A method and device for constructing a high-throughput drug screening model based on bioinformatics
By constructing a high-throughput drug screening model based on bioinformatics, combining gene network diagrams, protein structure models, and metabolic pathway models, the problem of insufficient understanding of complex biological processes by traditional models is solved, and efficient and highly accurate drug screening is achieved.
Patent Information
- Application Number
- CN202411244684.X
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2024-09-06
- Publication Date
- 2024-11-12
- Estimated Expiration
- 2044-09-06
AI Technical Summary
Traditional high-throughput drug screening models lack a comprehensive understanding of complex biological processes, leading to discrepancies between screening results and actual drug efficacy.
A bioinformatics-based high-throughput drug screening model construction method is used to construct gene network diagrams, protein structure models, and metabolic pathway models by collecting gene sequence data, protein structure data, and metabolic pathway data. Combined with drug response data, multi-target screening model combination simulation is performed to build a high-throughput drug screening platform.
This improved the efficiency and accuracy of drug screening, enabling highly efficient and precise identification of drug efficacy in test samples.
Smart Images

Figure CN118762758B_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the field of bioinformatics, and in particular to a method and device for constructing a high-throughput drug screening model based on bioinformatics. Background Art
[0002] High-throughput screening (HTS) is a technology platform used to evaluate the activity or toxicity of a large number of compounds. It allows researchers to test thousands of compounds in a short period of time to quickly identify candidate drugs with specific biological activity.
[0003] The current traditional way of constructing high-throughput drug screening models relies on automation technologies, such as microplate readers, automatic sample pipettes, and robotic arms, to achieve rapid testing of large numbers of compounds. However, traditional high-throughput drug screening models often lack a comprehensive understanding of complex biological processes, resulting in screening results that may differ from actual drug efficacy. Summary of the invention
[0004] The present invention provides a method and device for constructing a high-throughput drug screening model based on biological information, the main purpose of which is to improve the efficiency and accuracy of drug screening.
[0005] To achieve the above-mentioned purpose, the present invention provides a method for constructing a high-throughput drug screening model based on bioinformatics, comprising:
[0006] Collecting biological information data of an organism, wherein the biological information data includes gene sequence data, protein structure data, metabolic pathway data, and drug response data;
[0007] Cleaning the gene sequence data to obtain cleaned gene sequence data, constructing a gene network diagram of the organism based on the cleaned gene sequence data, and constructing a gene expression screening model for the sample to be tested based on the gene network diagram;
[0008] Based on the protein structure data, construct a protein structure model of the organism, identify the geometric quality and overall quality of the protein structure model, and construct a molecular docking screening model for the sample to be tested based on the geometric quality and overall quality of the protein structure model;
[0009] Based on the metabolic pathway data, analyzing the drug metabolism mechanism and drug metabolism regulatory network of the organism, and constructing a metabolic pathway screening model for the sample to be tested based on the drug metabolism mechanism and drug metabolism regulatory network;
[0010] Utilizing the drug response data, a multi-target screening model for the sample to be tested is constructed, and the gene expression screening model, the molecular docking screening model, the metabolic pathway screening model and the multi-target screening model are combined and simulated to obtain a target model combination for the sample to be tested, and a high-throughput drug screening platform for the sample to be tested is constructed. Based on the high-throughput drug screening platform and the target model combination, a high-throughput drug screening model for the sample to be tested is constructed.
[0011] Optionally, constructing a gene network diagram of the organism based on the cleaned gene sequence data comprises:
[0012] Using a preset BLAST tool to perform sequence comparison on the cleaned gene sequence data to obtain similar sequences and potential homologous genes of the cleaned gene sequence data;
[0013] Performing functional annotation on the potential homologous genes to obtain homologous gene annotation information;
[0014] Defining network nodes of the organism, and constructing an initial gene network diagram of the organism through the network nodes, similar sequences, potential homologous genes and homologous gene annotation information;
[0015] Identifying redundant connections and isolated nodes of the initial gene network graph;
[0016] Based on the redundant connections and isolated nodes, the initial gene network graph is optimized to obtain the gene network graph of the organism.
[0017] Optionally, the optimizing the initial gene network graph based on the redundant connections and isolated nodes to obtain the gene network graph of the organism comprises:
[0018] Removing redundant connections and isolated nodes corresponding to the initial gene network graph to obtain an optimized gene network graph;
[0019] The average degree of the network nodes corresponding to the optimized gene network graph is calculated using the following formula:
[0020]
[0021] in, represents the average degree of the network nodes corresponding to the optimized gene network graph, Indicates the number of network nodes corresponding to the optimized gene network graph, Represents the adjacency matrix element of the network node corresponding to the optimized gene network graph. If the network node and network nodes If there is an edge between is 1, otherwise is 0;
[0022] The focusing coefficient of the corresponding network node of the optimized gene network graph is calculated using the following formula:
[0023]
[0024] in, Indicates the corresponding network nodes of the optimized gene network graph The focusing factor, Indicates the corresponding network nodes of the optimized gene network graph The degree, Optimize the corresponding network nodes of the gene network graph The actual number of edges that exist;
[0025] The network density of the network nodes corresponding to the optimized gene network graph is calculated using the following formula:
[0026]
[0027] in, Indicates the network density of the corresponding network nodes in the optimized gene network graph, Indicates the number of network nodes corresponding to the optimized gene network graph, Optimize the number of network connection edges corresponding to the gene network graph;
[0028] Analyze the network topology stability coefficient of the optimized gene network graph based on the average degree, focusing coefficient and network density of the corresponding network nodes of the optimized gene network graph;
[0029] When the network topology stability coefficient meets a preset network topology stability threshold, the optimized gene network graph is used as the gene network graph of the organism.
[0030] Optionally, constructing a gene expression screening model for the sample to be tested based on the gene network diagram comprises:
[0031] Determine the drug screening target of the samples to be tested;
[0032] Based on the drug screening target, determining key network nodes in the gene network graph;
[0033] Based on the gene network diagram, analyzing the interaction relationship of the key network nodes, wherein the interaction relationship includes upstream and downstream regulatory relationships and signal transduction pathways;
[0034] Collecting gene expression data of the key network nodes and interaction relationships;
[0035] extracting gene expression features from the gene expression data;
[0036] A gene expression screening model for the sample to be tested is constructed based on the gene expression characteristics.
[0037] Optionally, the identifying the geometric quality and overall quality of the protein structure model comprises:
[0038] Calculating the model consistency and atomic position deviation of the protein structure model;
[0039] Identifying the residue conformations of the protein structure model and calculating conformational conformation coefficients of the residue conformations;
[0040] Analyzing the geometric quality of the protein structure model through the model consistency, atomic position deviation and conformational conformation coefficient;
[0041] Performing a dynamics simulation on the protein structure model to obtain a dynamics simulation result of the protein structure model;
[0042] The binding free energy of the protein structure model was calculated using the following formula based on the kinetic simulation results:
[0043] in, It represents the binding free energy of the interaction between the simulated protein and the ligand in the dynamics simulation results. It represents the free energy of the protein-ligand complex that simulates the interaction between protein and ligand in the dynamics simulation results. It represents the protein free energy of the interaction between the simulated protein and the ligand in the dynamics simulation results. It represents the ligand free energy of the interaction between the simulated protein and the ligand in the dynamics simulation results;
[0044] Based on the binding free energy, the overall quality of the protein structure model is analyzed.
