Molecular profiling and characterization of luminal-like and basal-like in vivo breast cancer xenograft models

Abstract

The number of relevant and well-characterized cell lines and xenograft models for studying human breast cancer are few, and may represent a limitation for this field of research. With the aim of developing new breast cancer model systems for in vivo studies of hormone dependent and independent tumor growth, progression and invasion, and for in vivo experimental therapy studies, we collected primary mammary tumor specimens from patients, and implanted them in immunodeficient mice. Primary tumor tissue from 29 patients with breast cancer was implanted subcutaneously with matrigel in SCID mice, in the presence of continuous release of estradiol. The tumors were transferred into new animals when reaching a diameter of 15mm and engrafted tumors were harvested for morphological and molecular characterization from passage six. Further, gene expression profiling was performed using Agilent Human Whole Genome Oligo Microarrays, as well as DNA copy number analysis using Agilent Human Genome CGH 244K Microarrays. Of the 30 primary tumors implanted into mice (including two implants from the same patient), two gave rise to viable tumors beyond passage ten. One showed high expression levels of estrogen receptor-alpha protein (ER) while the other was negative. Histopathological evaluation of xenograft tumors was carried out at passage 10-12; both xenografts maintained the morphological characteristics of the original tumors (classified as invasive grade III ductal carcinomas). The genomic profile of the ER-positive xenograft tumor resembled the profile of the primary tumor, while the profile obtained from the ER-negative parental tumor was different from the xenograft. However, the ER-negative parental tumor and xenograft clustered on the same branch using unsupervised hierarchical clustering analysis on RNA microarray expression data of "intrinsic genes". A significant variation was observed in the expression of extracellular matrix (ECM)-related genes, which were found downregulated in the engrafted tumors compared to the primary tumor. By IHC and qRT-PCR we found that the downregulation of stroma-related genes was compensated by the overexpression of such molecules by the mouse host tissue. The two established breast cancer xenograft models showed different histopathological characteristics and profound diversity in gene expression patterns that in part can be associated to their ER status and here described as basal-like and luminal-like phenotype, respectively. These two new breast cancer xenografts represent useful preclinical tools for developing and testing of new therapies and improving our knowledge on breast cancer biology.

Figure 1

Histopathological analysis. Histopathological evaluation was carried out on formalin‐fixed paraffin‐embedded tissue sections from xenografts and primary tumors. Panels A and B: H&E staining for primary tumor biopsies and xenografts respectively. Panels C and D: ER and PgR immunostaining of the two engrafted tumors.

Figure 2

Xenograft and primary tumor aCGH profile. A) Estimation of copy number ratios in MAS98.06 by the CGH‐Explorer PCF algorithm. Red color corresponds to primary tumor; blue color corresponds to the paired xenograft (vertical bars show chromosomes boundaries). High resolution of copy number profiles for chromosome 8 and 13 are showed. B) Evaluation of copy number ratios in MAS98.12 by the CGH‐Explorer PCF algorithm. Red color corresponds to primary tumor; blue color corresponds to the paired xenograft (vertical bars show chromosomes boundaries). High resolution of copy number profile for chromosome 1, 8 and 13 is reported.

Figure 3

Expression analysis of xenografts. A) Unsupervised hierarchical clustering of 12 breast carcinoma xenografts across 18.442 genes which passed the filtering criteria (Fig. S1). B–C) Selected panels of differential gene expression between MAS98.06 and MAS98.12 xenografts. Genes in red were investigated by Northern blotting. D) Northern blot analysis of genes differentially expressed in two representative MAS98.06 and MAS98.12 xenografts from mice maintained with and without estradiol after implantation.

Figure 4

Expression analysis of xenografts and primary tumors. Unsupervised hierarchical clustering of 12 breast carcinoma xenografts and two paired primary tumors. 19.072 genes passed the filtering criteria and were used for this analysis (Fig. S1A). B and D) Selected panels of differential gene expression patterns for xenografts and primary tumors.

Figure 5

Expression patterns of 278 ECM‐related genes in a group of 12 breast carcinomas and two primary tumors. A) Cluster of ECM genes upregulated in primary tumors compared to xenografts. B) Correlation of each sample to each of the four ECM centroids. Tumors with low correlation (<0.11) were considered unclassified.

Figure 6

A) qRT‐PCR analysis of 5 ECM‐related genes. Expression levels were normalized against GAPDH using species‐specific primer for mouse and human. Representative xenograft samples are shown. B) Representative IHC staining for COLIV carried out in formalin‐fixed paraffin‐embedded sections of primary tumors and xenografts.

Figure 7

Expression patterns of “intrinsic molecular subtypes genes” in xenografts and primary tumors. 40 primary tumors were included in the analysis along with two representative xenograft replicates and their primary tumors. 822 clones corresponding to the original intrinsic genelist were clustered. Sample dendrogram branches are color‐coded based on centroid classification (Sorlie et al., 2003). Colored vertical bars indicate gene clusters typical for the different subtypes.