Methods, systems, media, products and terminals for constructing gene relationship knowledge graphs

Abstract

This application provides a method, system, medium, product, and terminal for constructing a gene relationship knowledge graph. The method involves acquiring gene data from different databases and preprocessing the gene data; extracting entity information from the preprocessed gene data using a natural language model to generate an initial gene entity dataset and an initial gene entity relationship graph; performing data filtering on the initial gene entity dataset based on an adaptive filtering algorithm to obtain a target gene entity dataset; and constructing a gene relationship knowledge graph based on the target gene entity dataset, the initial gene entity relationship graph, and a pre-built gene database model. This not only comprehensively reveals the entirety of the gene network and its dynamic changes but also intuitively displays the interactions between genes through visualization, providing researchers with an intuitive and convenient research tool.

Description

Technical Field

[0001] This application relates to the field of medical device data transmission technology, and in particular to a method, system, medium, product and terminal for constructing a gene relationship knowledge graph. Background Technology

[0002] With the continuous advancement of life sciences in the 21st century, genomics and bioinformatics, as two cutting-edge disciplines, are propelling our understanding of the mysteries of life at an unprecedented pace. The development of these two disciplines has not only greatly enriched our knowledge of the genetic information of organisms but also revealed the complex and subtle connections between genes and biological functions. Genes, as the basic units of genetic information, encode proteins and other biomolecules that directly participate in various life activities of organisms, from cell division and metabolic regulation to disease occurrence and defense mechanisms, all demonstrating the core role of genes.

[0003] However, with the sequencing of more and more gene sequences and the accumulation of massive amounts of biological information data, how to efficiently and systematically analyze this data and uncover the hidden gene-gene interactions and their relationship with biological functions has become a key problem that urgently needs to be solved in the field of life sciences. Traditional data analysis methods often focus on the study of single genes or small-scale gene sets, making it difficult to comprehensively capture the full picture of gene networks and their dynamic changes, thus limiting our understanding of the deep mechanisms of complex biological systems. Summary of the Invention

[0004] In view of the shortcomings of the prior art described above, the purpose of this application is to provide a method, system, medium, product and terminal for constructing a gene relationship knowledge graph, which can solve the technical problems of existing gene data analysis technology focusing on the study of single genes or small-scale gene sets, making it difficult to comprehensively capture the whole picture of gene networks and their dynamic changes.

[0005] To achieve the above and other related objectives, a first aspect of this application provides a method for constructing a gene relationship knowledge graph, comprising: acquiring gene data from different databases and preprocessing the gene data; extracting entity information from the preprocessed gene data using a natural language model to generate an initial gene entity dataset and an initial gene entity relationship graph; performing data filtering operations on the initial gene entity dataset based on an adaptive filtering algorithm to obtain a target gene entity dataset; and constructing a gene relationship knowledge graph based on the target gene entity dataset, the initial gene entity relationship graph, and a pre-constructed gene database model.

[0006] In some embodiments of the first aspect of this application, the method of constructing a gene relationship knowledge graph based on the target gene entity dataset, the initial gene entity relationship graph, and a pre-constructed gene database model includes: constructing an initial gene relationship model based on the initial gene entity relationship graph; optimizing the initial gene relationship model based on the target gene entity dataset to obtain a target gene relationship model; and importing the data in the target gene entity dataset and the target gene relationship model into the pre-constructed gene database model according to a preset mapping rule to construct a gene relationship knowledge graph.

[0007] In some embodiments of the first aspect of this application, the preset mapping rules include preset entity mapping rules and preset relation mapping rules; the method of importing the data in the target gene entity dataset and the target gene relation model into a pre-constructed gene database model according to the preset mapping rules to construct a gene relation knowledge graph includes: importing the data in the target gene entity dataset into the node table of the gene database model according to the preset entity mapping rules; importing the data in the target gene relation model into the edge table of the gene database model according to the preset relation mapping rules; and constructing a gene relation knowledge graph based on the gene database model after the data import.

[0008] In some embodiments of the first aspect of this application, the method of extracting entity information from the preprocessed gene data using a natural language model to generate an initial gene entity dataset and an initial gene entity relationship graph includes: extracting entity information from the preprocessed gene data using a natural language model to obtain gene entity feature data and gene entity relationship data; generating an initial gene entity dataset based on the gene entity feature data; and constructing an initial gene entity relationship graph based on the gene entity relationship data.

[0009] In some embodiments of the first aspect of this application, the method further includes: visualizing the gene relationship knowledge graph.

[0010] In some embodiments of the first aspect of this application, the method further includes: constructing a gene data query interface based on the gene relationship knowledge graph.

[0011] To achieve the above and other related objectives, a second aspect of this application provides a gene relationship knowledge graph construction system, comprising: a data preprocessing module for acquiring gene data from different databases and preprocessing the gene data; an entity information extraction module for extracting entity information from the preprocessed gene data using a natural language model to generate an initial gene entity dataset and an initial gene entity relationship graph; a data filtering module for performing data filtering operations on the initial gene entity dataset based on an adaptive filtering algorithm to obtain a target gene entity dataset; and a knowledge graph construction module for constructing a gene relationship knowledge graph based on the target gene entity dataset, the initial gene entity relationship graph, and a pre-constructed gene database model.