[0045] Optionally, constructing a molecular docking screening model for the sample to be tested based on the geometric quality and overall quality of the protein structure model comprises:
[0046] Based on the geometric quality and overall quality of the protein structure model, the protein structure model is optimized to obtain an optimized protein structure model;
[0047] Constructing a drug molecular structure model of the sample to be tested;
[0048] Determine the docking software of the drug molecular structure model and the protein structure model;
[0049] Configuring docking parameters of the docking software;
[0050] The drug molecule structure model and the protein structure model are docked by using the docking parameters to obtain a docking conformation;
[0051] Based on the docking conformation, analyzing the binding ability and affinity of the drug molecular structure model and the protein structure model;
[0052] According to the binding ability and affinity, a molecular docking screening model of the sample to be tested is constructed.
[0053] Optionally, analyzing the drug metabolism mechanism and drug metabolism regulatory network of the organism based on the metabolic pathway data comprises:
[0054] analyzing a drug metabolism profile of the organism based on the metabolic pathway data;
[0055] identifying drug metabolism pathways in the drug metabolism profile;
[0056] Identify the key metabolic steps and metabolites in the drug metabolism pathway;
[0057] Determining the drug metabolism mechanism of the organism based on the key metabolic steps and metabolites;
[0058] identifying regulatory genes for said key metabolic steps;
[0059] The drug metabolism regulatory network of the organism is constructed through the drug metabolism pathway and regulatory genes.
[0060] Optionally, using the drug response data to construct a multi-target screening model for the sample to be tested includes:
[0061] Based on the drug response data, analyzing the drug action targets of the organism corresponding to the drug response data;
[0062] Determining the target action mechanism of the drug target through the drug response data;
[0063] Analyzing the drug target binding mode and signal transduction pathway of the drug target according to the target action mechanism;
[0064] analyzing adverse reactions of the organism based on the drug response data;
[0065] Based on the drug action targets, drug target binding modes, signal transduction pathways and adverse reactions, a multi-target screening model for the sample to be tested is constructed.
[0066] Optionally, the gene expression screening model, the molecular docking screening model, the metabolic pathway screening model and the multi-target screening model are combined and simulated to obtain the target model combination of the sample to be tested, including:
[0067] Constructing gene expression test data, molecular docking test data, metabolic pathway test data and multi-target test data of the gene expression screening model, molecular docking screening model, metabolic pathway screening model and multi-target screening model respectively;
[0068] Through the gene expression test data, molecular docking test data, metabolic pathway test data and multi-target test data, the gene expression screening model, molecular docking screening model, metabolic pathway screening model and multi-target screening model are optimized to obtain a target gene expression screening model, a target molecule docking screening model, a target metabolic pathway screening model and a target multi-target screening model;
[0069] Determine the model combination strategy of the target gene expression screening model, the target molecule docking screening model, the target metabolic pathway screening model and the target multi-target screening model;
[0070] Through the model combination strategy, a multi-combination model of the target gene expression screening model, the target molecule docking screening model, the target metabolic pathway screening model and the target multi-target screening model is constructed;
[0071] Using preset multi-model combination test data, simulating the multi-combination model to obtain simulation results;
[0072] Based on the simulation results, constructing the ROC curve of the multi-combination model;
[0073] The AUC value of the ROC curve was calculated using the following formula:
[0074]
[0075] in, Represents the AUC value of the ROC curve, Indicated in The true positive rate of the curve points is Indicates The false positive rate of the curve points is Indicates the number of curve points corresponding to the ROC curve;
[0076] Based on the AUC value of the ROC curve, the target model combination of the sample to be tested is determined.
[0077] To achieve the above object, the present invention also provides a high-throughput drug screening model construction device based on biological information, comprising:
[0078] A biological information data acquisition module, used to collect biological information data of an organism, wherein the biological information data includes gene sequence data, protein structure data, metabolic pathway data, and drug response data;
[0079] A gene expression screening model construction module, used for cleaning the gene sequence data to obtain cleaned gene sequence data, constructing a gene network diagram of the organism based on the cleaned gene sequence data, and constructing a gene expression screening model of the sample to be tested based on the gene network diagram;
[0080] A molecular docking screening model construction module is used to construct a protein structure model of the organism based on the protein structure data, identify the geometric quality and overall quality of the protein structure model, and construct a molecular docking screening model of the sample to be tested based on the geometric quality and overall quality of the protein structure model;
[0081] A metabolic pathway screening model construction module is used to analyze the drug metabolism mechanism and drug metabolism regulatory network of the organism based on the metabolic pathway data, and to construct a metabolic pathway screening model for the sample to be tested based on the drug metabolism mechanism and drug metabolism regulatory network;
[0082] A high-throughput drug screening model construction module is used to use the drug response data to construct a multi-target screening model for the sample to be tested, to perform combined simulation on the gene expression screening model, the molecular docking screening model, the metabolic pathway screening model and the multi-target screening model to obtain a target model combination for the sample to be tested, to construct a high-throughput drug screening platform for the sample to be tested, and to construct a high-throughput drug screening model for the sample to be tested based on the high-throughput drug screening platform and the target model combination.
[0083] In order to solve the above problem, the present invention further provides an electronic device, the electronic device comprising:
[0084] A memory storing at least one instruction; and a processor executing the instruction stored in the memory to implement the above-mentioned method for constructing a high-throughput drug screening model based on biological information.
[0085] In order to solve the above problems, the present invention also provides a computer-readable storage medium, in which at least one instruction is stored, and the at least one instruction is executed by a processor in an electronic device to implement the above-mentioned method for constructing a high-throughput drug screening model based on biological information.
[0086] The present invention constructs a gene network diagram of the organism based on the cleaned gene sequence data, which can construct a gene network diagram that reflects the gene interactions and regulatory relationships in the organism, which helps to deeply understand the gene expression regulation mechanism of the organism; the present invention constructs a gene expression screening model of the sample to be tested based on the gene network diagram as the basis for the subsequent target drug screening model; further, the present invention constructs a protein structure model of the organism based on the protein structure data as the basis for constructing a subsequent screening model. In detail, the geometric quality and overall quality of the protein structure model identified by the present invention can determine the reliability and applicability of the model, thereby improving the reliability of the later model construction. Further, based on the geometric quality and overall quality of the protein structure model, the present invention constructs the molecular docking screening model of the sample to be tested as the basis for the later target drug screening model construction. Further, based on the drug metabolism mechanism and drug metabolism regulatory network, the present invention constructs the metabolic pathway screening model of the sample to be tested, which can better understand the metabolic process of the drug in the organism and predict the metabolic behavior of the drug. Finally, based on the high-throughput drug screening platform and the target model combination, the high-throughput drug screening model of the sample to be tested can be constructed. The high-throughput drug screening platform can collect the biological information of the sample to be tested in large quantities and efficiently, and the target model combination is used to perform the potential drug efficacy analysis of the sample, thereby realizing the high-efficiency and high-precision drug efficacy identification of the sample to be tested. Therefore, the present invention can improve the efficiency and accuracy of drug screening. BRIEF DESCRIPTION OF THE DRAWINGS
[0087] Figure 1 A schematic diagram of a process for constructing a high-throughput drug screening model based on biological information provided by one embodiment of the present invention;
[0088] Figure 2 A functional module diagram of a high-throughput drug screening model construction device based on biological information provided by one embodiment of the present invention;
[0089] Figure 3 A schematic diagram of the structure of an electronic device for implementing the method for constructing a high-throughput drug screening model based on biological information provided in one embodiment of the present invention.
