Poison protein library building method, device, equipment and medium

Abstract

The invention relates to the field of biological information, and discloses a toxic protein library building method, device, equipment and medium, and the method comprises the following steps: obtaining a consensus peptide structure corresponding to a confirmed toxic protein sequence, and determining a toxic protein library on the basis of function expression characteristic data and fluctuation trend characteristic data of the consensus peptide structure; and constructing a target toxic protein core peptide set capable of covering the key functional domain of the confirmed toxic protein sequence. And performing function screening on the to-be-identified protein sequence on the functional feature domain by using the target toxic protein core peptide set to obtain an intermediate protein sequence which needs to be verified whether to conform to the toxic feature, performing toxicity screening on the intermediate protein sequence on the toxic feature domain, and determining the intermediate protein sequence conforming to the toxic feature as a target toxic protein sequence. And finally, constructing a toxic protein database by using the target toxic protein sequence. Therefore, through a two-layer screening mode combining function screening and toxicity screening, the toxic protein library building method which can discover new toxic proteins and detect low-abundance toxic proteins and is wide in coverage range is achieved.

Description

Technical Field

[0001] The present application relates to the field of bioinformatics, and in particular to a method, device, equipment and medium for building a toxic protein library. Background Art

[0002] The construction of toxic protein database has important application value in bioinformatics and toxicology research, especially in the fields of drug design, disease mechanism analysis and ecological risk assessment. However, the toxic protein database construction method in related technologies still has certain limitations. Summary of the invention

[0003] The present application aims to solve at least one of the technical problems in the related art to a certain extent. To this end, the present application proposes a method, device, equipment and medium for building a toxic protein library. The main technical solutions adopted in the present application include:

[0004] In a first aspect, an embodiment of the present application provides a method for constructing a toxic protein library, the method comprising: obtaining a common peptide structure corresponding to a confirmed toxic protein sequence, and constructing a target toxic protein core peptide set that can cover the key functional domains of the confirmed toxic protein sequence based on the functional performance characteristic data and fluctuation trend characteristic data of the common peptide structure; using the target toxic protein core peptide set to perform functional screening on the protein sequence to be identified in the functional characteristic domain, to obtain an intermediate protein sequence that needs to be verified whether it meets the toxic characteristics, and performing toxicity screening on the intermediate protein sequence in the toxic characteristic domain, and determining the intermediate protein sequence that meets the toxic characteristics as the target toxic protein sequence; wherein the intermediate protein sequence that meets the toxic characteristics is obtained by performing toxicity recognition on the intermediate protein sequence by a toxic protein recognition model; and constructing a toxic protein database using the target toxic protein sequence.

[0005] Optionally, based on the functional performance characteristic data and fluctuation trend characteristic data of the common peptide structure, a target toxic protein core peptide set that can cover the key functional domains of the confirmed toxic protein sequence is constructed, including: aggregating the common peptide structure into toxic protein family core peptides; clustering based on the functional performance characteristic data and fluctuation trend characteristic data of the toxic protein family core peptides to obtain multiple initial toxic protein core peptide sets; matching the confirmed toxic protein sequence with each initial toxic protein core peptide set to confirm the target toxic protein core peptide set in the multiple initial toxic protein core peptide sets.

[0006] Optionally, the confirmed toxic protein sequence is matched with each initial toxic protein core peptide set to confirm the target toxic protein core peptide set among multiple initial toxic protein core peptide sets, including: performing functional enrichment analysis on each initial toxic protein core peptide set to obtain the functional characteristics of each initial toxic protein core peptide set; based on the functional characteristics of each initial toxic protein core peptide set, calculating the matching degree between the confirmed toxic protein sequence and each initial toxic protein core peptide set; and determining the initial toxic protein core peptide set corresponding to the highest matching degree as the target toxic protein core peptide set.

[0007] In a second aspect, an embodiment of the present application provides a toxic protein library construction device, which includes: a target toxic protein core peptide set construction module, which is used to obtain the common peptide structure corresponding to the confirmed toxic protein sequence, and based on the functional performance characteristic data and fluctuation trend characteristic data of the common peptide structure, construct a target toxic protein core peptide set that can cover the key functional domains of the confirmed toxic protein sequence; a target toxic protein sequence determination module, which is used to use the target toxic protein core peptide set to perform functional screening on the protein sequence to be identified in the functional characteristic domain, to obtain the intermediate protein sequence that needs to be verified whether it meets the toxic characteristics, and to perform toxicity screening on the intermediate protein sequence in the toxic characteristic domain, and determine the intermediate protein sequence that meets the toxic characteristics as the target toxic protein sequence; wherein the intermediate protein sequence that meets the toxic characteristics is obtained by performing toxicity identification on the intermediate protein sequence by a toxic protein recognition model; a toxic protein database construction module, which is used to construct a toxic protein database using the target toxic protein sequence.

[0008] In a third aspect, the present application further provides a computer device including a memory and a processor, wherein the memory stores a computer program, and the processor implements the steps of any of the above methods when executing the computer program.

[0009] In a fourth aspect, the present application also provides a computer-readable storage medium having a computer program stored thereon, which implements the steps of any of the above methods when the computer program is executed by a processor.

[0010] In a fifth aspect, the present invention provides a computer program product, comprising a computer program, which implements the steps of any of the above methods when executed by a processor.

[0011] In the above embodiment, the common peptide structure corresponding to the confirmed toxic protein sequence is obtained, and based on the functional performance characteristic data and fluctuation trend characteristic data of the common peptide structure, a target toxic protein core peptide set that can cover the key functional domains of the confirmed toxic protein sequence is constructed. The target toxic protein core peptide set is used to perform functional screening on the functional characteristic domain of the protein sequence to be identified, and an intermediate protein sequence that needs to be verified whether it meets the toxic characteristics is obtained. The intermediate protein sequence is screened for toxicity in the toxic characteristic domain, and the intermediate protein sequence that meets the toxic characteristics is determined as the target toxic protein sequence. Finally, the target toxic protein sequence is used to construct a toxic protein database. At this point, a two-level screening method combining functional screening and toxicity screening is implemented to realize a toxic protein library construction method with a wide coverage range that can not only discover new toxic proteins but also detect low-abundance toxic proteins. BRIEF DESCRIPTION OF THE DRAWINGS

[0012] In order to more clearly illustrate the specific implementation methods of the present application or the technical solutions in the prior art, the drawings required for use in the specific implementation methods or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are some implementation methods of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0013] Figure 1a A flow chart of a method for building a toxic protein library according to one embodiment of the present application;

[0014] Figure 1b This is a schematic diagram of the interface of a toxic protein database provided according to one embodiment of the present application;

[0015] Figure 2 A flow chart of a method for confirming a core peptide set of a target toxic protein according to one embodiment of the present application;

[0016] Figure 3a A flow chart of a method for confirming a core peptide set of a target toxic protein according to another embodiment of the present application;

[0017] Figure 3b This is an analysis curve diagram of the enrichment degree of each toxic protein core peptide set provided according to one embodiment of the present application;

[0018] Figure 4 A flowchart of a method for determining a toxic protein recognition model according to one embodiment of the present application;

[0019] Figure 5 A flowchart of a method for obtaining an initial protein sequence set according to one embodiment of the present application;

[0020] Figure 6This is a structural block diagram of a toxic protein library building device according to one embodiment of the present application;

[0021] Figure 7 The figure is a diagram of the internal structure of a computer device according to one embodiment of the present application. DETAILED DESCRIPTION

[0022] In order to make the purpose, technical solution and advantages of the embodiments of the present application clearer, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of the present application.