[0012] To achieve the above and other related objectives, a third aspect of this application provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the gene relationship knowledge graph construction method as described above.

[0013] To achieve the above and other related objectives, a fourth aspect of this application provides a computer program product comprising computer program code, which, when executed on a computer, enables the computer to implement the gene relationship knowledge graph construction method as described above.

[0014] To achieve the above and other related objectives, a fifth aspect of this application provides an electronic terminal, including a memory, a processor, and a computer program stored in the memory; the processor executes the computer program to implement the gene relationship knowledge graph construction method described above.

[0015] As described above, the gene relationship knowledge graph construction method, system, medium, product, and terminal of this application have the following beneficial effects: By integrating gene data from different databases, a more comprehensive and accurate gene dataset is formed. Entity information is extracted using a natural language model, generating an initial gene entity dataset and an initial gene entity relationship graph. This achieves cross-database gene information integration. The application of natural language processing technology improves the accuracy of gene entity and relationship recognition, laying a solid foundation for constructing a gene relationship knowledge graph. Furthermore, an adaptive filtering algorithm is used to filter the initial gene entity dataset to obtain the target gene entity dataset. The filtering strategy is automatically adjusted based on the data's characteristics and quality, effectively removing redundant, inaccurate, or irrelevant information, improving the purity and reliability of the dataset. This not only optimizes the data processing flow but also significantly improves the efficiency and quality of knowledge graph construction. Finally, based on the target gene entity dataset, the initial gene entity relationship graph, and a pre-constructed gene database model, a gene relationship knowledge graph is constructed. This not only comprehensively reveals the entirety of the gene network and its dynamic changes but also visually demonstrates the interactions between genes, providing researchers with an intuitive and convenient research tool. In addition, this knowledge graph supports query and intelligent analysis functions, which can help researchers delve into the potential patterns and rules in gene networks, providing powerful data support and analysis tools for fields such as gene research, disease diagnosis, and drug development. Attached Figure Description

[0016] Figure 1 The diagram shown is a flowchart illustrating a method for constructing a gene relationship knowledge graph according to an embodiment of this application.

[0017] Figure 2 The diagram shown is a flowchart illustrating the process of extracting entity information from gene data in one embodiment of this application.

[0018] Figure 3 The diagram shown is a flowchart illustrating the process of constructing a gene relationship knowledge graph in one embodiment of this application.

[0019] Figure 4 The diagram shown is a schematic block diagram of a gene relationship knowledge graph construction system in one embodiment of this application.

[0020] Figure 5 The diagram shown is an architecture diagram of a gene relationship knowledge graph construction system in one embodiment of this application.

[0021] Figure 6 The diagram shown is a structural schematic of an electronic terminal according to an embodiment of this application. Detailed Implementation

[0022] The following specific examples illustrate the implementation of this application. Those skilled in the art can easily understand other advantages and effects of this application from the content disclosed in this specification. This application can also be implemented or applied through other different specific embodiments, and various details in this specification can also be modified or changed based on different viewpoints and applications without departing from the spirit of this application. It should be noted that, unless otherwise specified, the following embodiments and features in the embodiments can be combined with each other.

[0023] Before providing a further detailed description of the present invention, the nouns and terms used in the embodiments of the present invention are explained, and the nouns and terms used in the embodiments of the present invention are subject to the following interpretations:

[0024] <1> Automated web crawling tools are software that can automatically extract web page content. In the field of bioinformatics, these tools are often used to download gene-related data in bulk from database websites.

[0025] <2> API (Application Programming Interface): An application programming interface is a programming interface provided by a database or website that allows users to access and retrieve data programmatically.

[0026] <3> JavaScript is a high-level, interpreted, dynamically typed programming language widely used in web development.

[0027] <4> Web (World Wide Web): is a hypertext-based system that allows users to access and browse various resources on the Internet through a browser.

[0028] <5> Spring Boot is a module of the Spring framework that integrates many technologies within the Spring framework and provides a wealth of default configurations, thus simplifying the development and deployment of Spring applications. Through auto-configuration and the principle of "convention over configuration," it significantly reduces the workload for developers in configuration. It provides a large number of default configurations, allowing developers to customize configurations only when necessary.

[0029] <6> The Spring framework is an open-source Java (object-oriented programming language) platform that provides a comprehensive programming and configuration model for enterprise application development.

[0030] Despite significant progress in biological research in recent years, particularly in gene sequencing technology and the accumulation of bioinformatics data, efficiently analyzing massive amounts of gene sequences and bioinformatics data to reveal the complex interactions between genes and their relationship with biological functions remains a major challenge in the field of life sciences.

[0031] Traditional data analysis methods, such as those based on single genes or small gene sets, while helping us understand gene function and regulatory mechanisms to some extent, are limited in their inability to comprehensively capture the entirety of gene networks and their dynamic changes. Organisms are highly complex systems, with intricate interactions between genes forming a vast gene network. Each gene in this network may interact directly or indirectly with multiple other genes, collectively regulating various functions of the organism. Therefore, traditional methods for studying single genes or small gene sets cannot reveal the full picture and dynamic changes of gene networks.

