Key gene identification method and device, computer equipment and storage medium

Abstract

The invention belongs to the technical field of intelligent prediction, and relates to a key gene identification method and device, computer equipment and a storage medium, and the method comprises the steps: obtaining original sample data; preprocessing the original sample data to obtain preprocessed sample data; performing word segmentation operation on the preprocessed sample data according to the HFkme r to obtain word segmentation data; performing vector conversion operation on the word segmentation data to obtain word segmentation vector data; constructing an initial BGAC model, and performing model training operation on the initial BGAC model according to the word segmentation vector data to obtain a target BGAC model; obtaining a to-be-recognized genome protein sequence; and inputting the genome protein sequence into the target BGAC model for key gene recognition operation to obtain a key gene recognition result. The method not only solves the problems of high time and high cost in key gene identification in traditional molecular biology, but also provides a precious microscopic view angle for deeply exploring the origin and evolution of insect wings, and the complex biological macro-evolution process is better understood.

Description

Technical Field

[0001] The present application relates to the field of intelligent prediction technology, and in particular to a key gene identification method, device, computer equipment and storage medium. Background Art

[0002] Wings are a key innovation in the evolution of insects. They play a vital role in the survival and reproduction of insects and the stability and diversity of ecosystems. However, there is no authoritative scientific basis to explain the origin and evolution of insect wings. The current mainstream view is that winged insects evolved from wingless insects, which is a process from nothing to something. There are three main hypotheses to explain this process, namely the origin of the dorsal plate of the thorax, the origin of the lateral lobe of the thorax, and the origin of the tracheal gills. These hypotheses are based on studies of several specific species or specific orders, but there is still controversy about their evolutionary origins. The origin and evolution of insect wings involve the complex synergy of many key genes, but because the importance of these genes in the evolution of insect wings is difficult to assess, identifying the importance distribution of these genes to the origin and evolution of wings is a major challenge facing traditional molecular biology.

[0003] Traditional molecular bioinformatics methods analyze gene expression in different developmental stages or tissues using gene expression analysis such as RNA-Seq, and then verify the function of genes through technologies such as RNA interference, gene knockout, and CRISPR-Cas9.

[0004] However, the applicant found that traditional molecular bioinformatics methods lack data support for non-model insect species and are unable to fully capture the complex regulatory networks of multiple genes, thus affecting the accuracy of the results. Summary of the invention

[0005] The purpose of the embodiments of the present application is to provide a key gene identification method, apparatus, computer equipment and storage medium to solve the problem of low accuracy of traditional molecular bioinformatics methods.

[0006] In order to solve the above technical problems, the present application embodiment provides a key gene identification method, which adopts the following technical solution:

[0007] Get the original sample data;

[0008] Performing a preprocessing operation on the original sample data to obtain preprocessed sample data;

[0009] Performing a word segmentation operation on the preprocessed sample data according to HFkmer to obtain word segmentation data;

[0010] Performing a vector conversion operation on the word segmentation data to obtain word segmentation vector data;

[0011] Constructing an initial BGAC model, and performing a model training operation on the initial BGAC model according to the word segmentation vector data to obtain a target BGAC model;

[0012] Obtaining a genomic protein sequence to be identified;

[0013] The gene protein sequence is input into the target BGAC model to perform a key gene identification operation to obtain a key gene identification result.

[0014] Furthermore, the step of performing a preprocessing operation on the original sample data to obtain preprocessed sample data specifically includes the following steps:

[0015] The original sample data is expanded according to a random sampling method to obtain the preprocessed sample data.

[0016] Furthermore, before the step of performing an expansion operation on the original sample data according to the random sampling method to obtain the pre-processed sample data, the following steps are also included:

[0017] Performing an integrity assessment operation on the original sample data according to the BUSCO technology to obtain an integrity assessment result;

[0018] If the integrity assessment result is complete, performing the expansion operation;

[0019] If the integrity assessment result is incomplete, an integrity repair operation is performed on the original sample data.

[0020] Furthermore, the BGAC model consists of a word sequence encoder, a sentence encoder, a BiGRU network layer and an attention layer.

[0021] Furthermore, the step of performing a word segmentation operation on the pre-processed sample data according to HFkmer to obtain word segmentation data specifically includes the following steps:

[0022] Performing sliding window word segmentation processing on the preprocessed sample data according to a preset length to obtain a word segmentation subsequence;

[0023] Performing frequency statistics operation on the word segmentation subsequence to obtain frequency statistics data;

[0024] The frequency statistics data are screened according to the Pareto principle to obtain high-frequency word segmentation tags;

[0025] The preprocessed sample data is subjected to a word segmentation operation according to the high-frequency word segmentation mark to obtain the word segmentation data.

