Insect metamorphosis development key gene identification method and related equipment
Through deep learning methods and attention mechanisms, the problem that traditional methods are difficult to identify multi-gene regulatory networks in insect metamorphosis and development is solved, and high-precision and efficient gene identification is achieved, which is applicable to a variety of insect species.
Patent Information
- Application Number
- CN202411487957.3
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-10-24
- Publication Date
- 2025-09-19
AI Technical Summary
Traditional molecular bioinformatics methods are difficult to fully capture the complex multi-gene regulatory networks in insect metamorphosis and development, especially in non-model insect species where data support is insufficient, time-consuming and expensive.
A deep learning method based on the BPE algorithm and the CBOW model, combined with the GNCM model and the attention mechanism, automatically captures complex patterns and key features in gene expression data through word segmentation, vector conversion, model training, and important region identification.
It improves the accuracy and efficiency of key gene identification, analyzes complex gene regulatory networks, and is applicable to different macroevolutionary species, especially in non-model species with incomplete data.
Smart Images
Figure CN120673851A_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the field of gene identification technology, and in particular to a method for identifying key genes in insect metamorphosis and related equipment. Background Art
[0002] Metamorphosis is considered a key innovation in insect evolution, but the molecular mechanisms that influence its evolution remain uncertain. Insect metamorphosis involves the complex coordinated actions of numerous key genes, but because the importance of these genes in insect metamorphosis is difficult to assess, identifying the distribution of their importance is a major challenge for traditional molecular biology.
[0003] Traditional molecular bioinformatics methods analyze gene expression in different developmental stages or tissues using gene expression methods such as RNA-Seq, and then verify gene function through technologies such as RNA interference, gene knockout, and CRISPR-Cas9.
[0004] However, the applicant found that the experiments and data analysis of traditional molecular bioinformatics methods are time-consuming and expensive, lack data support for non-model insect species, and cannot fully capture the complex regulatory networks of multiple genes. Summary of the Invention
[0005] The purpose of the embodiments of the present application is to propose a method for identifying key genes in insect metamorphosis and related equipment to solve the problem that traditional molecular bioinformatics methods are difficult to fully capture the complex regulatory network of multiple genes.
[0006] In order to solve the above technical problems, the present invention provides a method for identifying key genes of insect metamorphosis, which adopts the following technical solutions:
[0007] Get the original sample data;
[0008] Perform word segmentation processing on the original sample data according to the BPE algorithm to obtain word segmentation data;
[0009] Perform vector conversion processing on the word segmentation data according to the CBOW model to obtain vectorized data;
[0010] Constructing an initial GNCM model, and performing a model training operation on the initial GNCM model according to the vectorized data to obtain a trained GNCM model;
[0011] Get the input sequence to be recognized;
[0012] The trained GNCM model is used to perform important region recognition processing on the input sequence to be identified to obtain target key genes.
[0013] Furthermore, after the step of obtaining the original sample data, the following steps are also included:
[0014] Performing integrity quality assessment on the original sample data according to BUSCO technology to obtain a quality assessment result;
[0015] If the quality assessment result is incomplete, outputting an incomplete quality signal to re-provide complete sample data;
[0016] If the quality assessment result is complete, the step of performing word segmentation processing on the original sample data according to the BPE algorithm to obtain word segmentation data is executed.
[0017] Furthermore, after the step of obtaining the original sample data and before the step of performing word segmentation processing on the original sample data according to the BPE algorithm to obtain word segmentation data, the following steps are also included:
[0018] The original sample data is subjected to sample expansion processing according to random sampling to obtain expanded original sample data.
[0019] Furthermore, the GNCM model consists of a word sequence encoder, a sentence encoder, a BiGRU network layer and an attention layer from bottom to top.