[0032] To address the problems mentioned above, this invention provides a method, system, medium, product, and terminal for constructing a gene relationship knowledge graph. It aims to solve the technical problems of existing gene data analysis technologies, which focus on the study of single genes or small-scale gene sets, making it difficult to comprehensively capture the full picture and dynamic changes of gene networks.

[0033] To facilitate understanding of the embodiments of this application, firstly, in conjunction with Figure 1 Detailed explanation. Figure 1 This document illustrates a flowchart of the gene relationship knowledge graph construction method in an embodiment of the present invention. The gene relationship knowledge graph construction method in this embodiment mainly includes the following steps:

[0034] S101: Obtain gene data from different databases and preprocess the gene data.

[0035] In this embodiment, the databases include, but are not limited to, public medical databases, medical research paper databases, and patent literature databases, ensuring the comprehensiveness and authority of the data. Automated web crawling tools and API interfaces are used to download key information such as gene sequences, protein structures, functional annotations, and interaction networks in batches from these different databases, thereby obtaining gene data from various sources and performing preprocessing. Obtaining gene data from multiple databases comprehensively covers gene information from different fields and research directions, avoiding the data limitations of a single database.

[0036] In this embodiment, the preprocessing methods include, but are not limited to, data cleaning preprocessing, data transformation preprocessing, and data standardization preprocessing. The data cleaning preprocessing includes: deleting duplicate or irrelevant gene data, and correcting or deleting obviously erroneous gene sequences or expression data. The data transformation preprocessing includes: converting gene data from different sources into a unified data format to facilitate subsequent analysis. The data standardization preprocessing includes: eliminating differences in gene data from different samples or under different experimental conditions to make the data comparable.

[0037] S102: Entity information is extracted from the preprocessed gene data using a natural language model to generate an initial gene entity dataset and an initial gene entity relationship graph.

[0038] In this embodiment, as Figure 2 The diagram illustrates a flowchart of entity information extraction from gene data in an embodiment of the present invention. The method of extracting entity information from the preprocessed gene data using a natural language model to generate an initial gene entity dataset and an initial gene entity relationship graph includes:

[0039] S1021: Entity information is extracted from the preprocessed gene data using a natural language model to obtain gene entity feature data and gene entity relationship data.

[0040] In this embodiment, the natural language model includes either the GPT model or the Llama3 model. The GPT (Generative Pre-trained Transformer) model is a deep learning-based natural language processing (NLP) model. This model learns and abstracts large-scale text through unsupervised learning, and then fine-tunes it for various specific NLP tasks. The Llama3 (Low Latency Memory-Augmented Language Model 3) model is a deep learning model based on the Transformer architecture. It is a neural network model that uses a self-attention mechanism to capture the contextual relationships in the input sequence. By optimizing the architecture and increasing training data, it achieves efficient processing of long text sequences and improves model performance.

[0041] In this embodiment, the natural language model is trained and fine-tuned to recognize key information such as gene names, gene sequences, and gene functions, thereby extracting gene entity feature data. This gene entity feature data includes basic gene attributes, functional descriptions, and expression patterns, providing a foundation for subsequent gene entity dataset construction. In addition to extracting gene entity feature data, the natural language model can further analyze the relationships between gene entities. This includes gene interactions, regulatory relationships, and co-expression relationships. By recognizing keywords, phrases, and sentence structures in the text, the model can infer potential relationships between gene entities and generate gene entity relationship data.

[0042] S1022: Generate an initial gene entity dataset based on the gene entity feature data.

[0043] In this embodiment, the extracted gene entity feature data are organized and summarized to generate an initial gene entity dataset. This initial gene entity dataset contains basic information and feature descriptions of the gene entities, such as gene names, protein functions, and interaction relationships, to facilitate subsequent analysis and mining.

[0044] S1023: Construct an initial gene entity relationship graph based on the gene entity relationship data.

[0045] In this embodiment, an initial gene entity relationship graph is constructed using the extracted gene entity relationship data. This initial gene entity relationship graph illustrates the interactions and relationship networks between gene entities. In the initial gene entity relationship graph, nodes represent gene entities (such as genes, proteins, and biological functions), and edges represent relationships between gene entities (such as regulatory relationships, interaction relationships, and functional associations). It is ensured that all nodes and edges in the graph are correctly labeled with their corresponding gene entities and relationship types. Through this initial gene entity relationship graph, the complex relationships between genes can be intuitively understood, providing strong data support for the construction of knowledge graphs.

[0046] S103: Based on the adaptive filtering algorithm, perform data filtering operations on the initial gene entity dataset to obtain the target gene entity dataset.

[0047] In this embodiment, the adaptive screening algorithm is a type of algorithm that can automatically adjust the screening strategy or parameters according to data characteristics, exhibiting high flexibility and accuracy in processing and analyzing data. The adaptive screening algorithm includes, but is not limited to, adaptive genetic algorithms, adaptive learning algorithms, gradient-based adaptive algorithms, etc.

[0048] In this embodiment, the adaptive genetic algorithm improves search efficiency and convergence speed by dynamically adjusting parameters such as crossover probability and mutation probability. In screening gene entity datasets, the adaptive genetic algorithm can be used to find optimal gene combinations or feature subsets to meet specific research objectives or application requirements.