[0023] The construction of toxic protein database has important application value in bioinformatics and toxicology research, especially in the fields of drug design, disease mechanism analysis and ecological risk assessment. However, there are still many technical bottlenecks in the toxic protein library construction methods in related technologies. Commonly used toxic protein library construction methods include the following:

[0024] 1. Experimental sequencing method: This is the most direct method to obtain protein sequences, and it usually relies on mass spectrometry technology for high-precision sequencing. Mass spectrometry sequencing provides accurate structural information of toxic proteins, and can better determine protein sequences, structures, and post-translational modifications. However, experimental sequencing has high requirements for experimental equipment and technicians, the sequencing cost is expensive, and each sample usually takes a long time. Therefore, the experimental sequencing method is mainly suitable for studying specific high-abundance toxic proteins, and its application is limited for samples with low abundance or complex sources. In addition, mass spectrometry is sensitive to sample extraction purity and abundance, and it is difficult to capture toxic proteins with low content or difficult to extract, resulting in the absence of some toxic proteins in the database.

[0025] 2. Homology alignment method: This method is based on the existing protein sequence database and predicts the potential sequence of toxic proteins through sequence alignment. For sequences similar to known toxic proteins, the homology alignment method can quickly infer unknown sequences. However, this method is powerless for toxic proteins with large evolutionary differences or toxic proteins that are not yet covered in the database. In particular, for newly discovered toxic proteins, if they do not have any known sequences as references, it will be difficult to obtain accurate predictions through homology alignment. In addition, as the amount of data increases, the alignment process may lead to an increase in the consumption of computing resources and reduce the efficiency of database updates.

[0026] 3. Public database integration method: This method provides researchers with a large amount of protein information by integrating protein sequence data from different sources, such as UniProt, PDB, etc. Although the integration provides rich toxic protein sequence information, the data sources are different and there may be redundant data. For example, multiple databases may include the same or highly similar sequences, which increases the storage burden of the system and affects the retrieval efficiency. In addition, there are differences in sequence formats, annotations, and naming rules among different databases, which can easily lead to inconsistent data during the integration process, increasing the difficulty of use.

[0027] It can be seen that the toxic protein library construction method in the related art faces challenges in many aspects, as follows:

[0028] (1) Data redundancy: In the integration method of public databases, data from different sources often contain a large number of repeated toxic protein sequences, which not only leads to a waste of storage resources, but also reduces the retrieval efficiency of the database in practical applications. For example, when searching for the sequence of a toxic protein, researchers may need to screen out different versions of the same sequence, thereby increasing the data processing burden. Data redundancy may also lead to distorted judgments on sequence variations, affecting downstream toxicology research and drug development processes.

[0029] (2) Data consistency issues: In the integration method of public databases, data from different sources often contain a large number of repeated toxic protein sequences, which not only leads to a waste of storage resources, but also reduces the retrieval efficiency of the database in practical applications. For example, when searching for the sequence of a toxic protein, researchers may need to screen out different versions of the same sequence, thereby increasing the data processing burden. Data redundancy may also lead to distorted judgments on sequence variations, affecting downstream toxicology research and drug development processes.

[0030] (3) Limitations of new toxic protein discovery: The reliance on homology comparison methods has led to significant limitations in the discovery of new toxic proteins. Many toxic proteins are difficult to accurately predict using existing databases due to the lack of evolutionarily similar sequences. This is particularly prominent in the study of environmental toxins and pathogen toxins. For drug target research on toxic proteins, the lack of accurate new toxic protein sequence data will limit new drug design and development work.

[0031] (4) High experimental cost: Although experimental sequencing methods are accurate, their high cost and time consumption pose a bottleneck to the construction of large-scale toxic protein databases. Especially when dealing with complex biological samples, the demand for experimental equipment and the cost of consumables may significantly increase the project budget. In addition, the collection of toxic proteins has certain risks, especially when detecting samples with strong toxicity, the operation and protection costs are also high, further increasing the difficulty.

[0032] (5) Difficulty in detecting low-abundance toxic proteins: Many important toxic proteins exist in low abundance in samples, and experimental sequencing methods are difficult to effectively detect such proteins, resulting in the lack of such information in the database. However, these low-abundance toxic proteins often have high toxicity and may be the key to the research and development of new antidotes or toxin neutralizers. The limitations of experimental sequencing methods make it difficult to detect and collect data on such toxic proteins.

[0033] According to an embodiment of the present application, a method, device, equipment and medium embodiment of a toxic protein library construction method is provided. It should be noted that the steps shown in the flowchart of 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.

[0034] In this embodiment, a method for constructing a toxic protein library is provided. Figure 1a is a flow chart of a method for building a toxic protein library according to an embodiment of the present application, such as Figure 1a As shown, the process includes the following steps:

[0035] S110. Obtain the common peptide structure corresponding to the confirmed toxic protein sequence, and construct a target toxic protein core peptide set that can cover the key functional domains of the confirmed toxic protein sequence based on the functional performance characteristic data and fluctuation trend characteristic data of the common peptide structure.

[0036] Among them, confirmed toxic protein sequences can be used to describe protein sequences that have been experimentally verified or confirmed to be toxic by authoritative databases. Specifically, confirmed toxic protein sequences can be screened and obtained from multiple databases such as the Toxin and Toxin Target Database (T3DB) or UNIPROT.

[0037] It is understandable that due to the sequence structure characteristics of proteins, it is difficult to find two proteins with exactly the same sequence structure. Therefore, when performing detection and identification, certain common peptide structures in proteins will be used as an important basis for identifying and classifying proteins. Among them, the common peptide structure refers to a peptide segment that is commonly present in a group of protein sequences and has similar structure and function. For example, for a toxic protein sequence, certain key regions of the toxic protein function can be used as common peptide structures that need to be extracted and identified.

[0038] Furthermore, after obtaining the common peptide structure corresponding to the confirmed toxic protein sequence, it is necessary to construct a target toxic protein core peptide set that can cover the key functional domains of the confirmed toxic protein sequence based on the functional performance characteristic data and fluctuation trend characteristic data contained in the common peptide structure.

[0039] Among them, the functional performance characteristic data can be used to describe the functional performance of proteins in biological processes, reflecting the activity, mechanism of action and interaction with other molecules of proteins. For example, the characteristic data of the role of the common peptide structure corresponding to the toxic protein sequence in the organism, the relationship between activity and disease can be used as functional performance characteristic data.

[0040] Fluctuation trend characteristic data can be used to describe the trend data of fluctuation height changes of protein sequences under different conditions or at different time points. For example, the change in the expression amount of the common peptide structure corresponding to the confirmed toxic protein sequence on its structural sequence or the sequence variation trend can be used as fluctuation trend characteristic data.

[0041] It can be understood that a core peptide set of target toxic protein can be constructed based on the functional performance characteristic data and fluctuation trend characteristic data contained in the common peptide structure.

[0042] The target toxin protein core peptide set may be used to refer to a toxin protein core peptide set formed by clustering a plurality of toxin protein core peptides with a common peptide structure that are similar in functional performance and have a common fluctuation trend in fluctuation structure. Exemplarily, the target toxin protein core peptide set may be a toxin protein family featured peptide module (TFFP module for short).

