Allergen identification system based on allergen family characteristic peptide group

Abstract

The invention discloses an allergen identification system based on an allergen family characteristic peptide group. According to the system, the allergen characteristic peptide group is obtained through an allergen characteristic peptide group determination module; an enriched allergen characteristic peptide group, enriched allergens, functional characteristics and distribution characteristics are determined through a distribution characteristic acquisition module according to the allergens and the allergen characteristic peptide group; determining a stable allergen characteristic peptide group, multi-target characteristics and an allergen recognition characteristic set according to the enriched allergen characteristic peptide group through an allergen recognition characteristic set construction module; obtaining an unknown allergen feature vector through an unknown allergen feature vector generation module according to the unknown allergen sequence and the stable allergen feature peptide group; and inputting the unknown allergen feature vector into a preset allergen discrimination model through a discrimination result determination module, and then determining a discrimination result of the unknown allergen sequence. According to the invention, the accuracy of distinguishing unknown allergens is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of allergen identification, and in particular to an allergen identification system based on characteristic peptide groups of allergen families. Background Art

[0002] Currently, with the increasing incidence of allergic reactions, rapid and accurate identification of allergens is of great significance in the diagnosis and prevention of allergic diseases. Most of the existing allergen identification methods are based on feature extraction and classification algorithms of protein sequences, but their accuracy and generalization ability vary due to different feature engineering technologies. Currently, commonly used allergen identification software includes ALLERGENFP, ALLERTOP, ALLERMATCH and SORTALLER. They mainly rely on the conversion of protein amino acid sequence features and different classification algorithms to extract and screen protein information related to allergen characteristics.

[0003] Most of the existing allergen identification methods are based on manual experience. Although they provide prediction standards to a certain extent, this method is difficult to accurately identify new or unknown allergens, which in turn reduces the accuracy of allergen identification. Summary of the invention

[0004] The present invention provides an allergen discrimination system based on a characteristic peptide group of an allergen family, which has wide applicability and stability in the face of new or unknown allergens, thereby improving the discrimination accuracy of unknown allergens.

[0005] An embodiment of the present invention provides an allergen identification system based on a characteristic peptide group of an allergen family, comprising:

[0006] Allergen characteristic peptide group determination module, distribution feature acquisition module, allergen identification feature set construction module, unknown allergen feature vector generation module and discrimination result determination module;

[0007] The allergen characteristic peptide group determination module is used to obtain the allergen characteristic peptide group according to the preset allergen database and the preset protein database;

[0008] The distribution feature acquisition module is used to determine the enriched allergen characteristic peptide group, the enriched allergens, the functional features corresponding to the enriched allergens, the enrichment and frequency corresponding to the allergens according to the allergens and the allergen characteristic peptide group, and obtain the distribution features of the enriched allergens according to the enrichment, frequency and functional features;

[0009] The allergen identification feature set construction module is used to determine a stable allergen feature peptide group with high stability and a multi-targeting feature based on the enriched allergen feature peptide group, and combine the multi-targeting feature, the distribution feature and the allergen feature peptide group to obtain an allergen identification feature set;

[0010] The unknown allergen feature vector generation module is used to obtain an unknown allergen feature vector according to the unknown allergen sequence to be identified and the stable allergen feature peptide group;

[0011] The above-mentioned discrimination result determination module is used to input the above-mentioned unknown allergen feature vector into a preset allergen discrimination model trained according to the above-mentioned allergen recognition feature set, so that the above-mentioned preset allergen discrimination model determines the discrimination result of the above-mentioned unknown allergen sequence according to the above-mentioned unknown allergen feature vector, the above-mentioned allergen recognition feature set, and the above-mentioned stable allergen characteristic peptide group.

[0012] Furthermore, the allergen characteristic peptide group is obtained according to the preset allergen database and the preset protein database, including:

[0013] Extracting allergen sequences from the above-mentioned preset allergen database;

[0014] Extracting non-allergen sequences from the preset protein database according to preset keywords, and removing duplicates from the non-allergen sequences to obtain a first simplified non-allergen sequence;

[0015] Calculating a first identity between the allergen sequence and the first simplified non-allergen sequence, retaining the first simplified non-allergen sequence whose first identity is less than a preset first identity threshold, and obtaining a second simplified non-allergen sequence;

[0016] The second simplified non-allergen sequence is divided into several amino acid sequences according to a preset number of amino acids, and the second identity between each amino acid sequence and the allergen sequence is calculated, and the amino acid sequence having the second identity less than a preset second identity threshold and not containing a preset number of consecutive identical amino acids in the amino acid sequence is determined as the third simplified non-allergen sequence;

[0017] Based on the above allergen sequence and the above third simplified non-allergen sequence, the above allergen characteristic peptide group is obtained.

