Systems and methods for classifying states of implants
By analyzing biological samples of transplant recipients, using machine learning models to generate probability rejection scores, the accurate classification of organ transplant status is achieved, the problems of high diagnostic accuracy and subjectivity in the existing technology are solved, and the transplant status monitoring and Accuracy and consistency of treatment.
Patent Information
- Application Number
- CN202380036983.1
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Priority Date
- 2022-04-29
- Filing Date
- 2023-04-27
- Publication Date
- 2024-12-06
AI Technical Summary
Existing diagnostic methods for organ rejection after transplantation are highly invasive, highly risky and subjective, making it difficult to improve diagnostic accuracy, especially in monitoring transplant status and guiding immunosuppressive treatment.
By receiving the expression levels of multiple genes in the biological sample of the transplant recipient, a probability rejection score was generated, and predictive rejection classification was used to classify the transplant status as antibody-mediated rejection, T-cell-mediated rejection, Mixed or non-rejection, providing more accurate diagnostic support.
It improves the diagnostic accuracy and consistency of transplant status, reduces the difference in results, provides objective monitoring and treatment guidance, and helps optimize immunosuppressive treatment plans.
Smart Images

Figure CN119096302A_ABST
Abstract
Description
[0001] CROSS-REFERENCE TO RELATED APPLICATIONS
[0002] This application claims the benefit of U.S. Provisional Application No. 63 / 336,870, filed on April 29, 2022, which is hereby incorporated by reference in its entirety. Technical Field
[0003] The present disclosure generally relates to systems and methods for classifying the status of a transplant. Background Art
[0004] Transplantation of cells, tissues, parts, or whole organs is a life-saving medical procedure when an individual experiences acute organ failure or suffers from certain malignancies. Many organs, including but not limited to the heart, kidneys, liver, lungs, and pancreas, can be successfully transplanted, and one of the most commonly performed types of organ transplants today is the kidney transplant.
[0005] When non-autologous (allogeneic) cells, tissues or organs (allogeneic transplants) are transplanted into the recipient, the recipient's immune system will recognize the allograft as a foreign body and activate various mechanisms to reject the allograft. Therefore, it is necessary to suppress such immune responses medically to minimize the risk of transplant rejection. After transplantation, the status of the transplant can be monitored by a variety of clinical laboratory diagnostic tests, including histopathological evaluation of transplant biopsy tissue. The status can be monitored to guide clinical care and immunosuppressive treatment regimens. Although histopathological evaluation methods (e.g., biopsy) are the current standards for diagnosing rejection, due to the invasiveness of the procedure and its associated risks to transplantation, potential sampling errors and the subjectivity of histopathological interpretation, it is essential to improve its diagnostic accuracy in determining and monitoring the status of transplantation (such as organ transplantation).
[0006] As described in the present disclosure, what are needed are related systems and methods for classifying and monitoring the status of transplants (such as organ transplants) and improving the accuracy of diagnosis. Summary of the invention
[0007] The present disclosure relates to a method for classifying the state of a transplant. The method includes: receiving the expression levels of multiple genes in a biological sample from a transplant recipient; receiving multiple weight sets of the multiple genes; generating one or more probability rejection scores of one or more rejection tags based on the multiple weight sets and the expression levels; and assigning a predictive rejection classification to the biological sample of the transplant recipient based on one or more probability rejection scores, wherein the predictive rejection classification classifies the state of the transplant. In some embodiments, at least one gene in the multiple genes is associated with one or more of the following items: immune cell activation, organ-specific defense against pathogens, regulation of tissue and cell processes, or transcriptional regulation. In some embodiments, the predictive rejection classification classifies the state of the transplant as experiencing antibody-mediated rejection (ABMR), T cell-mediated rejection (TCMR), mixed ABMR+TCMR, or no rejection. In some embodiments, the predictive rejection classification classifies the state of the transplant as experiencing antibody-mediated rejection (ABMR). In some embodiments, the predictive rejection classification classifies the state of the transplant as experiencing T cell-mediated rejection (TCMR). In some embodiments, the predictive rejection classification classifies the state of the transplant as experiencing mixed ABMR+TCMR rejection. In some embodiments, the predictive rejection classification classifies the state of the transplant as experiencing no rejection. In some embodiments, generating one or more probability rejection scores for one or more rejection labels includes: for each rejection label in a plurality of rejection labels, generating a probability rejection score based on the plurality of weight sets and the expression level. In some embodiments, each weight set comprises a weight for a corresponding rejection label. In some embodiments, assigning a predictive rejection classification to a biological sample of a transplant recipient includes assigning a rejection label with the highest probability rejection score in a plurality of rejection labels as a predictive rejection classification. In some embodiments, a plurality of weight sets for a plurality of genes come from a machine learning model that is trained to receive a discovery data set of biological samples from a discovery cohort of transplant recipients, wherein the discovery data set includes gene expression levels and rejection classifications of a plurality of genes; analyzing the association between the gene expression levels of the discovery data set and the rejection classification of the discovery data set; identifying a gene subset of a plurality of genes from the discovery data set; and generating a plurality of weight sets based on the association between the gene expression levels of the discovery data set and the rejection classification of the discovery data set, wherein each weight set is associated with a gene in a gene subset. In some embodiments, the gene expression levels are analyzed by analyzing the nucleic acids in the biological samples of the discovery cohort. In some embodiments, the gene expression levels are analyzed by analyzing the RNA in the biological samples of the discovery cohort. In some embodiments, at least some of the rejection classifications of the discovery data set include antibody-mediated rejection (ABMR). In some embodiments, at least some of the rejection classifications of the discovery data set include T cell-mediated rejection (TCMR).In some embodiments, at least some of the rejection classifications of the discovery data set include mixed ABMR+TCMR rejection. In some embodiments, at least some of the rejection classifications of the discovery data set include no rejection. In some embodiments, the expression levels of one or more genes in the discovery data set are normalized relative to the gene expression levels of one or more reference genes. In some embodiments, the validation of the machine learning model is performed by: obtaining a validation data set from a biological sample of a validation cohort of transplant recipients, wherein the validation data set includes gene expression levels and rejection classifications of multiple genes; determining one or more computer-determined predictive rejection classifications from the validation data set; comparing one or more rejection classifications in the rejection classifications in the validation data set with one or more computer-determined predictive rejection classifications; and determining diagnostic accuracy based on the comparison, wherein the diagnostic accuracy is greater than a predetermined value. In some embodiments, the predetermined value is 60%, 70%, 80% or 90%.In some embodiments, at least one gene in the plurality of genes includes a gene selected from KIR_Inhibiting_Subgroup_1, IL7R, KLRK1, BK large T Ag, PLA1A, LGALS3, HLA-F, SMAD3, HLA-C, SH2D1B, CXCL11, GBP4, SFTPC, SOST, AGT, HSPA12B, NCAM1, NCR1, ITGA4, LCN2, HLA-DPB1, XCL1 / 2, BK VP1, COL4A1, ARG2, MCM6, CD59, CD69, SMARCA4, IL18, CMV UL83, SIGIRR, KIT, CD160, SERPINE1, TFRC, CCR7, HLA-B, CXCL8, AQP2, SOD2, SFTPB, HLA-DQA1, IFI6, HFE, MAPK12, GDF15, IFIT1, KLRF1, SERINC5, FOXP3, BCL2L1, FABP1, CCL21, LOX, ROBO4, MYBL1, AGR3, CXCR6, CX CL13, FCER1A, BTG2, CTLA4, CASP3, SPRY4, RAF1, MAPK13, IGF2R, RHOU, LYVE1, CD80, KAAG1, CCL18, EHD3, I L1RL1, CRIP2, TNFSF9, CDH5, CD8B, PRDM1, SIRPG, ABCA1, ADORA2A, RASSF9, JUN, COL4A4, TRAF4, PIN1, SOX7 , CFB, CFH, SFTPD, THBS1, AIRE, RAMP3, IL1R2, GNG11, RAPGEF5, DEFB1, GNLY, PHEX, ENG, BMP7, RELA, COL1A 1. PLAAT4, CD81, ICAM2, PLAT, CD40LG, NPHS2, IL33, CD58, TIPARP, TNC, PECAM1, C5, EGFR, CD2, BMP2, CTNN Genes identified in the group consisting of B1, MYB, CRHBP, MT2A, EEF1A1, BCL2, SLC19A3, VMP1, PSEN1, MAPK3, TFF3, TNFSF4, CD55, PDPN, IL17RB, IGHG2, CXCL12, CD207, MICA, MMP9, EOMES, EPO, NOS3, KLF2, KLF4, SLC4A1, P2RX4, CCL3 / L1, and HPRT1.In some embodiments, the transplant recipient has received a transplant comprising one or more of the following: a kidney transplant, a heart transplant, a lung transplant, a pancreas transplant, a liver transplant, an intestinal transplant, or a vascularized composite allograft transplant. In some embodiments, the transplant recipient has received an allograft or a xenograft. In some embodiments, the biological sample is an organ tissue sample. In some embodiments, the step of administering immunosuppressive therapy is included.
[0008] The present disclosure relates to a kit for classifying the status of transplantation. The kit may include: a kit for classifying the status of transplantation from KIR_Inhibiting_Subgroup_1, IL7R, KLRK1, BK large T Ag, PLA1A, LGALS3, HLA-F, SMAD3, HLA-C, SH2D1B, CXCL11, GBP4, SFTPC, SOST, AGT, HSPA12B, NCAM1, NCR1, ITGA4, LCN2, HLA-DPB1, XCL1 / 2, BK VP1, COL4A1, ARG2, MCM6, CD59, CD69, SMARCA4, IL18, CMV UL83, SIGIRR, KIT, CD160, SERPINE1, TFRC, CCR7, HLA-B, CXCL8, AQP2, SOD2, SFTPB, HLA-DQA1, IFI6, HFE, MAPK 12. GDF15, IFIT1, KLRF1, SERINC5, FOXP3, BCL2L1, FABP1, CCL21, LOX, ROBO4, MYBL1, AGR3, CXCR6, CXCL13, FCE R1A, BTG2, CTLA4, CASP3, SPRY4, RAF1, MAPK13, IGF2R, RHOU, LYVE1, CD80, KAAG1, CCL18, EHD3, IL1RL1, CRIP2, TNFSF9, CDH5, CD8B, PRDM1, SIRPG, ABCA1, ADORA2A, RASSF9, JUN, COL4A4, TRAF4, PIN1, SOX7, CFB, CFH, SFTPD, THBS1, AIRE, RAMP3, IL1R2, GNG11, RAPGEF5, DEFB1, GNLY, PHEX, ENG, BMP7, RELA, COL1A1, PLAAT4, CD81, ICAM2 , PLAT, CD40LG, NPHS2, IL33, CD58, TIPARP, TNC, PECAM1, C5, EGFR, CD2, BMP2, CTNNB1, MYB, CRHBP, MT2A, EEF1A 1. One or more probe sets, reagents, controls and instructions for use that are specific for one or more genes identified in the group consisting of BCL2, SLC19A3, VMP1, PSEN1, MAPK3, TFF3, TNFSF4, CD55, PDPN, IL17RB, IGHG2, CXCL12, CD207, MICA, MMP9, EOMES, EPO, NOS3, KLF2, KLF4, SLC4A1, P2RX4, CCL3 / L1 and HPRT1.In some embodiments, the kit also includes instructions for the following items: receiving the expression levels of multiple genes in a biological sample from a transplant recipient; receiving multiple weight sets for the multiple genes; based on the multiple weight sets and the expression level, generating one or more probability rejection scores for one or more rejection tags; and assigning a predictive rejection classification to the biological sample of the transplant recipient based on the one or more probability rejection scores, wherein the predictive rejection classification classifies the state of the transplant. In some embodiments, the predictive rejection classification classifies the state of the transplant as experiencing antibody-mediated rejection (ABMR), T cell-mediated rejection (TCMR), mixed ABMR+TCMR or no rejection. In some embodiments, generating one or more probability rejection scores for one or more rejection tags includes: for each rejection tag in a plurality of rejection tags, generating a probability rejection score based on the multiple weight sets and the expression level. In some embodiments, each weight set includes a weight for a corresponding rejection tag. In some embodiments, the transplant recipient receives a transplant including one or more of the following items: a kidney transplant, a heart transplant, a lung transplant, a pancreas transplant, a liver transplant, an intestinal transplant, or a vascularized composite allograft transplant. In some embodiments, the transplant received by the transplant recipient is an allogeneic transplant or a xenograft. In some embodiments, the biological sample is an organ tissue sample. In some embodiments, assigning a predictive rejection classification to the biological sample of the transplant recipient includes assigning a rejection signature with the highest probability rejection score among the multiple rejection signatures as the predictive rejection classification.