[0043] Specifically, during polymerization, the key functional domains that need to cover the confirmed toxic protein sequence are constructed based on the functional performance characteristic data and fluctuation trend characteristic data contained in the common peptide structure. Among them, the key functional domains can be used to describe certain specific regions in the protein responsible for specific biological functions. Exemplarily, in the process of constructing the target toxic protein core peptide set, the key functional domain is a certain specific region directly related to the toxic effect.

[0044] S120. Use the target toxic protein core peptide set to perform functional screening on the protein sequence to be identified in the functional characteristic domain to obtain the intermediate protein sequence that needs to be verified whether it meets the toxic characteristics, and perform toxicity screening on the intermediate protein sequence in the toxic characteristic domain, and determine the intermediate protein sequence that meets the toxic characteristics as the target toxic protein sequence.

[0045] Among them, the protein sequence to be identified, the intermediate protein sequence, and the target toxic protein sequence can all refer to certain specific protein sequences. Specifically, the protein sequence to be identified can refer to a protein sequence that has not yet been confirmed to be toxic. Exemplarily, all protein sequences in the UniProt library can be used as protein sequences to be identified.

[0046] The intermediate protein sequence may refer to a protein sequence obtained after preliminary screening during the toxic protein identification process. For example, the intermediate protein sequence may be a protein sequence obtained after screening of the functional feature domain, which is similar to a known toxic protein in certain functional features, but has not yet been finally confirmed to be toxic.

[0047] The target toxic protein sequence may refer to a protein sequence that has been confirmed to have toxic characteristics after toxicity screening and verification and exhibits characteristics similar to known toxic proteins. Among them, the intermediate protein sequence that meets the toxic characteristics is obtained by performing toxicity recognition on the intermediate protein sequence through the toxic protein recognition model.

[0048] Specifically, the target toxic protein core peptide set established corresponding to the confirmed toxic protein sequence is first used to conduct a preliminary functional screening of the protein sequence to be identified, so as to identify protein sequences that are functionally similar to known toxic proteins. Exemplarily, the target toxic protein core peptide set, i.e., some core peptide structures in the TFFP module that can be used as identification features, can be used to compare with all the protein sequences to be identified in the database to screen out candidate toxic protein sequences with higher affinity, i.e., intermediate protein sequences. This screening can not only expand the coverage of the toxic protein database, but also identify potential toxic protein sequences, providing a reliable data basis for subsequent toxic protein detection and functional research.

[0049] Furthermore, after obtaining the intermediate protein sequence that needs to be verified to see if it meets the toxicity characteristics, the pre-trained machine learning model can be used to perform secondary verification on these candidate toxic proteins to obtain the target toxic protein sequence that is confirmed to have toxic characteristics. Specifically, the intermediate protein sequence is used as the input feature of the machine learning model, and secondary classification is performed using high-precision algorithms such as random forests. The model is used to conduct in-depth analysis of the characteristics of the candidate toxic proteins to identify and confirm the toxic properties of these proteins. Finally, the intermediate protein sequence that has been confirmed by the toxicity screening and toxic protein recognition model can be determined as the target toxic protein sequence if it meets the toxicity characteristics.

[0050] S130. Construct a toxic protein database using the target toxic protein sequence.

[0051] The toxic protein database may be a resource database for storing and providing a large amount of sequence structure data and related information of known toxic proteins.

[0052] Specifically, the toxic protein sequences that have undergone secondary screening are all high-reliability target toxic protein sequences that meet the characteristics of toxic proteins in terms of features and functions. Furthermore, a database architecture that can store, manage, and retrieve toxic protein sequences can be designed and the screened target toxic protein sequences can be stored in the database so that researchers can easily access and use these data. For example, Figure 1bThe target toxin protein sequences obtained by double screening are used to construct the toxin protein database TOXINIA, such as Figure 1b As shown, a conventional BLAST search can be performed on the toxin protein sequence, and the toxin protein information can be refined by screening according to different similarities.

[0053] In the above embodiment, the common peptide structure corresponding to the confirmed toxic protein sequence is obtained, and based on the functional performance characteristic data and fluctuation trend characteristic data of the common peptide structure, a target toxic protein core peptide set that can cover the key functional domains of the confirmed toxic protein sequence is constructed. The target toxic protein core peptide set is used to perform functional screening on the functional characteristic domain of the protein sequence to be identified, and an intermediate protein sequence that needs to be verified whether it meets the toxic characteristics is obtained. The intermediate protein sequence is screened for toxicity in the toxic characteristic domain, and the intermediate protein sequence that meets the toxic characteristics is determined as the target toxic protein sequence. Finally, the target toxic protein sequence is used to construct a toxic protein database. At this point, a two-level screening method combining functional screening and toxicity screening is implemented to realize a toxic protein library construction method with a wide coverage range that can not only discover new toxic proteins but also detect low-abundance toxic proteins.

[0054] In some embodiments, based on the functional performance characteristic data and fluctuation trend characteristic data of the common peptide structure, a target toxic protein core peptide set that can cover the key functional domains of the confirmed toxic protein sequence is constructed. Please refer to the attached Figure 2 ,include:

[0055] S210, aggregate the common peptide structure into the core peptide of the toxic protein family.

[0056] Among them, the toxin protein family core peptides can refer to representative and conservative peptides in the toxin protein family. These peptides are ubiquitous in toxin proteins and are closely related to the toxic function of toxin proteins. Specifically, the common peptide structure in the toxin protein sequence can be identified by bioinformatics tools and algorithms, and the common peptide structure extracted from the confirmed toxin protein sequence can be further polymerized into toxin protein family core peptides (Toxin Protein Family Featured Peptides, referred to as TFFP), which contain fragments with strong specificity for toxic proteins, ensuring that the target toxin protein core peptide set established subsequently has a strong recognition ability for toxin protein specificity.

[0057] S220. Clustering is performed based on the functional performance characteristic data and fluctuation trend characteristic data of the core peptides of the toxic protein family to obtain multiple initial toxic protein core peptide sets.

[0058] Among them, the initial toxic protein core peptide set can also refer to a toxic protein core peptide set that is clustered into a group of toxic protein core peptides with a common peptide structure that are similar in functional performance and have a common fluctuation trend in fluctuation structure. It should be understood that the initial toxic protein core peptide set is a preliminary set formed by clustering the functional performance characteristic data and fluctuation trend characteristic data of the core peptides of the toxic protein family, and may contain multiple toxic protein core peptides with similar functions or structural characteristics.

[0059] Specifically, clustering can be based on the co-fluctuation principle of the characteristic plane, determine the TFFPs with highly correlated fluctuation trends and merge them to realize the clustering process. It can be understood that the co-fluctuation principle of the characteristic plane shows that under the same biological function or specific action, the expression patterns of different characteristic modules usually show a consistent fluctuation trend, that is, under similar conditions, their expression characteristics change trends are similar and have strong synergy. Therefore, based on this, a similarity matrix between multiple TFFPs can be constructed to calculate the correlation and consistency between each TFFP. Specifically, the expression pattern of each TFFP is first analyzed, its fluctuation on the characteristic plane is quantified, and a similarity matrix is ​​constructed to quantify the correlation between different TFFPs. Furthermore, for TFFPs that show high correlation in the similarity matrix, they can be identified as modules with the same or similar fluctuation trends, and these TFFPs with consistent expression patterns and the same fluctuation trends are clustered into an initial toxic protein core peptide set.

