Data processing system and method for adverse prognosis of PD-1 / PD-L1 inhibitors

Abstract

The present application provides a data processing system for the poor prognosis of PD-1 / PD-L1 inhibitors, including: a data acquisition unit: used to obtain the expression level of biomarkers or the signal pathway activity score data; a data analysis unit: used to analyze the expression level of the biomarkers or the signal pathway activity score data to obtain the activation information of the interleukin 1 signal pathway; a data determination unit: used to determine the poor prognosis information of PD-1 / PD-L1 inhibitors based on the activation information of the interleukin 1 signal pathway. This method is currently the only method that can predict the poor prognosis after receiving PD-1 / PD-L1 inhibitors. It integrates traditional RNA and protein detection, bioinformatics analysis, etc. The judgment criteria are simple and clear, the speed is fast, the accuracy is high, and it is easy to implement in clinical applications, which is conducive to the selection of appropriate treatment plans.

Description

Technical Field

[0001] The present application belongs to the field of molecular biology technology, and in particular, relates to a data processing system and method for adverse prognosis of PD-1 / PD-L1 inhibitors. Background Art

[0002] The use of different mechanisms by tumor cells to escape immunity is an important feature of their development, and several immunosuppressive mechanisms in the tumor microenvironment have also become an important treatment direction. Among them, the immune checkpoint protein PD-1 and its main ligand PD-L1 are particularly valued. The development of monoclonal antibody drugs targeting PD-1 or PD-L1 to hinder the inhibitory effect of tumor cells on T cells has been widely carried out in actual treatment and clinical trials. However, as the third revolutionary breakthrough in tumor treatment, the proportion of the overall clinical response population (complete remission or partial remission) of immune checkpoint inhibitors is about 20%, which, like previous chemotherapy and targeted drugs, cannot cover all patients. In addition, disease progression after cancer treatment is also a particularly thorny problem, and clinical data show that among common cancers, about 10-30% of patients will have a poor prognosis of "hyperprogression (i.e., rapid tumor progression)", which seriously accelerates the deterioration of the disease.

[0003] Currently, there is no clinical method for predicting adverse prognosis of PD-1 / PD-L1 inhibitors, but there are discussions on the judgment of the population that responds to PD-1 / PD-L1 inhibitors. Commonly used biomarkers for detecting the population that responds include tumor mutation burden (TMB), mismatch repair deficiency / microsatellite instability (dMMR / MSI) or PD-L1 expression. However, among patients with common tumors in clinical practice, the overlap ratio of the population selected by these three methods is very low, ranging from about 1-30%. On the one hand, it shows that each of these three biomarkers can only identify a part of the population, and none of these three biomarkers can point to specific population characteristics; therefore, the current method of screening the population that responds to PD-1 / PD-L1 inhibitors is not effective enough, and it is even more impossible to infer the patient population that may have a poor prognosis.

[0004] Therefore, there is an urgent clinical need to provide a data processing system that can pre-judge whether the use of PD-1 / PD-L1 inhibitors will result in adverse prognosis, which will help to know in advance which patients will have adverse prognosis (i.e., including hyperprogressive disease progression), so that they can avoid inappropriate treatment plans and buy precious time for other effective medications. Summary of the invention

[0005] The purpose of the present application is to provide a post-data processing system and method for adverse prognosis of PD-1 / PD-L1 inhibitors, aiming to solve the problem that there is no prediction method for adverse prognosis of PD-1 / PD-L1 inhibitors in the prior art.

[0006] In order to achieve the above application purpose, the technical solution adopted in this application is as follows:

[0007] In a first aspect, the present application provides a data processing system for poor prognosis of PD-1 / PD-L1 inhibitors, comprising:

[0008] Data acquisition unit: used to obtain the expression level of biomarkers or signal pathway activity score data;

[0009] Data analysis unit: used to analyze the expression level of the biomarker or the signal pathway activity score data to obtain activation information of the interleukin-1 signal pathway;

[0010] Data determination unit: used to determine the adverse prognosis information of PD-1 / PD-L1 inhibitors according to the activation information of the interleukin 1 signaling pathway.