[0026] In order to solve the above technical problems, the present application also provides a key gene identification device, which adopts the following technical solution:

[0027] The original sample acquisition module is used to obtain the original sample data;

[0028] A preprocessing module, used for performing a preprocessing operation on the original sample data to obtain preprocessed sample data;

[0029] A word segmentation module, used for performing a word segmentation operation on the preprocessed sample data according to HFkmer to obtain word segmentation data;

[0030] A vector conversion module, used to perform a vector conversion operation on the word segmentation data to obtain word segmentation vector data;

[0031] A model training module is used to construct an initial BGAC model and perform a model training operation on the initial BGAC model according to the word segmentation vector data to obtain a target BGAC model;

[0032] A protein sequence acquisition module is used to obtain the genomic protein sequence to be identified;

[0033] The key gene identification module is used to input the gene protein sequence into the target BGAC model to perform a key gene identification operation to obtain a key gene identification result.

[0034] Furthermore, the preprocessing module includes:

[0035] The preprocessing submodule is used to perform an expansion operation on the original sample data according to a random sampling method to obtain the preprocessed sample data.

[0036] Furthermore, the preprocessing module also includes:

[0037] The integrity assessment submodule is used to perform an integrity assessment operation on the original sample data according to the BUSCO technology to obtain an integrity assessment result;

[0038] A first evaluation result submodule, configured to perform the expansion operation if the integrity evaluation result is complete;

[0039] The second evaluation result submodule is used to perform an integrity repair operation on the original sample data if the integrity evaluation result is incomplete.

[0040] In order to solve the above technical problems, the embodiment of the present application further provides a computer device, which adopts the following technical solution:

[0041] The method comprises a memory and a processor, wherein the memory stores computer-readable instructions, and the processor implements the steps of the key gene identification method as described above when executing the computer-readable instructions.

[0042] In order to solve the above technical problems, the embodiment of the present application further provides a computer-readable storage medium, which adopts the following technical solution:

[0043] The computer-readable storage medium stores computer-readable instructions, and when the computer-readable instructions are executed by the processor, the steps of the key gene identification method described above are implemented.

[0044] The present application provides a key gene identification method, including: obtaining original sample data; performing a preprocessing operation on the original sample data to obtain preprocessed sample data; performing a word segmentation operation on the preprocessed sample data according to HFkmer to obtain word segmentation data; performing a vector conversion operation on the word segmentation data to obtain word segmentation vector data; constructing an initial BGAC model, and performing a model training operation on the initial BGAC model according to the word segmentation vector data to obtain a target BGAC model; obtaining a genome protein sequence to be identified; inputting the genome protein sequence into the target BGAC model to perform a key gene identification operation to obtain a key gene identification result. Compared with the prior art, the present application has the following beneficial effects: (1) Improving recognition accuracy: The deep learning model, especially the attention mechanism, can automatically capture the complex patterns and key features in the gene expression data, effectively improving the accuracy of key gene identification; (2) Automated processing and high efficiency: The present invention reduces manual intervention through an automated data analysis process, significantly improves the analysis efficiency, and can quickly process large-scale genomic data; (3) Enhancing the ability to analyze complex networks: The attention mechanism can focus on the important interactions between genes, analyze the complex gene regulatory network, and reveal the genes and their regulatory mechanisms that play a key role in the origin and evolution of insect wings; (4) Reducing data redundancy and noise effects: The deep learning model has good noise resistance and can effectively filter out noise and redundant information in gene expression data to ensure the accuracy and stability of the recognition results; (5) Adapting to multi-species analysis: The model of the present invention has good generalization ability and is suitable for the identification of key genes of different macroevolutionary species, especially in non-model species with incomplete data. BRIEF DESCRIPTION OF THE DRAWINGS

[0045] In order to more clearly illustrate the scheme in the present application, a brief introduction is given below to the drawings required for use in the description of the embodiments of the present application. Obviously, the drawings described below are some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0046] Figure 1 is an exemplary system architecture diagram to which the present application may be applied;

[0047] Figure 2 It is a flowchart of the implementation of the key gene identification method provided in the embodiment of the present application;

[0048] Figure 3 It is a schematic diagram of the technical route of the key gene identification method provided in the embodiment of the present application;

[0049] Figure 4 It is a structural diagram of an embodiment of a BGAC classification model provided in an embodiment of the present application;

[0050] Figure 5 It is a structural diagram of the word segmentation and word embedding model provided in the embodiment of the present application;

[0051] Figure 6 is a schematic diagram of the structure of a key gene identification device provided in an embodiment of the present application;

[0052] Figure 7 It is a structural diagram of an embodiment of a computer device according to the present application. DETAILED DESCRIPTION

[0053] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by technicians in the technical field of the present application; the terms used in the specification of the application herein are only for the purpose of describing specific embodiments and are not intended to limit the present application; the terms "including" and "having" and any variations thereof in the specification and claims of the present application and the above-mentioned drawings are intended to cover non-exclusive inclusions. The terms "first", "second", etc. in the specification and claims of the present application or the above-mentioned drawings are used to distinguish different objects, not to describe a specific order.

