Antibacterial peptide generation method and device based on generative model and computer equipment

Abstract

The invention relates to an antibacterial peptide generation method and device based on a generative model and computer equipment, and relates to the technical field of artificial intelligence and bioinformatics. Predicting the novel antibacterial peptide on the basis of the existing antibacterial peptide sequence by using a pre-trained generative model to obtain a predicted sequence; inputting the prediction sequence into a pre-trained antibacterial peptide classifier, and judging whether the prediction sequence has antibacterial activity or not; the antibacterial peptide classifier is obtained by training based on an antibacterial peptide tag set and a non-antibacterial peptide sequence tag set; and outputting the prediction sequence with the antibacterial activity as a final target antibacterial peptide sequence, so that the problem of low antibacterial peptide design generation efficiency is solved, de novo generation and judgment of the antibacterial peptide can be realized by virtue of a generative model and a classifier, and the generation efficiency and accuracy are improved.

Description

Technical Field

[0001] The present application relates to the fields of artificial intelligence and bioinformatics technology, and in particular to a method, device and computer equipment for generating antimicrobial peptides based on a generative model. Background Art

[0002] Antimicrobial peptides (AMPs) are a class of short peptide molecules composed of amino acids. Due to their broad-spectrum antimicrobial properties, they are widely used in anti-infection treatment, food preservation and biomedicine. The current antimicrobial peptide database contains natural antimicrobial peptides and synthetic antimicrobial peptides. Natural antimicrobial peptides refer to metabolites with antimicrobial properties produced by organisms, while synthetic antimicrobial peptides are proteins synthesized using existing synthesis technology and have the same biochemical properties as natural antimicrobial peptides. The number of natural antimicrobial peptides is limited, and researchers hope to design and develop more types of antimicrobial peptides through artificial synthesis.

[0003] However, traditional antimicrobial peptide design mostly adopts a research model that relies on expert experience and manual trial and error, with a long production cycle, high cost, and a poor success rate.

[0004] There is currently no effective solution to the problem of low efficiency in the design and generation of antimicrobial peptides in related technologies. Summary of the invention

[0005] In this embodiment, a method, apparatus and computer device for generating antimicrobial peptides based on a generative model are provided to solve the problem of low efficiency in antimicrobial peptide design in related technologies.

[0006] In a first aspect, a method for generating antimicrobial peptides based on a generative model is provided in this embodiment, the method comprising: Obtaining a collection of existing antimicrobial peptide sequences; Using the pre-trained generative model, predicting new antimicrobial peptides based on the existing antimicrobial peptide sequences to obtain predicted sequences; Inputting the predicted sequence into a pre-trained antimicrobial peptide classifier to determine whether the predicted sequence has antimicrobial activity; the antimicrobial peptide classifier is trained based on an antimicrobial peptide label set and a non-antimicrobial peptide sequence label set; The predicted sequence with antibacterial activity is output as the final target antimicrobial peptide sequence.

[0007] In some embodiments, obtaining a collection of existing antimicrobial peptide sequences includes: Initial antimicrobial peptide data were extracted from public databases; The initial antimicrobial peptide data are cleaned to obtain a set of existing antimicrobial peptide sequences.

[0008] In some embodiments, a pre-trained generative model is used to predict a novel antimicrobial peptide based on the existing antimicrobial peptide sequence to obtain a predicted sequence, including: Based on the multiple sequence alignment technology, the existing set of antimicrobial peptide sequences is expanded to obtain an antimicrobial peptide multiple sequence alignment data set; The antimicrobial peptide multiple sequence alignment dataset is input into a pre-trained generative model to generate a predicted sequence based on an arbitrary decoding order.

[0009] In some of the embodiments, the pre-trained generative model uses an order-agnostic autoregressive diffusion model.

[0010] In some embodiments, the predicted sequence is input into a pre-trained antimicrobial peptide classifier to determine whether the predicted sequence has antimicrobial activity, comprising: Performing physical and chemical property screening on the predicted sequence to obtain a screened sequence; The screened sequence is input into a pre-trained antimicrobial peptide classifier, and a conclusion of whether the screened sequence has antimicrobial activity is output.

[0011] In some embodiments, the method further comprises: Training a binary classification model based on the obtained antimicrobial peptide label set and the non-antimicrobial peptide sequence label set; During the training process of the binary classification model, the parameters of the binary classification model are adjusted based on the ten-fold cross validation results to obtain a pre-trained antimicrobial peptide classifier.