[0018] Furthermore, the above allergen characteristic peptide group is obtained based on the above allergen sequence and the above third simplified non-allergen sequence, including:

[0019] The allergen sequence is segmented according to a preset base length by a sliding window method to obtain a number of allergen peptide segments;

[0020] Calculating the similarity between each of the above allergen peptide segments and each of the above third simplified non-allergen sequences, and retaining the allergen peptide segments whose similarity is not less than a preset similarity threshold, to obtain high-discrimination allergen peptide segments;

[0021] The adjacent high-discrimination allergen peptides on the same allergen sequence are spliced ​​to obtain the first allergen characteristic peptide;

[0022] Repeating the sequence alignment operation until a number of third allergen characteristic peptides are generated;

[0023] According to the third allergen characteristic peptide, the allergen characteristic peptide group is obtained;

[0024] Wherein, the above sequence comparison operation includes:

[0025] Obtaining the current second allergen characteristic peptide; wherein the initial second allergen characteristic peptide is the above-mentioned first allergen characteristic peptide;

[0026] Calculating the third identity between each current second allergen characteristic peptide and each of the above non-allergen sequences;

[0027] Comparing the current third identity with the above-mentioned preset first identity threshold;

[0028] If the current third identity is greater than the above-mentioned preset first identity threshold, the second allergen characteristic peptide corresponding to the current third identity is eliminated, and the second allergen characteristic peptides adjacent to each other on the above-mentioned allergen sequence among the remaining second allergen characteristic peptides are spliced ​​to obtain an updated second allergen characteristic peptide;

[0029] If the third identities of all current second allergen characteristic peptides are not greater than the above-mentioned preset first identity threshold, the current second allergen characteristic peptide is spliced ​​with another second allergen characteristic peptide adjacent to the above-mentioned allergen sequence to obtain a plurality of third allergen characteristic peptides.

[0030] Furthermore, the above-mentioned allergen characteristic peptide group is obtained based on the above-mentioned third allergen characteristic peptide, including:

[0031] According to the sequence characteristics of each third allergen characteristic peptide, a similarity matrix between each third allergen characteristic peptide is constructed;

[0032] The similarity scores between each pair of characteristic peptides of the third allergen are calculated based on the similarity matrix;

[0033] The third allergen characteristic peptides whose similarity scores are not less than a preset similarity score threshold are clustered to obtain the allergen characteristic peptide group.

[0034] Further, based on the allergens and the allergen characteristic peptide groups, the enriched allergen characteristic peptide groups, the enriched allergens, the functional characteristics corresponding to the enriched allergens, the enrichment and frequency corresponding to the allergens are determined, including:

[0035] Calculate the frequency and enrichment of each type of allergen in each of the above allergen characteristic peptide groups;

[0036] Determine the allergen characteristic peptide group with the above-mentioned enrichment greater than the preset enrichment threshold as the first enriched allergen characteristic peptide group, determine the allergens with the above-mentioned enrichment greater than the above-mentioned preset enrichment threshold as enriched allergens, and obtain the functional characteristics corresponding to the above-mentioned enriched allergens;

[0037] The functional characteristics of the corresponding enriched allergens are added to the above-mentioned first enriched allergen characteristic peptide group to generate the above-mentioned enriched allergen characteristic peptide group.

[0038] Furthermore, based on the above-mentioned enriched allergen characteristic peptide group, a stable allergen characteristic peptide group with high stability and multi-targeting characteristics is determined, including:

[0039] Calculating the correlation weights between different enriched allergen characteristic peptide groups, and merging the enriched allergen characteristic peptide groups whose correlation weights are not less than a preset correlation weight value or whose functional characteristics are the same according to the correlation weights and the functional characteristics, to obtain a functional allergen characteristic peptide group;

[0040] Obtaining the number of enriched allergens in the functional allergen characteristic peptide group and the number of the third allergen characteristic peptide;

[0041] Determine the functional allergen characteristic peptide group, in which the number of the enriched allergens is not less than the preset enriched allergen number threshold, and the number of the third allergen characteristic peptides is not less than the preset third allergen characteristic peptide number threshold, as the stable allergen characteristic peptide group with high stability;

[0042] Determine the number of different stable allergen characteristic peptide groups corresponding to the same enriched allergen;

[0043] If the above quantity is not less than the preset quantity threshold, the corresponding enriched allergen is determined to be a multi-targeted allergen;

[0044] Based on the above multi-targeted allergens, the above multi-targeted characteristics are obtained.

[0045] Furthermore, the above-mentioned multi-targeting characteristics are obtained based on the above-mentioned multi-targeting allergens, including:

[0046] Obtaining the enrichment, sequence characteristics, physicochemical characteristics and structural characteristics corresponding to the above multi-targeted allergens;

[0047] According to the principal component analysis method, the above-mentioned enrichment, the above-mentioned sequence characteristics, the above-mentioned physical and chemical characteristics and the above-mentioned structural characteristics, the principal component characteristics are obtained, and the above-mentioned principal component characteristics are used as the above-mentioned multi-targeting characteristics.

[0048] Furthermore, the unknown allergen feature vector is obtained based on the unknown allergen sequence to be identified and the stable allergen feature peptide group, including:

[0049] The unknown allergen sequence is segmented according to the preset base length by a sliding window method to obtain a number of unknown allergen peptide segments;

[0050] The above unknown allergen peptide segment is mapped to the above stable allergen characteristic peptide group to extract the first distribution feature and the first multi-targeting feature of the above unknown allergen peptide segment in each stable allergen characteristic peptide group, and then the above unknown allergen feature vector is generated according to the above first distribution feature and the first multi-targeting feature.

[0051] Furthermore, the preset allergen discrimination model determines the discrimination result of the unknown allergen sequence according to the unknown allergen feature vector, the allergen recognition feature set, and the stable allergen feature peptide group, including:

[0052] Extracting a second distribution feature and a second multi-targeting feature corresponding to the same allergen from the allergen identification feature set, and generating an allergen feature vector based on the second distribution feature and the second multi-targeting feature;

[0053] Based on the above unknown allergen feature vectors and the allergen feature vectors corresponding to different allergens, the feature similarity is calculated;

[0054] Calculating the third enrichment of the unknown allergen feature vector in each of the stable allergen feature peptide groups;

[0055] Counting a first number of stable allergen characteristic peptide groups whose third enrichment is greater than a preset third enrichment;

[0056] The identification result of the unknown allergen sequence is determined according to the feature similarity and the first quantity.

