Drug sensitivity related LncRNA-transcription factor-target gene regulation triple recognition method, equipment and medium
By obtaining database sample data and random walk algorithms, we can identify the triple of LncRNA-Transcription Factor-Target Gene Regulation of Drug Sensitivity, solve the identification problems in the study of cancer drug resistance mechanisms, realize individualized drug use guidance, and promote accurate Medical.
Patent Information
- Application Number
- CN202411111652.2
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-08-13
- Publication Date
- 2024-11-26
AI Technical Summary
The prior art is difficult to accurately and quickly identify the triple of drug sensitivity-related LncRNA-transcription factor-target gene regulation, resulting in insufficient research on the mechanism of cancer drug resistance and affecting the therapeutic effect.
By obtaining database sample data, including the maximum inhibitory concentration value of half of the drug on cell lines, the expression values of LncRNA and protein-encoded genes, the transcription factor and target gene regulation relationship, combined with the random walk algorithm, a drug-cell line heterogeneity network was constructed. , identify the drug sensitivity-related LncRNA-transcription factor-target gene regulation triplets, and determine the drug dispensing plan.
The rapid and accurate identification of the LncRNA-transcription factor-target gene regulation triple associated with drug sensitivity was achieved, revealing the regulatory role of LncRNA in the drug resistance mechanism, providing individualized drug use guidance, and promoting precise medical treatment.
Smart Images

Figure CN119028428A_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the field of data processing, and in particular to a method, device and medium for identifying a drug sensitivity-related LncRNA-transcription factor-target gene regulatory triplet. Background Art
[0002] LncRNA is a new type of non-coding RNA with a length of more than 200nt and no protein coding ability. However, LncRNA is abnormally expressed in a variety of human diseases and plays an important role in promoting or maintaining disease progression. With the development of next-generation sequencing technology, a large number of LncRNAs have been discovered, and their functions have gradually been revealed based on the research conducted at different omics levels. Although cancer research has made great progress in recent years, cancer treatment still faces severe challenges. Among them, drug resistance is still the main factor limiting the cure of cancer patients. Studies have shown that LncRNA is involved in the regulation of drug resistance in various cancers. LncRNA can mediate drug resistance by regulating the expression of drug sensitivity-related genes. For example, overexpression of LncRNAH19 is associated with acquired cisplatin resistance, and downregulation of LncRNAHOTAIR expression inhibits the expression of MRP, resulting in increased sensitivity of cells to imatinib. In addition to regulating drug sensitivity-related genes, LncRNA can also affect drug sensitivity by affecting the upstream and downstream regulatory mechanisms of drug sensitivity-related genes. Experiments have confirmed that LncRNA can regulate the expression of transcription factors, and then regulate the expression of transcription factor target genes, so that the body produces drug resistance. However, there is a lack of research on the functional role of LncRNA in drug resistance mechanisms, and the role of a large number of LncRNAs in drug sensitivity remains unknown. Therefore, identifying drug sensitivity-related LncRNA-transcription factor-target gene regulatory triads can reveal the regulatory role and function of LncRNA in drug resistance mechanisms.
[0003] However, how to accurately and quickly identify drug sensitivity-related LncRNA-transcription factor-target gene regulatory triads remains an urgent problem to be solved. Summary of the invention
[0004] The purpose of the present application is to provide a method, device and medium for identifying drug sensitivity-related LncRNA-transcription factor-target gene regulatory triples, which can quickly, conveniently and accurately identify drug sensitivity-related LncRNA-transcription factor-target gene regulatory triples.
