Immunotherapy effect prediction method, system, equipment, medium and product in cancer worsening period

Abstract

The invention discloses a cancer deterioration period immunotherapy effect prediction method, system and device, a medium and a product, and relates to the field of immunotherapy, and the method comprises the steps: obtaining multi-omics data of a patient; determining multi-omics characteristics related to cancer staging based on the multi-omics data; determining key pathways of dynamic changes in cancer progression based on the multiple omics characteristics; constructing a gene interaction network subnet based on the genes of the key pathway, and determining DNEX scores of the genes in the gene interaction network subnet; and based on the DNEX score, adopting a trained machine learning model to predict an immunotherapy effect. According to the application, the accelerated cancer deterioration stage can be identified, the influence of the gene on the tumor immunocompetence in the cancer deterioration process can be predicted, and the prediction of the immunotherapy effect can be realized.

Description

Technical Field

[0001] The present application relates to the field of immunotherapy, and in particular to a method, system, device, medium and product for predicting the effect of immunotherapy during the period of cancer exacerbation. Background Art

[0002] Cancer development usually goes through three clearly defined stages: early, rapid development, and late. In the early stages, the immune system is usually able to recognize and eliminate abnormal or cancerous cells, playing a certain protective role. However, with the rapid development of tumors, tumor cells will evade immune surveillance by reducing the expression of immune recognition molecules, promoting immune tolerance, and creating an immunosuppressive microenvironment, accelerating the growth and spread of tumors. In the late stages of cancer development, the immune system often faces greater challenges, and tumor cells may have established powerful immune escape mechanisms, which limits the effectiveness of immunotherapy. The intricate and dynamic interaction between the immune system and cancer cells is called cancer immunodynamics. Therefore, understanding the relationship between cancer immunodynamics and cancer development stages is crucial to the development of more effective immunotherapy strategies. By in-depth research on the functions and regulatory mechanisms of the immune system in different stages of cancer development, it can provide an important theoretical basis for personalized treatment and improving the efficacy of immunotherapy. Summary of the invention

[0003] The purpose of this application is to provide a method, system, device, medium and product for predicting the effect of immunotherapy during the period of cancer progression, which can identify the stage of accelerated cancer progression and predict the impact of genes on tumor immune activity during cancer progression.

[0004] To achieve the above objectives, this application provides the following solutions:

[0005] In a first aspect, the present application provides a method for predicting the effect of immunotherapy during the period of cancer exacerbation, comprising:

[0006] Obtain multi-omics data of patients;

[0007] determining a multi-omic signature associated with cancer stage based on the multi-omic data;

[0008] Identify key pathways that dynamically change during cancer progression based on the multi-omics signature;

[0009] constructing a gene interaction network subnetwork based on the genes of the key pathway, and determining the DNEX scores of the genes in the gene interaction network subnetwork;

[0010] Based on the DNEX score, a trained machine learning model is used to predict the effect of immunotherapy.

[0011] In a second aspect, the present application provides a system for predicting the effect of immunotherapy during the period of cancer exacerbation, comprising:

[0012] A data acquisition module, used to obtain multi-omics data of patients;

[0013] a feature determination module, configured to determine a multi-omic feature associated with cancer staging based on the multi-omic data;

[0014] A key pathway determination module, used to determine the key pathways that dynamically change during cancer progression based on the multi-omics features;

[0015] A DNEX score determination module, used to construct a gene interaction network subnetwork based on the genes of the key pathway, and determine the DNEX scores of the genes in the gene interaction network subnetwork;

[0016] The immunotherapy effect prediction module is used to predict the immunotherapy effect based on the DNEX score using a trained machine learning model.

[0017] 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 above-mentioned method for predicting the effect of immunotherapy during the cancer exacerbation period.

[0018] 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 above-mentioned method for predicting the effect of immunotherapy during the cancer exacerbation period.

[0019] In a fifth aspect, the present application provides a computer program product, including a computer program, which, when executed by a processor, implements the above-mentioned method for predicting the effect of immunotherapy during the cancer exacerbation period.

