Long noncoding RNAs with enhancer-like function in human cells

Abstract

While the long noncoding RNAs (ncRNAs) constitute a large portion of the mammalian transcriptome, their biological functions has remained elusive. A few long ncRNAs that have been studied in any detail silence gene expression in processes such as X-inactivation and imprinting. We used a GENCODE annotation of the human genome to characterize over a thousand long ncRNAs that are expressed in multiple cell lines. Unexpectedly, we found an enhancer-like function for a set of these long ncRNAs in human cell lines. Depletion of a number of ncRNAs led to decreased expression of their neighboring protein-coding genes, including the master regulator of hematopoiesis, SCL (also called TAL1), Snai1 and Snai2. Using heterologous transcription assays we demonstrated a requirement for the ncRNAs in activation of gene expression. These results reveal an unanticipated role for a class of long ncRNAs in activation of critical regulators of development and differentiation.

Figure 1. Identification of novel long ncRNAs in human annotated by GENCODE

(A) Analysis of coding potential using Gene ID for ancestral repeats (AR), long ncRNAs annotated by GENCODE and protein-coding genes. (B) Conservation of the genomic transcript sequences for AR, long ncRNAs, protein-coding genes, and (C) of their promoters. (D) Expression analysis of 3,019 long ncRNA in human fibroblasts, HeLa cells and primary human keratinocytes, showing numbers for transcripts detected in each cell line and the overlaps between cell lines. All microarray experiments have been done in four replicates. See also Figure S1 and Tables S1 and S2.

Figure 2. Long ncRNAs display responsiveness to differentiation signals in human primary keratinocytes

(A and B) Distribution of differentially expressed transcripts (dark colors) following TPA treatment for long ncRNAs (A), and mRNAs (B). Lighter colors show total number of transcripts, darker colors and percentage show number of differentially expressed transcripts. Bar-plots show number and fractions of transcripts induced (red) or repressed (green) at different fold-change cut-offs. (C) Gene onthology analysis of genes flanking the differentially expressed long ncRNAs (red) compared to genes flanking random positions (black). (D) Graphic representation of a locus with induction of the long ncRNA ncRNA-a1 and the adjacent ECM1 gene, with expression values from microarrays (upper panel) and qPCR quantification of transcripts (lower panel). Microarray experiments and qPCR validation are done in four replicates. Data shown are mean +/− S.D. See also Figure S2 and Table S3.

Figure 3. Stimulation of gene expression by activating RNAs

The thick black line representing each gene shows the span of the genomic region including exons and introns. The targeted activating RNAs are shown in red. Bar-plots show RNA levels as determined by triplicate qPCR experiments and represent at least three independent experiments. (A) ncRNA-a1 locus in HEK293 cells. (B) ncRNA-a2 locus in HeLa cells. (C) ncRNA-a3 locus in MCF-7 cells. (D) ncRNA-a4 locus in Jurkat cells. (E) ncRNA-a5 locus in HeLa cells. (F) ncRNA-a6 locus in A549 cells. All values are relative to GAPDH expression and relative to control siRNA transfected cells set to an average value of 1. Scale bar is 100 kb and applies to all figure panels. Error bars show +/− S.E.M. * p < 0.05, ** p < 0.01, *** p < 0.001 by two-tailed Student’s T-test. See also Figure S3 and Table S4. The results represent at least six independent experiments. See also Figure S3 and Table S4

Figure 4. Knock-down of ncRNA-a7 specifically targets Snai1 expression

(A) As in Figure 3, the ncRNA-a7 locus is depicted showing effects on RNA levels for the surrounding genes with and without knock-down of ncRNA-a7. The results represent at least six independent experiments. (B) Migration assay of A549 cells with control (right panel) or ncRNA-a7 (left panel) siRNA transfections. (C) Quantification of the data shown in (B). All experiments are done in three replicates, and are shown as mean +/− S.E.M. ** p < 0.01, *** p < 0.001 by two-tailed Student’s T-test. See also Figure S4 and Table S5.

Figure 5. Microarray analysis of Snai1 and ncRNA-a7 knock-down

Snai1 or ncRNA-a7 were knocked down using siRNA in A549 cells and the isolated RNA analyzed on microarrays in duplicate experiments. (A) All genes differentially expressed (>1.5 fold or <0.6 fold compared to control) in either Snai1 or ncRNA-a7 knock-down, or both, are shown clustered in a heat map according to expression profile. Numbers are log(2) transformed and color-scale is shown below the heat map. (B) Analysis of genes showing upregulation (>1.5 fold) or downregulation (<0.6 fold) in both Snai1 and ncRNA-a7 knock-down. Numbers represent number of genes regulated in the indicated condition. (C) Validation of microarray data by qPCR, and (D) analysis of the Snai1 locus and targets of Snai1 upon over-expression of ncRNA-a7. ncRNA-a7 was over-expressed from a vector in A549 cells and expression of select genes were measured by qPCR. Y-axes show expression value relative to GAPDH of the indicated gene. Values are normalized to those of control siRNA transfected cells, set to 1. ** p < 0.01, *** p < 0.001 by one-tailed Student’s T-test. See also Table S6.

Figure 6. ncRNA-activators potentiate transcription of a reporter gene

(A) ncRNA-a 3/4, 5 and 7 were cloned and inserted downstream of luciferase driven by a TK-promoter in a reporter plasmid as shown. (B) Graphical representation of the inserts in the various vectors used. The pGL3-TK-Control vector contains an insert of approximately 4 kb containing no annotated evidence of transcription. The depicted inserts show exons and transcriptional direction of the ncRNA-a. (C–E) Luciferase reporter assays. The Firefly luciferase vectors were co-transfected with a Renilla luciferase vector (pRL-TK) for transfection control. (C) The vector containing ncRNA-a3 and ncRNA-a4 from a bidirectional promoter, with control siRNA or siRNAs towards either of the two ncRNA-a, or both. (D) Reporter with ncRNA-5, and (E) the reporter with the ncRNA-a7 inserted downstream of luciferase. X-axes show relative Firefly (FL) to Renilla (RL) luciferase activity. Co-transfected siRNAs are indicated to the right of the bars. All data shown are from six independent experiments. * p < 0.05, ** p < 0.01, *** p < 0.001 by one-tailed Student’s T-test.

Figure 7. RNA-dependent activation of a reporter gene by ncNRA-a7

(A) Properties of the ncRNA-a7 containing luciferase reporter vector. (B, C, E and F) Luciferase reporter assays. The Firefly luciferase vectors were co-transfected with a Renilla luciferase vector (pRL-TK) for transfection control. (D) Semiquantitative PCR of ncRNA-a7. (B) Reporter experiments with the ncRNA-a7 insert reversed as indicated in the left panel. (C) The TK-promoter driving luciferase expression was deleted from the construct and expression values are shown relative to the pGL3-TK control plasmid as a reference. (E) Truncated reporter constructs containing the ncRNA-a7 promoter and downstream sequences, but not the ncRNA-a7 sequence (pGL3-TK-delta(ncRNA-a7)), or one with a poly(A) signal in the beginning of the ncRNA-a7 to induce premature polyadenylation (pGL3-TK.ncRNA-a7-p(A)). See also (D) for analysis of expression from these plasmids. (F) Protein coding sequences were inserted in place of ncRNA-a7 downstream of the ncRNA-a7 promoter. Full-length GTSF1L or ID1 sequences are used. X-axes show relative Firefly (FL) to Renilla (RL) luciferase activity. All data shown are from six independent experiments. *** p < 0.001 by one-tailed Student’s T-test.