[0012] In some embodiments, training a binary classification model based on the acquired antimicrobial peptide label set and the non-antimicrobial peptide sequence label set includes: Performing feature extraction on the antimicrobial peptide tag set and the non-antimicrobial peptide sequence tag set to obtain antimicrobial peptide features and non-antimicrobial peptide features; The antimicrobial peptide features and the non-antimicrobial peptide features are input into the binary classification model to train the binary classification model.

[0013] In a second aspect, in this embodiment, a device for generating antimicrobial peptides based on a generative model is provided, the device comprising: An existing data acquisition module, used to acquire a set of existing antimicrobial peptide sequences; A new sequence prediction module, used to obtain a predicted sequence with a structure similar to the existing antimicrobial peptide sequence using a pre-trained generative model; An activity verification module, used for inputting the predicted sequence into a pre-trained antimicrobial peptide classifier to determine whether the predicted sequence has antimicrobial activity; the antimicrobial peptide classifier is trained based on an antimicrobial peptide label set and a non-antimicrobial peptide sequence label set; The target antimicrobial peptide output module is used to output the predicted sequence with antimicrobial activity as the final target antimicrobial peptide sequence.

[0014] In a third aspect, the present application further provides a computer device, wherein the computer device comprises a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, the method for generating antimicrobial peptides based on a generative model as described in the first aspect is implemented.

[0015] In a fourth aspect, the present application further provides a computer-readable storage medium having a computer program stored thereon, and when the computer program is executed by a processor, the method for generating antimicrobial peptides based on a generative model as described in the first aspect is implemented.

[0016] Compared with the related art, the antimicrobial peptide generation method, device and computer equipment based on the generative model provided in this embodiment obtain a set of existing antimicrobial peptide sequences; use a pre-trained generative model to obtain a predicted sequence; input the predicted sequence into a pre-trained antimicrobial peptide classifier to determine whether the predicted sequence has antimicrobial activity; the antimicrobial peptide classifier is trained based on an antimicrobial peptide label set and a non-antimicrobial peptide sequence label set; and output the predicted sequence with antimicrobial activity as the final target antimicrobial peptide sequence, thereby solving the problem of low efficiency in antimicrobial peptide design and generation, and being able to achieve de novo generation and determination of antimicrobial peptides with the help of a generative model and a classifier, thereby improving generation efficiency and accuracy.

[0017] Details of one or more embodiments of the present application are set forth in the following drawings and description to make other features, objects, and advantages of the present application more readily apparent. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] The drawings described herein are used to provide a further understanding of the present application and constitute a part of the present application. The illustrative embodiments of the present application and their descriptions are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings: Figure 1 is a hardware structure block diagram of a terminal of an antimicrobial peptide generation method based on a generative model in one embodiment; Figure 2 is a schematic diagram of a process for generating antimicrobial peptides based on a generative model in one embodiment; Figure 3 Schematic diagram of a performance curve of an antimicrobial peptide classifier in a ten-fold cross validation in one embodiment; Figure 4 Schematic diagram of a process for generating antimicrobial peptides based on a generative model in a preferred embodiment; Figure 51 is a structural block diagram of an antimicrobial peptide generation device based on a generative model in one embodiment. DETAILED DESCRIPTION

[0019] In order to more clearly understand the purpose, technical solutions and advantages of the present application, the present application is described and illustrated below in conjunction with the accompanying drawings and embodiments.

[0020] Unless otherwise defined, the technical terms or scientific terms involved in this application shall have the general meaning understood by people with general skills in the technical field to which this application belongs. The words "one", "a", "a", "the", "these" and the like in this application do not indicate a quantitative limitation, and they may be singular or plural. The terms "include", "comprise", "have" and any variants thereof involved in this application are intended to cover non-exclusive inclusions; for example, a process, method and system, product or device comprising a series of steps or modules (units) is not limited to the listed steps or modules (units), but may include unlisted steps or modules (units), or may include other steps or modules (units) inherent to these processes, methods, products or devices. The words "connect", "connected", "coupled" and the like involved in this application are not limited to physical or mechanical connections, but may include electrical connections, whether direct or indirect. The "multiple" involved in this application refers to two or more. "And / or" describes the association relationship of associated objects, indicating that there may be three relationships, for example, "A and / or B" may mean: A exists alone, A and B exist at the same time, and B exists alone. Generally, the character " / " indicates that the objects associated with each other are in an "or" relationship. The terms "first", "second", "third", etc. in this application are only used to distinguish similar objects and do not represent a specific ordering of the objects.

