Method, equipment and medium for assisting in predicting immune-related adverse reactions

Abstract

The invention provides a method, equipment, a medium and a program product for assisting in predicting immune-related adverse reactions, and relates to the field of intelligent medical treatment. The method comprises the following steps: acquiring tested cell data; calculating the proportion of target cell subgroups including CXCR3 + CCR6 + CD8 + T cell subgroups and NK cell subgroups in the mononuclear cells on the basis of the cell data; calculating a prediction score based on the proportion of the target cell subpopulation; and according to the prediction score, outputting an auxiliary prediction result of the probability of the immune-related adverse reactions of the subject. The application explores and verifies that the higher baseline level of the immunotherapy CXCR3 + CCR6 + CD8 + T cell subset and the NK cell subset is closely related to the occurrence of irAE.

Description

Technical Field

[0001] The present invention relates to the field of intelligent medical treatment, and more specifically, to a method, device, medium and program product for assisting in predicting immune-related adverse reactions. Background Art

[0002] Immunotherapy represented by PD-1 / PD-L1 inhibitors has brought revolutionary progress to the treatment of tumors, greatly improved the prognosis of tumor patients, and prolonged the survival of patients. However, the use of this inhibitor can also lead to excessive activation of the immune system, causing tissue immune inflammatory damage, namely immune-related adverse events (irAEs). The incidence of irAEs in PD-1 / PD-L1 is as high as 74%, the incidence in CTLA4 is 89%, and the incidence in combined immunotherapy is more than 90%. The incidence of severe irAEs can reach 50%. irAE not only affects the quality of life of patients, but also seriously affects the efficacy of patients. 30% of patients interrupted treatment due to irAE, and 13% of patients were hospitalized due to irAE.

[0003] How to reduce the incidence of irAE and the serious consequences it causes has become an important clinical problem that needs to be urgently addressed. If a means of predicting irAE can be found and early intervention can be carried out, it will become an important method to solve this clinical problem. At present, a small number of research reports suggest that some markers are related to the occurrence of AE. Some studies suggest that patients with a neutrophil: lymphocyte ratio of less than 3 are prone to irAE, and some indicate that IL-17 levels are related to irAEs. However, these studies are all small sample studies and have not been verified by external data. The reliability is poor, which is manifested in that these indicators are only applicable to a certain tumor type, and negative results will be obtained after changing the tumor type. At present, there is an urgent need for markers with higher predictive value, higher sensitivity, and more reliable prediction of the occurrence of irAE. Summary of the invention

[0004] The present invention aims to solve at least one of the technical problems existing in the prior art. To this end, the present invention provides a method, device, medium and program product for assisting the prediction of immune-related adverse reactions; the present invention constructs an auxiliary prediction model based on the target cell subpopulation obtained by processing and screening the cell data set of the training set samples to improve the prediction performance of immunotherapy adverse reactions and solve related life science problems.

[0005] The first aspect of the present application discloses a method for assisting in predicting immune-related adverse reactions, the method comprising: 101, obtaining the tested cell data; 102, calculating the proportion of target cell subpopulations in mononuclear cells based on the cell data; the target cell subpopulations include CXCR3+CCR6+CD8+T cell subpopulations and NK cell subpopulations; 103, calculating a prediction score based on the proportion of the target cell subpopulation; 104. Output an auxiliary prediction result of the probability of the subject to have an immune-related adverse reaction according to the prediction score; when the prediction score is greater than a first threshold, output an auxiliary prediction result indicating that the subject has a high probability of having an immune-related adverse reaction; when the prediction score is less than the first threshold, output an auxiliary prediction result indicating that the subject has a low probability of having an immune-related adverse reaction.