[0060] S230, matching the confirmed toxic protein sequence with each initial toxic protein core peptide set to confirm the target toxic protein core peptide set in multiple initial toxic protein core peptide sets.

[0061] Specifically, the matching degree between the confirmed toxic protein sequence and each initial toxic protein core peptide set can be calculated to identify the best matching toxic protein core peptide set for each toxic protein and use it as the target toxic protein core peptide set. These several target toxic protein core peptide sets cover the key functional domains of the toxic protein, ensuring the high functionality and specificity of the toxic protein database finally constructed.

[0062] Optionally, the target toxic protein core peptide set can also be confirmed by calculating the correlation weights between different initial toxic protein core peptide sets, and combining their functional characteristics to identify modules with similar functions and related fluctuation trends in the same dimension, and clustering them into larger functional TFFP modules, that is, merging initial toxic protein core peptide sets with completely overlapping functions or highly consistent fluctuation trends, to achieve effective module redundancy contraction and enhance the stability and reliability of the TFFP module.

[0063] Furthermore, according to the distribution of toxic protein toxicity and the number of TFFPs in each initial toxic protein core peptide set, a toxic protein core peptide set that meets the high stability requirements is screened out. Among them, the toxic protein core peptide set with high stability meets the following conditions: it can enrich at least two or more toxicity information and contains at least two or more toxic protein family core peptides. The toxic protein core peptide set that meets these conditions can be regarded as a stable toxic protein core peptide set. And because they can maintain consistent performance in different characteristic peptides, they can be used as the target toxic protein core peptide set.

[0064] In the above implementation, by confirming the toxic protein sequence and performing step-by-step analysis and processing, the target toxic protein core peptide set is finally determined, which helps to accurately identify and classify toxic proteins and provide a scientific basis for building a high-quality toxic protein database. At the same time, this method can also improve the accuracy of toxic protein identification, reduce data redundancy, and provide more reliable data support for toxicology research and drug development.

[0065] In some embodiments, the confirmed toxic protein sequence is matched with each initial toxic protein core peptide set to confirm the target toxic protein core peptide set in multiple initial toxic protein core peptide sets. Figure 3a ,include:

[0066] S310. Perform functional enrichment analysis on each initial toxic protein core peptide set to obtain the functional characteristics of each initial toxic protein core peptide set.

[0067] Among them, functional enrichment analysis is a bioinformatics method used to determine whether certain biological functions or processes are over- or under-represented in a group of proteins to help identify biological pathways or functional categories that are significantly active under specific conditions, that is, to perform functional annotations on them. Functional features refer to the biological functional attributes of proteins to describe and classify certain characteristics of the biological effects of proteins. For example, functional features can refer to biological processes, molecular functions, or cellular components in which the core peptide of a toxic protein participates.

[0068] Specifically, each initial toxic protein core peptide set is analyzed using bioinformatics tools and databases to identify the common functions of the proteins in these sets. Furthermore, by comparing the functional distribution of these sets with background proteins (such as confirmed toxic proteins), it is determined which functions are enriched in the set. Exemplarily, the frequency and enrichment of a certain functional feature in each initial toxic protein core peptide set are calculated. When the enrichment of the functional feature in a certain initial toxic protein core peptide set reaches above the 90% quantile, the initial toxic protein core peptide set is identified as an initial toxic protein core peptide set with a significant enrichment of the functional feature. Similarly, based on most of the enriched functional features, including molecular functions (such as protein binding, catalytic activity, etc.) and biological processes (such as cellular processes, metabolic processes, etc.), a functional enrichment analysis is performed for each initial toxic protein core peptide set to assign functional annotations, that is, the functional features of each initial toxic protein core peptide set are obtained. Exemplarily, if the adhesion of the toxic protein is used as a functional feature, please refer to Figure 3b In the figure, the horizontal axis is the ID number of different toxin protein core peptide sets, and the vertical axis is the distribution of toxin protein enrichment. The figure shows the adhesion of each toxin protein core peptide set to the toxin protein, and shows the distribution of different toxin protein core peptide sets in terms of toxin protein enrichment.

[0069] S320. Based on the functional characteristics of each initial toxic protein core peptide set, calculate the matching degree between the confirmed toxic protein sequence and each initial toxic protein core peptide set.

[0070] Specifically, the functional annotation results (i.e., functional features) of each initial toxic protein core peptide set obtained by functional enrichment analysis are used to evaluate the functional similarity of each initial toxic protein core peptide set with the known confirmed toxic protein sequence. Furthermore, by calculating the matching degree of the functional features, the matching similarity between the confirmed toxic protein sequence and the initial toxic protein core peptide set can be quantified.

[0071] Exemplarily, functional enrichment analysis is first used to determine functional features from the confirmed toxic protein sequence and each initial toxic protein core peptide set, including the biological function of the protein, molecular function (such as protein binding, catalytic activity, etc.) and biological process (such as cellular process, metabolic process, etc.), and these functional features are used to functionally annotate each initial toxic protein core peptide set. Secondly, taking GPCR_Rhodpsn_7TM as an example, if the matching degree of the functional feature is to be calculated, it is necessary to convert it into a numerical feature vector first. That is, the frequency of occurrence of the functional feature in the confirmed toxic protein sequence and each initial toxic protein core peptide set or other relevant numerical indicators are calculated for quantitative analysis. Further, using similarity calculation methods such as cosine similarity or Jaccard similarity coefficient, the functional similarity of the feature vector in the confirmed toxic protein sequence and each initial toxic protein core peptide set is compared, and several matching scores are obtained. These matching scores can be used to evaluate the functional similarity between the confirmed toxic protein sequence and each initial toxic protein core peptide set in the functional feature of GPCR_Rhodpsn_7TM. Similarly, multiple functional features can also be converted into numerical feature vectors, and each feature can correspond to a functional dimension. Then, for each initial toxic protein core peptide set, a multidimensional numerical feature vector can be obtained, which contains functional features of multiple functional dimensions for subsequent calculation and matching.

[0072] S330, determining the initial toxic protein core peptide set corresponding to the highest matching degree as the target toxic protein core peptide set.

[0073] Specifically, after quantifying the matching degree between the confirmed toxic protein sequence and the initial toxic protein core peptide set, the initial toxic protein core peptide set that is most similar to the functional characteristics of the confirmed toxic protein sequence can be selected. That is, the initial toxic protein core peptide set corresponding to the highest matching degree is determined as the target toxic protein core peptide set to ensure that the target toxic protein core peptide set is most likely to contain key functional domains similar to the confirmed toxic protein. Exemplarily, for each functional feature determined by the functional enrichment analysis, the matching degree between the confirmed toxic protein sequence and each initial toxic protein core peptide set is calculated to identify the best matching toxic protein core peptide set for the confirmed toxic protein. After screening, 274 mature toxic protein core peptide sets were finally determined, and they can be used as the target toxic protein core peptide set. These target toxic protein core peptide sets serve as the core classification structure of the toxic protein database, covering the key functional domains of the toxic protein, ensuring the high functionality and specificity of the toxic protein database.

[0074] For example, please refer to Table 1, which shows the number of functional annotations and corresponding functional domain characteristics of each toxic protein core peptide set.