[0020] According to the specific embodiments provided in this application, this application has the following technical effects:

[0021] This application provides a method, system, device, medium and product for predicting the effect of immunotherapy during the period of cancer exacerbation. The key pathways that dynamically change during cancer progression are determined by identifying multi-omics features related to cancer staging, thereby identifying the accelerated deterioration stage of cancer. Then, a gene interaction network subnet is constructed based on the genes of the key pathways, and the DNEX scores of the genes in the gene interaction network subnet are determined. The effects of genes on tumor immune activity during cancer exacerbation are predicted based on the DNEX scores, thereby predicting the effect of immunotherapy. This application provides certain guiding significance for monitoring the exacerbation period of cancer and predicting the effect of immunotherapy, and provides more options for individualized treatment strategies. At the same time, it provides relevant candidate data for laboratory verification, which has an important directional guiding role. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] 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.

[0023] Figure 1 A schematic diagram of a flow chart of a method for predicting the effect of immunotherapy during the period of cancer exacerbation provided in one embodiment of the present application;

[0024] Figure 2 A schematic diagram of the principle framework of a method for predicting the effect of immunotherapy during the cancer exacerbation period provided in one embodiment of the present application;

[0025] Figure 3 A schematic diagram of the structure of a computer device provided in one embodiment of the present application. DETAILED DESCRIPTION

[0026] 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.

[0027] The tumor immune microenvironment refers to the complex ecosystem composed of cells, molecules and tissues surrounding the tumor. It includes tumor cells themselves, immune cells, blood vessels, fibroblasts, stromal cells and lysates. The tumor microenvironment is closely related to tumor growth, progression, metastasis and treatment response. In the tumor immune microenvironment, tumor cells interact with surrounding cells and regulate processes such as immune response, angiogenesis, cell proliferation and tissue remodeling, thereby promoting or inhibiting tumor development. The immune system plays a key role in identifying and eliminating abnormal or cancerous cells, including immune surveillance, activation of immune cells and production of immune molecules. The tumor immune microenvironment changes continuously during the progression of cancer, and identifying molecular changes in the deterioration stage of cancer is crucial for cancer treatment. However, the role and function of molecules in cancer progression remain unclear.

[0028] The purpose of this application is to provide a method, system, device, medium and product for predicting the effect of immunotherapy during the period of cancer progression, identifying molecular changes in the cancer progression stage and the impact of genes on tumor immune activity during cancer progression.

[0029] 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 in conjunction with the accompanying drawings and specific implementation methods.

[0030] In an exemplary embodiment, Figure 1-Figure 2 As shown, a method for predicting the effect of immunotherapy during the period of cancer exacerbation is provided. The method is executed by a computer device, and can be executed by a computer device such as a terminal or a server alone, or by a terminal and a server together. In the embodiment of the present application, the method is applied to a server as an example for explanation, and includes the following steps S1 to S5. Among them:

[0031] S1: Obtain multi-omics data of patients.

[0032] Collect multi-omics data of patients, including somatic mutation data, copy number variation data, methylation data, and gene expression RNA-seq data. In this example, maftools was used to process somatic mutation data, and the gene mutation status was binarized, with the mutant type marked as 1 and the wild type marked as 0. Copy number variation data was processed using GISTIC 2.

[0033] S2: Determine the multi-omics features associated with cancer staging based on the multi-omics data. Specifically, the following are used: based on the somatic mutation data, the somatic mutation features associated with cancer staging are determined using the Logistic regression analysis method; based on the copy number variation data, the copy number variation features associated with cancer staging are determined using the linear regression analysis method; based on the methylation data, the methylation features associated with cancer staging are determined using the Spearman correlation analysis method; based on the gene expression RNA-seq data, the differentially expressed gene features associated with cancer staging are determined using the "EdgeR" software package method.

[0034] This embodiment uses multi-omics data to screen features related to the patient's cancer stage. First, Logistic regression analysis is used to screen somatic mutation features that are significantly associated with the patient's cancer stage; second, linear regression analysis is used to identify copy number variation features that are significantly associated with cancer stage; third, Spearman correlation analysis is used to identify methylation features that are significantly associated with cancer stage; finally, for gene expression RNA-seq data, the normLibSizes() function of the "EdgeR" software package is used to standardize the data, and the cancer stage is input into the software package as a continuous variable, and the differentially expressed genes significantly associated with cancer stage are identified based on the negative binomial distribution model. In addition, this embodiment also uses the Benjamini and Hochberg method to perform multiple test corrections on the P values ​​of differentially expressed genes to obtain the corrected significant P values. Finally, multi-omics features significantly associated with cancer stage are obtained in somatic mutation data, copy number variation data, methylation data, and gene expression RNA-seq data.