[0020] Furthermore, the step of constructing an initial GNCM model and performing a model training operation on the initial GNCM model according to the vectorized data to obtain a trained GNCM model specifically includes the following steps:
[0021] Constructing a model training set, a model validation set, and a model test set based on the vectorized data;
[0022] Inputting the model training data into the initial GNCM model for training prediction processing to obtain a training prediction result;
[0023] Performing parameter optimization on the initial GNCM model according to the training prediction result and the model verification set to obtain an intermediate GNCM model;
[0024] Performing verification processing on the intermediate GNCM model according to the model test set;
[0025] If the result of the verification process meets the model convergence condition, the trained GNCM model is obtained;
[0026] If the result of the verification process does not meet the model convergence condition, the intermediate GNCM model parameters are adjusted according to the result of the verification process, and the training prediction process and the verification process are re-executed until the result of the verification process meets the model convergence condition, thereby obtaining the trained GNCM model.
[0027] In order to solve the above technical problems, the present application also provides a device for identifying key genes of insect metamorphosis, which adopts the following technical solution:
[0028] Sample acquisition module, used to obtain original sample data;
[0029] A word segmentation module is used to perform word segmentation processing on the original sample data according to the BPE algorithm to obtain word segmentation data;
[0030] A vector conversion module is used to perform vector conversion processing on the word segmentation data according to the CBOW model to obtain vectorized data;
[0031] A model training module is used to construct an initial GNCM model and perform a model training operation on the initial GNCM model according to the vectorized data to obtain a trained GNCM model;
[0032] An input sequence acquisition module, used to acquire an input sequence to be recognized;
[0033] The important region identification module is used to perform important region identification processing on the input sequence to be identified according to the trained GNCM model to obtain target key genes.
[0034] Furthermore, the device further comprises:
[0035] A quality assessment module is used to perform integrity quality assessment processing on the original sample data according to the BUSCO technology to obtain a quality assessment result;
[0036] A first evaluation result module is configured to output an incomplete quality signal if the quality evaluation result is incomplete, so as to re-provide complete sample data;
[0037] The second evaluation result module is used to execute the step of performing word segmentation processing on the original sample data according to the BPE algorithm to obtain word segmentation data if the quality evaluation result is complete.
[0038] Furthermore, the device further comprises:
[0039] The sample expansion module is used to perform sample expansion processing on the original sample data according to random sampling to obtain expanded original sample data.
[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 when the processor executes the computer-readable instructions, the steps of the method for identifying key genes of insect metamorphosis and development as described above are realized.
[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, which, when executed by a processor, implement the steps of the method for identifying key genes for insect metamorphosis as described above.
[0044] The present application provides a method for identifying key genes in insect metamorphosis, including: obtaining original sample data; performing word segmentation processing on the original sample data according to the BPE algorithm to obtain word segmentation data; performing vector conversion processing on the word segmentation data according to the CBOW model to obtain vectorized data; constructing an initial GNCM model, performing a model training operation on the initial GNCM model according to the vectorized data to obtain a trained GNCM model; obtaining an input sequence to be identified; performing important region recognition processing on the input sequence to be identified according to the trained GNCM model to obtain target key genes. Compared with the existing technology, this application uses deep learning models, especially attention mechanisms, to automatically capture complex patterns and key features in gene expression data, effectively improving the accuracy of key gene identification; through automated data analysis processes, it reduces manual intervention, significantly improves analysis efficiency, and can quickly process large-scale genomic data; the attention mechanism can focus on important interactions between genes, parse out complex gene regulatory networks, and reveal genes and their regulatory mechanisms that play a key role in insect metamorphosis and development; 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 identification results; the model has good generalization ability and is suitable for key gene identification 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 solutions in this application, a brief introduction will be given below to the drawings required for use in the description of the embodiments of this application. Obviously, the drawings described below are some embodiments of this application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.
[0046] Figure 1 is an exemplary system architecture diagram to which the present application may be applied;
[0047] Figure 2 This is a flowchart of the method for identifying key genes for insect metamorphosis provided in the embodiments of the present application;
[0048] Figure 3 This is a schematic diagram of the structure of the BPE word segmentation process and the Word2vec word embedding model provided in the embodiment of the present application;
[0049] Figure 4 : is a structural diagram of the GNCM classification model provided in an embodiment of the present application;
[0050] Figure 5 Schematic diagram of the structure of the key gene identification device for insect metamorphosis provided in the embodiment of the present application;
[0051] Figure 6 It is a structural diagram of an embodiment of a computer device according to the present application. DETAILED DESCRIPTION
[0052] Unless otherwise defined, all technical and scientific terms used herein have the same meanings as commonly understood by those skilled in the art to which this application belongs. The terms used in the specification of the application are for the purpose of describing specific embodiments only and are not intended to limit this application. The terms "including" and "having" and any variations thereof in the specification and claims of this application and the above-mentioned drawings are intended to cover non-exclusive inclusions. The terms "first", "second", etc. in the specification and claims of this application or the above-mentioned drawings are used to distinguish different objects, not to describe a specific order.