[0005] To achieve the above objectives, this application provides the following solutions:
[0006] In a first aspect, the present application provides a method for identifying a drug sensitivity-related LncRNA-transcription factor-target gene regulation triplet, the drug sensitivity-related LncRNA-transcription factor-target gene regulation triplet identification method comprising:
[0007] Obtaining sample data according to a database; the sample data includes: half-maximum inhibitory concentration value of the drug on the cell line, expression value of LncRNA and protein-coding genes in the cell line, regulatory relationship between transcription factors and target genes, expression value of protein-coding genes of cancer samples and clinical information of drug response;
[0008] Based on the expression values of LncRNA and protein-coding genes in the cell line, combined with the regulatory relationship between transcription factors and target genes, the LncRNA-mediated transcription factor-target gene regulatory pairs were determined; and based on the transcription factor-target gene regulatory pairs and the half-maximal inhibitory concentration values of drugs on the cell line, the drug sensitivity-related LncRNA-transcription factor-target gene regulatory triples were constructed;
[0009] A drug-cell line heterogeneity network was constructed based on the drug sensitivity-related LncRNA-transcription factor-target gene regulatory triplet and the half-maximal inhibitory concentration value of the drug on the cell line;
[0010] The random walk algorithm was used to determine the drug prescription according to the drug-cell line heterogeneity network, the half-maximal inhibitory concentration value of the drug on the cell line, and the expression values of LncRNA and protein-coding genes in the cell line.
[0011] Optionally, the acquiring sample data according to the database specifically includes:
[0012] The GDSC database was used to obtain the half-maximal inhibitory concentration values of drugs on cell lines;
[0013] The CCLE database was used to obtain the expression values of LncRNA and protein-coding genes in cell lines;
[0014] The TRANSFAC database was used to obtain the regulatory relationship between transcription factors and target genes;
[0015] The TCGA database was used to obtain the expression values of protein-coding genes and clinical information of drug responses of cancer samples.
[0016] Optionally, the method determines the LncRNA-mediated transcription factor-target gene regulatory pair based on the expression values of LncRNA and protein-coding genes in the cell line, combined with the transcription factor and target gene regulatory relationship; and constructs the drug sensitivity-related LncRNA-transcription factor-target gene regulatory triplet based on the transcription factor-target gene regulatory pair and the half-maximal inhibitory concentration value of the drug on the cell line, specifically including:
[0017] The cell lines were divided into high expression group and low expression group according to the expression value of LncRNA in the cell lines;
[0018] According to the expression values of LncRNA and protein-coding genes in the cell lines in the high-expression group and the low-expression group, the Pearson correlation coefficient was used to determine the expression correlation between the corresponding transcription factors and the target genes;
[0019] Based on the difference in expression correlation between the high expression group and the low expression group, it is determined whether LncRNA can mediate transcription factor-target gene regulation;
[0020] LncRNAs that can mediate transcription factor-target gene regulation and the corresponding transcription factor-target gene regulatory relationships are taken as candidate triplets;
[0021] According to the half-maximal inhibitory concentration values of the candidate triples and the drugs on the cell lines, the Spearman correlation coefficient was used to determine the correlation between the half-maximal inhibitory concentration values of the drugs on the cell lines and the expression values of the LncRNA in the candidate triples, as well as the correlation between the half-maximal inhibitory concentration values of the drugs on the cell lines and the expression values of the target genes in the candidate triples;
[0022] The LncRNAs and target genes whose correlations between the half-maximal inhibitory concentration values of the drugs on the cell lines and the expression values of the LncRNAs in the candidate triples and the half-maximal inhibitory concentration values of the drugs on the cell lines and the expression values of the target genes in the candidate triples are less than the set threshold are regarded as the LncRNAs and target genes associated with drug sensitivity;
[0023] The candidate triplets of drug sensitivity-related LncRNA and target genes were taken as drug sensitivity-related LncRNA-transcription factor-target gene regulatory triplets.
[0024] Optionally, the method of constructing a drug-cell line heterogeneity network based on the drug sensitivity-related LncRNA-transcription factor-target gene regulatory triplet and the half-maximal inhibitory concentration value of the drug on the cell line specifically includes:
[0025] Based on the drug sensitivity-related LncRNA-transcription factor-target gene regulatory triples, drug-drug similarity network and cell line-cell line similarity network were constructed respectively;
[0026] Construct a drug-cell line network based on the half-maximal inhibitory concentration values of drugs on cell lines;
[0027] A drug-cell line heterogeneity network was constructed based on the shared information of the drug-drug similarity network, the cell line-cell line similarity network, and the drug-cell line network.
