Predicting effect of mutations on protease activity

Abstract

The present disclosure relates to predicting the effect of mutations on protease activity. In the method for predicting the influence of mutation on protease activity, feature extraction is performed by using a pre-training model based on sequence information of a to-be-predicted protease sample to obtain a sequence feature of the to-be-predicted protease sample (S110); based on the three-dimensional structure information of the to-be-predicted protease sample, obtaining a structural feature of the to-be-predicted protease sample (S120); and performing prediction by using a prediction model based on a graph neural network based on the sequence features and the structural features, and determining an activity change prediction result of the to-be-predicted protease sample after mutation (S130). The invention also discloses a construction method of the prediction model for predicting the influence of mutation on protease activity. The method disclosed by the invention is based on an advanced natural language processing model and a graph neural network, combines a sequence and a three-dimensional structure, performs prediction through an artificial intelligence model, shows performance superior to that of other existing methods, and proves that the method has a wide application prospect in protease engineering.

Description

[0001] CROSS-REFERENCE TO RELATED APPLICATIONS

[0002] This application claims the priority of Chinese patent application No. 202311028534.0, filed with the Chinese Patent Office on August 15, 2023, and entitled “Predicting the Effect of Mutations on Protease Activity”, and incorporates its entire contents into this application by reference. Technical Field

[0003] The present disclosure relates to protease optimization, and more particularly to predicting the effects of amino acid mutations on protease activity. Background Art

[0004] Enzymes are important biocatalysts. Due to their high selectivity, biocompatibility and mild reaction, they have broad application prospects in industrial biocatalysis, especially in the production of pharmaceutical intermediates. The vast majority of enzymes are proteins, and the molecular structure and function of proteins are affected by factors such as temperature, pH, and activators. Therefore, the catalytic activity of proteases can only be manifested under certain conditions. Usually, the catalytic activity of proteases needs to be engineered to adapt to different production environments and functional requirements.

[0005] Directed evolution and rational design are two common protease optimization strategies. Directed evolution strategy has been successfully applied to the modification of protease properties such as activity, stability, substrate specificity, and stereoselectivity. American scientist Frances H. Arnold won the 2018 Nobel Prize in Chemistry for this. However, directed evolution requires the construction of a large-scale mutant library and the establishment of high-throughput screening methods, which will consume a lot of manpower, material resources and financial resources. The directed evolution method is also difficult to complete a comprehensive search of sequence space, and there are fundamental defects. The rational design strategy relies on the understanding of the relationship between the structure and function of the protease to predict possible mutants, and then constructs mutants in the target gene by means of site-directed mutagenesis. In essence, compared with directed evolution, rational design is more efficient in modifying proteases. In addition, the rational design method is universal, and an effective rational design strategy can be widely applied to the modification of a variety of proteases. However, the accuracy of the current rational design method is generally low, and its application range is far less extensive than directed evolution. In recent years, artificial intelligence-assisted protein engineering has gradually developed into a new and efficient protein design strategy, showing unique advantages in many aspects such as protein structure prediction, function prediction, stability prediction and antibody affinity prediction, becoming another technological wave after rational design and directed evolution.

[0006] In recent years, with the rapid development of computer technology, various neural network models are rapidly updating and iterating in a more accurate and efficient direction, and artificial intelligence (AI)-assisted enzyme engineering has gradually developed into a new and efficient protease design strategy. In order to cope with the explosive growth of protein sequence databases brought about by large-scale gene sequencing, the number of parameters of the current largest protein language model has reached 15 billion (see Lin, Zeming et al. 2023. "Evolutionary-scale prediction of atomic-level protein structure with a language model". Science 379 (6637): 1123–30. By citing here, the entire contents of the above-mentioned documents are incorporated into the present disclosure and become part of the contents of the present disclosure). The continuous development of high-performance computing and natural language processing (NLP) advances have enabled researchers to use large protein databases to enhance the prediction of sequence attributes or annotations of relatively small experimental data sets.

[0007] After decades of development, there are dozens of AI-based methods for predicting protein stability, and their performance has surpassed traditional rational design methods. Unlike the stability prediction of proteases, currently only the SCANEER (Sequence Co-Evolutionary Analysis To Control Efficiency Of Enzyme Reactions) method is based on sequence co-evolutionary analysis to find evolutionarily available alternative amino acids to improve protease activity (see Kim, Donghyo et al. 2022. "Enzyme activity engineering based on sequence co-evolution analysis". Metabolic Engineering 74: 49–60. By citing here, the entire contents of the above-mentioned documents are incorporated into the present disclosure to make it part of the content of the present disclosure). SCANEER evaluates the co-evolutionary relationship of amino acid pairs in multiple sequence alignments (MSA). Amino acid pairs that are not observed or rarely observed in MSA, i.e., amino acid substitutions, cannot be predicted, which ultimately leads to the number of predictable mutations for each protease accounting for only 47% of all possible mutations, which will greatly limit the scope of application of this method. There is still a gap in how to apply the current advanced AI methods to the prediction method of protease activity.

[0008] At present, the application of natural language processing to the prediction of protease activity encounters many problems. First, since artificial intelligence algorithms rely heavily on data, the quantity and quality of the initial data determine the generalization performance of the trained model (see Usmanova, Dinara R et al. 2018. "Self-consistency test reveals systematic bias in programs for prediction change of stability upon mutation". Bioinformatics 34 (21): 3653–58. By citing here, the entire content of the above document is incorporated into the present disclosure and becomes part of the content of the present disclosure). Insufficient sample quantity or low quality of the data set will cause the model to overfit or underfit, which may be one of the important factors limiting the prediction of protease activity based on AI. At the same time, due to the preference of protease evolution and experiment, the data set is unbalanced, which in turn affects the performance of the prediction model. Secondly, for different substrates under different experimental conditions such as temperature and pH, the same mutation will have different activity effects on the protease. This multi-label data also brings great difficulties to the prediction work. Summary of the invention

[0009] Stability and catalytic activity are the two most important properties of proteases, among which stability is studied more, and dozens of AI-based methods have been developed to predict the effect of mutations on protease stability and have excellent performance, while catalytic activity has been limited by data sets and methods and has stagnated so far. Only the SCANEER method (cited above) can predict the effect of single-point mutations on protease activity, but this method is limited because it can only predict mutations that have appeared in evolution based on co-evolution information, and it cannot be widely used. Based on the above-mentioned defects in the current method for predicting the effect of mutations on protease activity, the present disclosure proposes a method for predicting the effect of mutations on protease activity. It is a deep learning method based on a new natural language processing method and graph structure data, using T5 (i.e., TransferText-to-TextTransformer) pre-training model to extract sequence features, and graph neural network model (such as graph attention network, GraphAttentionNetwork (GAT)) to extract structural features, and successfully using protein language model and graph attention network model to predict changes in protease activity caused by single-point missense mutations.

[0010] According to the first aspect of the present disclosure, a method for predicting the effect of mutation on protease activity is provided. The method may include the following steps: based on the sequence information of the protease sample to be predicted, using a pre-trained model to perform feature extraction to obtain the sequence features of the protease sample to be predicted; based on the three-dimensional structure information of the protease sample to be predicted, obtaining the structural features of the protease sample to be predicted; based on the sequence features and the structural features, using a prediction model based on a graph neural network to perform prediction, and determining the predicted result of the activity change of the protease sample to be predicted after mutation.

[0011] In the method according to the first aspect of the present disclosure, the sequence information of the protease sample to be predicted may include the amino acid sequence information of the protease sample to be predicted before mutation and the amino acid sequence information of the protease sample to be predicted after mutation.

[0012] On the other hand, the sequence information of the protease sample to be predicted may include the amino acid sequence information of the protease sample to be predicted before mutation and the designated mutation information. Thus, based on the amino acid sequence information of the protease sample to be predicted before mutation and the designated mutation information, the amino acid sequence information of the protease sample to be predicted after mutation can be obtained.

[0013] Preferably, the specified mutation information includes a specified mutation site and / or a specified amino acid type after mutation.

[0014] In the method according to the first aspect of the present disclosure, the method of extracting features based on the sequence information of the protease sample to be predicted using a pre-trained model to obtain the sequence features of the protease sample to be predicted may further include: extracting features from the amino acid sequence information of the protease sample to be predicted before mutation and the amino acid sequence information after mutation using the pre-trained model respectively to obtain the sequence feature information before mutation and the sequence feature information after mutation; and splicing the sequence feature information before mutation and the sequence feature information after mutation to obtain the sequence features of the protease sample to be predicted.

[0015] In the method according to the first aspect of the present disclosure, the pre-trained model can be implemented by a combination of one or more of the following models: ESM-1b, UniRef, ProteinBert, TAPE, ProtGPT2, ProtTXL, ProtBert, ProtXLNet, ProtAlbert, ProtElectra, ProtT5-XL and ProtT5-XXL; preferably, the pre-trained model is ProtT5-XL or ProtT5-XXL; more preferably, the pre-trained model is ProtT5-XL.

[0016] In the method according to the first aspect of the present disclosure, the three-dimensional structural information of the protease sample to be predicted may include the three-dimensional structural information of the protease sample to be predicted obtained through at least one of the following databases or prediction software: PDB database, AlphaFold2, I-TASSER, RoseTTAFold, Modeller and Swiss-model.

[0017] In the method according to the first aspect of the present disclosure, the three-dimensional structural information of the protease sample to be predicted may include an interaction network, a secondary structure, an amino acid residue distance or a physical environment. Preferably, the three-dimensional structural information of the protease sample to be predicted includes an interaction network.

[0018] Preferably, the three-dimensional structural information of the protease sample to be predicted is obtained in the following manner: obtaining the coordinates of the three-dimensional structure of the protease sample to be predicted; calculating the distance between the amino acid residue pairs in the three-dimensional structure of the protease according to the coordinates of the obtained three-dimensional structure; when the alpha carbon atom distance between two residue pairs is less than 10 angstroms, it indicates that there is an edge relationship between the nodes, which is recorded as 1, otherwise it is 0, and it itself is recorded as 0, thereby obtaining the adjacency matrix of the entire protease sample to be predicted.

[0019] Correspondingly, in the method according to the first aspect of the present disclosure, the three-dimensional structural information based on the protease sample to be predicted, obtaining the structural characteristics of the protease sample to be predicted can include: taking the mutation site as the center, intercepting the adjacency matrix of a specified size from the adjacency matrix of the whole protease sample to be predicted, as the structural characteristics of the protease sample to be predicted. In some embodiments, taking the mutation site as the center, intercepting the adjacency matrix of N*N (N is an integer greater than or equal to 1) from the adjacency matrix of the whole protease sample to be predicted. Intercepting the adjacency matrix of N*N from the adjacency matrix of the whole protease sample to be predicted can be intercepted based on the sequence on the left and right sides of the mutation site, or can be intercepted based on the distance between the mutation site. In one embodiment, taking the mutation site as the center, selecting the amino acid less than 10 angstroms in the adjacency matrix of the whole protease sample to be predicted from the mutation site as the structural characteristics of the protease sample to be predicted.