[0075] Table 1 Functional annotation statistics of target toxic protein core peptide collection

[0076]

[0077]

[0078] It is understandable that the proteins enriched in each TFFP module usually have the same or similar functional domains, such as GPCR_Rhodpsn_7TM, P-loop_NTPase and Prot_kinase_dom, which are common and biologically important functional features in toxic proteins. It can be proved that the target toxic protein core peptide set can effectively focus on specific functional groups and achieve highly specific functional annotations. In addition, during the database construction process, the target toxic protein core peptide set can accurately identify and classify toxic proteins, effectively reduce noise data, and improve the accuracy of annotations, thereby improving the overall quality of the database.

[0079] Similarly, reference can also be made to Table 2 , which shows the total number of adhesion proteins in each toxin protein core peptide set, the category of functional annotation, the number of proteins that meet the annotation, and the proportion.

[0080] Table 2 Statistics and functional annotation analysis of adhesion proteins in the core peptide collection of target toxic proteins

[0081]

[0082] As can be seen from the table, the vast majority of toxic proteins have a high degree of consistency in the functional annotations of the corresponding target toxic protein core peptide sets, and the proportion of proteins that meet the annotations reaches 80%-100%, and even reaches 100% in some target toxic protein core peptide sets. This result shows that the target toxic protein core peptide set is highly stable when classifying and annotating toxic proteins. That is, the target toxic protein core peptide set can effectively enrich toxic proteins of the same functional group, thereby ensuring the accuracy of the functional annotations of the database. Especially in modules with a large total number of adhesion proteins (such as TFFP Module 23 and TFFPModule 9), it shows that these toxic protein core peptide sets can still maintain a high degree of functional consistency and have excellent stability.

[0083] In the above implementation, functional enrichment analysis is performed for each initial toxic protein core peptide set to give functional annotations, that is, the functional characteristics of each initial toxic protein core peptide set are obtained to ensure that each toxic protein core peptide set has a clear biological meaning and distinguishing ability in the discrimination process, thereby enhancing the accuracy and interpretability of the discrimination. At the same time, through functional enrichment analysis and matching calculation, toxic proteins can be more accurately identified and classified, providing more reliable data support for toxicological research and drug development.

[0084] In some embodiments, the consensus peptide structure is constructed in the following manner: a multiple sequence alignment method is used to analyze the confirmed toxic protein sequence to extract the consensus peptide structure in the confirmed toxic protein sequence.

[0085] Specifically, based on the confirmed toxin protein sequences collected from the database, preliminary preprocessing operations are performed on them, which may include removing non-coding regions or adjusting the sequence length for easy comparison. Furthermore, the toxin protein sequences are analyzed using a multiple sequence alignment method to identify similar regions and differences between sequences and display them in the form of an alignment matrix. Finally, representative conserved peptides are extracted as common peptide structures for subsequent aggregation into toxin protein family core peptides (Toxin Protein Family Featured Peptides, referred to as TFFP) to ensure their specific recognition ability for toxin proteins.

[0086] In the above embodiment, a multiple sequence alignment method is used to extract common peptide segments representing the key characteristics of toxic proteins from the alignment results so as to be subsequently aggregated into core peptides of the toxic protein family, thereby providing important characteristic information for constructing a toxic protein database and helping to improve the accuracy and practicality of the database.

[0087] In some embodiments, please refer to the attached Figure 4 , the toxic protein recognition model is obtained by the following method:

[0088] S410, obtaining an initial toxic protein sequence set and an initial non-toxic protein sequence set.

[0089] Among them, the initial toxic protein sequence set may refer to a set consisting of a group of known toxic protein sequences obtained from the whole library protein database, which are similar to the confirmed toxic protein sequences in functional performance and have a common fluctuation trend in fluctuation structure. The initial non-toxic protein sequence set may refer to a set consisting of a group of known non-toxic protein sequences corresponding to the initial toxic protein sequence set obtained from the whole library protein database. Similarly, the initial toxic protein sequence set and the initial non-toxic protein sequence set can be screened and obtained from multiple databases such as the Toxin and Toxin Target Database (T3DB) database or the UNIPROT database.

[0090] S420, using the target toxic protein core peptide set to match the initial toxic protein sequence set and the initial non-toxic protein sequence set respectively, to obtain a matched toxic protein sequence set and a matched non-toxic protein sequence set.

[0091] It can be understood that if the initial toxic protein sequence set is used as a positive sample for training the toxic protein recognition model, and the initial non-toxic protein sequence set is used as a negative sample for training the toxic protein recognition model, in order to ensure that it is highly representative and accurate, it is also necessary to use the target toxic protein core peptide set to match the initial toxic protein sequence set and the initial non-toxic protein sequence set respectively, that is, use the target toxic protein core peptide set as a feature to compare with each protein sequence in the initial toxic protein sequence set and the initial non-toxic protein sequence set to identify and extract matching toxic protein sequences.

[0092] Exemplarily, a matching threshold can be set to determine the degree of similarity between a non-toxic protein sequence and the target toxic protein core peptide set before it can be considered a potential toxic protein sequence. Further, based on the matching threshold, protein sequences with significant similarity to the target toxic protein core peptide set are screened from the protein sequences in the initial toxic protein sequence set and the initial non-toxic protein sequence set, and a matched toxic protein sequence set is formed, which contains protein sequences that are considered to have potential toxic characteristics. At the same time, protein sequences that do not meet the matching criteria are formed into a matched non-toxic protein sequence set, and finally a matched toxic protein sequence set and a matched non-toxic protein sequence set are obtained.

[0093] Among them, the matched toxic protein sequence set may refer to a sequence set consisting of toxic proteins with toxic characteristics that have significant matches with the target toxic protein core peptides after matching and screening the target toxic protein core peptide set with the initial toxic protein sequence set. The matched non-toxic protein sequence set is a sequence set consisting of the original initial non-toxic protein sequence set and the non-toxic proteins that are screened out from the original initial toxic protein sequence set after matching with the target toxic protein core peptide set and do not have toxic characteristics.

[0094] S430, performing model training and model testing based on the matched toxic protein sequence set and the matched non-toxic protein sequence set to obtain a toxic protein recognition model.

[0095] It is understandable that after matching and screening with the target toxic protein core peptide set, the matched toxic protein sequence set and the matched non-toxic protein sequence set are ensured to ensure their reliability and accuracy, and the training set and test set for model training and model testing can be constructed, and further, the training set is trained using a machine learning algorithm, and the recognition accuracy of the model is evaluated on the test set. Finally, a toxic protein recognition model that accurately and stably recognizes toxic proteins is obtained, so as to accurately identify the target toxic protein sequence that meets the characteristics of toxic proteins in terms of characteristics and functions, and a toxic protein database is established based on it.

[0096] Optionally, a random forest algorithm can be used to train a toxic protein recognition model using a set of matched toxic protein sequences as positive samples and a set of matched non-toxic protein sequences as negative samples. During the training process, the toxic protein recognition model will learn the features that distinguish toxic proteins from non-toxic proteins. After the training is completed, the toxic protein recognition model can also be evaluated using a test set to ensure the accuracy and generalization ability of the model.