[0009] The present disclosure relates to a system for classifying the state of a transplant. The system may include: a scoring unit, which is used to: receive the expression levels of multiple genes in a biological sample from a transplant recipient; receive multiple weight sets of the multiple genes; based on the multiple weight sets and the expression level, generate one or more probability rejection scores of one or more rejection tags; and based on the one or more probability rejection scores, assign a predictive rejection classification to the biological sample of the transplant recipient, wherein the predictive rejection classification classifies the state of the transplant. In some embodiments, at least one gene in the multiple genes is associated with one or more of the following items: immune cell activation, organ-specific defense against pathogens, regulation of tissue and cell processes, or transcriptional regulation. In some embodiments, the predictive rejection classification classifies the state of the transplant as experiencing antibody-mediated rejection (ABMR), T cell-mediated rejection (TCMR), mixed ABMR+TCMR, or no rejection. In some embodiments, the predictive rejection classification classifies the state of the transplant as experiencing antibody-mediated rejection (ABMR). In some embodiments, the predictive rejection classification classifies the state of the transplant as experiencing T cell-mediated rejection (TCMR). In some embodiments, the predictive rejection classification classifies the state of the transplant as experiencing mixed ABMR+TCMR rejection. In some embodiments, the predictive rejection classification classifies the state of the transplant as experiencing no rejection. In some embodiments, generating one or more probability rejection scores for one or more rejection labels includes: for each rejection label in a plurality of rejection labels, generating a probability rejection score based on the plurality of weight sets and the expression level. In some embodiments, each weight set comprises a weight for a corresponding rejection label. In some embodiments, assigning a predictive rejection classification to a biological sample of a transplant recipient includes assigning a rejection label with the highest probability rejection score in a plurality of rejection labels as a predictive rejection classification. In some embodiments, a plurality of weight sets for a plurality of genes come from a machine learning model that is trained to receive a discovery data set of biological samples from a discovery cohort of transplant recipients, wherein the discovery data set includes gene expression levels and rejection classifications of a plurality of genes; analyzing the association between the gene expression levels of the discovery data set and the rejection classification of the discovery data set; identifying a gene subset of a plurality of genes from the discovery data set; and generating a plurality of weight sets based on the association between the gene expression levels of the discovery data set and the rejection classification of the discovery data set, wherein each weight set is associated with a gene in a gene subset. In some embodiments, the gene expression levels are analyzed by analyzing nucleic acids in the biological samples of the discovery cohort. In some embodiments, the gene expression levels are analyzed by analyzing RNA in the biological samples of the discovery cohort. In some embodiments, at least some of the rejection classifications of the discovery data set include antibody-mediated rejection (ABMR).In some embodiments, at least some of the rejection classifications of the discovery data set include T cell-mediated rejection (TCMR). In some embodiments, at least some of the rejection classifications of the discovery data set include mixed ABMR+TCMR rejection. In some embodiments, at least some of the rejection classifications of the discovery data set include no rejection. In some embodiments, the expression levels of one or more genes in the multiple genes of the discovery data set are normalized relative to the gene expression levels of one or more reference genes. In some embodiments, the validation of the machine learning model is performed in the following manner: a validation data set is obtained from a biological sample of a validation cohort of a transplant recipient, wherein the validation data set includes gene expression levels and rejection classifications of multiple genes; one or more computer-determined predictive rejection classifications are determined from the validation data set; one or more rejection classifications in the rejection classifications in the validation data set are compared with one or more computer-determined predictive rejection classifications; and diagnostic accuracy is determined based on comparison, wherein the diagnostic accuracy is greater than a predetermined value. In some embodiments, the predetermined value is 60%, 70%, 80% or 90%.In some embodiments, at least one gene in the plurality of genes includes a gene selected from KIR_Inhibiting_Subgroup_1, IL7R, KLRK1, BK large T Ag, PLA1A, LGALS3, HLA-F, SMAD3, HLA-C, SH2D1B, CXCL11, GBP4, SFTPC, SOST, AGT, HSPA12B, NCAM1, NCR1, ITGA4, LCN2, HLA-DPB1, XCL1 / 2, BK VP1, COL4A1, ARG2, MCM6, CD59, CD69, SMARCA4, IL18, CMV UL83, SIGIRR, KIT, CD160, SERPINE1, TFRC, CCR7, HLA-B, CXCL8, AQP2, SOD2, SFTPB, HLA-DQA1, IFI6, HFE, MAPK12, GDF15, IFIT1, KLRF1, SERINC5, FOXP3, BCL2L1, FABP1, CCL21, LOX, ROBO4, MYBL1, AGR3, CXCR6, CX CL13, FCER1A, BTG2, CTLA4, CASP3, SPRY4, RAF1, MAPK13, IGF2R, RHOU, LYVE1, CD80, KAAG1, CCL18, EHD3, I L1RL1, CRIP2, TNFSF9, CDH5, CD8B, PRDM1, SIRPG, ABCA1, ADORA2A, RASSF9, JUN, COL4A4, TRAF4, PIN1, SOX7 , CFB, CFH, SFTPD, THBS1, AIRE, RAMP3, IL1R2, GNG11, RAPGEF5, DEFB1, GNLY, PHEX, ENG, BMP7, RELA, COL1A 1. PLAAT4, CD81, ICAM2, PLAT, CD40LG, NPHS2, IL33, CD58, TIPARP, TNC, PECAM1, C5, EGFR, CD2, BMP2, CTNN Genes identified in the group consisting of B1, MYB, CRHBP, MT2A, EEF1A1, BCL2, SLC19A3, VMP1, PSEN1, MAPK3, TFF3, TNFSF4, CD55, PDPN, IL17RB, IGHG2, CXCL12, CD207, MICA, MMP9, EOMES, EPO, NOS3, KLF2, KLF4, SLC4A1, P2RX4, CCL3 / L1, and HPRT1.In some embodiments, the transplant recipient has received a transplant comprising one or more of the following: a kidney transplant, a heart transplant, a lung transplant, a pancreas transplant, a liver transplant, an intestinal transplant, or a vascularized composite allograft transplant. In some embodiments, the transplant recipient has received an allograft or a xenograft. In some embodiments, the biological sample is an organ tissue sample. BRIEF DESCRIPTION OF THE DRAWINGS
[0010] Figure 1 An example system for classifying the status of a transplant is shown, according to an embodiment of the present disclosure, the system being applied to a biological sample from a transplant recipient.
[0011] Figure 2 A flow chart illustrating an example method for classifying the status of an organ transplant according to an embodiment of the present disclosure is shown.
[0012] Figure 3 An example system for providing expression levels of multiple genes and multiple weight sets according to an embodiment of the present disclosure is shown.
[0013] Figure 4 A flowchart of an example method performed by a machine learning model according to an embodiment of the present disclosure is shown.
[0014] Figure 5 A diagram of an example discovery dataset and a validation dataset is shown, according to an embodiment of the present disclosure.
[0015] Figure 6 A table illustrating an example discovery data set according to an embodiment of the present disclosure is shown.
[0016] Figure 7 A table showing example weight sets for a subset of genes according to an embodiment of the present disclosure is shown.
[0017] Figure 8 A table illustrating an example validation dataset according to an embodiment of the present disclosure is shown.
[0018] Fig. 9A and Fig. 9B An example graph of the diagnostic accuracy of a predictive rejection classification is shown, according to an embodiment of the present disclosure.
[0019] Fig.10 An example apparatus is shown that implements the systems and methods disclosed herein, according to an embodiment of the present disclosure. DETAILED DESCRIPTION
[0020] The present disclosure relates to systems, kits and methods for classifying the status of a transplant. The status of a transplant can be classified based on the expression levels of multiple genes in a biological sample of a transplant recipient. The status of a transplant can also be classified based on a predictive rejection classification. Examples of predictive rejection classifications may include, but are not limited to, antibody-mediated rejection (ABMR), T-cell-mediated rejection (TCMR), mixed ABMR+TCMR and no rejection. The predictive rejection classification can be assigned based on a probabilistic rejection score. In some embodiments, a probabilistic rejection score can be assigned to each rejection label. In some embodiments, the rejection label with the highest probabilistic rejection score in the multiple rejection labels is assigned to the predictive rejection classification. Non-limiting rejection labels may include ABMR, TCMR, mixed ABMR+TCMR and no rejection. The probabilistic rejection score can be generated for each rejection label based on multiple weight sets and the expression level of the gene.
[0021] The computer determination result of the state of the transplant can be provided by a medical analysis tool that is convenient for the physician or medical expert to access. The medical analysis tool can display the state of the transplant in a user interface, report printing, etc. The physician or medical expert can use the computer-determined state as a supplement, or replace the physician or medical expert's assessment of the state of the transplant. The computer-determined state can be provided to the physician or medical expert as a probabilistic rejection score of a predictive rejection classification and / or one or more rejection labels. For example, the medical analysis tool can output ABMR, TCMR, mixed ABMR+TCMR or no rejection as a predictive rejection classification of a biological sample of a specific transplant recipient. As another non-limiting example, the medical analysis tool can output 30% ABMR, 50% TCMR, 15% mixed ABMR+TCMR and 5% no rejection as a probabilistic rejection score of a rejection label of a biological sample of a specific transplant recipient. The computer-determined state can be used as a physician or medical expert's guidance in a treatment plan, a monitoring protocol and / or a clinical diagnosis.
[0022] By quantifying the state of the transplant or classifying the state based on a quantified value (e.g., a probability rejection score), the state of the transplant can be made objective, consistent, and reliable. The disclosed computer-implemented method can be used to compare the state of a transplant at a certain point in time with the state of a transplant at another point in time. In addition, the state can also serve as a guide for determining treatment options and related timing. Systematic evaluation helps to better characterize the response of the transplant recipient to treatment and provide a reference for subsequent management and care. The results of the computer-implemented method may be more reproducible, thereby reducing the difference in results between transplant recipients, or the difference in results between different measurement times in a specific transplant recipient.
[0023] Multiple weight sets may correspond to multiple genes and may be received by a machine learning model. The machine learning model may generate multiple weight sets based on a discovery data set (a biological sample from a discovery cohort of a transplant recipient) and a rejection classification. The machine learning model may analyze the association between the gene expression level of the discovery data set and the rejection classification of the discovery data set. A subset of genes from multiple genes in the discovery data set may be identified. The machine learning model may generate multiple weight sets for the gene subset. In some embodiments, multiple weight sets may be based on the association between the gene expression level of the discovery data set and the rejection classification of the discovery data set. In some embodiments, each weight set may be associated with a gene in a gene subset. For example, the first weight set for no rejection, ABMR, TCMR, and mixed ABMR+TCMR is 100.0, 0.0, 0.0, and 0.0, which may be associated with gene KIR_Inhibiting_Subgroup_1.
[0024] The following description is presented to enable those skilled in the art to make and use various embodiments. Descriptions of specific devices, techniques, and applications are provided only as examples. These examples are only used to provide background information to help understand the examples. Therefore, for those of ordinary skill in the art, the implementation of the examples may not rely on some or all of the specific details. Other applications are also possible, so the following examples should not be considered restrictive. For those of ordinary skill in the art, various modifications to the examples described herein will be apparent, and without departing from the essence and scope of the various embodiments, the general principles defined herein may be applied to other examples and applications. Therefore, the various embodiments are not intended to be limited to the examples described herein, but should be given a scope consistent with the claims.
[0025] Various techniques and process steps will be described in detail, with reference to the examples of the accompanying diagrams. In the following description, numerous specific details are listed to provide a comprehensive understanding of one or more aspects and / or features described or mentioned herein. However, for those of ordinary skill in the art, the implementation of one or more aspects and / or features described or mentioned herein may not rely on these specific details. In other cases, well-known process steps and / or structures are not described in detail to avoid obscuring certain aspects and / or features described or mentioned herein.
[0026] In the following description of the examples, reference is made to the accompanying drawings, which are part of the present disclosure and show by way of illustration specific examples that can be implemented. It should be understood that other examples can be used and structural changes can be made without departing from the scope of the disclosed examples.
[0027] The terms used in the various embodiments described herein are only used to describe specific embodiments and are not intended to be limiting. As used in the specification and the appended claims describing the various embodiments, the singular forms of "one", "a kind of" and "the" are also intended to include plural forms, unless the context clearly indicates otherwise different. It should be understood at the same time that the term "and / or" as used herein refers to and encompasses any and all possible combinations of one or more of the listed related items. It is further understood that the terms "including", "comprising", "consisting of" and / or "consisting of" are used in this specification to indicate the presence of the features, wholes, steps, operations, elements and / or components, but do not exclude the presence or addition of one or more other features, integers, steps, operations, elements, components and / or their groups.
[0028] As used herein, the term "sample" or "biological sample" refers to any sample obtained from a transplant recipient, including but not limited to biopsy tissue and / or cells, whole blood, plasma, serum, lymph, peripheral blood mononuclear cells, buccal swab, saliva, or urine.
[0029] The term "transplantation" includes solid organ transplantation and cavity organ transplantation (e.g., gastrointestinal transplantation from allogeneic, i.e., non-autologous, same species), or cross-species transplantation from a heterogeneous source, such as xenotransplantation or xenograft. The term "transplantation" also includes cell transplantation, such as hematopoietic stem cells, islet cells, pluripotent cells, skin tissue, skin cells, immune cells, including but not limited to NK cells and T cells, derived from allogeneic or xenogeneic sources. The term "transplantation" also includes autologous transplantation, i.e., cell transplantation of self-origin (e.g., including transplantation of autologous cells from the recipient), including autologous cells that have been genetically engineered before being re-administered to the recipient. The terms "transplantation" and "allogeneic transplantation" are used interchangeably herein, and their meanings include xenografts. "Transplantation" refers to any transplantation alone or in combination with one or more transplants.
[0030] As used herein, the term "solid organ transplant" refers to the transplantation of any solid organ, including but not limited to kidney transplantation, heart transplantation, lung transplantation, liver transplantation, pancreas transplantation, vascularized composite allograft transplantation, or a combination of the foregoing.
[0031] As used herein, the term "gene cluster" or "cluster" refers to two or more gene groups with related gene expression patterns (eg, gene expression levels with correlated or associated levels or degrees).
[0032] As used herein, the term "TCMR" refers to cell or T cell-mediated (allogeneic or xenograft) rejection, including but not limited to acute active cell or T cell-mediated rejection, chronic active cell or T cell-mediated rejection, and chronic stable cell or T cell-mediated rejection.
[0033] As used herein, the term "ABMR" refers to antibody-mediated (allogeneic or xenograft) rejection, including but not limited to acute active antibody-mediated rejection, chronic active antibody-mediated rejection, and chronic stable antibody-mediated rejection.
[0034] The terms "mixed rejection" and "mixed ABMR+TCMR" refer to rejections that exhibit characteristics of both ABMR and TCMR.
[0035] As used herein, the terms "no rejection" and "non-rejection" refer to a state characterized by the absence of biopsy-confirmed ABMR, TCMR and / or mixed ABMR+TCMR, or the absence of significant rejection-related clinical symptoms (e.g., elevated serum creatinine levels, decreased estimated glomerular filtration rate, abnormal echocardiogram results, or other clinical issues that may indicate a clinical need for a biopsy). As used herein, the terms "no rejection" and "non-rejection" may also refer to a state characterized by low levels of immune activity, indicating that the immune system is dormant or quiescent.
[0036] As used herein, the term "nucleic acid" refers to linear or branched, single-stranded or double-stranded RNA or DNA or a hybrid thereof. The term also encompasses RNA / DNA hybrids.
[0037] As used herein, the term "gene" refers to a nucleic acid (eg, DNA or RNA) sequence that contains a coding sequence required to produce an RNA or polypeptide. A polypeptide may be encoded by the entire coding sequence or any portion thereof.
[0038] As used herein, the term "gene expression" refers to the generation of a transcription or translation product of a gene (e.g., total RNA, mRNA, splice variant mRNA, or polypeptide). Unless otherwise clearly indicated by the context, gene expression levels can be measured at the RNA and / or polypeptide levels. The measurement of gene expression can indicate the presence of transplant rejection, or indicate the possibility of transplant rejection, characterized by increased activity of immune system cells; or indicate the absence of transplant rejection, or indicate the absence of the possibility of transplant rejection, characterized by immune system cells being in a dormant state, manifested as a lack of immune activity or a low level of immune activity. Gene expression measurements are optionally normalized relative to the gene expression levels of one or more reference genes, and can be used to calculate a probability rejection score to indicate the possibility of the presence or absence of transplant rejection. Such probability rejection scores can be used to predict the possibility of clinical outcomes (e.g., predicting the possibility of transplant rejection or the possibility of "no rejection" in a transplant recipient). For example, such probability rejection scores will enable treating physicians or medical experts to identify transplant recipients with a high probability of "no rejection", so there is no need to adjust (e.g., increase, decrease, change or start) their immunosuppressive therapy; or identify recipients with a high probability of transplant rejection, so it is necessary to adjust their immunosuppressive therapy. The probabilistic rejection score can serve as the basis for assigning a predictive rejection classification to categorize the status of the transplant.
[0039] The term "machine-readable medium" as used herein refers to a single medium and multiple media (e.g., a centralized or distributed database and / or associated caches and servers) storing one or more instruction sets, and includes any medium capable of storing, encoding, or carrying instruction sets for execution by a device and causing the device to perform any of the methods and more operations described in this disclosure. The term "machine-readable medium" as used herein includes, but is not limited to, solid-state memories, optical and magnetic media, and carrier signals.
[0040] Example system for classifying the status of a transplant recipient after transplantation
[0041] Figure 1 An example system 100 for classifying, determining, or evaluating the status of a transplant (e.g., an organ transplant) in a biological sample from a transplant recipient is shown in accordance with an embodiment of the present disclosure. Classifying, determining, and / or monitoring the status of a transplant can be valuable and informative to a treating physician or medical professional in clinical decision making regarding treatment of a transplant recipient (e.g., regarding whether to adjust (e.g., increase, decrease, change, or initiate) a transplant recipient's immunosuppression or anti-rejection therapy).
[0042] The system 100 may include an interface 160 and a scoring unit 170. Examples of the present disclosure may include some or all of the components shown in the figure, or other components not shown in the figure. The system 100 may be, for example, a medical analysis tool. A treating physician or medical expert may use the medical analysis tool to help monitor the status of a transplant recipient's transplant, and monitor and / or recommend adjustments to the immunosuppressive therapy administered to the transplant recipient. Monitoring the status of a transplant involves analyzing multiple aspects to provide useful information about the physiological state of the transplant. The method of the present disclosure may classify the status of a transplant by a predictive rejection classification 180. The predictive rejection classification 180 may indicate a diagnosis with the highest probability rejection score among multiple other diagnoses.
[0043] The interface 160 can receive expression levels of a plurality of genes 140 in a biological sample from a transplant recipient. In some embodiments, the expression levels can be provided as user input (e.g., input from a physician or medical professional). The scoring unit 170 can serve as a tool for assessing the status of a transplant. The scoring unit 170 can receive a plurality of weight sets 150 (e.g., from a machine learning model) and expression levels of a plurality of genes 140. The scoring unit 170 can assign a predictive rejection classification 180 to a biological sample of a transplant recipient.
[0044] In some embodiments, system 100 can be a kit for post-transplant monitoring by a treating physician or medical professional. The kit can classify the status of a transplant (e.g., an organ transplant) in a biological sample from a transplant recipient according to one or more methods disclosed herein. The kit can include a probe set specific to one or more genes in a plurality of genes.
[0045] Figure 2 A flow chart of an example method for classifying the state of a transplant, such as classifying an organ transplant after transplantation, is shown according to an embodiment of the present disclosure. Method 200 may include step 202, wherein the system 100 may receive expression levels of a plurality of genes. A plurality of genes may be from a biological sample of a transplant recipient (e.g., an organ transplant recipient). In some embodiments, the biological sample may be an organ tissue sample. A detailed discussion of expression levels will be provided below.
[0046] In step 204, the system may receive multiple weight sets for the multiple genes. For example, multiple weight sets may be received from a machine learning model. As discussed in more detail below, the machine learning model may be trained to generate multiple weight sets based on a discovery data set and corresponding rejection classifications. As a non-limiting example, each gene or subset of genes in the multiple genes may have a corresponding weight set. The generation of multiple weight sets will be discussed in more detail below.
[0047] In step 206, the system may use Figure 1 The scoring unit 170 in step 204 generates one or more probabilistic rejection scores for one or more rejection signatures. The probabilistic rejection score may be based on the multiple weight sets received in step 204 and the expression level received in step 202. The probabilistic rejection score for a rejection signature may be a percentage value (e.g., between 0% and 100%) indicating the contribution of the rejection type to the transplant (e.g., organ transplant) status (based on Figure 1 A higher probability rejection score may mean a higher contribution. For example, a rejection label may include ABMR, TCMR, mixed ABMR+TCMR, and no rejection. The probability rejection scores for ABMR, TCMR, mixed ABMR+TCMR, and no rejection for a biological sample (e.g., an organ transplant recipient) are 30%, 50%, 15%, and 5%, respectively. The highest percentage, 50%, may mean that the corresponding rejection label TCMR contributes more to the predictive rejection classification 180 than other rejection labels with lower percentages (e.g., the probability rejection score for ABMR is 30%). The generation of the probability rejection score will be discussed in more detail below.
[0048] In step 208, the system may assign a predictive rejection classification to a biological sample of a transplant recipient (e.g., an organ transplant recipient). The predictive rejection classification may classify the status of a transplant (e.g., an organ transplant). The system may assign one of a plurality of classifications or diagnoses to each biological sample (e.g., an organ tissue sample), such as four diagnoses including three different types of rejection and no rejection. The predictive rejection classification may include, but is not limited to, ABMR, TCMR, mixed ABMR+TCMR, or no rejection.
[0049] In some embodiments, the predictive rejection classification may be assigned based on one or more probability rejection scores. For example, the sum of the probability rejection scores may be equal to 1% or 100%. In some embodiments, the rejection label with the highest probability rejection score among the multiple rejection labels is assigned to the predictive rejection classification. Going back to the above example, with probability rejection scores of 30% ABMR, 50% TCMR, 15% mixed ABMR+TCMR, and 5% no rejection, the system may assign the predictive rejection classification to TCMR because TCMR has the highest probability rejection score of 50% among the multiple rejection labels. The assignment of predictive rejection classifications will be discussed in more detail below.
[0050] Embodiments of the present disclosure may include repeating one or more steps in method 200 and / or method 400 (discussed below). Although the description and illustrations show that specific steps of the method are performed in a particular order, the steps of the method may be performed in other orders not described or shown. In addition, embodiments of the present disclosure may include performing all, some, or none of the steps of method 200 and / or method 400, where appropriate. Further, although certain components, devices, or systems are described as performing the steps of method 200 and / or method 400, any suitable combination of components, devices, or systems (including combinations not explicitly disclosed) may be used to perform these steps.
[0051] As described above, system 100 (e.g., a medical analysis tool) can receive expression levels of multiple genes from a biological sample of a transplant recipient (e.g., an organ transplant recipient). In some embodiments, the expression levels can be used to generate one or more probabilistic rejection scores (e.g., Figure 2 206 of method 200), where the probabilistic rejection score can be used to assign a predictive rejection classification to the biological sample (e.g., Figure 2 208 of method 200). The probabilistic rejection score can be based on the expression levels of multiple genes and multiple weight sets.
[0052] Multiple weight sets may be generated by the machine learning model 330 (e.g., Figure 3 300 may include a biomarker unit 310, a database 320, and a machine learning model 330. The biomarker unit 310 may process and analyze one or more biological samples, including biological samples of transplant recipients from a discovery cohort (e.g., organ transplant recipients). In some embodiments, the biological sample may be an organ tissue sample. The database 320 may store the processing and analysis results performed by the biomarker unit 310. The machine learning model 330 may generate a plurality of weight sets 150, which may also be optionally stored in the database 320.
[0053] In some embodiments, before determining the expression levels of multiple genes in the biological sample of the transplant recipient, the biological sample can be processed using relevant devices (e.g., optical, immunofluorescence, and electron microscopy, etc.). For example, the transplant biopsy can be subjected to immunohistochemical staining of SV40 polyomavirus on formalin-fixed paraffin-embedded (FFPE) tissue, or immunofluorescence staining of C4d on unfixed tissue. One or more tissue sections in each FFPE kidney core biopsy tissue block can be dissected using a cutting tool (such as a slicer). The dissected tissue sections can be used directly or stored under conditions that maintain the integrity of nucleic acids (e.g., RNA), and to prevent degradation and / or contamination of the tissue sections until further processing, e.g., for RNA extraction.
[0054] The biomarker unit 310 may be configured to determine one or more features of a transplant recipient (e.g., an organ transplant recipient) biological sample. For example, the biomarker unit 310 may analyze the expression levels of multiple genes in the biological sample. The transplant recipient has received a transplant including one or more of the following: a kidney transplant, a heart transplant, a lung transplant, a pancreas transplant, a liver transplant, an intestinal transplant, or a vascularized composite allograft transplant. In some embodiments, the transplant that the transplant recipient may receive is an allograft or a xenograft. In some embodiments, the analysis of gene expression levels may include analyzing the association with a rejection classification (e.g., a discovery data set). In certain embodiments, the analysis of gene expression levels may include analyzing the association with ABMR. In other embodiments, the analysis of gene expression levels may include analyzing the association with TCMR. In certain embodiments, the analysis of gene expression levels may include analyzing based on association strength (e.g., low, medium, or high association strength), which is usually interpreted by those skilled in the art based on the statistical significance of the determined association strength.
[0055] According to embodiments of the present disclosure, example genes that may be associated with analyzing transplant rejection classifications, based on their gene expression levels, and therefore genes associated with the state of the transplantation of the transplant recipient, may include, but are not limited to, one or more genes associated with immune cell activation, organ-specific defense against pathogens, regulation of tissue and cellular processes, and / or transcriptional regulation. For example, in some embodiments, such genes may provide information about whether the transplant recipient experiences "no rejection" or active rejection, such as TCMR, ABMR, or mixed ABMR+TCMR, based on their gene expression levels. In some embodiments, such genes may provide information about the strength of association with one or more rejection classifications based on their gene expression levels. The same one or more information genes may be used for each transplant recipient; it may not be necessary to customize one or more information genes for different transplant recipients.
[0056] Table 1 lists non-limiting example informative genes associated with immune cell activation, organ-specific defense against pathogens, regulation of tissue and cellular processes, and / or transcriptional regulation; some of these genes belong to related gene clusters, as shown in Table 2, showing at least 0.6% or 60% correlation. Genes that show a correlation level or degree of at least 0.6% or 60% with the example informative genes described herein are also considered informative genes, at least based on their gene expression levels, providing information about whether a transplant recipient experiences "no rejection" or active rejection (e.g., TCMR, ABMR, or mixed ABMR+TCMR), and are considered to be within the scope of the present disclosure.
[0057] Table 1: Example informative gene list
[0058]
[0059]
[0060]
[0061]
[0062] Table 2: List of genes related to the example informative genes in Table 1
[0063]
[0064]
[0065]
[0066] Table 2 (continued)
[0067]
[0068]
[0069]
[0070] Table 2 (continued)
[0071]
[0072]
[0073] Table 2 (continued)
[0074]
[0075]
[0076] In some embodiments, if two or more genes show similar expression patterns in a group of samples from transplant recipients, it can be determined that they are related, some of which have experienced transplant rejection, while others have not. In some embodiments, when the expression levels of two or more genes increase or decrease to a similar degree in the same sample, it can be determined that they are related. Example methods for clustering based on gene expression patterns are described in, for example, Oyelade, J. et al., Bioinform Biol Insights. 2016; 10: 237–253, which is hereby incorporated by reference in its entirety. In some embodiments, clustering is based on genes, samples, and / or other variables, and is performed using various clustering methods, such as hierarchical clustering (HC), self-organizing maps (SOM), and / or K-means clustering.
[0077] In some embodiments, the plurality of genes associated with immune cell activation, organ-specific defense against pathogens, regulation of tissue and cellular processes, and / or transcriptional regulation may include 2 to 10, 11 to 20, 21 to 30, 31 to 40, 41 to 50, 51 to 60, 61 to 70, 71 to 80, 81 to 90, 91 to 100, 101 to 120, 121 to 150, 151 to 200, 201 to 250, 251 to 300, 301 to 400, 401 to 500, 501 to 600, 601 to 700, 701 to 800, 801 to 1000 or more genes.In some embodiments, at least one gene in the plurality of genes may include a gene selected from KIR_Inhibiting_Subgroup_1, IL7R, KLRK1, BK large T Ag, PLA1A, LGALS3, HLA-F, SMAD3, HLA-C, SH2D1B, CXCL11, GBP4, SFTPC, SOST, AGT, HSPA12B, NCAM1, NCR1, ITGA4, LCN2, HLA-DPB1, XCL1 / 2, BK VP1, COL4A1, ARG2, MCM6, CD59, CD69, SMARCA4, IL18, CMV UL83, SIGIRR, KIT, CD160, SERPINE1, TFRC, CCR7, HLA-B, CXCL8, AQP2, SOD2, SFTPB, HLA-DQA1, IFI6, HFE, MAPK12, GDF15, IFIT1, KLRF1, SERINC5, FOXP3, BCL2L1, FABP1, CCL21, LOX, ROBO4, MYBL1, AGR3, CXCR6, CX CL13, FCER1A, BTG2, CTLA4, CASP3, SPRY4, RAF1, MAPK13, IGF2R, RHOU, LYVE1, CD80, KAAG1, CCL18, EHD3, I L1RL1, CRIP2, TNFSF9, CDH5, CD8B, PRDM1, SIRPG, ABCA1, ADORA2A, RASSF9, JUN, COL4A4, TRAF4, PIN1, SOX7 , CFB, CFH, SFTPD, THBS1, AIRE, RAMP3, IL1R2, GNG11, RAPGEF5, DEFB1, GNLY, PHEX, ENG, BMP7, RELA, COL1A 1. PLAAT4, CD81, ICAM2, PLAT, CD40LG, NPHS2, IL33, CD58, TIPARP, TNC, PECAM1, C5, EGFR, CD2, BMP2, CTNN Genes identified in the group consisting of B1, MYB, CRHBP, MT2A, EEF1A1, BCL2, SLC19A3, VMP1, PSEN1, MAPK3, TFF3, TNFSF4, CD55, PDPN, IL17RB, IGHG2, CXCL12, CD207, MICA, MMP9, EOMES, EPO, NOS3, KLF2, KLF4, SLC4A1, P2RX4, CCL3 / L1, and HPRT1.
[0078] In some embodiments, at least one gene in the plurality of genes may include a gene associated with a gene determined to be associated with immune cell activation, organ-specific defense against pathogens, regulation of tissue and cellular processes, or transcriptional regulation.
[0079] In some embodiments, the biomarker unit 310 can provide gene expression levels using a biological sample (such as FFPE kidney allograft biopsy tissue, including nucleic acids) by testing a gene panel, which contains one or more informative genes from multiple genes associated with immune cell activation, organ-specific defense against pathogens, regulation of tissue and cellular processes, and / or transcriptional regulation. In some embodiments, the nucleic acid from the biological sample includes mRNA. In some embodiments, the nucleic acid from the biological sample includes total RNA. In some embodiments, nucleic acids (such as total RNA) can be extracted from a biological sample, such as from a tissue curl of an organ tissue sample. Various methods for extracting nucleic acids (such as mRNA or total RNA) are known in the art, such as methods described in the following literature: Sambrook et al., "Molecular Cloning: A Laboratory Manual" 4th edition (2014) Cold Spring Harbor Laboratory Press, Cold Spring Harbor, New York; Ausubel et al., "Current Protocols in Molecular Biology" (2010). Nucleic acid extraction can also be performed using commercial purification kits, buffer sets, and proteases, following the manufacturer's instructions or any suitable method. Once the nucleic acids are extracted, they can be frozen or otherwise stored under conditions that maintain integrity and prevent degradation and / or contamination of the nucleic acids, or used directly for downstream applications and analysis, such as analysis of gene expression levels of one or more informative genes. In some embodiments, gene expression levels can be determined by analyzing total RNA in a sample (e.g., using RNA sequencing). In some embodiments, gene expression levels can be determined by analyzing mRNA in a sample. In some embodiments, RNA can be fragmented and used as a template for synthesizing cDNA. The cDNA can then be 3' adenylated and 5' end-repaired. Sequencing adapters can be attached to the 3' adenylated and 5' end-repaired cDNA, and the cDNA attached to the adapter can then be amplified prior to sequencing. In some embodiments, gene expression levels are determined by quantifying RNA levels (e.g., mRNA transcript levels) without amplification and / or reverse transcription to cDNA, for example using a gene expression platform such as NanoString Technologies system. In some embodiments, the gene expression platform can quantify the mRNA transcript levels of one or more informative genes from a gene panel. As discussed in more detail below, a gene panel can be a subset of genes identified from a plurality of genes in a biological sample that is associated with immune cell activation, organ-specific defense against pathogens, regulation of tissue cell processes, and / or transcriptional regulation. In some embodiments, a gene expression platform can be used that does not need to be stored in RNA stabilization and storage reagents immediately after sample collection, such as by using the same biopsy core in a routine histopathology assessment. In some embodiments, FFPE organ tissue samples (e.g., renal allograft biopsy tissue samples) can be obtained from routine clinical pathology practice and used to determine gene expression levels. In some embodiments, FFPE organ tissue samples used to determine gene expression levels can be archived clinical samples, including older samples (e.g., samples from 5, 6, 10, 13 years ago, etc.). In some embodiments, a gene expression platform such as NanoString Technologies can be used. System to develop gene expression signatures for transplant rejection diagnosis in transplant recipients.
[0080] In some embodiments, database 320 may store multiple features, such as gene expression levels of multiple genes in biological samples (e.g., organ tissue samples) from transplant recipients, which may help determine the status of the transplant or transplant lesion scores (e.g., organ transplant lesion scores), which may be assigned by one or more pathologists (e.g., renal pathologists) when performing histopathological evaluation of biological samples (e.g., organ tissue samples) from kidney transplant recipients. In some embodiments, one or more lesion scores may be stored in database 320. In some embodiments, one or more rejection classifications may be stored in database 320, which may be assigned by one or more pathologists (e.g., renal pathologists) based on one or more lesion scores assigned when performing histopathological evaluation of biological samples (e.g., organ tissue samples). In some embodiments, one or more rejection classifications may be stored in database 320, which may be assigned by one or more pathologists (e.g., renal pathologists) based on one or more lesion scores alone or in combination with other laboratory test results. In some embodiments, one or more rejection classifications may be stored in database 320, which may be assigned based on one or more lesion scores alone or in combination with other laboratory test results, consistent with classification guidelines for human transplants, for example, "Banff 2019 classification guidelines for human organ transplants" (Mengel et al., (2019) Am J Transplant. 2020; 20:2305-2317.)
[0081] In some embodiments, the data stored in the database 320 may include a discovery data set of biological samples from a discovery cohort of a transplant recipient (e.g., an organ transplant recipient), and a validation data set of biological samples from a validation cohort of a transplant recipient (e.g., an organ transplant recipient). In some embodiments, one or more transplant recipients (in a discovery data set, a validation data set, or both) may have received an organ transplant including one or more of the following items: a kidney transplant, a heart transplant, a lung transplant, a pancreas transplant, a liver transplant, an intestinal transplant, or a vascularized composite allograft transplant. In some embodiments, the transplant that one or more transplant recipients may receive is an allograft or a xenograft. In some embodiments, the discovery data set may include the gene expression levels of multiple genes and the rejection classification of the discovery cohort biological samples. In some embodiments, the discovery data set may include the gene expression levels of multiple genes associated with immune cell activation, organ-specific defense against pathogens, regulation of tissue and cell processes, and / or transcriptional regulation. In some embodiments, the validation data set may include the gene expression levels of multiple genes and the rejection classification of the validation cohort biological samples. The discovery data set may also include the rejection classification of the discovery cohort biological samples. In some embodiments, the validation dataset may include gene expression levels of a plurality of genes associated with immune cell activation, organ-specific defense against pathogens, regulation of tissue and cellular processes, and / or transcriptional regulation.
[0082] In some embodiments, the discovery data set may include data from biological samples obtained from transplant recipients that exhibit a variety of histological findings (e.g., different types of rejection, non-diagnostic rejection from both renal allografts and native kidneys, etc.). For example, in some embodiments, at least some of the rejection classifications of the discovery data set may include ABMR. In some embodiments, at least some of the rejection classifications of the discovery data set may include TCMR. In some embodiments, at least some of the rejection classifications of the discovery data set may include mixed ABMR+TCMR. In some embodiments, at least some of the rejection classifications of the discovery data set may include no rejection.
[0083] Embodiments of the present disclosure may include systems and methods capable of distinguishing inflammatory conditions associated with renal allograft rejection from conditions caused by other pathological conditions unrelated to rejection (including various types of viral or bacterial infections, or various types of glomerular diseases). In some embodiments, the discovery data set may include data from biological samples (e.g., organ tissue samples, such as biopsy samples), which are derived from both native organs (e.g., native kidneys) and organ transplants (e.g., kidney transplants), and exhibit various types of inflammation, such as cytomegalovirus (CMV) or BK virus (BKV) nephropathy, acute pyelonephritis, diabetic nephropathy, etc.
[0084] The machine learning model 330 may be trained to generate multiple weight sets for use by the system 100 in generating one or more probability rejection scores and assigning predictive rejection classifications. In some embodiments, the machine learning model 330 may be trained to analyze the association of gene expression levels of a discovery data set with the rejection classification of the discovery data set. In some embodiments, the machine learning model 330 may narrow the gene set range (generating a weight set) by identifying a subset of genes (multiple informative genes from a discovery data set) based on the fitting process disclosed herein. In some embodiments, the machine learning model 330 may generate multiple weight sets for a subset of genes.
[0085] Figure 4 A flow chart of an exemplary method performed by a machine learning model according to an embodiment of the present disclosure is shown. In some embodiments, a plurality of weight sets of a plurality of information genes may come from a machine learning model trained to perform one or more steps of method 400. In some embodiments, method 400 may include receiving a discovery data set from, for example, database 320 in step 402. In some embodiments, the discovery data set may include gene expression levels and associated rejection classifications of biological samples of a discovery cohort of a transplant recipient (e.g., an organ transplant recipient). In some embodiments, the discovery data set may be data obtained by one or more units (such as biomarker unit 310).
[0086] For example, Figure 5 As shown, the discovery data set may include data related to multiple transplant tissue samples (e.g., organ tissue biopsies) of the discovery cohort, such as histopathological assessments, lesion scores, etc. In some embodiments, the system may perform quality control, such as using a predetermined threshold or expected range that is not exceeded, so that biological sample data that does not meet certain criteria (e.g., based on a predetermined threshold) may not be included in any subsequent evaluation or calculation. In some embodiments, an example criterion may include identifying genes with an expected range or not exceeding a predetermined threshold, such as related to gene normalization quality control, such as when identifying housekeeping genes for gene normalization. In certain embodiments, another example criterion may include identifying genes that meet certain performance criteria, such as related to assay efficiency, detection limit, or minimum detection threshold, such as setting a target threshold for detecting and quantifying a target, such as a performance criterion for a probe that detects a certain percentage of a targeted information gene, such as a detection threshold of 62%.
[0087] Figure 6A table of example discovery data sets is shown according to an embodiment of the present disclosure. In some embodiments, the biological samples of the discovery cohort may include biological samples assigned with (active or chronic) ABMR rejection classification. In some embodiments, the biological samples of the discovery cohort may include biological samples assigned with (various levels of acute) TCMR rejection classification. In some embodiments, the biological samples of the discovery cohort may include biological samples assigned with mixed ABMR+TCMR rejection classification. In some embodiments, the biological samples of the discovery cohort may include biological samples with a "no rejection" rejection classification (with various histological findings that are not diagnostic of any type of rejection, or lack one or more histological findings that are diagnostic of any type of rejection). In some embodiments, the "no rejection" biological samples of the discovery data set may include biological samples with or without various types of inflammation from native organs (e.g., native kidneys). In some embodiments, the "no rejection" biological samples of the discovery data set may include biological samples such as renal allograft biopsies without inflammation or with inflammation, such as viral infection-related inflammation (CMV or BKV).
[0088] In some embodiments, at least one informative gene among the plurality of informative genes of the discovery data set may be associated with one or more of: immune cell activation, organ-specific defense against pathogens, regulation of tissue and cellular processes, or transcriptional regulation.
[0089] In some embodiments, at least one of the multiple informative genes in the discovery data set may include KIR_Inhibiting_Subgroup_1, IL7R, KLRK1, BK large T Ag, PLA1A, LGALS3, HLA-F, SMAD3, HLA-C, SH2D1B, CXCL11, GBP4, SFTPC, SOST, AGT, HSPA12B, NCAM1, NCR1, ITGA4, LCN2, HLA-DPB1, XCL1 / 2, BK VP1, COL4A1, ARG2, MCM6, CD59, CD69, SMARCA4, IL18, CMV UL83, SIGIRR, KIT, CD160, SERPINE1, TFRC, CCR7, HLA-B, CXCL8, AQP2, SOD2, SFTPB, HLA-DQA1, IFI6, HFE, MAPK12, GDF15, IFIT1, KLRF1, SERINC5, FOXP3, BCL2L1, FABP1, CCL21, LOX, ROBO4, MYBL1, AGR3, CXCR6, CX CL13, FCER1A, BTG2, CTLA4, CASP3, SPRY4, RAF1, MAPK13, IGF2R, RHOU, LYVE1, CD80, KAAG1, CCL18, EHD3, I L1RL1, CRIP2, TNFSF9, CDH5, CD8B, PRDM1, SIRPG, ABCA1, ADORA2A, RASSF9, JUN, COL4A4, TRAF4, PIN1, SOX7 , CFB, CFH, SFTPD, THBS1, AIRE, RAMP3, IL1R2, GNG11, RAPGEF5, DEFB1, GNLY, PHEX, ENG, BMP7, RELA, COL1A 1. PLAAT4, CD81, ICAM2, PLAT, CD40LG, NPHS2, IL33, CD58, TIPARP, TNC, PECAM1, C5, EGFR, CD2, BMP2, CTNN Genes identified in the group consisting of B1, MYB, CRHBP, MT2A, EEF1A1, BCL2, SLC19A3, VMP1, PSEN1, MAPK3, TFF3, TNFSF4, CD55, PDPN, IL17RB, IGHG2, CXCL12, CD207, MICA, MMP9, EOMES, EPO, NOS3, KLF2, KLF4, SLC4A1, P2RX4, CCL3 / L1, and HPRT1.
[0090] In some embodiments, at least one of the multiple informative genes in the discovery data set may include a gene that is related to KIR_Inhibiting_Subgroup_1, IL7R, KLRK1, BK large T Ag, PLA1A, LGALS3, HLA-F, SMAD3, HLA-C, SH2D1B, CXCL11, GBP4, SFTPC, SOST, AGT, HSPA12B, NCAM1, NCR1, ITGA4, LCN2, HLA-DPB1, XCL1 / 2, BK VP1, COL4A1, ARG2, MCM6, CD59, CD69, SMARCA4, IL18, CMV UL83, SIGIRR, KIT, CD160, SERPINE1, TFRC, CCR7, HLA-B, CXCL8, AQP2, SOD2, SFTPB, HLA-DQA1, IFI6, HFE, MA PK12, GDF15, IFIT1, KLRF1, SERINC5, FOXP3, BCL2L1, FABP1, CCL21, LOX, ROBO4, MYBL1, AGR3, CXCR6, CXCL13, FCER1A, BTG2, CTLA4, CASP3, SPRY4, RAF1, MAPK13, IGF2R, RHOU, LYVE1, CD80, KAAG1, CCL18, EHD3, IL1RL1, CR IP2, TNFSF9, CDH5, CD8B, PRDM1, SIRPG, ABCA1, ADORA2A, RASSF9, JUN, COL4A4, TRAF4, PIN1, SOX7, CFB, CFH, S FTPD, THBS1, AIRE, RAMP3, IL1R2, GNG11, RAPGEF5, DEFB1, GNLY, PHEX, ENG, BMP7, RELA, COL1A1, PLAAT4, CD8 1. ICAM2, PLAT, CD40LG, NPHS2, IL33, CD58, TIPARP, TNC, PECAM1, C5, EGFR, CD2, BMP2, CTNNB1, MYB, CRHBP, MT Genes identified in the group consisting of 2A, EEF1A1, BCL2, SLC19A3, VMP1, PSEN1, MAPK3, TFF3, TNFSF4, CD55, PDPN, IL17RB, IGHG2, CXCL12, CD207, MICA, MMP9, EOMES, EPO, NOS3, KLF2, KLF4, SLC4A1, P2RX4, CCL3 / L1, and HPRT1 showed at least 0.6% or 60% correlation.
[0091] Back to Figure 4In step 404, the association between the gene expression levels of the discovery data set and the rejection classification of the discovery data set can be analyzed. For example, in some embodiments, a polynomial regression model can be used to fit the gene expression levels of the discovery data set to determine whether there is an association with the corresponding rejection classification. In some embodiments, the polynomial regression model can use regularized likelihood to estimate coefficients. In some embodiments, the gene expression levels can be analyzed by detecting and / or quantifying nucleic acids or RNA in the biological samples of the discovery cohort.
[0092] In some embodiments, the expression levels of one or more genes in the plurality of genes of the discovery data set can be normalized relative to the gene expression levels of one or more reference genes. In some embodiments, normalization can be performed using housekeeping genes. In some embodiments, normalization can be performed using normalization quality control indicators.
[0093] In step 406, a subset of genes from the plurality of genes in the discovery dataset may be identified. In an exemplary embodiment of the present disclosure, the plurality of genes in the discovery dataset represents more than 700 genes, and a subset of less than 200 genes is identified for subsequent predictive rejection classification.
[0094] In step 408, machine learning model 330 can generate multiple weight sets for this gene subset (from step 406).This multiple weight sets may be generated based on the association between the gene expression level of the discovery data set and the exclusion classification of the discovery data set.In some embodiments, each weight set may be associated with a gene in the gene subset.This multiple weight sets can be calculated using prediction models such as Lasso regularized regression, elastic network random forest, gradient boosting machine, k nearest neighbor or support vector machine.The process performed by the prediction model may involve fitting using cross validation (e.g., 10 times cross validation) to determine one or more hyper parameters.
[0095] Figure 7 A table of example weight sets for gene subsets according to embodiments of the present disclosure is shown. For example, for different exclusion labels: no exclusion, ABMR, TCMR, and mixed ABMR+TCMR, the KIR_Inhibiting_Subgroup_1 gene may have weights of 100, 0, 0, and 0, respectively, relative to other genes in multiple information genes. For another example, for different exclusion labels: no exclusion, ABMR, TCMR, and mixed ABMR+TCMR, the PLA1A gene may have weights of 65.1, 58.0, 58.0, and 84.6, respectively, relative to other genes in multiple information genes. As shown in the table, in some embodiments, each weight set includes weights for corresponding exclusion labels.
[0096] Embodiments of the present disclosure may include training a machine learning model. The machine learning model may be trained using a discovery data set of biological samples from a discovery cohort of transplant recipients (e.g., organ transplant recipients). The machine learning model may be trained to receive a discovery data set, analyze gene expression levels of the discovery data set, identify a subset of genes, and generate multiple weight sets for the subset of genes.
[0097] The machine learning model can be validated using a validation cohort to determine whether it has been trained according to certain criteria (e.g., diagnostic accuracy). In some embodiments, diagnostic accuracy above a predetermined value can be used as a criterion. In some embodiments, diagnostic accuracy can be determined based on comparing one or more rejection classifications in a data set with one or more computer-determined predictive rejection classifications.
[0098] In some embodiments, the dataset used to validate the machine learning model can be a validation dataset or cohort, such as Figure 5 and Figure 8 As shown. In some embodiments, the validation data set may include data from hundreds or thousands of biological samples (e.g., organ tissue samples of the validation cohort, such as biopsy samples). In some embodiments, the validation data set may be evaluated according to various quality control indicators to evaluate and ensure the consistency, reliability, and repeatability of the predicted rejection classification, which must be met before it can be used to validate the machine learning model later. In some embodiments, the biological samples of the validation cohort may include biological samples assigned an ABMR rejection classification. In some embodiments, the biological samples of the validation cohort may include biological samples assigned a TCMR rejection classification. In some embodiments, the biological samples of the validation cohort may include biological samples assigned a mixed ABMR+TCMR rejection classification. In some embodiments, the biological samples of the validation cohort may include biological samples assigned a "no rejection" rejection classification.
[0099] The computer-determined predictive rejection classification can be determined using a probability rejection score generated based on the expression levels of multiple genes with multiple weight sets to determine a validation data set, and the multiple weight sets are generated by the biological samples of the validation cohort through a machine learning model. In some embodiments, if the diagnostic accuracy exceeds a predetermined value, the computer-determined predictive classification will be acceptable. In some embodiments, the predetermined value may be 60%, 70%, 80% or 90%. The diagnostic accuracy may represent the percentage of predictive rejection classifications in the validation data set that match the computer-determined predictive rejection classification (determined according to the validation data set).
[0100] In some embodiments, the diagnostic accuracy may vary for different predictive rejection categories and / or different data sets. Fig. 9AThe diagnostic accuracy of a discovery data set is shown according to an embodiment of the present disclosure. For example, for a discovery data set, the overall diagnostic accuracy may be 84.6%. In some embodiments, the performance characteristics of the disclosed systems and methods, such as sensitivity and specificity, may vary for different predictive rejection classifications and / or different data sets. In some example embodiments, the sensitivity and specificity of the disclosed systems and methods are 93.7% and 89.9%, respectively, regardless of the predictive rejection classification. In some example embodiments, the sensitivity of the ABMR or TCMR predictive rejection classification exceeds 85%. In some example embodiments, the sensitivity of the mixed ABMR+TCMR predictive rejection classification is about 50%. In some example embodiments, the specificity of each of the three different types of rejection (e.g., ABMR, TCMR, mixed ABMR+TCMR) exceeds 90%.
[0101] In some embodiments, the performance characteristics of the disclosed systems and methods, such as diagnostic accuracy, sensitivity, specificity, may vary for different predictive rejection classes and / or different data sets. Fig. 9B The diagnostic accuracy of the validation data set according to the example embodiments of the present disclosure is shown. In some example embodiments, the diagnostic accuracy is 79.7%, while the sensitivity and specificity are 85.2% and 88.1%, respectively, regardless of the predictive rejection classification. In some example embodiments, the sensitivity of the predictive rejection classification of ABMR, TCMR and mixed ABMR+TCMR is 80.4%, 70.5% and 44.4%, respectively. In some embodiments, the specificity of each rejection in three different types of rejection (e.g., ABMR, TCMR, mixed ABMR+TCMR) may exceed 90%. The high specificity of predicting transplant rejection indicates that the disclosed system and method have potential in successfully and reproducibly distinguishing transplant rejection from other rejection-related conditions that may show clinical parameters similar to rejection-related parameters, such conditions including acute and / or chronic inflammatory diseases and / or systemic infections. In a demonstration of improved diagnostic accuracy, the disclosed systems and methods can be used to differentiate between transplant rejection and inflammatory conditions and / or infectious conditions unrelated to rejection (e.g., diabetic nephropathy, acute pyelonephritis, BK virus nephropathy) in transplant recipients who present with some clinical problems and / or clinical parameters suggestive of transplant rejection but who, by accurately assigning a predictive rejection classification of "no rejection," actually have inflammatory conditions and / or infectious conditions unrelated to rejection.
[0102] If the machine learning model is not adequately trained (e.g., the diagnostic accuracy is not greater than a predetermined value), the training data (e.g., the discovery data set) may be revised to provide feedback to the model. In some embodiments, the output of the machine learning model between training iterations may be evaluated by a medical expert or treating physician to determine which data in the training data should be revised. The treating physician or medical expert may revise the data in certain potential areas of improvement, such as the weights of the expression levels of multiple genes.
[0103] Example Administration of Immunosuppressive Therapy
[0104] Immunosuppressive therapy generally refers to administering immunosuppressants to transplant recipients or other therapeutic agents that inhibit the immune response of transplant recipients. Example immunosuppressants may include, for example, calcineurin inhibitors, mTor inhibitors, anticoagulants, antimalarials, cardiovascular drugs (including but not limited to ACE inhibitors and beta-blockers), nonsteroidal anti-inflammatory drugs (NSAIDs), aspirin, azathioprine, B7RP-1-fc, buquina sodium, campath-1H, celecoxib, chloroquine, corticosteroids, warfarin, cyclophosphamide, cyclosporin A, DHEA, deoxyspergualin, dexamethasone, diclofenac, diflunisal, etodolac, everolimus, FK778, piroxicam, fenoprofen, flurbiprofen, heparin, hydralazine, hydroxychloroquine, CTLA-4 or LFA3 immunoglobulins, ibuprofen, indomethacin, ISAt x-247, ketoprofen, ketorolac, leflunomide, meclofenamic acid, mefenamic acid, mikrin, 6-mercaptopurine, meloxicam, methotrexate, mizoribine, mycophenolate mofetil, naproxen, oxaprozin, hydroxychloroquine, NOX-100, prednisone, methylprednisolone, rapamycin (sirolimus), sulindac, tacrolimus (FK506), thymocyte globulin, tolmetin, tripelimus, UO126, and antibodies, including, for example, alpha lymphocyte antibodies, adalimumab, anti-CD3, anti-CD25, anti-CD52, anti-IL2R, anti-TAC antibodies, basiliximab, daclizumab, etanercept, hu5C8, infliximab, OKT4, natalizumab, and any combination thereof. Immunosuppressive therapy may be adjusted based on the status of the transplant classified as experiencing "no rejection," ABMR, TCMR, or mixed ABMR+TCMR rejection. For example, high-dose steroid therapy may be initiated or the dose and / or frequency of maintenance immunosuppressive therapy may be increased based on the status of the transplant classified as experiencing TCMR. For example, plasma exchange or intravenous immunoglobulin (IVIg) may be initiated based on the status of the transplant classified as experiencing ABMR.
[0105] In some embodiments, no change in the status of the transplant (e.g., as shown by no change in the predictive rejection classification) may indicate that no adjustment is needed to the immunosuppressive therapy administered to the transplant recipient, or that the immunosuppressive therapy administered may be maintained. The decision whether to maintain the immunosuppressive therapy administered to the transplant recipient may be based on additional clinical factors, such as the health status, age, and comorbidities of the transplant recipient.
[0106] In some embodiments, the adjustment of immunosuppressive therapy includes changing the type, form or frequency of immunosuppressive therapy or other transplant-related therapy administered to the transplant recipient. In some embodiments, when the transplant recipient is not receiving immunosuppressive therapy, the methods of the present disclosure may indicate the need to start administering immunosuppressive therapy to the transplant recipient.
[0107] Other transplantation-related therapies include administering treatment or therapy other than transplantation or immunosuppressive therapy to the transplant recipient to promote the survival of the transplant or treat transplantation-related symptoms (e.g., cytokine release syndrome, neurotoxicity). Examples of other transplantation-related therapies include, but are not limited to, administering antibodies, antigen-targeting ligands, non-immunosuppressive drugs, and other agents that stabilize or destabilize components of the transplant that are critical to the activity of the transplant or directly activate or inhibit the activity of one or more transplants. These activities may include the ability to induce an immune response, recognize specific antigens, replicate, and / or repair damaged tissue. Adjusting immunosuppressive therapy may be combined with adjusting, starting, or stopping other transplantation-related therapies.
[0108] The disclosed method can classify the status of a transplant (e.g., an organ transplant). The status of the transplant can be used to inform the need to adjust the monitoring of the transplant recipient. In general, changes in the predictive rejection classification over time may be instructive for determining whether it is necessary to adjust the monitoring of the transplant recipient. In some embodiments, as described above, classifying the status of the transplant is instructive for determining whether it is necessary to adjust the monitoring of the transplant recipient.
[0109] Depending on the status of the transplant, the monitoring of the transplant recipient may be adjusted accordingly. For example, the monitoring may be adjusted by appropriately increasing or decreasing the frequency of monitoring. Monitoring may be adjusted by changing the means of monitoring, for example, by changing the indicators used to monitor the transplant recipient.
[0110] Example system for classifying the status of a transplant
[0111] The systems and methods discussed herein may be implemented via a device. Fig.10An example apparatus for implementing the disclosed systems and methods according to an embodiment of the present disclosure is shown. Device 1002 may be a portable electronic device, such as a mobile phone, a tablet computer, a laptop computer, or a wearable device. Device 1002 may include a processor 1004 (e.g., a central processing unit (CPU), a graphics processing unit (GPU), or both), a main memory 1006 (e.g., a read-only memory (ROM), a flash memory, a dynamic random access memory (DRAM), such as a synchronous DRAM (SDRAM) or a Rambus DRAM (RDRAM), etc.), and a static memory 1008 (e.g., a flash memory, a static random access memory (SRAM), etc.), which components may communicate with each other via a bus 1010.
[0112] The device 1002 may also include a display 1012, an input / output device 1014 (e.g., a touch screen), a transceiver 1016, and a memory 1018. The memory 1018 includes a machine-readable medium 1020 having stored thereon one or more instruction sets 1024 (e.g., software) embodying any of the methods or functions described herein. The software may also reside, in whole or in part, within the main memory 1006 and / or the processor 1004 during execution by the device 1002. The one or more instruction sets 1024 (e.g., software) may also be transmitted or received over a network via the network interface device 1022.
[0113] Although the machine-readable medium 1020 is shown as a single medium in one embodiment, the term "machine-readable medium" should be understood to include a single medium or multiple media (e.g., a centralized or distributed database and / or associated caches and servers) storing one or more sets of instructions. The term "machine-readable medium" should also be understood to mean any medium that can store, encode, or carry a set of instructions for execution by a device and cause the device to perform one or more methods of the present invention. Therefore, the term "machine-readable medium" should include, but is not limited to, solid-state memories, optical and magnetic media, and carrier signals.
[0114] The systems and methods described herein and corresponding data may be stored in memory 1018, main memory 1006, static memory 1008, or a combination thereof. Display 1012 may be used to present a user interface to a physician or medical professional treating a transplant recipient, and input / output device 1014 may be used to receive input from the treating physician or medical professional (e.g., clicking on a graphical representation representing a microblog). For example, transceiver 1016 may be configured to communicate with a network.
[0115] Although the examples of the present disclosure have been fully described according to the accompanying drawings, it is noted that various changes and modifications will be apparent to those skilled in the art. Such changes and modifications should be understood to be included within the scope of the examples of the present disclosure as defined by the appended claims.
Claims
1. A method for classifying a state of a transplant, the method comprising: receiving expression levels of multiple genes in biological samples from transplant recipients; receiving a plurality of weight sets for the plurality of genes; generating one or more probabilistic rejection scores for one or more rejection signatures based on the plurality of weight sets and the expression level; as well as The biological sample of the transplant recipient is assigned a predictive rejection classification based on the one or more probabilistic rejection scores, wherein the predictive rejection classification classifies the status of the transplant.
2. The method of claim 1, wherein at least one gene of the plurality of genes is associated with one or more of: immune cell activation, organ-specific defense against pathogens, regulation of tissue and cellular processes, or transcriptional regulation.
3. The method of claim 1, wherein the predictive rejection classification classifies the status of the transplant as experiencing antibody-mediated rejection (ABMR), T-cell-mediated rejection (TCMR), mixed ABMR+TCMR, or no rejection.
4. The method of claim 1, wherein the predictive rejection classification classifies the status of the transplant as experiencing antibody-mediated rejection (ABMR).
5. The method of claim 1, wherein the predictive rejection classification classifies the status of the transplant as undergoing T cell mediated rejection (TCMR).
6. The method of claim 1, wherein the predictive rejection classification classifies the status of the transplant as experiencing mixed ABMR+TCMR rejection.
7. The method of claim 1, wherein the predictive rejection classification classifies the status of the transplant as experiencing no rejection.
8. The method of any one of the preceding claims, wherein generating one or more probabilistic rejection scores for one or more rejection tags comprises: For each rejection signature in the plurality of rejection signatures, a probabilistic rejection score is generated based on the plurality of weight sets and the expression level.
9. A method according to any one of the preceding claims, wherein each weight set contains a weight for a corresponding rejection label.
10. The method of any of the preceding claims, wherein assigning a predictive rejection classification to the biological sample of the transplant recipient comprises assigning as the predictive rejection classification a rejection signature of the plurality of rejection signatures having a highest probability rejection score.
11. The method of any one of the preceding claims, wherein the plurality of weight sets for the plurality of genes are from a machine learning model trained to: receiving a discovery dataset of biological samples from a discovery cohort of transplant recipients, wherein the discovery dataset includes gene expression levels of a plurality of genes and a rejection classification; analyzing the association between the gene expression levels of the discovery dataset and the rejection classification of the discovery dataset; identifying a subset of genes from the plurality of genes in the discovery dataset; as well as The plurality of weight sets for the gene subset are generated based on the association between the gene expression levels of the discovery dataset and the rejection classification of the discovery dataset, wherein each weight set is associated with a gene in the gene subset. 12 . The method of claim 11 , wherein the gene expression levels are analyzed by analyzing nucleic acids in the biological samples of the discovery cohort.
13. The method of claim 11, wherein the gene expression level is analyzed by analyzing RNA in the biological samples of the discovery cohort.
14. The method of claim 11, wherein at least some of the rejection classifications of the discovery dataset include antibody-mediated (ABMR).
15. The method of claim 11, wherein at least some of the rejection classifications of the discovery dataset include T cell mediated (TCMR).
16. The method of claim 11, wherein at least some of the rejection classifications of the discovery data set include mixed ABMR+TCMR rejections.
17. The method of claim 11, wherein at least some of the rejection classifications of the discovery data set include no rejection.
18. The method of claim 11, wherein the expression levels of one or more genes in the plurality of genes from the discovery dataset are normalized relative to gene expression levels of one or more reference genes.
19. The method of claim 11, wherein the machine learning model is validated by: obtaining a validation data set from biological samples of a validation cohort of transplant recipients, wherein the validation data set includes gene expression levels and rejection classification of a plurality of genes; determining one or more computer-determined predictive rejection classifications from the validation dataset; comparing one or more of the rejection classifications in the validation data set to the one or more computer-determined predictive rejection classifications; as well as A diagnostic accuracy is determined based on the comparison, wherein the diagnostic accuracy is greater than a predetermined value.
20. The method of claim 19, wherein the predetermined value is 60%, 70%, 80% or 90%.
21. The method of any of the preceding claims, wherein at least one of the plurality of genes comprises a gene identified from the group consisting of: KIR_Inhibiting_Subgroup_1, IL7R, KLRK1, BK large T Ag, PLA1A, LGALS3, HLA-F, SMAD3, HLA-C, SH2D1B, CXCL11, GBP4, SFTPC, SOST, AGT, HSPA12B, NCAM1, NCR1, ITGA4, LCN2, HLA-DPB1, XCL1 / 2, BKVP1, COL4A1, ARG2, MCM6, CD59, CD69, SMARCA4, IL18, CMV UL83, SIGIRR, KIT, CD160, SERPINE1, TFRC, CCR7, HLA-B, CXCL8, AQP2, SOD2, SFTPB, HLA-DQA1, IFI6, HFE , MAPK12, GDF15, IFIT1, KLRF1, SERINC5, FOXP3, BCL2L1, FABP1, CCL21, LOX, ROBO4, MYBL1, AGR3, CXCR6, CXCL13, FCER1A, BTG2, CTLA4, CASP3, SPRY4, RAF1, MAPK13, IGF2R, RHOU, LYVE1, CD80, KAAG1, CCL18, EHD 3. IL1RL1, CRIP2, TNFSF9, CDH5, CD8B, PRDM1, SIRPG, ABCA1, ADORA2A, RASSF9, JUN, COL4A4, TRAF4, PIN1 , SOX7, CFB, CFH, SFTPD, THBS1, AIRE, RAMP3, IL1R2, GNG11, RAPGEF5, DEFB1, GNLY, PHEX, ENG, BMP7, RELA , COL1A1, PLAAT4, CD81, ICAM2, PLAT, CD40LG, NPHS2, IL33, CD58, TIPARP, TNC, PECAM1, C5, EGFR, CD2, BM P2, CTNNB1, MYB, CRHBP, MT2A, EEF1A1, BCL2, SLC19A3, VMP1, PSEN1, MAPK3, TFF3, TNFSF4, CD55, PDPN, IL 17RB, IGHG2, CXCL12, CD207, MICA, MMP9, EOMES, EPO, NOS3, KLF2, KLF4, SLC4A1, P2RX4, CCL3 / L1 and HPRT1.
22. The method of any of the preceding claims, wherein the transplant recipient has received a transplant comprising one or more of: a kidney transplant, a heart transplant, a lung transplant, a pancreas transplant, a liver transplant, an intestinal transplant, or a vascularized composite allograft transplant.
23. The method of any of the preceding claims, wherein the transplant recipient receives an allogeneic or xenograft.
24. The method according to any one of the preceding claims, wherein the biological sample is an organ tissue sample.
25. The method of any one of the preceding claims, further comprising the step of administering immunosuppressive therapy.
26. A kit for classifying the status of a transplant, the kit comprising: Inhibiting genes from KIR_Inhibiting_Subgroup_1, IL7R, KLRK1, BK large Tag, PLA1A, LGALS3, HLA-F, SMAD3, HLA-C, SH2D1B, CXCL11, GBP4, SFTPC, SOST, AGT, HSPA12B, NCAM1, NCR1, ITGA4, LCN2, HLA-DPB1, XCL1 / 2, BK VP1, COL4A1, ARG2, MCM6, CD59, CD69, SMARCA4, IL18, CMVUL83, SIGIRR, KIT, CD160, SERPINE1, TFRC, CCR7, HLA-B, CXC L8, AQP2, SOD2, SFTPB, HLA-DQA1, IFI6, HFE, MAPK12, GDF15, IFIT1, KLRF1, SERINC5, FOXP3, BCL2L1, FABP1, CCL21, LO X, ROBO4, MYBL1, AGR3, CXCR6, CXCL13, FCER1A, BTG2, CTLA4, CASP3, SPRY4, RAF1, MAPK13, IGF2R, RHOU, LYVE1, CD80, K AAG1, CCL18, EHD3, IL1RL1, CRIP2, TNFSF9, CDH5, CD8B, PRDM1, SIRPG, ABCA1, ADORA2A, RASSF9, JUN, COL4A4, TRAF4, P IN1, SOX7, CFB, CFH, SFTPD, THBS1, AIRE, RAMP3, IL1R2, GNG11, RAPGEF5, DEFB1, GNLY, PHEX, ENG, BMP7, RELA, COL1A1, PLAAT4, CD81, ICAM2, PLAT, CD40LG, NPHS2, IL33, CD58, TIPARP, TNC, PECAM1, C5, EGFR, CD2, BMP2, CTNNB1, MYB, CRHBP , MT2A, EEF1A1, BCL2, SLC19A3, VMP1, PSEN1, MAPK3, TFF3, TNFSF4, CD55, PDPN, IL17RB, IGHG2, CXCL12, CD207, MICA, MMP9, EOMES, EPO, NOS3, KLF2, KLF4, SLC4A1, P2RX4, CCL3 / L1, and HPRT1, reagents, controls, and instructions for use.
27. The kit of claim 26, wherein the kit further comprises instructions for: receiving expression levels of multiple genes in biological samples from transplant recipients; receiving a plurality of weight sets for the plurality of genes; generating one or more probabilistic rejection scores for one or more rejection signatures based on the plurality of weight sets and the expression levels; as well as The biological sample of the transplant recipient is assigned a predictive rejection classification based on the one or more probabilistic rejection scores, wherein the predictive rejection classification classifies the status of the transplant.
28. The kit of claim 26, wherein the predictive rejection classification classifies the status of the transplant as experiencing antibody-mediated rejection (ABMR), T-cell-mediated rejection (TCMR), mixed ABMR+TCMR, or no rejection.
29. The kit of any one of the preceding claims, wherein generating one or more probabilistic rejection scores for one or more rejection signatures comprises: For each rejection signature in the plurality of rejection signatures, a probabilistic rejection score is generated based on the plurality of weight sets and the expression level.
30. A kit according to any one of the preceding claims, wherein each weight set comprises a weight for a corresponding rejection tag.
31. The kit of any of the preceding claims, wherein the transplant recipient has received a transplant comprising one or more of: a kidney transplant, a heart transplant, a lung transplant, a pancreas transplant, a liver transplant, an intestinal transplant, or a vascularized composite allograft transplant.
32. The kit of any one of the preceding claims, wherein the transplant recipient receives an allogeneic or xenograft.
33. The kit according to any one of the preceding claims, wherein the biological sample is an organ tissue sample.
34. The kit of any of the preceding claims, wherein assigning a predictive rejection classification to the biological specimen of the transplant recipient comprises assigning as the predictive rejection classification a rejection signature of the plurality of rejection signatures having a highest probability rejection score.
35. A system for classifying the status of a transplant, the system comprising: A scoring unit, wherein the scoring unit is used to: receiving expression levels of multiple genes in biological samples from transplant recipients; receiving a plurality of weight sets for the plurality of genes; generating one or more probabilistic rejection scores for one or more rejection signatures based on the plurality of weight sets and the expression level; as well as The biological sample of the transplant recipient is assigned a predictive rejection classification based on the one or more probabilistic rejection scores, wherein the predictive rejection classification classifies the status of the transplant.
36. The system of claim 35, wherein at least one gene of the plurality of genes is associated with one or more of: immune cell activation, organ-specific defense against pathogens, regulation of tissue and cellular processes, or transcriptional regulation.
37. The system of claim 35, wherein the predictive rejection classification classifies the status of the transplant as experiencing antibody-mediated rejection (ABMR), T-cell-mediated rejection (TCMR), mixed ABMR+TCMR, or no rejection.
38. The system of claim 35, wherein the predictive rejection classification classifies the status of the transplant as experiencing antibody-mediated rejection (ABMR).
39. The system of claim 35, wherein the predictive rejection classification classifies the status of the transplant as undergoing T cell mediated rejection (TCMR).
40. The system of claim 35, wherein the predictive rejection classification classifies the status of the transplant as experiencing mixed ABMR+TCMR rejection.
41. The system of claim 35, wherein the predictive rejection classification classifies the status of the transplant as experiencing no rejection.
42. The system of any of the preceding claims, wherein generating one or more probabilistic rejection scores for one or more rejection tags comprises: For each rejection signature in the plurality of rejection signatures, a probabilistic rejection score is generated based on the plurality of weight sets and the expression level.
43. A system according to any of the preceding claims, wherein each weight set contains a weight for a corresponding rejection label.
44. The system of any of the preceding claims, wherein assigning a predictive rejection classification to the biological specimen of the transplant recipient comprises assigning a rejection signature having a highest probability rejection score among the plurality of rejection signatures as the predictive rejection classification.
45. The system of any of the preceding claims, wherein the plurality of weight sets for the plurality of genes are from a machine learning model trained to: receiving a discovery dataset of biological samples from a discovery cohort of transplant recipients, wherein the discovery dataset includes gene expression levels of a plurality of genes and a rejection classification; analyzing the association between the gene expression levels of the discovery dataset and the rejection classification of the discovery dataset; identifying a subset of genes from the plurality of genes in the discovery dataset; as well as The plurality of weight sets for the gene subset are generated based on the association between the gene expression levels of the discovery dataset and the rejection classification of the discovery dataset, wherein each weight set is associated with a gene in the gene subset.
46. The system of claim 45, wherein analyzing the gene expression levels is performed by analyzing nucleic acids in the biological samples of the discovery cohort.
47. The system of claim 45, wherein the gene expression levels are analyzed by analyzing RNA in the biological samples of the discovery cohort.
48. The system of claim 45, wherein at least some of the rejection classifications of the discovery dataset include antibody-mediated rejection (ABMR).
49. The system of claim 45, wherein at least some of the rejection classifications of the discovery dataset include T cell mediated rejection (TCMR).
50. The system of claim 45, wherein at least some of the rejection classifications of the discovery data set include mixed ABMR+TCMR rejections.
51. The system of claim 45, wherein at least some of the rejection classifications of the discovery data set include no rejection.
52. The system of claim 45, wherein the expression levels of one or more genes in the plurality of genes from the discovery dataset are normalized relative to gene expression levels of one or more reference genes.
53. The system of claim 45, wherein the machine learning model is validated by: obtaining a validation data set from biological samples of a validation cohort of transplant recipients, wherein the validation data set includes gene expression levels and rejection classification of a plurality of genes; determining one or more computer-determined predictive rejection classifications from the validation dataset; comparing one or more of the rejection classifications in the validation data set to the one or more computer-determined predictive rejection classifications; as well as A diagnostic accuracy is determined based on the comparison, wherein the diagnostic accuracy is greater than a predetermined value.
54. The system of claim 53, wherein the predetermined value is 60%, 70%, 80% or 90%.
55. The system of any of the preceding claims, wherein at least one of the plurality of genes comprises a gene identified from the group consisting of: KIR_Inhibiting_Subgroup_1, IL7R, KLRK1, BK large T Ag, PLA1A, LGALS3, HLA-F, SMAD3, HLA-C, SH2D1B, CXCL11, GBP4, SFTPC, SOST, AGT, HSPA12B, NCAM1, NCR1, ITGA4, LCN2, HLA-DPB1, XCL1 / 2, BKVP1, COL4A1, ARG2, MCM6, CD59, CD69, SMARCA4, IL18, CMV UL83, SIGIRR, KIT, CD160, SERPINE1, TFRC, CCR7, HLA-B, CXCL8, AQP2, SOD2, SFTPB, HLA-DQA1, IFI6, HFE , MAPK12, GDF15, IFIT1, KLRF1, SERINC5, FOXP3, BCL2L1, FABP1, CCL21, LOX, ROBO4, MYBL1, AGR3, CXCR6, CXCL13, FCER1A, BTG2, CTLA4, CASP3, SPRY4, RAF1, MAPK13, IGF2R, RHOU, LYVE1, CD80, KAAG1, CCL18, EHD 3. IL1RL1, CRIP2, TNFSF9, CDH5, CD8B, PRDM1, SIRPG, ABCA1, ADORA2A, RASSF9, JUN, COL4A4, TRAF4, PIN1 , SOX7, CFB, CFH, SFTPD, THBS1, AIRE, RAMP3, IL1R2, GNG11, RAPGEF5, DEFB1, GNLY, PHEX, ENG, BMP7, RELA , COL1A1, PLAAT4, CD81, ICAM2, PLAT, CD40LG, NPHS2, IL33, CD58, TIPARP, TNC, PECAM1, C5, EGFR, CD2, BM P2, CTNNB1, MYB, CRHBP, MT2A, EEF1A1, BCL2, SLC19A3, VMP1, PSEN1, MAPK3, TFF3, TNFSF4, CD55, PDPN, IL 17RB, IGHG2, CXCL12, CD207, MICA, MMP9, EOMES, EPO, NOS3, KLF2, KLF4, SLC4A1, P2RX4, CCL3 / L1 and HPRT1.
56. The system of any of the preceding claims, wherein the transplant recipient has received a transplant comprising one or more of: a kidney transplant, a heart transplant, a lung transplant, a pancreas transplant, a liver transplant, an intestinal transplant, or a vascularized composite allograft transplant.
57. The system of any of the preceding claims, wherein the transplant recipient receives an allogeneic transplant or a xenograft.
58. The system of any of the preceding claims, wherein the biological sample is an organ tissue sample.