[0011] In a second aspect, the present application provides a method for processing data of adverse prognosis of a PD-1 / PD-L1 inhibitor, comprising the following steps:

[0012] Obtain biomarker expression levels or signaling pathway activity score data;

[0013] Analyzing the expression level of the biomarker or the signal pathway activity score data to obtain activation information of the interleukin 1 signal pathway;

[0014] Based on the activation information of the interleukin 1 signaling pathway, the adverse prognostic information of the PD-1 / PD-L1 inhibitor is determined.

[0015] The data processing system for the adverse prognosis of PD-1 / PD-L1 inhibitors provided in the first aspect of the present application obtains the expression level of relevant biomarkers or signal pathway activity score data through a data acquisition unit; then analyzes through a data analysis unit to determine that the interleukin 1 signal pathway is activated; further, the data determination unit determines the adverse prognosis information of the PD-1 / PD-L1 inhibitor according to the activation information of the interleukin 1 signal pathway; this method is currently the only method that can predict the adverse prognosis after receiving PD-1 / PD-L1 inhibitors, and integrates traditional RNA and protein detection, bioinformatics analysis, etc. The judgment criteria are simple and clear, the speed is fast, the accuracy is high, it is easy to implement in clinical applications, and it is conducive to selecting appropriate treatment plans.

[0016] The second aspect of the present application provides a data processing method for the adverse prognosis of a PD-1 / PD-L1 inhibitor. The method has simple and clear judgment criteria, fast speed, high accuracy, is easy to implement in clinical applications, and is conducive to selecting an appropriate treatment plan. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required for use in the embodiments or the description of the prior art 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 any creative work.

[0018] Figure 1 This is the protein immunoblotting test result of the growth marker provided in Example 1 of the present application. DETAILED DESCRIPTION

[0019] In order to make the technical problems, technical solutions and beneficial effects to be solved by the present application more clearly understood, the present application is further described in detail below in conjunction with the embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0020] In this application, the term "and / or" describes the association relationship of associated objects, indicating that there may be three relationships. For example, A and / or B can mean: A exists alone, A and B exist at the same time, and B exists alone. A and B can be singular or plural. The character " / " generally indicates that the associated objects are in an "or" relationship.

[0021] In this application, "at least one" means one or more, and "plurality" means two or more. "At least one of the following" or similar expressions refers to any combination of these items, including any combination of single items or plural items. For example, "at least one of a, b, or c", or "at least one of a, b, and c" can all mean: a, b, c, ab (i.e., a and b), ac, bc, or abc, where a, b, c can be single or multiple, respectively.

[0022] It should be understood that in the various embodiments of the present application, the size of the serial numbers of the above-mentioned processes does not mean the order of execution, some or all of the steps can be executed in parallel or sequentially, and the execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0023] The terms used in the embodiments of the present application are only for the purpose of describing specific embodiments, and are not intended to limit the present application. The singular forms "a", "said" and "the" used in the embodiments of the present application and the appended claims are also intended to include plural forms, unless the context clearly indicates other meanings.

[0024] The weight of the relevant components mentioned in the embodiment description of the present application can not only refer to the specific content of each component, but also represent the proportional relationship between the weights of the components. Therefore, as long as the content of the relevant components is proportionally enlarged or reduced according to the embodiment description of the present application, it is within the scope disclosed in the embodiment description of the present application. Specifically, the mass described in the embodiment description of the present application can be a mass unit known in the chemical industry such as μg, mg, g, kg, etc.

[0025] The terms "first" and "second" are used only for descriptive purposes to distinguish objects such as substances from each other, and should not be understood as indicating or implying relative importance or implicitly indicating the number of indicated technical features. For example, without departing from the scope of the embodiments of the present application, the first XX may also be referred to as the second XX, and similarly, the second XX may also be referred to as the first XX. Thus, features defined as "first" and "second" may explicitly or implicitly include one or more of the features.

