The stromal proteinase MMP3/stromelysin-1 promotes mammary carcinogenesis

Abstract

Matrix metalloproteinases (MMPs) are invariably upregulated in the stromal compartment of epithelial cancers and appear to promote invasion and metastasis. Here we report that phenotypically normal mammary epithelial cells with tetracycline-regulated expression of MMP3/stromelysin-1 (Str1) form epithelial glandular structures in vivo without Str1 but form invasive mesenchymal-like tumors with Str1. Once initiated, the tumors become independent of continued Str1 expression. Str1 also promotes spontaneous premalignant changes and malignant conversion in mammary glands of transgenic mice. These changes are blocked by coexpression of a TIMP1 transgene. The premalignant and malignant lesions have stereotyped genomic changes unlike those seen in other murine mammary cancer models. These data indicate that Str1 influences tumor initiation and alters neoplastic risk.

Figure 1. Effect of Str1 on Morphology and Intermediate Filament Expression in Scp2 Cells

Cells were maintained for 6 days in the (a) absence or (b) presence of activated recombinant Str1 (rStr1) and stained by indirect immunofluorescence for cytokeratins (red) and vimentin (green). Nuclei were counterstained with DAPI (blue). Scale bar, 50 µm.

Figure 2. Effect of Str1 on Mammary Epithelial Growth In Vivo

(A) Histologic appearance of p2S10 mammary epithelial cells grown in cleared mammary fat pads. (a–d) Appearance of epithelial ductal and gland-like structures (Ep) that form in the absence of Str1 expression as seen by (a) whole-mount, (b) H&E, (c) anti-cytokeratin-8, and (d) anti-smooth muscle actin staining. The arrowhead in (d) indicates vascular smooth muscle cells. (e–h) Appearance of spindle-cell tumors (Sp) that form when Str1 expression is induced in vivo or prior to injection as seen by (e) H&E, (f) Alcian blue, (g) anti-vimentin, and (h) anti-cytokeratin-8 staining. Areas of cartilage (chondroid metaplasia, Cm) are present in the upper right corner (e–h). Scale bars, (a) 200 µm and (b–h) 100 µm. (B) Tumor incidence (percent of injected sites) and volume (cm³; mean ± SEM) following injection of parental (Scp2), nonexpressing (p2S3), uninduced (S10un), and preinduced (S10pre) cells into cleared mammary fat pads in mice maintained for 6 weeks with (+) or without (−) Tet in their drinking water or without Tet for the first 12 days only (−/+). *, p < 0.0001 versus S10pre cells in mice maintained with or without Tet (two-tailed Fisher’s exact test); †, p < 0.05 versus S10un cells in mice maintained with Tet and p < 0.001 versus S10pre cells in mice maintained with or without Tet (Fisher’s exact test); ‡, p < 0.005 and p < 0.001 versus S10pre cells in mice maintained with and without Tet, respectively (t test).

Figure 3. Incidence of Mammary Gland Pathologies in Str1 Transgenic Mice

The Str1-expressing transgenics include 100, 31, 16, 9, and 7 mice from five independent transgenic lines, respectively. *, p < 0.00001 versus nontransgenic or nonexpressing transgenic controls (two-tailed Fisher’s exact test); †, p = 0.002 and p = 0.02 versus non-transgenic and nonexpressing transgenic controls, respectively (Fisher’s exact test).

