Systems and methods for classifying graft status - Patents.com

Abstract

Disclosed herein are systems, kits, and methods for classifying a graft status based on expression levels of multiple genes from a biological sample of a transplant recipient. The graft status may be classified based on a predicted rejection classification, including but not limited to antibody-mediated rejection (ABMR), T-cell-mediated rejection (TCMR), mixed ABMR+TCMR, and no rejection. The predicted rejection classification may be assigned based on a probability rejection score, which may be assigned to each rejection label. In some embodiments, the rejection label with the highest probability rejection score among the multiple rejection labels may be assigned as the predicted rejection classification. Non-limiting rejection labels may include ABMR, TCMR, mixed ABMR+TCMR, and no rejection. The probability rejection score for each rejection label may be generated based on multiple sets of weights and the expression levels of the genes.

Description

[Technical field]

[0001] (CROSS REFERENCE TO RELATED APPLICATIONS) This application claims the benefit of U.S. Provisional Application No. 63 / 336,870, filed April 29, 2022, which is incorporated by reference herein in its entirety.

[0002] FIELD OF THEINVENTION The present disclosure relates generally to systems and methods for classifying the condition of a graft. [Background technology]

[0003] Transplantation of cells, tissues, parts of organs or whole organs is a life-saving medical procedure when an individual experiences acute organ failure or suffers from any malignancy. Many organs can be successfully transplanted, including but not limited to the heart, kidney, liver, lung, and pancreas, and one of the most common types of organ transplants performed today is kidney transplantation.

[0004] When non-self (allogeneic) cells, tissues, or organs (allografts) are transplanted into a recipient, the immune system of the transplant recipient recognizes the allograft as foreign to the body and activates various mechanisms to reject the allograft. It is therefore necessary to medically suppress such immune responses to minimize the risk of graft rejection. After transplantation, the status of the graft can be monitored by various clinical laboratory diagnostic tests, including histopathological evaluation of transplant biopsy tissue. The status can be monitored to guide clinical care and immunosuppressive treatment options. Although histopathological evaluation (e.g., biopsy) is the current standard for diagnosis of rejection, improving its diagnostic accuracy for determining and monitoring the status of transplants such as organ transplants is important due to the invasive nature of the procedure and associated risks to the transplant, potential sampling errors, and the subjective nature of histopathological interpretation.

[0005] What is needed, as provided by this disclosure, are systems and methods for classifying and monitoring the condition of a transplant, such as an organ transplant, with improved diagnostic accuracy. Summary of the Invention

[0006] A method for classifying a status of a graft is disclosed. The method includes receiving expression levels of a plurality of genes from a biological sample of a transplant recipient, receiving a plurality of sets of weights for the plurality of genes, generating one or more probabilistic rejection scores of one or more rejection labels based on the plurality of sets of weights and the expression levels, and assigning a predicted rejection classification of the biological sample of the transplant recipient based on the one or more probabilistic rejection scores, the predicted rejection classification classifying the status of the graft. In some embodiments, at least one 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. In some embodiments, the predicted rejection classification classifies the status of the graft as experiencing antibody-mediated rejection (ABMR), T-cell mediated rejection (TCMR), mixed ABMR+TCMR, or no rejection. In some embodiments, the predicted rejection classification classifies the status of the graft as experiencing antibody-mediated rejection (ABMR). In some embodiments, the predicted rejection classification classifies the status of the graft as experiencing T cell mediated rejection (TCMR). In some embodiments, the predicted rejection classification classifies the status of the graft as experiencing mixed ABMR+TCMR rejection. In some embodiments, the predicted rejection classification classifies the status of the graft as experiencing no rejection. In some embodiments, generating one or more probabilistic rejection scores for the one or more rejection labels comprises generating a probabilistic rejection score for each rejection label of the plurality of rejection labels based on a plurality of sets of weights and the expression level. In some embodiments, each set of weights comprises a weight for a corresponding rejection label. In some embodiments, assigning a predicted rejection classification of the transplant recipient biological sample comprises assigning a rejection label having a highest probabilistic rejection score among the plurality of rejection labels as the predicted rejection classification.In some embodiments, the multiple sets of weights for the multiple genes are from a machine learning model trained to: receive a discovery dataset from a biological sample of a discovery cohort of transplant recipients, the discovery dataset comprising gene expression levels and rejection classifications for a multiple genes; analyze the gene expression levels of the discovery dataset for association with rejection classifications in the discovery dataset; identify a subset of genes from the multiple genes of the discovery dataset; and generate multiple sets of weights for the subset of genes based on the association between the gene expression levels of the discovery dataset and the rejection classifications of the discovery dataset, each set of weights being associated with one gene of the subset of genes. In some embodiments, the gene expression levels are analyzed by analyzing nucleic acids from the biological sample of the discovery cohort. In some embodiments, the gene expression levels are analyzed by analyzing RNA from the biological sample of the discovery cohort. In some embodiments, at least some of the rejection classifications of the discovery dataset include antibody-mediated rejection (ABMR). In some embodiments, at least some of the rejection classifications of the discovery dataset include T-cell-mediated rejection (TCMR). In some embodiments, at least some of the rejection classifications of the discovery dataset include mixed ABMR+TCMR rejection. In some embodiments, at least some of the rejection classifications of the discovery dataset include no rejection. In some embodiments, the expression levels of one or more genes from the plurality of genes of the discovery dataset are normalized to gene expression levels of one or more reference genes.In some embodiments, the machine learning model is validated by obtaining a validation dataset from biological samples of a validation cohort of transplant recipients, the validation dataset including gene expression levels of a plurality of genes and a rejection classification, determining one or more computer-determined predicted rejection classifications from the validation dataset, comparing one or more of the rejection classifications in the validation dataset to the one or more computer-determined predicted rejection classifications, and determining a diagnostic accuracy based on the comparison, where the diagnostic accuracy is greater than a predetermined value. In some embodiments, the predetermined value is 60 percent, 70 percent, 80 percent, or 90 percent.In some embodiments, at least one gene of the plurality of genes is selected 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, 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, M APK12, GDF15, IFIT1, KLRF1, SERINC5, FOXP3, BCL2L1, FABP1, CCL21, LOX, ROBO4, MYBL1, AGR3, CXCR6, CXCL1 3, FCER1A, BTG2, CTLA4, CASP3, SPRY4, RAF1, MAPK13, IGF2R, RHOU, LYVE1, CD80, KAAG1, CCL18, EHD3, IL1RL 1, 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, PLAA T4, CD81, ICAM2, PLAT, CD40LG, NPHS2, IL33, CD58, TIPARP, TNC, PECAM1, C5, EGFR, CD2, BMP2, CTNNB1, MYB, C The present invention includes genes identified from the group consisting of RHBP, 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 a kidney transplant, a heart transplant, a lung transplant, a pancreas transplant, a liver transplant, an intestine transplant, or a vascularized composite allograft transplant. In some embodiments, the transplant recipient has received a transplant that is an allograft or a xenograft. In some embodiments, the biological sample is an organ tissue sample. In some embodiments, the step of administering an immunosuppressive treatment.

[0007] A kit for classifying graft status is disclosed, the kit comprising: 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, CXCL13, FCER1A, 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, AIR E, RAMP3, IL1R2, GNG11, RAPGEF5, DEFB1, GNLY, PHEX, ENG, BMP7, RELA, COL1A1, PLAAT4, CD81, ICAM2, PLAT, CD40L G, 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.In some embodiments, the kit further comprises instructions for receiving expression levels of a plurality of genes from the transplant recipient biological sample, receiving a plurality of sets of weights for the plurality of genes, generating one or more probabilistic rejection scores for one or more rejection labels based on the plurality of sets of weights and the expression levels, and assigning a predicted rejection classification for the transplant recipient biological sample based on the one or more probabilistic rejection scores, the predicted rejection classification classifying a status of the graft. In some embodiments, the predicted rejection classification classifies the status of the graft as experiencing antibody mediated rejection (ABMR), T cell mediated rejection (TCMR), mixed ABMR+TCMR, or no rejection. In some embodiments, generating the one or more probabilistic rejection scores for the one or more rejection labels comprises generating a probabilistic rejection score for each rejection label of the plurality of rejection labels based on the plurality of sets of weights and the expression levels. In some embodiments, each set of weights comprises a weight for a corresponding rejection label. In some embodiments, 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 intestine transplant, or a vascularized composite allograft transplant. In some embodiments, the transplant recipient has received a transplant that is an allograft or a xenograft. In some embodiments, the biological sample is an organ tissue sample. In some embodiments, assigning a predicted rejection classification of the transplant recipient biological sample comprises assigning as the predicted rejection classification a rejection label having a highest probability rejection score among the plurality of rejection labels.