[0026] Definitions of key terms provided in the embodiments of this application:

[0027] Tumor immune escape: refers to the process by which tumor cells evade recognition and attack by the immune system through a variety of mechanisms, thereby proliferating and developing.

[0028] Population that will benefit clinically: In cancer immunotherapy, the efficacy is divided into complete remission, partial remission, disease stabilization and disease progression through imaging examination of lesion changes and according to the iRECIST (immune response evaluation criteria in solid tumor) criteria; patients with complete remission, partial remission and disease stabilization belong to the population that will benefit clinically.

[0029] Clinical response population: Patients with complete remission and partial remission during immunotherapy are eligible for the clinical response population as determined by imaging examination of lesion changes and in accordance with iRECIST standards.

[0030] Poor prognosis: According to the iRECIST criteria, disease progression (including hyperprogression) is considered a poor prognosis.

[0031] Hyperprogression: refers to the rapid progression of the disease after immunotherapy, specifically defined as: tumor progression time during treatment is <2 months; tumor burden increases by >50% compared to baseline; tumor growth rate after treatment is >2.

[0032] Tumor microenvironment: the environment in which tumor cells are produced and live, including tumor cells, surrounding fibroblasts, immune and inflammatory cells, glial cells and other cells, as well as tissue structures such as the extracellular matrix and microvessels in the nearby area, as well as the biological molecules infiltrating therein (small molecules such as hormones, large molecules such as immune proteins, complement proteins, etc.), and the interactions between these cells (such as receptor recognition, secretory regulation, etc.).

[0033] Immune checkpoints: a series of molecules expressed on immune cells that can regulate the degree of immune activation, so that the immune function will not be overactivated when stimulated, and play an important role in preventing the occurrence of autoimmunity; PD-1 is an immune checkpoint molecule. Tumor cells will express some factors to activate immune checkpoints, so that the immune function is suppressed and the tumor can survive.

[0034] PD-1 / PD-L1: Immune cells express PD-1, which inhibits the activation, proliferation and tumor killing of T cells by binding to the primary ligand PD-L1 (or secondary ligand PD-L2). It is a type of immune checkpoint.

[0035] Signal pathway: refers to the process by which receptor proteins convert extracellular signals into intracellular signals, and then amplify, disperse and regulate the signals to produce a series of comprehensive cellular responses.

[0036] Deep learning computing model: refers to the process of reading a certain set of input information, organizing information transformation and node integration through a hierarchical neural network model, and obtaining an output set that can describe the overall characteristics of the target. In the embodiment of the present application, it specifically refers to the input of the patient's genomic information, and the output is a description of the activity of the interleukin-1 signaling pathway.

[0037] In a first aspect, an embodiment of the present application provides a data processing system for poor prognosis of a PD-1 / PD-L1 inhibitor, comprising:

[0038] Data acquisition unit: used to obtain the expression level of biomarkers or signal pathway activity score data;

[0039] Data analysis unit: used to analyze the expression level of biomarkers or signal pathway activity score data to obtain activation information of interleukin-1 signal pathway;

[0040] Data determination unit: used to determine the adverse prognostic information of PD-1 / PD-L1 inhibitors based on the activation information of the interleukin 1 signaling pathway.

[0041] The data processing system for the adverse prognosis of PD-1 / PD-L1 inhibitors provided in the first aspect of the present application obtains the expression level of relevant biomarkers or signal pathway activity score data through a data acquisition unit; then analyzes through a data analysis unit to determine that the interleukin 1 signal pathway is activated; further, the data determination unit determines the adverse prognosis information of the PD-1 / PD-L1 inhibitor according to the activation information of the interleukin 1 signal pathway; this method is currently the only method that can predict the adverse prognosis after receiving PD-1 / PD-L1 inhibitors, and integrates traditional RNA and protein detection, bioinformatics analysis, etc. The judgment criteria are simple and clear, the speed is fast, the accuracy is high, it is easy to implement in clinical applications, and it is conducive to selecting appropriate treatment plans.

