Genomic prediction of relapse in recipients of allogeneic haematopoietic stem cell transplantation

Liquid Biopsy, a Potential New Detection Method in Heart Allograft Rejection

Allografts rejection remains the most important reason causing allograft dysfunction in heart transplantation recipients. Currently, the golden standard for detecting graft rejection is endomyocardial biopsy (EMB). As a new noninvasive technique, liquid biopsy emerges along with the great developments of droplet-based digital PCR and the various optimizations of next-generation sequencing technologies, which is also cheaper than EMB. This review introduces several types of liquid biopsy and its application in heart transplantation.

A systematic review of the predicted outcomes related to hematopoietic stem cell transplantation: focus on applied machine learning methods' performance

INTRODUCTION

: Hematopoietic stem cell transplantation (HSCT) is a critical therapeutic procedure in blood diseases, and the investigation of HSCT data can provide valuable information. Machine learning (ML) techniques are novel and useful data analysis tools that have been applied in many studies to predict HSCT survival and estimate the risk of transplantation.

AREAS COVERED

: A systematic review was performed with a search of PubMed, Science Direct, Embase, Scopus, and the European Society for Blood and Marrow Transplantation, the Center for International Blood and Marrow Transplant Research, and the American Society for Transplantation and Cellular Therapy publications for articles published by September 2020.

EXPERT OPINION

: After investigating the results, 24 papers that met eligibility criteria were included in this study. The applied ML algorithms with the highest performance were Random Survival Forests (AUC=0.72) for survival-related, Random Survival Forests and Logistic Regression (AUC=0.77) for mortality-related, Deep Learning (AUC=0.8) for relapse, L2-Regularized Logistic Regression (AUC=0.66) for Acute-Graft Versus Host Disease, Random Survival Forests (AUC=0.88) for sepsis, Elastic-Net Regression (AUC=0.89) for cognitive impairment, and Bayesian Network (AUC=0.997) for oral mucositis outcome. This review reveals the potential of ML techniques to predict HSCT outcomes and apply them to developing clinical decision support systems.

A Systematic Review of Machine Learning Techniques in Hematopoietic Stem Cell Transplantation (HSCT)

Machine learning techniques are widely used nowadays in the healthcare domain for the diagnosis, prognosis, and treatment of diseases. These techniques have applications in the field of hematopoietic cell transplantation (HCT), which is a potentially curative therapy for hematological malignancies. Herein, a systematic review of the application of machine learning (ML) techniques in the HCT setting was conducted. We examined the type of data streams included, specific ML techniques used, and type of clinical outcomes measured. A systematic review of English articles using PubMed, Scopus, Web of Science, and IEEE Xplore databases was performed. Search terms included "hematopoietic cell transplantation (HCT)," "autologous HCT," "allogeneic HCT," "machine learning," and "artificial intelligence." Only full-text studies reported between January 2015 and July 2020 were included. Data were extracted by two authors using predefined data fields. Following PRISMA guidelines, a total of 242 studies were identified, of which 27 studies met the inclusion criteria. These studies were sub-categorized into three broad topics and the type of ML techniques used included ensemble learning (63%), regression (44%), Bayesian learning (30%), and support vector machine (30%). The majority of studies examined models to predict HCT outcomes (e.g., survival, relapse, graft-versus-host disease). Clinical and genetic data were the most commonly used predictors in the modeling process. Overall, this review provided a systematic review of ML techniques applied in the context of HCT. The evidence is not sufficiently robust to determine the optimal ML technique to use in the HCT setting and/or what minimal data variables are required.

Review of Genetic Variation as a Predictive Biomarker for Chronic Graft-Versus-Host-Disease After Allogeneic Stem Cell Transplantation

Chronic graft-versus-host disease (cGvHD) is one of the major complications of allogeneic stem cell transplantation (HSCT). cGvHD is an autoimmune-like disorder affecting multiple organs and involves a dermatological rash, tissue inflammation and fibrosis. The incidence of cGvHD has been reported to be as high as 30% to 60% and there are currently no reliable tools for predicting the occurrence of cGvHD. There is therefore an important unmet clinical need for predictive biomarkers. The present review summarizes the state of the art for genetic variation as a predictive biomarker for cGvHD. We discuss three different modes of action for genetic variation in transplantation: genetic associations, genetic matching, and pharmacogenetics. The results indicate that currently, there are no genetic polymorphisms or genetic tools that can be reliably used as validated biomarkers for predicting cGvHD. A number of recommendations for future studies can be drawn. The majority of studies to date have been under-powered and included too few patients and genetic markers. Like in all complex multifactorial diseases, large collaborative genome-level studies are now needed to achieve reliable and unbiased results. Some of the candidate genes, in particular, CTLA4, HSPE, IL1R1, CCR6, FGFR1OP, and IL10, and some non-HLA variants in the HLA gene region have been replicated to be associated with cGvHD risk in independent studies. These associations should now be confirmed in large well-characterized cohorts with fine mapping. Some patients develop cGvHD despite very extensive immunosuppression and other treatments, indicating that the current therapeutic regimens may not always be effective enough. Hence, more studies on pharmacogenetics are also required. Moreover, all of these studies should be adjusted for diagnostic and clinical features of cGvHD. We conclude that future studies should focus on modern genome-level tools, such as machine learning, polygenic risk scores and genome-wide association study-transcription meta-analyses, instead of focusing on just single variants. The risk of cGvHD may be related to the summary level of immunogenetic differences, or whole genome histocompatibility between each donor-recipient pair. As the number of genome-wide analyses in HSCT is increasing, we are approaching an era where there will be sufficient data to incorporate these approaches in the near future.

Donor genetic backgrounds contribute to the functional heterogeneity of stem cells and clinical outcomes

Stable and sustainable stem cell sources for stem cell‐based therapies are scarce and a key bottleneck for clinical applications. The regenerative potential of stem cells is usually attributed to several allogeneic or even autologous donor‐related factors. Genetic background and epigenetic variations in different individuals may significantly affect the functional heterogeneity of stem cells. Particularly, single‐nucleotide polymorphisms (SNPs) have been implicated in diseases with monogenetic or multifactorial and complex genetic etiologies. However, the possible effects of individual SNPs on donor stem cells remain far from fully elucidated. In this Perspective, we will discuss the roles played by donor genetic traits in the functional heterogeneity of induced pluripotent stem cells, mesenchymal stem cells, and hematopoietic stem cells and their implications for regenerative medicine and therapy.

Meta-Analysis of Genome-Wide Association and Gene Expression Studies Implicates Donor T Cell Function and Cytokine Pathways in Acute GvHD

Graft-vs.-host disease (GvHD) is a major complication after allogeneic hematopoietic stem cell transplantation that causes mortality and severe morbidity. Genetic disparities in human leukocyte antigens between the recipient and donor are known contributors to the risk of the disease. However, the overall impact of genetic component is complex, and consistent findings across different populations and studies remain sparse. To gain a comprehensive understanding of the genes responsible for GvHD, we combined genome-wide association studies (GWAS) from two distinct populations with previously published gene expression studies on GvHD in a single gene-level meta-analysis. We hypothesized that genes driving GvHD should be associated in both data modalities and therefore could be detected more readily through their combined effects in the integrated analysis rather than in separate analyses. The meta-analysis yielded a total of 51 acute GvHD-associated genes (false detection rate [FDR] <0.1). In support of our hypothesis, this number was significantly higher than that in a permutation meta-analysis involving the whole data set, as well as in separate meta-analyses on the GWAS and gene expression data sets. The genes indicated by the meta-analysis were significantly enriched in 277 Gene Ontology terms (FDR < 0.05), such as T cell function and cytokine-mediated signaling pathways, and the results highlighted several established immune mediators, such as interleukins and JAK-STAT signaling, and presented TRAF6 and TERT as potential effector candidates. Altogether, the results support the chosen methodological approach, implicate a role of gene-level variation in donors' key immunological regulators predisposing patients to acute GVHD, and present potential targets for therapeutic intervention.

Computational Analysis of HLA-presentation of Non-synonymous Recipient Mismatches Indicates Effect on the Risk of Chronic Graft-vs.-Host Disease After Allogeneic HSCT

Genetic mismatches in protein coding genes between allogeneic hematopoietic stem cell transplantation (allo-HSCT) recipient and donor can elicit an alloimmunity response via peptides presented by the recipient HLA receptors as minor histocompatibility antigens (mHAs). While the impact of individual mHAs on allo-HSCT outcome such as graft-vs.-host and graft-vs.-leukemia effects has been demonstrated, it is likely that established mHAs constitute only a small fraction of all immunogenic non-synonymous variants. In the present study, we have analyzed the genetic mismatching in 157 exome-sequenced sibling allo-HSCT pairs to evaluate the significance of polymorphic HLA class I associated peptides on clinical outcome. We applied computational mismatch estimation approaches based on experimentally verified HLA ligands available in public repositories, published mHAs, and predicted HLA-peptide affinites, and analyzed their associations with chronic graft-vs.-host disease (cGvHD) grades. We found that higher estimated recipient mismatching consistently increased the risk of severe cGvHD, suggesting that HLA-presented mismatching influences the likelihood of long-term complications in the patient. Furthermore, computational approaches focusing on estimation of HLA-presentation instead of all non-synonymous mismatches indiscriminately may be beneficial for analysis sensitivity and could help identify novel mHAs.