[0053] References herein to "embodiments" mean that a particular feature, structure, or characteristic described in connection with the embodiments may be included in at least one embodiment of the present application. The appearance of this phrase in various places in the specification does not necessarily refer to the same embodiment, nor does it constitute an independent or alternative embodiment that is mutually exclusive of other embodiments. It is understood, both explicitly and implicitly, by those skilled in the art that the embodiments described herein may be combined with other embodiments.
[0054] 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.
[0055] like Figure 1As shown, system architecture 100 may include a terminal device 101, a network 102, and a server 103. Terminal device 101 may be a laptop computer 1011, a tablet computer 1012, or a mobile phone 1013. Network 102 is a medium for providing a communication link between terminal device 101 and server 103. Network 102 may include various connection types, such as wired or wireless communication links or fiber optic cables.
[0056] The user can use the terminal device 101 to interact with the server 103 via 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.
[0057] The terminal device 101 can be various electronic devices 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) player, a laptop computer and a desktop computer, etc.
[0058] The server 103 may be a server that provides various services, such as a background server that provides support for web pages displayed on the terminal device 101 .
[0059] It should be noted that the method for identifying key genes for insect metamorphosis and development provided in the embodiments of the present application is generally executed by a server / terminal device, and accordingly, the device for identifying key genes for insect metamorphosis and development is generally set in the server / terminal device.
[0060] It should be understood that Figure 1 The number of terminal devices, networks and servers in the embodiment is merely illustrative. Any number of terminal devices, networks and servers may be provided as required.
[0061] Continue to refer Figure 2 , shows a flow chart of an embodiment of a method for identifying key genes for insect metamorphosis according to the present application. The method for identifying key genes for insect metamorphosis includes: step S201, step S202, step S203, step S204, step S205, and step S206.
[0062] In step S201, original sample data is obtained.
[0063] In step S202, the original sample data is segmented according to the BPE algorithm to obtain segmented data.
[0064] In the present embodiment, BPE is a data compression algorithm that constructs a fixed-size vocabulary by iteratively merging the most frequently occurring genomic fragments in a corpus. It has been widely used as a word segmentation strategy in the field of natural language processing. This method uses the BPE algorithm to perform word segmentation on the genomic protein sequences of 138 insects. Figure 3 a shows the detailed process of building a vocabulary from a given corpus. First, we initialize the vocabulary with all the unique characters in the corpus. Then, in each iteration, we will take the character segment with the highest frequency (e.g. Figure 3 a) in iteration 1 is treated as a new word added to the vocabulary and all identical character segments are replaced with this new word, thus updating the corpus. This iteration continues until the required vocabulary size is reached.
[0065] Word embedding is an important technology in the field of NLP. It overcomes the limitations of traditional one-hot encoding methods and maps words into a 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 3 b) The amino acids in each protein sequence are replaced by their vector representations obtained from a pre-trained word embedding model, and then the average of all amino acid embedding vectors in the protein sequence is taken as its feature representation.
[0066] In step S203, the word segmentation data is vectorized according to the CBOW model to obtain vectorized data.
[0067] In step S204 , an initial GNCM model is constructed, and a model training operation is performed on the GNCM model according to the vectorized data to obtain a trained GNCM model.
[0068] In the embodiment of the present application, the overall structure of the GNCM model is as follows: Figure 4 As shown in the figure, from bottom to top, it consists of a word sequence encoder, a sentence encoder, a BiGRU network layer, and an attention layer. First, the protein sequence is input for word embedding encoding. Second, the feature vectors of the words in each sequence are averaged to obtain a sentence vector, which is input into the BiGRU network with an attention mechanism. Finally, the fully connected layer calculates the output probability. Here, Xi and Si represent the input representations of the i-th word and i-th sentence, respectively, and h represents the hidden state.