[0006] In some embodiments, the calculation of the prediction score in 103 is calculated by inputting the proportion of the target cell subpopulation into the auxiliary prediction model; Optionally, the method for constructing the auxiliary prediction model includes: Obtain a cell data set of training set samples; process the cell data set to obtain the proportion of each immune cell subpopulation in a single sample; screen out a target cell subpopulation from each immune cell subpopulation; input the proportion of the target cell subpopulation and whether the corresponding sample has an adverse immune reaction as a classification label into a machine learning model to obtain a predicted classification result, compare it with the classification label, optimize the model according to the comparison result, and obtain the auxiliary prediction model; Optionally, the method for processing the cell data set includes: quality control, clustering, subpopulation annotation, and calculating the proportion of each immune cell subpopulation in each sample.

[0007] In some embodiments, the method for screening the target cell subpopulation includes: performing correlation analysis on the correlation between the immune cell subpopulations, and screening out the immune cell subpopulations whose collinearity is greater than a second threshold as the target cell subpopulation; Optionally, the collinearity is a spearman correlation coefficient.

[0008] In some embodiments, the target cell subpopulations include: CXCR3+CCR6+CD8+T cell subpopulation, NK cell subpopulation, and CXCR3+CCR6+CD4+T cell subpopulation.

[0009] In some embodiments, the method for screening the target cell subpopulation further includes: removing the cell subpopulation whose AUC value is less than a third threshold among the immune cell subpopulations whose collinearity is greater than the second threshold by a single factor screening method as the target cell subpopulation.

[0010] In some embodiments, the method for calculating the prediction score in 103 includes: the auxiliary prediction model includes: logit(P) = 0.758 * C14-0.119 * C20- 0.715; wherein, C14 is the proportion of CXCR3+CCR6+CD8+T cell subpopulation, C20 is the proportion of CD56dimNK cell subpopulation, and logit(P) is the prediction score.

[0011] In some embodiments, the calculation method of the proportion in 102 includes: interested cell subpopulation / total number of all cells; Optionally, the cell data comes from a peripheral blood sample of the subject.

[0012] The second aspect of the present application discloses a computer device, which includes: a memory and a processor; the memory is used to store a computer program; and the processor executes the computer program to implement the steps of the above method.

[0013] A third aspect of the present application discloses a computer-readable storage medium having a computer program stored thereon, wherein the computer program implements the steps of the above method when executed by a processor.

[0014] A fourth aspect of the present application discloses a computer program product, including a computer program, which implements the steps of the above method when executed by a processor.

[0015] This application has the following beneficial effects: 1. This application innovatively uses the largest sample size of single-cell dataset for adverse reactions to immunotherapy currently available. By processing and screening the cell dataset of the training set samples, the target cell subpopulation is finally obtained, and a prediction model for irAE is constructed to improve the prediction performance of adverse reactions to immunotherapy, thus making up for the problem of small sample size of current detection indicators. Moreover, this scheme is constructed through discovery set data and has been verified by external data, making it more reliable and making up for the poor reliability of existing indicators.

[0016] 2. This application innovatively discloses a method for assisting in the prediction of immune-related adverse reactions, exploring the relationship between CXCR3+CCR6+CD8+T cell subsets, NK cell subsets, CXCR3+CCR6+CD4+T cell subsets and irAEs, and confirming that the higher baseline levels of the two cell subtypes before immunotherapy are closely related to the occurrence of irAEs. Further, the exact relationship between the proportion of 2 or 3 or more cell subsets and the occurrence of immune-related adverse reactions is studied, and 2 cell subsets with high performance and more simplicity are screened out. The proportion of the two cell subsets is used to calculate the prediction score, and then the auxiliary prediction result of the probability of immune-related adverse reactions is predicted based on the prediction score. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative work.