[0042] Specifically, the data processing system for poor prognosis of PD-1 / PD-L1 inhibitors provided in the embodiments of the present application includes: a data acquisition unit; the data acquisition unit is used to obtain the expression level of the biomarker or the signal pathway activity score data.

[0043] Furthermore, the biomarkers include at least one of IL-1α, IL-1β, IL-1R1, IL-1RAP, ECSIT, FOS, JUN, MAP3K1, MAP3K7, MAP3K14, MYD88, TAB1, TAB2, TRAF6, and TOLLIP. By obtaining the expression levels of the above biomarkers, the activation information of the interleukin-1 signaling pathway can be reflected.

[0044] Furthermore, in the acquisition process of the data acquisition unit, the step of acquiring the expression level of the biomarker includes: extracting the soluble extracellular protein or mRNA containing the biomarker and determining the expression level of the contained biomarker.

[0045] In some embodiments, during the acquisition process of the data acquisition unit, the step of obtaining signal pathway activity score data includes: providing soluble extracellular protein of an in vitro sample, using any one of ELISA protein quantification method, BCA protein quantification method, protein immunoblotting method, and immunohistochemistry to determine the biomarkers of the soluble extracellular protein, and obtaining the expression level of the biomarker.

[0046] Among them, the soluble extracellular proteins of the ex vivo sample are selected from at least one of the soluble extracellular proteins of whole blood of the ex vivo sample, the soluble extracellular proteins of serum of the ex vivo sample, the soluble extracellular proteins of plasma of the ex vivo sample, the soluble extracellular proteins of tumor-specific exosomes, the soluble extracellular proteins of tumor tissue, and the soluble extracellular proteins of circulating tumor cells.

[0047] In other embodiments, during the acquisition process of the data acquisition unit, the steps for obtaining signal pathway activity score data include: providing mRNA of an in vitro sample, using any one of the following methods: Noser hybridization method, in situ hybridization method, and reverse transcription-polymerase chain reaction method to determine the biomarkers of the mRNA, and obtaining the expression level of the biomarkers.

[0048] Furthermore, in the acquisition process of the data acquisition unit, the step of acquiring the signal pathway activity score data includes:

[0049] Provide whole exome sequencing data of tumor tissue cells or circulating tumor cells, use bioinformatics methods to score, and obtain signal pathway activity score data.

[0050] In some embodiments, in the step of obtaining signal pathway activity score data, the neural network deep learning algorithm DAGG is used to convert the circulating tumor cell DNA whole exome sequencing data into signal pathway activity score data to obtain the signal pathway activity score data.

[0051] Specifically, the data processing system for poor prognosis of PD-1 / PD-L1 inhibitors provided in the embodiments of the present application includes: a data analysis unit: used to analyze the expression level of biomarkers or signal pathway activity score data to obtain activation information of the interleukin 1 signaling pathway.

[0052] Since specific phenomena in organisms are based on the interaction of various molecules through known or unknown mechanisms, the sum of the events that ultimately occur involves the activation or inhibition of signaling pathways, changes in the content of metabolites, or the state of interaction between biological molecules and their changes. Similarly, after PD-1 / PD-L1 inhibitors enter cells, they directly act on the immune system, causing changes in the state of various downstream signaling pathways, among which the interleukin 1 (IL-1, interleukin-1) signaling pathway is closely related to the occurrence and development of tumors. Interleukin 1 family proteins can be synthesized and released by tumor cells through self-regulation, or they can be released by other cells in the tumor microenvironment. They can maintain the production of reactive oxygen species (ROS) and nitric oxide (NO), increase the mutation rate, bind to receptors and activate downstream signaling pathways such as MAPK, IKK / NF-κb and JNK, avoid cell apoptosis, or activate stromal cells in the stromal tumor microenvironment, causing new angiogenesis and other tumor development. By analyzing the expression levels of biomarkers or signaling pathway activity score data, we can obtain information on whether the interleukin-1 signaling pathway is activated, determine the occurrence of cell hyperprogression, and thus reflect the therapeutic effect of PD-1 / PD-L1 inhibitors.