[0054] Reference to "embodiments" herein means that a particular feature, structure, or characteristic described in conjunction with the embodiments may be included in at least one embodiment of the present application. The appearance of the phrase in various locations in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0055] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the accompanying drawings.

[0056] like Figure 1As shown, the system architecture 100 may include a terminal device 101, a network 102 and a server 103. The terminal device 101 may be a laptop 1011, a tablet computer 1012 or a mobile phone 1013. The network 102 is used to provide a medium for a communication link between the terminal device 101 and the server 103. The network 102 may include various connection types, such as wired, wireless communication links or optical fiber cables, etc.

[0057] The user can use the terminal device 101 to interact with the server 103 through the network 102 to receive or send messages, etc. Various communication client applications can be installed on the terminal device 101, such as web browser applications, shopping applications, search applications, instant messaging tools, email clients, social platform software, etc.

[0058] The terminal device 101 can be any electronic device with a display screen and supporting web browsing. In addition to the laptop computer 1011, tablet computer 1012 or mobile phone 1013, the terminal device 101 can also be an e-book reader, an MP3 player (Moving Picture Experts Group Audio Layer III), an MP4 (Moving Picture Experts Group Audio Layer IV), a laptop computer, a desktop computer, etc.

[0059] The server 103 may be a server that provides various services, such as a background server that provides support for a web page displayed on the terminal device 101 .

[0060] It should be noted that the key gene identification method provided in the embodiment of the present application is generally executed by a server / terminal device, and accordingly, the key gene identification device is generally set in the server / terminal device.

[0061] It should be understood that Figure 1 The number of terminal devices, networks and servers in the embodiment is only for illustration. Any number of terminal devices, networks and servers may be provided according to the implementation requirements.

[0062] Continue to refer Figure 2 , shows a flow chart of an embodiment of a key gene identification method according to the present application. The key gene identification method comprises: step S201, step S202, step S203, step S204, step S205, step S206 and step S207.

[0063] In step S201, original sample data is obtained.

[0064] In step S202, a preprocessing operation is performed on the original sample data to obtain preprocessed sample data.

[0065] In step S203, a word segmentation operation is performed on the preprocessed sample data according to HFkmer to obtain word segmentation data.

[0066] In step S204, a vector conversion operation is performed on the word segmentation data to obtain word segmentation vector data.

[0067] In step S205, an initial BGAC model is constructed, and a model training operation is performed on the initial BGAC model according to the word segmentation vector data to obtain a target BGAC model.

[0068] In step S206, the genomic protein sequence to be identified is obtained.

[0069] In step S207, the gene protein sequence is input into the target BGAC model to perform a key gene identification operation to obtain a key gene identification result.

[0070] In the embodiments of this application, see Figure 3 The technical route diagram of the key gene identification method shown in the figure mainly consists of four parts: Data preprocessing, Construction of word hierarchies, BGAC models construction and Validation, among which:

[0071] (1) Data preprocessing: It includes two parts: Data quality assessment and Dataset Construction. First, the BUSCO technology is used to assess the integrity quality of the original samples, and then random sampling is used to expand the samples and construct the dataset.

[0072] (2) Word level construction: First, use HFkmer to segment all sequences, and then use the CBOW model in Word2Vec to vectorize all words.

[0073] (3) Construction of BGAC classification model: First, sentence-level construction is performed (the dataset is divided into training set, validation set, and test set, and then the word vectors in the training set are concatenated to form the input of the BGAC model), and then the BGAC model is trained.

[0074] (4) Evaluation: Functional annotation and KEGG enrichment analysis were performed on these high-weight orthologous genes to assess their importance to the development of the two groups.