[0021] The method embodiment provided in this embodiment can be executed in a terminal, a computer or a similar computing device. For example, running on a terminal, Figure 1 is a hardware structure block diagram of a terminal of the antimicrobial peptide generation method based on a generative model in this embodiment. Figure 1 As shown, the terminal may include one or more ( Figure 1 Only one is shown in the figure) a processor 102 and a memory 104 for storing data, wherein the processor 102 may include but is not limited to a processing device such as a microprocessor MCU or a programmable logic device FPGA. The above terminal may also include a transmission device 106 and an input and output device 108 for communication functions. It can be understood by those skilled in the art that Figure 1 The structure shown is only for illustration and does not limit the structure of the above terminal. Figure 1 More or fewer components as shown, or with Figure 1 Different configurations shown.

[0022] The memory 104 can be used to store computer programs, for example, software programs and modules of application software, such as the computer program corresponding to the antimicrobial peptide generation method based on the generative model in this embodiment. The processor 102 executes various functional applications and data processing by running the computer program stored in the memory 104, that is, to implement the above method. The memory 104 may include a high-speed random access memory, and may also include a non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some examples, the memory 104 may further include a memory remotely arranged relative to the processor 102, and these remote memories may be connected to the terminal via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and a combination thereof.

[0023] The transmission device 106 is used to receive or send data via a network. The above network includes a wireless network provided by the communication provider of the terminal. In one example, the transmission device 106 includes a network adapter (Network Interface Controller, referred to as NIC), which can be connected to other network devices through a base station so as to communicate with the Internet. In one example, the transmission device 106 can be a radio frequency (Radio Frequency, referred to as RF) module, which is used to communicate with the Internet wirelessly.

[0024] In this embodiment, a method for generating antimicrobial peptides based on a generative model is provided. Figure 2 is a flow chart of the method for generating antimicrobial peptides based on the generative model of this embodiment, such as Figure 2 As shown, the process includes the following steps: Step S210, obtaining a set of existing antimicrobial peptide sequences.

[0025] Specifically, in actual application, the method for obtaining existing antimicrobial peptide sequences in the embodiments of the present application includes, but is not limited to, obtaining them from a pre-stored database, or crawling antimicrobial peptide data with antimicrobial activity from literature reports on a network platform, merging, deduplicating, filtering, and other operations on the obtained antimicrobial peptide data sequences to obtain a set of existing antimicrobial peptide sequences. The embodiments of the present application do not limit the method for obtaining antimicrobial peptide sequences.

[0026] Step S220, using the pre-trained generative model, predicting new antimicrobial peptides based on existing antimicrobial peptide sequences to obtain a test sequence.

[0027] Specifically, based on the multiple sequence alignment technology, the existing set of antimicrobial peptide sequences is expanded to obtain an antimicrobial peptide multiple sequence alignment data set; the antimicrobial peptide multiple sequence alignment data set is input into a pre-trained diffusion model, and a predicted sequence is generated based on an arbitrary decoding order. In other specific embodiments, step S220 can also be implemented in the following manner: a large pre-trained language model (such as the GPT series) is trained on a corpus, so that the model can learn the syntax, semantics and potential features of the antimicrobial peptide sequence to obtain a predicted sequence, and the corpus includes existing antimicrobial peptide sequence information and some annotation information, such as characteristics, functions, similarities, etc. In other specific embodiments, some candidate antimicrobial peptide sequences can also be generated through a long short-term memory network (LSTM, Long Short-Term Memory); these candidate sequences are input into a Transformer converter, decoded and optimized, and an expanded antimicrobial peptide sequence, i.e., a predicted sequence, is obtained.

[0028] Step S230, input the predicted sequence into a pre-trained antimicrobial peptide classifier to determine whether the predicted sequence has antimicrobial activity; the antimicrobial peptide classifier is trained based on an antimicrobial peptide label set and a non-antimicrobial peptide sequence label set.

[0029] Specifically, the antimicrobial peptide classifier includes but is not limited to using models such as support vector machines, neural networks, and decision trees to learn the characteristics of antimicrobial peptides. The antimicrobial peptide label set can be obtained based on the existing antimicrobial peptide sequence set, and the non-antimicrobial peptide sequence label set includes various protein sequences that do not belong to antimicrobial peptides.

[0030] Step S240: outputting the predicted sequence with antimicrobial activity as the final target antimicrobial peptide sequence.