[0090] The realization of the purpose, functional features and advantages of the present invention will be further explained in conjunction with embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION
[0091] It should be understood that the specific embodiments described herein are only used to explain the present invention, and are not used to limit the present invention.
[0092] The embodiment of the present application provides a method for constructing a high-throughput drug screening model based on biological information. The execution subject of the method for constructing a high-throughput drug screening model based on biological information includes but is not limited to at least one of the electronic devices such as a server and a terminal that can be configured to execute the method provided in the embodiment of the present application. In other words, the method for constructing a high-throughput drug screening model based on biological information can be executed by software or hardware installed on a terminal device or a server device, and the software can be a blockchain platform. The server includes but is not limited to: a single server, a server cluster, a cloud server or a cloud server cluster, etc.
[0093] Reference Figure 1 FIG. 1 is a flow chart of a method for constructing a high-throughput drug screening model based on biological information provided by an embodiment of the present invention. In this embodiment, the method for constructing a high-throughput drug screening model based on biological information includes:
[0094] S1. Collect biological information data of an organism, wherein the biological information data includes gene sequence data, protein structure data, metabolic pathway data, and drug response data.
[0095] It should be explained that the gene sequence data refers to the base sequence on the DNA molecule, which encodes the amino acid sequence of the protein. These data can be obtained from public databases such as GenBank, Ensembl, etc. The protein structure data refers to the data reflecting the three-dimensional spatial structure of the protein. These data can be obtained from databases such as Protein DataBank (PDB). The metabolic pathway data refers to the data describing a series of enzymatic reactions in organisms. These data can be obtained from databases such as Kyoto Encyclopedia of Genes and Genomes (KEGG) and Reactome. The drug response data refers to the data describing the interaction between drugs and organisms. These data can be obtained from drug databases such as DrugBank, ChEMBL, etc.
[0096] S2. Cleaning the gene sequence data to obtain cleaned gene sequence data, constructing a gene network diagram of the organism based on the cleaned gene sequence data, and constructing a gene expression screening model for the sample to be tested based on the gene network diagram.
[0097] It should be explained that the cleaned gene sequence data refers to the gene sequence data after removing low-quality sequences, removing linker sequences, removing short sequences, removing duplicate sequences and performing sequence correction operations on the gene sequence data.
[0098] The present invention constructs a gene network diagram of the organism based on the cleaned gene sequence data, and can construct a gene network diagram that reflects the gene interactions and regulatory relationships in the organism, which helps to deeply understand the gene expression regulatory mechanism of the organism.
[0099] In detail, the constructing of the gene network diagram of the organism based on the cleaned gene sequence data includes:
[0100] Using a preset BLAST tool to perform sequence comparison on the cleaned gene sequence data to obtain similar sequences and potential homologous genes of the cleaned gene sequence data;
[0101] Performing functional annotation on the potential homologous genes to obtain homologous gene annotation information;
[0102] Defining network nodes of the organism, and constructing an initial gene network diagram of the organism through the network nodes, similar sequences, potential homologous genes and homologous gene annotation information;
[0103] Identifying redundant connections and isolated nodes of the initial gene network graph;
[0104] Based on the redundant connections and isolated nodes, the initial gene network graph is optimized to obtain the gene network graph of the organism.
[0105] Among them, the BLAST tool refers to a sequence alignment tool used in bioinformatics, the similar sequence refers to a sequence that has a certain degree of similarity with the query sequence during the BLAST alignment process, the potential homologous gene refers to a gene found in the sequence alignment process that has sufficient similarity with the query sequence so that it may be derived from the same ancestral gene, the homologous gene annotation information refers to a description of the function, biological process, cellular component and molecular function of potential homologous genes through bioinformatics methods, the initial gene network diagram refers to a preliminary network diagram of the relationship between genes constructed based on sequence alignment and homologous gene annotation information, the redundant connection refers to multiple paths that can connect the same pair of nodes in the gene network diagram, the isolated node refers to a node that is not connected to any other node in the gene network diagram, and the gene network diagram refers to a graphical representation of the relationship between genes.
[0106] Furthermore, the initial gene network diagram is optimized based on the redundant connections and isolated nodes to obtain the gene network diagram of the organism, including:
[0107] Removing redundant connections and isolated nodes corresponding to the initial gene network graph to obtain an optimized gene network graph;
[0108] The average degree of the network nodes corresponding to the optimized gene network graph is calculated using the following formula:
[0109]
[0110] in, represents the average degree of the network nodes corresponding to the optimized gene network graph, Indicates the number of network nodes corresponding to the optimized gene network graph, Represents the adjacency matrix element of the network node corresponding to the optimized gene network graph. If the network node and network nodes If there is an edge between is 1, otherwise is 0;
[0111] The focusing coefficient of the corresponding network node of the optimized gene network graph is calculated using the following formula:
[0112]
[0113] in, Indicates the corresponding network nodes of the optimized gene network graph The focusing factor, Indicates the corresponding network nodes of the optimized gene network graph The degree, Optimize the corresponding network nodes of the gene network graph The actual number of edges that exist;
[0114] The network density of the network nodes corresponding to the optimized gene network graph is calculated using the following formula:
[0115]
[0116] in, Indicates the network density of the corresponding network nodes in the optimized gene network graph, Indicates the number of network nodes corresponding to the optimized gene network graph, Optimize the number of network connection edges corresponding to the gene network graph;
[0117] Analyze the network topology stability coefficient of the optimized gene network graph based on the average degree, focusing coefficient and network density of the corresponding network nodes of the optimized gene network graph;
[0118] When the network topology stability coefficient meets a preset network topology stability threshold, the optimized gene network graph is used as the gene network graph of the organism.
[0119] Among them, the average degree refers to the average value of the degrees of all nodes in the network, the focusing coefficient refers to the degree of triangular relationship formed between node neighbors in the network, the network density refers to the ratio of the actual number of edges in the network to the maximum number of edges that may exist, the network topology stability coefficient refers to an indicator used to measure the stability of the network topology, the adjacency matrix element refers to the matrix representing the connection relationship between nodes in the network, and the network topology stability threshold refers to a preset standard used to determine whether the network topology stability coefficient reaches an acceptable level.
[0120] Based on the gene network diagram, the present invention constructs a gene expression screening model for the sample to be tested as the basis for a later target drug screening model.
[0121] In detail, the gene expression screening model of the sample to be tested is constructed based on the gene network diagram, including:
[0122] Determine the drug screening target of the samples to be tested;
[0123] Based on the drug screening target, determining key network nodes in the gene network graph;
[0124] Based on the gene network diagram, analyzing the interaction relationship of the key network nodes, wherein the interaction relationship includes upstream and downstream regulatory relationships and signal transduction pathways;
[0125] Collecting gene expression data of the key network nodes and interaction relationships;
[0126] extracting gene expression features from the gene expression data;
[0127] A gene expression screening model for the sample to be tested is constructed based on the gene expression characteristics.