[0057] Furthermore, the determination of the identification result of the unknown allergen sequence according to the feature similarity and the first quantity includes:

[0058] When the feature similarity is greater than a preset feature similarity threshold, or the first quantity is greater than a preset first quantity threshold, the unknown allergen sequence is determined to be an allergen.

[0059] The embodiments of the present invention have the following beneficial effects:

[0060] The present invention provides an allergen discrimination system based on allergen family characteristic peptide groups. The above system includes: an allergen characteristic peptide group determination module, a distribution feature acquisition module, an allergen identification feature set construction module, an unknown allergen feature vector generation module and a discrimination result determination module; the above allergen characteristic peptide group determination module is used to obtain the allergen characteristic peptide group according to a preset allergen database and a preset protein database; the above distribution feature acquisition module is used to determine the enriched allergen characteristic peptide group, the enriched allergens, the functional features corresponding to the above enriched allergens, the enrichment and frequency corresponding to the above allergens according to the allergens and the allergen characteristic peptide group, and obtain the distribution features of the above enriched allergens according to the above enrichment, frequency and functional features; the above allergen identification feature set construction module is used to obtain the allergen characteristic peptide group according to the above enriched allergen characteristic peptide group. group, determine a stable allergen characteristic peptide group with high stability and a multi-targeting feature, and combine the above-mentioned multi-targeting feature, the above-mentioned distribution feature and the above-mentioned allergen characteristic peptide group to obtain an allergen recognition feature set; the above-mentioned unknown allergen feature vector generation module is used to obtain an unknown allergen feature vector according to the unknown allergen sequence to be judged and the above-mentioned stable allergen characteristic peptide group; the discrimination result determination module is used to input the above-mentioned unknown allergen feature vector into a preset allergen discrimination model trained according to the above-mentioned allergen recognition feature set, so that the above-mentioned preset allergen discrimination model determines the discrimination result of the above-mentioned unknown allergen sequence according to the above-mentioned unknown allergen feature vector, the above-mentioned allergen recognition feature set, and the above-mentioned stable allergen characteristic peptide group. Therefore, in the process of distinguishing unknown allergens, the present invention utilizes the feature vector of the unknown allergen and the constructed allergen recognition feature set including multi-targeting features, distribution features and allergen characteristic peptide groups, so that in the process of distinguishing unknown allergens, the multi-range features of the allergens are fully combined. Therefore, it has wide applicability and stability in the face of new or unknown allergens, thereby improving the accuracy of distinguishing unknown allergens. BRIEF DESCRIPTION OF THE DRAWINGS

[0061] Figure 1 It is a schematic diagram of the structure of an allergen discrimination system based on characteristic peptide groups of allergen families provided by one embodiment of the present invention.

[0062] Figure 2 It is a schematic diagram of a characteristic specificity curve between an allergen peptide segment and a third simplified non-allergen sequence provided by an embodiment of the present invention.

[0063] Figure 3 It is a schematic diagram of the stability curve of the stable allergen characteristic peptide group provided by one embodiment of the present invention. DETAILED DESCRIPTION

[0064] The technical solution of the present invention will be described clearly and completely below in conjunction with the accompanying drawings of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0065] like Figure 1 As shown, an allergen discrimination system based on a characteristic peptide group of an allergen family is provided in one embodiment of the present invention, comprising:

[0066] Allergen characteristic peptide group determination module, distribution feature acquisition module, allergen identification feature set construction module, unknown allergen feature vector generation module and discrimination result determination module;

[0067] The allergen characteristic peptide group determination module is used to obtain the allergen characteristic peptide group according to the preset allergen database and the preset protein database;

[0068] In a preferred embodiment, the allergen characteristic peptide group is obtained according to the preset allergen database and the preset protein database, including:

[0069] Extracting allergen sequences from the above-mentioned preset allergen database;

[0070] Specifically, the preset allergen database is the ALLEGENIA2.0 allergen database, and sequences of all allergens are extracted from the ALLEGENIA2.0 allergen database. The extracted allergen sequences are converted into FASTA format to ensure consistency of the data format, thereby obtaining the allergen sequences.

[0071] Extracting non-allergen sequences from the preset protein database according to preset keywords, and removing duplicates from the non-allergen sequences to obtain a first simplified non-allergen sequence;

[0072] Specifically, the protein database is the Uniprot database, and keywords such as "non-allergen", "nonallergenic", "non-allergenic", "hypoallergenic", "non-allergy", and "noallergenicity" are used to extract the possible non-allergen candidate sequences from the Uniprot database, and then the non-allergen candidate sequences are further screened according to the corresponding functional annotations, and the sequences that are not marked as allergens in the functional annotations are selected to obtain the non-allergen sequences. At the same time, the non-allergen sequences are converted into FASTA format to ensure data consistency.

[0073] Calculating a first identity between the allergen sequence and the first simplified non-allergen sequence, retaining the first simplified non-allergen sequence whose first identity is less than a preset first identity threshold, and obtaining a second simplified non-allergen sequence;

[0074] Preferably, the first identity threshold is preset to be 75%.