Figure 4. Histologic Appearance of Normal and WAP-Str1 Mammary Glands

Histologic sections are from (a) nontransgenic, (b–g) WAP-Str1 transgene–expressing, (h) WAP-Str1 transgene–nonexpressing, and (i) Str1/TIMP1 double transgene–positive female mice. (a) Normal mammary gland with resting ducts (Du), abundant adipose tissue (asterisk), and minimal periductal (Pd) and septal (S) collagen (stained blue). (b) Severe hyperplasia (Hp) with considerable intervening fibrosis (Fb; stained blue) and multilocular adipocytes (asterisk). (c) Hyperplastic alveolar nodule (HAN) with lipid droplets characteristic of secretory activity even though this gland comes from a nulliparous mouse. (d) Multifocal alveolar hyperplasia (Hp) with eosinophilic (pink) fibrotic areas and multilocular adipocytes (asterisk). (e) Intraductal papillary hyperplasia with lymphocytic infiltrates (Ly). The small hyperchromatic cells (Me) were cytokeratin-8 negative and smooth muscle actin positive, indicating the abnormal presence of myoepithelial cells within the severely distended ducts. (f) Atypical hyperplasia (AH) with lymphocytic infiltrates (Ly) and mild fibrosis (Fb). (g) Atypical hyperplasia with considerable fibrosis. (h and i) Normal mammary histology seen with the loss of Str1 transgene expression or its inhibition by TIMP1, respectively. (a and b) Masson’s trichrome. (c–i) Hematoxylin/eosin. Scale bar, 200 µm.

Figure 5. Histologic Appearance of Malignant Mammary Tumors from Str1 Transgenic Mice

(a–c) Moderately differentiated adenocarcinoma (Ad) with adjacent and intervening vimentin-positive stromal cells (St). (d–f) Renal metastasis (Met) from an undifferentiated mammary carcinoma. Normal kidney (Kid) is present on the right. (g–i) Carcinosarcoma with distinct carcinomatous (Ca) and sarcomatous (Sa) areas exhibiting epithelial and mesenchymal features, respectively. H&E, hematoxylin/eosin stains. Scale bar, 200 µm.

Figure 6. Effect of a TIMP1 Transgene on Str1 Transgene–Induced Mammary Hyperplasias as Seen by Whole-Mount Staining

(a) 16-month-old nontransgenic control. (b) 16-month-old WAP-Str1 transgenic mouse with multifocal alveolar hyperplasia (Hp). (c) 12-month-old WAP-Str1-positive/WAP-TIMP1-negative mouse with diffuse alveolar hyperplasia. (d) 12-month-old Str1/TIMP1 double transgenic mouse from the same litter as the mouse in (c). The mammary gland in (d) was judged to be within normal limits by whole-mount and hematoxylin/eosin staining. The glands shown are from mice that had undergone a single pregnancy and lactation at least 5 months prior to sacrifice. LN, lymph node. Scale bar, 500 µm. (e) Incidence of mammary hyperplasias in double and single transgenic mice. The single transgenic mice are from the related M2-5 line. Gray and black bars indicate mild and moderate to severe hyperplasias, respectively. *, p < 0.02 versus littermates carrying the Str1 transgene alone and p < 0.0006 versus the large cohort of M2-5 Str1 transgenics, respectively (two-tailed Fisher’s exact test).

Figure 7. CGH Profiles

(A) Genomic changes seen in the mammary glands of 12 individual Str1 transgenic mice. Samples 1, 3, 10, and 11 were from one transgenic founder line; samples 4 and 8 were from another line; and the remaining samples were from a third independent line. Approximate locations of macroscopic DNA gains (green) and losses (red) are indicated along otherwise unaltered (yellow) chromosomes, with black circles representing acrocentric centromeres. Sample 12, a carcinosarcoma, was microdissected and its carcinomatous and sarcomatous regions analyzed separately. All adjacent stromal and nonmammary control tissues had normal CGH profiles. (B) Normalized fluorescence intensity profiles for chromosome 15 obtained with DNA isolated from (a) parental Scp2 cells, (b) a p2S7 cell–derived tumor, (c) preinduced p2S10 cells, (d) microdissected spindle-cell areas from a tumor derived from the same preinduced cells as in (c), (e) chondroid areas from the same tumor as in (d), and (f) normal stroma adjacent to the tumor in (d) and (e). Average green:red fluorescence ratios (heavy lines) ± 1 standard deviation (thin lines) are shown for the number of metaphase chromosomes examined (n). Dashed horizontal lines and upper and lower dotted lines indicate fluorescence ratios of 1, 1.5, and 0.5, respectively.