[0128] Among them, the drug screening target refers to the target disease or pathological state for drug screening, the key network node refers to the gene that has an important regulatory effect on a specific biological process or disease state in the gene network diagram, and the upstream and downstream regulatory relationship refers to the regulatory order of genes in the network, including which genes control the expression of which genes (upstream), and which genes are regulated by other genes (downstream). This relationship usually involves regulatory elements such as transcription factors, promoters, and enhancers. The signal transduction pathway refers to how signal molecules inside and outside the cell transmit signals to cells through a series of biochemical reactions and ultimately cause specific biological responses. These pathways usually involve multiple protein kinases, phosphorylation events, and signal molecules. The gene expression data refers to the expression level information of genes under different conditions (such as drug treatment, disease state, etc.) measured by experimental means (such as RNA-seq, microarray, etc.), and the gene expression feature refers to the quantitative or qualitative indicators extracted from the gene expression data that can represent a specific biological state or response, such as differentially expressed genes, expression changes, expression patterns, and other features. The gene expression screening model refers to a model based on gene expression features for predicting drug effects or screening potential drugs.
[0129] S3. Based on the protein structure data, construct a protein structure model of the organism, identify the geometric quality and overall quality of the protein structure model, and construct a molecular docking screening model for the sample to be tested based on the geometric quality and overall quality of the protein structure model.
[0130] The present invention constructs a protein structure model of the organism based on the protein structure data as a basis for constructing a later screening model. In detail, the protein structure model can be constructed using tools such as PyMOL and Chimera.
[0131] The present invention identifies the geometric quality and overall quality of the protein structure model to determine the reliability and applicability of the model, thereby improving the reliability of subsequent model construction.
[0132] In detail, the identifying the geometric quality and overall quality of the protein structure model comprises:
[0133] Calculating the model consistency and atomic position deviation of the protein structure model;
[0134] Identifying the residue conformations of the protein structure model and calculating conformational conformation coefficients of the residue conformations;
[0135] Analyzing the geometric quality of the protein structure model through the model consistency, atomic position deviation and conformational conformation coefficient;
[0136] Performing a dynamics simulation on the protein structure model to obtain a dynamics simulation result of the protein structure model;
[0137] The binding free energy of the protein structure model was calculated using the following formula based on the kinetic simulation results:
[0138] in, It represents the binding free energy of the interaction between the simulated protein and the ligand in the dynamics simulation results. It represents the free energy of the protein-ligand complex that simulates the interaction between protein and ligand in the dynamics simulation results. It represents the protein free energy of the interaction between the simulated protein and the ligand in the dynamics simulation results. It represents the ligand free energy of the interaction between the simulated protein and the ligand in the dynamics simulation results;
[0139] Based on the binding free energy, the overall quality of the protein structure model is analyzed.
[0140] Among them, the model consistency refers to the similarity between the protein structure model and the known three-dimensional structure, the atomic position deviation refers to the deviation of each atom in the protein structure model relative to its theoretical position, the residue conformation refers to the specific three-dimensional conformation of each residue in the protein structure, the conformational conformation coefficient refers to a quantitative indicator used to evaluate the similarity between the residue conformation in the protein structure model and the residue conformation in the known structure, the geometric quality refers to the geometric rationality and accuracy of the protein structure model, the dynamics simulation result refers to the behavior of the protein structure model obtained by molecular dynamics simulation during the dynamics process, the binding free energy refers to the parameter for predicting the stability of protein binding to the ligand, the protein-ligand complex free energy refers to the free energy of the complex formed after the protein binds to the ligand, the protein free energy refers to the free energy of the protein when it is not bound to the ligand, the ligand free energy refers to the free energy of the ligand when it is not bound to the protein, and the overall quality refers to the stability of the protein structure model in the dynamics simulation.
[0141] The present invention constructs a molecular docking screening model of the sample to be tested based on the geometric quality and overall quality of the protein structure model as a basis for constructing a subsequent target drug screening model.
[0142] In detail, the molecular docking screening model of the sample to be tested is constructed based on the geometric quality and overall quality of the protein structure model, including:
[0143] Based on the geometric quality and overall quality of the protein structure model, the protein structure model is optimized to obtain an optimized protein structure model;
[0144] Constructing a drug molecular structure model of the sample to be tested;
[0145] Determine the docking software of the drug molecular structure model and the protein structure model;
[0146] Configuring docking parameters of the docking software;
[0147] The drug molecule structure model and the protein structure model are docked by using the docking parameters to obtain a docking conformation;
[0148] Based on the docking conformation, analyzing the binding ability and affinity of the drug molecular structure model and the protein structure model;
[0149] According to the binding ability and affinity, a molecular docking screening model of the sample to be tested is constructed.
[0150] Among them, the optimized protein structure model refers to the three-dimensional structure model of the protein after optimization processing, the drug molecular structure model refers to the molecular structure model of the chemical substance used to treat the disease, the docking software refers to a computer program used to simulate the interaction between the drug molecule and the protein target, such as AutoDock, DockBlaster, Gold, etc., the docking parameters refer to the parameters set in the docking software, including search space, scoring function, docking algorithm, etc., which are used to control the docking process and results, the docking conformation refers to the different three-dimensional forms that may appear when the drug molecule binds to the protein target, the binding ability refers to the strength and efficiency of the binding of the drug molecule to the protein target, the affinity refers to the strength and specificity of the binding of the drug molecule to the protein target, and the molecular docking screening model refers to a screening model constructed based on the docking results and experimental data, which is used to predict the binding potential and activity of new compounds.
[0151] Furthermore, the analysis of the binding ability and affinity of the drug molecular structure model and the protein structure model based on the docking conformation can be achieved through MM-PBSA and MM-GBSA tools.
[0152] S4. Based on the metabolic pathway data, analyzing the drug metabolism mechanism and drug metabolism regulatory network of the organism, and constructing a metabolic pathway screening model for the sample to be tested based on the drug metabolism mechanism and drug metabolism regulatory network.
[0153] The present invention can analyze the metabolic process of the drug in the organism by analyzing the drug metabolism mechanism and drug metabolism regulatory network of the organism based on the metabolic pathway data.
[0154] In detail, the analyzing the drug metabolism mechanism and drug metabolism regulatory network of the organism based on the metabolic pathway data includes:
[0155] analyzing a drug metabolism profile of the organism based on the metabolic pathway data;
[0156] identifying drug metabolism pathways in the drug metabolism profile;
[0157] Identify the key metabolic steps and metabolites in the drug metabolism pathway;
[0158] Determining the drug metabolism mechanism of the organism based on the key metabolic steps and metabolites;
[0159] identifying regulatory genes for said key metabolic steps;
[0160] The drug metabolism regulatory network of the organism is constructed through the drug metabolism pathway and regulatory genes.
[0161] Among them, the drug metabolism map refers to a map that describes how drugs are metabolized and transformed in organisms, the drug metabolism pathway refers to the specific path by which drugs are metabolized and transformed in organisms, the key metabolic steps refer to those steps in the drug metabolism pathway that play a decisive role in drug metabolism, and these steps usually involve chemical transformation of drugs, such as oxidation, reduction, hydrolysis, etc., the metabolites refer to the intermediates and final products produced during the metabolism of drugs, the drug metabolism mechanism refers to the biological process by which drugs are metabolized and transformed in organisms, including key enzymes, metabolic steps and metabolites in the metabolic pathway, the regulatory genes refer to genes involved in the regulatory process of drug metabolism pathways, and the drug metabolism regulatory network refers to a network composed of drug metabolism pathways and regulatory genes.