[0069] In step S205, an input sequence to be recognized is obtained.
[0070] In step S206, the input sequence to be identified is processed for important region identification based on the trained GNCM model to obtain target key genes.
[0071] In the embodiment of the present application, the genomic protein sequence can be regarded as from words (amino acids) to sentences (genes), so a corresponding deep learning model can be designed and an attention mechanism can be added to identify important regions of the input sequence.
[0072] In an embodiment of the present application, a method for identifying key genes in insect metamorphosis is provided, including: obtaining original sample data; performing word segmentation processing on the original sample data according to the BPE algorithm to obtain word segmentation data; performing vector conversion processing on the word segmentation data according to the CBOW model to obtain vectorized data; constructing an initial GNCM model, performing a model training operation on the GNCM model according to the vectorized data to obtain a trained GNCM model; obtaining an input sequence to be identified; performing important region recognition processing on the input sequence to be identified according to the trained GNCM model to obtain target key genes. Compared with the existing technology, this application uses deep learning models, especially attention mechanisms, to automatically capture complex patterns and key features in gene expression data, effectively improving the accuracy of key gene identification; through automated data analysis processes, it reduces manual intervention, significantly improves analysis efficiency, and can quickly process large-scale genomic data; the attention mechanism can focus on important interactions between genes, parse out complex gene regulatory networks, and reveal genes and their regulatory mechanisms that play a key role in insect metamorphosis and development; 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 identification results; the model has good generalization ability and is suitable for key gene identification of different macroevolutionary species, especially in non-model species with incomplete data.
[0073] In some optional implementations of the embodiments of the present application, after the step of obtaining the original sample data, the following steps are further included:
[0074] Perform integrity quality assessment on the original sample data according to BUSCO technology to obtain quality assessment results;
[0075] If the quality assessment result is incomplete, an incomplete quality signal is output to provide complete sample data again;
[0076] If the quality assessment result is complete, the step of performing word segmentation processing on the original sample data according to the BPE algorithm is executed to obtain the word segmentation data.
[0077] In some optional implementations of the embodiments of the present application, after the step of obtaining the original sample data and before the step of performing word segmentation processing on the original sample data according to the BPE algorithm to obtain word segmentation data, the following steps are also included:
[0078] The original sample data is subjected to sample expansion processing according to random sampling to obtain expanded original sample data.
[0079] In some optional implementations of the embodiments of the present application, the steps of constructing an initial GNCM model, performing a model training operation on the GNCM model according to the vectorized data, and obtaining a trained GNCM model specifically include the following steps:
[0080] Construct model training sets, model validation sets, and model test sets based on vectorized data;
[0081] Input the model training data into the initial GNCM model for training prediction processing to obtain the training prediction results;
[0082] Perform parameter optimization on the initial GNCM model based on the training prediction results and the model validation set to obtain the intermediate GNCM model;
[0083] Verify the intermediate GNCM model based on the model test set;
[0084] If the result of the verification process meets the model convergence conditions, the trained GNCM model is obtained;
[0085] If the result of the verification process does not meet the model convergence conditions, the intermediate GNCM model parameters are adjusted according to the result of the verification process, and the training prediction process and the verification process are re-executed until the result of the verification process meets the model convergence conditions to obtain a trained GNCM model.
[0086] In the examples of this application, by combining advanced artificial intelligence technology, automated analysis of gene expression data and accurate identification of key genes are achieved. Compared with traditional methods, the technical solution of the present invention has the following beneficial effects:
[0087] (1) Improve recognition accuracy: 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.
[0088] (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.
[0089] (3) Enhanced ability to analyze complex networks: The attention mechanism can focus on important interactions between genes, analyze complex gene regulatory networks, and reveal genes and their regulatory mechanisms that play a key role in insect metamorphosis and development.
[0090] (4) Reduce data redundancy and noise impact: Deep learning models have 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.