[0075] In an embodiment of the present application, a key gene identification method is provided, including: obtaining original sample data; performing preprocessing operations on the original sample data to obtain preprocessed sample data; performing word segmentation operations on the preprocessed sample data according to HFkmer to obtain word segmentation data; performing vector conversion operations on the word segmentation data to obtain word segmentation vector data; constructing an initial BGAC model, and performing model training operations on the initial BGAC model according to the word segmentation vector data to obtain a target BGAC model; obtaining a genome protein sequence to be identified; inputting the genome protein sequence into the target BGAC model to perform a key gene identification operation to obtain a key gene identification result. Compared with the prior art, the present application has the following beneficial effects:

[0076] (1) Improve recognition accuracy: The deep learning model, especially the attention mechanism, can automatically capture the complex patterns and key features in the gene expression data, effectively improving the accuracy of key gene identification; (2) Automated processing and high efficiency: The present invention reduces manual intervention through an automated data analysis process, significantly improves analysis efficiency, and can quickly process large-scale genomic data; (3) Enhance the ability to analyze complex networks: The attention mechanism can focus on the important interactions between genes, analyze the complex gene regulatory network, and reveal the genes and their regulatory mechanisms that play a key role in the origin and evolution of insect wings; (4) Reduce data redundancy and noise effects: The deep learning model has good noise resistance and can effectively filter out noise and redundant information in gene expression data to ensure the accuracy and stability of the recognition results; (5) Adapt to multi-species analysis: The model of the present invention has good generalization ability and is suitable for the identification of key genes of different macroevolutionary species, especially in non-model species with incomplete data.

[0077] In some optional implementations of the embodiments of the present application, the above-mentioned step of performing a preprocessing operation on the original sample data to obtain the preprocessed sample data specifically includes the following steps:

[0078] The original sample data is expanded according to the random sampling method to obtain the preprocessed sample data.

[0079] In the embodiment of the present application, expanding the original sample data according to the random sampling method is an effective data preprocessing method, which can significantly improve the generalization ability and performance of the model.

[0080] In some optional implementations of the embodiments of the present application, before the step of performing an expansion operation on the original sample data according to the random sampling method to obtain the preprocessed sample data, the following steps are also included:

[0081] Perform integrity assessment on the original sample data according to the BUSCO technology to obtain integrity assessment results;

[0082] If the integrity assessment result is complete, the expansion operation is performed;

[0083] If the integrity assessment result is incomplete, the original sample data will be repaired.

[0084] In the embodiment of the present application, when the BUSCO test result shows that the data is incomplete, the following measures can be taken to deal with it:

[0085] (1) Reasons for incomplete analysis:

[0086] Insufficient sequencing depth: Sequencing depth is a key factor affecting the integrity of the genome or transcriptome. If the sequencing depth is insufficient, some genes may not be sequenced, resulting in incompleteness.

[0087] Assembly errors: If there are errors during the genome or transcriptome assembly process, such as sequence breaks, improper splicing of repetitive sequences, etc., the BUSCO test results may also be incomplete.

[0088] Incomplete reference genome or transcriptome annotation: If the reference genome or transcriptome annotation used is incomplete, the BUSCO test results may also appear incomplete.

[0089] (2) Optimizing sequencing and assembly strategies:

[0090] Increase sequencing depth: If insufficient sequencing depth is the main cause of incompleteness, consider increasing sequencing depth to improve genome coverage and transcriptome completeness.

[0091] Improve assembly algorithms: For assembly errors, you can try using different assembly algorithms or parameters to improve the accuracy and completeness of the assembly.

[0092] Update reference genome or transcriptome annotations: If the reference genome or transcriptome annotations are incomplete, you can try using a newer, more complete annotation version.

[0093] (3) Re-test with BUSCO:

[0094] After optimizing the sequencing and assembly strategies, BUSCO re-testing is required to verify whether the optimization measures are effective. When re-testing, ensure that the same BUSCO dataset and evaluation criteria are used to enable accurate comparison and analysis.

[0095] (4) In-depth analysis of incomplete genes:

[0096] If the BUSCO test results still show incompleteness, the function and regulatory mechanism of the incomplete genes can be deeply analyzed to reveal their possible biological significance. This helps to understand the reasons for the incompleteness of the genome or transcriptome and provides clues for subsequent research.

[0097] (5) Consider other evaluation methods:

[0098] In addition to the BUSCO test, other assessment methods can be considered to verify the integrity of the genome or transcriptome. For example, methods such as CEGMA (Core Eukaryotic Genes Mapping Approach) can be used to assess the integrity of the genome. These methods can provide additional information to help researchers understand the quality of the genome or transcriptome more comprehensively.