[0162] Furthermore, the key metabolic steps and metabolites of the drug metabolic pathway can be analyzed by biological tools such as Pathway Studio and Ingenuity Pathway Analysis.
[0163] The present invention is based on the drug metabolism mechanism and drug metabolism regulatory network, and constructs the metabolic pathway screening model of the sample to be tested, which can better understand the metabolic process of the drug in the organism and predict the metabolic behavior of the drug. The metabolic pathway screening model refers to a model that analyzes the metabolic pathway and regulatory process of the drug in the organism to predict and screen drug samples. In detail, the metabolic pathway screening model can train the metabolic data features using machine learning algorithms (such as support vector machines, random forests, neural networks, etc.) through the metabolic data of key metabolic steps and their regulatory genes to construct a screening model.
[0164] S5. Utilize the drug response data to construct a multi-target screening model for the sample to be tested, perform combined simulation on the gene expression screening model, molecular docking screening model, metabolic pathway screening model and multi-target screening model to obtain a target model combination for the sample to be tested, construct a high-throughput drug screening platform for the sample to be tested, and construct a high-throughput drug screening model for the sample to be tested based on the high-throughput drug screening platform and the target model combination.
[0165] The present invention utilizes the drug reaction data to construct a multi-target screening model for the sample to be tested, thereby constructing a drug screening model based on multiple targets to improve the accuracy of drug screening.
[0166] In detail, the use of the drug response data to construct a multi-target screening model for the sample to be tested includes:
[0167] Based on the drug response data, analyzing the drug action targets of the organism corresponding to the drug response data;
[0168] Determining the target action mechanism of the drug target through the drug response data;
[0169] Analyzing the drug target binding mode and signal transduction pathway of the drug target according to the target action mechanism;
[0170] analyzing adverse reactions of the organism based on the drug response data;
[0171] Based on the drug action targets, drug target binding modes, signal transduction pathways and adverse reactions, a multi-target screening model for the sample to be tested is constructed.
[0172] Among them, the drug target refers to the key molecule that the drug compound acts on in vivo, usually a protein, receptor, enzyme or other biomacromolecule, the target action mechanism refers to how the drug compound affects the physiological process or disease state of the organism after binding to the target, the drug target binding mode refers to the way the drug compound binds to the target, including the interaction force between the compound and the target (such as hydrogen bond, hydrophobic interaction, van der Waals force, etc.) and the binding conformation, the signal transduction pathway refers to the specific biological process of transmitting signals to cells through a series of molecular events (such as phosphorylation, transcriptional regulation, etc.) after the drug binds to the target, the adverse reaction refers to the adverse physiological reaction that may be caused by the action of the compound and the reaction of the target, including side effects, toxic reactions, etc., and the multi-target screening model refers to a drug screening model based on multiple drug action targets. This model can predict the effect of new compounds on different targets.
[0173] The present invention combines and simulates the gene expression screening model, the molecular docking screening model, the metabolic pathway screening model and the multi-target screening model to obtain the target model combination of the sample to be tested, which can improve the accuracy and reliability of drug screening.
[0174] In detail, the gene expression screening model, the molecular docking screening model, the metabolic pathway screening model and the multi-target screening model are combined and simulated to obtain the target model combination of the sample to be tested, including:
[0175] Constructing gene expression test data, molecular docking test data, metabolic pathway test data and multi-target test data of the gene expression screening model, molecular docking screening model, metabolic pathway screening model and multi-target screening model respectively;
[0176] Through the gene expression test data, molecular docking test data, metabolic pathway test data and multi-target test data, the gene expression screening model, molecular docking screening model, metabolic pathway screening model and multi-target screening model are optimized to obtain a target gene expression screening model, a target molecule docking screening model, a target metabolic pathway screening model and a target multi-target screening model;
[0177] Determine the model combination strategy of the target gene expression screening model, the target molecule docking screening model, the target metabolic pathway screening model and the target multi-target screening model;
[0178] Through the model combination strategy, a multi-combination model of the target gene expression screening model, the target molecule docking screening model, the target metabolic pathway screening model and the target multi-target screening model is constructed;
[0179] Using preset multi-model combination test data, simulating the multi-combination model to obtain simulation results;
[0180] Based on the simulation results, constructing the ROC curve of the multi-combination model;
[0181] The AUC value of the ROC curve was calculated using the following formula:
[0182]
[0183] in, Represents the AUC value of the ROC curve, Indicated in The true positive rate of the curve points is Indicates The false positive rate of the curve points is Indicates the number of curve points corresponding to the ROC curve;
[0184] Based on the AUC value of the ROC curve, the target model combination of the sample to be tested is determined.
[0185] Among them, the gene expression test data refers to a real data set used to evaluate the performance of a gene expression screening model, the molecular docking test data refers to a real data set used to evaluate the performance of a molecular docking screening model, the metabolic pathway test data refers to a real data set used to evaluate the performance of a metabolic pathway screening model, the multi-target test data refers to a real data set used to evaluate the performance of a target multi-target screening model, the model combination strategy defines how to divide multiple drug screening models into different combinations, the simulation results refer to the analysis results of compound data by different combination models, the ROC curve refers to the true positive rate (TPR) and the false positive rate (FPR) plotted in the same coordinate system, the AUC value refers to the area under the ROC curve, the curve point refers to each point on the ROC curve, the true positive rate refers to the proportion of positive examples correctly predicted by the model (actually positive examples) at a specific curve point, the false positive rate refers to the proportion of negative examples incorrectly predicted by the model as positive examples at a specific curve point, and the target model combination refers to the optimal model combination selected based on the performance evaluation of the model and actual application requirements.
[0186] Furthermore, the target model combination for the sample to be tested can be determined based on the AUC value of the ROC curve by selecting the model combination with the maximum AUC value as the target model combination. In detail, the AUC value ranges from 0 to 1, and the closer to 1, the stronger the performance of the model combination.
[0187] It should be explained that the high-throughput drug screening platform refers to a platform for testing biological information of samples to be tested. In detail, the high-throughput drug screening platform can be constructed by using a microplate as a reaction carrier, combined with an automated operating system and sensitive detection instruments (such as a fluorescence detector, a spectrophotometer, etc.).
[0188] Finally, the present invention is based on the high-throughput drug screening platform and the target model combination, and constructs the high-throughput drug screening model of the sample to be tested. The high-throughput drug screening platform can collect the biological information of the sample to be tested in large quantities and efficiently, and use the target model combination to perform potential drug efficacy analysis of the sample, thereby achieving high-efficiency and high-precision drug efficacy identification of the sample to be tested. The high-throughput drug screening model refers to a drug screening model that can quickly and accurately analyze a large number of samples to be tested.