[0031] Specifically, the target antimicrobial peptide sequence can be further processed or analyzed, and applied in different scenarios according to the processing results or analysis results. For example, the tumor inhibition performance of the target antimicrobial peptide sequence can be analyzed for application in the medical field, or the bactericidal effect of the target antimicrobial peptide sequence can be analyzed, and the target antimicrobial peptide sequence that meets the bactericidal standard can be used as a preservative in the field of food safety. In addition, it can also be applied in scientific research or agriculture.

[0032] In this embodiment, a set of existing antimicrobial peptide sequences is obtained; a predicted sequence with a structure similar to the existing antimicrobial peptide sequence is obtained by using a pre-trained generative model; the predicted sequence is input into a pre-trained antimicrobial peptide classifier to determine whether the predicted sequence has antimicrobial activity; the antimicrobial peptide classifier is trained based on an antimicrobial peptide label set and a non-antimicrobial peptide sequence label set; and the predicted sequence with antimicrobial activity is output as the final target antimicrobial peptide sequence, thereby solving the problem of low efficiency in antimicrobial peptide design and generation, and being able to achieve de novo generation and determination of antimicrobial peptides with the help of a generative model and a classifier, thereby significantly improving the efficiency and success rate of antimicrobial peptide design.

[0033] In some embodiments, step S210, obtaining a set of existing antimicrobial peptide sequences, includes: Step S211, extracting initial antimicrobial peptide data from a public database.

[0034] Step S212: cleaning the initial antimicrobial peptide data to obtain a set of existing antimicrobial peptide sequences.

[0035] Specifically, the existing collection of antimicrobial peptide sequences, namely the AMP dataset, is compiled based on the following six public databases: APD (Antimicrobial Peptide Database); DADP (Collection of Antimicrobial Peptides); DBAASP (Database of Antimicrobial Activity and Structure of Peptides); DRAMP (Database of Research on Antimicrobial Peptides); YADAMP (Yet Another Database of Antimicrobial Peptides); and dbAMP (Database of Antimicrobial Peptides). The data extracted from these databases are merged, deduplicated, and filtered, and incomplete or meaningless data entries are deleted to improve the quality of the AMP dataset (i.e., the existing collection of antimicrobial peptide sequences).

[0036] In some of the embodiments, based on step S220, a pre-trained generative model is used to obtain a predicted sequence that is similar in structure to an existing antimicrobial peptide sequence, including: Step S221, based on the multiple sequence alignment technology, the existing set of antimicrobial peptide sequences is expanded to obtain an antimicrobial peptide multiple sequence alignment data set.

[0037] Specifically, a multiple sequence alignment (MSA) is performed on the existing collection of antimicrobial peptide sequences (i.e., AMP dataset) to obtain an antimicrobial peptide multiple sequence alignment dataset AMP-MSA with evolutionary information. In one embodiment, AMP-positive (i.e., having antimicrobial activity) MSA sequences are extracted through a search tool to obtain an antimicrobial peptide multiple sequence alignment dataset AMP-MSA.

[0038] Step S222, inputting the antimicrobial peptide multiple sequence alignment dataset into a pre-trained generative model to generate a predicted sequence based on an arbitrary decoding order.

[0039] Specifically, taking the antimicrobial peptide multiple sequence alignment dataset as a condition, the generation length is set (eg, set to 15-35 amino acids), and the generative model is used to predict new sequences.

[0040] Among them, the pre-trained generative model uses the order-agnostic autoregressive diffusion model (OADM). This model is trained on the evolutionary multiple sequence alignment (MSA) data used for training, allowing sequences to be generated in any order, expanding the generation capabilities of traditional autoregressive models.

[0041] The OADM diffusion model is trained using the log-likelihood of the generated sequence as the loss function. The log-likelihood of the generated sequence is expressed as the expectation of all possible decoding orders: ; Among them, x σ(t) represents the amino acid generated at position t according to the decoding order σ. σ(＜t) represents all the previous amino acids arranged in this order, where logp(x) represents the logarithmic likelihood of generating the x sequence, Eσ~U(S L ) represents the expected value of all possible decoding orders, L represents the length of the sequence, S L Represents all possible decoding orders.

[0042] During training, the model processes the MSA matrix through an alternating axial attention mechanism, reducing the row attention computation complexity to O(ML 2 ), the column attention complexity is reduced to O(LM 2 ), and combined with the tied row attention mechanism to share the inter-sequence structure.

