lncRNA profiling in early-stage chronic lymphocytic leukemia identifies transcriptional fingerprints with relevance in clinical outcome

Abstract

Long non-coding RNAs (lncRNAs) represent a novel class of functional RNA molecules with an important emerging role in cancer. To elucidate their potential pathogenetic role in chronic lymphocytic leukemia (CLL), a biologically and clinically heterogeneous neoplasia, we investigated lncRNAs expression in a prospective series of 217 early-stage Binet A CLL patients and 26 different subpopulations of normal B-cells, through a custom annotation pipeline of microarray data. Our study identified a 24-lncRNA-signature specifically deregulated in CLL compared with the normal B-cell counterpart. Importantly, this classifier was validated on an independent data set of CLL samples. Belonging to the lncRNA signature characterizing distinct molecular CLL subgroups, we identified lncRNAs recurrently associated with adverse prognostic markers, such as unmutated IGHV status, CD38 expression, 11q and 17p deletions, and NOTCH1 mutations. In addition, correlation analyses predicted a putative lncRNAs interplay with genes and miRNAs expression. Finally, we generated a 2-lncRNA independent risk model, based on lnc-IRF2-3 and lnc-KIAA1755-4 expression, able to distinguish three different prognostic groups in our series of early-stage patients. Overall, our study provides an important resource for future studies on the functions of lncRNAs in CLL, and contributes to the discovery of novel molecular markers with clinical relevance associated with the disease.

Figure 1

LncRNA expression profile of CLL and normal B-cells samples. (a) Hierarchical clustering of the 26 normal B-cell samples using the 141 lncRNAs most variable across the data set. The red line identified five branches related to the distinct normal B-cells subtypes. (b) Principal component analysis (PCA) that includes CLL samples shows that CLLs are closer in a three-dimensional space of similarity to M, N and MZ tonsillar B-lymphocytes than to other B-cell types, based on the expression of the 226 lncRNAs resulting as differentially expressed in the five normal B-cell subset from the multiclass analysis. (c) A heatmap showing the differentially expressed lncRNAs in the training group of CLL patients compared with normal (N) 'comparator' samples. For each lncRNA, information about chromosomal localization (Chr), alias name, transcripts overlapping in sense or antisense (indicated as S or AS, respectively) direction is indicated.

Figure 2

A 2-lncRNA risk model in CLL. (a) Progression-free survival of IGHV unmutated (UM)-CLL grouped according to lnc-IRF2-3 expression levels. Kaplan–Meier estimated curves of the two groups defined by lnc-IRF2-3 high (gray) and low (black) expression levels. (b) Kaplan–Meier estimated curves of the 2-lncRNA model. CLL are divided into a low-risk group (low expression of both lncRNAs), an intermediate group (high expression of one of the two lncRNAs) and a high-risk group (high expression of both lncRNAs). The high-risk group has a median PFS of 862 days.

Figure 3

Representative enrichment plots of gene sets significantly up- and downregulated in CLL with increasing expression levels of lnc-IRF2-3 (a) or lnc-KIAA1755-4 (b) detected by gene set enrichment analysis. The green curves show the enrichment score and reflect the degree to which each gene (black vertical lines) is represented at the bottom of the ranked gene list.