[0028] In a second aspect, the present application provides a drug sensitivity-related LncRNA-transcription factor-target gene regulation triple identification device, the drug sensitivity-related LncRNA-transcription factor-target gene regulation triple identification device comprising:
[0029] A data acquisition module is used to acquire sample data according to a database; the sample data includes: half-maximum inhibitory concentration value of the drug on the cell line, expression value of LncRNA and protein-coding genes in the cell line, regulatory relationship between transcription factors and target genes, expression value of protein-coding genes of cancer samples and clinical information of drug response;
[0030] The triplet determination module is used to determine the transcription factor-target gene regulatory pair mediated by LncRNA based on the expression values of LncRNA and protein-coding genes in the cell line, combined with the regulatory relationship between transcription factors and target genes; and to construct the drug sensitivity-related LncRNA-transcription factor-target gene regulatory triplet based on the transcription factor-target gene regulatory pair and the half-maximal inhibitory concentration value of the drug on the cell line;
[0031] The drug-cell line heterogeneity network construction module is used to construct the drug-cell line heterogeneity network based on the drug sensitivity-related LncRNA-transcription factor-target gene regulatory triples and the half-maximal inhibitory concentration values of drugs on cell lines;
[0032] The medication scheme determination module is used to determine the medication scheme based on the drug-cell line heterogeneity network, the half-maximum inhibitory concentration value of the drug on the cell line, and the expression value of LncRNA and protein-coding genes in the cell line using a random walk algorithm.
[0033] In a third aspect, the present application provides a computer device, comprising: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the method for identifying drug sensitivity-related LncRNA-transcription factor-target gene regulatory triples.
[0034] Optionally, the computer device further comprises:
[0035] Use the Eclipse platform as the front-end code writing and implementation tool;
[0036] Use Boostrap as the front-end framework;
[0037] Use MySQL database platform as the backend storage database;
[0038] Use Rserve as the backend data analysis tool;
[0039] Use JSP technology, Struts2 framework, Java connection pool Proxool technology and R language to build the Web engine;
[0040] Use Apache Tomcat Web server.
[0041] In a fourth aspect, the present application provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the method for identifying drug sensitivity-related LncRNA-transcription factor-target gene regulatory triples.
[0042] According to the specific embodiments provided in this application, this application discloses the following technical effects:
[0043] The present application provides a method, device and medium for identifying drug sensitivity-related LncRNA-transcription factor-target gene regulatory triples, which integrates high-throughput expression profile data of LncRNA and mRNA, drug sensitivity data and transcription factor-target gene regulatory relationship to determine drug sensitivity-related LncRNA-transcription factor-target gene regulatory triples, revealing the regulatory role and function of LncRNA in drug resistance mechanism; then, a drug-cell line heterogeneity network is constructed based on the drug sensitivity-related LncRNA-transcription factor-target gene regulatory triples, and the drug-cell line heterogeneity network is used to accurately determine the drug dispensing scheme to achieve individualized drug screening; the present application determines personalized medication guidance based on drug sensitivity-related LncRNA-transcription factor-target gene regulatory triple query, further realizing the regulatory role of LncRNA in tumor resistance mechanism and achieving precision medicine, which has important practical significance. BRIEF DESCRIPTION OF THE DRAWINGS
[0044] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.
[0045] Figure 1 A schematic diagram of a process for identifying a drug sensitivity-related LncRNA-transcription factor-target gene regulatory triple provided in an embodiment of the present application;
[0046] Figure 2 A schematic diagram of the principle of a method for identifying a drug sensitivity-related LncRNA-transcription factor-target gene regulatory triple provided in one embodiment of the present application. DETAILED DESCRIPTION
[0047] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.
[0048] In order to make the above-mentioned objects, features and advantages of the present application more obvious and easy to understand, the present application is further described in detail below with reference to the accompanying drawings and specific implementation methods.