[0043] The model is pre-trained with the Masked Language Modeling (MLM) objective, and its loss function is expressed as: ; Among them, (m,i) represents the masking position, To correctly predict the probability of a masked amino acid at position (m,i), is the MSA sequence after masking, X represents the MSA sequence before masking, and θ represents the parameters of the model.

[0044] In some of the embodiments, based on S230, the predicted sequence is input into a pre-trained antimicrobial peptide classifier to determine whether the predicted sequence has antimicrobial activity, including: Based on S231, the predicted sequence was screened for physical and chemical properties to obtain the screened sequence.

[0045] Based on S232, the screened sequence is input into a pre-trained antimicrobial peptide classifier, and a conclusion on whether the screened sequence has antimicrobial activity is output.

[0046] Specifically, the screening conditions include isoelectric point, positive charge and hydrophobicity, etc. The purpose of the physicochemical property screening is to evaluate whether the sequence generated by the generator has AMP (antimicrobial peptide)-like properties.

[0047] In some of these embodiments, the method further comprises: Step S250: training a binary classification model based on the acquired antimicrobial peptide label set and non-antimicrobial peptide sequence label set.

[0048] Step S260: During the training of the binary classification model, the parameters of the binary classification model are adjusted based on the ten-fold cross validation result to obtain a pre-trained antimicrobial peptide classifier.

[0049] Specifically, the ten-fold cross validation divides all the data into ten parts, and then uses each part as a validation set, and the others as training sets for training and validation. In this process, the hyperparameters are kept consistent, and then the average training loss and average validation loss of the 10 models are taken to measure the quality of the hyperparameters. Finally, after obtaining a satisfactory hyperparameter, all the data is used as the training set, and the final model is obtained by training with the hyperparameter. The beneficial effect of using cross validation is to reduce contingency and improve the generalization ability of the model. Due to the contingency caused by a single division of the training set and the validation set, make full use of the existing data set to perform multiple divisions to avoid the selection of accidental hyperparameters and models that do not have generalization ability due to special divisions.

[0050] In some embodiments, based on step S250, based on the acquired antimicrobial peptide label set and non-antimicrobial peptide sequence label set, training a binary classification model includes: Step S251, feature extraction is performed on the antimicrobial peptide tag set and the non-antimicrobial peptide sequence tag set to obtain antimicrobial peptide features and non-antimicrobial peptide features.

[0051] Step S252: inputting the antimicrobial peptide features and the non-antimicrobial peptide features into a binary classification model to train the binary classification model.

[0052] Specifically, the feature extraction methods include a pseudo K-tuple reduced amino acid composition (PseKRAAC) encoding method and a quasi-sequence-order (QSOrder) encoding method.

[0053] After the features are extracted, the features are selected. The feature selection adopts a two-step process. First, the features are evaluated according to the Pearson correlation coefficient (PCC), which is calculated as follows: ; where y i represents the true target value, represents the predicted value, u y and is the average of the true value and the predicted value, and N is the total number of samples. This step enables us to rank the features according to the predictive power of the feature type, thereby quantifying the effectiveness of the features. Subsequently, the most effective features were selected and further evaluated using a multi-branch convolutional neural network with attention mechanism (MBC-Attention) model to obtain the antimicrobial peptide features and non-antimicrobial peptide features used to train the binary classification model.

[0054] After the feature engineering process, the feature data is used to train a binary classification model, which uses the Extreme Gradient Boosting (XGBoost) decision tree algorithm. Among them, the antimicrobial peptide feature sequence is marked as 1, and the non-antimicrobial peptide feature sequence is marked as 0. The XGBoost model optimizes a regularized objective function to balance the accuracy and complexity of the model to prevent overfitting. Objective function Defined as: ; Among them, n represents the number of samples in the training process, l represents the loss function, and k represents the index of each tree in the XGBoost ensemble model. is x i The prediction formula is: ; Ω(f) is the regularization term: ; where T represents the number of leaves in the tree, w j represents the weight of the (j)th leaf, γ controls the number of leaves, and λ controls the L of the leaf weight. 2 Norm.

[0055] During training, the XGBoost model is built in an additive manner, optimizing the following objective L at each iteration t: ; Among them, n represents the number of samples in the training process, l represents the loss function, Ω(f t ) represents the regularization term at time t, f t (x i ) means that in the tth iteration of the training process, the new tree f t For sample x i Predictions made.

