Transcriptional recapitulation and subversion of embryonic colon development by mouse colon tumor models and human colon cancer

Abstract

Background: The expression of carcino-embryonic antigen by colorectal cancer is an example of oncogenic activation of embryonic gene expression. Hypothesizing that oncogenesis-recapitulating-ontogenesis may represent a broad programmatic commitment, we compared gene expression patterns of human colorectal cancers (CRCs) and mouse colon tumor models to those of mouse colon development embryonic days 13.5-18.5.

Results: We report here that 39 colon tumors from four independent mouse models and 100 human CRCs encompassing all clinical stages shared a striking recapitulation of embryonic colon gene expression. Compared to normal adult colon, all mouse and human tumors over-expressed a large cluster of genes highly enriched for functional association to the control of cell cycle progression, proliferation, and migration, including those encoding MYC, AKT2, PLK1 and SPARC. Mouse tumors positive for nuclear beta-catenin shifted the shared embryonic pattern to that of early development. Human and mouse tumors differed from normal embryonic colon by their loss of expression modules enriched for tumor suppressors (EDNRB, HSPE, KIT and LSP1). Human CRC adenocarcinomas lost an additional suppressor module (IGFBP4, MAP4K1, PDGFRA, STAB1 and WNT4). Many human tumor samples also gained expression of a coordinately regulated module associated with advanced malignancy (ABCC1, FOXO3A, LIF, PIK3R1, PRNP, TNC, TIMP3 and VEGF).

Conclusion: Cross-species, developmental, and multi-model gene expression patterning comparisons provide an integrated and versatile framework for definition of transcriptional programs associated with oncogenesis. This approach also provides a general method for identifying pattern-specific biomarkers and therapeutic targets. This delineation and categorization of developmental and non-developmental activator and suppressor gene modules can thus facilitate the formulation of sophisticated hypotheses to evaluate potential synergistic effects of targeting within- and between-modules for next-generation combinatorial therapeutics and improved mouse models.

Figure 1

Stratification of murine colon tumor models by localization of β-catenin and plan for analysis. Colon tumors from four etiologically distinct mouse models of CRC were subjected to microarray gene expression profiling. The gene expression profiles from the different mouse model tumors were compared and contrasted to each other, as well as to those from embryonic mouse colon development and 100 human CRCs.

Figure 2

Active canonical WNT signaling (as determined by nuclear β-catenin) stratifies the four murine colon tumor models into two groups. (a) Hierarchical clustering of gene transcripts separates the four models into two groups. The upper panel shows 1,798 gene transcripts identified as differentially expressed among any of the four mouse tumor models (Kruskal-Wallis test + Student-Newman-Keuls test + FDR < 5.10^-5). Results demonstrate that AOM (A) and Apc^Min/+ (M) tumors are transcriptionally more similar to each other than to tumors from Smad3^-/- (S) and Tgfb1^-/-; Rag2^-/- (T) mice. Five clusters have been identified (C1-C5) that correspond to the K-means functional clusters listed in Table 1. Please refer to Table 1 for an in-depth description of the functional classification of the genes found in these clusters. The lower panel illustrates the extent of the similarity between A/M and S/T tumors by identifying the top-ranked 1,265 transcripts of the 1,798 that were higher or lower in the two tumor super-groups (rank based on Wilcoxon-Mann-Whitney test for between-group differences with a FDR < 5.10^-5 cutoff). Up-regulated transcripts in A/M tumors are highly enriched for genes associated with canonical WNT signaling activity, cell proliferation, chromatin remodeling, cell cycle progression and mitosis; transcripts over-expressed in S/T tumors are highly enriched for genes related to immune and defense responses, endocytosis, transport, oxidoreductase activity, signal transduction and metabolism. (b) Representative histologies for each of the four tumor models. The lower panel illustrates the model-dependent localization of β-catenin. Tumors from M (bottom left) and A (not shown) mice exhibited prominent nuclear β-catenin accumulation and reduced cell surface staining. Conversely, tumors from S (bottom right) and T(not shown) mice exhibited retention of plasma membrane β-catenin immunoreactivity. A and M in top panel 100× magnification; S and T 200× magnification. M and S in lower panel both 400× magnification.