[0049] In an exemplary embodiment, Figure 1 and Figure 2 As shown, a method for identifying a drug sensitivity-related LncRNA-transcription factor-target gene regulatory triple is provided, and the method includes the following S101 to S104. Among them:
[0050] S101, obtaining sample data according to a database; the sample data includes: half-maximum inhibitory concentration value of the drug on the cell line, expression value of LncRNA and protein-coding gene in the cell line, regulatory relationship between transcription factors and target genes, expression value of protein-coding gene of cancer samples and clinical information of drug response;
[0051] S101 specifically includes:
[0052] S1, the half-maximal inhibitory concentration (IC50) value of the drug on the cell line was obtained using the GDSC database;
[0053] S2, the CCLE database was used to obtain the expression values of LncRNA and protein-coding genes in cell lines;
[0054] S3, using the TRANSFAC database to obtain the regulatory relationship between transcription factors and target genes;
[0055] S4, the TCGA database was used to obtain the expression values of protein-coding genes and clinical information of drug responses of cancer samples.
[0056] Meanwhile, samples with complete remission and partial remission of drug treatment were defined as samples that responded to treatment, and samples with clinical progressive disease and stable disease were defined as samples that did not respond to treatment;
[0057] Different data are obtained through different databases to ensure the accuracy of the drug treatment response data of the samples used.
[0058] S102, according to the expression values of lncRNA and protein-coding genes in the cell line, combined with the regulatory relationship between transcription factors and target genes, determine the lncRNA-mediated transcription factor-target gene regulatory pairs; and construct drug sensitivity-related lncRNA-transcription factor-target gene regulatory triples according to the transcription factor-target gene regulatory pairs and the half-maximal inhibitory concentration values of drugs on the cell line;
[0059] S102 specifically includes:
[0060] S201, the cell lines were divided into high expression group and low expression group according to the expression value of LncRNA in the cell lines;
[0061] S202, according to the expression values of LncRNA and protein-coding genes in the high expression group and the low expression group in the cell line, the Pearson correlation coefficient is used to determine the expression correlation between the corresponding transcription factor and the target gene;
[0062] S202 specifically includes:
[0063]
[0064] Where n is the number of cell lines, X i is the expression value of transcription factor X in cell line i, X u is the mean expression value of transcription factor X in the cell line, Y i is the expression value of gene Y in cell line i, Y u is the mean expression value of gene Y in the cell line.
[0065] Formula (1) was used to determine the expression correlation r1 of the high expression group and the expression correlation r2 of the low expression group;
[0066] S203, judging whether LncRNA can mediate transcription factor-target gene regulation based on the difference in expression correlation between the high expression group and the low expression group;
[0067] The difference Δr between the expression correlation of the high expression group and the expression correlation of the low expression group was determined using Δr=|r1-r2|;
[0068] If Δr>0.7, it is determined that LncRNA can mediate the regulation of transcription factors and target genes;
[0069] S204, taking LncRNAs that can mediate transcription factor-target gene regulation and the corresponding transcription factor and target gene regulatory relationships as candidate triplets;
[0070] S205, according to the half-maximal inhibitory concentration values of the candidate triples and the drugs for the cell line, using the Spearman correlation coefficient, determine the correlation between the half-maximal inhibitory concentration values of the drugs for the cell line and the expression values of the lncRNA in the candidate triples, and the correlation between the half-maximal inhibitory concentration values of the drugs for the cell line and the expression values of the target genes in the candidate triples;
[0071] S205 specifically includes:
[0072]
[0073] Where n is the number of cell lines, d i =rank(X i )-rank(Y i ), X i represents the rank of the expression value of LncRNA or protein-coding gene X in cell line i, Y i Represents the ranking of the IC50 value of drug Y in cell i.
[0074] Formula (2) was used to determine the correlation between the half-maximum inhibitory concentration value of the drug on the cell line and the LncRNA expression value in the candidate triplet, and the correlation between the half-maximum inhibitory concentration value of the drug on the cell line and the expression value of the target gene in the candidate triplet;
[0075] That is, when the correlation between the most upstream LncRNA and the most downstream target gene and the IC50 value is less than 0.05, the triplet is a triplet associated with drug sensitivity.