[0020] In the method according to the first aspect of the present disclosure, preferably, the prediction based on the sequence features and the structural features using a prediction model based on a graph neural network to determine the predicted result of the activity change after the mutation of the protease sample to be predicted can further include: inputting the sequence features and the structural features into the graph neural network to obtain probability features about the activity change; combining the probability features of the activity change with supplementary features from other prediction methods, and inputting them into a decision tree model to finally obtain a classification about the activity change.

[0021] Preferably, the inputting of the sequence features and the structural features into the graph neural network to obtain the probability features about the activity change may include: inputting the sequence features and the structural features into the graph neural network; updating and outputting the features using several layers of graph network structures through matrix multiplication and aggregation operations; merging the features outputted by several layers of graph network structures respectively; compressing the features using pooling operations; classifying the features according to the activity changes according to the classification function of the output layer, and outputting the probability features about the activity changes. Preferably, the pooling operation here may be average pooling, maximum pooling or K-max pooling. The probability features of the activity changes here may be the probability value of the increased activity after the protease sample mutates.

[0022] In the method according to the first aspect of the present disclosure, the prediction model based on the graph neural network can be constructed by the following steps: obtaining a training set, the training set including information of multiple training samples, the information of each training sample including three-dimensional structural information of the sample protease, amino acid sequence information of the sample protease before and after mutation, and a mutation activity change label; based on the amino acid sequence information of the sample protease before and after mutation, performing feature extraction through a pre-training model to obtain sequence features of the multiple training samples; based on the three-dimensional structural information of the sample protease, obtaining structural features of the multiple training samples; based on the sequence features, the structural features and the mutation activity change labels, training the graph neural network to obtain the prediction model based on the graph neural network.

[0023] Preferably, the graph neural network-based prediction model is a classifier.

[0024] Preferably, the graph neural network is a graph convolutional network or a graph attention network.

[0025] Preferably, the graph neural network is trained based on the sequence features, the structural features and the mutation activity change labels to obtain the prediction model based on the graph neural network, which may further include: inputting the sequence features and the structural features into the graph neural network to obtain probability features about activity changes; combining the probability features of activity changes with supplementary features from other prediction methods and inputting them into a decision tree model to obtain a classification of activity changes; and adjusting the parameters of the prediction model using the mutation activity change label as the output target.

[0026] Preferably, the decision tree model is a gradient boosted decision tree (GBDT) model. More preferably, the GBDT model is implemented using the LightGBM framework.

[0027] Preferably, experimental data in a public database can be obtained as a training set. At the same time, the training set can be doubled in size by inverting the experimental data in the public database.

[0028] According to the second aspect of the present disclosure, a method for constructing a prediction model for predicting the effect of mutation on protease activity is provided. The method may include the following steps: obtaining a training set, the training set including information of multiple training samples, the information of each training sample including three-dimensional structural information of the sample protease, amino acid sequence information of the sample protease before and after mutation, and mutation activity change label; based on the amino acid sequence information of the sample protease before and after mutation, feature extraction is performed through a pre-training model to obtain sequence features of the multiple training samples; based on the three-dimensional structural information of the sample protease, the structural features of the multiple training samples are obtained; based on the sequence features, the structural features and the mutation activity change label, the graph neural network is trained to obtain a prediction model for predicting the effect of mutation on protease activity.

[0029] In the method according to the second aspect of the present disclosure, the amino acid sequence information of the sample protease before and after mutation is used to extract features through a pre-trained model to obtain the sequence features of the multiple training samples, which may include: using the pre-trained model to extract features from the amino acid sequence information of the sample protease before and after mutation, respectively, to obtain the sequence feature information before mutation and the sequence feature information after mutation; splicing the sequence feature information before mutation and the sequence feature information after mutation to obtain the sequence features of the multiple training samples.

[0030] In the method according to the second aspect of the present disclosure, the pre-trained model can be implemented by a combination of one or more of the following models: ESM-1b, UniRef, ProteinBert, TAPE, ProtGPT2, ProtTXL, ProtBert, ProtXLNet, ProtAlbert, ProtElectra, ProtT5-XL and ProtT5-XXL; preferably, the pre-trained model is ProtT5-XL or ProtT5-XXL; more preferably, the pre-trained model is ProtT5-XL.

[0031] In the method according to the second aspect of the present disclosure, the three-dimensional structural information of the sample protease may include the three-dimensional structural information of the sample protease obtained through at least one of the following databases or prediction software: PDB database, AlphaFold2, I-TASSER, RoseTTAFold, Modeller and Swiss-model.

[0032] In the method according to the second aspect of the present disclosure, the three-dimensional structural information of the sample protease may include an interaction network, a secondary structure, an amino acid residue distance or a physical environment. Preferably, the three-dimensional structural information of the sample protease includes an interaction network.

[0033] Preferably, the three-dimensional structural information of the sample protease can be obtained in the following manner: obtaining the coordinates of the three-dimensional structure of the sample protease; calculating the distance between the amino acid residue pairs in the three-dimensional structure of the sample protease based on the obtained coordinates of the three-dimensional structure; when the alpha carbon atom distance between two residue pairs is less than 10 angstroms, it indicates that there is an edge relationship between the nodes, which is recorded as 1, otherwise it is 0, and it itself is recorded as 0, thereby obtaining the adjacency matrix of the entire sample protease.

[0034] Correspondingly, in the method according to the second aspect of the present disclosure, the three-dimensional structural information based on the sample protease, obtaining the structural characteristics of multiple training samples may include: taking the mutation site as the center, intercepting an adjacency matrix of a specified size from the adjacency matrix of the entire sample protease as the structural characteristics of the sample protease. In some embodiments, taking the mutation site as the center, intercepting an adjacency matrix of N*N (N is an integer greater than or equal to 1) from the adjacency matrix of the entire sample protease. Intercepting the adjacency matrix of N*N from the adjacency matrix of the entire sample protease can be intercepted based on the sequences on the left and right sides of the mutation site, or can be intercepted based on the distance between the mutation site. In one embodiment, taking the mutation site as the center, selecting the amino acids in the adjacency matrix of the entire sample protease that are less than 10 angstroms away from the mutation site as the structural characteristics of the sample protease.

[0035] In the method according to the second aspect of the present disclosure, the training of the graph neural network based on the sequence features, the structural features and the mutation activity change labels to obtain a prediction model for predicting the effect of mutations on protease activity may further include: inputting the sequence features and the structural features into the graph neural network to obtain probability features about activity changes; combining the probability features of activity changes with supplementary features from other prediction methods and inputting them into a decision tree model to obtain a classification of activity changes; and adjusting the parameters of the prediction model using the mutation activity change label as the output target.

[0036] Preferably, the inputting of the sequence features and the structural features into the graph neural network to obtain the probability features about the activity change may include: inputting the sequence features and the structural features into the graph neural network; updating and outputting the features using several layers of graph network structures through matrix multiplication and aggregation operations; merging the features outputted by several layers of graph network structures respectively; compressing the features using pooling operations; classifying the features according to the activity changes according to the output layer classification function, and outputting the probability features about the activity changes. Preferably, the pooling operation may be average pooling, maximum pooling, or K-max pooling.

[0037] Preferably, the prediction model is a classifier.

[0038] Preferably, the graph neural network is a graph convolutional network or a graph attention network.

[0039] Preferably, the decision tree model is a GBDT model. More preferably, the GBDT model is implemented using the LightGBM framework.

[0040] Preferably, experimental data in a public database can be obtained as a training set. At the same time, the training set can be doubled in size by inverting the experimental data in the public database.

[0041] According to the third aspect of the present disclosure, a system for predicting the effect of mutation on protease activity is provided. The system may include: an acquisition module for acquiring sequence information and three-dimensional structure information of the protease sample to be predicted; a processing module for obtaining the activity change prediction result of the protease sample to be predicted after mutation by inputting the sequence information and three-dimensional structure information of the protease sample to be predicted. The processing module further includes the following submodules: a sequence feature submodule for extracting features based on the sequence information of the protease sample to be predicted using a pre-trained model to obtain the sequence features of the protease sample to be predicted; a structural feature submodule for obtaining the structural features of the protease sample to be predicted based on the three-dimensional structure information of the protease sample to be predicted; a model prediction submodule for predicting based on the sequence features and the structural features using a prediction model based on a graph neural network to determine the activity change prediction result of the protease sample to be predicted after mutation.

[0042] According to the third aspect of the present disclosure, the system for predicting the effect of mutation on protease activity can be implemented by a computer. Preferably, the following operations can be implemented by executing a computer program: obtaining the sequence information and three-dimensional structure information of the protease sample to be predicted; obtaining the predicted result of the activity change of the protease sample to be predicted after mutation by inputting the sequence information and three-dimensional structure information of the protease sample to be predicted, and the operation further includes the following sub-operations: based on the sequence information of the protease sample to be predicted, using a pre-trained model to perform feature extraction to obtain the sequence characteristics of the protease sample to be predicted; based on the three-dimensional structure information of the protease sample to be predicted, obtaining the structural characteristics of the protease sample to be predicted; based on the sequence characteristics and the structural characteristics, using a prediction model based on a graph neural network to perform prediction to determine the predicted result of the activity change of the protease sample to be predicted after mutation.

[0043] According to a fourth aspect of the present disclosure, a non-transient computer-readable storage medium is provided for storing a computer program. The computer program includes instructions. When the instructions are executed by a processor of an electronic device, the electronic device implements the method for predicting the effect of a mutation on protease activity according to the first aspect of the present disclosure or the method for constructing a prediction model for predicting the effect of a mutation on protease activity according to the second aspect of the present disclosure.

[0044] According to a fifth aspect of the present disclosure, a computer system is provided. The computer system comprises: a processor, a memory and a computer program. The computer program is stored in the memory and is configured to be executed by the processor. The computer program comprises instructions for implementing the method for predicting the effect of mutation on protease activity according to the first aspect of the present disclosure or the method for constructing a prediction model for predicting the effect of mutation on protease activity according to the second aspect of the present disclosure.

[0045] The above method is characterized by establishing a connection between the primary sequence and three-dimensional structure of the protease through a graph neural network, particularly a graph attention network (GraphAttentionNetwork, GAT), and then predicting the mutation effect, so it is possible to provide new insights for the annotation challenges brought by the increasing sequence and structure data. For the problems of low quality and preference of experimental data, the present disclosure extracts and screens 5449 data containing experimental mutation information from the D3DistalMutation database, and reverses the data set (see below for the specific operation description of the reversal), which means that the data set finally used for training contains 10998 mutation information, and the number of mutations causing reduced activity and increased activity is equal. The model finally obtained can not only predict mutations at any position in the specified protease sequence, but also exceed expectations in performance on the experimental test set. This method can be combined with a method for predicting protein stability after mutation to solve this negative correlation between protease stability and activity, the so-called activity-stability trade-off mechanism. It can not only improve the stability of the protease, but also solve the problem that the activity may decrease, and has a wide range of application prospects.

[0046] The beneficial technical effects of the method disclosed herein include:

[0047] 1. Highly innovative: Based on a self-constructed data set, the latest AI method is used to predict the effect of mutations on protease activity, filling a gap in this field.