[0053] Furthermore, in the analysis process of the data analysis unit, the step for analyzing the expression level of the biomarker includes: analyzing the activation information of the interleukin 1 signaling pathway according to the increase or decrease of the expression level of the biomarker.

[0054] In some embodiments, when the biomarker is selected from at least one of IL-1α, IL-1β, IL-1R1, IL-1RAP, ECSIT, FOS, JUN, MAP3K1, MAP3K7, MAP3K14, MYD88, TAB1, TAB2, and TRAF6, the expression level of the above biomarker increases and the interleukin 1 signaling pathway is in an activated state.

[0055] In other embodiments, when the biomarker is selected from TOLLIP, the expression level of the above biomarker decreases and the interleukin 1 signaling pathway is activated.

[0056] Furthermore, in the analysis process of the data analysis unit, the step of analyzing the signal pathway activity score data includes: if the score of the signal pathway activity score data is greater than 0.5, the interleukin 1 signal pathway is in an activated state.

[0057] Specifically, the data processing system for the adverse prognosis of the PD-1 / PD-L1 inhibitor provided in the embodiment of the present application includes: a data determination unit: used to determine the adverse prognosis information of the PD-1 / PD-L1 inhibitor based on the activation information of the interleukin 1 signaling pathway.

[0058] Since the expression of the above-provided biomarkers in the interleukin 1 family proteins can effectively reflect the activation information of the interleukin 1 signaling pathway, when the interleukin 1 signaling pathway is in an activated state, it can be determined whether the PD-1 / PD-L1 inhibitor has a response result with a poor prognosis.

[0059] In some embodiments, during the determination process of the data determination unit, the interleukin 1 signaling pathway is in an activated state, and a response result with a poor prognosis of the PD-1 / PD-L1 inhibitor is determined.

[0060] In other embodiments, during the determination process of the data determination unit, the interleukin 1 signaling pathway is in an inactive state, and the response result of the PD-1 / PD-L1 inhibitor is determined to have no adverse prognosis.

[0061] The data processing system for poor prognosis of PD-1 / PD-L1 inhibitors provided in the second aspect of the embodiment of the present application corresponds to a data processing method for poor prognosis of PD-1 / PD-L1 inhibitors, which specifically includes the following steps:

[0062] S01. Obtaining the expression level of biomarkers or signaling pathway activity score data (corresponding to the above-mentioned data acquisition unit);

[0063] S02. Analyze the expression level of the biomarker or the signal pathway activity score data to obtain activation information of the interleukin-1 signal pathway (corresponding to the above-mentioned data analysis unit);

[0064] S03. Determine the adverse prognosis information of PD-1 / PD-L1 inhibitors based on the activation information of the interleukin-1 signaling pathway (corresponding to the above-mentioned data determination unit).

[0065] The second aspect of the present application provides a data processing method for the adverse prognosis of a PD-1 / PD-L1 inhibitor. The method has simple and clear judgment criteria, fast speed, high accuracy, is easy to implement in clinical applications, and is conducive to selecting an appropriate treatment plan.

[0066] The following describes the invention in conjunction with specific embodiments.

[0067] Example 1

[0068] Data processing methods for adverse prognosis of PD-1 / PD-L1 inhibitors

[0069] (1) Obtaining the expression level of biomarkers: Non-small cell lung cancer cell lines NCI-H1299, A549, HCC827 and PC9 were cultured in RPMI1640 medium containing 10% FBS and 1% PS dual antibody in an incubator at 37°C and 5% CO2. After the cells were fully grown, the cells were treated with RIPA lysis buffer and centrifuged to obtain the supernatant containing cytokines. After the total protein in the supernatant was quantified, 20 μg of protein samples were taken from each group for Western blotting detection, respectively detecting IL-1α, IL-1β and IL1R1;