[0097] In the above embodiment, a machine model that can accurately and stably identify toxic proteins is constructed, which can quickly process and screen a large amount of sequence data, thereby reducing the experimental investment and time cost required for library construction. At the same time, since the input of the toxic protein recognition model is further matched with the target toxic protein core peptide set, it can achieve more sensitive recognition of low-abundance toxic proteins. This method makes up for the limitations of experimental detection and makes the toxic protein information in the constructed toxic protein database more comprehensive and accurate, which is convenient for subsequent research and application. In addition, combining model fine-tuning and transfer learning methods for training and testing can also improve the predictive ability of the toxic protein recognition model for new toxic proteins, especially toxic proteins that lack homologous sequences, greatly improving the sensitivity of the toxic protein database to new toxic proteins, and supporting the discovery of new targets in toxicology and drug development.

[0098] In some embodiments, the initial toxic protein sequence set and the initial non-toxic protein sequence set are obtained. Figure 5 ,include:

[0099] S510. Collect toxic protein data and non-toxic protein data from multiple protein databases.

[0100] Among them, toxic protein data may refer to protein data that has a certain similarity with the confirmed toxic protein sequence. Specifically, these data can be derived from a special toxic protein database or collected through literature research, and are used to identify and study toxic proteins. Exemplarily, protein data with a certain similarity to the confirmed toxic protein sequence can be collected from multiple databases such as the Toxin and Toxin Target Database (T3DB) database or UNIPROT as toxic protein data. Similarly, non-toxic protein data may refer to data containing known non-toxic protein sequences obtained from a full library protein database. Specifically, these data can be used to compare with toxic protein data to help establish features that distinguish toxic proteins from non-toxic proteins. Similarly, non-toxic protein sequences can be screened from databases such as UniProt and PDB as non-toxic protein data.

[0101] S520. Use homology modeling to remove redundant sequences from the toxic protein data to obtain cleaned toxic protein data.

[0102] Among them, homology modeling is a bioinformatics method used to predict the three-dimensional structure of proteins and identify their similarities based on the structural information of known homologous proteins (proteins with similar sequences and structures). Specifically, for the collected toxic protein data, duplicate and invalid sequences can be removed first to ensure the uniqueness of the data. Furthermore, highly similar toxic protein sequences are eliminated through homology screening to maintain the diversity of the data, and finally the cleaned toxic protein data is obtained.

[0103] S530 , performing format conversion based on the cleaned toxic protein data and the non-toxic protein data to obtain an initial toxic protein sequence set and an initial non-toxic protein sequence set.

[0104] Specifically, the cleaned toxic protein data and non-toxic protein data can be converted into a unified format to facilitate subsequent analysis and model training. After the format conversion is completed, the initial toxic protein sequence set and the initial non-toxic protein sequence set are obtained.

[0105] In the above-mentioned implementation, the collected toxic protein sequence data is deduplicated and de-redundant, duplicate or invalid sequences are effectively cleaned up, and homology modeling is used to remove toxic proteins that are highly similar to existing sequences. This method ensures that the content of the toxic protein database is more streamlined and efficient, significantly reduces data redundancy problems, and thus improves the storage and computing efficiency of the toxic protein database. Furthermore, by using a unified data format and annotation standard, toxic protein data from different databases are normalized to form a basic data set with high consistency. This consistency processing can effectively reduce problems such as incomplete annotations or inconsistent naming, and ensure the accuracy of the toxic protein database during large-scale applications and data mining.

[0106] In some embodiments, the method further includes: if the toxic protein recognition model recognizes an intermediate protein sequence that does not meet the toxicity characteristics, determining the intermediate protein sequence that does not meet the toxicity characteristics as a non-toxic protein sequence.

[0107] Specifically, the target toxic protein core peptide set is first used to perform functional screening on the protein sequence to be identified in the functional feature domain to obtain the intermediate protein sequence that needs to be verified to see if it meets the toxicity characteristics. Secondly, the intermediate protein sequence is screened for toxicity in the toxicity feature domain. If the toxic protein recognition model identifies an intermediate protein sequence that does not meet the toxicity characteristics, that is, an intermediate protein sequence does not meet the preset toxicity characteristic threshold or classification mode under the evaluation of the toxic protein recognition model, then this intermediate protein sequence will be considered to be non-compliant with the toxicity characteristics. Furthermore, the intermediate protein sequence will also be recorded and classified as a non-toxic protein sequence and added to the non-toxic protein sequence set to provide a more accurate data basis for subsequent training, testing or application of the toxic protein recognition model.

[0108] Optionally, if the above situation occurs when applying the toxic protein recognition model, the toxic protein database can be updated according to the recognition results of the toxic protein recognition model, and the sequences determined to be non-toxic proteins can be removed from the candidate list of potential toxic proteins to ensure the accuracy of the toxic protein database.

[0109] In the above implementation, this feedback update method helps researchers screen out potential non-toxic proteins from a large number of protein sequences, thereby more accurately identifying and classifying toxic proteins, and providing more reliable data support for toxicology research and drug development.

[0110] The present specification also provides a method for constructing a toxic protein library, which comprises the following steps:

[0111] S602. Collect and confirm toxic protein sequences from multiple protein databases.

[0112] S604. Analyze the confirmed toxic protein sequence using a multiple sequence alignment method to extract the common peptide structure in the confirmed toxic protein sequence.

[0113] S606. Aggregate the common peptide structure into the core peptide of the toxic protein family.

[0114] S608. Clustering is performed based on the functional performance characteristic data and fluctuation trend characteristic data of the core peptides of the toxic protein family to obtain multiple initial toxic protein core peptide sets.

[0115] S610. Perform functional enrichment analysis on each initial toxic protein core peptide set to obtain functional characteristics of each initial toxic protein core peptide set.

[0116] S612. Based on the functional characteristics of each initial toxic protein core peptide set, calculate the matching degree between the confirmed toxic protein sequence and each initial toxic protein core peptide set.

[0117] S614. Determine the initial toxic protein core peptide set corresponding to the highest matching degree as the target toxic protein core peptide set.

[0118] S616. Collect toxic protein data and non-toxic protein data from multiple protein databases.

[0119] S618. Use homology modeling to remove redundant sequences from the toxic protein data to obtain cleaned toxic protein data.

[0120] S620 , performing format conversion based on the cleaned toxic protein data and the non-toxic protein data to obtain an initial toxic protein sequence set and an initial non-toxic protein sequence set.

[0121] S622. Use the target toxic protein core peptide set to match the initial toxic protein sequence set and the initial non-toxic protein sequence set respectively, to obtain a matched toxic protein sequence set and a matched non-toxic protein sequence set.

[0122] S624. Perform model training and model testing based on the matched toxic protein sequence set and the matched non-toxic protein sequence set to obtain a toxic protein recognition model.

[0123] S626. Collect protein sequences to be identified from multiple protein databases.

[0124] S628. Use the target toxic protein core peptide set to perform functional screening on the protein sequence to be identified in the functional characteristic domain to obtain the intermediate protein sequence that needs to be verified to see if it meets the toxic characteristics.

[0125] S630. Use the toxic protein recognition model to perform toxicity screening on the intermediate protein sequence in the toxicity characteristic domain, and identify the intermediate protein sequence that meets the toxicity characteristics as the target toxic protein sequence.

[0126] S632: If the toxic protein recognition model recognizes an intermediate protein sequence that does not meet the toxicity characteristics, the intermediate protein sequence that does not meet the toxicity characteristics is determined as a non-toxic protein sequence, and added to the matched non-toxic protein sequence set for the toxic protein recognition model to perform model training and model testing.