[0008] A system for classifying a status of a graft is disclosed. The system may comprise a scoring unit that receives expression levels of a plurality of genes from a biological sample of a transplant recipient, receives a plurality of sets of weights for the plurality of genes, generates one or more probabilistic rejection scores for one or more rejection labels based on the plurality of sets of weights and the expression levels, and assigns a predicted rejection classification of the biological sample of the transplant recipient based on the one or more probabilistic rejection scores, the predicted rejection classification classifying the status of the graft. In some embodiments, at least one 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. In some embodiments, the predicted rejection classification classifies the status of the graft as experiencing antibody-mediated rejection (ABMR), T-cell-mediated rejection (TCMR), mixed ABMR+TCMR, or no rejection. In some embodiments, the predicted rejection classification classifies the status of the graft as experiencing antibody-mediated rejection (ABMR). In some embodiments, the predicted rejection classification classifies the status of the graft as experiencing T-cell-mediated rejection (TCMR). In some embodiments, the predicted rejection classification classifies the status of the graft as experiencing mixed ABMR+TCMR rejection. In some embodiments, the predicted rejection classification classifies the status of the graft as experiencing no rejection. In some embodiments, generating one or more probabilistic rejection scores for the one or more rejection labels includes generating a probabilistic rejection score for each rejection label of the plurality of rejection labels based on a plurality of sets of weights and the expression levels. In some embodiments, each set of weights includes a weight for a corresponding rejection label. In some embodiments, assigning a predicted rejection classification of the transplant recipient biological sample includes assigning a rejection label having a highest probabilistic rejection score among the plurality of rejection labels as the predicted rejection classification.In some embodiments, the multiple sets of weights for the multiple genes are from a machine learning model trained to: receive a discovery dataset from a biological sample of a discovery cohort of transplant recipients, the discovery dataset comprising gene expression levels and rejection classifications for a multiple genes; analyze the gene expression levels of the discovery dataset for association with rejection classifications in the discovery dataset; identify a subset of genes from the multiple genes of the discovery dataset; and generate multiple sets of weights for the subset of genes based on the association between the gene expression levels of the discovery dataset and the rejection classifications of the discovery dataset, each set of weights being associated with one gene of the subset of genes. In some embodiments, the gene expression levels are analyzed by analyzing nucleic acids from the biological sample of the discovery cohort. In some embodiments, the gene expression levels are analyzed by analyzing RNA from the biological sample of the discovery cohort. In some embodiments, at least some of the rejection classifications of the discovery dataset include antibody-mediated rejection (ABMR). In some embodiments, at least some of the rejection classifications of the discovery dataset include T-cell-mediated rejection (TCMR). In some embodiments, at least some of the rejection classifications of the discovery dataset include mixed ABMR+TCMR rejection. In some embodiments, at least some of the rejection classifications of the discovery dataset include no rejection. In some embodiments, the expression levels of one or more genes from the plurality of genes of the discovery dataset are normalized to gene expression levels of one or more reference genes.In some embodiments, the machine learning model is validated by obtaining a validation dataset from biological samples of a validation cohort of transplant recipients, the validation dataset including gene expression levels of a plurality of genes and a rejection classification, determining one or more computer-determined predicted rejection classifications from the validation dataset, comparing one or more of the rejection classifications in the validation dataset to the one or more computer-determined predicted rejection classifications, and determining a diagnostic accuracy based on the comparison, where the diagnostic accuracy is greater than a predetermined value. In some embodiments, the predetermined value is 60 percent, 70 percent, 80 percent, or 90 percent.In some embodiments, at least one gene of the plurality of genes is selected 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, 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, M APK12, GDF15, IFIT1, KLRF1, SERINC5, FOXP3, BCL2L1, FABP1, CCL21, LOX, ROBO4, MYBL1, AGR3, CXCR6, CXCL1 3, FCER1A, BTG2, CTLA4, CASP3, SPRY4, RAF1, MAPK13, IGF2R, RHOU, LYVE1, CD80, KAAG1, CCL18, EHD3, IL1RL 1, 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, PLAA T4, CD81, ICAM2, PLAT, CD40LG, NPHS2, IL33, CD58, TIPARP, TNC, PECAM1, C5, EGFR, CD2, BMP2, CTNNB1, MYB, C The present invention includes genes identified from the group consisting of RHBP, 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 a kidney transplant, a heart transplant, a lung transplant, a pancreas transplant, a liver transplant, an intestine transplant, or a vascularized composite allograft transplant. In some embodiments, the transplant recipient has received a transplant that is an allograft or a xenograft. In some embodiments, the biological sample is an organ tissue sample. [Brief description of the drawings]

[0009] [Figure 1] 1 illustrates an exemplary system for classifying a graft status in a biological sample from a graft recipient, according to an embodiment of the present disclosure. [Diagram 2] 1 shows a flowchart of an exemplary method for classifying organ transplant status, according to an embodiment of the present disclosure. [Diagram 3] 1 illustrates an exemplary system for providing multiple sets of expression levels and weights for multiple genes, according to an embodiment of the present disclosure. [Figure 4] 1 illustrates a flowchart of an exemplary method performed by a machine learning model, according to an embodiment of the present disclosure. [Diagram 5] 1 illustrates a diagram of an exemplary discovery dataset and validation dataset, according to an embodiment of the present disclosure. [Figure 6-1] 1 illustrates a table of an exemplary discovery dataset, according to an embodiment of the present disclosure. [Figure 6-2] 1 illustrates a table of an exemplary discovery dataset, according to an embodiment of the present disclosure. [Figure 7] 1 shows a table of an exemplary set of weights for a subset of genes, according to an embodiment of the present disclosure. [Figure 8] 1 illustrates a table of an exemplary validation dataset, according to an embodiment of the present disclosure. [Figure 9A] 1 shows an exemplary diagnostic accuracy graph of predictive rejection classification, according to an embodiment of the present disclosure. [Figure 9B] 1 shows an exemplary diagnostic accuracy graph of predictive rejection classification, according to an embodiment of the present disclosure. [Figure 10]1 illustrates an exemplary device for implementing the systems and methods disclosed herein, according to an embodiment of the present disclosure. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0010] Disclosed herein are systems, kits, and methods for classifying a graft status. The graft status may be classified based on the expression levels of a plurality of genes from a biological sample of a transplant recipient. The transplant status may be classified based on a predicted rejection classification. Exemplary predicted 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 predicted rejection classification may be assigned based on a probability rejection score. In some embodiments, a probability rejection score may be assigned to each rejection label. In some embodiments, the rejection label with the highest probability rejection score among the plurality of rejection labels may be assigned as the predicted rejection classification. Non-limiting rejection labels may include ABMR, TCMR, mixed ABMR+TCMR, and no rejection. A probability rejection score for each rejection label may be generated based on a plurality of sets of weights and the expression levels of the genes.

[0011] The computer-determined status of the graft may be provided by a medical analysis tool that is easily accessible to a physician or medical professional. The medical analysis tool may display the status of the graft, for example, in a user interface, a report printout, etc. The physician or medical professional may use the computer-determined status in addition to or instead of the physician's or medical professional's assessment of the status of the graft. The computer-determined status may be provided to the physician or medical professional as a predicted rejection classification and / or a probability rejection score for one or more rejection labels. For example, the medical analysis tool may output ABMR, TCMR, mixed ABMR+TCMR, or no rejection as the predicted rejection classification for a given biological sample of the transplant recipient. As another non-limiting example, the medical analysis tool may output 30% ABMR, 50% TCMR, 15% mixed ABMR+TCMR, and 5% no rejection as the probability rejection scores for the rejection labels of a given biological sample of the transplant recipient. The computer-determined status may be used by the physician or medical professional as a guide for treatment options, monitoring protocols, and / or clinical diagnosis.

[0012] By quantifying the status of the graft or classifying the status based on a quantified value (e.g., a probability rejection score), the status of the graft can be objective, consistent, and reliable. The disclosed computer-implemented method can be used to compare the status of the graft at one time point to another. Additionally or alternatively, the status may be used as a guide to determine treatment options and associated timing. Systematic assessment can help to better characterize the response of the transplant recipient to therapy and can help inform subsequent management and care. The results of the computer-implemented method can be more reproducible such that variability in results between transplant recipients or from different measurement times for a given transplant recipient can be reduced.

[0013] The multiple sets of weights may correspond to multiple genes and may be received by the machine learning model. The machine learning model may generate the multiple sets of weights based on a discovery dataset (from biological samples from a discovery cohort of transplant recipients) and a rejection classification. The machine learning model may analyze gene expression levels of the discovery dataset for association with rejection classifications in the discovery dataset. A subset of genes from the multiple genes of the discovery dataset may be identified. The machine learning model may generate multiple sets of weights for the subset of genes. In some embodiments, the multiple sets of weights may be based on associations between gene expression levels of the discovery dataset and rejection classifications of the discovery dataset. In some embodiments, each set of weights may be associated with one gene of the subset of genes. For example, a first set of weights of 100.0, 0.0, 0.0, and 0.0 for no rejection, ABMR, TCMR, and mixed ABMR+TCMR, respectively, may be associated with gene KIR_Inhibiting_Subgroup_1.