[0070] (2) Analyze the expression level data of biomarkers to obtain the activation information of interleukin-1 signaling pathway; as shown in the attached Figure 1 As shown, the results of western blot showed that the expression of three proteins, IL-1α, IL-1β and IL1R1, were upregulated in HCC827 and PC9 cell lines, which means that the interleukin-1 signaling pathway of HCC827 and PC9 cell lines was activated;

[0071] (3) Based on the activation information of the interleukin 1 signaling pathway, the adverse prognostic information of PD-1 / PD-L1 inhibitors was determined; the interleukin 1 signaling pathway of HCC827 and PC9 cell lines was in an activated state, so the PD-1 / PD-L1 inhibitors had a response result of adverse prognosis.

[0072] Among them, HCC827 and PC9 are sensitive mutant cell lines that respond poorly to PD-1 / PD-L1 inhibitors, which is consistent with the "PD-1 / PD-L1 inhibitor response result with poor prognosis" obtained by the above-mentioned data processing method of the adverse prognosis of PD-1 / PD-L1 inhibitors.

[0073] Example 2

[0074] Data processing methods for adverse prognosis of PD-1 / PD-L1 inhibitors

[0075] (1) Obtaining signal pathway activity score data: From 26 patients with lung adenocarcinoma who were resistant to PD-1 / PD-L1 (determined by professional doctors as having progressive or hyperprogressive disease according to iRECIST) admitted to a tertiary hospital in Guangdong Province from 2017 to 2018, the patients' ctDNA (circulating tumor cell DNA) whole exome sequencing data were retrieved, and the neural network deep learning algorithm DAGG was used to convert the patients' genomic data into signal pathway activity scores in tumor cells;

[0076] (2) The signal pathway activity score data were analyzed to obtain the activation information of the interleukin-1 signal pathway; among them, 21 patients had an interleukin-1 signal pathway activity score > 0.5, and were judged to have activated the interleukin-1 signal pathway, with a judgment validity of 81%;

[0077] (3) Based on the activation information of the interleukin 1 signaling pathway, the adverse prognostic information of PD-1 / PD-L1 inhibitors was determined; among them, the interleukin 1 signaling pathway activity score of the above 21 patients was greater than 0.5, and they were judged to have activated the interleukin 1 signaling pathway, and the response results with adverse prognosis of PD-1 / PD-L1 inhibitors were determined.

[0078] Therefore, the data processing method for the adverse prognosis of PD-1 / PD-L1 inhibitors provided in the present application can confirm the activation of the interleukin-1 signaling pathway through the expression level of biomarkers or the scoring of exons. It is currently the only method that can predict the adverse prognosis after receiving PD-1 / PD-L1 inhibitors; the discrimination criteria are simple and clear, making clinical application easy to implement, and precious time can be saved to choose an appropriate treatment plan.

[0079] The above description is only a preferred embodiment of the present application and is not intended to limit the present application. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present application should be included in the protection scope of the present application.

Claims

1. A data processing system for predicting adverse prognosis of PD-1 / PD-L1 inhibitors, characterized in that: include: Data acquisition unit: used to obtain the expression level of biomarkers or signal pathway activity score data; Data analysis unit: used to analyze the expression level of the biomarker or the signal pathway activity score data to obtain activation information of the interleukin-1 signal pathway; A data determination unit: used to determine the adverse prognosis information of the PD-1 / PD-L1 inhibitor according to the activation information of the interleukin-1 signaling pathway; The method is used to determine the adverse prognosis information of the PD-1 / PD-L1 inhibitor based on the activation information of the interleukin 1 signaling pathway: when the interleukin 1 signaling pathway is in an activated state, a response result of the PD-1 / PD-L1 inhibitor with a poor prognosis is determined; when the interleukin 1 signaling pathway is in an inactivated state, a response result of the PD-1 / PD-L1 inhibitor with no poor prognosis is determined.

2. The data processing system for predicting adverse prognosis of PD-1 / PD-L1 inhibitors according to claim 1, characterized in that: The biomarkers include at least one of IL-1α, IL-1β, IL-1R1, IL-1RAP, ECSIT, FOS, JUN, MAP3K1, MAP3K7, MAP3K14, MYD88, TAB1, TAB2, TRAF6, and TOLLIP.

3. The data processing system for predicting adverse prognosis of PD-1 / PD-L1 inhibitors according to claim 1, characterized in that: In the acquisition process of the data acquisition unit, the step of acquiring the expression level of the biomarker includes: Providing soluble extracellular protein of an in vitro sample, and determining the biomarker of the soluble extracellular protein by any one of ELISA protein quantification method, BCA protein quantification method, protein immunoblotting method, and immunohistochemistry to obtain the expression level of the biomarker; and / or, Providing mRNA of an in vitro sample, and using any one of a Noser hybridization method, an in situ hybridization method, and a reverse transcription-polymerase chain reaction method to measure the biomarker of the mRNA, and obtaining the expression level of the biomarker.

4. The data processing system for predicting adverse prognosis of PD-1 / PD-L1 inhibitors according to claim 1, characterized in that: In the acquisition process of the data acquisition unit, the step of acquiring the signal pathway activity score data includes: Provide whole exome sequencing data of tumor tissue cells or circulating tumor cells, use bioinformatics methods to score, and obtain signal pathway activity score data.

5. The data processing system for predicting adverse prognosis of PD-1 / PD-L1 inhibitors according to claim 4, characterized in that: In the step of obtaining signal pathway activity scoring data, the circulating tumor cell DNA whole exome sequencing data is converted into signal pathway activity scoring data using the neural network deep learning algorithm DAGG to obtain signal pathway activity scoring data.

6. The data processing system for predicting adverse prognosis of PD-1 / PD-L1 inhibitors according to any one of claims 1 to 5, characterized in that: In the analysis process of the data analysis unit, the step for analyzing the expression level of the biomarker includes: analyzing the activation information of the interleukin 1 signaling pathway according to the increase or decrease of the expression level of the biomarker.

7. The data processing system for predicting adverse prognosis of PD-1 / PD-L1 inhibitors according to claim 6, characterized in that: When the biomarker is selected from at least one of IL-1α, IL-1β, IL-1R1, IL-1RAP, ECSIT, FOS, JUN, MAP3K1, MAP3K7, MAP3K14, MYD88, TAB1, TAB2, and TRAF6, the expression level of the biomarker increases, and the interleukin 1 signaling pathway is in an activated state; and / or, When the biomarker is selected from TOLLIP, the expression level of the biomarker decreases and the interleukin 1 signaling pathway is in an activated state.

8. The data processing system for predicting adverse prognosis of PD-1 / PD-L1 inhibitors according to any one of claims 1 to 5, characterized in that: During the analysis process of the data analysis unit, the step of analyzing the signal pathway activity score data includes: if the score of the signal pathway activity score data is greater than 0.5, the interleukin 1 signal pathway is in an activated state.

9. A data processing method for predicting poor prognosis of PD-1 / PD-L1 inhibitors, characterized in that: The steps include: Obtain biomarker expression levels or signaling pathway activity score data; Analyzing the expression level of the biomarker or the signal pathway activity score data to obtain activation information of the interleukin-1 signal pathway; Determining adverse prognostic information of PD-1 / PD-L1 inhibitors based on the activation information of the interleukin-1 signaling pathway; According to the activation information of the interleukin 1 signaling pathway, the adverse prognosis information of the PD-1 / PD-L1 inhibitor is determined: when the interleukin 1 signaling pathway is in an activated state, the response result of the PD-1 / PD-L1 inhibitor with a poor prognosis is determined; when the interleukin 1 signaling pathway is in an inactivated state, the response result of the PD-1 / PD-L1 inhibitor with no poor prognosis is determined.

Images