[0048] 2. Superior performance: As can be seen from the comparison results between the method in the embodiments and the only SCANEER in the following text, the method disclosed in the present invention has better performance.

[0049] 3. Broad application prospects: This method can predict the effect of mutations on protease activity that cannot be predicted by the current SCANEER. The unpredictable mutations are more meaningful because the parts that SCANEER can predict have a high degree of overlap with the rationally designed methods, and the screened results are easily restricted by other patents or literature. The method disclosed in this disclosure can discover beneficial mutation sites that are difficult to discover with evolutionary information. BRIEF DESCRIPTION OF THE DRAWINGS

[0050] The present disclosure will be more fully understood from the following detailed description taken in conjunction with the accompanying drawings, in which like elements are numbered in a similar manner, and in which:

[0051] Figure 1 is a flow chart of a method for predicting the effect of a mutation on protease activity according to an embodiment of the present disclosure.

[0052] Figure 2It is a schematic diagram of the association between a method for predicting the effect of a mutation on protease activity and a method for constructing a prediction model for predicting the effect of a mutation on protease activity according to an embodiment of the present disclosure.

[0053] Figure 3 Detailed description of the invention The invention is a flowchart of a method for constructing a prediction model for predicting the effect of mutations on protease activity.

[0054] Figure 4 It is a diagram of the adjacency matrix.

[0055] Figure 5 It is a schematic diagram of forming a node feature matrix.

[0056] Figure 6 It is a schematic diagram of the construction of the structure-based adjacency matrix.

[0057] Figure 7 It is a schematic diagram of constructing a sequence-based node feature matrix.

[0058] Figure 8 It is a schematic diagram of the prediction model framework.

[0059] Fig. 9 A schematic block diagram of a system for predicting the effect of a mutation on protease activity according to the present disclosure is shown. DETAILED DESCRIPTION

[0060] Unless otherwise defined, technical and scientific terms used in the present disclosure have the same meaning as commonly understood by one of ordinary skill in the art to which the present disclosure belongs.

[0061] The technical scheme of the present disclosure is further described in detail below by way of examples and in conjunction with the accompanying drawings. Unless otherwise specified, the methods and materials of the embodiments described below are conventional products that can be purchased from the market. It will be understood by those skilled in the art that the present disclosure belongs to that the methods and materials described below are merely exemplary and should not be construed as limiting the scope of the present disclosure.

[0062] From the overall perspective of forecasting methods, Figure 1 A flow chart of a method for predicting the effect of a mutation on protease activity according to an embodiment of the present disclosure is shown.

[0063] like Figure 1 As described in, the method 100 for predicting the effect of mutation on protease activity according to an embodiment of the present disclosure starts at step S110. In this step, based on the sequence information of the protease sample to be predicted, a pre-trained model is used to perform feature extraction to obtain the sequence features of the protease sample to be predicted.

[0064] The sequence information of the protease sample to be predicted mentioned here may include the amino acid sequence information of the protease sample to be predicted before mutation and the amino acid sequence information of the protease sample to be predicted after mutation.

[0065] In another case, the sequence information of the protease sample to be predicted may also include the amino acid sequence information and the specified mutation information of the protease sample to be predicted before mutation. In this case, the amino acid sequence information of the protease sample to be predicted after mutation can be obtained according to the amino acid sequence information and the specified mutation information of the protease sample to be predicted before mutation. The specified mutation information may include a specified mutation site and / or a specified amino acid type after mutation. For example, in the case where the specified mutation information is a specified mutation site, the amino acid at the site may be changed to form the amino acid sequence information of the protease sample to be predicted after mutation. That is, in the case where the specified mutation information does not include the specified amino acid type after mutation, the amino acid sequence information after mutation may be 19 amino acid sequences in which the amino acid at the mutation site is replaced with other 19 amino acids. In the case where the specified mutation information also includes the specified amino acid type after mutation, the amino acid sequence information after mutation may be an amino acid sequence. In another case, the specified mutation information only includes the specified amino acid type after mutation but does not include the mutation site. In this case, each site of the sequence before mutation needs to be replaced with the specified amino acid type in sequence to form N sequences after mutation (N is the number of sites on the sequence). In addition, another extreme case is that the specified mutation sites are multiple sites or even all sites, or the specified amino acid types after mutation are multiple types or all other 19 types. In this case, it is necessary to traverse all mutation possibilities to form a maximum of 19*N mutated sequences. The "amino acid types" mentioned here refer to the 20 different amino acids that make up the main units of proteins in living organisms, including glycine, alanine, valine, leucine, isoleucine, methionine (methionine), proline, tryptophan, serine, tyrosine, cysteine, phenylalanine, asparagine, glutamine, threonine, aspartic acid, glutamic acid, lysine, arginine and histidine.

[0066] Those skilled in the art should understand that in subsequent steps, it is necessary to extract features of the amino acid sequences before and after mutation respectively, and finally splice them into features about the amino acid sequence. Therefore, no matter what the protease sequence information initially obtained is, when executing step S110, it is necessary to form the amino acid sequences before and after mutation.

[0067] Specifically, in step S110, the amino acid sequence information of the to-be-predicted protease sample before mutation and the amino acid sequence information after mutation are respectively subjected to feature extraction using the pre-trained model to obtain the sequence feature information before mutation and the sequence feature information after mutation. Then, still in step S110, the sequence feature information before mutation and the sequence feature information after mutation are spliced ​​to obtain the sequence feature of the to-be-predicted protease sample.

[0068] In the field of natural language processing research, with the continuous increase in computer computing power, more and more pre-trained models (PTMs) of general language representation have gradually emerged. This is very helpful for downstream pre-processing tasks. It can learn the knowledge of the language itself from massive unlabeled data, and then fine-tune on a small amount of labeled data, so that downstream tasks can better learn the characteristics of the language itself and the knowledge of specific tasks. By training on protein or nucleic acid sequence corpora, pre-trained models that can be used in the biological field can be obtained. The existing models trained on protein sequence corpora mainly include ESM-1b, UniRef, ProteinBert, TAPE, ProtGPT2, ProtTXL, ProtBert, ProtXLNet, ProtAlbert, ProtElectra, ProtT5-XL and ProtT5-XXL. Although it is also possible to obtain pre-trained models by training on protein sequence corpora, the performance of self-trained models is usually not as good as the above models due to cost and time issues.

[0069] As mentioned above, the pre-trained model is essentially a natural language model. In the biological field, a pre-trained model that is improved and optimized for the characteristics and uses of the biological field is generally used. The pre-trained model has learned biological field-related knowledge from a large amount of unlabeled sequence data in the existing protein corpus, and can be used to extract mutation-related features from the protein sequence information of the training sample; then based on the extracted mutation-related features, training is performed, and only a small amount of labeled training samples are needed to optimize the parameters of the model. For example, the pre-trained model described in the present disclosure can be implemented using a combination of one or more of the models mentioned above and listed again below: ESM-1b, UniRef, ProteinBert, TAPE, ProtGPT2, ProtTXL, ProtBert, ProtXLNet, ProtAlbert, ProtElectra, ProtT5-XL and ProtT5-XXL. Preferably, the pre-trained model can be ProtT5-XL or ProtT5-XXL. More preferably, the pre-trained model is ProtT5-XL. That is, the pre-trained model used here is preferably a T5 (ie, Transfer Text-to-Text Transformer) pre-trained model based on the latest natural language processing method.

[0070] The purpose of step S110 is to obtain the sequence characteristics of the protease sample to be predicted, while the purpose of step S120 to be described next is to obtain the structural characteristics of the protease sample to be predicted.

[0071] In step S120, the structural features of the protease sample to be predicted are obtained based on the three-dimensional structural information of the protease sample to be predicted.

[0072] In addition to obtaining relevant features through the pre-training model, relevant features can also be obtained in combination with the three-dimensional structural information of the protease for supplementary information. The three-dimensional structural information can be obtained through the PDB database (https: / / www.rcsb.org / ) (see Berman, Helen M et al. 2000. "The protein databank". Nucleic acid research 28 (1): 235-42. By citing here, the entire contents of the above-mentioned documents are incorporated into the present disclosure and become part of the contents of the present disclosure) or obtained through prediction software, such as the following prediction software (reference introduction or source in brackets):

[0073] AlphaFold2(https: / / alphafold.ebi.ac.uk / );

[0074] I-TASSER(https: / / zhanggroup.org / I-TASSER / );

[0075] RoseTTAFold (see Minkyung Baeketal. "Accurate prediction of protein structures and interactions using a three-track neural network". Science373, 871-876 (2021). DOI: 10.1126 / science.abj8754);

[0076] Modeller(https: / / salilab.org / modeller / );

[0077] Swiss-model (https: / / swissmodel.expasy.org / ) etc.

[0078] The available three-dimensional structural information of proteases usually includes secondary structure, interaction network, distance between amino acid residues, physical environment, and energy information obtained through three-dimensional structure, etc. Among them, the interaction network is one of the most commonly used features in structure-based prediction methods because it contains the contact information between all residue pairs.

[0079] According to a preferred embodiment of the present disclosure, the three-dimensional structural information used is an interaction network. More specifically, it is based on the characteristics of the interaction network that a prediction model based on a graph neural network (GNN) and its various variants is selected.

[0080] Those skilled in the art should understand that the present disclosure does not limit the order of step S110 and step S120. That is, the acquisition of sequence features and structural features can be performed in any order or simultaneously.

[0081] Finally, in step S130, based on the sequence features obtained in step S110 and the structural features obtained in step S120, a prediction model based on a graph neural network is used to perform predictions to determine the predicted results of the activity changes of the protease sample to be predicted after mutation.

[0082] The prediction model based on graph neural network is actually a classifier.

[0083] In step S130, the sequence-based features and structure-based features are placed in a classifier to predict a specific task. Classifiers are generally divided into machine learning methods and deep learning methods. Machine learning methods are generally commonly used: linear regression (LinearRegression) algorithm, support vector machine (Support Vector Machine, SVM) algorithm, nearest neighbor / k-nearest neighbor (K-Nearest Neighbors, KNN) algorithm, logistic regression (LogisticRegression, LR) algorithm, decision tree (DecisionTree) algorithm, k-means (K-Means) algorithm, random forest (RandomForest) algorithm, naive Bayes (NaiveBayes) algorithm, gradient boosting (Gradient Boosting) algorithm, ensemble (EnsembleLearning) method. Deep learning methods generally include: convolutional neural network (ConvolutionalNeuralNetwork), recurrent neural network (RecurrentNeuralNetwork), recursive neural network (RecursiveNeuralNetwork), long short-term memory network (LSTM). Graph neural network (GNN) is a deep learning model based on graph structured data, which is used to process structured data of nodes and edges. Graph Convolutional Network (GCN) is a GNN model based on Convolutional Neural Network (CNN). It achieves effective representation and learning of node features by aggregating the information of neighboring nodes. Graph Attention Network (GAT) is a GNN model based on attention mechanism. It achieves adaptive aggregation of node features by learning the attention weights of neighboring nodes, and can better handle the relationship between different nodes. GraphSAGE (Graph Sampling and Aggregation, SageConv) is a GNN model based on sampling. It achieves effective learning and representation of node features by sampling and aggregating neighboring nodes. GraphSAGE can process large-scale graph data while ensuring the efficiency and accuracy of the model. Graph Isomorphism Network (GINConv) is a GNN model based on graph isomorphism. It achieves effective learning and representation of node features by aggregating the features of neighboring nodes and combining the aggregation results with the features of the node itself.Diffusion Convolutional Neural Network (DCNN) is a GNN model based on the diffusion process. It achieves effective learning and representation of node features by diffusing and aggregating node features. These methods have their own advantages and scope of application. You can choose the appropriate method according to the specific task and data characteristics.