[0075] The second simplified non-allergen sequence is divided into several amino acid sequences according to a preset number of amino acids, and the second identity between each amino acid sequence and the allergen sequence is calculated, and the amino acid sequence having the second identity less than a preset second identity threshold and not containing a preset number of consecutive identical amino acids in the amino acid sequence is determined as the third simplified non-allergen sequence;

[0076] Specifically, the FAO / WHO criteria are applied for screening: within the 80 amino acid window, the sequence with the allergen sequence whose identity is lower than the preset second identity threshold of 35% and does not contain the preset number of consecutive identical amino acids, i.e., the sequence of 6 consecutive identical amino acid fragments, is used as the third simplified non-allergen sequence. Through this screening step, accurate and pure non-allergen sequences are generated, laying a solid foundation for subsequent feature extraction and analysis.

[0077] Based on the above allergen sequence and the above third simplified non-allergen sequence, the above allergen characteristic peptide group is obtained.

[0078] Preferably, deduplication processing is performed on the non-allergen sequences to remove redundant information, thereby simplifying the data structure and improving the accuracy of the data.

[0079] In this preferred embodiment, the allergen characteristic peptide group is obtained by using a preset allergen database and a preset protein database.

[0080] In another preferred embodiment, the allergen characteristic peptide group is obtained according to the allergen sequence and the third simplified non-allergen sequence, including:

[0081] The allergen sequence is segmented according to a preset base length by a sliding window method to obtain a number of allergen peptide segments;

[0082] Calculating the similarity between each of the above allergen peptide segments and each of the above third simplified non-allergen sequences, and retaining the allergen peptide segments whose similarity is not less than a preset similarity threshold, to obtain high-discrimination allergen peptide segments;

[0083] Specifically, the BLAST tool is used to perform a similarity comparison between each allergen peptide segment and the third simplified non-allergen sequence to obtain the similarity E between the two. The above-mentioned preset similarity is 0.5. The highly discriminating allergen peptide segment obtained is a peptide segment with allergen specificity. Schematically, the characteristic specificity curve between the allergen peptide segment and the third simplified non-allergen sequence is shown in FIG. Figure 2 As shown, Figure 2 The “E value” in represents the similarity E mentioned above.

[0084] The adjacent high-discrimination allergen peptides on the same allergen sequence are spliced ​​to obtain the first allergen characteristic peptide;

[0085] Repeating the sequence alignment operation until a number of third allergen characteristic peptides are generated;

[0086] According to the third allergen characteristic peptide, the allergen characteristic peptide group is obtained;

[0087] Wherein, the above sequence comparison operation includes:

[0088] Obtaining the current second allergen characteristic peptide; wherein the initial second allergen characteristic peptide is the above-mentioned first allergen characteristic peptide;

[0089] Calculating the third identity between each current second allergen characteristic peptide and each of the above non-allergen sequences;

[0090] Comparing the current third identity with the above-mentioned preset first identity threshold;

[0091] If the current third identity is greater than the above-mentioned preset first identity threshold, the second allergen characteristic peptide corresponding to the current third identity is eliminated, and the second allergen characteristic peptides adjacent to each other on the above-mentioned allergen sequence among the remaining second allergen characteristic peptides are spliced ​​to obtain an updated second allergen characteristic peptide;

[0092] If the third identities of all current second allergen characteristic peptides are not greater than the above-mentioned preset first identity threshold, the current second allergen characteristic peptide is spliced ​​with another second allergen characteristic peptide adjacent to the above-mentioned allergen sequence to obtain a plurality of third allergen characteristic peptides.

[0093] Specifically, the highly differentiated allergen peptides that fall on the same allergen sequence and are adjacent to each other are spliced ​​to form a preliminary allergen characteristic peptide (preAFFP), that is, the first allergen characteristic peptide mentioned above, to ensure the continuity and integrity of the characteristics.

[0094] Specifically, a recursive feature comparison elimination method is used to screen out the AFFP combination with minimal noise in a stepwise optimization manner, and then generate information-rich and reliable allergen family characteristic peptides, namely, several of the above-mentioned third allergen characteristic peptides.

[0095] Specifically, the first allergen characteristic peptide is compared with the non-allergen sequence, and peptides with high identity to the non-allergen sequence are identified and marked as noise. Then, after removing the noise peptides, the remaining peptides are adjacently spliced ​​to strengthen the peptides with allergen specificity, thereby improving the significance and reliability of the features. Through this recursive optimization method, each iteration can effectively reduce those high-discrimination allergen peptides with low identity but which may interfere with the accuracy of discrimination. The recursive process continues until no significant noise peptides are marked or removed, and finally a noise-minimized AFFP combination is obtained, that is, several third allergen characteristic peptides. This process ensures that the generated several third allergen characteristic peptides have high specificity and reliability, and can accurately reflect the core characteristics of allergens.

[0096] In this preferred embodiment, a third allergen characteristic peptide is generated by repeatedly performing the sequence alignment operation, and then an allergen characteristic peptide group is obtained based on the third allergen characteristic peptide.

[0097] In another preferred embodiment, the allergen characteristic peptide group is obtained according to the third allergen characteristic peptide, comprising:

[0098] According to the sequence characteristics of each third allergen characteristic peptide, a similarity matrix between each third allergen characteristic peptide is constructed;

[0099] The similarity scores between each pair of characteristic peptides of the third allergen are calculated based on the similarity matrix;

[0100] The third allergen characteristic peptides whose similarity scores are not less than a preset similarity score threshold are clustered to obtain the allergen characteristic peptide group.