[0076] S206, the LncRNA and target gene whose correlation between the half-maximal inhibitory concentration value of the drug for the cell line and the expression value of the LncRNA in the candidate triplet and the correlation between the half-maximal inhibitory concentration value of the drug for the cell line and the expression value of the target gene in the candidate triplet are both less than the set threshold are regarded as the LncRNA and target gene associated with drug sensitivity; the threshold is set to 0.05.
[0077] S207, taking the candidate triples corresponding to the drug sensitivity-related LncRNA and the target gene as the drug sensitivity-related LncRNA-transcription factor-target gene regulatory triplet.
[0078] S103, constructing a drug-cell line heterogeneity network based on drug sensitivity-related LncRNA-transcription factor-target gene regulatory triples and the half-maximal inhibitory concentration values of drugs on cell lines;
[0079] S103 specifically includes:
[0080] S301, constructing drug-drug similarity network and cell line-cell line similarity network according to drug sensitivity-related LncRNA-transcription factor-target gene regulatory triples;
[0081] The edge between two drugs in the drug-drug similarity network indicates that there is a shared drug sensitivity-related LncRNA-transcription factor-target gene regulatory triple between the edges;
[0082] The average expression value of LncRNA, transcription factor and target gene of each drug sensitivity-related LncRNA-transcription factor-target gene regulatory triplet in the cell line was taken as the activity value of the triplet in the cell line;
[0083] The edges between cell lines in the cell line-cell line similarity network indicate that the activity values of the drug sensitivity-related LncRNA-transcription factor-target gene regulatory triples of the two cell lines are significantly correlated (P<0.05 and Pearson correlation coefficient r>0.8).
[0084] S302, constructing a drug-cell line network according to the half-maximal inhibitory concentration value of the drug on the cell line;
[0085] The cell lines were ranked from low to high according to the IC50 values of each drug in the cell lines. The top 12.5% of the cell lines were used as the cell lines associated with drug sensitivity, and the drug-cell line sensitivity association was performed using the cell lines associated with drug sensitivity.
[0086] S303, constructing a drug-cell line heterogeneity network based on the shared information of the drug-drug similarity network, the cell line-cell line similarity network and the drug-cell line network.
[0087] At the same time, S103 constructed the above network based on the assumption that individuals with similar molecular characteristics have more similar targeted therapeutic drugs.
[0088] S104, according to the drug-cell line heterogeneity network, the half-maximal inhibitory concentration value of the drug on the cell line, and the expression value of LncRNA and protein-coding genes in the cell line, a random walk algorithm is used to determine the drug dispensing plan.
[0089] S104 includes:
[0090] The common cell lines in the GDSC database and the CCLE database were extracted, and the half-maximum inhibitory concentration values of the drugs corresponding to the common cell lines and the expression values of LncRNA and protein-coding genes in the cell lines were standardized to obtain the high-throughput expression profiles of LncRNA and protein-coding genes; the standardization process included: ID conversion and removal of missing values;
[0091] Based on the high-throughput expression profiles of lncRNA and protein-coding genes and the drug-cell line heterogeneity network, a random walk algorithm was used to determine the drug dispensing plan.
[0092] The random walk algorithm is a global optimal method that has been developed and used to analyze various disease mechanisms and has advantages in identifying risk or prognostic genes based on global networks. The random walk algorithm captures global relationships in interaction networks and is superior to local distance metrics in interaction networks.
[0093] Use the random walk algorithm for individual drug screening and drug response prediction. Based on the drug cell line heterogeneity network, personalized drug selection is achieved through the following steps:
[0094] (1) For a disease sample, the activity value of the drug sensitivity-related LncRNA-transcription factor-target gene regulatory triplet in the disease sample is calculated.