[0049] In this embodiment, the adaptive learning algorithm is a machine learning algorithm that can automatically adjust parameters based on data to improve classification or prediction performance. In bioinformatics fields such as gene sequence analysis and protein structure prediction, adaptive learning algorithms can automatically learn the patterns of matching known genes or proteins by training gene sequences or protein sequences, thereby improving the accuracy and robustness of screening.

[0050] In this embodiment, the gradient-based adaptive algorithm adjusts parameters by calculating the gradient of the error to minimize the error function, such as the minimum mean square error algorithm. In screening gene entity datasets, gradient-based adaptive algorithms can be used to optimize the screening model, improving screening efficiency and accuracy.

[0051] In this embodiment, the method of performing data filtering operations on the initial gene entity dataset based on an adaptive filtering algorithm to obtain the target gene entity dataset includes:

[0052] (1) Initialize the screening model based on the adaptive screening algorithm. The screening model can be a machine learning model, such as a classifier or clusterer, used to classify or cluster data.

[0053] (2) Based on the collected historical gene entity training dataset, select genes closely related to the target gene entity according to preset rules (such as gene function, expression level, etc.). These selected gene entities are used as positive examples.

[0054] (3) In the historical gene entity training dataset, gene entities unrelated to the target gene entity are generated by replacing or modifying certain key attributes (such as head entities, tail entities, etc.) in the positive examples. These are called negative examples. The introduction of negative examples aims to help the screening model learn to better distinguish between related and unrelated genes.

[0055] (4) Divide the historical gene entity training dataset into K data groups, each containing a certain number of gene entities (including positive and negative examples). This grouping strategy aims to ensure that the screening model can learn the features under different data distributions during training, thereby improving the model's generalization ability.

[0056] (5) At the start of training, set a sampling probability for each data set. The sampling probabilities can be the same or set based on some prior knowledge (such as data distribution, feature importance, etc.). This probability sampling mechanism ensures that the screening model can be exposed to diverse data in the early stages of training, avoiding overfitting or underfitting problems caused by uneven data distribution.

[0057] (6) The screening model is trained using the pre-defined data sets and the set sampling probabilities. During training, the screening model learns to distinguish target gene entities based on the input positive and negative examples.

[0058] (7) As training progresses, the selection model dynamically adjusts the sampling probability based on the training status (e.g., classification error) of each data group. Specifically, for data groups with larger classification errors (i.e., groups that the model has not yet fully learned), the probability of their sampling is increased to give them more attention in subsequent training; while for data groups with smaller classification errors (i.e., groups that the model has already learned well), the probability of their sampling is decreased to reduce unnecessary repetitive training. This adaptive probability update strategy helps the selection model utilize training data more efficiently, improving training efficiency and model performance.

[0059] (8) After training, the trained screening model is used to screen the initial gene entity dataset to obtain the target gene entity dataset.

[0060] In this embodiment, an adaptive filtering algorithm is used to filter the initial gene entity dataset to obtain the target gene entity dataset. The data is further filtered to ensure high reliability and relevance, thus laying a solid foundation for subsequent knowledge graph construction and ensuring that the data used for knowledge graph construction is both reliable and highly relevant.

[0061] S104: Based on the target gene entity dataset, the initial gene entity relationship graph, and the pre-built gene database model, construct a gene relationship knowledge graph.

[0062] In this embodiment, as Figure 3 The diagram illustrates the process of constructing a gene relationship knowledge graph in an embodiment of the present invention. Based on the target gene entity dataset, the initial gene entity relationship graph, and a pre-built gene database model, the gene relationship knowledge graph is constructed in the following ways:

[0063] S1041: Construct an initial gene relationship model based on the initial gene entity relationship diagram.

[0064] In this embodiment, the initial gene entity relationship graph typically contains some kind of relationship or interaction between gene entities. Redundant information or erroneous data in the graph is checked and removed to ensure accurate labeling of nodes and edges, including the names of gene entities and the types of relationships. Appropriate data structures are used to represent the nodes and edges in the graph to construct an initial gene relationship model. This initial gene relationship model reflects the interactions and relationship networks between gene entities in the graph. Additional attribute information, such as the biological function, expression level, and interaction strength of the gene entities, is added to the nodes and edges in the initial gene relationship model. This attribute information helps enhance the interpretability and predictive ability of the model.

[0065] S1042: Based on the target gene entity dataset, optimize the initial gene relationship model to obtain the target gene relationship model.

[0066] In this embodiment, the target gene entity dataset is used to optimize the initial gene relationship model. Optimization methods include adding new relationships, adjusting the weights of existing relationships, and filtering out irrelevant gene entities, thereby improving the model's predictive ability and interpretability.

[0067] S1043: Import the data from the target gene entity dataset and the target gene relationship model into a pre-built gene database model according to a preset mapping rule to construct a gene relationship knowledge graph.

[0068] In this embodiment, the preset mapping rules include preset entity mapping rules and preset relationship mapping rules; the method of importing the data in the target gene entity dataset and the target gene relationship model into a pre-constructed gene database model according to the preset mapping rules to construct a gene relationship knowledge graph includes:

[0069] (1) According to the preset entity mapping rules, import the data in the target gene entity dataset into the node table of the gene database model.

