Distinct lncRNA transcriptional fingerprints characterize progressive stages of multiple myeloma

Abstract

Although many efforts have recently contributed to improve our knowledge of molecular pathogenesis of multiple myeloma (MM), the role and significance of long non-coding RNAs (lncRNAs) in plasma cells (PC) malignancies remains virtually absent. To this aim, we developed a custom annotation pipeline of microarray data investigating lncRNA expression in PCs from 20 monoclonal gammopathies of undetermined significance, 33 smoldering MM, 170 MM, and 36 extra-medullary MMs/plasma cell leukemia patients, and 9 healthy donors. Our study identified 31 lncRNAs deregulated in tumor samples compared to normal controls; among these, the upregulation of MALAT1 appeared associated in MM patients with molecular pathways involving cell cycle regulation, p53-mediated DNA damage response, and mRNA maturation processes. Furthermore, we found 21 lncRNAs whose expression were progressively deregulated trough the more aggressive stages of PC dyscrasia, suggesting a possible role in the progression of the disease. Finally, in the context of molecular heterogeneity of MM, we identified a transcriptional fingerprint in hyperdiploid patients, characterized by the upregulation of lncRNAs/pseudogenes related to ribosomal protein genes, known to be upregulated in this molecular group. Overall, the data provides an important resource for future studies on the functions of lncRNAs in the pathology.

Keywords: MALAT1; expression profiling; lncRNA; multiple myeloma; plasma cell dyscrasia.

Figure 1. Custom annotation pipeline

Flow diagram highlighting the different steps for processing the Gene 1.0 ST array data to investigate lncRNAs in combined databases (GSE66293 and GSE47552).

Figure 2. LncRNA expression profiling in plasma cell dyscrasia

Hierarchical clustering of the 268 samples using the 230 most variable lncRNAs (patients in columns, lncRNAs in rows). The color scale bar represents the relative lncRNA expression changes normalized by the standard deviation. Color above the matrix indicates the type of samples: white, light blue, pink, yellow, and red represent Normal (N), MGUS, SMM, MM, and PCL samples, respectively. Specific types are enriched in colored sub-branches (see text). Black box identifies lncRNAs strongly upregulated in normal samples (see text).

Figure 3. Identification of lncRNA signatures characterizing distinct MM genetic subgroups

Heatmap of the differentially expressed lncRNAs in 129 MM patients stratified into the five molecular groups as specified in methods; black boxes indicate the ten most differentially expressed lncRNAs resulting from the supervised analysis comparing each subgroup versus the rest of the dataset. LncRNA expression levels in normal plasma cells are shown on the right. For each lncRNA, information about chromosomal localization (Chr), alias name, transcripts overlapping in sense or antisense (indicated as S or AS, respectively) direction, and the Pearson's correlation coefficient between lncRNA and the overlapping transcript (when detected by the array) are indicated. For lncRNAs/pseudogenes, the last column reports the putative parental gene and the Pearson's correlation coefficient between lncRNA and the parental gene expression when detected by the array. ^a Sense (S) to, or Antisense (AS) to overlapping transcripts; ^b NA indicates transcripts not detected by the array; ^c PsG =pseudogene; Ensembl type: PP= Processed Pseudogene; UP= Unitary Pseudogene; UnP= Unprocessed Pseudogene; M= miscellaneous RNA.

Figure 4. Quantitative RT-PCR validation of lncRNA expression in 60 MM cases

A. Box plots of lnc-SPRYD7-1 and lnc-SERPINC1-1 expression show a significant correlation with group membership based on Wilcoxon rank-sum tests (p-values are shown above each panel). The expression levels are represented as 2^−ΔCt. B. MALAT1 expression validation; Pearson's correlation coefficient was calculated between GEP data and quantitative RT-PCR results expressed as 2^−ΔCt. C. Genomic map of lncRNAs (red) and antisense genes (blue) with custom primers (green) localization. Sense or antisense chromosomal position (St+ or St-, respectively) are specified. For lnc-LRRC47-1, the scheme was limited to longer transcripts. Pearson's correlation coefficient was calculated between GEP data and quantitative RT-PCR results expressed as 2^−ΔCt.

Figure 5. MALAT1 expression deregulation in MM patients

A. Box plot of MALAT1 expression level in 9 N, 20 MGUS, 33 SMM, 170 MM, and 36 PCL samples, as detected by GEP; p-value was calculated by Kruskal-Wallis rank sum test. B. Heatmap of the 518 differentially expressed lncRNAs identified by comparing the first vs fourth quartile of 129 MM patients stratified into four groups based on MALAT1 expression level. C. Gene sets significantly up- and down-regulated in MALAT1 quartile IV versus I. Gene sets were selected on nominal p-value<0.01 and are ordered according to NES value. D. Enrichment plot of “DNA damage response signal transduction resulting in induction of apoptosis” gene set detected by GSEA. 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. Genes contributing to the core enrichment in the gene set are indicated in bold.