[0095] (2) The Pearson correlation coefficient was used to calculate the correlation between samples and cell lines based on the activity values of the drug sensitivity-related LncRNA-transcription factor-target gene regulatory triad. Cell lines and samples with p-values < 0.05 and correlation coefficients greater than 0.8 were screened and added to the drug-cell line heterogeneity network.
[0096] (3) The samples are used as seed nodes and the random walk algorithm (Formula 3) is used to score the nodes in the drug-cell line heterogeneity network.
[0097] P t+1 =(1-r)WP t +rP 0 (Formula 3)
[0098] Where W is the adjacency matrix of the global network, which consists of 0 and 1. t is a vector containing the probability that a node in the global network finds itself in the process up to step t. Construct the initial probability vector P 0 , the seed node is 1 and the remaining nodes are 0.
[0099] In addition, the probability of restarting the walker at each step is r (r = 0.7). t With P t+1 The difference is less than 10 -6 When , the probability reaches a steady state.
[0100] Finally, each node in the global network is scored according to the value in the steady-state probability vector. The scores of all drugs in the drug-cell line heterogeneity network are extracted. The higher the score, the more similar the sample is to the drug-adapted sample. The more likely the drug is to be a candidate for the treatment of this patient.
[0101] In a specific embodiment, Html, JavaScript and other languages are used, and the Eclipse platform is used as the front-end code writing and implementation tool; Boostrap is used as the front-end framework; the MySQL database platform is used as the back-end storage database; Rserve is used as the back-end data analysis tool; JSP technology, Struts2 framework, Java connection pool Proxool technology and R language are used to build a Web engine; and Apache Tomcat Web server is used. A network platform is developed based on the above technologies. The network platform mainly provides drug sensitivity-related LncRNA-transcription factor-target gene regulation triple association relationship query, data download and individual medication screening, etc.
[0102] On the online platform, the MySQL database was searched by the name of the drug, the name of the LncRNA and the ensembl ID; the results on the online platform were: the name of the drug, the drug sensitivity-related LncRNA-transcription factor-target gene regulatory triplet, the name of the LncRNA, the ensembl ID of the LncRNA, the name of the transcription factor, the ensembl ID of the transcription factor, the name of the target gene, the ensembl ID of the target gene, and the drug sensitivity score.
[0103] Based on the same inventive concept, the embodiment of the present application also provides a drug sensitivity-related LncRNA-transcription factor-target gene regulation triple identification device for implementing the above-mentioned drug sensitivity-related LncRNA-transcription factor-target gene regulation triple identification method. The implementation scheme for solving the problem provided by the device is similar to the implementation scheme recorded in the above-mentioned method, so the specific limitations in the one or more drug sensitivity-related LncRNA-transcription factor-target gene regulation triple identification device embodiments provided below can refer to the limitations of the drug sensitivity-related LncRNA-transcription factor-target gene regulation triple identification method in the above text, and will not be repeated here.
[0104] In an exemplary embodiment, a device for identifying a drug sensitivity-related LncRNA-transcription factor-target gene regulation triplet is provided, comprising:
[0105] A data acquisition module is used to acquire sample data according to a database; the sample data includes: half-maximum inhibitory concentration value of the drug on the cell line, expression value of LncRNA and protein-coding genes in the cell line, regulatory relationship between transcription factors and target genes, expression value of protein-coding genes of cancer samples and clinical information of drug response;
[0106] The triplet determination module is used to determine the transcription factor-target gene regulatory pair mediated by LncRNA based on the expression values of LncRNA and protein-coding genes in the cell line, combined with the regulatory relationship between transcription factors and target genes; and to construct the drug sensitivity-related LncRNA-transcription factor-target gene regulatory triplet based on the transcription factor-target gene regulatory pair and the half-maximal inhibitory concentration value of the drug on the cell line;
[0107] The drug-cell line heterogeneity network construction module is used to construct the drug-cell line heterogeneity network based on the drug sensitivity-related LncRNA-transcription factor-target gene regulatory triples and the half-maximal inhibitory concentration values of drugs on cell lines;
[0108] The medication scheme determination module is used to determine the medication scheme based on the drug-cell line heterogeneity network, the half-maximum inhibitory concentration value of the drug on the cell line, and the expression value of LncRNA and protein-coding genes in the cell line using a random walk algorithm.