[0070] (2) According to the preset relation mapping rules, import the data in the target gene relation model into the side table of the gene database model.

[0071] (3) Construct a gene relationship knowledge graph based on the gene database model after importing the data.

[0072] In this embodiment, the gene database model includes a MySQL database model. A MySQL database model is a relational database management system that uses tables (also called relations) to store and organize data. In the MySQL database model, data is stored in tables, each consisting of columns and rows. The MySQL database model is used to store and process complex data related to biological entities such as genes and proteins. To improve query efficiency, appropriate indexes are set for node tables and edge tables in the MySQL database, and query statements are optimized to ensure that the required information can be obtained quickly and accurately.

[0073] In this embodiment, the node table in the gene database model is typically used to store information related to gene entities (such as genes, proteins, diseases, etc.). By following preset entity mapping rules, it can be ensured that data from the target gene entity dataset is correctly and consistently imported into the node table, providing accurate node information for constructing a knowledge graph.

[0074] In this embodiment, the edge tables in the gene database model are used to store information about relationships between gene entities (such as interaction relationships, functional relationships, regulatory relationships, etc.). By following preset relationship mapping rules, it can be ensured that the data in the target gene relationship model is correctly and consistently imported into the edge tables, providing accurate relationship information for constructing a knowledge graph. Data mapping not only improves the accuracy of the data but also enhances the richness and diversity of the knowledge graph.

[0075] In this embodiment, after importing the data from the target gene entity dataset and the target gene relationship model into a pre-constructed gene database model according to preset mapping rules, the gene database model already contains the data from the target gene entity dataset and the target gene relationship model. At this point, this data can be used to construct a gene relationship knowledge graph and establish triple relationships, namely (node ​​1, relationship, node 2). These triple relationships contain a rich set of biological entities and their relationships, such as (gene A, interaction, gene B), (protein C, function, pathway D), etc. A gene relationship knowledge graph is a structure used to display gene entities and their relationships, which can help researchers intuitively understand the complex relationships between genes and facilitate further analysis and mining. Furthermore, the gene relationship knowledge graph constructed based on the MySQL database model also supports efficient query and analysis functions, providing strong support for subsequent research and applications.

[0076] In this embodiment, the method further includes: visualizing the gene relationship knowledge graph. The Vue framework, combined with relationship graphs in ECharts, is used for front-end display, dynamically presenting the constructed gene relationship knowledge graph to the user.

[0077] In this embodiment, the Vue framework is a progressive JavaScript framework for building user interfaces, suitable for constructing single-page applications. In the visualization of a gene relationship knowledge graph, the Vue framework can be used to build the overall structure and interaction logic of the user interface.

[0078] In this embodiment, ECharts is an open-source visualization library implemented in JavaScript that provides a rich variety of chart types, including relationship graphs. Relationship graphs are suitable for displaying the network of relationships between gene entities, clearly showing nodes (such as genes, proteins, etc.) and edges (such as interaction relationships, regulatory relationships, etc.).

[0079] In this embodiment, the Vue framework is used to construct the overall structure and layout of the front-end page, reserving a container within the page for displaying the gene relationship knowledge graph. The ECharts library is imported into the Vue component, and a relationship graph instance is initialized. The nodes and edges of the relationship graph are configured based on data extracted from the gene relationship knowledge graph, including node styles, edge styles, and layout. Dynamic data can be passed to the ECharts relationship graph instance through Vue's data binding mechanism, enabling dynamic data updates. Interactive features, such as node click events and edge hover events, are added to the relationship graph. These interactive features enhance the user experience, allowing users to flexibly query and explore gene relationships and their functions, providing a visual display and an intuitive, vivid information experience, enabling users to deeply explore complex gene networks.

[0080] In this embodiment, the method further includes: constructing a gene data query interface based on the gene relationship knowledge graph. A backend service is built using the Spring Boot framework to provide an efficient data query interface. By combining feature vectors generated by a natural language model, a high-level semantic structure is formed, achieving accurate matching between the gene relationship knowledge graph and user query needs, thereby improving query accuracy and response speed.

[0081] It is worth noting that the gene relationship knowledge graph construction method in this application integrates gene data from different databases to form a more comprehensive and accurate gene dataset. It then utilizes a natural language model for entity information extraction, generating an initial gene entity dataset and an initial gene entity relationship graph. This achieves cross-database gene information integration. The application of natural language processing technology improves the accuracy of gene entity and relationship identification, laying a solid foundation for constructing the gene relationship knowledge graph. Furthermore, an adaptive filtering algorithm is used to filter the initial gene entity dataset to obtain the target gene entity dataset. The filtering strategy is automatically adjusted based on data characteristics and quality, effectively removing redundant, inaccurate, or irrelevant information, improving the purity and reliability of the dataset. This not only optimizes the data processing workflow but also significantly improves the efficiency and quality of knowledge graph construction. Finally, based on the target gene entity dataset, the initial gene entity relationship graph, and a pre-constructed gene database model, a gene relationship knowledge graph is constructed. This graph not only comprehensively reveals the entirety of the gene network and its dynamic changes but also visually demonstrates the interactions between genes, providing researchers with an intuitive and convenient research tool. In addition, this knowledge graph supports query and intelligent analysis functions, which can help researchers delve into the potential patterns and rules in gene networks, providing powerful data support and analysis tools for fields such as gene research, disease diagnosis, and drug development.