[0099] In the examples of this application, when the BUSCO test results show that the data is incomplete, it should be handled by analyzing the cause, optimizing the sequencing and assembly strategy, retesting, in-depth analysis of incomplete genes, and considering other evaluation methods. These measures help to improve the integrity and accuracy of the genome or transcriptome, and provide a reliable basis for subsequent data analysis and research.

[0100] In some optional implementations of the embodiments of the present application, the BGAC model consists of a word sequence encoder, a sentence encoder, a BiGRU network layer and an attention layer.

[0101] In the embodiments of this application, see Figure 4 The structural diagram of the BGAC classification model shown in Figure 1 is composed of a word sequence encoder, a sentence encoder, a BiGRU network layer, and an attention layer from bottom to top. First, the protein sequence is input for word embedding encoding. Secondly, the feature vectors of the words in each sequence are averaged to obtain the sentence vector, which is input into the BiGRU network with an attention mechanism. Finally, the probability is output through the calculation of the fully connected layer. Where Xi and Si represent the input representations of the i-th word and the i-th sentence, respectively, and h represents the hidden state.

[0102] In some optional implementations of the embodiments of the present application, the above step of performing a word segmentation operation on the preprocessed sample data according to HFkmer to obtain the word segmentation data specifically includes the following steps:

[0103] Perform sliding window word segmentation processing on the preprocessed sample data according to the preset length to obtain a word segmentation subsequence;

[0104] Perform frequency statistics operation on the word segmentation subsequence to obtain frequency statistics data;

[0105] According to the Pareto principle, the frequency statistics are screened to obtain high-frequency word segmentation tags;

[0106] The preprocessed sample data is segmented according to the high-frequency segmentation tags to obtain segmentation data.

[0107] In the embodiments of the present application, in order to solve the problem of information redundancy and insufficient revelation of evolutionary mechanisms caused by direct mapping of biological sequence language and natural language, the present invention uses high-frequency k-mers (called HFkmer) for sequence segmentation. The HFkmer word segmentation we proposed abandons the previous practice of directly analogizing fixed-length amino acids to words, and instead uses HFkmer to re-segment the original sequence. This method can efficiently capture the molecular details that drive the key innovative evolution of insect wings and effectively reduce the redundancy in information expression.

[0108] HFkmer participle: see Figure 5 , (a)-(e) are HFkmer word segmentation methods, where (a) is sliding window word segmentation, (b) is counting the frequency of each k-mers, (c) is selecting high-frequency k-mers as word segmentation tags, called HFkmer, (d) represents the original genomic protein sequence, (e) is the result of HFkmer word segmentation; (f) is the BPE word segmentation process. (g) is the CBOW word embedding model of Word2vec; (h) and (I) represent the word embedding results of HFkmer and BPE word segmentation, respectively. Specifically, firstly, the insect genomic protein sequence is subjected to sliding window word segmentation according to a fixed length k ( Figure 5 a), perform frequency statistics on the obtained k-mers ( Figure 5 b). Then, according to the Pareto principle, high-frequency k-mers are selected as word segmentation markers ( Figure 5 c). Finally, the original sequence is segmented according to these segmentation tags ( Figure 5 d), generating a series of sequence fragments of varying lengths but rich in biological significance ( Figure 5 e).

[0109] Word embedding is an important technology in the field of NLP. It overcomes the limitations of traditional one-hot encoding methods and maps words to low-dimensional continuous vector space to capture semantic relationships. In this method, the Continuous Bag of Words (CBOW) algorithm in Word2vec is used for word embedding training ( Figure 5 b) The amino acids of each protein sequence are replaced by their vector representations obtained by the pre-trained word embedding model, and then the average of all the amino acid embedding vectors in the protein sequence is taken as its feature representation.

[0110] In the embodiments of the present application,

[0111] The embodiments of the present application can acquire and process relevant data based on artificial intelligence technology. Among them, artificial intelligence (AI) is the theory, method, technology and application system that uses digital computers or machines controlled by digital computers to simulate, extend and expand human intelligence, perceive the environment, acquire knowledge and use knowledge to obtain the best results.

[0112] AI basic technologies generally include sensors, dedicated AI chips, cloud computing, distributed storage, big data processing technology, operation / interaction systems, mechatronics, etc. AI software technologies mainly include computer vision technology, robotics technology, biometrics technology, speech processing technology, natural language processing technology, and machine learning / deep learning.

[0113] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiments can be implemented by instructing the relevant hardware through computer-readable instructions, and the computer-readable instructions can be stored in a computer-readable storage medium. When the program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, the aforementioned storage medium can be a non-volatile storage medium such as a disk, an optical disk, a read-only memory (ROM), or a random access memory (RAM).