[0014] The following description is presented to enable those skilled in the art to make and use the various embodiments. Descriptions of specific devices, techniques, and applications are provided only as examples. These examples are provided merely to add context and aid in understanding the described examples. Thus, it will be apparent to one skilled in the art that the described examples may be practiced without some or all of the specific details. Other applications are possible, and the following examples should not be construed as limiting. Various modifications in the examples described herein will be readily apparent to those skilled in the art, and the general principles defined herein may be applied to other examples and applications without departing from the spirit and scope of the various embodiments. The various embodiments are not limited to the examples described and shown herein, but are to be accorded the scope consistent with the claims.

[0015] Various techniques and process flow steps are described in detail with reference to examples illustrated in the accompanying drawings. In the following description, numerous specific details are set forth in order to provide a thorough understanding of one or more aspects and / or features described or referenced herein. However, it will be apparent to one of ordinary skill in the art that one or more aspects and / or features described or referenced herein may be practiced without some or all of these specific details. In other instances, well-known process steps and / or structures have not been described in detail in order to avoid obscuring some of the aspects and / or features described or referenced herein.

[0016] In the following description of examples, reference is made to the accompanying drawings that form a part hereof, and in which is shown, by way of illustration, specific examples that may be implemented. It is to be understood that other examples may be utilized and structural changes may be made without departing from the scope of the disclosed examples.

[0017] The terms used in the description of the various embodiments described herein are for the purpose of describing particular embodiments only and are not intended to be limiting. As used in the description of the various described embodiments and the appended claims, the singular forms "a," "an," and "the" are intended to include the plural forms unless the context clearly indicates otherwise. It will also be understood that the term "and / or" as used herein refers to and encompasses any and all possible combinations of one or more of the associated listed items. It will be further understood that the terms "includes," "including," "comprises," and / or "comprising," as used herein, specify the presence of stated features, integers, steps, operations, elements, and / or components, but do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and / or groups thereof.

[0018] The term "sample" or "biological sample," as used herein, refers to any sample obtained from a transplant recipient, including, but not limited to, tissue and / or cells from a biopsy, whole blood, plasma, serum, lymph, peripheral blood mononuclear cells, buccal swab, saliva, or urine.

[0019] The term "transplant" includes solid organ transplants, such as allogeneic, i.e., from a non-autologous source within the same species, or across species from a different source, such as xenografts or xenografts, as well as hollow organ transplants, e.g., gastrointestinal transplants. The term "graft" also includes cellular grafts, such as hematopoietic stem cells, pancreatic islet cells, pluripotent cells, skin tissue, skin cells, immune cells, including but not limited to, skin cells, NK cells, and T cells, of allogeneic or xenogeneic origin. The term "graft" also includes autologous, i.e., autologous cell grafts, e.g., grafts that contain autologous cells derived from the recipient, including autologous cells that have been genetically engineered before being re-administered to the recipient. The terms "graft" and "allograft" are used interchangeably herein and include xenografts in meaning. "Graft" refers to any graft that is transplanted alone or in combination with one or more grafts.

[0020] The term "solid organ transplant," as used herein, refers to any transplantation of a solid organ, including, but not limited to, kidney transplants, heart transplants, lung transplants, liver transplants, pancreas transplants, vascularized composite allograft transplants, or a combination of the above transplants.

[0021] The term "gene cluster" or "cluster," as used herein, refers to a group of two or more genes having related gene expression patterns, e.g., gene expression levels, that have a level or degree of correlation or association.

[0022] As used herein, the term "TCMR" refers to cell- or T-cell-mediated (allograft 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.

[0023] As used herein, the term "ABMR" refers to antibody-mediated (allograft or xenograft) rejection, including, but not limited to, acute active antibody-mediated rejection, chronic active antibody-mediated rejection, and chronic stable antibody-mediated rejection.

[0024] The terms "mixed rejection" and "mixed ABMR+TCMR" refer to rejection that displays features of both ABMR and TCMR.

[0025] The terms "no rejection" and "non-rejection", as used herein, refer to a state characterized by the absence of biopsy-confirmed ABMR, TCMR, and / or mixed ABMR+TCMR, or the absence of significant rejection-associated clinical symptoms, as indicated, for example, by elevated serum creatinine levels, reduced estimated glomerular filtration rate, abnormal echocardiographic results, or some other clinical concern indicating the clinical need for a biopsy. The terms "no rejection" and "non-rejection", as used herein, can also refer to a state characterized by low levels of immune activity, indicative of a dormant, quiescent state of the immune system.

[0026] As used herein, the term "nucleic acid" refers to RNA or DNA that is linear or branched, single or double stranded, or a hybrid thereof. The term also encompasses RNA / DNA hybrids.

[0027] As used herein, the term "gene" refers to a nucleic acid, e.g., DNA or RNA, sequence that comprises coding sequences necessary for the production of an RNA or polypeptide. A polypeptide can be encoded by a full-length coding sequence or any portion thereof.

[0028] The term "gene expression" as used herein refers to the production of a transcription or translation product of a gene, e.g., total RNA, mRNA, splice variant mRNA, or polypeptide. Unless otherwise clear from the context, gene expression levels can be measured at the RNA and / or polypeptide levels. Measurement of gene expression can provide an indication of the presence or possibility or probability of transplant rejection, characterized by elevated activity of cells of the immune system, or the absence or possibility or probability of transplant rejection, characterized by the absence of immune activity or a quiescent state of cells of the immune system exhibiting a low level of immune activity. Gene expression measurements, optionally normalized to gene expression levels of one or more reference genes, can be used to calculate a probability rejection score according to an indication of the presence or absence of a probability of transplant rejection. Such a probability rejection score can be used to predict the likelihood of a clinical outcome in a transplant recipient, e.g., the likelihood of transplant rejection or the likelihood of "no rejection". For example, such probabilistic rejection scores allow the treating physician or medical professional to identify transplant recipients who have a high likelihood of "no rejection" and therefore do not require adjustment, e.g., an increase, decrease, change, or initiation, of their immunosuppressive treatment, or who have a high likelihood of transplant rejection and therefore require adjustment of their immunosuppressive treatment. The probabilistic rejection scores can be the basis for assigning a predicted rejection classification for classifying the status of the transplant.

[0029] The term "machine-readable medium" as used herein refers to both a single medium and multiple media (e.g., centralized or distributed databases and / or associated caches and servers) that store one or more sets of instructions, and includes any medium that can store, encode, or carry a set of instructions for execution by a device, causing the device to perform any of the methods disclosed herein, etc. As used herein, the term "machine-readable medium" includes, but is not limited to, solid-state memories, optical and magnetic media, and carrier wave signals.

[0030] Exemplary System for Classifying Transplant Status in a Transplant Recipient After Transplant 1 illustrates an exemplary system 100 for classifying or determining or assessing the status of a graft, e.g., an organ graft, in a biological sample from a recipient of the graft, according to an embodiment of the present disclosure. Classifying, determining, and / or monitoring the status of the graft may be valuable and beneficial with regard to clinical decisions by a treating physician or medical professional involved in the treatment of the transplant recipient, e.g., with regard to the need to adjust, e.g., increase, decrease, change, or initiate, the transplant recipient's immunosuppressive or anti-rejection treatment.

[0031] 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 figures, or other components not shown in the figures. The system 100 may be, for example, a medical analysis tool. The treating physician or medical professional may use the medical analysis tool to help monitor the status of the transplant in the transplant recipient, as well as to monitor and / or suggest adjustments to the immunosuppressive therapy administered or to be administered to the transplant recipient. Monitoring the status of the transplant includes analyzing various aspects that provide useful information regarding the physiological status of the transplant. The method of the present disclosure may be used to classify the status of the transplant by a predictive rejection classification 180. The predictive rejection classification 180 may indicate a diagnosis that has the highest probability rejection score among a number of other diagnoses.

[0032] The interface 160 can receive expression levels of the plurality of genes 140 of the transplant recipient biological sample. 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 be a tool for assessing the status of the transplant. The scoring unit 170 can receive the plurality of sets of weights 150 (e.g., from a machine learning model) and the expression levels of the plurality of genes 140. The scoring unit 170 can assign a predicted rejection classification 180 to the transplant recipient biological sample.

[0033] In some embodiments, system 100 may be a kit for use by a treating physician or medical professional for post-transplant monitoring. 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 set of probe sets specific for one or more genes from a plurality of genes.

[0034] 2 shows a flow chart of an exemplary method for classifying a transplant status, e.g., organ transplant, post-transplant, according to an embodiment of the present disclosure. The method 200 may include a step 202, in which the system 100 may receive expression levels of a plurality of genes. The plurality of genes may be derived 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. The expression levels are discussed in more detail below.