[0035] S3: Determine the key pathways that change dynamically during cancer progression based on the multi-omics features. Specifically, it includes: performing gene set enrichment analysis on the multi-omics features to identify pathways related to cancer progression; calculating the activation state score of each pathway; and based on the activation state score, using a dynamic network biomarker analysis method to determine the key pathways that change dynamically during cancer progression.

[0036] In this example, the ActivePathways R software package developed by Paczkowska was used to perform gene set enrichment analysis on significantly correlated multi-omics features and identify pathways associated with cancer progression. Subsequently, the gsva() function in the GSVA package was used with the parameter method = "ssgsea" to calculate the enrichment score of each pathway associated with cancer progression, and this enrichment score was defined as the activation state score of the pathway, which was used to quantify the activation state of the pathway associated with cancer progression.

[0037] According to the activation status score of each pathway, the changes of these scores in cancer progression are evaluated, and the dynamic network biomarker (DNB) analysis method is used to further screen the key pathways that change dynamically in cancer progression. These key pathways play an important role in the accelerated progression and deterioration of cancer. This implementation uses the "DNB" R software package to implement this process. Specifically, time series data is used to analyze the changes in network structure at different stages of cancer, and molecules are screened by the following features: (1) The intra-DNB group correlation (PCCin) increases significantly; (2) The correlation (PCCout) of the molecules in the DNB group with other non-DNB groups decreases sharply; (3) The standard deviation (SD) or coefficient of variation (CV) of the molecules in the DNB group increases significantly. These three features are crucial for identifying critical states. When these features show strong fluctuations and high correlations, it indicates that the cancer will further deteriorate. The composite index CI (Composite index) is further used to quantify these conditions. The formula is as follows:

[0038] CI=mean(CV)×PCCin / PCCout.

[0039] Among them, mean(CV) is the average value of the coefficient of variation (CV), PCCin is the correlation coefficient within the DNB group, and PCCout is the correlation coefficient between the numerator of the DNB group and other non-DNB groups.

[0040] S4: constructing a gene interaction network subnet based on the genes of the key pathway, and determining the DNEX score of the genes in the gene interaction network subnet. Specifically, it includes: using the PageRank algorithm to calculate the ranking score of the genes in the gene interaction network subnet; using differential expression analysis to identify the differential expression score of the genes in the gene interaction network subnet; and determining the DNEX score of the genes in the gene interaction network subnet based on the ranking score and the differential expression score.

[0041] A gene interaction network subnetwork was constructed based on the genes of the key pathways that dynamically change during cancer progression identified in step S3. The DNEX scores of genes were obtained by integrating the results of differential network analysis and differential expression analysis using immunotherapy target genes, PageRank algorithm, and differential expression analysis to evaluate the importance of genes in the gene interaction network subnetwork in immunotherapy.

[0042] The PageRank algorithm is a ranking algorithm that evaluates the importance of web pages by analyzing the link relationship between them. This embodiment applies this algorithm to the gene interaction network subnet and converts the generated gene ranking into a ranking score PRscore x , and its calculation formula is as follows:

[0043]

[0044] Among them, L x represents the total number of genes with PageRank scores (ranking scores), R x is the rank of each gene in the list.

[0045] Then, differential expression analysis was used to identify the differential expression of genes before and after the accelerated progression of cancer. The correlation between genes and cancer progression status was integrated and their importance in the progression process was calculated. The formula is as follows:

[0046]

[0047] Wherein, i is the order of expression profiles to be calculated, n is the number of expression profiles to be calculated, Rank(log(FC)) is the rank of log(FC), and FC is the differential expression fold of genes in the expression profile.