[0189] The present invention constructs a gene network diagram of the organism based on the cleaned gene sequence data, which can construct a gene network diagram that reflects the gene interactions and regulatory relationships in the organism, which helps to deeply understand the gene expression regulation mechanism of the organism; the present invention constructs a gene expression screening model of the sample to be tested based on the gene network diagram as the basis for the subsequent target drug screening model; further, the present invention constructs a protein structure model of the organism based on the protein structure data as the basis for constructing a subsequent screening model. In detail, the geometric quality and overall quality of the protein structure model identified by the present invention can determine the reliability and applicability of the model, thereby improving the reliability of the later model construction. Further, based on the geometric quality and overall quality of the protein structure model, the present invention constructs the molecular docking screening model of the sample to be tested as the basis for the later target drug screening model construction. Further, based on the drug metabolism mechanism and drug metabolism regulatory network, the present invention constructs the metabolic pathway screening model of the sample to be tested, which can better understand the metabolic process of the drug in the organism and predict the metabolic behavior of the drug. Finally, based on the high-throughput drug screening platform and the target model combination, the high-throughput drug screening model of the sample to be tested can be constructed. The high-throughput drug screening platform can collect the biological information of the sample to be tested in large quantities and efficiently, and the target model combination is used to perform the potential drug efficacy analysis of the sample, thereby realizing the high-efficiency and high-precision drug efficacy identification of the sample to be tested. Therefore, the present invention can improve the efficiency and accuracy of drug screening.
[0190] like Figure 2 , which is a functional module diagram of a high-throughput drug screening model construction device based on biological information provided by one embodiment of the present invention.
[0191] The high-throughput drug screening model construction device 100 based on biological information of the present invention can be installed in an electronic device. According to the functions to be implemented, the high-throughput drug screening model construction device 100 based on biological information can include a biological information data acquisition module 101, a gene expression screening model construction module 102, a molecular docking screening model construction module 103, a metabolic pathway screening model construction module 104 and a high-throughput drug screening model construction module 105. The module of the present invention can also be called a unit, which refers to a series of computer program segments that can be executed by an electronic device processor and can complete fixed functions, which are stored in the memory of the electronic device.
[0192] The biological information data acquisition module 101 is used to collect biological information data of an organism, wherein the biological information data includes gene sequence data, protein structure data, metabolic pathway data and drug reaction data;
[0193] The gene expression screening model construction module 102 is used to clean the gene sequence data to obtain cleaned gene sequence data, construct a gene network diagram of the organism based on the cleaned gene sequence data, and construct a gene expression screening model for the sample to be tested based on the gene network diagram;
[0194] The molecular docking screening model construction module 103 is used to construct a protein structure model of the organism based on the protein structure data, identify the geometric quality and overall quality of the protein structure model, and construct a molecular docking screening model of the sample to be tested based on the geometric quality and overall quality of the protein structure model;
[0195] The metabolic pathway screening model construction module 104 is used to analyze the drug metabolism mechanism and drug metabolism regulatory network of the organism based on the metabolic pathway data, and to construct a metabolic pathway screening model for the sample to be tested based on the drug metabolism mechanism and drug metabolism regulatory network;
[0196] The high-throughput drug screening model construction module 105 is used to use the drug response data to construct a multi-target screening model for the sample to be tested, perform combined simulation on the gene expression screening model, the molecular docking screening model, the metabolic pathway screening model and the multi-target screening model to obtain a target model combination for the sample to be tested, and construct a high-throughput drug screening platform for the sample to be tested. Based on the high-throughput drug screening platform and the target model combination, a high-throughput drug screening model for the sample to be tested is constructed.
[0197] In detail, each module in the high-throughput drug screening model construction device 100 based on biological information in the embodiment of the present invention is used in the same manner as described above. Figure 1 The same technical means as the method for constructing a high-throughput drug screening model based on bioinformatics described in the text and can produce the same technical effects are used and will not be repeated here.
[0198] like Figure 3 , which is a schematic diagram of the structure of an electronic device for implementing a method for constructing a high-throughput drug screening model based on biological information provided by an embodiment of the present invention.
[0199] The electronic device 1 may include a processor 10, a memory 11 and a bus 12, and may also include a computer program stored in the memory 11 and executable on the processor 10, such as a high-throughput drug screening model construction method program based on biological information.
[0200] Wherein, the memory 11 includes at least one type of readable storage medium, and the readable storage medium includes flash memory, mobile hard disk, multimedia card, card-type memory (for example: SD or DX memory, etc.), magnetic memory, disk, optical disk, etc. In some embodiments, the memory 11 can be an internal storage unit of the electronic device 1, such as a mobile hard disk of the electronic device 1. In other embodiments, the memory 11 can also be an external storage device of the electronic device 1, such as a plug-in mobile hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (SecureDigital, SD) card, a flash card (Flash Card), etc. equipped on the electronic device 1. Further, the memory 11 also includes an internal storage unit of the electronic device 1 and an external storage device. The memory 11 can not only be used to store application software and various types of data installed in the electronic device 1, such as the code of the high-throughput drug screening model construction method program based on biological information, but also can be used to temporarily store data that has been output or is to be output.
[0201] The processor 10 may be composed of an integrated circuit in some embodiments, for example, a single packaged integrated circuit, or a plurality of packaged integrated circuits with the same or different functions, including one or more central processing units (CPUs), microprocessors, digital processing chips, graphics processors, and combinations of various control chips, etc. The processor 10 is the control core (Control Unit) of the electronic device, and uses various interfaces and lines to connect various components of the entire electronic device, and executes or executes programs or modules stored in the memory 11 (such as a high-throughput drug screening model construction method program based on biological information, etc.), and calls data stored in the memory 11 to execute various functions of the electronic device 1 and process data.
[0202] The bus 12 may be a peripheral component interconnect (PCI) bus or an extended industry standard architecture (EISA) bus, etc. The bus 12 may be divided into an address bus, a data bus, a control bus, etc. The bus 12 is configured to realize connection and communication between the memory 11 and at least one processor 10, etc.
[0203] Figure 3 Only an electronic device with components is shown, and those skilled in the art will understand that Figure 3The structure shown does not constitute a limitation on the electronic device 1, and may include fewer or more components than shown in the figure, or combine certain components, or arrange the components differently.
[0204] For example, although not shown, the electronic device 1 may also include a power source (such as a battery) for supplying power to various components. Preferably, the power source may be logically connected to the at least one processor 10 through a power management device, so that the power management device can realize functions such as charging management, discharging management, and power consumption management. The power source may also include one or more DC or AC power sources, recharging devices, power failure detection circuits, power converters or inverters, power status indicators, and other arbitrary components. The electronic device 1 may also include a variety of sensors, Bluetooth modules, Wi-Fi modules, etc., which will not be repeated here.
[0205] Furthermore, the electronic device 1 may also include a network interface. Optionally, the network interface may include a wired interface and / or a wireless interface (such as a WI-FI interface, a Bluetooth interface, etc.), which is generally used to establish a communication connection between the electronic device 1 and other electronic devices.
[0206] Optionally, the electronic device 1 may further include a user interface, which may be a display, an input unit (such as a keyboard), or a standard wired interface or a wireless interface. Optionally, in some embodiments, the display may be an LED display, a liquid crystal display, a touch-sensitive liquid crystal display, and an OLED (Organic Light-Emitting Diode) touch device. The display may also be appropriately referred to as a display screen or a display unit, which is used to display information processed in the electronic device 1 and to display a visual user interface.
[0207] It should be understood that the embodiment is for illustration only and the scope of the patent application is not limited to this structure.