[0101] Specifically, 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, this embodiment is based on the co-fluctuation principle of the characteristic plane, clustering and merging the third allergen characteristic peptides with highly correlated fluctuation trends, and finally obtaining the above-mentioned allergen characteristic peptide group. Among them, the correlation of the fluctuation trend is quantified by constructing a similarity matrix.

[0102] Preferably, through this clustering method, third allergen characteristic peptides with similar functions but loosely connected can be clustered together, making the clustered allergen characteristic peptide group more synergistic and representative, thereby improving the subsequent discrimination and generalization capabilities of unknown allergens.

[0103] In this preferred embodiment, the allergen characteristic peptide group is obtained by clustering the third allergen characteristic peptides.

[0104] The distribution feature acquisition module is used to determine the enriched allergen characteristic peptide group, the enriched allergens, the functional features corresponding to the enriched allergens, the enrichment and frequency corresponding to the allergens according to the allergens and the allergen characteristic peptide group, and obtain the distribution features of the enriched allergens according to the enrichment, frequency and functional features;

[0105] In a preferred embodiment, based on the allergens and the allergen characteristic peptide groups, the enriched allergens, the functional characteristics corresponding to the enriched allergens, the enrichment and frequency corresponding to the allergens are determined, including:

[0106] Calculate the frequency and enrichment of each type of allergen in each of the above allergen characteristic peptide groups;

[0107] Determine the allergen characteristic peptide group with the above-mentioned enrichment greater than the preset enrichment threshold as the first enriched allergen characteristic peptide group, determine the allergens with the above-mentioned enrichment greater than the above-mentioned preset enrichment threshold as enriched allergens, and obtain the functional characteristics corresponding to the above-mentioned enriched allergens;

[0108] The functional characteristics of the corresponding enriched allergens are added to the above-mentioned first enriched allergen characteristic peptide group to generate the above-mentioned enriched allergen characteristic peptide group.

[0109] Specifically, the frequency and enrichment of each type of allergen in each allergen characteristic peptide group are calculated. When the enrichment of a certain type of allergen in a certain allergen characteristic peptide group is greater than the preset enrichment threshold of 90%, it means that this type of allergen has a significant enrichment feature in this allergen characteristic peptide group.

[0110] Specifically, the above functional characteristics include: molecular functions (such as protein binding, catalytic activity, etc.) and biological processes (such as cellular processes, metabolic processes, etc.).

[0111] Preferably, functional features are added to the first enriched allergen characteristic peptide group to ensure that it has clear biological meaning and discrimination ability in the subsequent discrimination process of unknown allergen sequences, thereby enhancing the accuracy and interpretability of the discrimination results.

[0112] In this preferred embodiment, the enriched allergen characteristic peptide group, the enriched allergens, the functional characteristics corresponding to the enriched allergens, the enrichment degree and the frequency corresponding to the allergens are determined through the allergens and the allergen characteristic peptide group.

[0113] The allergen identification feature set construction module is used to determine a stable allergen feature peptide group with high stability and a multi-targeting feature based on the enriched allergen feature peptide group, and combine the multi-targeting feature, the distribution feature and the allergen feature peptide group to obtain an allergen identification feature set;

[0114] In a preferred embodiment, based on the above-mentioned enriched allergen characteristic peptide group, a stable allergen characteristic peptide group with high stability and multi-targeting characteristics is determined, including:

[0115] Calculating the correlation weights between different enriched allergen characteristic peptide groups, and merging the enriched allergen characteristic peptide groups whose correlation weights are not less than a preset correlation weight value or whose functional characteristics are the same according to the correlation weights and the functional characteristics, to obtain a functional allergen characteristic peptide group;

[0116] Specifically, based on the correlation weights and functional characteristics, enriched allergen characteristic peptide groups with similar functions and related fluctuation trends at the same latitude can be identified. After merging them, they can be clustered into larger functional allergen characteristic peptide groups.

[0117] Preferably, in this way, enriched allergen characteristic peptide groups with completely overlapping functions or highly consistent fluctuation trends are merged to achieve effective redundancy contraction, further enhance the stability of the functional allergen characteristic peptide group, and make the functional orientation clearer.

[0118] Obtaining the number of enriched allergens in the functional allergen characteristic peptide group and the number of the third allergen characteristic peptide;

[0119] Determine the functional allergen characteristic peptide group, in which the number of the enriched allergens is not less than the preset enriched allergen number threshold, and the number of the third allergen characteristic peptides is not less than the preset third allergen characteristic peptide number threshold, as the stable allergen characteristic peptide group with high stability;

[0120] Specifically, the functional allergen characteristic peptide group with high stability meets the following conditions: it can enrich at least two or more enriched allergens and contains at least two or more third allergen characteristic peptides. Functional allergen characteristic peptide groups that meet these conditions are considered stable functional allergen characteristic peptide groups because they can maintain consistent performance in different allergens and characteristic peptides, thereby providing a more representative feature set for subsequent feature analysis and model building. Schematically, the stability curve diagram of the stable allergen characteristic peptide group is as follows Figure 3 As shown, Figure 3 The vertical axis in is a functional allergen characteristic peptide group that contains at least the "preset enriched allergen number threshold" of enriched allergens corresponding to the horizontal axis, and at least the third allergen characteristic peptide that contains the preset third allergen characteristic peptide number threshold, Figure 3 The "Allergen" in the formula refers to the above-mentioned enriched allergens.