[0127] S634. Construct a toxic protein database using the target toxic protein sequence.

[0128] It should be understood that, although the various steps in the above flowchart are displayed in sequence according to the indication of the arrows, these steps are not necessarily executed in sequence according to the order indicated by the arrows. Unless there is a clear description in this article, there is no strict order restriction on the execution of these steps, and these steps can be executed in other orders. Moreover, at least a part of the steps in the above flowchart may include multiple steps or multiple stages, and these steps or stages are not necessarily executed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily to be carried out in sequence, but can be executed in turn or alternately with other steps or at least a part of the steps or stages in other steps.

[0129] The present specification also provides a toxic protein library building device 600, such as Figure 6 As shown, it includes: a target toxic protein core peptide set construction module 610, a target toxic protein sequence determination module 620 and a toxic protein database construction module 630, wherein:

[0130] The target toxic protein core peptide set construction module 610 is used to obtain the common peptide structure corresponding to the confirmed toxic protein sequence, and based on the functional performance characteristic data and fluctuation trend characteristic data of the common peptide structure, construct a target toxic protein core peptide set that can cover the key functional domains of the confirmed toxic protein sequence.

[0131] The target toxic protein sequence determination module 620 is used to perform functional screening on the protein sequence to be identified in the functional characteristic domain using the target toxic protein core peptide set, obtain the intermediate protein sequence that needs to be verified whether it meets the toxic characteristics, and perform toxicity screening on the intermediate protein sequence in the toxic characteristic domain, and determine the intermediate protein sequence that meets the toxic characteristics as the target toxic protein sequence; wherein the intermediate protein sequence that meets the toxic characteristics is obtained by performing toxicity identification on the intermediate protein sequence through a toxic protein recognition model.

[0132] The toxic protein database construction module 630 is used to construct a toxic protein database using the target toxic protein sequence.

[0133] In some embodiments, the target toxic protein core peptide set construction module 610 is also used to construct a target toxic protein core peptide set that can cover the key functional domains of the confirmed toxic protein sequence based on the functional performance characteristic data and fluctuation trend characteristic data of the common peptide structure, including: aggregating the common peptide structure into toxic protein family core peptides; clustering based on the functional performance characteristic data and fluctuation trend characteristic data of the toxic protein family core peptides to obtain multiple initial toxic protein core peptide sets; matching the confirmed toxic protein sequence with each initial toxic protein core peptide set to confirm the target toxic protein core peptide set in the multiple initial toxic protein core peptide sets.

[0134] In some embodiments, the target toxic protein core peptide set construction module 610 is also used to match the confirmed toxic protein sequence with each initial toxic protein core peptide set to confirm the target toxic protein core peptide set among multiple initial toxic protein core peptide sets, including: performing functional enrichment analysis on each initial toxic protein core peptide set to obtain the functional characteristics of each initial toxic protein core peptide set; based on the functional characteristics of each initial toxic protein core peptide set, calculating the matching degree between the confirmed toxic protein sequence and each initial toxic protein core peptide set; and determining the initial toxic protein core peptide set corresponding to the highest matching degree as the target toxic protein core peptide set.

[0135] In some embodiments, the target toxic protein core peptide set construction module 610 is also used to construct a common peptide structure in the following manner: using a multiple sequence alignment method to analyze the confirmed toxic protein sequence to extract the common peptide structure in the confirmed toxic protein sequence.

[0136] In some embodiments, the target toxic protein sequence determination module 620 is also used to obtain a toxic protein recognition model in the following manner: obtaining an initial toxic protein sequence set and an initial non-toxic protein sequence set; using a target toxic protein core peptide set to match the initial toxic protein sequence set and the initial non-toxic protein sequence set, respectively, to obtain a matched toxic protein sequence set and a matched non-toxic protein sequence set; performing model training and model testing based on the matched toxic protein sequence set and the matched non-toxic protein sequence set to obtain a toxic protein recognition model.

[0137] In some embodiments, the target toxic protein sequence determination module 620 is also used to obtain an initial toxic protein sequence set and an initial non-toxic protein sequence set, including: collecting toxic protein data and non-toxic protein data from multiple protein databases; removing redundant sequences from the toxic protein data using homology modeling to obtain cleaned toxic protein data; performing format conversion based on the cleaned toxic protein data and non-toxic protein data to obtain an initial toxic protein sequence set and an initial non-toxic protein sequence set.

[0138] In some embodiments, a toxic protein library building device 600 is also used to determine the intermediate protein sequence that does not meet the toxicity characteristics as a non-toxic protein sequence if the toxic protein recognition model identifies the intermediate protein sequence that does not meet the toxicity characteristics.

[0139] For the specific definition of a toxic protein library construction device, please refer to the definition of a toxic protein library construction method above, which will not be repeated here. Each module in the above-mentioned toxic protein library construction device can be implemented in whole or in part by software, hardware and a combination thereof. The above-mentioned modules can be embedded in or independent of the processor in the computer device in the form of hardware, or can be stored in the memory of the computer device in the form of software, so that the processor can call and execute the operations corresponding to the above modules.

[0140] In this embodiment, a toxic protein library building device is presented in the form of a functional unit, where the unit refers to an ASIC (Application Specific Integrated Circuit) circuit, a processor and memory that executes one or more software or fixed programs, and / or other devices that can provide the above functions.

[0141] The embodiment of the present application also provides a computer device, which may be a terminal, and its internal structure diagram may be as follows: Figure 7As shown. The computer device includes a processor, a memory, a communication interface, a display screen and an input device connected by a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The communication interface of the computer device is used to communicate with an external terminal in a wired or wireless manner, and the wireless manner can be achieved through WIFI, a mobile cellular network, NFC (near field communication) or other technologies. When the computer program is executed by the processor, a method for building a toxic protein library is implemented. The display screen of the computer device can be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer device can be a touch layer covered on the display screen, or a key, trackball or touchpad set on the computer device housing, or an external keyboard, touchpad or mouse, etc.

[0142] Those skilled in the art will understand that Figure 7 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0143] The embodiment of the present application also provides a computer-readable storage medium. The above method according to the embodiment of the present application can be implemented in hardware, firmware, or can be implemented as a computer code that can be recorded in a storage medium, or can be implemented as a computer code that is originally stored in a remote storage medium or a non-temporary machine-readable storage medium and will be stored in a local storage medium through a network download, so that the method described herein can be stored in such software processing on a storage medium using a general-purpose computer, a dedicated processor, or programmable or dedicated hardware. Among them, the storage medium can be a magnetic disk, an optical disk, a read-only storage memory, a random access memory, a flash memory, a hard disk or a solid-state hard disk, etc.; further, the storage medium can also include a combination of the above types of memories. It can be understood that a computer, a processor, a microprocessor controller, or programmable hardware includes a storage component that can store or receive software or computer code. When the software or computer code is accessed and executed by a computer, a processor, or hardware, the method shown in the above embodiment is implemented.

[0144] The embodiment of the present application provides a computer program product, which includes computer instructions, which are stored in a computer-readable storage medium. A processor of a computer device reads the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions, so that the computer device executes the method of any embodiment of the present application.