[0208] The program of the method for constructing a high-throughput drug screening model based on biological information stored in the memory 11 of the electronic device 1 is a combination of multiple instructions. When running in the processor 10, the following can be achieved:
[0209] Collecting biological information data of an organism, wherein the biological information data includes gene sequence data, protein structure data, metabolic pathway data, and drug response data;
[0210] Cleaning the gene sequence data to obtain cleaned gene sequence data, constructing a gene network diagram of the organism based on the cleaned gene sequence data, and constructing a gene expression screening model for the sample to be tested based on the gene network diagram;
[0211] Based on the protein structure data, construct a protein structure model of the organism, identify the geometric quality and overall quality of the protein structure model, and construct a molecular docking screening model for the sample to be tested based on the geometric quality and overall quality of the protein structure model;
[0212] Based on the metabolic pathway data, analyzing the drug metabolism mechanism and drug metabolism regulatory network of the organism, and constructing a metabolic pathway screening model for the sample to be tested based on the drug metabolism mechanism and drug metabolism regulatory network;
[0213] Utilizing the drug response data, a multi-target screening model for the sample to be tested is constructed, and the gene expression screening model, the molecular docking screening model, the metabolic pathway screening model and the multi-target screening model are combined and simulated to obtain a target model combination for the sample to be tested, and a high-throughput drug screening platform for the sample to be tested is constructed. Based on the high-throughput drug screening platform and the target model combination, a high-throughput drug screening model for the sample to be tested is constructed.
[0214] Specifically, the specific implementation method of the processor 10 for the above instructions can refer to Figures 1 to 3 The description of the relevant steps in the corresponding embodiments will not be repeated here.
[0215] Furthermore, if the module / unit integrated in the electronic device 1 is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. The computer-readable storage medium can be volatile or non-volatile. For example, the computer-readable medium can include: any entity or device capable of carrying the computer program code, a recording medium, a USB flash drive, a mobile hard disk, a magnetic disk, an optical disk, a computer memory, and a read-only memory (ROM).
[0216] The present invention further provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor of an electronic device, the computer program can implement:
[0217] Collecting biological information data of an organism, wherein the biological information data includes gene sequence data, protein structure data, metabolic pathway data, and drug response data;
[0218] Cleaning the gene sequence data to obtain cleaned gene sequence data, constructing a gene network diagram of the organism based on the cleaned gene sequence data, and constructing a gene expression screening model for the sample to be tested based on the gene network diagram;
[0219] Based on the protein structure data, construct a protein structure model of the organism, identify the geometric quality and overall quality of the protein structure model, and construct a molecular docking screening model for the sample to be tested based on the geometric quality and overall quality of the protein structure model;
[0220] Based on the metabolic pathway data, analyzing the drug metabolism mechanism and drug metabolism regulatory network of the organism, and constructing a metabolic pathway screening model for the sample to be tested based on the drug metabolism mechanism and drug metabolism regulatory network;
[0221] Utilizing the drug response data, a multi-target screening model for the sample to be tested is constructed, and the gene expression screening model, the molecular docking screening model, the metabolic pathway screening model and the multi-target screening model are combined and simulated to obtain a target model combination for the sample to be tested, and a high-throughput drug screening platform for the sample to be tested is constructed. Based on the high-throughput drug screening platform and the target model combination, a high-throughput drug screening model for the sample to be tested is constructed.
[0222] In the several embodiments provided by the present invention, it should be understood that the disclosed devices, systems and methods can be implemented in other ways. For example, the system embodiments described above are only illustrative, and actual implementation may have other division methods.
[0223] The modules described as separate components may or may not be physically separated, and the components shown as modules may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment.
[0224] In addition, each functional module in each embodiment of the present invention may be integrated into one processing unit, each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of hardware plus software functional modules.
[0225] It is obvious to those skilled in the art that the present invention is not limited to the details of the above exemplary embodiments, and that the present invention can be implemented in other specific forms without departing from the spirit or essential characteristics of the present invention.
[0226] In addition, it is clear that the word "comprising" does not exclude other units or steps, and the singular does not exclude the plural. Multiple units or devices stated in the system claim can also be implemented by one unit or device through software or hardware. The second and other words are used to indicate names, but not to indicate any particular order.
[0227] Finally, it should be noted that the above embodiments are only used to illustrate the technical solution of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solution of the present invention can be modified or replaced by equivalents without departing from the spirit and scope of the technical solution of the present invention.
Claims
1. A method for constructing a high-throughput drug screening model based on bioinformatics, characterized in that: The method comprises: Collecting biological information data of an organism, wherein the biological information data includes gene sequence data, protein structure data, metabolic pathway data, and drug response data; Cleaning the gene sequence data to obtain cleaned gene sequence data, constructing a gene network diagram of the organism based on the cleaned gene sequence data, and constructing a gene expression screening model for the sample to be tested based on the gene network diagram; Based on the protein structure data, construct a protein structure model of the organism, identify the geometric quality and overall quality of the protein structure model, and construct a molecular docking screening model for the sample to be tested based on the geometric quality and overall quality of the protein structure model; Based on the metabolic pathway data, analyzing the drug metabolism mechanism and drug metabolism regulatory network of the organism, and constructing a metabolic pathway screening model for the sample to be tested based on the drug metabolism mechanism and drug metabolism regulatory network; Utilizing the drug response data, a multi-target screening model for the sample to be tested is constructed, and the gene expression screening model, the molecular docking screening model, the metabolic pathway screening model and the multi-target screening model are combined and simulated to obtain a target model combination for the sample to be tested, and a high-throughput drug screening platform for the sample to be tested is constructed. Based on the high-throughput drug screening platform and the target model combination, a high-throughput drug screening model for the sample to be tested is constructed.
2. The method for constructing a high-throughput drug screening model based on biological information according to claim 1, characterized in that: The step of constructing a gene network diagram of the organism based on the cleaned gene sequence data comprises: Using a preset BLAST tool to perform sequence comparison on the cleaned gene sequence data to obtain similar sequences and potential homologous genes of the cleaned gene sequence data; Performing functional annotation on the potential homologous genes to obtain homologous gene annotation information; Defining network nodes of the organism, and constructing an initial gene network diagram of the organism through the network nodes, similar sequences, potential homologous genes and homologous gene annotation information; Identifying redundant connections and isolated nodes of the initial gene network graph; Based on the redundant connections and isolated nodes, the initial gene network graph is optimized to obtain the gene network graph of the organism.
3. The method for constructing a high-throughput drug screening model based on biological information according to claim 2, characterized in that: The step of optimizing the initial gene network diagram based on the redundant connections and isolated nodes to obtain the gene network diagram of the organism comprises: Removing redundant connections and isolated nodes corresponding to the initial gene network graph to obtain an optimized gene network graph; The average degree of the network nodes corresponding to the optimized gene network graph is calculated using the following formula: in, represents the average degree of the network nodes corresponding to the optimized gene network graph, Indicates the number of network nodes corresponding to the optimized gene network graph, Represents the adjacency matrix element of the network node corresponding to the optimized gene network graph. If the network node and network nodes If there is an edge between is 1, otherwise is 0; The focusing coefficient of the corresponding network node of the optimized gene network graph is calculated using the following formula: in, Indicates the corresponding network nodes of the optimized gene network graph The focusing factor, Indicates the corresponding network nodes of the optimized gene network graph The degree, Optimize the corresponding network nodes of the gene network graph The actual number of edges that exist; The network density of the network nodes corresponding to the optimized gene network graph is calculated using the following formula: in, Indicates the network density of the corresponding network nodes in the optimized gene network graph, Indicates the number of network nodes corresponding to the optimized gene network graph, Optimize the number of network connection edges corresponding to the gene network graph; Analyze the network topology stability coefficient of the optimized gene network graph based on the average degree, focusing coefficient and network density of the corresponding network nodes of the optimized gene network graph; When the network topology stability coefficient meets a preset network topology stability threshold, the optimized gene network graph is used as the gene network graph of the organism.