[0084] In a preferred embodiment of the present disclosure, the graph neural network is a graph convolutional network or a graph attention network.

[0085] In addition, in a preferred embodiment of the present disclosure, in step S130, the sequence features and the structural features can be first input into the graph neural network to obtain the probability features of the activity change; then, the probability features of the activity change are combined with the supplementary features from other prediction methods (see the detailed description below) and input into the decision tree model to finally obtain the classification of the activity change. In a more preferred embodiment, the decision tree model used is a gradient boosting decision tree model. The decision tree model is implemented using the LightGBM framework. A more detailed description of this will be given in the description of the embodiments below.

[0086] For the method of constructing the prediction model, please refer to the detailed description below.

[0087] As mentioned earlier, stability and catalytic activity are the two most important properties of proteases. Stability has been studied more, and dozens of AI-based methods have been developed to predict the impact of mutations on protease stability with excellent performance. However, catalytic activity has been limited by problems with data sets and methods and has stagnated to date. Only the SCANEER method can predict the impact of single-point mutations on protease activity. However, this method can only predict mutations that have occurred in evolution based on co-evolution information, which has many limitations and cannot be widely used.

[0088] The difference between the technology provided by the present disclosure and the above-mentioned prior art is that the technology of the present disclosure introduces a graph neural network, particularly a graph convolutional network or a graph attention network, into the prediction of the activity change after the protease mutation, and is combined with a mature protein natural language model (pre-training model) in the prior art to jointly act on the determination of the prediction result. In other words, the sequence characteristics (obtained according to the primary sequence) of the protease sample to be predicted are combined with the structural characteristics (obtained according to the three-dimensional structure) and jointly serve as the input of the prediction model based on the graph neural network, thereby outputting the prediction result of the activity change after the protease mutation. The prediction result determined in this way is better than the prediction result determined by the method of the prior art.

[0089] Figure 2A schematic diagram 200 is provided showing the association between a method for predicting the effect of a mutation on protease activity and a method for constructing a prediction model for predicting the effect of a mutation on protease activity according to an embodiment of the present disclosure. Figure 2 In the schematic diagram 200 shown, the left side of the dotted line shows a method for constructing a prediction model based on a graph neural network, while the right side of the dotted line shows a method for performing predictions using a prediction model based on a graph neural network.

[0090] Figure 2 The process on the right side of the dotted line is actually Figure 1 The method for predicting the effect of a mutation on protease activity according to an embodiment of the present disclosure is shown. Figure 2 The process on the left side of the dashed line will be described in detail below (for example Figure 3 and its corresponding text description). Figure 2 It can be seen that both model construction and the actual prediction process require the use of two feature extraction steps, namely: the extraction of sequence features and structural features. For the training sample, it includes the three-dimensional structural information of the sample protease, the amino acid sequence information of the sample protease before and after mutation, and also includes the mutation activity change label. As described later, the mutation activity change label can be that the protease activity becomes stronger or weaker (increases or decreases). Therefore, in the model construction process, the sequence information in the training sample is used to extract sequence features. Structural features are extracted through three-dimensional structural information. The GNN-based prediction model, i.e., the classifier, is fully trained using sequence features and structural features as input data and mutation activity change labels in the training samples as output data, thereby obtaining the final GNN-based prediction model for predicting the effect of mutations on protease activity. For the constructed prediction model, it can be put into the actual work of predicting protease mutation activity changes, i.e. Figure 2 The process on the right side of the dotted line. In addition, it should be noted that Figure 2 In the figure, for sequence information and sequence features, hollow arrows are used to represent their signal transmission process; for three-dimensional structure information and structure features, different solid arrows are used to represent their signal transmission process; in addition, other signal flows and control flows are also represented by solid arrows.

[0091] The following is a detailed description of the process of the method for constructing a prediction model for predicting the effect of mutations on protease activity according to an embodiment of the present disclosure.

[0092] Figure 3 is a flow chart of a method 300 for constructing a prediction model for predicting the effect of a mutation on protease activity used in the present disclosure.

[0093] Those skilled in the art should know that Figure 3As shown in , in step S310, a training set should first be obtained, and the training set includes information of multiple training samples. Specifically, the information of each training sample includes the three-dimensional structure information of the sample protease, the amino acid sequence information of the sample protease before and after mutation, and the mutation activity change label.

[0094] Artificial intelligence (AI) algorithms rely heavily on data. The quantity and quality of the initial data determine the generalization performance of the trained model, which is most directly reflected in the prediction accuracy of the model. Insufficient sample quantity or low quality of the data set will lead to overfitting or underfitting problems in the model. To solve this problem, the most effective way is to obtain more experimental data as a training set. The main source of experimental data is public databases. For the task of predicting the effect of mutations on the catalytic activity of proteases based on sequence-based methods, the data set can be inverted to twice its original size by inverting the data in the database. Inversion means that under the same environmental conditions, opposite mutations at the same position have opposite active effects. According to the above definition, the original data can be merged with the inverted data to double the original data volume. By inverting this method, the original data set is expanded and balanced at the same time, making the final prediction model more robust.

[0095] It should be noted that this method of expanding the dataset by reversing the original dataset is only implemented for the training set.

[0096] In the specific embodiments below, the acquisition of the training data set will be described in more detail.

[0097] The mutation activity change label can be used to reflect the influence trend of amino acid mutation on the catalytic activity of protease. For example, the mutation activity change label can be that the catalytic activity becomes stronger or weaker (activity increases or decreases). More specifically, the description about constructing the training data set in the specific embodiments below can be referred to. It is understandable that using the mutation activity change information as the label of the training sample, the prediction model obtained by training can output the prediction result about the influence of amino acid mutation on the catalytic activity of protease. Preferably, the protease mutation mentioned in the present application can be a single point mutation of the protease amino acid sequence.

[0098] In step S320, based on the amino acid sequence information of the sample protease before and after mutation, feature extraction is performed through a pre-training model to obtain sequence features of the multiple training samples.

[0099] Specifically, in step S320, the amino acid sequence information of the sample protease before and after mutation is respectively subjected to feature extraction using the pre-training model to obtain sequence feature information before mutation and sequence feature information after mutation. Then, still in step S320, the sequence feature information before mutation and the sequence feature information after mutation are spliced ​​to obtain the sequence features of the plurality of training samples.

[0100] As mentioned above, the pre-trained model is implemented by a combination of one or more of the following models: ESM-1b, UniRef, ProteinBert, TAPE, ProtGPT2, ProtTXL, ProtBert, ProtXLNet, ProtAlbert, ProtElectra, ProtT5-XL and ProtT5-XXL. Preferably, the pre-trained model is ProtT5-XL or ProtT5-XXL. More preferably, the pre-trained model is ProtT5-XL. That is, the pre-trained model used here is preferably a T5 (i.e., TransferText-to-TextTransformer) pre-trained model based on the latest natural language processing method.

[0101] The purpose of step S320 is to obtain the sequence characteristics of the training sample, while the purpose of step S330 to be described next is to obtain the structural characteristics of the training sample.

[0102] In step S330, structural features of a plurality of training samples are obtained based on the three-dimensional structural information of the sample protease.

[0103] As mentioned above, the three-dimensional structure information of the sample protease can be obtained through at least one of the following databases or prediction software: PDB database, AlphaFold2, I-TASSER, RoseTTAFold, Modeller and Swiss-model, etc.

[0104] The available three-dimensional structural information of proteases usually includes secondary structure, interaction network, distance between amino acid residues, physical environment, and energy information obtained through three-dimensional structure, etc. Among them, the interaction network is one of the most commonly used features in structure-based prediction methods because it contains the contact information between all residue pairs.

[0105] According to a preferred embodiment of the present disclosure, the three-dimensional structural information used here is an interaction network. More specifically, it is based on the characteristics of the interaction network that the GNN-based prediction model is selected.

[0106] Those skilled in the art should understand that the present disclosure does not limit the order of step S320 and step S330. That is, the acquisition of sequence features and structural features can be performed in any order or simultaneously.

[0107] In step S340, based on the sequence features, the structural features and the mutation activity change labels, a graph neural network is trained to obtain a prediction model for predicting the effect of mutations on protease activity.

[0108] As mentioned earlier, this prediction model is actually a classifier.

[0109] In a preferred embodiment of the present disclosure, the graph neural network is a graph convolutional network (GCN) or a graph attention network (GAT).

[0110] For the method of constructing the prediction model, please refer to the detailed description in the embodiments below.

[0111] In addition, it should be noted that: for sequence features, by placing the processed protease activity change data set into the pre-trained model, the pre-trained model can be migrated to the new task through transfer learning. In transfer learning, there are two commonly used application methods: feature extraction and fine-tuning. In feature extraction, after the network structure is pre-trained, a simple classifier can be modified or added, and the pre-trained network on the original task can be used as a feature extractor for another target task. Only the last added classifier parameters are re-learned, and the pre-trained network parameters will not be modified or frozen. The preferred embodiment of the present disclosure adopts a transfer learning method of feature extraction.

[0112] In the model training process, sequence features and structural features are used as input data of the prediction model, and mutation activity change labels are used as output targets of the prediction model to fully train the prediction model. As the parameters of the prediction model are continuously optimized, the output data of the prediction model will be consistent with the prediction results represented by the mutation activity change labels.

[0113] In a preferred embodiment of the present disclosure, step S340 may further include: inputting sequence features and structural features into a graph neural network to obtain probability features about activity changes; then, combining the probability features of activity changes with supplementary features from other prediction methods, and inputting them into a decision tree model to obtain a classification of activity changes; and adjusting the parameters of the prediction model using the mutation activity change label as the output target.

[0114] More specifically, in some embodiments of the present disclosure, the prediction model (classifier) ​​can be supervised trained based on the sequence features, structural features and mutation activity change labels of multiple training samples to obtain the trained classifier. Supervised training is the process of adjusting the parameters of the classifier using a set of samples of known categories to achieve the required performance. In some embodiments, a loss function can be constructed, such as a cross entropy loss function, which reflects the difference between the predicted result of the catalytic activity change after the protease mutation predicted by the classifier and the actual mutation activity change label of the training sample, and then the parameters of the classifier are adjusted according to the difference to obtain the model optimization parameters of the classifier. When the loss function meets the predetermined conditions, such as the loss function converges, or the loss function value is less than the preset value, or the training set and the test set loss function values ​​are simultaneously reduced to the lowest point or the training set loss function value reaches the lowest point, the classifier training is completed. In some embodiments, the parameter search algorithm can be used to adjust the classifier parameters, for example, a search algorithm, such as a grid search, a Bayesian search, etc. In some embodiments, supervised training is the process of training the prediction model according to the mutation activity change label.