[0082] Furthermore, the gene relationship knowledge graph constructed in this invention can also be used in the following scenarios:

[0083] (1) Improve the efficiency of biological research: By integrating various gene data and literature information, researchers can obtain the required information more quickly and save time in literature retrieval and data organization.

[0084] (2) Facilitating the understanding of gene function: Knowledge graphs provide a systematic view of the interactions between genes, enabling researchers to intuitively understand the biological functions and interrelationships of genes, thereby allowing for in-depth exploration of biological mechanisms.

[0085] (3) Facilitating new discoveries: Through network analysis, new gene functions and potential regulatory relationships can be identified, and previously unnoticed gene interactions can be discovered, thus promoting scientific innovation.

[0086] (4) Supporting multidisciplinary collaboration: Knowledge graphs can provide data support for multiple fields such as bioinformatics, drug development, and clinical research, and promote cross-disciplinary cooperation among various disciplines.

[0087] (5) Improve the scientific nature of decision-making: Knowledge graphs provide data-driven decision support for biomedical research, helping researchers make more scientific judgments in experimental design, data interpretation and clinical application.

[0088] (6) Provide educational tools: Knowledge graphs can be used as teaching resources to help biology and bioinformatics students better understand gene functions and interactions, thus empowering biology education.

[0089] (7) Sustainable updates and expansion: Since knowledge graphs are dynamic, they can be continuously updated and expanded with the emergence of new research results and data, thus maintaining the cutting-edge nature and accuracy of information.

[0090] (8) Assisting in disease research and treatment: Through in-depth analysis of gene relationships, identifying genes related to diseases can help develop new diagnostic tools and treatment strategies, and promote the development of precision medicine.

[0091] It should be noted that, in the embodiments of this application, the words "exemplary" or "for example" refer to examples, illustrations, or descriptions. Any embodiment or design described as "exemplary" or "for example" in this application should not be construed as being more preferred or advantageous than other embodiments or design solutions. Specifically, the use of words such as "exemplary" or "for example" is intended to present the relevant concepts in a concrete manner.

[0092] In this application embodiment, "at least one" refers to one or more, and "more than one" refers to two or more. "And / or" describes the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A alone, A and B simultaneously, or B alone, where A and B can be singular or plural. The character " / " generally indicates that the preceding and following related objects are in an "or" relationship. "At least one of the following" or similar expressions refer to any combination of these items, including any combination of single or plural items. For example, at least one of a, b, or c can represent: a, b, c, ab, ac, bc, or abc, where a, b, and c can be single or multiple.

[0093] Figure 4 This is a schematic block diagram of the gene relationship knowledge graph construction system provided in the embodiments of this application. For example... Figure 4 As shown, this gene relationship knowledge graph construction system includes:

[0094] The data preprocessing module 401 is used to acquire gene data from different databases and preprocess the gene data;

[0095] The entity information extraction module 402 is used to extract entity information from the preprocessed gene data using a natural language model to generate an initial gene entity dataset and an initial gene entity relationship graph.

[0096] The data filtering module 403 is used to perform data filtering operations on the initial gene entity dataset based on an adaptive filtering algorithm to obtain the target gene entity dataset.

[0097] The knowledge graph construction module 404 is used to construct a gene relationship knowledge graph based on the target gene entity dataset, the initial gene entity relationship graph, and a pre-constructed gene database model.

[0098] In this embodiment, the knowledge graph construction module 404 is further configured to perform the following steps: (1) visualize the gene relationship knowledge graph; (2) construct a gene data query interface based on the gene relationship knowledge graph.

[0099] It should be understood that the specific process of each module performing the above-mentioned corresponding steps has been described in detail in the above method embodiments, and will not be repeated here for the sake of brevity.

[0100] It should also be understood that the module division in the embodiments of this application is illustrative and only represents a logical functional division; in actual implementation, there may be other division methods. Furthermore, the functional modules in the various embodiments of this application can be integrated into a single processor, exist as separate physical entities, or be integrated into a single module. The integrated modules described above can be implemented in hardware or as software functional modules.

[0101] Figure 5 This is an architecture diagram of the gene relationship knowledge graph construction system provided in the embodiments of this application. For example... Figure 5 As shown, gene data is collected from various databases, including but not limited to: public medical databases, medical research paper databases, and patent literature databases. After extracting entity information from the preprocessed gene data using a natural language model (AI model), an adaptive filtering algorithm is used for data filtering, combined with manual comparison and verification, to obtain the target gene entity dataset. The data from the target gene entity dataset and the target gene relationship model are imported into a pre-constructed gene database model according to preset mapping rules to construct a gene relationship knowledge graph and establish triplet relationships. A backend service is built to provide an efficient data query interface. Based on the built frontend, the queried data is visualized.

