Intronic miR-211 assumes the tumor suppressive function of its host gene in melanoma

Abstract

When it escapes early detection, malignant melanoma becomes a highly lethal and treatment-refractory cancer. Melastatin is greatly downregulated in metastatic melanomas and is widely believed to function as a melanoma tumor suppressor. Here we report that tumor suppressive activity is not mediated by melastatin but instead by a microRNA (miR-211) hosted within an intron of melastatin. Increasing expression of miR-211 but not melastatin reduced migration and invasion of malignant and highly invasive human melanomas characterized by low levels of melastatin and miR-211. An unbiased network analysis of melanoma-expressed genes filtered for their roles in metastasis identified three central node genes: IGF2R, TGFBR2, and NFAT5. Expression of these genes was reduced by miR-211, and knockdown of each gene phenocopied the effects of increased miR-211 on melanoma invasiveness. These data implicate miR-211 as a suppressor of melanoma invasion whose expression is silenced or selected against via suppression of the entire melastatin locus during human melanoma progression.

Figure 1

A genome-wide miRNA screen identifies reduced miR-211 in melanoma invasive activity. (A) Screening strategy followed to identify miRNAs regulating A375M melanoma cell invasiveness. (B) Number of invasive cells (average of 5 high power fields) after transfection with the miRNA library in A375M cells. The experiment was performed in duplicate (Replicates 1, 2). (C) Number of invasive cells after transfection with positive hits derived from the miRNA library screen experiment. The experiment was performed in duplicate; means ± s.e.m.

Figure 2

Perturbing miR-211 but not melastatin affects melanoma invasion and motility. (A) Schematic presentation of the miR-211 gene in intron 6 of the melastatin (TRPM1) gene. (B) qRT-PCR of TRPM1 (black bars) normalized to actin, and mature miR-211 (gray bars) normalized to RNU48 in multiple human primary melanocytes (HP) and melanoma short term cultures (MSTCs). Y-axis is logarithmic scale. (N=5; means ± s.e.m.). (C) Matrigel assays for WM3682, WM3526, and 451LU (panels at left) transfected with control antagomir (Anti-miR-Ctrl, row 1), a miR-211-specific antagomir (Anti-miR-211, row 2), a control siRNA (siCtrl, row 3), or a melastatin-specific siRNA (siTRPM1, row 4). Membranes prior to scraping non-invasive cells from the top are shown (row 5). Matrigel assays for WM1745, WM1716, or WM3314 (panels at right) transfected with control miRNA mimic (Ctrl mimic, row 1) a miR-211 mimic (miR-211-mimic, row 2), a control Renilla cDNA (Renilla) or TRPM1 cDNA (TRPM1, row 3). The membranes prior to scraping cells from the top of the membrane are shown (row 4). Graphical presentation of the data quantifies the number of invasive cells in 10 high power fields (means ± s.e.m.; *p<0.005). (D) Modulating miR-211 but not melastatin affects melanoma motility. Real-time video microscopy of WM1716 (top panel) expressing Renilla cDNA, melastatin cDNA (TRPM1), a control miRNA mimic (Ctrl mimic), or miR-211 mimic. Real-time video microscopy of 451LU (bottom panel) expressing a control antagomir (Anti-miR-Ctrl), a miR-211 antagomir (Anti-miR-211) a siRNA control (siCtrl), or a melastatin siRNA (siTRPM1). Results quantify cell migration in μm/hr (>25 representative cells analyzed for each category from 2 movies, means ± s.e.m.; *p<0.005). Real-time video images are added as web-browsable links.

Figure 3

Gene network analysis identifies three central nodes regulating melanoma metastasis potentially targeted by miR-211. (A) Literature-based melanoma and metastasis gene lists as demonstrated in the Venn diagram were used to construct the melanoma metastasis gene network. (B) Bioinformatically-predicted melanoma metastasis gene network (p=10⁻³⁷). Solid lines indicate direct interactions and dashed lines indicate indirect interactions. Arrows indicate activation. Lines ending in short perpendicular lines indicate repression. Targetscan-predicted miR-211 targets genes are shaded in grey (IGFR= −0.42, TGFBR2 = −0.49, NFAT= −0.06, DPP4= 0.14, −0.08, AKT2 = −0.01, MMP3= −0.09, ADAM19 = −0.11, −0.08, MCAM= −0.12). Knockdown of each central nodes genes is predicted to inhibit the entire metastasis network except for the genes indicated by hatch marks.

Figure 4

miR-211 targets multiple genes regulating melanoma metastasis. (A) Statistical association analysis of previously published mRNA profiling data (13,211 transcripts) versus miR-211 expression using Kendall’s tau. mRNA names are sorted by Kendall’s tau coefficient and periodically listed on the horizontal axis. Magnitude of coefficient measures the degree of association, and a negative coefficient denotes an inverse association. Representative melanoma-relevant genes directly correlated with miR-211 are highlighted in red: MLANA (τ = 0.831), MITF (τ = 0.821), CDK2 (τ = 0.776), SILV (τ = 0.738), and TYRP1 (τ = 0.627). Predicted miR-211 target genes are inversely correlated with miR-211 and are highlighted in green: IGF2R (τ = −0.297), NFAT5 (τ = −0.357), and TGFB2R (τ = −0.620). (B) miR-211 represses endogenous IGF2R, NFAT and TGFBR2 expression in melanoma cells. Transfection of a miR-211 antagomir into WM3526 de-represses IGF2R, NFAT5, and TGFBR2 expression compared to a control antagomir (Anti-miR-Ctrl). Transfection of a miR-211 mimic into WM1716 or A375M represses IGF2R, NFAT5, and TGFBR2 expression compared to a control miRNA mimic (Ctrl mimic). N=3; means ± s.e.m. (C) NFAT5 and TGFBR2 but not IGF2R are direct miR-211 target genes. Schematic presentation of predicted miR-211 target sites identified in the IGF2R, NFAT5 or TGFBR2. Numbers indicate positions of miR-211 binding sites on target mRNA 3′UTRs. HeLa cells were transfected with luciferase constructs possessing wildtype (wt) or miR-211 binding site mutant (mut) 3′UTRs of IGF2R, NFAT5 or TGFBR2 with a miR-211 mimic or a control miRNA mimic (ctrl Mimic). N=5; means ± s.e.m. (D) Knockdown of IGF2R, NFAT5, or TGFBR2 phenocopies the effect of increasing miR-211 on melanoma invasive activity. WM1716 cells were transfected with a control siRNA (siCtrl), or siRNAs against indicated genes and subjected to matrigel assays. Invasive cells were counted (top panels and are quantitated (graphs, right). The bottom panels demonstrate the membranes prior to scraping (N=3; means ± s.e.m.).