[0121] Determine the number of different stable allergen characteristic peptide groups corresponding to the same enriched allergen;

[0122] If the above quantity is not less than the preset quantity threshold, the corresponding enriched allergen is determined to be a multi-targeted allergen;

[0123] Specifically, if a certain enriched allergen is significantly enriched in multiple different stable allergen characteristic peptide groups, it can be judged to have multi-targeting properties.

[0124] Specifically, the above-mentioned multi-targeting is further divided into the following three situations: multi-targeting of the object of action: the same enriched allergen is enriched in a stable allergen characteristic peptide group with completely different functions, indicating that the enriched allergen can play a role in multiple biological functions; multi-targeting within the functional family: enriched allergens are enriched in a stable allergen characteristic peptide group with similar functions but inconsistent fluctuation trends. The correlation between these modules is low and they have independent functions; combined multi-targeting: that is, it has the first two types of multi-targeting at the same time and shows a dominant effect in a specific direction.

[0125] Based on the above multi-targeted allergens, the above multi-targeted characteristics are obtained.

[0126] In this preferred embodiment, based on the enriched allergen characteristic peptide group, a stable allergen characteristic peptide group with high stability and multi-targeting characteristics is determined.

[0127] In another preferred embodiment, the above-mentioned multi-targeting characteristics are obtained based on the above-mentioned multi-targeting allergens, including:

[0128] Obtaining the enrichment, sequence characteristics, physicochemical characteristics and structural characteristics corresponding to the above multi-targeted allergens;

[0129] According to the principal component analysis method, the above-mentioned enrichment, the above-mentioned sequence characteristics, the above-mentioned physical and chemical characteristics and the above-mentioned structural characteristics, the principal component characteristics are obtained, and the above-mentioned principal component characteristics are used as the above-mentioned multi-targeting characteristics.

[0130] Specifically, we first counted the enrichment distribution of each multi-targeted allergen in each functional allergen characteristic peptide group, and combined its sequence characteristics, physicochemical characteristics and structural characteristics, and quantified the degree of enrichment and characteristic performance through enrichment. Then, we used principal component analysis to reduce the dimension of these comprehensive data, screened out the principal components that can explain most of the data variation, and thus extracted the most representative multi-targeted features.

[0131] In this preferred embodiment, a multi-targeting signature is obtained based on multi-targeted allergens.

[0132] The unknown allergen feature vector generation module is used to obtain an unknown allergen feature vector according to the unknown allergen sequence to be identified and the stable allergen feature peptide group;

[0133] In a preferred embodiment, the unknown allergen feature vector is obtained based on the unknown allergen sequence to be identified and the stable allergen feature peptide group, including:

[0134] The unknown allergen sequence is segmented according to the preset base length by a sliding window method to obtain a number of unknown allergen peptide segments;

[0135] The above unknown allergen peptide segment is mapped to the above stable allergen characteristic peptide group to extract the first distribution feature and the first multi-targeting feature of the above unknown allergen peptide segment in each stable allergen characteristic peptide group, and then the above unknown allergen feature vector is generated according to the above first distribution feature and the first multi-targeting feature.

[0136] Preferably, the unknown allergen sequences are pre-processed for standardization before segmentation using the sliding window.

[0137] In this preferred embodiment, the unknown allergen sequence is segmented by a sliding window method to obtain a number of unknown allergen peptides, and then an unknown allergen feature vector is generated by positional allergen peptides and stable allergen feature peptide groups.

[0138] The above-mentioned discrimination result determination module is used to input the above-mentioned unknown allergen feature vector into a preset allergen discrimination model trained according to the above-mentioned allergen recognition feature set, so that the above-mentioned preset allergen discrimination model determines the discrimination result of the above-mentioned unknown allergen sequence according to the above-mentioned unknown allergen feature vector, the above-mentioned allergen recognition feature set, and the above-mentioned stable allergen characteristic peptide group.

[0139] In a preferred embodiment, the preset allergen discrimination model determines the discrimination result of the unknown allergen sequence according to the unknown allergen feature vector, the allergen identification feature set, and the stable allergen feature peptide group, including:

[0140] Extracting a second distribution feature and a second multi-targeting feature corresponding to the same allergen from the allergen identification feature set, and generating an allergen feature vector based on the second distribution feature and the second multi-targeting feature;

[0141] Based on the above unknown allergen feature vectors and the allergen feature vectors corresponding to different allergens, the feature similarity is calculated;

[0142] Calculating the third enrichment of the unknown allergen feature vector in each of the stable allergen feature peptide groups;

[0143] Counting a first number of stable allergen characteristic peptide groups whose third enrichment is greater than a preset third enrichment;

[0144] The identification result of the unknown allergen sequence is determined according to the feature similarity and the first quantity.

[0145] Specifically, the above-mentioned preset allergen discrimination model is a machine learning discrimination machine, which is trained based on the allergen recognition feature set.

[0146] Preferably, using the allergen recognition feature set to train the model can enable the preset allergen discrimination model to learn and recognize the characteristic patterns of allergens of different categories, ensuring its high efficiency and wide applicability under different data conditions.

[0147] In this preferred embodiment, the discrimination result of the unknown allergen sequence is determined by a preset allergen discrimination model according to the unknown allergen feature vector, the above-mentioned allergen recognition feature set, and the stable allergen characteristic peptide group.