[0102] Figure 6 This is a schematic block diagram of an electronic terminal provided in an embodiment of this application. The electronic terminal includes a memory, a processor, and a computer program stored in the memory. The processor executes the computer program to implement the gene relationship knowledge graph construction method described above. Figure 6 As shown, the electronic terminal 600 includes at least one processor 601, a memory 602, at least one network interface 603, and a user interface 605. The various components in the device are coupled together via a bus system 604. It is understood that the bus system 604 is used to implement communication between these components. In addition to a data bus, the bus system 604 also includes a power bus, a control bus, and a status signal bus. However, for clarity, in… Figure 6 The general will label all buses as bus systems.

[0103] The user interface 605 may include a monitor, keyboard, mouse, trackball, clicker, button, touchpad, or touch screen.

[0104] It is understood that memory 602 can be volatile memory or non-volatile memory, or both. Non-volatile memory can be read-only memory (ROM) or programmable read-only memory (PROM), used as an external cache. By way of example, but not limitation, many forms of RAM are available, such as static random access memory (SRAM) and synchronous static random access memory (SSRAM). The memories described in the embodiments of this invention are intended to include, but are not limited to, these and any other suitable categories of memory.

[0105] In this embodiment of the invention, the memory 602 is used to store various types of data to support the operation of the electronic terminal 600. Examples of this data include: any executable program for operation on the electronic terminal 600, such as the operating system 6021 and application programs 6022; the operating system 6021 includes various system programs, such as the framework layer, core library layer, driver layer, etc., for implementing various basic services and handling hardware-based tasks. The application program 6022 may include various applications, such as media players, browsers, etc., for implementing various application services. The gene relationship knowledge graph construction method provided in this embodiment of the invention can be included in the application program 6022.

[0106] The methods disclosed in the above embodiments of the present invention can be applied to processor 601, or implemented by processor 601. Processor 601 may be an integrated circuit chip with signal processing capabilities. In the implementation process, each step of the above method can be completed by the integrated logic circuit of the hardware in processor 601 or by instructions in the form of software. The processor 601 may be a general-purpose processor, a digital signal processor (DSP), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. Processor 601 can implement or execute the methods, steps, and logic block diagrams disclosed in the embodiments of the present invention. General-purpose processor 601 may be a microprocessor or any conventional processor, etc. The steps of the accessory optimization method provided in the embodiments of the present invention can be directly reflected as being executed by a hardware decoding processor, or being executed by a combination of hardware and software modules in the decoding processor. The software module may be located in a storage medium, which is located in memory. The processor reads the information in the memory and combines it with its hardware to complete the steps of the aforementioned method.

[0107] In an exemplary embodiment, the electronic terminal 600 may be used by one or more application-specific integrated circuits (ASICs), DSPs, programmable logic devices (PLDs), or complex programmable logic devices (CPLDs) to perform the aforementioned method.

[0108] According to the method provided in the embodiments of this application, this application also provides a computer program product, which includes: computer program code, which, when run on a computer, causes the computer to execute... Figures 1 to 3 The method of any of the embodiments shown.

[0109] According to the method provided in the embodiments of this application, this application also provides a computer-readable storage medium storing program code, which, when executed on a computer, causes the computer to perform... Figures 1 to 3 The method of any of the embodiments shown.

[0110] As used in this specification, the terms "component," "module," "system," etc., are used to refer to computer-related entities, hardware, firmware, combinations of hardware and software, software, or software in execution. For example, a component can be, but is not limited to, a process running on a processor, a processor, an object, an executable file, an execution thread, a program, and / or a computer. As illustrated, applications running on computing devices and computing devices can both be components. One or more components may reside in a process and / or an execution thread, and components may be located on a single computer and / or distributed among two or more computers. Furthermore, these components can be executed from various computer-readable media on which various data structures are stored. Components can communicate, for example, via local and / or remote processes based on signals having one or more data packets (e.g., data from two components interacting with another component between a local system, a distributed system, and / or a network, such as the Internet interacting with other systems via signals).

[0111] Those skilled in the art will recognize that the various illustrative logical blocks and steps described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementations should not be considered beyond the scope of this application.

[0112] Those skilled in the art will understand that, for the sake of convenience and brevity, the specific working processes of the systems, devices, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0113] In the several embodiments provided in this application, it should be understood that the disclosed systems, apparatuses, and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between apparatuses or units may be electrical, mechanical, or other forms.

[0114] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0115] In addition, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit.

[0116] In the above embodiments, the functions of each functional unit can be implemented entirely or partially through software, hardware, firmware, or any combination thereof. When implemented using software, it can be implemented entirely or partially in the form of a computer program product. A computer program product includes one or more computer instructions (programs). When the computer program instructions (programs) are loaded and executed on a computer, all or part of the flow or function according to the embodiments of this application is generated. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. Computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center via wired (e.g., coaxial cable, fiber optic, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) means. The computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server or data center that integrates one or more available media. The available media can be magnetic media (e.g., floppy disks, hard disks, magnetic tapes), optical media (e.g., high-density digital video discs, DVDs), or semiconductor media (e.g., solid-state disks, SSDs, etc.).