[0018] Figure 1 is a schematic diagram of a method flow chart provided by the first aspect of an embodiment of the present invention; Figure 2 is a schematic diagram of a system for assisting in predicting immune-related adverse reactions provided by the second aspect of an embodiment of the present invention; Figure 3 is a schematic diagram of a computer device provided by an embodiment of the present invention; Figure 4 is a schematic diagram of the architecture of an exemplary computing device provided by an embodiment of the present invention; Figure 5 is a schematic diagram of a storage medium provided by an embodiment of the present invention; Figure 6 is a schematic diagram of the construction process of the auxiliary prediction model provided by an embodiment of the present invention; Figure 7 This is a schematic diagram of the results of cell subpopulations that are solely related to adverse reactions to immunotherapy obtained through univariate analysis provided by an embodiment of the present invention; Figure 8 is a schematic diagram of the results of correlation analysis of immune cell subsets provided in an embodiment of the present invention; Fig. 9 : is a schematic diagram of the predictive performance of C14 and C04 for adverse reactions evaluated by AUROC according to an embodiment of the present invention; wherein, Fig. 9 A is the AUROC display diagram of C14. Fig. 9 B is the AUROC display diagram of C04; Fig.10 It is a schematic diagram of the predictive performance of the C20 cell subset for adverse reactions evaluated by AUROC according to an embodiment of the present invention; Fig.11 is a schematic diagram of the prediction performance of the auxiliary prediction model provided by an embodiment of the present invention in a training set sample; wherein, Fig.11 A is the AUROC display diagram of the model in the training set samples. Fig.11 B is a comparison chart of the scores of patients with and without adverse reactions calculated using the model; Fig.12 is a result diagram of annotating each immune cell subset in the validation set sample provided by an embodiment of the present invention; Fig.13is a schematic diagram of clustering cells in a validation set sample provided by an embodiment of the present invention; Fig.14 The embodiment of the present invention provides Fig.13 Comparison diagram of immune cell subsets in validation set sample clustering and training set samples; Fig.15 is a schematic diagram of the prediction performance of the auxiliary prediction model provided by an embodiment of the present invention in a validation set sample; Fig.15 A is the AUROC display diagram of the model in the validation set samples. Fig.15 B is a comparison chart of the scores of patients with and without adverse reactions calculated using the model; Fig.16 This is a graph showing the AUROC of the prediction model constructed using three types of cells, C14, C04, and C20, in the training set samples provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0019] In order to enable those skilled in the art to better understand the solutions of the present invention, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the accompanying drawings in the embodiments of the present invention.

[0020] In some of the processes described in the specification and claims of the present invention and the above-mentioned figures, multiple operations that appear in a specific order are included, but it should be clearly understood that these operations may not be executed in the order in which they appear in this article or executed in parallel. The serial numbers of the operations, such as 101, 102, etc., are only used to distinguish different operations, and the serial numbers themselves do not represent any execution order. In addition, these processes may include more or fewer operations, and these operations may be executed in sequence or in parallel. It should be noted that the descriptions of "first", "second", etc. in this article are used to distinguish different messages, devices, modules, etc., do not represent the order of precedence, and do not limit the "first" and "second" to be different types.

[0021] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of the present invention.

[0022] Figure 1 1 is a flow chart of a method for assisting in predicting immune-related adverse reactions provided by an embodiment of the present invention. Specifically, the method comprises the following steps: 101: Obtaining the tested cell data; In some embodiments, the term "subject" or "test subject" or "test sample" used herein refers to any animal (e.g., mammal), including but not limited to humans, non-human primates, rodents, etc., which will be the recipient of a specific treatment. Generally, the terms "subject" and "patient" are used interchangeably herein when referring to human subjects.

[0023] Preferably, the subject is a human.

[0024] In some embodiments, the sample to be tested is a patient undergoing clinical prognosis assessment.

[0025] In some embodiments, the cellular data is from a peripheral blood sample of a subject.

[0026] 102: Calculate the proportion of target cell subpopulations in mononuclear cells based on the cell data; the target cell subpopulations include CXCR3+CCR6+CD8+T cell subpopulations and NK cell subpopulations; In some embodiments, the calculation method of the proportion in 102 includes: interested cell subpopulation / total number of all cells.

