ketoreductase mutant
CN115295076A
Method, device and system for establishing bio-enzyme database and medium
CN115410652A
Enzyme kinetic parameter prediction method and device
CN116206696A
