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.

Beyond Human Limits: Harnessing Artificial Intelligence to Optimize Immunosuppression in Kidney Transplantation

“…Operative tolerance, a state of long-term allograft acceptance without continuous immunosuppression, is an important tenet for the success of solid organ transplantation that can help minimize exposure of immunosuppressive treatments. In a recent study, Fu et al [ 13 ], investigated the identification of potential biomarkers for allograft tolerance in kidney transplantation using ML techniques. The study utilized three publicly available gene expression datasets from peripheral blood lymphocytes of 63 tolerant patients.…”

The Value of Single-cell Technologies in Solid Organ Transplantation Studies

“…A T-cell population expressing programmed cell death protein 1 had the greatest influence on the principle component segregation, suggesting that this immune cell population could be a key indicator of the risk of rejection. 145 Using microarray gene expression data, Fu et al 146 recently compared different machine-learning models to predict renal allograft tolerance. The predictive power of such machine-learning algorithms could possibly be enhanced with scRNAseq data: cluster-specific differential gene expressions can get lost in bulk sequencing, and gene expression within a specific cell subset might provide better predictions that the gene expression of all immune cells.…”

Natural killer cells in liver transplantation: Can we harness the power of the immune checkpoint to promote tolerance?

“…Machine learning may aid in future efforts to improve precision medicine techniques during liver transplantation. Indeed, genetic predictive models of tolerance during solid organ transplant have been established via machine learning in kidney 109 and pancreatic islet cell transplant. 110 Potentially, these methodologies could be used to decipher the KIR‐HLA axis and find other positive phenotype matches for liver transplantation.…”