[0091] (5) Adaptability to multi-species analysis: The model of the present invention has good generalization ability and is suitable for identifying key genes in different macroevolutionary species, especially in non-model species with incomplete data.
[0092] In summary, the method for identifying key genes in insect metamorphosis and development based on deep learning and attention mechanism in this application is not only significantly superior to traditional methods in terms of identification accuracy, efficiency and applicability, but also reduces long-term costs by reducing manual intervention and repeated experiments, providing strong and cost-effective technical support for the study of gene regulation in complex biological processes.
[0093] The embodiments of the present application can acquire and process relevant data based on artificial intelligence technology. 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 achieve optimal results.
[0094] Fundamental AI technologies generally include sensors, dedicated AI chips, cloud computing, distributed storage, big data processing, operating / interaction systems, and mechatronics. AI software technologies primarily encompass computer vision, robotics, biometrics, speech processing, natural language processing, and machine learning / deep learning.
[0095] Those skilled in the art will appreciate that all or part of the processes in the above-described method embodiments can be implemented by instructing related hardware via computer-readable instructions. The computer-readable instructions can be stored in a computer-readable storage medium, and when the program is executed, it can include the processes in the above-described method embodiments. The aforementioned storage medium can be a non-volatile storage medium such as a magnetic disk, an optical disk, a read-only memory (ROM), or a random access memory (RAM).
[0096] It should be understood that although the steps in the flowcharts of the accompanying drawings are shown in sequence as indicated by the arrows, these steps are not necessarily executed 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 some of the steps in the flowcharts 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 portion of the sub-steps or stages of other steps.
[0097] Further references Figure 5 , as a response to the above Figure 2 The present application provides an embodiment of a device for identifying key genes of insect metamorphosis. Figure 2 Corresponding to the method embodiment shown, the device can be specifically applied to various electronic devices.
[0098] like Figure 5 As shown, the insect metamorphosis key gene identification device 200 of the embodiment of the present application includes:
[0099] The sample acquisition module 210 is used to obtain original sample data;
[0100] The word segmentation module 220 is used to perform word segmentation processing on the original sample data according to the BPE algorithm to obtain word segmentation data;
[0101] The vector conversion module 230 is used to perform vector conversion processing on the word segmentation data according to the CBOW model to obtain vectorized data;
[0102] The model training module 240 is used to construct an initial GNCM model and perform a model training operation on the GNCM model according to the vectorized data to obtain a trained GNCM model;
[0103] An input sequence acquisition module 250 is used to acquire an input sequence to be identified;
[0104] The important region identification module 260 is used to perform important region identification processing on the input sequence to be identified based on the trained GNCM model to obtain target key genes.
[0105] In an embodiment of the present application, a device 200 for identifying key genes in insect metamorphosis is provided, including: a sample acquisition module 210 for acquiring original sample data; a word segmentation module 220 for performing word segmentation processing on the original sample data according to the BPE algorithm to obtain word segmentation data; a vector conversion module 230 for performing vector conversion processing on the word segmentation data according to the CBOW model to obtain vectorized data; a model training module 240 for constructing an initial GNCM model, performing model training operations on the GNCM model according to the vectorized data to obtain a trained GNCM model; an input sequence acquisition module 250 for acquiring an input sequence to be identified; and an important region identification module 260 for performing important region identification processing on the input sequence to be identified according to the trained GNCM model to obtain target key genes. Compared with the existing technology, this application uses deep learning models, especially attention mechanisms, to automatically capture complex patterns and key features in gene expression data, effectively improving the accuracy of key gene identification; through automated data analysis processes, it reduces manual intervention, significantly improves analysis efficiency, and can quickly process large-scale genomic data; the attention mechanism can focus on important interactions between genes, parse out complex gene regulatory networks, and reveal genes and their regulatory mechanisms that play a key role in insect metamorphosis and development; 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 identification results; the model has good generalization ability and is suitable for key gene identification of different macroevolutionary species, especially in non-model species with incomplete data.