[0056] In the objective function L (t) middle, Calculated when adding the new tree f t The overall loss for all samples in the dataset after improving the previous prediction. The regularization term Ω(f t ) for the new tree f t The complexity of the model is penalized to prevent overfitting.

[0057] Use the second-order Taylor expansion to approximate L: ; Among them, g i and h i are the first and second order gradients respectively.

[0058] XGBoost model tuning is based on the F1 score and AUC index, using 10-fold cross validation (k times 10) to prevent overfitting. The F1 score is a metric that considers both precision and recall to calculate a balanced measure of model accuracy, especially when dealing with imbalanced classes. It is defined as the harmonic mean of precision and recall: ; Among them, F1 Score represents the F1 score, Precision represents accuracy, and Recall (also known as sensitivity or true positive rate) is the proportion of actual positive cases correctly identified by the model, which is calculated as follows: ; Among them, TP stands for true positive and FN stands for false negative.

[0059] The best split for each node during training is determined by maximizing the gain Gain: ; Among them, I L and I R Represents the left and right child nodes after segmentation, g i and h i are the first-order and second-order gradients, respectively. λ controls the L2 norm of the leaf node weights to prevent overfitting, and γ penalizes the split that increases the number of leaf nodes in the tree.

[0060] Apply shrinkage (learning rate η) to each tree’s predictions to scale them: ; in, represents the updated sample after adding the tth tree The predicted value of Represents the sample x before joining the tth tree i The predicted value, f t (x i ) means that in the tth iteration of the training process, the new tree f t For sample x i The output value of . η represents the learning rate, which prevents overfitting by reducing the influence of each tree.

[0061] The best performing model determined by cross-validation was used for subsequent analyses.

[0062] Figure 3 The performance curves (receiver operating characteristic, ROC) of the XGBoost-based antimicrobial peptide classifier model in ten-fold cross validation are shown. Each curve represents a fold receiver operating characteristic curve, depicting the trade-off between the true positive rate and the false positive rate under different threshold settings. The average ROC curve marked with a bold line summarizes the overall performance of the model, and the area under the curve (AUC) provides a measure of classification accuracy.

[0063] The present embodiment is described and illustrated below through preferred embodiments.

[0064] Figure 4 FIG. 4 is a flow chart of the method for generating antimicrobial peptides based on a generative model according to the preferred embodiment of the present invention. Figure 4 As shown, the method for generating antimicrobial peptides based on a generative model provided in this preferred embodiment includes: S1, construct an antimicrobial peptide dataset, that is, a collection of existing antimicrobial peptide sequences. Antimicrobial peptide data are extracted from the antimicrobial peptide public database, and after merging, deduplication and filtering, incomplete or meaningless data entries are deleted to obtain the antimicrobial peptide dataset.

[0065] S2, constructing an antimicrobial peptide multiple sequence alignment dataset. Based on the multiple sequence alignment technology, the existing antimicrobial peptide sequence set is expanded to obtain an antimicrobial peptide multiple sequence alignment dataset.

[0066] S3, the antimicrobial peptide multiple sequence alignment dataset is input into the pre-trained order-agnostic autoregressive diffusion model to generate predicted sequences based on arbitrary decoding order.

[0067] S4, screening the predicted sequence for physical and chemical properties to obtain a screened sequence.

[0068] S5, training a binary classification model based on the obtained antimicrobial peptide label set and non-antimicrobial peptide sequence label set; during the training process of the binary classification model, adjusting the parameters of the binary classification model based on the ten-fold cross validation results to obtain an antimicrobial peptide classifier.

[0069] S6, inputting the screened sequence into the antimicrobial peptide classifier to determine whether the predicted sequence has antimicrobial activity.

[0070] S7, outputting the sequence with antimicrobial activity as the final target antimicrobial peptide sequence.

[0071] This preferred embodiment proposes a generation and screening strategy that combines diffusion models, multiple sequence alignment data and machine learning optimization tools to significantly improve the efficiency and success rate of antimicrobial peptide design, which is an important innovation in the field of bioinformatics and protein engineering.

[0072] It should be noted that the steps shown in the above process or the flowchart in the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0073] In this embodiment, a device for generating antimicrobial peptides based on a generative model is also provided, which is used to implement the above-mentioned embodiments and preferred embodiments, and the descriptions that have been made will not be repeated. The terms "module", "unit", "subunit", etc. used below can implement a combination of software and / or hardware for a predetermined function. Although the devices described in the following embodiments are preferably implemented in software, the implementation of hardware, or a combination of software and hardware, is also possible and conceivable.