[0115] It will be understood by those skilled in the art that by, for example Figure 3 The prediction model obtained by this method can be used Figure 1 The prediction method shown in .

[0116] Specific example embodiments will be given below.

[0117] Examples Methods and Materials

[0118] 1. Training Dataset

[0119] In order to overcome the problems caused by poor data quality, 5449 experimental samples containing activity change information were screened out from the D3 Distal Mutation database published in 2021 (see Wang, Xiaoyu et al. 2021. "D3 Distal Mutation: a database to explore the effect of distal mutation on enzyme activity". Journal of Chemical Information and Modeling 61 (5): 2499-2508. The entire contents of the above document are incorporated into the present disclosure by reference and become part of the content of the present disclosure). Among them, 5279 samples have mutations that reduce activity and 220 samples have mutations that increase activity. The specific screening criteria are as follows:

[0120] (1) Remove all multi-point mutation samples and limit the training data set to a single-point mutation data set;

[0121] (2) neutral mutations (mutations that have no effect on protease activity) were removed, and mutations that reduced or lost activity were uniformly defined as mutations that reduced activity;

[0122] (3) Remove samples with different labels for the same mutation. The reason for removing samples with different labels is that samples with different labels for the same mutation may be caused by different experimental conditions or experimental errors. This makes it difficult to define labels for such data. If such samples are not removed, they may introduce noise to the model and affect its accuracy.

[0123] (4) Reverse and merge the data.

[0124] Finally, the dataset used to train the model contains 10,898 samples.

[0125] 2. Test Dataset

[0126] The test data comes from the BRENDA database (https: / / brenda-enzymes.org / news.php?) (see Chang, Antje et al. 2021. "BRENDA, the ELIXIR core data resource in 2021: new developments and updates". Nucleic acids research 49(D1): D498–508. By citation, the entire contents of the above documents are incorporated into the present disclosure to become part of the content of the present disclosure), literature (for example, see Amorosi, Clara J et al. 2021. "Massively parallel characterization of CYP2C9 variant enzyme activity and abundance". The American Journal of Human Genetics 108(9): 1735–51, Cheng, Ya-Shan et al. 2015. "Improving the catalytic performance of aGH11 xylanase by rational protein engineering". Applied microbiology and biotechnology 99:9503–10, You, Chun, Hanying Yuan, Qiang Huang and Hong Lu. 2010. “Substrate molecule enhances the thermostability of a mutant of a family 11xylanase from Neocallimastix patriciarum”. African Journal of Biotechnology 9 (9). The entire contents of the above documents are hereby incorporated into the present disclosure by reference, making them part of the contents of the present disclosure) and patents (WO2020234200A1; EP3854872A1; WO2018195850; WO2017109262A1). The screening criteria are as follows:

[0127] (1) Remove non-single point mutation samples and limit the test data set to single point mutation data sets;

[0128] (2) neutral mutation samples were removed and mutations with reduced activity or loss of activity were uniformly defined as mutations that reduced activity;

[0129] (3) Remove samples with multiple labels. Samples with multiple labels mean that the protease activity reported at the same mutation site has different activities. In this case, the sample with the mutation needs to be deleted to ensure the accuracy of the data;

[0130] (4) Remove samples that are repeated in the training set.

[0131] Finally, the data set used to test the model effect contained 6103 samples, of which 4950 and 1153 were mutation samples that reduced activity and increased activity, respectively.

[0132] 2.1S3459

[0133] Due to algorithmic limitations, SCANEER can only predict mutations that have occurred in evolution. Among the 6103 data in the test set, 3459 samples can be predicted by SCANEER, of which 1797 samples are from DMS (Deep Mutational Scanning). DMS introduces random mutations into the gene of a protein, and then evaluates the effects of these mutations on protein function through methods such as pressure screening or high-throughput sequencing. The remaining 1662 samples are non-DMS data.

[0134] 2.2S2644

[0135] Among all the test data, there are 2644 samples where SCANEER cannot predict mutations. As in 2.1, this part of the data is also divided into DMS data and non-DMS data, with sample sizes of 1492 and 1152 respectively.

[0136] 3. Pre-trained Model

[0137] The ProtT5-XL (ProtT5-XL-U50 / ProtT5-XL-UniRef50) model used in this method was released by Ahmed Elnaggar et al. in 2021. The T5 model was first trained on the BFD dataset, and then the model was fine-tuned and optimized using the UniRef50 dataset to obtain a pre-trained protein model. The model contains 24 layers of attention structure, each layer consisting of 32 self-attention heads and 1024 neurons. See Elnaggar, Ahmed et al. 2021. "Prottrans: Toward understanding the language of life through self-supervised learning". IEEE transactions on pattern analysis and machine intelligence 44 (10): 7112–27. By reference, the entire contents of the above-mentioned documents are incorporated into the present disclosure and become part of the contents of the present disclosure.

[0138] 4. Graph Convolutional Neural Network Model Construction

[0139] This preferred embodiment is based on a variant of the graph convolutional network (GCN): the graph attention network (Graph Attention Network, GAT) (see Petar et al. 2017. “Graph attention networks”. arXiv preprint arXiv:1710.10903. The entire contents of the above document are hereby incorporated into the present disclosure by reference, making it a part of the contents of the present disclosure).

[0140] 4.1 GAT-1 model construction

[0141] 4.1.1 Adjacency Matrix

[0142] The three-dimensional structure of each protease was obtained through prediction software such as PDB database, AlphaFold2, I-TASSER, RoseTTAFold, Modeller and Swiss-model. The distance between the amino acid residue pairs in the three-dimensional structure of the protease was calculated according to the coordinates of the obtained three-dimensional structure of the protease. When the alpha carbon atom distance between two residue pairs is less than 10 angstroms, it indicates that there is an edge relationship between the nodes, which is recorded as 1, otherwise it is 0 (itself is 0), which is the adjacency matrix of the entire protease.

[0143] In this embodiment, 10 amino acids are taken on each side of the mutation site, that is, 10 consecutive amino acids are taken as the residue sequence, and a 21*21 adjacency matrix is ​​intercepted from the adjacency matrix of the entire protease.

[0144] Figure 4 It is a schematic diagram of the adjacency matrix. As shown in the figure, the adjacency matrix of 100 amino acids in length, where the mutation site is assumed to be residue 12, then the box is the 21*21 adjacency matrix of the residue. The McBASC Covariance algorithm (see McLachlan, Andrew D. 1971. "Tests for comparing related amino-acid sequences. Cytochrome c and cytochrome c551". Journal of molecular biology 61 (2): 409–24. By citing here, the entire contents of the above document are incorporated into the present disclosure to make it a part of the contents of the present disclosure) is used to calculate the coevolution scores between the corresponding 21 amino acids in the adjacency matrix, forming a 21*21 coevolution score matrix, which is multiplied with the adjacency matrix to obtain an updated 21*21 adjacency matrix.

[0145] 4.1.2 Node feature matrix

[0146] After a protease sequence information is input into the pre-trained model, the model first encodes each amino acid in the protease sequence through an encoder. Each amino acid will correspond to a vector of length 1024 after encoding, that is, a protease sequence of length N will obtain a vector of length N*1024. The model has a 24-layer structure. In order to obtain the most information about the mutation, the last layer can be selected as the output, and the 1024-dimensional feature vectors corresponding to the mutation positions of the wild type and mutant types are extracted respectively. The feature vectors of the wild type (i.e. before mutation) and the mutant type (i.e. after mutation) are spliced ​​into 2048 dimensions in sequence. With 21 as the sliding window size and the mutation site as the center, the 10 amino acid residues before and after are spliced, and finally a 21*2048-dimensional feature is obtained as the node feature matrix. The structure is as follows: Figure 5 shown.

[0147] 4.1.3 Model Construction

[0148] The matrices generated in 4.1.1 and 4.1.2 are input into the graph convolutional neural network as structural features and sequence features respectively. Through matrix multiplication and aggregation operations, the node features of the three-layer graph network structure are updated to 32, 64 and 64-dimensional feature vectors respectively. Four attention heads are used in each layer. The node features output by the three-layer graph network are merged into a 21*640-dimensional feature vector through the residual network structure. Then the average pooling operation is used to compress the updated feature matrix into a 1*640-dimensional feature vector to represent the feature representation of the 21 amino acid residue sequences. The specific parameters are: the output dimensions of the three-layer graph convolution are 32, 64, and 64 respectively; the number of neurons in the fully connected layer is 64 and 2; the optimizer uses Adam; the loss function is binary cross entropy loss; 'relu' is used as the activation function; 'softmax' is used as the output layer classification function; the l2 regularization term coefficient is 0.05, the dropout rate is 0.3; and the learning rate is 0.001.

[0149] The aggregation operation mentioned here is implemented through the attention mechanism, in which each node has an attention weight distribution. The feature matrix and the attention coefficient are weighted and summed to obtain the node's aggregated feature vector. Through such an aggregation operation, each node can use the feature information of its neighboring nodes to update features and transfer information.

[0150] The residual network mentioned here is a deep convolutional neural network structure that constructs jump connections between network layers by introducing residual connections. That is, the input of each network layer is not only the output of the previous layer, but also includes a directly connected jump connection. This jump connection adds the input directly to the output to form a residual. Its purpose is to solve the problem of gradient disappearance and network difficulty in training deep networks.

[0151] The average pooling operation mentioned here is a commonly used technique to reduce the feature dimension of the convolutional layer output. It is achieved by averaging the features output by the convolutional layer. Its purpose is to effectively reduce network parameters and prevent overfitting. Those skilled in the art should understand that the average pooling operation here can also be replaced by any pooling operation such as maximum pooling or K-max pooling.

[0152] 4.2 GAT-2 model construction

[0153] Directly use the matrices generated in 4.1.1 and 4.1.2 to input the graph convolutional neural network. Through matrix multiplication and aggregation operations, each layer of the three-layer graph network structure updates the node features into a 128-dimensional feature vector. Each layer uses 4 attention heads, and the node features output by the three-layer graph network are merged into a 21*1536-dimensional feature vector through the residual network structure. Then the average pooling operation is used to compress the updated feature matrix into a 1*1536-dimensional feature vector to represent the feature representation of the 21 amino acid residue sequences. The specific parameters are: the output dimensions of the three-layer graph convolution are 128, 128, and 128 respectively; the number of neurons in the fully connected layer is 64 and 2; the optimizer uses Adam; the loss function is binary cross entropy loss; 'relu' is used as the activation function; 'softmax' is used as the output layer classification function; the l2 regularization term coefficient is 0.01, the dropout rate is 0.5; and the learning rate is 0.001.

[0154] 4.3 GAT-3 model construction

[0155] 4.3.1 First-order adjacency matrix

[0156] First, the adjacency matrix of the entire protease is obtained according to 4.1.1. Then, taking the mutation site residue as the center, all amino acids whose spatial distance from the mutation site is less than 10 angstroms are selected, and the adjacency matrix composed of these amino acids is calculated.