[0048] The ranking score of the PageRank differential network analysis and the gene score of the differential expression analysis are integrated to obtain the DNEX score. The DNEX score is a metric that integrates network structure and degree of difference. It is used to evaluate the immunomodulatory activity of genes during cancer progression, and then to evaluate the importance of genes in cancer progression and their potential value as immunotherapy biomarkers. It is calculated as follows:

[0049] DNEX score = PR score x ×Prog x

[0050] Among them, DNEXscore is the DNEX score of the gene in the gene interaction network subnet, PRscore x is the ranking score of the gene, Prog x is the differential expression score of the gene.

[0051] S5: Based on the DNEX score, a trained machine learning model is used to predict the effect of immunotherapy.

[0052] The dataset GSE91061 containing the immunotherapy effect was used as the training set, and 10 machine learning algorithms (random survival forest, elastic network, Lasso, ridge regression, stepwise Cox regression, CoxBoost, partial least squares Cox regression model, supervised principal component analysis, generalized boosted regression modeling, and survival support vector machine) were integrated into 62 algorithm combinations to predict the prognosis of immunotherapy. The datasets GSE131521, GSE78220, PRJEB23709, and VanAllen_Science_2015 containing the immunotherapy effect were used as the validation set to validate the model.

[0053] In addition, this example screened the top 100 genes in the DNEX score ranking and used the Cmap database to predict possible targeted drugs. Then, the AutoDock software was used for molecular docking to calculate the binding energy between the drug and the target protein to identify candidate drugs with strong binding ability to predict potential drugs in the period of accelerated cancer progression.

[0054] like Figure 2 As shown, the method for predicting the effect of immunotherapy during the period of cancer exacerbation provided by this application mainly includes five parts: (1) integrating multi-omics features to identify pathways related to cancer progression; (2) using dynamic network analysis to identify key pathways in the accelerated exacerbation stage; (3) evaluating the importance of genes in immunotherapy through differential expression networks; (4) predicting immunotherapy response based on network-based machine learning; (5) screening potential drugs based on molecular docking technology. The above five parts identify the accelerated exacerbation stage in the process of cancer exacerbation and the influence of genes on tumor immune activity during cancer exacerbation, which provides certain guidance for monitoring the exacerbation period of cancer and predicting the effect of immunotherapy, and provides more options for individualized treatment strategies. At the same time, it provides relevant candidate data for laboratory verification, which has an important directional guidance role.

[0055] Based on the same inventive concept, the embodiment of the present application also provides a system for implementing the above-mentioned method for predicting the effect of immunotherapy during the period of cancer exacerbation. The implementation scheme for solving the problem provided by the system is similar to the implementation scheme recorded in the above-mentioned method, so the specific limitations in one or more embodiments of the system for predicting the effect of immunotherapy during the period of cancer exacerbation provided below can refer to the limitations of the method for predicting the effect of immunotherapy during the period of cancer exacerbation above, and will not be repeated here.

[0056] In an exemplary embodiment, a system for predicting the effect of immunotherapy during the period of cancer exacerbation is provided, comprising:

[0057] The data acquisition module is used to obtain the multi-omics data of patients.

[0058] A feature determination module is used to determine a multi-omic feature associated with cancer staging based on the multi-omic data.

[0059] A key pathway determination module is used to determine the key pathways that dynamically change during cancer progression based on the multi-omics features.

[0060] The DNEX score determination module is used to construct a gene interaction network subnetwork based on the genes of the key pathway and determine the DNEX scores of the genes in the gene interaction network subnetwork.

[0061] The immunotherapy effect prediction module is used to predict the immunotherapy effect based on the DNEX score using a trained machine learning model.

[0062] 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. The computer device may be a server or a terminal, and its internal structure diagram may be as shown in FIG. Figure 3As shown. The computer device includes a processor, a memory, an input / output interface (Input / Output, referred to as I / O) and a communication interface. Among them, the processor, the memory and the input / output interface are connected through a system bus, and the communication interface is connected to the system bus through the input / output interface. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store data to be processed. The input / output interface of the computer device is used to exchange information between the processor and an external device. The communication interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, a method for predicting the effect of immunotherapy during the period of cancer exacerbation is implemented.

[0063] Those skilled in the art will understand that Figure 3 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components. 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.

[0064] 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.