[0114] It should be understood that, although the steps in the flowchart of the accompanying drawings are displayed in sequence as indicated by the arrows, these steps are not necessarily executed in sequence in the order indicated by the arrows. Unless otherwise specified herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least a part of the steps in the flowchart of the accompanying drawings may include multiple sub-steps or multiple stages, and these sub-steps or stages are not necessarily executed at the same time, but can be executed at different times, and their execution order is not necessarily sequential, but can be executed in turn or alternately with other steps or at least a part of the sub-steps or stages of other steps.

[0115] Further references Figure 6 , as a response to the above Figure 2 The present application provides an embodiment of a key gene identification device, and the device embodiment is similar to Figure 2 Corresponding to the method embodiment shown, the device can be specifically applied to various electronic devices.

[0116] like Figure 6 As shown, the key gene identification device 200 of the embodiment of the present application includes:

[0117] The original sample acquisition module 210 is used to acquire original sample data;

[0118] The preprocessing module 220 is used to perform preprocessing operations on the original sample data to obtain preprocessed sample data;

[0119] The word segmentation module 230 is used to perform word segmentation operation on the pre-processed sample data according to HFkmer to obtain word segmentation data;

[0120] A vector conversion module 240 is used to perform a vector conversion operation on the word segmentation data to obtain word segmentation vector data;

[0121] The model training module 250 is used to construct an initial BGAC model and perform a model training operation on the initial BGAC model according to the word segmentation vector data to obtain a target BGAC model;

[0122] The protein sequence acquisition module 260 is used to acquire the genomic protein sequence to be identified;

[0123] The key gene identification module 270 is used to input the gene protein sequence into the target BGAC model to perform a key gene identification operation and obtain a key gene identification result.

[0124] In an embodiment of the present application, a key gene identification device 200 is provided, including: an original sample acquisition module 210, used to obtain original sample data; a preprocessing module 220, used to perform preprocessing operations on the original sample data to obtain preprocessed sample data; a word segmentation module 230, used to perform word segmentation operations on the preprocessed sample data according to HFkmer to obtain word segmentation data; a vector conversion module 240, used to perform vector conversion operations on the word segmentation data to obtain word segmentation vector data; a model training module 250, used to construct an initial BGAC model, and perform model training operations on the initial BGAC model according to the word segmentation vector data to obtain a target BGAC model; a protein sequence acquisition module 260, used to obtain a genome protein sequence to be identified; a key gene identification module 270, used to input the genome protein sequence into the target BGAC model to perform a key gene identification operation to obtain a key gene identification result. Compared with the prior art, the present application has the following beneficial effects: (1) Improving recognition accuracy: The deep learning model, especially the attention mechanism, can automatically capture the complex patterns and key features in the gene expression data, effectively improving the accuracy of key gene identification; (2) Automated processing and high efficiency: The present invention reduces manual intervention through an automated data analysis process, significantly improves the analysis efficiency, and can quickly process large-scale genomic data; (3) Enhancing the ability to analyze complex networks: The attention mechanism can focus on the important interactions between genes, analyze the complex gene regulatory network, and reveal the genes and their regulatory mechanisms that play a key role in the origin and evolution of insect wings; (4) Reducing data redundancy and noise effects: The deep learning model has good noise resistance and can effectively filter out noise and redundant information in gene expression data to ensure the accuracy and stability of the recognition results; (5) Adapting to multi-species analysis: The model of the present invention has good generalization ability and is suitable for the identification of key genes of different macroevolutionary species, especially in non-model species with incomplete data.

[0125] In some optional implementations of the embodiments of the present application, the preprocessing module includes:

[0126] The preprocessing submodule is used to perform expansion operations on the original sample data according to the random sampling method to obtain preprocessed sample data.

[0127] In some optional implementations of the embodiments of the present application, the preprocessing module further includes:

[0128] The integrity assessment submodule is used to perform integrity assessment operations on the original sample data according to the BUSCO technology to obtain integrity assessment results;

[0129] A first evaluation result submodule, configured to perform an expansion operation if the integrity evaluation result is complete;

[0130] The second evaluation result submodule is used to perform an integrity repair operation on the original sample data if the integrity evaluation result is incomplete.

[0131] To solve the above technical problems, the present application also provides a computer device. Figure 7 , Figure 7 This is a basic structural block diagram of a computer device according to an embodiment of the present application.

