RNA Sequencing of Whole Blood Defines the Signature of High Intensity Exercise at Altitude in Elite Speed Skaters

Abstract

Although high altitude training has been increasingly popular among endurance athletes, the molecular and cellular bases of this adaptation remain poorly understood. We aimed to define the underlying physiological changes and screen for potential biomarkers of adaptation using transcriptional profiling of whole blood. Seven elite female speed skaters were profiled on the 18th day of high-altitude adaptation. Whole blood RNA-seq before and after an intense 1 h skating bout was used to measure gene expression changes associated with exercise. In order to identify the genes specifically regulated at high altitudes, we have leveraged the data from eight previously published microarray datasets studying blood expression changes after exercise at sea level. Using cell type-specific signatures, we were able to deconvolute changes of cell type abundance from individual gene expression changes. Among these were PHOSPHO1, with a known role in erythropoiesis, and MARC1 with a role in endogenic NO metabolism. We find that platelet and erythrocyte counts uniquely respond to altitude exercise, while changes in neutrophils represent a more generic marker of intense exercise. Publicly available data from both single cell atlases and exercise-related blood profiling dramatically increases the value of whole blood RNA-seq for the dynamic evaluation of physiological changes in an athlete's body.

Keywords: RNA sequencing; RNA-seq; elite athletes; exercise; expression profiling; high altitude adaptation; live high; platelets; speed skating; train high (LHTH); whole blood.

Figure 1

Overall assessment and differential expression analysis of whole blood RNA-seq from seven altitude-adapted female skaters before and after exercise. Differential expression analysis was performed using DESeq2 and “donor + exercise” design. Differentially expressed genes were reported at 10% FDR. “Up-regulated” indicates genes whose expression increased after the exercise. (a,b) PCA plot of the 14 studied samples, before and after donor-effect correction using comBat. Top 18,000 genes were used. Read counts were normalized using the rlog function from the DESeq2 package. (c) Log ratio—mean expression (MA) plot, with marked differentially expressed genes. (d) Number of differentially expressed genes depending on mean expression cutoff; TPM, transcripts per million. (e) Volcano plot of differentially expressed genes. Point size is scaled proportionally to mean gene expression.

Figure 2

Gene overrepresentation and gene set enrichment (GSEA) analysis of the differentially expressed genes. Molecular signature database (MsigDB) H and CP collections were used to functionally characterize expression changes. Letter following the pathway name denotes its source: R, Reactome; K, KEGG; W, WikiPathways. (a–c) Top 10 significantly up- and down-regulated pathways, according to Fisher’s exact test, calculated with clusterProfiler. Down-regulated hallmark pathways only included one significant gene set (HALLMARK MYC TARGETS V2), and were omitted from the plot. (d–f) Top 10 significantly up- and down-regulated pathways according to GSEA, calculated with fGSEA. Down-regulated hallmark pathways only included one significant gene set (HALLMARK MYC TARGETS V2) and were omitted from the plot. Gene overlap indicates the number of genes in the leading edge.

Figure 3

Using single cell markers to infer changes of the cell types from the whole blood RNA-seq data. Twenty markers specific to the 12 listed blood cell types were derived using two public single cell RNA-seq datasets (Methods). Donor-corrected, rlog-transformed expression matrix was used for all heatmap plots. Wilcoxon ranked sum p-value notation: ***, p < 0.001; **, p < 0.01; -, p ≥ 0.05. (a) Observed gene expression of 20 cell type markers in all seven profiled donors. (b) Cell types that increase after the exercise: neutrophils, CD14+ monocytes, platelets, and erythrocytes. (c) Cell types that decrease after the exercise: CD4+ memory T cells, CD8+ T cells, natural killer cells, B cells, and plasmacytoid dendritic cells. (d) Cell types that did not display concerted change in markers: CD4+ naive T cells, CD16+ monocytes, and myeloid dendritic cells.

Figure 4

Analysis of genes uniquely up- or down-regulated in our dataset, as compared to seven public microarray datasets. Full list of datasets is given in Supplementary Table S1. (a) Volcano plot of genes uniquely regulated in the whole blood of altitude-adapted skaters. Light blue points indicate differentially expressed genes previously seen in at least one other exercise dataset. Point size is scaled proportionally to mean gene expression. (b) A circle plot representing the enrichment of cell type markers among all differentially expressed genes and altitude-specific differentially expressed genes. The size of the circle is proportional to the percentage of marker genes in the target set, and the fill of the circle corresponds to the significance levels of Fisher’s exact test. (c) Heatmap of highly expressed (TPM > 10) and regulated (absolute log fold change > 0.5) genes unique to our dataset. Breakdown by cell type is conducted based on single cell markers defined earlier. Rows are sorted by cell type and then by log fold change.