Circulating miRNAs in Small Extracellular Vesicles Secreted by a Human Melanoma Xenograft in Mouse Brains

Abstract

The identification of liquid biomarkers remains a major challenge to improve the diagnosis of melanoma patients with brain metastases. Circulating miRNAs packaged into tumor-secreted small extracellular vesicles (sEVs) contribute to tumor progression. To investigate the release of tumor-secreted miRNAs by brain metastasis, we developed a xenograft model where human metastatic melanoma cells were injected intracranially in nude mice. The comprehensive profiles of both free miRNAs and those packaged in sEVs secreted by the melanoma cells in the plasma demonstrated that most (80%) of the sEV-associated miRNAs were also present in serum EVs from a cohort of metastatic melanomas, included in a publicly available dataset. Remarkably, among them, we found three miRNAs (miR-224-5p, miR-130a-3p and miR-21-5p) in sEVs showing a trend of upregulation during melanoma progression. Our model is proven to be valuable for identifying miRNAs in EVs that are unequivocally secreted by melanoma cells in the brain and could be associated to disease progression.

Keywords: circulating miRNAs; melanoma; small extracellular vesicles.

Figure 1

In vivo imaging of M14 metastatic melanoma cells transfected with pcDNA3-luc plasmid (M14-LUC stable cell line) intracranial xenografts. (A) Luminescence of M14-LUC cells intracranially injected in the mouse brain was monitored weekly using the In Vivo Imaging Systems (IVIS, 200 series, Caliper Life Sciences, Hopkinton, MA, USA). Mice were anesthetized to perform measurement of luminescence. Representative tumor images on day 7, 14 and 23 after tumor cell injection are shown. Data were acquired and analyzed using the Living Image Software version 3.0 (Caliper Life Sciences). (B) Histograms report bioluminescence at day 7, 14 and 23 after tumor cell injection. Error bars indicate ± SD. Unpaired-one-tailed student’s t test was used for statistical comparison between the different groups and the control (CTRL) group (* = p < 0.05). (C) Representative histopathological examination of mouse brains in control (CTRL) and tumor-bearing (TUMOR) mice after 23 days from tumor cell injection. Images shown are at 4× magnification.

Figure 2

Characterization of M14-released tumor-secreted small extracellular vesicles (sEVs) in cell culture. (A) Morphological examination of small extracellular vesicles (sEVs) purified from M14 cell culture medium was performed by transmission electron microscopy (TEM). Bars, 100 nm. (B) Size and number of the released sEVs was measured by dynamic light scattering. The representative Intensity distribution curve and Zeta potential distribution are an average of five different measurements of the same sample. (C) sEVs purified from cell culture were immunocaptured by magnetic Dynabeads conjugated with CD63 tetraspanin. The bead-bound sEVs stained by Fuse-It membrane-specific dye were studied by confocal microscopy (left panel, bars, 500 nm). The stained sEVs were then detached from the beads and analysed by confocal microscopy (middle panel, bars, 500 nm) and by TEM (right panels, bars, 100 nm). (D) Bead-bound sEVs were processed for the detection of the indicated molecules by immunofluorescence and flow cytometry. Aggregates and debris were excluded (gating) from the fluorescence analysis, as shown in the cytogram relative to the light scatter parameters (left panel, top). In each cytogram the number reported represents the percentage of positivity for the indicated molecule. As an example, right top panel reported the confocal microscopy of bead-bound sEVs stained with anti-CD81 antibody conjugated with phycoerythrin (PE). Bar, 500 nm. PdI, intensity distribution; SSC, side scatter; FSC, forward side scatter; FITC, fluorescein isothiocyanate; ZONAB, ZO-1-associated nucleic acid-binding protein; GFAP, glial fibrillary acidic protein.

Figure 3

Detection of human sEVs in the mouse plasma. (A) TEM analysis of the sEVs purified from the mouse plasma. Bars, 100 nm when not indicated. (B) sEVs purified from the mouse plasma were immunocaptured by the magnetic beads conjugated to human CD63 tetraspanin and then processed for immunofluorescence of the human CD81-PE. Aggregates and debris were excluded (gating) from the fluorescence analysis, as shown in the cytogram relative to the light scatter parameters (left panel). The number reported in each cytogram represents the percentage of positivity.

Figure 4

Hierarchical clustering analysis of the human-specific miRNAs released in the mouse total plasma. (A) Clustering analysis was performed as a function of the tumor growth in the brain. (B) Expression of the human-specific miRNAs released in the total plasma during the tumor growth at different time points after intracranial cell injection. Unpaired-one-tailed student’s t test was used for statistical comparison between the different groups and the CTRL group (* = p < 0.05).

Figure 5

Human-specific miRNA abundance analysis in the mouse plasma. (A) Rank abundance curve of the human-specific miRNAs both expressed in the mouse total plasma (left panel) and enriched in the sEVs (right panel). The threshold was set at 2% of the miRNA expression (horizontal line). (B) The most abundant miRNAs are shown in the ring graph in both total plasma (left panel) and sEV (right panel) compartments. The number reported in each slice of the ring represents the percentage of expression of the indicated miRNA.

Figure 6

Conserved miRNA abundance analysis in the mouse plasma. (A) Rank abundance curve of the conserved miRNAs both expressed in the mouse total plasma (left panel) and enriched in the sEVs (right panel). The threshold was set at 2% of the miRNA expression (horizontal line). (B) The most abundant conserved miRNAs are shown in the ring graph in both total plasma (left panel) and sEV (right panel) compartments. The number reported in each slice of the ring represents the percentage of expression of the indicated miRNA.

Figure 7

miRNAs expressed in EVs of metastatic melanoma patients included in a public dataset of melanoma clinical cases. (A) For the 20 validated miRNAs, normalized expression levels are reported for Stage IV metastatic melanoma group (n = 8, red) and healthy controls (n = 8, blue) included in the dataset. Values are expressed as mean of the log2 quantile-normalized probe intensity values obtained from GEO Series GSE100508 ± standard error. (B) Three EV-associated miRNAs showing a trend of upregulation during melanoma progression from healthy control to primary and metastatic tumors. Boxplots show normalized probe intensity values for each miRNA in healthy controls (n = 8, blue), primary (n = 2, green) and metastatic (n = 8, red) melanoma patients obtained from GEO Series GSE100508.