[0074] Figure 5 is a structural block diagram of the antimicrobial peptide generation device based on the generative model of this embodiment, such as Figure 5 As shown, the device includes: an existing data acquisition module 51, a new sequence prediction module 52, an activity verification module 53 and a target antimicrobial peptide output module 54.

[0075] An existing data acquisition module 51 is used to acquire a set of existing antimicrobial peptide sequences; A new sequence prediction module 52 is used to predict new antimicrobial peptides based on existing antimicrobial peptide sequences using a pre-trained generative model to obtain a predicted sequence; Activity verification module 53, used for inputting the predicted sequence into a pre-trained antimicrobial peptide classifier to determine whether the predicted sequence has antimicrobial activity; the antimicrobial peptide classifier is trained based on an antimicrobial peptide label set and a non-antimicrobial peptide sequence label set; The target antimicrobial peptide output module 54 is used to output the predicted sequence with antimicrobial activity as the final target antimicrobial peptide sequence.

[0076] In some embodiments, obtaining the existing set of antimicrobial peptide sequences includes: extracting initial antimicrobial peptide data from a public database; and cleaning the initial antimicrobial peptide data to obtain the existing set of antimicrobial peptide sequences.

[0077] In some of the embodiments, a pre-trained generative model is used to obtain a predicted sequence that is similar in structure to an existing antimicrobial peptide sequence, including: based on a multiple sequence alignment technique, expanding a set of existing antimicrobial peptide sequences to obtain an antimicrobial peptide multiple sequence alignment dataset; and inputting the antimicrobial peptide multiple sequence alignment dataset into a pre-trained generative model to generate a predicted sequence based on an arbitrary decoding order.

[0078] In some of the embodiments, the pre-trained generative model uses an order-agnostic autoregressive diffusion model.

[0079] In some of the embodiments, the predicted sequence is input into a pre-trained antimicrobial peptide classifier to determine whether the predicted sequence has antimicrobial activity, including: screening the predicted sequence for physical and chemical properties to obtain a screened sequence; inputting the screened sequence into the pre-trained antimicrobial peptide classifier to output a conclusion on whether the screened sequence has antimicrobial activity.

[0080] In some of the embodiments, the method further comprises: training a binary classification model based on the acquired antimicrobial peptide label set and non-antimicrobial peptide sequence label set; during the training of the binary classification model, adjusting the parameters of the binary classification model based on the ten-fold cross validation results to obtain a pre-trained antimicrobial peptide classifier.

[0081] In some of the embodiments, a binary classification model is trained based on the obtained antimicrobial peptide label set and non-antimicrobial peptide sequence label set, including: extracting features from the antimicrobial peptide label set and the non-antimicrobial peptide sequence label set to obtain antimicrobial peptide features and non-antimicrobial peptide features; inputting the antimicrobial peptide features and the non-antimicrobial peptide features into the binary classification model to train the binary classification model.

[0082] It should be noted that the above modules can be functional modules or program modules, and can be implemented by software or hardware. For modules implemented by hardware, the above modules can be located in the same processor; or the above modules can be located in different processors in any combination.

[0083] In this embodiment, a computer device is further provided, including a memory and a processor, wherein a computer program is stored in the memory, and the processor is configured to run the computer program to execute the steps in any one of the above method embodiments.

[0084] Optionally, the computer device may further include a transmission device and an input / output device, wherein the transmission device is connected to the processor, and the input / output device is connected to the processor.

[0085] It should be noted that the specific examples in this embodiment can refer to the examples described in the above embodiments and optional implementation modes, and will not be repeated in this embodiment.

[0086] In addition, in combination with the antimicrobial peptide generation method based on the generative model provided in the above embodiments, a storage medium can also be provided in this embodiment to implement the method. The storage medium stores a computer program; when the computer program is executed by the processor, any one of the antimicrobial peptide generation methods based on the generative model in the above embodiments is implemented.

[0087] It should be understood that the specific embodiments described herein are only used to explain the application, rather than to limit it. Based on the embodiments provided in this application, all other embodiments obtained by ordinary technicians in this field without creative work are within the protection scope of this application.

[0088] Obviously, the drawings are only some examples or embodiments of the present application. For ordinary technicians in the field, the present application can also be applied to other similar situations based on these drawings without creative work. In addition, it is understandable that although the work done in this development process may be complicated and lengthy, for ordinary technicians in the field, certain changes in design, manufacturing or production based on the technical content disclosed in this application are only conventional technical means and should not be regarded as insufficient content disclosed in this application.