[0035] In step 204, the system can receive multiple sets of weights for the multiple genes. The multiple sets of weights can be received, for example, from a machine learning model. As described in more detail below, the machine learning model can be trained to generate the multiple sets of weights based on the discovery dataset and the corresponding rejection classification. As one non-limiting example, each gene or subset of genes in the multiple genes can have a corresponding set of weights. The generation of the multiple sets of weights is described in more detail below.

[0036] In step 206, the system may generate one or more probabilistic rejection scores for one or more rejection labels using the scoring unit 170 of FIG. 1. The probabilistic rejection scores may be based on the multiple sets of weights (received in step 204) and the expression levels (received in step 202). The probabilistic rejection scores for the rejection labels may be percentage values ​​(e.g., between 0% and 100%) indicating the contribution of the type of rejection to the status of the transplant, e.g., the status of an organ transplant (according to the predictive rejection classification 180 of FIG. 1). A higher probabilistic rejection score may mean a higher contribution. For example, the rejection labels may include ABMR, TCMR, mixed ABMR+TCMR, and no rejection. The probabilistic rejection scores for ABMR, TCMR, mixed ABMR+TCMR, and no rejection for a biological sample, e.g., for an organ transplant recipient, may be 30%, 50%, 15%, and 5%, respectively. The highest percentage, 50%, may mean that the corresponding rejection label TCMR may have a higher contribution to the predicted rejection classification 180 than another rejection label having a lower percentage (e.g., an ABMR with a probability rejection score of 30%). The generation of the probability rejection scores is described in more detail below.

[0037] In step 208, the system can assign a predicted rejection classification of the biological sample of the transplant recipient, e.g., organ transplant recipient. The predicted rejection classification can classify the status of the graft, e.g., organ transplant. The system can assign one of a plurality of classifications or diagnoses to each biological sample (e.g., organ tissue sample), such as four diagnoses including three different types of rejection and no rejection. The predicted rejection classifications can include, but are not limited to, ABMR, TCMR, mixed ABMR+TCMR, or no rejection.

[0038] In some embodiments, a predicted rejection classification may be assigned based on one or more probability rejection scores. The sum of the probability rejection scores may be equal to 1 or 100%, for example. In some embodiments, the rejected label with the highest probability rejection score among the multiple rejected labels may be assigned as the predicted rejection classification. Returning to the previous example of 30% ABMR, 50% TCMR, 15% mixed ABMR+TCMR, and 5% no rejection for probability rejection scores, the system may assign a predicted rejection classification of TCMR due to the TCMR having the highest probability rejection score of 50% among the multiple rejected labels. Assigning predicted rejection classifications is discussed in more detail below.

[0039] Embodiments of the present disclosure may include repeating one or more steps of method 200 and / or method 400 (described below). Although the description and figures show certain steps of the methods being performed in a particular order, the method steps may be performed in other orders not described or shown. Additionally or alternatively, embodiments of the present disclosure may include performing all, some, or none of the steps of method 200 and / or method 400, where appropriate. Furthermore, although certain components, devices, or systems are described as performing steps of method 200 and / or method 400, any suitable combination of components, devices, or systems (including those not expressly disclosed) may be used to perform the steps.

[0040] As described above, the system 100 (e.g., a medical analysis tool) can receive expression levels of a plurality of 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., step 206 of method 200 of FIG. 2), and the probabilistic rejection scores can be used to assign a predicted rejection classification for the biological sample (e.g., step 208 of method 200 of FIG. 2). The probabilistic rejection scores can be based on the expression levels of the plurality of genes with multiple sets of weights.

[0041] The multiple sets of weights may be generated by a machine learning model 330, for example, as shown in the exemplary system of FIG. 3. The system 300 may comprise 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 from a discovery cohort of transplant recipients, for example, organ transplant recipients. In some embodiments, the biological samples may be organ tissue samples. The database 320 may store results from the processing and analysis performed by the biomarker unit 310. The machine learning model 330 may generate the multiple sets of weights 150, which may also be optionally stored in the database 320.

[0042] In some embodiments, prior to determining the expression levels of multiple genes from the transplant recipient biological sample, the biological sample can be processed, for example, using light, immunofluorescence, and electron microscopy. For example, the transplant biopsy can undergo immunohistochemical staining for SV40 polyomavirus on formalin-fixed paraffin embedded (FFPE) tissue, or immunofluorescence staining for C4d on unfixed tissue. One or more tissue sections from each FFPE block of kidney core biopsy tissue can be dissected using a cutting tool such as a microtome. The dissected tissue sections can be used directly or stored under conditions that maintain the integrity of nucleic acids, e.g., RNA, and prevent degradation and / or contamination of the tissue sections until further processing, e.g., for RNA extraction.

[0043] The biomarker unit 310 can be configured to determine one or more characteristics of a biological sample of a transplant recipient, e.g., an organ transplant recipient. For example, the biomarker unit 310 can analyze expression levels of a plurality of genes from the biological sample. The transplant recipient may have received a transplant including one or more of a kidney transplant, a heart transplant, a lung transplant, a pancreas transplant, a liver transplant, an intestine transplant, or a vascularized composite allograft transplant. In some embodiments, the transplant recipient may have received a transplant that is an allograft or a xenograft. In some embodiments, the analysis of the gene expression levels can include analyzing for association with a rejection classification (e.g., of a discovery dataset). In certain embodiments, the analysis of the gene expression levels can include analyzing for association with ABMR. In other embodiments, the analysis of the gene expression levels can include analyzing for association with TCMR. In certain embodiments, the analysis of the gene expression levels can include analyzing for association based on association strength, e.g., low, moderate, or high association strength, as commonly interpreted by one of skill in the art based on the statistical significance of the determined association strength.

[0044] Exemplary genes that may be informative for analyzing associations with transplant rejection classifications based on their gene expression levels according to embodiments of the present disclosure, and thus may be informative for the status of the transplant in a transplant recipient, may include, but are not limited to, one or more genes related to 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 be informative for whether a transplant recipient experiences "no rejection" or active rejection, e.g., TCMR, ABMR, or mixed ABMR+TCMR, based on their gene expression levels. In some embodiments, such genes may be informative for the strength of association with one or more rejection classifications, based on their gene expression levels. The same one or more informative genes may be used for each transplant recipient. It may not be necessary to customize one or more informative genes for different recipients of transplants.

[0045] Table 1 lists non-limiting exemplary informative genes related to immune cell activation, organ-specific defense against pathogens, regulation of tissue and cellular processes, and / or transcriptional regulation. Some of these genes belong to correlated gene clusters that show at least 0.6 or 60% correlation, as shown in Table 2. Genes that show a level or degree of correlation of at least 0.6 or 60% with the exemplary informative genes described herein, based at least on their gene expression levels, are also considered to be informative as to whether a transplant recipient will experience "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.

[0046] [Table 1-1]

[0047] [Table 1-2]

[0048]

Table 1-3

[0049]

Table 2-1-1

[0050]

Table 2-1-2

[0051]

Table 2-1-3

[0052]

Table 2-2-1

[0053]

Table 2-2-2

[0054]

Table 2-3-1

[0055]

Table 2-3-2

[0056]

Table 2-4-1

[0057]

Table 2-4-2

[0058] In some embodiments, two or more genes are determined to be correlated if they show similar expression patterns across a set of samples from transplant recipients, some of which have experienced transplant rejection and some of which have not. In some embodiments, two or more genes are determined to be correlated if their expression levels increase or decrease to the same extent in the same samples. Exemplary methods of clustering based on gene expression patterns are described, for example, in Oyelade, J. et al., Bioinform Biol Insights. 2016; 10: 237-253, the contents of which are specifically incorporated by reference in their entirety. In some embodiments, clustering is performed based on genes, samples, and / or other variables using various clustering methods, such as hierarchical clustering (HC), self-organizing map (SOM), and / or K-means clustering.

[0059] 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 can include 2-10, 11-20, 21-30, 31-40, 41-50, 51-60, 61-70, 71-80, 81-90, 91-100, 101-120, 121-150, 151-200, 201-250, 251-300, 301-400, 401-500, 501-600, 601-700, 701-800, 801-1000, or more genes.In some embodiments, at least one gene of the plurality of genes is selected 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, 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, M APK12, GDF15, IFIT1, KLRF1, SERINC5, FOXP3, BCL2L1, FABP1, CCL21, LOX, ROBO4, MYBL1, AGR3, CXCR6, CXCL1 3, FCER1A, 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, C FH, SFTPD, THBS1, AIRE, RAMP3, IL1R2, GNG11, RAPGEF5, DEFB1, GNLY, PHEX, ENG, BMP7, RELA, COL1A1, PLAAT 4, CD81, ICAM2, PLAT, CD40LG, NPHS2, IL33, CD58, TIPARP, TNC, PECAM1, C5, EGFR, CD2, BMP2, CTNNB1, MYB, CR The gene may include a gene identified from the group consisting of HBP, 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.