[0157] 4.3.2 Node feature matrix

[0158] After a protease sequence information is input into the pre-trained model, the model first encodes each amino acid in the protease sequence through an encoder. Each amino acid is encoded to correspond to a vector of length 1024, that is, a protease sequence of length N will obtain a vector of length N*1024. The model has a 24-layer structure. In order to obtain the information about the mutation to the greatest extent, this embodiment selects the last layer as the output, and simultaneously extracts the 1024-dimensional feature vectors of the wild type and mutant corresponding to the mutation position, and splices the feature vectors of the wild type and mutant into 2048 dimensions in sequence, and finally obtains N f *2048-dimensional features as node feature matrix, where N f is the number of corresponding amino acids obtained from 4.3.1. The order is the same. The number of amino acids obtained from different proteases may be different. The maximum N f As a benchmark, fill in the missing 0 so that all proteases can obtain a matrix of the same size.

[0159] 4.3.3 Model Construction

[0160] The matrices generated in 4.3.1 and 4.3.2 are input into the graph convolutional neural network as structural features and sequence features respectively. Through matrix multiplication and aggregation operations, the two-layer graph network structure updates the node features into 128- and 256-dimensional feature vectors respectively. Four attention heads are used in each layer, and the node features output by the two-layer graph network are merged into N through the residual network structure. f *1536-dimensional feature vector. Then the average pooling operation is used to compress the updated feature matrix into a 1*1536-dimensional feature vector represented as N f The specific parameters are as follows: the output dimensions of the two-layer graph convolution are 128 and 256 respectively; the number of neurons in the fully connected layer is 128 and 2; the optimizer is Adam; the loss function is binary cross entropy loss; 'relu' is used as the activation function; 'softmax' is used as the classification function of the output layer; the l2 regularization coefficient is 0.05, the dropout rate is 0.3; and the learning rate is 0.001.

[0161] 5. LightGBM model construction

[0162] Gradient Boosting Decision Tree (GBDT) (see Friedman, Jerome H. 2001. "Greedy function approximation: a gradient boosting machine". Annals of statistics: 1189–1232. By reference, the entire contents of the above document are incorporated into the present disclosure and become part of the content of the present disclosure) is a commonly used model in machine learning. Its main idea is to use weak classifiers (decision trees) for iterative training to obtain the optimal model. LightGBM (Light Gradient Boosting Machine, or LGBM for short) is a framework for implementing the GBDT algorithm (see Ke, Guolin et al. 2017. "Lightgbm: A highly efficient gradient boosting decision tree". Advances in neural information processing systems 30. By reference, the entire contents of the above document are incorporated into the present disclosure and become part of the content of the present disclosure). The LightGBM used in the method of the present disclosure is version 3.3.3.

[0163] 5.1LGBM-1 model construction

[0164] 5.1.1 Feature extraction

[0165] The probability value (representing the probability of increased protease activity) obtained from the GAT-1 model constructed in 4.1 is used as a one-dimensional feature, and the feature extraction described by the PremPS (see Chen, Yuting et al. 2020. "PremPS: Predicting the impact of missense mutations on protein stability". PLoS computational biology 16 (12): e1008543. By citing here, the entire content of the above document is incorporated into the present disclosure and becomes part of the content of the present disclosure) and SCANEER (as described above) method is used to supplement the feature 11 dimension, and a total of 12 dimensions of features are obtained after splicing. Among them, 10 dimensions are supplemented by PremPS and 1 dimension is supplemented by SCANEER.

[0166] 5.1.2 Model Construction

[0167] The obtained 12-dimensional features are input into the LightGBM framework for training, the learning rate is set to 0.05, extra_trees is set to True, and other parameters use the default values.

[0168] 5.2LGBM-2 model construction

[0169] 5.2.1 Feature extraction

[0170] Same as 5.1.1, the probability values ​​(representing the probability of increased protease activity) are obtained from the GAT-2 and GAT-3 models constructed in 4.2 and 4.3 as two-dimensional features, and the feature extraction described by the PremPS and SCANEER methods is used to supplement the 11-dimensional features, and a total of 13-dimensional features are obtained after splicing.

[0171] 5.2.2 Model Construction

[0172] The obtained 13-dimensional features are input into the LightGBM framework for training, the learning rate is set to 0.05, extra_trees is set to True, and other parameters use the default values.

[0173] Some summary is given below.

[0174] Figure 6 A schematic diagram showing the structure-based adjacency matrix construction. Figure 7 A schematic diagram showing the construction of a sequence-based node feature matrix. Figure 8 A schematic diagram of the prediction model framework is shown.

[0175] According to the above embodiments, it can be seen that in the process of constructing a prediction model, the three-dimensional structural information of the sample protease can be obtained in the following manner: obtaining the coordinates of the three-dimensional structure of the sample protease; calculating the distance between the amino acid residue pairs in the three-dimensional structure of the sample protease according to the coordinates of the obtained three-dimensional structure; when the alpha carbon atom distance between the two residue pairs is less than 10 angstroms, it indicates that there is an edge relationship between the nodes, which is recorded as 1, otherwise it is 0, and it is recorded as 0 itself, and the adjacency matrix of the entire sample protease is obtained. Based on the three-dimensional structural information of the sample protease, obtaining the structural features of multiple training samples may include: taking the mutation site as the center, intercepting the adjacency matrix of a specified size from the adjacency matrix of the entire sample protease as the structural feature of the sample protease. Based on sequence features, structural features and mutation activity change labels, the graph neural network is trained, and obtaining a prediction model for predicting the effect of mutation on protease activity may further include: inputting the sequence features and the structural features into the graph neural network to obtain probability features about activity changes; combining the probability features of the activity changes with the supplementary features from other prediction methods, and inputting them into the decision tree model to obtain classification about activity changes; taking the mutation activity change label as the output target, adjusting the parameters of the prediction model. The step of inputting the sequence features and the structural features into the graph neural network to obtain the probability features about the activity change may further include: inputting the sequence features and the structural features into the graph neural network; updating and outputting the features using several layers of graph network structures through matrix multiplication and aggregation operations; merging the features outputted by several layers of graph network structures respectively; compressing the features using pooling operations; classifying the features for activity changes according to the output layer classification function, and outputting the probability features about the activity change. The pooling operation mentioned here may be average pooling, maximum pooling, or K-max pooling.

[0176] Accordingly, in the process of applying the prediction model to the prediction of activity change after protease mutation, the three-dimensional structural information of the protease sample to be predicted is obtained in the following manner: obtaining the coordinates of the three-dimensional structure of the protease sample to be predicted; calculating the distance between the amino acid residue pairs in the three-dimensional structure of the protease according to the coordinates of the obtained three-dimensional structure; when the alpha carbon atom distance between the two residue pairs is less than 10 angstroms, it indicates that there is an edge relationship between the nodes, which is recorded as 1, otherwise it is 0, and it is recorded as 0 itself, and the adjacency matrix of the entire protease sample to be predicted is obtained. Based on the three-dimensional structural information of the protease sample to be predicted, obtaining the structural features of the protease sample to be predicted includes: taking the mutation site as the center, intercepting an adjacency matrix of a specified size from the adjacency matrix of the entire protease sample to be predicted as the structural features of the protease sample to be predicted. Based on the sequence features and the structural features, using the prediction model based on the graph neural network for prediction, determining the prediction result of the activity change of the protease sample to be predicted after mutation can further include: inputting the sequence features and the structural features into the graph neural network to obtain the probability features of the activity change; combining the probability features of the activity change with the supplementary features from other prediction methods, and inputting them into the decision tree model to obtain the classification of the activity change. More specifically, the step of inputting the sequence features and the structural features into the graph neural network to obtain the probability features of activity changes includes: inputting the sequence features and the structural features into the graph neural network; updating and outputting the features using several layers of graph network structures through matrix multiplication and aggregation operations; merging the features outputted by several layers of graph network structures; compressing the features using pooling operations; classifying the features according to activity changes according to the output layer classification function, and outputting the probability features of activity changes. Similarly, the pooling operation mentioned here can be average pooling, maximum pooling, or K-max pooling.

[0177] 6. Performance indicators

[0178] This example uses the following indicators for evaluation, namely, area under the curve (AUC), precision, and recall. The specific definitions are as follows:

[0179] True Positive (TP)

[0180] False Positive (FP)

[0181] True Negative (TN)

[0182] False Negative (FN)

[0183] Among them, TP (True Positive) and TN (True Negative) represent the number of correctly classified positive samples and negative samples, FP (False Positive) and FN (False Negative) represent the number of incorrectly classified positive samples and negative samples, and P and N represent the number of positive samples and negative samples.

[0184] AUC is a popular parameter-independent metric used to describe binary classifiers. AUC is the area under the receiver operating characteristic (ROC) curve. The larger the value, the better the classifier performance, and the maximum value is 1.

[0185] Precision refers to the proportion of correctly predicted results among all the results predicted as positive samples. The precision calculation formula is: precision = TP / (TP+FP), where TP (True Positive) is the positive sample judged to be correctly classified, and FP (False Positive) is the positive sample judged to be incorrectly classified.

[0186] Recall refers to the ratio of the number of correctly predicted positive samples to the total number of positive samples. The calculation formula for recall is: recall = TP / (TP+FN), where FN (False Negative) is the negative sample that is judged to be misclassified.

[0187] Results Evaluation

[0188] 1. Model Performance

[0189] The model was trained on a self-designed balanced dataset containing the effects of 10,898 single-point mutations on enzyme activity of 1,303 proteases from the D3DistalMutation database. In a five-fold cross validation, the performance of the model on the test data is shown in Table 1 below.

[0190] Evaluation indicators Accuracy Recall AUC LGBM-1 0.96 0.93 0.97 LGBM-2 0.95 0.96 0.99

[0191] Table 1: Five-fold cross-validation performance indicators of the prediction model disclosed in the present invention on the training set

[0192] 2. Comparison with other methods

[0193] In order to evaluate the difference between the method disclosed in the present invention and the SCANEER method, the model disclosed in the present invention was compared with the only prediction method SCANEER. SCANEER evaluates the co-evolutionary relationship of amino acid pairs in multiple sequence alignments (MSA). Amino acid pairs that are not observed or rarely observed in MSA, i.e., amino acid substitutions, cannot be predicted, which ultimately results in the number of mutations that can be predicted for each protease accounting for only 47% of all possible mutations (the authors of SCANEER assume that amino acid substitutions that are not observed or rarely observed in MSA will lead to loss of protease function and have been eliminated during the evolution process. Therefore, the authors exclude positions with a gap of more than 20% or that are not in the top N co-evolved amino acid pairs. That is, in MSA, positions with a gap of more than 20% or that are completely conserved, and amino acids that are not in the top N co-evolved amino acid pairs, cannot calculate their mutation effects (N = protease length * 2)), which will greatly limit the scope of application of this method. Therefore, among the 6103 samples in the experimental test set, SCANEER can predict 3459 samples, of which 2855 and 604 are mutation samples that reduce activity and increase activity, respectively. Among the 3459 samples, the number of DMS and non-DMS data samples is 1797 and 1662, respectively. The comparison results are shown in Table 2 below.