[0089] The term "embodiment" in this application refers to a specific feature, structure or characteristic described in conjunction with the embodiment that can be included in at least one embodiment of the present application. The appearance of this phrase in various locations in the specification does not necessarily mean the same embodiment, nor does it mean that it is mutually exclusive with other embodiments and is independent or optional. It is clearly or implicitly understood by those of ordinary skill in the art that the embodiments described in this application can be combined with other embodiments without conflict.

[0090] The above-mentioned embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of patent protection. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the scope of protection of the present application. Therefore, the scope of protection of the present application shall be subject to the attached claims.

Claims

1. A method for generating antimicrobial peptides based on a generative model, characterized in that: The method comprises: Obtaining a collection of existing antimicrobial peptide sequences; Using the pre-trained generative model, predicting new antimicrobial peptides based on the existing antimicrobial peptide sequences to obtain predicted sequences; Inputting the predicted sequence into a pre-trained antimicrobial peptide classifier to determine whether the predicted sequence has antimicrobial activity; the antimicrobial peptide classifier is trained based on an antimicrobial peptide label set and a non-antimicrobial peptide sequence label set; The predicted sequence with antibacterial activity is output as the final target antimicrobial peptide sequence.

2. The method for generating antimicrobial peptides based on a generative model according to claim 1, characterized in that: Access a collection of existing antimicrobial peptide sequences, including: Initial antimicrobial peptide data were extracted from public databases; The initial antimicrobial peptide data are cleaned to obtain a set of existing antimicrobial peptide sequences.

3. The method for generating antimicrobial peptides based on a generative model according to claim 1, characterized in that: Using the pre-trained generative model, novel antimicrobial peptides are predicted based on the existing antimicrobial peptide sequences to obtain predicted sequences, including: Based on the multiple sequence alignment technology, the existing set of antimicrobial peptide sequences is expanded to obtain an antimicrobial peptide multiple sequence alignment data set; The antimicrobial peptide multiple sequence alignment dataset is input into a pre-trained generative model to generate a predicted sequence based on an arbitrary decoding order.

4. The method for generating antimicrobial peptides based on a generative model according to claim 1, characterized in that: The pre-trained generative model adopts an order-agnostic autoregressive diffusion model.

5. The method for generating antimicrobial peptides based on a generative model according to claim 1, characterized in that: Inputting the predicted sequence into a pre-trained antimicrobial peptide classifier to determine whether the predicted sequence has antimicrobial activity comprises: Performing physical and chemical property screening on the predicted sequence to obtain a screened sequence; The screened sequence is input into a pre-trained antimicrobial peptide classifier, and a conclusion of whether the screened sequence has antimicrobial activity is output.

6. The method for generating antimicrobial peptides based on a generative model according to claim 1, characterized in that: The method further comprises: Training a binary classification model based on the obtained antimicrobial peptide label set and the non-antimicrobial peptide sequence label set; During the training process of the binary classification model, the parameters of the binary classification model are adjusted based on the ten-fold cross validation results to obtain a pre-trained antimicrobial peptide classifier.

7. The method for generating antimicrobial peptides based on a generative model according to claim 5, characterized in that: Based on the obtained antimicrobial peptide label set and the non-antimicrobial peptide sequence label set, training a binary classification model includes: Performing feature extraction on the antimicrobial peptide tag set and the non-antimicrobial peptide sequence tag set to obtain antimicrobial peptide features and non-antimicrobial peptide features; The antimicrobial peptide features and the non-antimicrobial peptide features are input into the binary classification model to train the binary classification model.

8. A device for generating antimicrobial peptides based on a generative model, characterized in that: The device comprises: An existing data acquisition module, used to acquire a set of existing antimicrobial peptide sequences; A new sequence prediction module, used for predicting new antimicrobial peptides based on the existing antimicrobial peptide sequences using a pre-trained generative model to obtain a predicted sequence; An activity verification module, used for inputting the predicted sequence into a pre-trained antimicrobial peptide classifier to determine whether the predicted sequence has antimicrobial activity; the antimicrobial peptide classifier is trained based on an antimicrobial peptide label set and a non-antimicrobial peptide sequence label set; The target antimicrobial peptide output module is used to output the predicted sequence with antimicrobial activity as the final target antimicrobial peptide sequence.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 7 are implemented.

Images