[0109] In an exemplary embodiment, a computer device is provided, including a memory and a processor, wherein a computer program is stored in the memory, and the processor implements the steps in the above-mentioned method embodiments when executing the computer program.
[0110] In an exemplary embodiment, a computer-readable storage medium is provided, storing a computer program, and when the computer program is executed by a processor, the steps in the above method embodiments are implemented.
[0111] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with relevant regulations.
[0112] Those of ordinary skill in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to the memory, database or other medium used in the embodiments provided in the present application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM may be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM).
[0113] The database involved in each embodiment provided in this application may include at least one of a relational database and a non-relational database. The non-relational database may include a distributed database based on blockchain, etc., but is not limited thereto. The processor involved in each embodiment provided in this application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, etc., but is not limited thereto.
[0114] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.
[0115] This article uses specific examples to illustrate the principles and implementation methods of this application. The description of the above embodiments is only used to help understand the method and core ideas of this application. At the same time, for those skilled in the art, according to the ideas of this application, there will be changes in the specific implementation methods and application scope. In summary, the content of this specification should not be understood as limiting this application.
Claims
1. A method for identifying drug sensitivity-related LncRNA-transcription factor-target gene regulatory triplet, characterized in that: The method for identifying drug sensitivity-related LncRNA-transcription factor-target gene regulation triplet comprises: Obtaining sample data according to a database; the sample data includes: half-maximum inhibitory concentration value of the drug on the cell line, expression value of LncRNA and protein-coding genes in the cell line, regulatory relationship between transcription factors and target genes, expression value of protein-coding genes of cancer samples and clinical information of drug response; Based on the expression values of LncRNA and protein-coding genes in the cell line, combined with the regulatory relationship between transcription factors and target genes, the LncRNA-mediated transcription factor-target gene regulatory pairs were determined; and based on the transcription factor-target gene regulatory pairs and the half-maximal inhibitory concentration values of drugs on the cell line, the drug sensitivity-related LncRNA-transcription factor-target gene regulatory triples were constructed; A drug-cell line heterogeneity network was constructed based on the drug sensitivity-related LncRNA-transcription factor-target gene regulatory triplet and the half-maximal inhibitory concentration value of the drug on the cell line; The random walk algorithm was used to determine the drug prescription according to the drug-cell line heterogeneity network, the half-maximal inhibitory concentration value of the drug on the cell line, and the expression values of LncRNA and protein-coding genes in the cell line.
2. The method for identifying drug sensitivity-related LncRNA-transcription factor-target gene regulation triplet according to claim 1, characterized in that: The obtaining of sample data according to the database specifically includes: The GDSC database was used to obtain the half-maximal inhibitory concentration values of drugs on cell lines; The CCLE database was used to obtain the expression values of LncRNA and protein-coding genes in cell lines; The TRANSFAC database was used to obtain the regulatory relationship between transcription factors and target genes; The TCGA database was used to obtain the expression values of protein-coding genes and clinical information of drug responses of cancer samples.