[0060] In some embodiments, at least one gene of the plurality of genes may include a gene determined to be correlated with a gene associated with immune cell activation, organ-specific defense against pathogens, regulation of tissue and cellular processes, or transcriptional regulation.

[0061] In some embodiments, the biomarker unit 310 can utilize a biological sample, such as an FFPE kidney allograft biopsy tissue, that contains nucleic acid to provide gene expression levels by testing a gene panel that includes one or more informative genes from a plurality of genes related to 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, the nucleic acid, e.g., total RNA, can be extracted from a biological sample, e.g., tissue curl of an organ tissue sample. Various methods of extracting nucleic acids, such as mRNA or total RNA, are known in the art, such as those described in Sambrook et al. Molecular Cloning: A Laboratory Manual 4th edition (2014) Cold Spring Harbor Laboratory Press, Cold Spring Harbor, NY; Ausubel, et al., Current Protocols in Molecular Biology (2010). Nucleic acid extraction can also be performed using commercially available purification kits, buffer sets, and proteases according to 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 the integrity and prevent degradation and / or contamination of the nucleic acids, or can be used directly for downstream applications and analyses (e.g., analysis of gene expression levels of one or more informative genes). In some embodiments, gene expression levels can be determined by analyzing total RNA from the sample, for example, using RNA sequencing. In some embodiments, gene expression levels can be determined by analyzing mRNA from the sample. In some embodiments, the RNA can be fragmented and used as a template to synthesize cDNA. The cDNA can then be subjected to 3'-adenylation and 5'-end repair.Sequencing adaptors can be ligated onto the 3'-adenylated and 5-end repaired cDNA, and the adaptor-ligated cDNA 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 into cDNA, using a gene expression platform, such as, for example, the NanoString Technologies nCounter® system. In some embodiments, the gene expression platform can quantify mRNA transcript levels for one or more informative genes from a gene panel. As discussed in more detail below, the gene panel can be a subset of genes identified from a plurality of genes of a biological sample that are associated with immune cell activation, organ-specific defense against pathogens, regulation of tissue and cellular processes, and / or transcriptional regulation. In some embodiments, a gene expression platform can be utilized that does not require immediate storage in RNA stabilization and storage reagents after sample collection, for example, by using the same biopsy core from a routine histopathological evaluation. In some embodiments, FFPE organ tissue samples, such as kidney allograft biopsy tissue samples, are obtained from routine clinical pathology practice and used to determine gene expression levels. In some embodiments, the FFPE organ tissue samples used to determine gene expression levels can be archived clinical samples, including older samples (e.g., 5, 6, 10, 13 years old, etc.). In some embodiments, gene expression platforms such as the NanoString Technologies nCounter® system can be used to develop gene expression signatures for graft rejection diagnosis in graft recipients.

[0062] In some embodiments, the database 320 may store various features, such as gene expression levels of multiple genes in a biological sample, e.g., an organ tissue sample, from a transplant recipient, that may be beneficial with respect to determining the status of the transplant, or transplant lesion scores, e.g., organ transplant lesion scores, that may be assigned by one or more pathologists, e.g., renal pathologists, upon histopathological evaluation of a biological sample, e.g., an organ tissue sample, from a kidney transplant recipient. In some embodiments, one or more lesion scores may be stored in the database 320. In some embodiments, one or more rejection classifications may be stored in the database 320 that may be assigned by one or more pathologists, e.g., renal pathologists, based on one or more lesion scores assigned upon histopathological evaluation of a biological sample, e.g., an organ tissue sample. In some embodiments, one or more rejection classifications may be stored in the database 320 that may be assigned by one or more pathologists, e.g., renal pathologists, based on one or more lesion scores alone or in combination with additional laboratory test results. In some embodiments, one or more rejection classifications may be stored in database 320 that may be assigned based on one or more lesion scores alone or in combination with additional laboratory test results according to guidelines for classification of human transplants, for example, the Banff 2019 classification guidelines for human organ transplantation (Mengel et al. (2019) Am J Transplant. 2020;20:2305- 2317.).

[0063] In some embodiments, the data stored in database 320 may include a discovery cohort of transplant recipients, e.g., a discovery dataset from biological samples of organ transplant recipients, and a validation cohort of transplant recipients, e.g., a validation dataset from biological samples of organ transplant recipients. In some embodiments, one or more of the transplant recipients (in the discovery dataset, the validation dataset, or both) may have received an organ transplant, including one or more of a kidney transplant, a heart transplant, a lung transplant, a pancreas transplant, a liver transplant, an intestine transplant, or a vascularized composite allograft transplant. In some embodiments, one or more of the transplant recipients may have received a transplant that is an allograft or a xenograft. In some embodiments, the discovery dataset may include gene expression levels of a plurality of genes and a rejection classification for the discovery cohort biological samples. In some embodiments, the discovery 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. In some embodiments, the validation dataset may include gene expression levels of a plurality of genes and a rejection classification for the validation cohort biological samples. The discovery dataset may also include rejection classifications for 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.

[0064] In some embodiments, the discovery dataset may include data from biological samples obtained from transplant recipients exhibiting a variety of histological findings (e.g., different types of rejection, non-diagnostic for rejection from both kidney allografts and native kidneys, etc.). For example, in some embodiments, at least some of the rejection classifications in the discovery dataset may include ABMR. In some embodiments, at least some of the rejection classifications in the discovery dataset may include TCMR. In some embodiments, at least some of the rejection classifications in the discovery dataset may include mixed ABMR+TCMR. In some embodiments, at least some of the rejection classifications in the discovery dataset may not include rejection.

[0065] Embodiments of the present disclosure may include systems and methods that can distinguish inflammatory conditions associated with kidney allograft rejection from conditions caused by other pathological conditions not associated with rejection, including various types of viral or bacterial infections, or various types of glomerulopathies. In some embodiments, discovery datasets may include data from biological samples, e.g., organ tissue samples, e.g., from both native organs (e.g., native kidneys), organ transplants (e.g., kidney transplants), and biological samples indicative of various types of inflammation, such as cytomegalovirus (CMV) or BK virus (BKV) nephropathy, acute pyelonephritis, diabetic nephropathy, etc.

[0066] The machine learning model 330 may be trained to generate one or more probabilistic rejection scores and generate multiple sets of weights to be used by the system 100 in assigning a predicted rejection classification. In some embodiments, the machine learning model 330 may be trained to analyze gene expression levels of the discovery dataset for association with rejection classifications in the discovery dataset. In some embodiments, the machine learning model 330 may narrow down the set of genes (for which the set of weights is generated) by identifying a subset of genes (from the plurality of informative genes of the discovery dataset) based on a fitting process disclosed herein. In some embodiments, the machine learning model 330 may generate multiple sets of weights for the subset of genes.

[0067] 4 shows a flowchart of an exemplary method performed by a machine learning model, according to an embodiment of the present disclosure. In some embodiments, the sets of weights for the informative genes may be from a machine learning model trained to perform one or more steps of method 400. In some embodiments, method 400 may include, for example, receiving a discovery dataset from database 320, at step 402. In some embodiments, the discovery dataset may include gene expression levels and associated rejection classifications for a discovery cohort of transplant recipients, for example, biological samples of organ transplant recipients. In some embodiments, the discovery dataset may be data obtained by one or more units, such as biomarker unit 310.

[0068] For example, as shown in FIG. 5, a discovery dataset may include data related to, e.g., histopathological evaluation, lesion scoring, etc., for multiple transplant tissue samples, e.g., organ tissue biopsies, of a discovery cohort. In some embodiments, the system may perform quality control, e.g., using a predefined threshold or expected range that is not exceeded, such that data from biological samples that do not meet certain criteria, e.g., based on the predefined threshold, may not be included in any subsequent evaluation or calculation. In some embodiments, one exemplary criterion may include, e.g., identifying genes that have an expected range or do not exceed a predefined threshold, e.g., associated with gene normalization quality control, when identifying housekeeping genes for gene normalization. In certain embodiments, another exemplary criterion may include, e.g., identifying genes that meet certain performance criteria related to assay efficiency, limiting detection or minimum detection thresholds, e.g., setting a target threshold for detecting and quantifying a target, e.g., a performance criterion that detects a certain percentage of probes targeting informative genes, e.g., a detection threshold of 62%.

[0069] FIG. 6 illustrates a table of an exemplary discovery dataset, according to an embodiment of the present disclosure. In some embodiments, the discovery cohort biological samples may include biological samples assigned a rejection classification of ABMR (either active or chronic). In some embodiments, the discovery cohort biological samples may include biological samples assigned a rejection classification of TCMR (various grades of acute). In some embodiments, the discovery cohort biological samples may include biological samples assigned a rejection classification of mixed ABMR+TCMR. In some embodiments, the discovery cohort biological samples may include biological samples with a rejection classification of "no rejection" (having various histological findings that are non-diagnostic for any type of rejection or lacking one or more histological findings that are diagnostic for any type of rejection). In some embodiments, the discovery dataset "no rejection" biological samples may include biological samples with or without various types of inflammation from native organs, e.g., native kidneys. In some embodiments, the discovery dataset "no rejection" biological samples may include biological samples, e.g., kidney allograft biopsies with or without inflammation, e.g., viral infection-associated inflammation (CMV or BKV).

[0070] In some embodiments, at least one of the plurality of informative genes of the discovery dataset 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.

[0071] In some embodiments, at least one gene of the plurality of informative genes of the discovery dataset is selected 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, 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, M APK12, GDF15, IFIT1, KLRF1, SERINC5, FOXP3, BCL2L1, FABP1, CCL21, LOX, ROBO4, MYBL1, AGR3, CXCR6, CXCL1 3, FCER1A, 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, C FH, SFTPD, THBS1, AIRE, RAMP3, IL1R2, GNG11, RAPGEF5, DEFB1, GNLY, PHEX, ENG, BMP7, RELA, COL1A1, PLAAT 4, CD81, ICAM2, PLAT, CD40LG, NPHS2, IL33, CD58, TIPARP, TNC, PECAM1, C5, EGFR, CD2, BMP2, CTNNB1, MYB, CR The gene may include a gene identified from the group consisting of HBP, 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.

[0072] In some embodiments, at least one gene of the plurality of informative genes of the discovery dataset is selected 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, 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, FCER 1A, BTG2, CTLA4, CASP3, SPRY4, RAF1, MAPK13, IGF2R, RHOU, LYVE1, CD80, KAAG1, CCL18, EHD3, IL1RL1, CRIP2, T NFSF9, CDH5, CD8B, PRDM1, SIRPG, ABCA1, ADORA2A, RASSF9, JUN, COL4A4, TRAF4, PIN1, SOX7, CFB, CFH, SFTPD, TH BS1, AIRE, RAMP3, IL1R2, GNG11, RAPGEF5, DEFB1, GNLY, PHEX, ENG, BMP7, RELA, COL1A1, PLAAT4, CD81, ICAM2, P LAT, CD40LG, NPHS2, IL33, CD58, TIPARP, TNC, PECAM1, C5, EGFR, CD2, BMP2, CTNNB1, MYB, CRHBP, MT2A, EEF1A1, B The gene may include genes that show at least 0.6 or 60% correlation with genes identified from the group consisting of CL2, 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.

[0073] Returning to FIG. 4, in step 404, gene expression levels of the discovery dataset may be analyzed for association with rejection classifications in the discovery dataset. For example, in some embodiments, a multinomial regression model may be used to fit gene expression levels of the discovery dataset to determine whether there is an association with a corresponding rejection classification. In some embodiments, the multinomial regression model may estimate coefficients using regularized likelihood. In some embodiments, gene expression levels may be analyzed by detecting and / or quantifying nucleic acids or RNA from biological samples of the discovery cohort.

[0074] In some embodiments, the expression level of one or more genes from the plurality of genes of the discovery dataset may be normalized to the gene expression level of one or more reference genes. In some embodiments, the normalization may be performed using a housekeeping gene. In some embodiments, the normalization may be performed using a normalization quality control metric.

[0075] A subset of genes may be identified from the plurality of genes in the discovery dataset at step 406. In one 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 predicted rejection classification.

[0076] In step 408, the machine learning model 330 can generate multiple sets of weights for the subset of genes (from step 406). The multiple sets of weights can be generated based on an association between gene expression levels in the discovery dataset and rejection classifications in the discovery dataset. In some embodiments, each set of weights can be associated with one gene in the subset of genes. The multiple sets of weights can be calculated using a predictive model such as Lasso regularized regression, elastic net random forest, gradient boosting machine, k-nearest neighbors, or support vector machine. The process performed by the predictive model can include fitting by cross-validation (e.g., 10-fold cross-validation) to determine one or more hyperparameters.

[0077] 7 shows a table of exemplary sets of weights for subsets of genes according to embodiments of the present disclosure. For example, the KIR_Inhibiting_Subgroup_1 gene may have weights of 100, 0, 0, and 0 relative to other genes of the plurality of informative genes for different rejection labels: No Rejection, ABMR, TCMR, and mixed ABMR+TCMR, respectively. As another example, the PLA1A gene may have weights of 65.1, 58.0, 58.0, and 84.6 relative to other genes of the plurality of informative genes for different rejection labels: No Rejection, ABMR, TCMR, and mixed ABMR+TCMR, respectively. As shown in the table, in some embodiments, each set of weights includes the weight of the corresponding rejection label.

[0078] An embodiment of the present disclosure may include training a machine learning model. The machine learning model may be trained by using a discovery dataset from biological samples of a discovery cohort of transplant recipients, such as organ transplant recipients. The machine learning model may be trained to receive the discovery dataset, analyze gene expression levels of the discovery dataset, identify a subset of genes, and generate a plurality of sets of weights for the subset of genes.

[0079] The machine learning model may be validated using a validation cohort to determine whether it has been trained according to a certain criterion, for example, diagnostic accuracy. In some embodiments, a diagnostic accuracy greater than a predetermined value may be one criterion. In some embodiments, the diagnostic accuracy may be determined based on a comparison of one or more rejection classifications in a dataset with one or more computer-determined predicted rejection classifications.

[0080] In some embodiments, the dataset used to validate the machine learning model may be a validation dataset or cohort, as shown in FIG. 5 and FIG. 8. In some embodiments, the validation dataset may include data for hundreds or thousands of biological samples, e.g., organ tissue samples, such as biopsy samples, of a validation cohort. In some embodiments, the validation dataset may be evaluated based on various quality control metrics to assess and ensure consistency, reliability, and reproducibility in predicting the rejection classification that must be met for later use in validating the machine learning model. In some embodiments, the biological samples of the validation cohort may include biological samples assigned a rejection classification of ABMR. In some embodiments, the biological samples of the validation cohort may include biological samples assigned a rejection classification of TCMR. In some embodiments, the biological samples of the validation cohort may include biological samples assigned a rejection classification of mixed ABMR+TCMR. In some embodiments, the biological samples of the validation cohort may include biological samples assigned a rejection classification of "no rejection."

[0081] The computer-determined predicted rejection classification may be determined for the validation dataset using a probabilistic rejection score generated based on the expression levels of a plurality of genes with a plurality of sets of weights generated by a machine learning model from biological samples of the validation cohort. In some embodiments, the computer-determined predicted classification is accepted if the diagnostic accuracy exceeds a predetermined value. In some embodiments, the predetermined value may be 60%, 70%, 80%, or 90%. The diagnostic accuracy may represent the percentage of predicted rejection classifications in the validation dataset that match the computer-determined predicted rejection classification (determined from the validation dataset).

[0082] In some embodiments, the diagnostic accuracy may be different for different predicted rejection classifications and / or different datasets. FIG. 9A shows the diagnostic accuracy of the discovery dataset according to an embodiment of the present disclosure. For example, for the discovery dataset, the overall diagnostic accuracy may be 84.6%. In some embodiments, the performance characteristics, e.g., sensitivity and specificity, of the disclosed systems and methods may be different for different predicted rejection classifications and / or different datasets. In some exemplary embodiments, the sensitivity and specificity of the disclosed systems and methods were 93.7% and 89.9%, respectively, regardless of the predicted rejection classification. In some exemplary embodiments, the sensitivity of the ABMR or TCMR predicted rejection classification was greater than 85%. In some exemplary embodiments, the sensitivity of the mixed ABMR+TCMR predicted rejection classification was about 50%. In some exemplary embodiments, the specificity for each of the three different types of rejection (e.g., ABMR, TCMR, mixed ABMR+TCMR) was greater than 90%.

[0083] In some embodiments, the performance characteristics of the disclosed systems and methods, such as diagnostic accuracy, sensitivity, specificity, may be different for different predicted rejection classifications and / or different datasets. FIG. 9B shows the diagnostic accuracy of the validation dataset, according to an exemplary embodiment of the present disclosure. In some exemplary embodiments, the diagnostic accuracy was 79.7%, and the sensitivity and specificity were 85.2% and 88.1%, respectively, regardless of the predicted rejection classification. In some exemplary embodiments, the sensitivity was 80.4%, 70.5%, and 44.4%, respectively, for the ABMR, TCMR, and mixed ABMR+TCMR predicted rejection classifications. In some embodiments, the specificity for each of the three different types of rejection (e.g., ABMR, TCMR, mixed ABMR+TCMR) may be greater than 90%. The high specificity for predicting transplant rejection indicates the potential of the disclosed system and method to successfully and reproducibly distinguish transplant rejection from other non-rejection related conditions that may present clinical parameters similar to the rejection related parameters, including acute and / or chronic inflammatory diseases and / or systemic infections. In demonstrating improved diagnostic accuracy, the disclosed system and method may be useful in distinguishing transplant rejection from non-rejection related inflammatory and / or infectious conditions (e.g., diabetic nephropathy, acute pyelonephritis, BK virus nephropathy) in transplant recipients that exhibit some clinical concerns and / or clinical parameters suggestive of transplant rejection, but are actually suffering from a non-rejection related inflammatory and / or infectious condition by accurately assigning a predictive rejection classification of "no rejection".