[0194]

[0195] Table 2: Performance comparison of the disclosed model and the SCANEER method on comparable experimental test sets

[0196] It can be seen from the above table that on S3459 and S1662, the method disclosed in the present invention is slightly better than or basically equal to SCANEER in terms of precision and recall, while on S1797, it has a great advantage in precision.

[0197] The S2644 dataset is data that SCANEER cannot predict, in which 2095 and 549 mutation samples that reduce activity and increase activity are respectively. In this part of the data, the sample sizes of DMS data and non-DMS data are respectively 1492 and 1152. The performance of the method disclosed in the present invention on this part of the dataset is shown in Table 3 below.

[0198]

[0199] Table 3: Performance of the disclosed model on experimental test data that SCANEER cannot predict

[0200] The results show that the method disclosed herein can still achieve good performance on experimental test data that cannot be predicted by SCANEER, which shows the advantages of the method disclosed herein.

[0201] Prediction Process

[0202] Here, two cases are taken as examples to describe the process of using a prediction model to predict changes in protease activity.

[0203] One case is that the input protease sequence information includes a single protease sequence and mutation site information. First, according to the input single protease sequence and mutation site information, the protease mutation site preprocessing is performed. Specifically, the input protease sequence is recorded as the original sequence, and the mutated sequence is obtained according to the mutation site information. Then, the amino acid embedding layer extraction is performed, which is the extraction of sequence information mentioned above. That is, the original sequence is input into the natural language processing T5 pre-training model to read the embedded features; the mutated protease sequence is input into the natural language processing T5 pre-training model to read the embedded features; the amino acid embedding features are extracted according to the mutation site, and the features before and after the mutation are spliced ​​as the input of the subsequent model. Next is the construction of the graph network, which requires the protease embedding layer feature network and the protease residue interaction feature network. The above feature network is applied to the GAT-based prediction model to predict the probability of protease activity change before and after amino acid mutation. Then, based on the probability of protease activity change, LightGMB is used to predict the protease activity change before and after amino acid mutation. Finally, the prediction results are output and displayed. For this example, the single point mutation prediction result can be output.

[0204] Another situation is that the input protease sequence information only includes a single protease sequence. First, according to the input single protease sequence, the protease mutation site preprocessing is performed. Specifically, the input protease sequence is recorded as the original sequence, and each site amino acid of the protease sequence is mutated to other 19 amino acids in turn as the mutated sequence. Then, the amino acid embedding layer is extracted, which is the extraction of sequence information mentioned above. That is, the original sequence is input into the natural language processing T5 pre-training model to read the embedded features; the mutated protease sequence is input into the natural language processing T5 pre-training model to read the embedded features; the amino acid embedding features are extracted according to the mutation site, and the features before and after the mutation are spliced ​​as the input of the subsequent model. Next is the construction of the graph neural network, which requires the protease embedding layer feature network and the protease residue interaction feature network. The above feature network is applied to the GAT-based prediction model to predict the probability of protease activity change before and after amino acid mutation. Then, based on the probability of protease activity change, LightGMB is used to predict the protease activity change before and after amino acid mutation. Finally, the prediction results are output and displayed. For this example case, a table of all mutation probabilities that improve enzyme activity and / or a ranking of all mutation possibilities that improve enzyme activity may be output as the final prediction result.

[0205] in conclusion

[0206] Protease mutants with higher activity are necessary for academia and industry to find more applications for these proteases. The present disclosure proposes a new method for discovering the effect of amino acid mutations on protease activity. The method of the present disclosure is based on advanced natural language processing models and graph neural network models, combined with sequence and three-dimensional structure, can be applied to different biological fields, and shows better performance than other methods, proving the broad application prospects of the method of the present disclosure in protease engineering.

[0207] The reasons why the method disclosed in the present invention is superior to the prior art are discussed below. From the above description, it can be seen that:

[0208] 1. In general, the method disclosed in the present invention is based on the tertiary structure and amino acid sequence information of the protease, and a prediction model is constructed through AI training.

[0209] 2. The prediction model constructed in the present disclosure can be applied to predict the activity of protease mutations.

[0210] 3. After the training data set used in the method disclosed in the present invention is inverted, the original data set is expanded and the data set is balanced at the same time, making the final prediction model more robust.

[0211] Those skilled in the art will appreciate that, based on the method for predicting the effect of a mutation on protease activity disclosed herein, a system for predicting the effect of a mutation on protease activity can be developed. Fig. 9 A schematic block diagram of a system for predicting the effect of mutations on protease activity according to the present disclosure is shown. Specifically, the system 900 for predicting the effect of mutations on protease activity includes an acquisition module 910 and a processing module 920 .

[0212] The acquisition module 910 is used to acquire the sequence information and three-dimensional structure information of the protease sample to be predicted.

[0213] The processing module 920 is used to obtain the activity change prediction result of the protease sample to be predicted after mutation by inputting the sequence information and three-dimensional structure information of the protease sample to be predicted. Fig. 9 As shown in, the processing module 920 may further include: a sequence feature submodule 921, which is used to extract features based on the sequence information of the protease sample to be predicted using a pre-trained model to obtain the sequence features of the protease sample to be predicted; a structural feature submodule 922, which is used to obtain the structural features of the protease sample to be predicted based on the three-dimensional structural information of the protease sample to be predicted; a model prediction submodule 923, which is used to predict based on the sequence features and the structural features using a prediction model based on a graph neural network to determine the predicted result of the activity change of the protease sample to be predicted after mutation.

[0214] Those skilled in the art should understand that the above-mentioned system for predicting the effect of mutation on protease activity can be implemented by a computer. For example, the following operations can be implemented by executing a computer program: obtaining the sequence information and three-dimensional structure information of the protease sample to be predicted; by inputting the sequence information and three-dimensional structure information of the protease sample to be predicted, obtaining the predicted result of the activity change of the protease sample to be predicted after mutation, and the operation further includes the following sub-operations: based on the sequence information of the protease sample to be predicted, using a pre-trained model to extract features, and obtaining the sequence features of the protease sample to be predicted; based on the three-dimensional structure information of the protease sample to be predicted, obtaining the structural features of the protease sample to be predicted; based on the sequence features and the structural features, using a prediction model based on a graph neural network to predict, and determining the predicted result of the activity change of the protease sample to be predicted after mutation.

[0215] That is to say, although in the system for predicting the effect of mutations on protease activity according to the present disclosure, the various operational functions corresponding to the prediction method are described as modules or sub-modules, those skilled in the art should understand that such modules or sub-modules may be circuit components or other physical components, or may not be composed of circuit components or other physical components, but may be functional modules constructed by computer programs.

[0216] In addition, it should be recognized by those skilled in the art that the method of the present disclosure can be implemented as a computer program. As described above in conjunction with the accompanying drawings, the method of the above embodiment is executed by one or more programs, and the instructions in the program cause the computer or processor to execute the algorithm described in conjunction with the accompanying drawings. These programs can be stored and provided to the computer or processor using various types of non-transient computer-readable media. Non-transient computer-readable media include various types of tangible storage media. Examples of non-transient computer-readable media include magnetic recording media (such as floppy disks, tapes, and hard disk drives), magneto-optical recording media (such as magneto-optical disks), CD-ROMs (compact disk read-only memories), CD-Rs, CD-R / Ws, and semiconductor memories (such as ROMs, PROMs (programmable ROMs), EPROMs (erasable PROMs), flash ROMs, and RAMs (random access memories)). Further, these programs can be provided to the computer using various types of transient computer-readable media. Examples of transient computer-readable media include electrical signals, optical signals, and electromagnetic waves. Transient computer-readable media can be used to provide programs to the computer through wired communication paths or wireless communication paths such as wires and optical fibers.

[0217] For example, according to one embodiment of the present disclosure, a non-transitory computer-readable storage medium may be provided for storing a computer program, wherein the computer program includes instructions that, when executed by a processor of an electronic device, enable the electronic device to implement the method for predicting the effect of a mutation on protease activity as described above.

[0218] In addition, according to the content disclosed in the present disclosure, a computer system can also be provided, the computer system comprising: a processor; a memory; and a computer program. The computer program is stored in the memory and is configured to be executed by the processor. The computer program includes instructions for implementing the above-mentioned instructions for predicting the effect of mutations on protease activity.

[0219] On the other hand, according to one embodiment of the present disclosure, a non-transitory computer-readable storage medium may be provided for storing a computer program, wherein the computer program includes instructions, which, when executed by a processor of an electronic device, enable the electronic device to implement the method for constructing a prediction model for predicting the effect of mutations on protease activity as described above.

[0220] In addition, according to the content disclosed in the present disclosure, a computer system can also be provided, the computer system comprising: a processor; a memory; and a computer program. The computer program is stored in the memory and is configured to be executed by the processor. The computer program includes instructions for implementing the above-mentioned method for constructing a prediction model for predicting the effect of mutations on protease activity.

[0221] The implementation methods of the present disclosure are not limited to the above-mentioned embodiments. Without departing from the spirit and scope of the present disclosure, ordinary technicians in this field can make various changes and improvements to the present disclosure in form and details, and these are considered to fall within the protection scope of the present disclosure.

Claims

1. A method for predicting the effect of a mutation on protease activity, characterized in that: The method comprises: Based on the sequence information of the protease sample to be predicted, a pre-trained model is used to perform feature extraction to obtain the sequence features of the protease sample to be predicted; Based on the three-dimensional structural information of the protease sample to be predicted, obtaining the structural characteristics of the protease sample to be predicted; Based on the sequence features and the structural features, a prediction model based on a graph neural network is used to perform predictions to determine the predicted results of the activity changes of the protease sample to be predicted after mutation.

2. The method according to claim 1, characterized in that The sequence information of the protease sample to be predicted includes the amino acid sequence information of the protease sample to be predicted before mutation and the amino acid sequence information of the protease sample to be predicted after mutation.

3. The method according to claim 1, characterized in that The sequence information of the protease sample to be predicted includes the amino acid sequence information of the protease sample to be predicted before mutation and the designated mutation information.

4. The method according to claim 3, characterized in that The method further comprises: obtaining the amino acid sequence information of the protease sample to be predicted after the mutation according to the amino acid sequence information of the protease sample to be predicted before the mutation and the designated mutation information.

5. The method according to claim 3 or 4, characterized in that: The specified mutation information includes a specified mutation site and / or a specified amino acid type after mutation.

6. The method according to claim 2 or 4, characterized in that: The method of extracting features based on the sequence information of the protease sample to be predicted using a pre-trained model to obtain the sequence features of the protease sample to be predicted further comprises: The amino acid sequence information of the protease sample to be predicted before mutation and the amino acid sequence information after mutation are respectively subjected to feature extraction using the pre-trained model to obtain sequence feature information before mutation and sequence feature information after mutation; The sequence feature information before the mutation and the sequence feature information after the mutation are spliced ​​to obtain the sequence feature of the protease sample to be predicted.