[0145] The method, device, equipment and medium for building a toxic protein library described in the above embodiments can be implemented by a computer chip or entity, or by a product with a certain function. A typical implementation device is a computer. Specifically, the computer can be, for example, a personal computer, a laptop computer, a cellular phone, a camera phone, a smart phone, a personal digital assistant, a media player, a navigation device, an email device, a game console, a tablet computer, a wearable device, or a combination of any of these devices.

[0146] For the convenience of description, the above device is described in various units according to their functions. Of course, when implementing the present application, the functions of each unit can be implemented in the same or multiple software and / or hardware.

[0147] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment in combination with software and hardware. Moreover, the present application may adopt the form of a computer program product implemented in one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that include computer-usable program code.

[0148] The present application is described with reference to the flowchart and / or block diagram of the method, device (system) and computer program product according to the embodiment of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, and the combination of the process and / or box in the flowchart and / or block diagram can be realized by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device produce a device for realizing the function specified in one process or multiple processes in the flowchart and / or one box or multiple boxes in the block diagram.

[0149] These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer-readable memory produce a manufactured product including an instruction device that implements the functions specified in one or more processes in the flowchart and / or one or more boxes in the block diagram.

[0150] These computer program instructions may also be loaded onto a computer or other programmable data processing device so that a series of operational steps are executed on the computer or other programmable device to produce a computer-implemented process, whereby the instructions executed on the computer or other programmable device provide steps for implementing the functions specified in one or more processes in the flowchart and / or one or more boxes in the block diagram.

[0151] In the description of this specification, the description with reference to the terms "one embodiment", "some embodiments", "example", "specific example", or "some examples" means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present application. In this specification, the schematic representation of the above terms does not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described may be combined in any one or more embodiments or examples in a suitable manner.

[0152] In addition, the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Therefore, the features defined as "first" and "second" may explicitly or implicitly include at least one of the features. In the description of this application, the meaning of "plurality" is at least two, such as two, three, etc., unless otherwise clearly and specifically defined.

[0153] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, commodity or device including the elements.

[0154] Each embodiment in this specification is described in a progressive manner, and the same or similar parts between the embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. Since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment.

[0155] The above are only embodiments of the present application and are not intended to limit the present application. For those skilled in the art, the present application may have various changes and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included within the scope of the claims of the present application.

[0156] Although the embodiments of the present application are described in conjunction with the accompanying drawings, those skilled in the art may make various modifications and variations without departing from the spirit and scope of the present application, and such modifications and variations are all within the scope defined by the appended claims.

Claims

1. A method for constructing a toxic protein library, characterized in that: The method comprises: Obtaining the common peptide structure corresponding to the confirmed toxic protein sequence, and constructing a target toxic protein core peptide set that can cover the key functional domains of the confirmed toxic protein sequence based on the functional performance characteristic data and fluctuation trend characteristic data of the common peptide structure; The target toxic protein core peptide set is used to perform functional screening on the protein sequence to be identified in the functional characteristic domain to obtain an intermediate protein sequence that needs to be verified whether it meets the toxic characteristics, and the intermediate protein sequence is screened for toxicity in the toxic characteristic domain, and the intermediate protein sequence that meets the toxic characteristics is determined as the target toxic protein sequence; wherein the intermediate protein sequence that meets the toxic characteristics is obtained by performing toxicity recognition on the intermediate protein sequence through a toxic protein recognition model; A toxic protein database is constructed using the target toxic protein sequence.

2. The method according to claim 1, characterized in that The functional performance characteristic data and fluctuation trend characteristic data based on the common peptide structure are used to construct a target toxic protein core peptide set that can cover the key functional domains of the confirmed toxic protein sequence, including: aggregating the common peptide structure into a core peptide of the toxic protein family; Clustering is performed based on the functional performance characteristic data and fluctuation trend characteristic data of the core peptides of the toxic protein family to obtain multiple initial toxic protein core peptide sets; The confirmed toxic protein sequence is matched with each of the initial toxic protein core peptide sets to confirm the target toxic protein core peptide set in the multiple initial toxic protein core peptide sets.

3. The method according to claim 2, characterized in that The step of matching the confirmed toxic protein sequence with each of the initial toxic protein core peptide sets to confirm the target toxic protein core peptide set in the multiple initial toxic protein core peptide sets comprises: Performing functional enrichment analysis on each of the initial toxic protein core peptide sets to obtain functional characteristics of each of the initial toxic protein core peptide sets; Based on the functional characteristics of each of the initial toxic protein core peptide sets, calculating the matching degree between the confirmed toxic protein sequence and each of the initial toxic protein core peptide sets; The initial toxic protein core peptide set corresponding to the highest matching degree is determined as the target toxic protein core peptide set.

4. The method according to claim 1, characterized in that: The consensus peptide structure was constructed by: The confirmed toxic protein sequence is analyzed using a multiple sequence alignment method to extract the common peptide structure in the confirmed toxic protein sequence.

5. The method according to claim 1, characterized in that The toxin protein recognition model is obtained by the following method: Obtaining an initial toxic protein sequence set and an initial non-toxic protein sequence set; Using the target toxic protein core peptide set to match the initial toxic protein sequence set and the initial non-toxic protein sequence set, respectively, to obtain a matched toxic protein sequence set and a matched non-toxic protein sequence set; Model training and model testing are performed based on the matched toxic protein sequence set and the matched non-toxic protein sequence set to obtain the toxic protein recognition model.

6. The method according to claim 5, characterized in that The obtaining of the initial toxic protein sequence set and the initial non-toxic protein sequence set comprises: Collect toxic protein data and non-toxic protein data from multiple protein databases; Using homology modeling to remove redundant sequences from the toxic protein data to obtain cleaned toxic protein data; Format conversion is performed based on the cleaned toxic protein data and the non-toxic protein data to obtain the initial toxic protein sequence set and the initial non-toxic protein sequence set.

7. The method according to claim 1, characterized in that The method further comprises: If the toxic protein recognition model recognizes an intermediate protein sequence that does not meet the toxicity characteristics, the intermediate protein sequence that does not meet the toxicity characteristics is determined as a non-toxic protein sequence.

8. A toxic protein library building device, characterized in that: The device comprises: A target toxic protein core peptide set construction module is used to obtain a common peptide structure corresponding to a confirmed toxic protein sequence, and based on the functional performance characteristic data and fluctuation trend characteristic data of the common peptide structure, construct a target toxic protein core peptide set that can cover the key functional domains of the confirmed toxic protein sequence; A target toxic protein sequence determination module is used to perform functional screening on the protein sequence to be identified in the functional characteristic domain using the target toxic protein core peptide set to obtain an intermediate protein sequence that needs to be verified to be consistent with the toxic characteristics, and to perform toxicity screening on the intermediate protein sequence in the toxicity characteristic domain, and determine the intermediate protein sequence that meets the toxic characteristics as the target toxic protein sequence; wherein the intermediate protein sequence that meets the toxic characteristics is obtained by performing toxicity identification on the intermediate protein sequence by a toxic protein recognition model; The toxic protein database construction module is used to construct a toxic protein database using the target toxic protein sequence.

9. A computer device, characterized in that: include: A memory and a processor, wherein the memory and the processor are communicatively connected to each other, the memory stores computer instructions, and the processor executes the method for building a toxic protein library according to any one of claims 1 to 7 by executing the computer instructions.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a computer to execute a toxic protein library construction method according to any one of claims 1 to 7.

Images