[0084] If the machine learning model is not properly trained (e.g., the diagnostic accuracy is below a predetermined value), the training data (e.g., the discovery dataset) can be modified to provide feedback to the model. In some embodiments, the output of the machine learning model between training iterations can be evaluated by a medical professional or treating physician to determine which data in the training data should be modified. The treating physician or medical professional can modify certain data in areas of potential improvement, such as weights of expression levels of multiple genes.

[0085] Examples of immunosuppressant therapy Immunosuppressive therapy generally refers to the administration of immunosuppressants or other therapeutic agents that suppress the immune response to the transplant recipient. Examples of immunosuppressants include, for example, calcineurin inhibitors, mTor inhibitors, anticoagulants, antimalarials, cardiovascular agents, including but not limited to ACE inhibitors and beta-blockers, non-steroidal anti-inflammatory agents, and the like. drug, NSAID), aspirin, azathioprine, B7RP-1-fc, brequinar sodium, cambus-1H, celecoxib, chloroquine, corticosteroids, coumadin, cyclophosphamide, cyclosporine A, DHEA, deoxyspergualin, dexamethasone, diclofenac, dolobid, etodolac, everolimus, FK778, feldene, fenoprofen, flurbiprofen, heparin, hydralazine, hydroxychloroquine, CTLA-4 or LFA3 immunoglobulin, ibuprofen, indomethacin, ISAtx-247, ketoprofen, ketorolac, leflunomide, meclofenamate, mefenamic acid, mepa These include cyclosporine, 6-mercaptopurine, meloxicam, methotrexate, mizoribine, mycophenolate mofetil, naproxen, oxaprozin, plaquenil, NOX-100, prednisone, methylprednisolone, rapamycin (sirolimus), sulindac, tacrolimus (FK506), thymoglobulin, tolmetin, tresperimus, 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 depending on the classification of the graft status as experiencing "no rejection", ABMR, TCMR, or mixed ABMR+TCMR rejection. For example, in response to the graft status being classified as experiencing TCMR, bolus steroid treatment may be initiated or maintenance immunosuppressive therapy may be increased in dose and / or frequency.In response to classification of the graft status as experiencing ABMR, for example, plasmapheresis or intravenous immunoglobulin (IVIg) may be initiated.

[0086] In some embodiments, no change in graft status (e.g., as indicated by no change in predicted rejection classification) may indicate that the immunosuppressive therapy administered to the transplant recipient does not need to be adjusted or that the immunosuppressive therapy administered may be maintained. The decision to maintain the immunosuppressive therapy administered to the transplant recipient may be based on additional clinical factors, such as, for example, the health status, age, comorbidities, etc., of the transplant recipient.

[0087] In some embodiments, adjusting immunosuppressive therapy includes altering the type, form, or frequency of immunosuppressive therapy or other transplant-related therapy administered to the transplant recipient, hi some embodiments, if the transplant recipient is not receiving immunosuppressive therapy, the methods of the present disclosure can indicate the need to initiate administration of immunosuppressive therapy to the transplant recipient.

[0088] Other transplant-related therapies include treatments or therapies other than transplant or immunosuppressive therapy that are administered to transplant recipients to promote graft survival or treat transplant-related conditions (e.g., cytokine release syndrome, neurotoxicity). Examples of other transplant-related therapies include, but are not limited to, administration of antibodies, antigen-targeting ligands, non-immunosuppressive drugs, and other agents that stabilize or destabilize graft components that are important for transplant activity or that directly activate or inhibit one or more transplant activities. These activities may include the ability to induce an immune response, recognize specific antigens, replicate, and / or induce repair of damaged tissue. Adjusting immunosuppressive therapy can be combined with adjusting, initiating, or discontinuing other transplant-related therapies.

[0089] The disclosed methods 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 predicted rejection classification over time can be informative with regard to determining the need to adjust the monitoring of the transplant recipient. In some embodiments, classifying the status of the graft as described above is informative with regard to determining the need to adjust the monitoring of the transplant recipient.

[0090] Depending on the status of the transplant, monitoring of the transplant recipient can be adjusted accordingly. For example, monitoring can be adjusted by increasing or decreasing the frequency of monitoring as appropriate. Monitoring can be adjusted by changing the means of monitoring, for example, by changing the metrics used to monitor the transplant recipient.

[0091] Exemplary Systems for Classifying Implant Condition The systems and methods discussed herein may be implemented by a device. FIG. 10 illustrates an exemplary device implementing the disclosed systems and methods according to an embodiment of the present disclosure. The device 1002 may be a portable electronic device, such as a mobile phone, a tablet computer, a laptop computer, or a wearable device. The 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., read-only memory (ROM), flash memory, dynamic random access memory (DRAM), such as synchronous dynamic random access memory (SDRAM) or Rambus dynamic random access memory (RDRAM), etc.), and a static memory 1008 (e.g., flash memory, static random access memory (SRAM), etc.), which may communicate with each other via a bus 1010.

[0092] The device 1002 may also include a display 1012, an input / output device 1014 (e.g., a touch screen), a transceiver 1016, and storage 1018. The storage 1018 includes a machine-readable medium 1020 having stored thereon one or more sets of instructions 1024 (e.g., software) that embody any of the methods or functions described herein. The software may also reside, completely or at least partially, within the main memory 1006 and / or within the processor 1004 during its execution by the device 1002. The one or more sets of instructions 1024 (e.g., software) may further be transmitted or received over a network via a network interface device 1022.

[0093] While the machine-readable medium 1020 is shown in one embodiment to be a single medium, the term "machine-readable medium" should be interpreted to include a single medium or multiple media (e.g., a centralized or distributed database and / or associated caches and servers) that store one or more sets of instructions. The term "machine-readable medium" should also be interpreted to include any medium capable of storing, encoding, or carrying a set of instructions for execution by a device, causing the device to perform any one or more of the methods of the present invention. Thus, the term "machine-readable medium" should be interpreted to include, but is not limited to, solid-state memories, optical and magnetic media, and carrier wave signals.

[0094] The systems and methods described herein and corresponding data may be stored in storage 1018, main memory 1006, static memory 1008, or a combination thereof. The display 1012 may be used to present a user interface to a physician or medical professional treating the transplant recipient, and the input / output device 1014 may be used to receive input from the treating physician or medical professional (e.g., clicking on a graphic representing a microblog). The transceiver 1016 may be configured to communicate with a network, for example.

[0095] Although examples of the present disclosure have been fully described with reference to the accompanying drawings, it should be noted that various changes and modifications will become apparent to those skilled in the art, and such changes and modifications should be understood as being included within the scope of the examples of the present disclosure as defined by the appended claims.

Claims

1. A method for classifying the condition of grafts, wherein the method is Receiving the expression levels of multiple genes from the biological sample of the transplant recipient, Receiving multiple sets of weights for the aforementioned multiple genes, Based on the aforementioned sets of weights and the expression levels, one or more probabilistic rejection scores are generated for one or more rejection labels. A method comprising assigning a predictive rejection classification to a biological sample of a transplant recipient, based on one or more probability rejection scores, wherein the predictive rejection classification classifies the state of the graft.

2. The method according to claim 1, wherein at least one of the plurality of genes is related to one or more of the following: activation of immune cells, organ-specific defense against pathogens, regulation of tissue and cellular processes, or transcriptional regulation.

3. The method according to claim 1, wherein the predicted rejection classification classifies the state of the graft as having experienced antibody-mediated rejection (ABMR), T-cell-mediated rejection (TCMR), mixed ABMR + TCMR, or no rejection.

4. Generating one or more probabilistic rejection scores for one or more rejection labels is, The method according to any one of claims 1 to 3, comprising generating a probabilistic rejection score for each of a plurality of rejection labels based on a plurality of sets of weights and the expression level.

5. The method according to any one of claims 1 to 3, wherein each set of weights includes the weight of the corresponding rejection label.

6. The method according to any one of claims 1 to 3, wherein assigning a predicted rejection classification to the biological sample of the transplant recipient includes assigning the rejection label having the highest probability rejection score among the plurality of rejection labels as the predicted rejection classification.