4. The method for constructing a high-throughput drug screening model based on biological information according to claim 3, characterized in that: The method of constructing a gene expression screening model for the sample to be tested based on the gene network diagram comprises: Determine the drug screening target of the samples to be tested; Based on the drug screening target, determining key network nodes in the gene network graph; Based on the gene network diagram, analyzing the interaction relationship of the key network nodes, wherein the interaction relationship includes upstream and downstream regulatory relationships and signal transduction pathways; Collecting gene expression data of the key network nodes and interaction relationships; extracting gene expression features from the gene expression data; A gene expression screening model for the sample to be tested is constructed based on the gene expression characteristics.
5. The method for constructing a high-throughput drug screening model based on biological information according to claim 4, characterized in that: The identifying the geometric quality and overall quality of the protein structure model comprises: Calculating the model consistency and atomic position deviation of the protein structure model; Identifying the residue conformations of the protein structure model and calculating conformational conformation coefficients of the residue conformations; Analyzing the geometric quality of the protein structure model through the model consistency, atomic position deviation and conformational conformation coefficient; Performing a dynamics simulation on the protein structure model to obtain a dynamics simulation result of the protein structure model; The binding free energy of the protein structure model was calculated using the following formula based on the kinetic simulation results: in, It represents the binding free energy of the interaction between the simulated protein and the ligand in the dynamics simulation results. It represents the free energy of the protein-ligand complex that simulates the interaction between protein and ligand in the dynamics simulation results. It represents the protein free energy of the interaction between the simulated protein and the ligand in the dynamics simulation results. It represents the ligand free energy of the interaction between the simulated protein and the ligand in the dynamics simulation results; Based on the binding free energy, the overall quality of the protein structure model is analyzed.
6. The method for constructing a high-throughput drug screening model based on biological information according to claim 5, characterized in that: The step of constructing a molecular docking screening model for the sample to be tested based on the geometric quality and overall quality of the protein structure model comprises: Based on the geometric quality and overall quality of the protein structure model, the protein structure model is optimized to obtain an optimized protein structure model; Constructing a drug molecular structure model of the sample to be tested; Determine the docking software of the drug molecular structure model and the protein structure model; Configuring docking parameters of the docking software; The drug molecule structure model and the protein structure model are docked by using the docking parameters to obtain a docking conformation; Based on the docking conformation, analyzing the binding ability and affinity of the drug molecular structure model and the protein structure model; According to the binding ability and affinity, a molecular docking screening model of the sample to be tested is constructed.
7. The method for constructing a high-throughput drug screening model based on biological information according to claim 6, characterized in that: The step of analyzing the drug metabolism mechanism and drug metabolism regulatory network of the organism based on the metabolic pathway data comprises: analyzing a drug metabolism profile of the organism based on the metabolic pathway data; identifying drug metabolism pathways in the drug metabolism profile; Identify the key metabolic steps and metabolites in the drug metabolism pathway; Determining the drug metabolism mechanism of the organism based on the key metabolic steps and metabolites; identifying regulatory genes for said key metabolic steps; The drug metabolism regulatory network of the organism is constructed through the drug metabolism pathway and regulatory genes.
8. The method for constructing a high-throughput drug screening model based on biological information according to claim 7, characterized in that: The method of using the drug response data to construct a multi-target screening model for the sample to be tested includes: Based on the drug response data, analyzing the drug action targets of the organism corresponding to the drug response data; Determining the target action mechanism of the drug target through the drug response data; Analyzing the drug target binding mode and signal transduction pathway of the drug target according to the target action mechanism; analyzing adverse reactions of the organism based on the drug response data; Based on the drug action targets, drug target binding modes, signal transduction pathways and adverse reactions, a multi-target screening model for the sample to be tested is constructed.
9. The method for constructing a high-throughput drug screening model based on biological information according to claim 8, characterized in that: The combined simulation of the gene expression screening model, the molecular docking screening model, the metabolic pathway screening model and the multi-target screening model to obtain the target model combination of the sample to be tested includes: Constructing gene expression test data, molecular docking test data, metabolic pathway test data and multi-target test data of the gene expression screening model, molecular docking screening model, metabolic pathway screening model and multi-target screening model respectively; Through the gene expression test data, molecular docking test data, metabolic pathway test data and multi-target test data, the gene expression screening model, molecular docking screening model, metabolic pathway screening model and multi-target screening model are optimized to obtain a target gene expression screening model, a target molecule docking screening model, a target metabolic pathway screening model and a target multi-target screening model; Determine the model combination strategy of the target gene expression screening model, the target molecule docking screening model, the target metabolic pathway screening model and the target multi-target screening model; Through the model combination strategy, a multi-combination model of the target gene expression screening model, the target molecule docking screening model, the target metabolic pathway screening model and the target multi-target screening model is constructed; Using preset multi-model combination test data, simulating the multi-combination model to obtain simulation results; Based on the simulation results, constructing the ROC curve of the multi-combination model; The AUC value of the ROC curve was calculated using the following formula: in, Represents the AUC value of the ROC curve, Indicated in The true positive rate of the curve points is Indicates The false positive rate of the curve points is Indicates the number of curve points corresponding to the ROC curve; Based on the AUC value of the ROC curve, the target model combination of the sample to be tested is determined.
10. A high-throughput drug screening model construction device based on biological information, characterized in that: The device comprises: A biological information data acquisition module, used to collect biological information data of an organism, wherein the biological information data includes gene sequence data, protein structure data, metabolic pathway data, and drug response data; A gene expression screening model construction module, used for cleaning the gene sequence data to obtain cleaned gene sequence data, constructing a gene network diagram of the organism based on the cleaned gene sequence data, and constructing a gene expression screening model of the sample to be tested based on the gene network diagram; A molecular docking screening model construction module is used to construct a protein structure model of the organism based on the protein structure data, identify the geometric quality and overall quality of the protein structure model, and construct a molecular docking screening model of the sample to be tested based on the geometric quality and overall quality of the protein structure model; A metabolic pathway screening model construction module is used to analyze the drug metabolism mechanism and drug metabolism regulatory network of the organism based on the metabolic pathway data, and to construct a metabolic pathway screening model for the sample to be tested based on the drug metabolism mechanism and drug metabolism regulatory network; A high-throughput drug screening model construction module is used to use the drug response data to construct a multi-target screening model for the sample to be tested, to perform combined simulation on the gene expression screening model, the molecular docking screening model, the metabolic pathway screening model and the multi-target screening model to obtain a target model combination for the sample to be tested, to construct a high-throughput drug screening platform for the sample to be tested, and to construct a high-throughput drug screening model for the sample to be tested based on the high-throughput drug screening platform and the target model combination.