3. The method for identifying drug sensitivity-related LncRNA-transcription factor-target gene regulation triplet according to claim 1, characterized in that: The method determines the LncRNA-mediated transcription factor-target gene regulatory pair based on the expression values of LncRNA and protein-coding genes in the cell line, combined with the transcription factor and target gene regulatory relationship; and constructs the drug sensitivity-related LncRNA-transcription factor-target gene regulatory triplet based on the transcription factor-target gene regulatory pair and the half-maximal inhibitory concentration value of the drug on the cell line, specifically including: The cell lines were divided into high expression group and low expression group according to the expression value of LncRNA in the cell lines; According to the expression values of LncRNA and protein-coding genes in the cell lines in the high-expression group and the low-expression group, the Pearson correlation coefficient was used to determine the expression correlation between the corresponding transcription factors and the target genes; Based on the difference in expression correlation between the high expression group and the low expression group, it is determined whether LncRNA can mediate transcription factor-target gene regulation; LncRNAs that can mediate transcription factor-target gene regulation and the corresponding transcription factor-target gene regulatory relationships are taken as candidate triplets; According to the half-maximal inhibitory concentration values of the candidate triples and the drugs on the cell lines, the Spearman correlation coefficient was used to determine the correlation between the half-maximal inhibitory concentration values of the drugs on the cell lines and the expression values of the LncRNA in the candidate triples, as well as the correlation between the half-maximal inhibitory concentration values of the drugs on the cell lines and the expression values of the target genes in the candidate triples; The LncRNAs and target genes whose correlations between the half-maximal inhibitory concentration values of the drugs on the cell lines and the expression values of the LncRNAs in the candidate triples and the half-maximal inhibitory concentration values of the drugs on the cell lines and the expression values of the target genes in the candidate triples are less than the set threshold are regarded as the LncRNAs and target genes associated with drug sensitivity; The candidate triplets of drug sensitivity-related LncRNA and target genes were taken as drug sensitivity-related LncRNA-transcription factor-target gene regulatory triplets.
4. The method for identifying drug sensitivity-related LncRNA-transcription factor-target gene regulation triplet according to claim 1, characterized in that: The method of constructing a drug-cell line heterogeneity network based on the drug sensitivity-related LncRNA-transcription factor-target gene regulatory triple and the half-maximal inhibitory concentration value of the drug on the cell line specifically includes: Based on the drug sensitivity-related LncRNA-transcription factor-target gene regulatory triples, drug-drug similarity network and cell line-cell line similarity network were constructed respectively; Construct a drug-cell line network based on the half-maximal inhibitory concentration values of drugs on cell lines; A drug-cell line heterogeneity network was constructed based on the shared information of the drug-drug similarity network, the cell line-cell line similarity network, and the drug-cell line network.
5. A drug sensitivity-related LncRNA-transcription factor-target gene regulation triple identification device, characterized in that: The drug sensitivity-related LncRNA-transcription factor-target gene regulation triple identification device includes: A data acquisition module is used to acquire sample data according to a database; the sample data includes: half-maximum inhibitory concentration value of the drug on the cell line, expression value of LncRNA and protein-coding genes in the cell line, regulatory relationship between transcription factors and target genes, expression value of protein-coding genes of cancer samples and clinical information of drug response; The triplet determination module is used to determine the transcription factor-target gene regulatory pair mediated by LncRNA based on the expression values of LncRNA and protein-coding genes in the cell line, combined with the regulatory relationship between transcription factors and target genes; and to construct the drug sensitivity-related LncRNA-transcription factor-target gene regulatory triplet based on the transcription factor-target gene regulatory pair and the half-maximal inhibitory concentration value of the drug on the cell line; The drug-cell line heterogeneity network construction module is used to construct the drug-cell line heterogeneity network based on the drug sensitivity-related LncRNA-transcription factor-target gene regulatory triples and the half-maximal inhibitory concentration values of drugs on cell lines; The medication scheme determination module is used to determine the medication scheme based on the drug-cell line heterogeneity network, the half-maximum inhibitory concentration value of the drug on the cell line, and the expression value of LncRNA and protein-coding genes in the cell line using a random walk algorithm.
6. A computer device comprising: A memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the method for identifying the drug sensitivity-related LncRNA-transcription factor-target gene regulatory triplet according to any one of claims 1 to 4.
7. The computer device according to claim 6, characterized in that Also includes: Use the Eclipse platform as the front-end code writing and implementation tool; Use Boostrap as the front-end framework; Use MySQL database platform as the backend storage database; Use Rserve as the backend data analysis tool; Use JSP technology, Struts2 framework, Java connection pool Proxool technology and R language to build the Web engine; Use Apache Tomcat Web server.
8. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the method for identifying the drug sensitivity-related LncRNA-transcription factor-target gene regulatory triplet according to any one of claims 1 to 4 is implemented.