7. The sets of weights for the aforementioned multiple genes are: A discovery dataset is obtained from biological samples of a discovery cohort of transplant recipients, and the discovery dataset includes gene expression levels and rejection classifications for multiple genes. Regarding the association with the rejection classification in the aforementioned discovery dataset, the gene expression levels in the aforementioned discovery dataset are analyzed, Identifying a subset of genes from the multiple genes in the aforementioned discovery dataset, The method according to any one of claims 1 to 3, wherein, based on the association between the gene expression levels of the discovery dataset and the rejection classifications of the discovery dataset, a plurality of sets of weights for a subset of the gene, each set of weights being associated with one of the genes in the subset, and the method according to any one of claims 1 to 3.

8. The method according to claim 7, wherein the gene expression level is analyzed by analyzing nucleic acids or RNA from the biological samples of the discovery cohort.

9. The method according to claim 7, wherein at least some of the rejection classifications of the discovery dataset include antibody-mediated rejection (ABMR), T cell-mediated rejection (TCMR), mixed ABMR + TCMR rejection, or no rejection.

10. The method according to claim 7, wherein the expression levels of one or more genes from the plurality of genes in the discovery dataset are normalized with respect to the gene expression levels of one or more reference genes.

11. The aforementioned machine learning model, Obtaining a validation dataset from biological samples of a validation cohort of transplant recipients, wherein the validation dataset includes gene expression levels and rejection classifications for multiple genes, The process involves determining one or more computer-determined predicted rejection classifications from the aforementioned validation dataset, Comparing one or more of the rejection classifications in the validation dataset with one or more computer-determined predicted rejection classifications, The method according to claim 7, verified by determining a diagnostic accuracy, wherein the diagnostic accuracy is greater than a predetermined value, based on the comparison described above.

12. The method according to claim 11, wherein the predetermined value is 60 percent, 70 percent, 80 percent, or 90 percent.

13. At least one of the aforementioned multiple genes is 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 The method according to any one of claims 1 to 3, comprising a gene identified from 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.

14. The method according to any one of claims 1 to 3, wherein 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, a bowel transplant, or an angiogenic composite allograft transplant, or the transplant recipient has received a transplant of an allograft or a xenograft.

15. The method according to any one of claims 1 to 3, wherein the biological sample is an organ tissue sample.

16. The method according to any one of claims 1 to 3, wherein the condition of the graft indicates that an immunosuppressive treatment should be administered.

17. A kit for classifying the condition of grafts, the kit comprises: 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, CXCL13, FCER1A, B TG2, 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, EEF1A1, BCL2, SLC19A3, A kit comprising one or more probe sets, reagents, controls, and instructions for use, each specific to one or more genes identified from the group consisting of VMP1, PSEN1, MAPK3, TFF3, TNFSF4, CD55, PDPN, IL17RB, IGHG2, CXCL12, CD207, MICA, MMP9, EOMES, EPO, NOS3, KLF2, KLF4, SLC4A1, P2RX4, CCL3 / L1, and HPRT1.

18. The aforementioned kit is We obtain the expression levels of multiple genes from the biological sample of the transplant recipient. The system receives multiple sets of weights for the aforementioned multiple genes, Based on the set of weights and the expression level, one or more probabilistic rejection scores are generated for one or more rejection labels. The kit according to claim 17, further comprising instructions for assigning the predicted rejection classification of the biological sample of the transplant recipient, based on one or more probability rejection scores, wherein the predicted rejection classification classifies the state of the graft.

19. The kit according to claim 17, wherein the predicted rejection classification classifies the state of the graft as having experienced antibody-mediated rejection (ABMR), T-cell-mediated rejection (TCMR), mixed ABMR + TCMR, or no rejection.

20. Generating one or more probabilistic rejection scores for one or more rejection labels is, The kit according to any one of claims 17 to 19, comprising generating a probabilistic rejection score for each of a plurality of rejection labels based on a plurality of sets of weights and the expression level.

21. The kit according to any one of claims 17 to 19, wherein each set of weights includes the weight of the corresponding rejection label.

22. The kit according to any one of claims 17 to 19, wherein 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, a bowel transplant, or an angiogenic composite allograft transplant, or the transplant recipient has received a transplant of an allograft or a xenograft.

23. The kit according to any one of claims 17 to 19, wherein the biological sample is an organ tissue sample.

24. The kit according to any one of claims 17 to 19, wherein assigning a predicted rejection classification to the biological sample of the transplant recipient includes assigning the rejection label having the highest probability rejection score among the plurality of rejection labels as the predicted rejection classification.

25. A system for classifying the state of transplantation, wherein the system is It is a scoring unit, We obtain the expression levels of multiple genes from the biological sample of the transplant recipient. The system receives multiple sets of weights for the aforementioned multiple genes, Based on the set of weights and the expression level, one or more probabilistic rejection scores are generated for one or more rejection labels. A system comprising a scoring unit that assigns a predicted rejection classification to the biological sample of the transplant recipient, based on one or more probability rejection scores, wherein the predicted rejection classification classifies the state of the graft.

26. The system according to claim 25, wherein at least one of the plurality of genes is related to one or more of the following: activation of immune cells, organ-specific defense against pathogens, regulation of tissue and cellular processes, or transcriptional regulation.

27. The system according to claim 25, wherein the predictive rejection classification classifies the state of the graft as having experienced antibody-mediated rejection (ABMR), T-cell-mediated rejection (TCMR), mixed ABMR + TCMR, or no rejection.

28. Generating one or more probabilistic rejection scores for one or more rejection labels is, The system according to any one of claims 25 to 27, comprising generating a probabilistic rejection score for each of a plurality of rejection labels based on a plurality of sets of weights and the expression level.

29. The system according to any one of claims 25 to 27, wherein each set of weights includes the weight of the corresponding rejection label.

30. The system according to any one of claims 25 to 27, wherein assigning a predicted rejection classification to the biological sample of the transplant recipient includes assigning the rejection label having the highest probability rejection score among the plurality of rejection labels as the predicted rejection classification.

31. The sets of weights for the aforementioned multiple genes are: A discovery dataset is obtained from biological samples of a discovery cohort of transplant recipients, and the discovery dataset includes gene expression levels and rejection classifications for multiple genes. Regarding the association with the rejection classification in the aforementioned discovery dataset, the gene expression levels in the aforementioned discovery dataset are analyzed, Identifying a subset of genes from the multiple genes in the aforementioned discovery dataset, The system according to any one of claims 25 to 27, wherein, based on the association between the gene expression levels of the discovery dataset and the rejection classifications of the discovery dataset, a plurality of sets of weights for a subset of the genes, each set of weights being associated with one of the genes in the subset, is from a machine learning model trained to do the following:

32. The system according to claim 31, wherein the gene expression level is analyzed by analyzing nucleic acids or RNA from the biological samples of the discovery cohort.

33. The system according to claim 31, wherein at least some of the rejection classifications of the discovery dataset include antibody-mediated rejection (ABMR), T cell-mediated rejection (TCMR), mixed ABMR + TCMR rejection, or no rejection.

34. The system according to claim 31, wherein the expression levels of one or more genes from the plurality of genes in the discovery dataset are normalized with respect to the gene expression levels of one or more reference genes.

35. The aforementioned machine learning model, Obtaining a validation dataset from biological samples of a validation cohort of transplant recipients, wherein the validation dataset includes gene expression levels and rejection classifications for multiple genes, The process involves determining one or more computer-determined predicted rejection classifications from the aforementioned validation dataset, Comparing one or more of the rejection classifications in the validation dataset with one or more computer-determined predicted rejection classifications, The system according to claim 31, verified by determining a diagnostic accuracy, wherein the diagnostic accuracy is greater than a predetermined value, based on the comparison described above.

36. The system according to claim 35, wherein the predetermined value is 60 percent, 70 percent, 80 percent, or 90 percent.

37. At least one of the aforementioned multiple genes is 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, FCER 1A, BTG2, CTLA4, CASP3, SPRY4, RAF1, MAPK13, IGF2R, RHOU, LYVE1, CD80, KAAG1, CCL18, EHD3, IL1RL1, CRIP2, T NFSF9, CDH5, CD8B, PRDM1, SIRPG, ABCA1, ADORA2A, RASSF9, JUN, COL4A4, TRAF4, PIN1, SOX7, CFB, CFH, SFTPD, TH BS1, AIRE, RAMP3, IL1R2, GNG11, RAPGEF5, DEFB1, GNLY, PHEX, ENG, BMP7, RELA, COL1A1, PLAAT4, CD81, ICAM2, P LAT, CD40LG, NPHS2, IL33, CD58, TIPARP, TNC, PECAM1, C5, EGFR, CD2, BMP2, CTNNB1, MYB, CRHBP, MT2A, EEF1A1, B The system according to any one of claims 25 to 27, comprising a gene identified from the group consisting of CL2, 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.

38. The system according to any one of claims 25 to 27, wherein 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, a bowel transplant, or an angiogenic composite allograft transplant, or the transplant recipient has received a transplant which is an allograft or a xenograft.

39. The system according to any one of claims 25 to 27, wherein the biological sample is an organ tissue sample.

Images