Dataset Information

An unbiased machine learning exploration reveals gene sets predictive of allograft tolerance after kidney transplantation

ABSTRACT: Efforts at finding potential biomarkers of tolerance after kidney transplantation have been hindered by limited sample size, as well as the complicated mechanisms underlying tolerance and the potential risk of rejection after immunosuppressant withdrawal. In this work, three different publicly available genome-wide expression data sets of peripheral blood lymphocyte (PBL) from 63 tolerant patients were used to compare 14 different machine learning models for their ability to predict spontaneous kidney graft tolerance. We found that the Best Subset Selection (BSS) regression approach was the most powerful with a sensitivity of 91.7% and a specificity of 93.8% in the test group, and a specificity of 86.1% and a sensitivity of 80% in the validation group. A feature set with five genes (HLA-DOA, TCL1A, EBF1, CD79B, and PNOC) was identified using the BSS model. EBF1 downregulation was also an independent factor predictive of graft rejection and graft loss. An AUC value of 84.4% was achieved using the two-gene signature (EBF1 and HLA-DOA) as an input to our classifier. Overall, our systematic machine learning exploration suggests novel biological targets that might affect tolerance to renal allografts, and provides clinical insights that can potentially guide patient selection for immunosuppressant withdrawal.

ORGANISM(S): Homo sapiens

PROVIDER: GSE166865 | GEO | 2021/06/04

REPOSITORIES: GEO

ACCESS DATA

Dataset's files

Source:

			Action	DRS
		Other

Items per page:

1 - 1 of 1

Similar Datasets

Project description:Background Immune tolerance and persistent mixed chimerism can be achieved reproducibly after combined organ and hematopoietic cell transplantation in mice conditioned with total lymphoid irradiation plus anti-thymocyte globulin. We studied the safety and reproducibility of this approach in a cohort of kidney transplant patients, and tried to identify immune monitoring procedures that can predict tolerance and guide complete immunosuppressive drug withdrawal. Methods Ten patients conditioned with 10 doses of total lymphoid irradiation and 5 doses of anti-thymocyte globulin were given kidney transplants and an injection of CD34+ hematopoietic progenitor cells and T cells from HLA matched donors. Blood cell monitoring included changes in chimerism, balance of T cell subsets, gene expression, and responses to donor alloantigens. Results Nine of 10 patients developed multi-lineage chimerism without graft versus host disease (GVHD), and all had excellent graft function at the last observation point. Five of these with chimerism persisting for at least 12 months were completely withdrawn from immunosuppressive drugs for 6 to 35 months. Blood cells from patients off drugs showed development of specific unresponsiveness to donor alloantigens, M-bM-^@M-^\toleranceM-bM-^@M-^] profiles on gene microarrays, early high ratios of regulatory versus conventional naM-CM-/ve T cells, and early high levels of chimerism among NK cells. Conclusions Total lymphoid irradiation, and anti-thymocyte globulin promoted the development of persistent chimerism and tolerance in a cohort of patients given kidney transplants and donor cell injections. Assays were identified that can assist in the safe withdrawal of immunosuppressive drugs. 45 Agilent Microarray samples were conducted, including 16 tolerance patients, 10 chronic rejection patients, 5 healthy normal controls, and 7 paired pre and post-transplant induced tolerance patients. The aim is to see whether induced tolerance patients show operational tolerance gene expression signature and can withdraw or minimize the immunosuppression regimens.

Dataset Information

An unbiased machine learning exploration reveals gene sets predictive of allograft tolerance after kidney transplantation

Dataset's files

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets