Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2023 Jan-Dec:32:9636897231195116.
doi: 10.1177/09636897231195116.

A Machine Learning Analysis of Prognostic Genes Associated With Allograft Tolerance After Renal Transplantation

Zhibiao Li  1 , Zechao Lu  1 , Chuxian Hu  2 , Yixin Zhang  3   4 , Yushu Chen  1 , Jiahao Zhang  1 , Feng Guo  1 , Jinjin Wang  1 , Zhicheng Tang  1 , Fucai Tang  1 , Zhaohui He  1
Affiliations

A Machine Learning Analysis of Prognostic Genes Associated With Allograft Tolerance After Renal Transplantation

Zhibiao Li et al. Cell Transplant. 2023 Jan-Dec.

Abstract

In this study, we aimed to identify transplantation tolerance (TOL)-related gene signature and use it to predict the different types of renal allograft rejection performances in kidney transplantation. Gene expression data were obtained from the Gene Expression Omnibus (GEO) database, differently expressed genes (DEGs) were performed, and the gene ontology (GO) function enrichment and Kyoto Encyclopedia of Genes and Genomes (KEGG) pathway enrichment analysis were also conducted. The machine learning methods were combined to analyze the feature TOL-related genes and verify their predictive performance. Afterward, the gene expression levels and predictive performances of TOL-related genes were conducted in the context of acute rejection (AR), chronic rejection (CR), and graft loss through heatmap plots and the receiver operating characteristic (ROC) curves, and their respective immune infiltration results were also performed. Furthermore, the TOL-related gene signature for graft survival was conducted to discover gene immune cell enrichment. A total of 25 TOL-related DEGs were founded, and the GO and KEGG results indicated that DEGs mainly enriched in B cell-related functions and pathways. 7 TOL-related gene signature was constructed and performed delightedly in TOL groups and different types of allograft rejection. The immune infiltration analysis suggested that gene signature was correlated with different types of immune cells. The Kaplan-Meier (KM) survival analysis demonstrated that BLNK and MZB1 were the prognostic TOL-related genes. Our study proposed a novel gene signature that may influence TOL in kidney transplantation, providing possible guidance for immunosuppressive therapy in kidney transplant patients.

Keywords: GEO; kidney transplantation; machine learning; transplantation tolerance.

PubMed Disclaimer

Conflict of interest statement

The author(s) declared no potential conflicts of interest with respect to the research, authorship, and/or publication of this article.

Figures

Figure 1.
Figure 1.
The Venn diagram of identified DEGs for intersections between different samples. (A) The intersection DEGs among HV, TOL, and STA patients. (B) The intersection DEGs in the TOL–STA and HV–TOL cohorts. (C) The intersection DEGs in the TOL–STA and HV–STA cohorts. (D) PCA plot for the STA and TOL groups. DEGs: differently expressed genes; HV: healthy volunteer; TOL: transplantation tolerance; STA: stable function; PCA: principal component analysis; PC1: first principal component; PC2: second principal component.
Figure 2.
Figure 2.
The gene functional enrichment and GSEA enrichment plots. (A) The GO function enrichment cluster plot. (B) The KEGG pathway enrichment cluster plot. (C) The GSEA enrichment plot in the TOL cohort. (D) The GSEA enrichment plot in the STA cohort. GSEA: gene set enrichment analysis; GO: gene ontology; KEGG: Kyoto Encyclopedia of Genes and Genomes; TOL: transplantation tolerance; STA: stable function.
Figure 3.
Figure 3.
The LASSO and SVM-RFE analysis results. (A) The 10-time cross-validation method was applied in the LASSO model. (B) Screened out the feature gene signature. (C) The SVM-RFE method to identify the feature gene signature. (D) The intersection of the screened gene signature by LASSO and SVM-RFE analysis. LASSO: the least absolute shrinkage and selection operator; SVM: support vector machine; RFE: recursive feature elimination; RMSE: root mean square error.
Figure 4.
Figure 4.
The heatmap and ROC curves in TOL training and testing set. (A) The heatmap plot of the TOL training set. (B) The ROC curve for predicting the TOL-related gene signature performance in TOL training set. (C) The heatmap plot of the TOL testing set. (D) The ROC curve for predicting the TOL-related gene signature performance in TOL testing set. ROC: receiver operating characteristic; TOL: transplantation tolerance.
Figure 5.
Figure 5.
Immune infiltration result in the TOL group. (A) The bar plot of the enriched immune cells in TOL and STA samples. (B) The violin plot of the enriched immune cells in TOL and STA samples. TOL: transplantation tolerance; STA: stable function; NK: natural killer.
Figure 6.
Figure 6.
The heatmap and ROC curves in the AR, CR, and graft loss groups. (A) The heatmap plot of the AR group. (B) The ROC curve for predicting the TOL-related gene signature performance in the AR group. (C) The heatmap plot of the CR group. (D) The ROC curve for predicting the TOL-related gene signature performance in the CR group. (E) The heatmap plot of the graft loss group. (F) The ROC curve for predicting the TOL-related gene signature performance in the graft loss group. ROC: receiver operating characteristic; AR: acute rejection; CR: chronic rejection; TOL: transplantation tolerance.
Figure 7.
Figure 7.
Immune infiltration result in the AR, CR, and graft loss groups. (A) The bar plot of the enriched immune cells in the NAR and AR samples. (B) The violin plot of the enriched immune cells in the NAR and AR samples. (C) The bar plot of the enriched immune cells in the TOL and CR samples. (D) The violin plot of the enriched immune cells in the TOL and CR samples. (E) The bar plot of the enriched immune cells in the graft survival and graft loss samples. (F) The violin plot of the enriched immune cells in the graft survival and graft loss samples. AR: acute rejection; NAR: non-acute rejection; CR: chronic rejection; TOL: transplantation tolerance; NK: natural killer.
Figure 8.
Figure 8.
The graft survival analysis of the TOL-related gene signature. (A) The KM plot analysis between BLNK high-expression and BLNK low-expression samples. (B) The KM plot analysis between MZB1 high-expression and MZB1 low-expression samples. TOL: transplantation tolerance; KM: Kaplan–Meier.
Figure 9.
Figure 9.
BLNK- and MZB1-enriched immune infiltration result in different groups. (A) The lollipop plot of the BLNK-enriched immune cells in the TOL group. (B) The lollipop plot of the MZB1-enriched immune cells in the TOL group. (C) The lollipop plot of the BLNK-enriched immune cells in the AR group. (D) The lollipop plot of the MZB1-enriched immune cells in the AR group. (E) The lollipop plot of the BLNK-enriched immune cells in the CR group. (F) The lollipop plot of the MZB1-enriched immune cells in the CR group. (G) The lollipop plot of the BLNK-enriched immune cells in the graft loss group. (H) The lollipop plot of the MZB1-enriched immune cells in the graft loss group. TOL: transplantation tolerance; AR: acute rejection; CR: chronic rejection; NK: natural killer.
See this image and copyright information in PMC

Similar articles

See all similar articles

References

    1. Meng M, Zhang W, Tang Q, Yu B, Li T, Rong R, Zhu T, Xu M, Shi Y. Bioinformatics analyses on the immune status of renal transplant patients, a systemic research of renal transplantation. BMC Med Genomics. 2020;13(1):24. - PMC - PubMed
    1. Kakkar B, Makroo RN, Agrawal S, Chowdhry M, Nayak S, Jasuja S, Sagar G, Guleria S. Role of therapeutic plasma exchange in acute humoral rejection patients undergoing live-related renal transplantation: a single-center experience. Asian J Transfus Sci. 2021;15(1):62–67. - PMC - PubMed
    1. Rodrigue JR, Kazley AS, Mandelbrot DA, Hays R, LaPointe Rudow D, Baliga P, American Society of Transplantation. Living donor kidney transplantation: overcoming disparities in live kidney donation in the US–recommendations from a consensus conference. Clin J Am Soc Nephrol. 2015;10(9):1687–95. - PMC - PubMed
    1. Lv C, Chen M, Xu M, Xu G, Zhang Y, He S, Xue M, Gao J, Yu M, Gao X, Zhu T. Influencing factors of new-onset diabetes after a renal transplant and their effects on complications and survival rate. PLoS ONE. 2014;9(6): e99406. - PMC - PubMed
    1. Nafar M, Farrokhi F, Hemati K, Pour-Reza-Gholi F, Firoozan A, Einollahi B. Plasmapheresis in the treatment of early acute kidney allograft dysfunction. Exp Clin Transplant. 2006;4(2):506–509. - PubMed

Publication types