[0027] 103: Calculating a prediction score based on the proportion of the target cell subpopulation; In some embodiments, the calculation of the prediction score in 103 is calculated by inputting the proportion of the target cell subpopulation into the auxiliary prediction model; Optionally, the method for constructing the auxiliary prediction model includes: Obtain a cell data set of training set samples; process the cell data set to obtain the proportion of each immune cell subpopulation in a single sample; screen out a target cell subpopulation from each immune cell subpopulation; input the proportion of the target cell subpopulation and whether the corresponding sample has an adverse immune reaction as a classification label into a machine learning model to obtain a predicted classification result, compare it with the classification label, optimize the model according to the comparison result, and obtain the auxiliary prediction model; Optionally, the method for processing the cell data set includes: quality control, clustering, subpopulation annotation, and calculating the proportion of each immune cell subpopulation in each sample.

[0028] In some embodiments, the method for screening the target cell subpopulation includes: correlation analysis of the correlation between the immune cell subpopulations, and screening out the immune cell subpopulations with collinearity greater than a second threshold as the target cell subpopulation; in some embodiments, the target cell subpopulations include: CXCR3+CCR6+CD8+T cell subpopulation, NK cell subpopulation, CXCR3+CCR6+CD4+T cell subpopulation.

[0029] Optionally, the collinearity is a spearman correlation coefficient; the second threshold is 0.8; In some embodiments, the method for screening the target cell subpopulation further includes: removing the cell subpopulation whose AUC value is less than a third threshold among the immune cell subpopulations whose collinearity is greater than the second threshold by a single factor screening method as the target cell subpopulation.

[0030] In some embodiments, the method for calculating the prediction score in 103 includes: the auxiliary prediction model includes: logit(P) = 0.758 * C14-0.119 * C20- 0.715; wherein, C14 is the proportion of CXCR3+CCR6+CD8+T cell subpopulation, C20 is the proportion of CD56dimNK cell subpopulation, and logit(P) is the prediction score.

[0031] 104: Outputting an auxiliary prediction result of the probability of the subject to have an immune-related adverse reaction according to the prediction score; when the prediction score is greater than a first threshold, outputting an auxiliary prediction result indicating that the subject has a high probability of having an immune-related adverse reaction; when the prediction score is less than the first threshold, outputting an auxiliary prediction result indicating that the subject has a low probability of having an immune-related adverse reaction.

[0032] In some embodiments, the first threshold is obtained through training of training set samples, and may be a specific threshold or an interval range. The specific form is not specifically limited in this embodiment.

[0033] In some embodiments, the auxiliary prediction results output based on the prediction score include but are not limited to paper or electronic report forms. The results are only obtained by the intelligent machine based on the analysis of relevant data of the subject and are only used as a reference for medical staff and are not used as a diagnosis result of the subject.

[0034] Figure 3 is a schematic diagram of a computer device provided by an embodiment of the present invention, such as Figure 3 As shown, the device may include: one or more processors, and one or more memories; wherein the memories store computer-readable codes, and when the computer-readable codes are run by the one or more processors, the method described above may be executed.

[0035] The processor in this embodiment can be an integrated circuit chip with signal processing capabilities. The above processor can be a general-purpose processor, a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components. The disclosed methods, operations and logic block diagrams in the embodiments of the present disclosure can be implemented or executed. The general-purpose processor can be a microprocessor or the processor can also be any conventional processor, etc., which can be an X86 architecture or an ARM architecture.

[0036] In general, various example embodiments of the present disclosure may be implemented in hardware or dedicated circuits, software, firmware, logic, or any combination thereof. Certain aspects may be implemented in hardware, while other aspects may be implemented in firmware or software that may be executed by a controller, microprocessor, or other computing device. When various aspects of the disclosed embodiments are illustrated or described as block diagrams, flow charts, or using some other graphical representation, it will be understood that the blocks, devices, systems, techniques, or methods described herein may be implemented in hardware, software, firmware, dedicated circuits or logic, general purpose hardware or controllers or other computing devices, or some combination thereof as non-limiting examples.

[0037] For example, the method or device according to the embodiment of the present disclosure may also be implemented by Figure 4 The architecture of the computing device 3000 shown in FIG. Figure 4 As shown, the computing device 3000 may include a bus 3010, one or more CPUs 3020, a read-only memory (ROM) 3030, a random access memory (RAM) 3040, a communication port 3050 connected to a network, an input / output component 3060, a hard disk 3070, etc. The storage device in the computing device 3000, such as ROM 3030 or hard disk 3070, may store various data or files used for processing and / or communication of the method provided by the present disclosure and program instructions executed by the CPU. The computing device 3000 may also include a user interface 3080. Of course, Figure 4 The architecture shown is only exemplary and can be omitted according to actual needs when implementing different devices. Figure 4 One or more components of a computing device are shown.

[0038] The embodiment of the present invention also provides a computer-readable storage medium, such as Figure 5As shown, it is a schematic diagram of a storage medium provided by an embodiment of the present invention, and a computer readable instruction 4010 is stored on the computer storage medium 4020. When the computer readable instruction 4010 is executed by the processor, the method according to the embodiment of the present disclosure described with reference to the above figures can be executed. The computer readable storage medium in the embodiment of the present disclosure can be a volatile memory or a non-volatile memory, or can include both volatile and non-volatile memories. The non-volatile memory can be a read-only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electrically erasable programmable read-only memory (EEPROM) or a flash memory. The volatile memory can be a random access memory (RAM), which is used as an external cache. By way of example and not limitation, many forms of RAM are available, such as static random access memory (SRAM), dynamic random access memory (DRAM), synchronous dynamic random access memory (SDRAM), double data rate synchronous dynamic random access memory (DDRSDRAM), enhanced synchronous dynamic random access memory (ESDRAM), synchronous link dynamic random access memory (SLDRAM), and direct memory bus random access memory (DR RAM). It should be noted that the memory of the methods described herein is intended to include, but is not limited to, these and any other suitable types of memory. It should be noted that the memory of the methods described herein is intended to include, but is not limited to, these and any other suitable types of memory.

[0039] The embodiments of the present disclosure further provide a computer program product or system, including a computer program, which implements the steps of the above method when executed by a processor.

[0040] In some embodiments, this embodiment also discloses a system for assisting in predicting immune-related adverse reactions, such as Figure 2 As shown, the system comprises: An acquisition module 201 is used or configured to acquire the cell data of a test subject; A cell subpopulation ratio calculation module 202 is used or configured to calculate the ratio of target cell subpopulations in mononuclear cells based on the cell data; the target cell subpopulations include CXCR3+CCR6+CD8+T cell subpopulations and NK cell subpopulations; A prediction score calculation module 203, used or configured to calculate a prediction score based on the proportion of the target cell subpopulation; The auxiliary result output module 204 is used to or is configured to output an auxiliary prediction result of the probability of the subject to have an immune-related adverse reaction based on the prediction score; when the prediction score is greater than a first threshold, an auxiliary prediction result indicating a high probability of the subject to have an immune-related adverse reaction is output; when the prediction score is less than the first threshold, an auxiliary prediction result indicating a low probability of the subject to have an immune-related adverse reaction is output. Specific embodiments

[0041] In this solution, there are 68 training set samples and 16 validation set samples. The model construction process is as follows: Figure 6 As shown, firstly, the mass spectrometry or single-cell data are subjected to quality control, clustering, and subgroup annotation, and the proportion of each immune cell subgroup is calculated for each patient, and the proportion of immune cell subgroup is used as the patient's feature and the input of the model. Correlation analysis obtains the correlation between features, and for subgroups with high collinearity (spearman correlation coefficient>0.8), the features with low univariate AUC are eliminated. The final model in the figure is the auxiliary prediction model described in this embodiment. Further univariate analysis suggests that the number of activated CXCR3+CCR6+ T cells, NK cells, and classical monocytes is independently correlated with adverse reactions to immunotherapy (such as Figure 7 Therefore, we integrated the CXCR3+CCR6+ positive cell subsets for modeling to improve the prediction performance of adverse reactions to immunotherapy.

[0042] Further, several machine learning techniques including random forests, support vector machines and other nonlinear modeling methods were evaluated, but due to the relative simplicity and robustness of generalized linear models, logistic regression (glm in R) was finally selected for modeling. Figure 7 We found three cell subsets closely related to immune-related adverse reactions, including C04 (CXCR3+CCR6+CD4+T), C14 (CXCR3+CCR6+CD8+T) and C20 (CD56dim NK). Correlation analysis showed that there was a high correlation between C14 and C04 subpopulations (r = 0.835, p < 0.001) (as shown in Figure 8 ), while the correlation with C20 was relatively low (p < 0.5). Then, we evaluated the prediction performance of C14 and C04 for adverse reactions by calculating the area under the receiver operating characteristic curve (AUROC). The results showed that the AUROC value of C14 was higher than that of C04 (0.76 vs. 0.73, as shown in Figure 2). Fig. 9 As shown, Fig. 9 A is the AUROC display diagram of C14. Fig. 9B is the AUROC display diagram of C04). At the same time, the prediction performance of the C20 cell subset for adverse reactions was evaluated by AUROC, and the results showed that the AUROC value of C20 was 0.74 (e.g. Fig.10 Finally, we selected C14 and C20 for further modeling.

[0043] We constructed a logistic regression model with the formula: logit(P) = 0.758 * C14-0.119 * C20-0.715, where C14 and C20 represent the proportion of these subpopulations in peripheral blood mononuclear cells. The AUROC of this model in the mass spectrometry training cohort reached 0.79, and the model scores of patients with adverse events were significantly higher than those of patients without adverse reactions (e.g. Fig.11 As shown, Fig.11 A is the AUROC display diagram of the model in the training set samples. Fig.11 B is a comparison of the scores of patients with adverse reactions and those without adverse reactions calculated using the model). The performance of the model is better than that of any single cell subset such as C04, C14 or C20 in predicting immune-related adverse reactions. In some embodiments, Fig.16 The AUROC display diagram of the prediction model constructed using three types of cells, C14, C04, and C20, in the training set samples provided by the embodiment of the present invention, and the AUROC values ​​thereof are Fig.11 The AUROC values ​​in A are the same, that is, the model with two cells achieved the same predictive value as the model with three cells, indicating that the model constructed with two cells in this case is more concise without reducing performance.

[0044] In order to verify the performance of the model, we selected a single-cell public dataset for model validation. We extensively annotated each immune cell subset and annotated 8 major categories (such as Fig.12 ), the cells were further clustered into 34 clusters (as shown in Fig.13 After analyzing the expression characteristics of these clusters, it was found that cluster 10 corresponds to CD8+CXCR3+ T cells, cluster 26 corresponds to CD4+CXCR3+ T cells, and cluster 2 corresponds to NK cells (as shown in Fig.14 As shown in Figure 2 ). Therefore, we designated cluster 10 of the single cell subsets as the equivalent of the C14 cell subset in mass spectrometry flow cytometry (CXCR3+CD8+T) and cluster 2 as the equivalent of C20 (CD56dimNK). Using the ratios of these two subsets as input, we predicted the occurrence of sAE (9 out of 16 samples) and obtained an AUROC of 0.75 (P=0.06) in the single cell validation cohort (as shown in Figure 2 ). Fig.15 As shown, Fig.15 A is the AUROC display diagram of the model in the validation set samples. Fig.15 (B) is a comparison chart of the scores of patients with adverse reactions and those without adverse reactions calculated using this model).

[0045] It was finally confirmed that the model had good predictive value for the occurrence of immune-related adverse reactions, and its predictive performance was better than that of any single subgroup.

[0046] Among them, CD8+T cells and CD4+T cells are two important types of cells in the immune system, and they each play a key role in the anti-tumor immune response. CD8+T cells, also known as cytotoxic T cells, are a type of immune cell that can directly recognize and kill tumor cells. They express T cell receptors (TCRs), bind to antigenic peptides on tumor cells, and initiate cytotoxic effects. The main function of CD8+T cells is to recognize and eliminate infected cells and tumor cells, and they are the main killing force of the immune system.

[0047] CD4+T cells, also known as helper T cells, are mainly responsible for regulating and coordinating immune responses. CD4+T cells activate CD8+T cells by presenting antigens to the latter, enhancing their anti-tumor ability. At the same time, CD4+T cells can also secrete a variety of cytokines, such as IL-2, IFN-γ and TNF-α, to directly kill tumor cells or enhance the function of other immune cells. CD4+T cells play an auxiliary and regulatory role in immune responses. They can promote the proliferation and differentiation of B cells, enhance the activity of other immune cells, and regulate the type and intensity of immune responses.

[0048] These two types of immune cells are closely related to the efficacy and adverse reactions of immunotherapy represented by PD-1 / PD-L1. Among these two types of cells, there are two special subtypes of cells, namely cells that highly express two molecules, CXCR3 and CCR6. CXCR3 is a G protein-coupled receptor and a member of the CXC chemokine receptor family. It is mainly expressed on a variety of immune cells, including T cells, natural killer cells (NK cells) and dendritic cells. CXCR3 binds to specific CXC chemokines, which can attract immune cells to migrate to sites of inflammation or infection.

[0049] CXCR3 plays an important role in immune responses, especially in fighting viral infections and certain types of tumor cells. It is involved in the recruitment and activation of immune cells, as well as the regulation of immune responses. For example, CXCR3 is crucial in regulating the migration and activation of T cells, which are essential for clearing infections and controlling tumor growth.

[0050] Studies have found that CXCR3 plays a role in a variety of diseases, including autoimmune diseases, viral infections, and tumors. In the tumor environment, the expression and function of CXCR3 may be altered, affecting the distribution and activity of immune cells, thereby affecting tumor development and treatment response.

[0051] Overall, CXCR3 is a key immune regulator, and its role in immune response, disease development, and treatment is gaining increasing attention. Further research will help to better understand the specific mechanisms of action of CXCR3 in health and disease states and develop new therapeutic approaches.

[0052] CCR6 is a member of the CC chemokine receptor family. It is a G protein-coupled receptor that is responsible for binding CC chemokines. These chemokines include CCL19, CCL20, and CCL21, which play a key role in the migration and localization of immune cells. The receptor encoded by the CCR6 gene is mainly expressed on a variety of immune cells, including T cells, B cells, macrophages, and dendritic cells. It plays a role in a variety of physiological and pathological processes, including: Immune cell homing: CCR6 is involved in regulating the migration of immune cells from the blood to tissues, especially in primary and memory immune responses. For example, CCR6 plays an important role in the migration of T cells to lymph nodes, which are key sites for antigen presentation and immune response.

[0053] Inflammation and Autoimmune Diseases: CCR6 may also play a role in the pathogenesis of inflammatory and autoimmune diseases. The binding of chemokines to CCR6 can attract immune cells to the site of inflammation, thereby exacerbating the inflammatory response.

[0054] Overall, CCR6 is an important immune regulator whose role in immune response, disease development and treatment is being discovered and understood. Further research will help to better utilize knowledge of CCR6 to improve disease treatment and management.

[0055] It should be noted that the flowcharts and block diagrams in the accompanying drawings illustrate the possible architecture, functions and operations of the systems, methods and computer program products according to various embodiments of the present disclosure. In this regard, each box in the flowchart or block diagram can represent a module, a program segment, or a part of a code, and the module, program segment, or a part of the code contains one or more executable instructions for implementing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in a different order from the order marked in the accompanying drawings. For example, two boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram and / or flowchart, and the combination of boxes in the block diagram and / or flowchart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0056] In general, various example embodiments of the present disclosure may be implemented in hardware or dedicated circuits, software, firmware, logic, or any combination thereof. Certain aspects may be implemented in hardware, while other aspects may be implemented in firmware or software that may be executed by a controller, microprocessor, or other computing device. When various aspects of the disclosed embodiments are illustrated or described as block diagrams, flow charts, or using some other graphical representation, it will be understood that the blocks, devices, systems, techniques, or methods described herein may be implemented in hardware, software, firmware, dedicated circuits or logic, general purpose hardware or controllers or other computing devices, or some combination thereof as non-limiting examples.

[0057] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0058] In the several embodiments provided in the present application, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be an indirect coupling or communication connection through some interfaces, devices or units, which can be electrical, mechanical or other forms.

[0059] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0060] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0061] The exemplary embodiments of the present disclosure described in detail above are merely illustrative and not restrictive. It should be understood by those skilled in the art that various modifications and combinations may be made to these embodiments or their features without departing from the principles and spirit of the present disclosure, and such modifications should fall within the scope of the present disclosure.

Claims

1. A method for assisting in predicting immune-related adverse reactions, characterized in that: The method comprises: 101, obtaining the tested cell data; 102, calculating the proportion of target cell subpopulations in mononuclear cells based on the cell data; the target cell subpopulations include CXCR3+CCR6+CD8+T cell subpopulations and NK cell subpopulations; 103, calculating a prediction score based on the proportion of the target cell subpopulation; 104. Output an auxiliary prediction result of the probability of the subject to have an immune-related adverse reaction according to the prediction score; when the prediction score is greater than a first threshold, output an auxiliary prediction result indicating that the subject has a high probability of having an immune-related adverse reaction; when the prediction score is less than the first threshold, output an auxiliary prediction result indicating that the subject has a low probability of having an immune-related adverse reaction.

2. The method for assisting in predicting immune-related adverse reactions according to claim 1, characterized in that: The prediction score calculated in 103 is obtained by inputting the proportion of the target cell subpopulation into the auxiliary prediction model; Optionally, the method for constructing the auxiliary prediction model includes: Obtain a cell data set of training set samples; process the cell data set to obtain the proportion of each immune cell subpopulation in a single sample; screen out a target cell subpopulation from each immune cell subpopulation; input the proportion of the target cell subpopulation and whether the corresponding sample has an adverse immune reaction as a classification label into a machine learning model to obtain a predicted classification result, compare it with the classification label, optimize the model according to the comparison result, and obtain the auxiliary prediction model; Optionally, the method for processing the cell data set includes: quality control, clustering, subpopulation annotation, and calculating the proportion of each immune cell subpopulation in each sample.

3. The method for assisting in predicting immune-related adverse reactions according to claim 1, characterized in that: The method for screening the target cell subpopulation comprises: performing correlation analysis on the correlation between the immune cell subpopulations, and screening out the immune cell subpopulations whose collinearity is greater than a second threshold as the target cell subpopulation; Optionally, the collinearity is a spearman correlation coefficient.

4. The method for assisting in predicting immune-related adverse reactions according to claim 3, characterized in that: The target cell subpopulations include: CXCR3+CCR6+CD8+T cell subpopulation, NK cell subpopulation, and CXCR3+CCR6+CD4+T cell subpopulation.

5. The method for assisting in predicting immune-related adverse reactions according to claim 3, characterized in that: The method for screening the target cell subpopulation also includes: removing the cell subpopulation whose AUC value is less than the third threshold value from the immune cell subpopulation whose collinearity is greater than the second threshold value by a single factor screening method as the target cell subpopulation.

6. The method for assisting in predicting immune-related adverse reactions according to claim 1, characterized in that: The method for calculating the prediction score in 103 includes: the auxiliary prediction model includes: logit(P) = 0.758 * C14-0.119 * C20-0.715; wherein C14 is the proportion of CXCR3+CCR6+CD8+T cell subpopulation, C20 is the proportion of CD56dimNK cell subpopulation, and logit(P) is the prediction score.

7. The method for assisting in predicting immune-related adverse reactions according to claim 1, characterized in that: The calculation method of the proportion in 102 includes: the subpopulation of cells of interest / the total number of all cells; Optionally, the cell data comes from a peripheral blood sample of the subject.

8. A computer device, characterized in that: The device comprises: a memory and a processor; the memory is used to store a computer program; the processor executes the computer program to implement the steps of the method according to any one of claims 1 to 7.

9. A computer-readable storage medium, characterized in that: A computer program is stored thereon, and when the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 7 are implemented.

10. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the steps of the method described in any one of claims 1 to 7 are implemented.

Images