[0132] The computer device 300 includes a memory 310, a processor 320, and a network interface 330 that are interconnected and communicated through a system bus. It should be noted that the figure only shows a computer device 300 having components 310-330, but it should be understood that it is not required to implement all the components shown, and more or fewer components can be implemented instead. Among them, those skilled in the art can understand that the computer device here is a device that can automatically perform numerical calculations and / or information processing according to pre-set or stored instructions, and its hardware includes but is not limited to microprocessors, application specific integrated circuits (Application Specific Integrated Circuit, ASIC), programmable gate arrays (Field-Programmable Gate Array, FPGA), digital processors (Digital Signal Processor, DSP), embedded devices, etc.

[0133] The computer device may be a computing device such as a desktop computer, a notebook, a PDA, a cloud server, etc. The computer device may interact with a user through a keyboard, a mouse, a remote controller, a touch pad, or a voice control device.

[0134] The memory 310 includes at least one type of readable storage medium, and the readable storage medium includes flash memory, hard disk, multimedia card, card-type memory (for example, SD or DX memory, etc.), random access memory (RAM), static random access memory (SRAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), programmable read-only memory (PROM), magnetic memory, magnetic disk, optical disk, etc. In some embodiments, the memory 310 can be an internal storage unit of the computer device 300, such as a hard disk or memory of the computer device 300. In other embodiments, the memory 310 can also be an external storage device of the computer device 300, such as a plug-in hard disk equipped on the computer device 300, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital, SD) card, a flash card, etc. Of course, the memory 310 can also include both the internal storage unit of the computer device 300 and its external storage device. In the embodiment of the present application, the memory 310 is generally used to store the operating system and various application software installed on the computer device 300, such as computer-readable instructions of the key gene identification method, etc. In addition, the memory 310 can also be used to temporarily store various data that have been output or are to be output.

[0135] The processor 320 may be a central processing unit (CPU), a controller, a microcontroller, a microprocessor, or other data processing chip in some embodiments. The processor 320 is generally used to control the overall operation of the computer device 300. In the embodiment of the present application, the processor 320 is used to run the computer-readable instructions or process data stored in the memory 310, such as computer-readable instructions for running the key gene identification method.

[0136] The network interface 330 may include a wireless network interface or a wired network interface. The network interface 330 is generally used to establish a communication connection between the computer device 300 and other electronic devices.

[0137] The computer device provided by the present application has the following beneficial effects: (1) Improving recognition accuracy: Using deep learning models, especially attention mechanisms, can automatically capture complex patterns and key features in gene expression data, effectively improving the accuracy of key gene identification; (2) Automated processing and high efficiency: The present invention reduces manual intervention through automated data analysis processes, significantly improves analysis efficiency, and can quickly process large-scale genomic data; (3) Enhancing complex network analysis capabilities: The attention mechanism can focus on important interactions between genes, parse complex gene regulatory networks, and reveal genes and their regulatory mechanisms that play a key role in the origin and evolution of insect wings; (4) Reducing data redundancy and noise effects: The deep learning model has good noise resistance and can effectively filter out noise and redundant information in gene expression data to ensure the accuracy and stability of recognition results; (5) Adapting to multi-species analysis: The model of the present invention has good generalization ability and is suitable for key gene identification of different macroevolutionary species, especially in non-model species with incomplete data.

[0138] The present application also provides another embodiment, namely, providing a computer-readable storage medium, which stores computer-readable instructions, and the computer-readable instructions can be executed by at least one processor to enable the at least one processor to perform the steps of the key gene identification method as described above.

[0139] The computer-readable storage medium provided in the present application has the following beneficial effects: (1) Improving recognition accuracy: The deep learning model, especially the attention mechanism, can automatically capture the complex patterns and key features in the gene expression data, effectively improving the accuracy of key gene identification; (2) Automated processing and high efficiency: The present invention reduces manual intervention through an automated data analysis process, significantly improves analysis efficiency, and can quickly process large-scale genomic data; (3) Enhancing the ability to analyze complex networks: The attention mechanism can focus on the important interactions between genes, analyze the complex gene regulatory network, and reveal the genes and their regulatory mechanisms that play a key role in the origin and evolution of insect wings; (4) Reducing data redundancy and noise effects: The deep learning model has good noise resistance and can effectively filter out noise and redundant information in gene expression data to ensure the accuracy and stability of the recognition results; (5) Adapting to multi-species analysis: The model of the present invention has good generalization ability and is suitable for the identification of key genes of different macroevolutionary species, especially in non-model species with incomplete data.

[0140] Through the description of the above implementation methods, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be implemented by means of software plus a necessary general hardware platform, and of course by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present application, or the part that contributes to the prior art, can be embodied in the form of a software product, which is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk), and includes a number of instructions for a terminal device (which can be a mobile phone, computer, server, air conditioner, or network device, etc.) to execute the methods described in each embodiment of the present application.

[0141] Obviously, the embodiments described above are only some embodiments of the present application, rather than all embodiments. The preferred embodiments of the present application are given in the accompanying drawings, but they do not limit the patent scope of the present application. The present application can be implemented in many different forms. On the contrary, the purpose of providing these embodiments is to make the understanding of the disclosure of the present application more thorough and comprehensive. Although the present application is described in detail with reference to the aforementioned embodiments, for those skilled in the art, it is still possible to modify the technical solutions recorded in the aforementioned specific implementation methods, or to perform equivalent replacement of some of the technical features therein. Any equivalent structure made using the contents of the specification and drawings of this application, directly or indirectly used in other related technical fields, is similarly within the scope of patent protection of this application.

Claims

1. A key gene identification method, characterized in that: The steps include: Get the original sample data; Performing a preprocessing operation on the original sample data to obtain preprocessed sample data; Performing a word segmentation operation on the preprocessed sample data according to HFkmer to obtain word segmentation data; Performing a vector conversion operation on the word segmentation data to obtain word segmentation vector data; Constructing an initial BGAC model, and performing a model training operation on the initial BGAC model according to the word segmentation vector data to obtain a target BGAC model; Obtaining a genomic protein sequence to be identified; The gene protein sequence is input into the target BGAC model to perform a key gene identification operation to obtain a key gene identification result.

2. The key gene identification method according to claim 1, characterized in that: The step of performing a preprocessing operation on the original sample data to obtain preprocessed sample data specifically includes the following steps: The original sample data is expanded according to a random sampling method to obtain the preprocessed sample data.

3. The key gene identification method according to claim 2, characterized in that: Before the step of performing an expansion operation on the original sample data according to the random sampling method to obtain the pre-processed sample data, the following steps are also included: Performing an integrity assessment operation on the original sample data according to the BUSCO technology to obtain an integrity assessment result; If the integrity assessment result is complete, performing the expansion operation; If the integrity assessment result is incomplete, an integrity repair operation is performed on the original sample data.

4. The key gene identification method according to claim 1, characterized in that: The BGAC model consists of a word sequence encoder, a sentence encoder, a Bi GRU network layer and an attention layer.

5. The key gene identification method according to claim 1, characterized in that: The step of performing a word segmentation operation on the pre-processed sample data according to HFkmer to obtain word segmentation data specifically includes the following steps: Performing sliding window word segmentation processing on the preprocessed sample data according to a preset length to obtain a word segmentation subsequence; Performing frequency statistics operation on the word segmentation subsequence to obtain frequency statistics data; The frequency statistics data are screened according to the Pareto principle to obtain high-frequency word segmentation tags; The preprocessed sample data is subjected to a word segmentation operation according to the high-frequency word segmentation mark to obtain the word segmentation data.

6. A key gene identification device, characterized in that: include: The original sample acquisition module is used to obtain the original sample data; A preprocessing module, used for performing a preprocessing operation on the original sample data to obtain preprocessed sample data; A word segmentation module, used for performing a word segmentation operation on the preprocessed sample data according to HFkmer to obtain word segmentation data; A vector conversion module, used to perform a vector conversion operation on the word segmentation data to obtain word segmentation vector data; A model training module is used to construct an initial BGAC model and perform a model training operation on the initial BGAC model according to the word segmentation vector data to obtain a target BGAC model; A protein sequence acquisition module is used to obtain the genomic protein sequence to be identified; The key gene identification module is used to input the gene protein sequence into the target BGAC model to perform a key gene identification operation to obtain a key gene identification result.

7. The key gene identification device according to claim 6, characterized in that: The preprocessing module comprises: The preprocessing submodule is used to perform an expansion operation on the original sample data according to a random sampling method to obtain the preprocessed sample data.

8. The key gene identification device according to claim 7, characterized in that: The preprocessing module also includes: The integrity assessment submodule is used to perform an integrity assessment operation on the original sample data according to the BUSCO technology to obtain an integrity assessment result; A first evaluation result submodule, configured to perform the expansion operation if the integrity evaluation result is complete; The second evaluation result submodule is used to perform an integrity repair operation on the original sample data if the integrity evaluation result is incomplete.

9. A computer device comprising a memory and a processor, characterized in that: The memory stores computer-readable instructions, and when the processor executes the computer-readable instructions, the steps of the key gene identification method according to any one of claims 1 to 5 are implemented.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer-readable instructions, and when the computer-readable instructions are executed by a processor, the steps of the key gene identification method according to any one of claims 1 to 5 are implemented.

Images