[0148] In another preferred embodiment, the determination of the identification result of the unknown allergen sequence according to the feature similarity and the first quantity includes:

[0149] When the feature similarity is greater than a preset feature similarity threshold, or the first quantity is greater than a preset first quantity threshold, the unknown allergen sequence is determined to be an allergen.

[0150] Specifically, when the feature similarity is not greater than a preset feature similarity threshold, and the first quantity is not greater than a preset first quantity threshold, the position allergen sequence is determined to be a non-allergen.

[0151] In this preferred embodiment, the identification result of the unknown allergen sequence is determined by the feature similarity and the first quantity.

[0152] Preferably, 500 allergens for which four existing software (ALLERGENFP, ALLERTOP, ALLERMATCH, SORTALLER) have no unified prediction results and 500 randomly selected non-allergens are selected as the validation set, and the allergen discrimination system based on the characteristic peptide group of the allergen family of the present invention is used for discrimination, and the accuracy (ACC), specificity (specificity), sensitivity (sensitivity) and Matthews correlation coefficient (MCC) of the discrimination are recorded as shown in the following table:

[0153]

[0154]

[0155] As can be seen from the above table, the accuracy of the discrimination results obtained by the allergen discrimination system based on the characteristic peptide group of the allergen family of the present invention in the experimental data is as high as more than 99%, and the Matthews correlation coefficient is more than 99%, which is significantly better than the existing technology. This shows that the allergen discrimination system based on the characteristic peptide group of the allergen family of the present invention shows excellent generalization performance in identifying new or mutant allergens.

[0156] The above are preferred embodiments of the present invention. It should be pointed out that, for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principle of the present invention. These improvements and modifications are also considered to be within the scope of protection of the present invention.

Claims

1. An allergen discrimination system based on characteristic peptide groups of allergen families, characterized in that: include: Allergen characteristic peptide group determination module, distribution feature acquisition module, allergen identification feature set construction module, unknown allergen feature vector generation module and discrimination result determination module; The allergen characteristic peptide group determination module is used to obtain the allergen characteristic peptide group according to a preset allergen database and a preset protein database; The distribution feature acquisition module is used to determine the enriched allergen characteristic peptide group, the enriched allergens, the functional features corresponding to the enriched allergens, the enrichment and frequency corresponding to the allergens according to the allergens and the allergen characteristic peptide group, and obtain the distribution features of the enriched allergens according to the enrichment, frequency and functional features; The allergen identification feature set construction module is used to determine a stable allergen characteristic peptide group with high stability and a multi-targeting feature according to the enriched allergen characteristic peptide group, and combine the multi-targeting feature, the distribution feature and the allergen characteristic peptide group to obtain an allergen identification feature set; The unknown allergen feature vector generation module is used to obtain an unknown allergen feature vector according to the unknown allergen sequence to be identified and the stable allergen feature peptide group; The discrimination result determination module is used to input the unknown allergen feature vector into a preset allergen discrimination model trained according to the allergen recognition feature set, so that the preset allergen discrimination model determines the discrimination result of the unknown allergen sequence according to the unknown allergen feature vector, the allergen recognition feature set, and the stable allergen characteristic peptide group.

2. The allergen discrimination system based on the characteristic peptide group of the allergen family according to claim 1, characterized in that: The method of obtaining the allergen characteristic peptide group according to the preset allergen database and the preset protein database includes: Extracting allergen sequences from the preset allergen database; Extracting non-allergen sequences from the preset protein database according to preset keywords, and removing duplicates from the non-allergen sequences to obtain a first simplified non-allergen sequence; calculating a first identity between the allergen sequence and the first simplified non-allergen sequence, retaining the first simplified non-allergen sequence whose first identity is less than a preset first identity threshold, and obtaining a second simplified non-allergen sequence; The second simplified non-allergen sequence is divided into several amino acid sequences according to a preset number of amino acids, and the second identity between each amino acid sequence and the allergen sequence is calculated, and the amino acid sequence whose second identity is less than a preset second identity threshold and does not contain a preset number of consecutive identical amino acids is determined as the third simplified non-allergen sequence; The allergen characteristic peptide group is obtained according to the allergen sequence and the third simplified non-allergen sequence.

3. The allergen discrimination system based on the characteristic peptide group of the allergen family according to claim 2, characterized in that: The step of obtaining the allergen characteristic peptide group according to the allergen sequence and the third simplified non-allergen sequence comprises: The allergen sequence is segmented according to a preset base length by a sliding window method to obtain a plurality of allergen peptide segments; Calculating the similarity between each of the allergen peptide segments and each of the third simplified non-allergen sequences, and retaining the allergen peptide segments whose similarity is not less than a preset similarity threshold, to obtain high-discrimination allergen peptide segments; The adjacent high-discrimination allergen peptides on the same allergen sequence are spliced ​​to obtain the first allergen characteristic peptide; Repeating the sequence alignment operation until a number of third allergen characteristic peptides are generated; According to the third allergen characteristic peptide, obtaining the allergen characteristic peptide group; Wherein, the sequence comparison operation includes: Acquire the current second allergen characteristic peptide; wherein the initial second allergen characteristic peptide is the first allergen characteristic peptide; Calculating the third identity between each current second allergen signature peptide and each of the non-allergen sequences; Comparing the current third identity with the preset first identity threshold; If the current third identity is greater than the preset first identity threshold, the second allergen characteristic peptide corresponding to the current third identity is eliminated, and the adjacent second allergen characteristic peptides on the allergen sequence among the remaining second allergen characteristic peptides are spliced ​​to obtain an updated second allergen characteristic peptide; If the third identities of all current second allergen characteristic peptides are not greater than the preset first identity threshold, the current second allergen characteristic peptide is spliced ​​with another second allergen characteristic peptide adjacent to the allergen sequence to obtain a plurality of third allergen characteristic peptides.

