Role of MXD3 in proliferation of DAOY human medulloblastoma cells

Abstract

A subset of medulloblastomas, the most common brain tumor in children, is hypothesized to originate from granule neuron precursors (GNPs) in which the sonic hedgehog (SHH) pathway is over-activated. MXD3, a basic helix-look-helix zipper transcription factor of the MAD family, has been reported to be upregulated during postnatal cerebellar development and to promote GNP proliferation and MYCN expression. Mxd3 is upregulated in mouse models of medulloblastoma as well as in human medulloblastomas. Therefore, we hypothesize that MXD3 plays a role in the cellular events that lead to medulloblastoma biogenesis. In agreement with its proliferative role in GNPs, MXD3 knock-down in DAOY cells resulted in decreased proliferation. Sustained overexpression of MXD3 resulted in decreased cell numbers due to increased apoptosis and cell cycle arrest. Structure-function analysis revealed that the Sin3 interacting domain, the basic domain, and binding to E-boxes are essential for this activity. Microarray-based expression analysis indicated up-regulation of 84 genes and down-regulation of 47 genes. Potential direct MXD3 target genes were identified by ChIP-chip. Our results suggest that MXD3 is necessary for DAOY medulloblastoma cell proliferation. However, increased level and/or duration of MXD3 expression ultimately reduces cell numbers via increased cell death and cell cycle arrest.

Figure 1. Expression of MXD3 in human medulloblastomas.

MXD3 mRNA levels in ten human medulloblastoma samples, normal developing and normal mature cerebellum determined by quantitative RT-PCR analysis. Values represent the mean fold-difference in mRNA (n  = 4) relative to developing cerebellum. Error bars indicate standard deviation (SD). Note the logarithmic scale of the Y-axis. The developing cerebellum sample and eight out of ten medulloblastomas showed significantly higher expression of MXD3 when compared to normal mature tissue (asterisks, p<0.01; one-way ANOVA).

Figure 2. MXD3 knock-down decreases DAOY medulloblastoma cell proliferation.

(A) Loss of MXD3 decreases DAOY cell proliferation. Quantification of cell proliferation (as total number of cells relative to control) of DAOY cells transfected with MXD3 (siRNA1, 2) or control (siRNAc) siRNAs. Knock-down of endogenous MXD3 resulted in reduced DAOY cell counts (asterisks, p<0.05; n  = 3; two-way ANOVA). (B) siRNA-mediated reduction of HA-MXD3 expression. DAOY cells were transiently co-transfected with HA-MXD3 and siRNAs as in (A). Extracts were probed with anti-HA antibody to detect HA-MXD3 (lower panel) or anti-tubulin antibodies for load control (upper panel).

Figure 3. Persistent expression of MXD3 reduces cell proliferation.

(A) Proliferation curves for DAOY (filled circles), individual “M” (filled squares) and “C” (open triangles) cell lines expressed as fold increase from starting cell count. Each data point represents the mean ± SD of 2–3 independent experiments. All cell lines overexpressing MXD3 showed reduced cell proliferation. Control lines were not different from the parental line. For clarity, the same traces are used for different cell lines within each group. (B) For statistical analysis, proliferation data from all cell lines in (A) were pooled into 3 groups: DAOY (filled circles), MXD3 (filled squares) and control (open triangles). From day eight onwards, MXD3 group showed significantly slower proliferation than the parental or control groups (p<0.01, n  = 15, two-way ANOVA with Scheffe post-test for individual comparisons between groups).

Figure 4. MXD3 influences cell cycle and apoptosis.

(A−B) Cell cycle (A) and apoptosis (B) analysis by flow cytometry of MXD3 and control cell lines. Bars represent the average ± SD of two independent experiments, each performed on four MXD3 lines (“M”) and four control lines (“C”). MXD3 overexpression resulted in a significantly higher percentage of the population in the G2 phase and increased apoptosis (p<0.05, two-way ANOVA). (C) Theoretical proliferation curves (empty symbols) and experimental data (full symbols) for representative cell lines.

Figure 5. MXD3 structure-function analysis.

(A) Quantification of cell proliferation (as total number of cells relative to control) of DAOY cells transfected with full-length MXD3 or mutated forms as indicated in Figure S2. MXD3-transfected cells showed 50% reduction of proliferation compared with vector-only (pHM6). Transfection of ΔC and E66Q constructs resulted in similar reduction in proliferation as full-length MXD3. Transfection of the ΔSID, Δbasic, E66D and E66N constructs had no effect on proliferation compared to control (ns, not significant; asterisks, p<0.001; n  = 4, one-way ANOVA with Bonferroni’s multiple comparison test). (B) Immunoblot analysis of total protein extracts from DAOY cells transfected with the MXD3 constructs in (B). All constructs used expressed the expected proteins at similar levels. Bottom panel, anti-HA; top panel, anti-β-tubulin used as a load control. Molecular mass markers are indicated on the right.

Figure 6. Identity of MXD3 direct target genes.

MXD3 direct target genes from ChIP-chip analysis were validated by PCR on an independent ChIP sample. Specific bands are shown in the panels on the right. Transcription factor binding prediction analysis indicated the presence of E-boxes of the c-Myc (○), Max (▵) and N-Myc (□) type. Symbols represent the position of the predicted binding site, relative to the transcription start site. The position of the peak for MXD3 binding, as determined by Maxfour analysis of ChIP data, is indicated by a line (|–|).