[0117] If a function is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or a part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods of the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0118] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the technical scope disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

[0119] In summary, this application provides a method, system, medium, product, and terminal for constructing a gene relationship knowledge graph. By integrating gene data from different databases, a more comprehensive and accurate gene dataset is formed. Entity information is extracted using a natural language model, generating an initial gene entity dataset and an initial gene entity relationship graph. This achieves cross-database gene information integration. The application of natural language processing technology improves the accuracy of gene entity and relationship recognition, laying a solid foundation for constructing a gene relationship knowledge graph. Furthermore, an adaptive filtering algorithm is used to filter the initial gene entity dataset to obtain the target gene entity dataset. The filtering strategy is automatically adjusted based on data characteristics and quality, effectively removing redundant, inaccurate, or irrelevant information, improving the purity and reliability of the dataset. This not only optimizes the data processing flow but also significantly improves the efficiency and quality of knowledge graph construction. Finally, based on the target gene entity dataset, the initial gene entity relationship graph, and a pre-constructed gene database model, a gene relationship knowledge graph is constructed. This graph not only comprehensively reveals the entirety of the gene network and its dynamic changes but also visually demonstrates the interactions between genes, providing researchers with an intuitive and convenient research tool. Furthermore, this knowledge graph supports query and intelligent analysis functions, enabling researchers to delve deeper into the potential patterns and regularities within gene networks, providing powerful data support and analytical tools for fields such as gene research, disease diagnosis, and drug development. Therefore, this application effectively overcomes the various shortcomings of existing technologies and possesses high industrial applicability.

[0120] The above embodiments are merely illustrative of the principles and effects of this application and are not intended to limit this application. Any person skilled in the art can modify or alter the above embodiments without departing from the spirit and scope of this application. Therefore, all equivalent modifications or alterations made by those skilled in the art without departing from the spirit and technical concept disclosed in this application should still be covered by the claims of this application.

Claims

1. A method for constructing a gene relationship knowledge graph, characterized in that, include: Gene data from different databases are acquired and the gene data is preprocessed. Entity information is extracted from the preprocessed gene data using a natural language model to generate an initial gene entity dataset and an initial gene entity relationship graph. Based on an adaptive filtering algorithm, the initial gene entity dataset is filtered to obtain the target gene entity dataset. Based on the target gene entity dataset, the initial gene entity relationship graph, and a pre-built gene database model, a gene relationship knowledge graph is constructed.

2. The method for constructing a gene relationship knowledge graph according to claim 1, characterized in that, The methods for constructing a gene relationship knowledge graph based on the target gene entity dataset, the initial gene entity relationship graph, and a pre-built gene database model include: Based on the initial gene entity relationship diagram, construct an initial gene relationship model; Based on the target gene entity dataset, the initial gene relationship model is optimized to obtain the target gene relationship model; The data from the target gene entity dataset and the target gene relationship model are imported into a pre-built gene database model according to preset mapping rules to construct a gene relationship knowledge graph.

3. The method for constructing a gene relationship knowledge graph according to claim 2, characterized in that, The preset mapping rules include preset entity mapping rules and preset relation mapping rules; the method of importing the data in the target gene entity dataset and the target gene relation model into the pre-constructed gene database model according to the preset mapping rules to construct a gene relation knowledge graph includes: According to the preset entity mapping rules, the data in the target gene entity dataset is imported into the node table of the gene database model; According to the preset relation mapping rules, the data in the target gene relation model is imported into the side table of the gene database model; Based on the imported data and the resulting gene database model, a gene relationship knowledge graph is constructed.

4. The method for constructing a gene relationship knowledge graph according to claim 1, characterized in that, The methods for extracting entity information from the preprocessed gene data using natural language models to generate an initial gene entity dataset and an initial gene entity relationship graph include: The preprocessed gene data is extracted using a natural language model to obtain gene entity feature data and gene entity relationship data. Based on the gene entity feature data, an initial gene entity dataset is generated; Based on the gene entity relationship data, an initial gene entity relationship graph is constructed.

5. The method for constructing a gene relationship knowledge graph according to claim 1, characterized in that, The method further includes: visualizing the gene relationship knowledge graph.

6. The method for constructing a gene relationship knowledge graph according to claim 1, characterized in that, The method further includes: constructing a gene data query interface based on the gene relationship knowledge graph.

7. A gene relationship knowledge graph construction system, characterized in that, include: A data preprocessing module is used to acquire gene data from different databases and preprocess the gene data; The entity information extraction module is used to extract entity information from the preprocessed gene data using a natural language model to generate an initial gene entity dataset and an initial gene entity relationship graph. The data filtering module is used to perform data filtering operations on the initial gene entity dataset based on an adaptive filtering algorithm to obtain the target gene entity dataset. The knowledge graph construction module is used to construct a gene relationship knowledge graph based on the target gene entity dataset, the initial gene entity relationship graph, and a pre-built gene database model.

8. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the gene relationship knowledge graph construction method as described in any one of claims 1 to 6.

9. A computer program product, characterized in that, The computer program product includes computer program code, which, when run on a computer, enables the computer to implement the gene relationship knowledge graph construction method as described in any one of claims 1 to 6.

10. An electronic terminal, comprising a memory, a processor, and a computer program stored in the memory, characterized in that, The processor executes the computer program to implement the gene relationship knowledge graph construction method as described in any one of claims 1 to 6.

Images