4. The allergen discrimination system based on the characteristic peptide group of the allergen family according to claim 3, characterized in that: The step of obtaining the allergen characteristic peptide group according to the third allergen characteristic peptide comprises: According to the sequence characteristics of each third allergen characteristic peptide, a similarity matrix between each third allergen characteristic peptide is constructed; Calculating the similarity scores between each pair of characteristic peptides of the third allergen according to the similarity matrix; The third allergen characteristic peptides whose similarity scores are not less than a preset similarity score threshold are clustered to obtain the allergen characteristic peptide group.

5. The allergen discrimination system based on the allergen family characteristic peptide group according to claim 4, characterized in that According to the allergens and the allergen characteristic peptide groups, the enriched allergen characteristic peptide groups, the enriched allergens, the functional characteristics corresponding to the enriched allergens, the enrichment degree and frequency corresponding to the allergens are determined, including: Calculate the frequency and enrichment of each type of allergen in each of the allergen characteristic peptide groups; Determining the allergen characteristic peptide group with an enrichment greater than a preset enrichment threshold as a first enriched allergen characteristic peptide group, determining the allergens with an enrichment greater than the preset enrichment threshold as enriched allergens, and obtaining functional characteristics corresponding to the enriched allergens; The functional characteristics of the corresponding enriched allergens are added to the first enriched allergen characteristic peptide group to generate the enriched allergen characteristic peptide group.

6. The allergen discrimination system based on the allergen family characteristic peptide group according to claim 5, characterized in that: According to the enriched allergen characteristic peptide group, a stable allergen characteristic peptide group with high stability and multi-targeting characteristics is determined, including: Calculating the correlation weights between different enriched allergen characteristic peptide groups, and merging the enriched allergen characteristic peptide groups whose correlation weights are not less than a preset correlation weight value or whose functional characteristics are the same, according to the correlation weights and the functional characteristics, to obtain a functional allergen characteristic peptide group; Obtaining the number of enriched allergens in the functional allergen characteristic peptide group and the number of the third allergen characteristic peptide; Determine the functional allergen characteristic peptide group, in which the number of the enriched allergens is not less than a preset enriched allergen number threshold, and the number of the third allergen characteristic peptides is not less than a preset third allergen characteristic peptide number threshold, as the stable allergen characteristic peptide group with high stability; Determine the number of different stable allergen characteristic peptide groups corresponding to the same enriched allergen; If the quantity is not less than a preset quantity threshold, determining that the corresponding enriched allergen is a multi-targeted allergen; Based on the multi-targeted allergens, the multi-targeting characteristics are obtained.

7. The allergen discrimination system based on the characteristic peptide group of the allergen family according to claim 6, characterized in that: The multi-targeting feature is obtained according to the multi-targeting allergens, including: Obtaining the enrichment, sequence characteristics, physicochemical characteristics and structural characteristics corresponding to the multi-targeted allergens; According to the principal component analysis method, the enrichment, the sequence characteristics, the physicochemical characteristics and the structural characteristics, the principal component characteristics are obtained, and the principal component characteristics are used as the multi-targeting characteristics.

8. The allergen discrimination system based on the characteristic peptide group of the allergen family according to claim 7, characterized in that: The step of obtaining an unknown allergen feature vector based on the unknown allergen sequence to be identified and the stable allergen feature peptide group includes: The unknown allergen sequence is segmented according to the preset base length by a sliding window method to obtain a plurality of unknown allergen peptide segments; The unknown allergen peptide segment is mapped to the stable allergen characteristic peptide group to extract the first distribution feature and the first multi-targeting feature of the unknown allergen peptide segment in each stable allergen characteristic peptide group, and then the unknown allergen feature vector is generated according to the first distribution feature and the first multi-targeting feature.

9. The allergen discrimination system based on the characteristic peptide group of the allergen family according to claim 8, characterized in that: The preset allergen discrimination model determines the discrimination result of the unknown allergen sequence according to the unknown allergen feature vector, the allergen identification feature set, and the stable allergen feature peptide group, including: Extracting a second distribution feature and a second multi-targeting feature corresponding to the same allergen from the allergen identification feature set, and generating an allergen feature vector according to the second distribution feature and the second multi-targeting feature; Calculating feature similarity based on the unknown allergen feature vector and the allergen feature vectors corresponding to different allergens; Calculating the third enrichment of the unknown allergen feature vector in each of the stable allergen feature peptide groups; Counting a first number of stable allergen characteristic peptide groups whose third enrichment is greater than a preset third enrichment; A discrimination result of the unknown allergen sequence is determined according to the feature similarity and the first quantity.

10. The allergen discrimination system based on the characteristic peptide group of the allergen family according to claim 9, characterized in that: The step of determining the identification result of the unknown allergen sequence according to the feature similarity and the first quantity includes: When the feature similarity is greater than a preset feature similarity threshold, or the first quantity is greater than a preset first quantity threshold, the unknown allergen sequence is determined to be an allergen.

Images