[0106] In some optional implementations of the embodiments of the present application, the above-mentioned insect metamorphosis key gene identification device 200 further includes:
[0107] The quality assessment module is used to perform integrity quality assessment on the original sample data according to the BUSCO technology to obtain the quality assessment results;
[0108] A first evaluation result module is configured to output an incomplete quality signal if the quality evaluation result is incomplete, so as to provide complete sample data again;
[0109] The second evaluation result module is used to execute the step of performing word segmentation processing on the original sample data according to the BPE algorithm to obtain word segmentation data if the quality evaluation result is complete.
[0110] In some optional implementations of the embodiments of the present application, the above-mentioned insect metamorphosis key gene identification device 200 further includes:
[0111] The sample expansion module is used to perform sample expansion processing on the original sample data according to random sampling to obtain the expanded original sample data.
[0112] To solve the above technical problems, the present application also provides a computer device. Figure 6 , Figure 6 This is a basic structural block diagram of the computer device according to an embodiment of the present application.
[0113] The computer device 300 includes a memory 310, a processor 320, and a network interface 330 that are interconnected through a system bus. It should be noted that the figure only shows the 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 (ASICs), field-programmable gate arrays (FPGAs), digital signal processors (DSPs), embedded devices, etc.
[0114] The computer device may be a desktop computer, notebook computer, PDA, cloud server, etc. The computer device may interact with the user via a keyboard, mouse, remote control, touchpad, or voice control device.
[0115] The memory 310 includes at least one type of readable storage medium, including flash memory, hard disk, multimedia card, card-type memory (e.g., SD or DX memory), 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 storage, magnetic disk, optical disk, etc. In some embodiments, the memory 310 may 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 may 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 media card (SMC), a secure digital (SD) card, a flash card, etc. Of course, the memory 310 may 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 an operating system and various application software installed on the computer device 300, such as computer-readable instructions for a method for identifying key genes for insect metamorphosis. In addition, the memory 310 can also be used to temporarily store various data that has been output or is about to be output.
[0116] In some embodiments, the processor 320 can be a central processing unit (CPU), a controller, a microcontroller, a microprocessor, or other data processing chip. 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 execute computer-readable instructions or process data stored in the memory 310, such as computer-readable instructions for executing the method for identifying key genes for insect metamorphosis.
[0117] 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.
[0118] The computer equipment provided in this application utilizes a deep learning model, especially an attention mechanism, to automatically capture complex patterns and key features in gene expression data, effectively improving the accuracy of key gene identification; through an automated data analysis process, manual intervention is reduced, analysis efficiency is significantly improved, and large-scale genomic data can be quickly processed; the attention mechanism can focus on important interactions between genes, parse out complex gene regulatory networks, and reveal genes and their regulatory mechanisms that play a key role in insect metamorphosis and development; 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 identification results; the model has good generalization ability and is suitable for key gene identification of different macroevolutionary species, especially in non-model species with incomplete data.
[0119] 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 method for identifying key genes of insect metamorphosis as described above.
[0120] The computer-readable storage medium provided in this application utilizes a deep learning model, particularly an attention mechanism, to automatically capture complex patterns and key features in gene expression data, thereby effectively improving the accuracy of key gene identification. The automated data analysis process reduces manual intervention, significantly improves analysis efficiency, and enables rapid processing of large-scale genomic data. The attention mechanism can focus on important interactions between genes, analyze complex gene regulatory networks, and reveal genes and their regulatory mechanisms that play a key role in insect metamorphosis and development. The deep learning model possesses excellent noise resistance and can effectively filter out noise and redundant information in gene expression data, ensuring the accuracy and stability of identification results. The model has excellent generalization capabilities and is suitable for key gene identification in different macroevolutionary species, especially in non-model species with incomplete data.
[0121] 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 the necessary general hardware platform, and of course can also be implemented by hardware, but in many cases the former is a better implementation method. Based on this 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 enabling 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.
[0122] Obviously, the embodiments described above are only some of the embodiments of the present application, rather than all of the 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 has been described in detail with reference to the aforementioned embodiments, for those skilled in the art, it is still possible to modify the technical solutions described in the aforementioned specific embodiments, or to make equivalent replacements for some of the technical features therein. Any equivalent structure made using the contents of the present application specification and the accompanying drawings, directly or indirectly used in other related technical fields, is also within the scope of patent protection of the present application.
