Comparative Analyses of Signature Genes in Acute Rejection and Operational Tolerance

Abstract

Using biomarkers as prediction tools or therapeutic targets can be a valuable strategy in transplantation. Recent studies identified biomarkers of acute rejection (AR) and operational tolerance (TOL) through the application of meta-analysis. In this study, we comparatively analyzed the signature genes in acute rejection and operational tolerance seen in human allogeneic transplantations using massive bioinformatical meta-analysis. To identify the signature genes in opposite immunological conditions, AR and TOL, we first collected the 1,252 gene expression data specifically intended for those circumstances. Then we excluded based on biological cut-values, Principal Component Analysis (PCA) as well as Multi-Dimensional Scaling (MDS). Using differentially expressed genes (DEGs) from meta-analysis, we then applied a ranked scoring system to identify the signature genes of AR and TOL. We identified 53 up-regulated and 32 down-regulated signature genes in acute rejection condition. Among them, ISG20, CXCL9, CXCL10, CCL19, FCER1G, PMSE1, UBD are highly expressed in AR condition. In operational tolerance, we identified 110 up-regulated and 48 down-regulated signature genes. TCL1A, BLNK, MS4A1, EBF1, IGHM are up-regulated in TOL condition. These genes are highly representative of AR or TOL across the different organs such as liver, kidney and heart. Since immune response is the sum of complex biological and molecular dynamics, these signature genes as well as pathway analysis using a systems biology approach could be used to catch the insights of the certain pathways that would be overlooked with the conventional gene-level comparative analysis.

Keywords: Graft rejection; Signature genes; Systems biology; Transplantation tolerance.

Figure 1

Global analysis of total AR and TOL groups with experimental strategy. (A) Global PCA results using 7 different microarray datasets related to AR. Each group made different clusters regardless of what condition they have. (B) A heart microarray dataset (GDS1684) shows wide spread global expression data and not well distinguished data clustering. It is excluded for later investigation. (C) Heat map visualization with AR global analysis. We selected only 200 genes in each direction (up-regulated and down-regulated). (D) Global PCA results using 4 different microarray datasets related to TOL. The datasets are significantly biased because of wide spreading patterns of kidney GSE4775 datasets. (E) Global PCA results without GSE4775 data. Each group made different clusters regardless of what condition they have. (F) Heat map visualization with TOL global analysis. We selected only 200 genes in each direction (up-regulated and down-regulated). (G) Comprehensive key experimental strategy features.

Figure 2

Analysis of PCA and Heatmap visualization of DEGs in AR group sets. (A) PCA analysis of AR microarray datasets obtained from GEO. The organ names of each data are shown at the top with GSE number. Stable condition is visualized in triangle and AR in circle. (B) Heatmap visualization of DEGs in AR group sets. We identified 200 up-regulated and 200 down-regulated genes in AR group.

Figure 3

Analysis of PCA and Heatmap visualization of DEGs in TOL group sets. (A) PCA analysis of TOL microarray datasets obtained from GEO. The organ names of each data are shown at the top with GSE number. Stable condition is visualized in triangle and TOL in circle. (B) Heatmap visualization of DEGs in TOL group sets. We identified 200 up-regulated and 200 down-regulated genes in TOL group.

Figure 4

Scoring visualization of AR signature genes and TOL signature genes. (A) Scoring visualization of up-regulated and down-regulated signature genes in AR condition. (B) Scoring visualization of up-regulated and down-regulated signature genes in TOL condition. Using DEGs of each datasets in AR, we identified the signature genes. Note X axis is a score, while Y is a ratio of up- and down-score/base score. Base score is determined by the total number of array sets containing a specific gene. Dashed circles are the boundary of the signature genes in each panel.

Figure 5

Expression pattern and validation of signature genes across organs. (A) Expression patterns of top 5 genes in the signature genes of AR condition. Table shows the global average expression level of the signature genes in AR sorted by score. (B) Expression patterns of top 5 genes in the signature genes of TOL condition. Table shows the global average expression level of the signature genes in TOL sorted by score.