[0065] In an exemplary embodiment, a computer program product is provided, including a computer program, and when the computer program is executed by a processor, the steps in the above method embodiments are implemented.

[0066] 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.

[0067] Those skilled 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), magnetoresistive 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).

[0068] 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.

[0069] 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.

[0070] 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 predicting the effect of immunotherapy during the period of cancer exacerbation, characterized in that: include: Obtain multi-omics data of patients; determining a multi-omic signature associated with cancer stage based on the multi-omic data; Identify key pathways that dynamically change during cancer progression based on the multi-omics signature; constructing a gene interaction network subnetwork based on the genes of the key pathway, and determining the DNEX scores of the genes in the gene interaction network subnetwork; Based on the DNEX score, a trained machine learning model is used to predict the effect of immunotherapy.

2. The method for predicting the effect of immunotherapy during the cancer exacerbation period according to claim 1, characterized in that: The multi-omics data include: somatic mutation data, copy number variation data, methylation data and gene expression RNA-seq data.

3. The method for predicting the effect of immunotherapy during the cancer exacerbation period according to claim 2, characterized in that: Determining multi-omics features associated with cancer staging based on the multi-omics data specifically includes: Based on the somatic mutation data, determining the somatic mutation signature associated with cancer stage using logistic regression analysis; Based on the copy number variation data, determining a copy number variation signature associated with cancer stage using a linear regression analysis method; Based on the methylation data, determining the methylation signature associated with cancer stage using Spearman correlation analysis; Based on gene expression RNA-seq data, the "EdgeR" software package was used to determine the differentially expressed gene signatures associated with cancer stage.

4. The method for predicting the effect of immunotherapy during the cancer exacerbation period according to claim 1, characterized in that: Based on the multi-omics signature, key pathways that dynamically change during cancer progression are identified, including: performing gene set enrichment analysis on the multi-omics signature to identify pathways associated with cancer progression; Calculate the activation status score of each pathway; Based on the activation status score, a dynamic network biomarker analysis method is used to identify key pathways that dynamically change during cancer progression.

5. The method for predicting the effect of immunotherapy during the cancer exacerbation period according to claim 1, characterized in that: Determine the DNEX score of genes in the gene interaction network subnetwork, including: The PageRank algorithm is used to calculate the ranking scores of genes in the gene interaction network subnetwork; Differential expression analysis was used to identify differential expression scores of genes in subnetworks of gene interaction networks; The DNEX scores of genes in the gene interaction network subnetwork are determined based on the ranking scores and the differential expression scores.

6. The method for predicting the effect of immunotherapy during the cancer exacerbation period according to claim 5, characterized in that: The calculation formula of the DNEX score of the gene in the gene interaction network subnet is: DNEXscore=PRscore x ×Prog x Among them, DNEXscore is the DNEX score of the gene in the gene interaction network subnet, PRscore x is the ranking score of the gene, L x is the total number of genes with ranking scores, R x For each gene's ranking in the list, Prog x is the differential expression score of the gene, i is the order of the expression profiles calculated, n is the number of expression profiles calculated, Rank(log(FC)) is the rank of log(FC), and FC is the differential expression fold of the gene in the expression profile.

7. A system for predicting the effect of immunotherapy during the period of cancer exacerbation, characterized in that: include: A data acquisition module, used to obtain multi-omics data of patients; a feature determination module, configured to determine a multi-omic feature associated with cancer staging based on the multi-omic data; A key pathway determination module, used to determine the key pathways that dynamically change during cancer progression based on the multi-omics features; A DNEX score determination module, used to construct a gene interaction network subnetwork based on the genes of the key pathway, and determine the DNEX scores of the genes in the gene interaction network subnetwork; The immunotherapy effect prediction module is used to predict the immunotherapy effect based on the DNEX score using a trained machine learning model.

8. 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 predicting the effect of immunotherapy during the cancer exacerbation period according to any one of claims 1 to 6.

9. 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 predicting the effect of immunotherapy during the cancer exacerbation period according to any one of claims 1 to 6 is implemented.

10. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the method for predicting the effect of immunotherapy during the cancer exacerbation period according to any one of claims 1 to 6 is implemented.

Images