Claims
1. A method for identifying key genes for insect metamorphosis, characterized in that: The steps include: Get the original sample data; Perform word segmentation processing on the original sample data according to the BPE algorithm to obtain word segmentation data; Perform vector conversion processing on the word segmentation data according to the CBOW model to obtain vectorized data; Constructing an initial GNCM model, and performing a model training operation on the initial GNCM model according to the vectorized data to obtain a trained GNCM model; Get the input sequence to be recognized; The trained GNCM model is used to perform important region recognition processing on the input sequence to be identified to obtain target key genes.
2. The method for identifying key genes for insect metamorphosis according to claim 1, wherein: After the step of obtaining the original sample data, the following steps are also included: Performing integrity quality assessment on the original sample data according to BUSCO technology to obtain a quality assessment result; If the quality assessment result is incomplete, outputting an incomplete quality signal to re-provide complete sample data; If the quality assessment result is complete, the step of performing word segmentation processing on the original sample data according to the BPE algorithm to obtain word segmentation data is executed.
3. The method for identifying key genes for insect metamorphosis according to claim 1, wherein: After the step of obtaining the original sample data and before the step of performing word segmentation processing on the original sample data according to the BPE algorithm to obtain word segmentation data, the following steps are also included: The original sample data is subjected to sample expansion processing according to random sampling to obtain expanded original sample data.
4. The method for identifying key genes for insect metamorphosis according to claim 1, wherein: The GNCM model consists of a word sequence encoder, a sentence encoder, a BiGRU network layer and an attention layer from bottom to top.
5. The method for identifying key genes for insect metamorphosis according to claim 1, wherein: The step of constructing an initial GNCM model and performing a model training operation on the initial GNCM model according to the vectorized data to obtain a trained GNCM model specifically includes the following steps: Constructing a model training set, a model validation set, and a model test set based on the vectorized data; Inputting the model training data into the initial GNCM model for training prediction processing to obtain a training prediction result; Performing parameter optimization on the initial GNCM model according to the training prediction result and the model verification set to obtain an intermediate GNCM model; Performing verification processing on the intermediate GNCM model according to the model test set; If the result of the verification process meets the model convergence condition, the trained GNCM model is obtained; If the result of the verification process does not meet the model convergence condition, the intermediate GNCM model parameters are adjusted according to the result of the verification process, and the training prediction process and the verification process are re-executed until the result of the verification process meets the model convergence condition, thereby obtaining the trained GNCM model.
6. A device for identifying key genes of insect metamorphosis, characterized in that: include: Sample acquisition module, used to obtain original sample data; A word segmentation module is used to perform word segmentation processing on the original sample data according to the BPE algorithm to obtain word segmentation data; A vector conversion module is used to perform vector conversion processing on the word segmentation data according to the CBOW model to obtain vectorized data; A model training module is used to construct an initial GNCM model and perform a model training operation on the initial GNCM model according to the vectorized data to obtain a trained GNCM model; An input sequence acquisition module, used to acquire an input sequence to be recognized; The important region identification module is used to perform important region identification processing on the input sequence to be identified according to the trained GNCM model to obtain target key genes.
7. The device for identifying key genes for insect metamorphosis according to claim 6, characterized in that: The device further comprises: A quality assessment module is used to perform integrity quality assessment processing on the original sample data according to the BUSCO technology to obtain a quality assessment result; A first evaluation result module is configured to output an incomplete quality signal if the quality evaluation result is incomplete, so as to re-provide complete sample data; The second evaluation result module is used to execute the step of performing word segmentation processing on the original sample data according to the BPE algorithm to obtain word segmentation data if the quality evaluation result is complete.
8. The device for identifying key genes for insect metamorphosis according to claim 6, characterized in that: The device further comprises: The sample expansion module is used to perform sample expansion processing on the original sample data according to random sampling to obtain expanded original sample data.
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 method for identifying key genes for insect metamorphosis 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, which, when executed by a processor, implement the steps of the method for identifying key genes for insect metamorphosis according to any one of claims 1 to 5.