7. The method according to claim 1, characterized in that The pre-trained model is implemented by a combination of one or more of the following models: ESM-1b, UniRef, ProteinBert, TAPE, ProtGPT2, ProtTXL, ProtBert, ProtXLNet, ProtAlbert, ProtElectra, ProtT5-XL and ProtT5-XXL; preferably, the pre-trained model is ProtT5-XL or ProtT5-XXL; more preferably, the pre-trained model is ProtT5-XL.

8. The method according to claim 1, characterized in that: The three-dimensional structural information of the protease sample to be predicted includes the three-dimensional structural information of the protease sample to be predicted obtained through at least one of the following databases or prediction software: PDB database, AlphaFold2, I-TASSER, RoseTTAFold, Modeller and Swiss-model.

9. The method according to claim 1, characterized in that: The three-dimensional structural information of the protease sample to be predicted includes an interaction network, a secondary structure, an amino acid residue distance or a physical environment; preferably, the three-dimensional structural information of the protease sample to be predicted includes an interaction network.

10. The method according to claim 8 or 9, characterized in that: The three-dimensional structure information of the protease sample to be predicted is further obtained by the following method: Obtaining the coordinates of the three-dimensional structure of the protease sample to be predicted; Calculating the distances between pairs of amino acid residues in the three-dimensional structure of the protease based on the coordinates of the acquired three-dimensional structure; When the alpha carbon atom distance between two residue pairs is less than 10 angstroms, it indicates that there is an edge relationship between the nodes, which is recorded as 1, otherwise it is 0, and the node itself is recorded as 0, thus obtaining the adjacency matrix of the entire protease sample to be predicted.

11. The method according to claim 10, characterized in that The method of obtaining the structural features of the protease sample to be predicted based on the three-dimensional structural information of the protease sample to be predicted includes: Taking the mutation site as the center, an adjacency matrix of a specified size is intercepted from the adjacency matrix of the entire protease sample to be predicted as the structural feature of the protease sample to be predicted.

12. The method according to claim 1, characterized in that The prediction based on the sequence features and the structural features using a prediction model based on a graph neural network to determine the predicted activity change result of the protease sample to be predicted after mutation further includes: Inputting the sequence features and the structural features into a graph neural network to obtain probability features regarding activity changes; The probability features of the activity changes are combined with supplementary features from other prediction methods and input into a decision tree model to obtain a classification of the activity changes.

13. The method according to claim 12, characterized in that The step of inputting the sequence features and the structural features into the graph neural network to obtain the probability features regarding the activity change includes: Inputting the sequence features and the structural features into a graph neural network; Through matrix multiplication and aggregation operations, the features are updated and output using several layers of graph network structures; Merge the features output by several layers of graph network structures; Use pooling operation to compress features; The activity changes of the features are classified according to the output layer classification function, and the probability features of the activity changes are output.

14. The method according to claim 1, characterized in that The graph neural network-based prediction model is constructed through the following steps: Acquire a training set, wherein the training set includes information of a plurality of training samples, and the information of each training sample includes three-dimensional structure information of the sample protease, amino acid sequence information of the sample protease before and after mutation, and a mutation activity change label; Based on the amino acid sequence information of the sample protease before and after mutation, feature extraction is performed through a pre-training model to obtain sequence features of the plurality of training samples; Based on the three-dimensional structural information of the sample protease, obtaining structural features of the plurality of training samples; Based on the sequence features, the structural features and the mutation activity change labels, the graph neural network is trained to obtain the graph neural network-based prediction model.

15. The method according to claim 14, characterized in that The graph neural network-based prediction model is a classifier.

16. The method according to claim 14, characterized in that The graph neural network is a graph convolutional network or a graph attention network.

17. The method according to claim 14, characterized in that The training of the graph neural network based on the sequence features, the structural features and the mutation activity change labels to obtain the prediction model based on the graph neural network further includes: Inputting the sequence features and the structural features into a graph neural network to obtain probability features regarding activity changes; Combining the probability features of the activity change with supplementary features from other prediction methods and inputting them into a decision tree model to obtain a classification of the activity change; The mutation activity change label is used as the output target to adjust the parameters of the prediction model.

18. The method according to claim 12 or 17, characterized in that The decision tree model is a gradient boosted decision tree (GBDT) model.

19. The method according to claim 18, characterized in that The LightGBM framework is used to implement the GBDT model.

20. The method according to claim 14, characterized in that The step of obtaining the training set includes: Obtain experimental data from a public database as a training set; The training set is doubled in size by inverting the experimental data in the public database.

21. A method for constructing a prediction model for predicting the effect of mutation on protease activity, characterized in that: The method comprises: Acquire a training set, wherein the training set includes information of a plurality of training samples, and the information of each training sample includes three-dimensional structure information of the sample protease, amino acid sequence information of the sample protease before and after mutation, and a mutation activity change label; Based on the amino acid sequence information of the sample protease before and after mutation, feature extraction is performed through a pre-training model to obtain sequence features of the plurality of training samples; Based on the three-dimensional structural information of the sample protease, the structural features of multiple training samples are obtained; Based on the sequence features, the structural features and the mutation activity change labels, a graph neural network is trained to obtain a prediction model for predicting the effect of mutations on protease activity.

22. The method according to claim 21, characterized in that The method of extracting features based on the amino acid sequence information of the sample protease before and after mutation by using a pre-training model to obtain sequence features of the plurality of training samples includes: The amino acid sequence information of the sample protease before and after mutation is respectively subjected to feature extraction using the pre-trained model to obtain sequence feature information before and after mutation; The sequence feature information before the mutation and the sequence feature information after the mutation are concatenated to obtain the sequence features of the multiple training samples.

23. The method according to claim 21 or 22, characterized in that The pre-trained model is implemented by a combination of one or more of the following models: ESM-1b, UniRef, ProteinBert, TAPE, ProtGPT2, ProtTXL, ProtBert, ProtXLNet, ProtAlbert, ProtElectra, ProtT5-XL and ProtT5-XXL; preferably, the pre-trained model is ProtT5-XL or ProtT5-XXL; more preferably, the pre-trained model is ProtT5-XL.

24. The method according to claim 21, characterized in that The three-dimensional structural information of the sample protease includes the three-dimensional structural information of the sample protease obtained through at least one of the following databases or prediction software: PDB database, AlphaFold2, I-TASSER, RoseTTAFold, Modeller and Swiss-model.

25. The method according to claim 21, characterized in that The three-dimensional structural information of the sample protease includes an interaction network, a secondary structure, an amino acid residue distance or a physical environment; preferably, the three-dimensional structural information of the sample protease includes an interaction network.

26. The method according to claim 24 or 25, characterized in that The three-dimensional structural information of the sample protease is further obtained by: Obtaining coordinates of the three-dimensional structure of the sample protease; Calculating the distances between pairs of amino acid residues in the three-dimensional structure of the sample protease based on the coordinates of the acquired three-dimensional structure; When the alpha carbon atom distance between two residue pairs is less than 10 angstroms, it indicates that there is an edge relationship between the nodes, which is recorded as 1, otherwise it is 0, and the node itself is recorded as 0 to obtain the adjacency matrix of the entire sample protease.

27. The method according to claim 26, characterized in that The method of obtaining the structural features of multiple training samples based on the three-dimensional structural information of the sample protease comprises: Taking the mutation site as the center, an adjacency matrix of a specified size is intercepted from the adjacency matrix of the entire sample protease as the structural feature of the sample protease.

28. The method according to claim 21, characterized in that The training of the graph neural network based on the sequence features, the structural features and the mutation activity change labels to obtain a prediction model for predicting the effect of mutations on protease activity further includes: Inputting the sequence features and the structural features into a graph neural network to obtain probability features regarding activity changes; Combining the probability features of the activity change with supplementary features from other prediction methods and inputting them into a decision tree model to obtain a classification of the activity change; The mutation activity change label is used as the output target to adjust the parameters of the prediction model.

29. The method according to claim 28, characterized in that The step of inputting the sequence features and the structural features into the graph neural network to obtain the probability features regarding the activity change includes: Inputting the sequence features and the structural features into a graph neural network; Through matrix multiplication and aggregation operations, the features are updated and output using several layers of graph network structures; Merge the features output by several layers of graph network structures; Use pooling operation to compress features; The activity changes of the features are classified according to the output layer classification function, and the probability features of the activity changes are output.

30. The method according to claim 21, characterized in that The predictive model is a classifier.

31. The method according to claim 21, characterized in that The graph neural network is a graph convolutional network or a graph attention network.

32. The method according to claim 28, characterized in that The decision tree model is a GBDT model.

33. The method according to claim 32, characterized in that The LightGBM framework is used to implement the GBDT model.

34. The method according to claim 21, characterized in that The step of obtaining the training set includes: Obtain experimental data from a public database as a training set; The training set is doubled in size by inverting the experimental data in the public database.

35. A system for predicting the effect of mutations on protease activity, characterized in that: The system comprises: An acquisition module is used to obtain sequence information and three-dimensional structure information of the protease sample to be predicted; The processing module is used to obtain the activity change prediction result of the protease sample to be predicted after mutation by inputting the sequence information and three-dimensional structure information of the protease sample to be predicted. The processing module further includes the following submodules: A sequence feature submodule, used to extract features based on the sequence information of the protease sample to be predicted using a pre-trained model to obtain the sequence features of the protease sample to be predicted; A structural feature submodule, used for obtaining the structural features of the protease sample to be predicted based on the three-dimensional structural information of the protease sample to be predicted; The model prediction submodule is used to make predictions based on the sequence features and the structural features using a prediction model based on a graph neural network to determine the predicted results of the activity changes of the protease sample to be predicted after mutation.

36. A computer-implemented system for predicting the effect of a mutation on protease activity, the computer-implemented system implementing the following operations by executing a computer program: Obtaining sequence information and three-dimensional structure information of the protease sample to be predicted; By inputting the sequence information and three-dimensional structure information of the protease sample to be predicted, the activity change prediction result of the protease sample to be predicted after mutation is obtained, and the operation further includes the following sub-operations: Based on the sequence information of the protease sample to be predicted, using a pre-trained model to perform feature extraction to obtain sequence features of the protease sample to be predicted; Based on the three-dimensional structural information of the protease sample to be predicted, obtaining the structural characteristics of the protease sample to be predicted; Based on the sequence features and the structural features, a prediction model based on a graph neural network is used to perform predictions to determine the predicted results of the activity changes of the protease sample to be predicted after mutation.

37. A non-transitory computer-readable storage medium for storing a computer program, wherein the computer program includes instructions that, when executed by a processor of an electronic device, cause the electronic device to implement the method for predicting the effect of a mutation on protease activity as described in any one of claims 1-20 or the method for constructing a predictive model for predicting the effect of a mutation on protease activity as described in any one of claims 21-34.

38. A computer system, the computer system comprising: processor; Memory; and A computer program, wherein the computer program is stored in the memory and is configured to be executed by the processor, the computer program comprising instructions for implementing the method for predicting the effect of mutations on protease activity as described in any one of claims 1-20 or the method for constructing a predictive model for predicting the effect of mutations on protease activity as described in any one of claims 21-34.

Images