Figure 3

Selective validation of microarray results by qRT-PCR and immunohistochemistry. Differential expression of transcripts identified by the microarray analyses was examined using (a) qRT-PCR and (b) immunohistochemistry. Additional colon tumors from five Apc^Min/+ (M; nuclear β-catenin-positive) mice and four Smad3^-/- (S; nuclear β-catenin-negative) mice were harvested, and qRT-PCR was performed on nine genes that exhibited representative strong or subtle patterns in the microarray analyses. All nine patterns detected in the microarray set were validated by the qRT-PCR results. Alox12, Arachidonate 12-lipoxygenase; Casp6, Caspase 6; Matn2, Matrilin 2; Ptplb, Protein tyrosine phosphatase-like B; Sox21, SRY (sex determining region Y)-box 21; Spock2, Sparc/osteonectin, CWCV, and Kazal-like domains proteoglycan (testican) 2; Tesc, Tescalcin; Tpm2, Tropomysin 2; Wif1, WNT inhibitory factor; Stmn1, stathmin 1; Ptp4a2, phosphatase 4a2. In (a), *p < 0.05 and **p < 0.01.

Figure 4

All four murine tumor models exhibit reactivation of embryonic gene expression. The expression level of each gene in each sample was calculated relative to that in adult colon. Genes and samples were subjected to unsupervised hierarchical tree clustering for similarities among genes and tumors. (a) Heatmap shows the relative behaviors of 20,393 transcripts that passed basic signal quality filters with gene transcripts shown as separate rows and samples as separate columns. Note that the majority of genes over-expressed in tumors (red) are also over-expressed in embryonic colon; similarly, the genes under-expressed in tumors (blue) are under-expressed in embryonic colon. The color bars to the right indicate the position of 4,693 transcripts over-expressed in both tumors and development (red) or under-expressed in both (green). In addition, there are genes over-expressed in embryonic colon that are under-expressed in tumors and vice versa (asterisks). (b) The genes represented in (a) were divided into those over-expressed and under-expressed in embryonic colon and in the tumors, respectively. Fisher's exact test was used to calculate expected overlaps between lists and confirmed significant over-representation of development-regulated signatures among the tumors (*p < 1^-300, **p < 1.3^-19, ***p < 4^-296, ****p < 1^-300). (c) Heatmap showing the behavior of a subset of the transcripts in (a) (n = 4,693 features) that were over-expressed in both embryonic colon and tumor samples. Refer to Table 2 for a complete description of the genes associated with these clusters. (d) Embryonic gene expression can be further refined into genes expressed differentially during early (ED; E13.5-15.5) and late (LD; E16.5-18.5) embryonic development. Heatmap showing the relative behaviors of 750 transcripts that are highest-ranked for early versus late embryonic regulation. Overall, transcripts with the highest early embryonic expression were expressed at higher levels in nuclear β-catenin-positive tumors (A and M), whereas nuclear β-catenin-negative tumors (S and T) were representative of later stages of embryonic development. Sample groups: ED, early development (E13.5-E15.5); LD, late development (E16.5-E18.5); A, AOM-induced; M, Apc^Min/+; T, Tgfb1^-/-; Rag2^-/-; S, Smad3^-/-. Staging: nAC, normal colon. Clusters C8-C10 to the right of the heatmap correspond to the K-means functional clusters listed in Table 2.

Figure 5

Human CRCs exhibit gene expression profile complexity consistent with significant tumor subclasses. Genes potentially able to distinguish cancer subtypes were identified from Affymetrix HG-U133 plus2 Genechip expression profiles by filtering for 3,285 probe sets that were top-ranked by raw expression and their differential regulation in at least 10 out of 100 human colorectal cancer tumors. Coordinately regulated transcripts and similarly behaving samples were identified via hierarchical tree clustering. Seven different gene clusters (C11-17) were identified that distinguished ten or more tumors from the other tumors. Gene clusters were found to be highly enriched for gene functions listed in Table 3. Data were processed using Robust Microarray Analysis (RMA) with expression value ratios depicted as the relative expression per probe set in each sample relative to the median of its expression across the 100 CRCs. A striking heterogeneity of gene expression was observed, including metallothionein genes in cluster C15 previously shown to be predictive of microsatellite instability (indicated by asterisk), and C17 represented by 734 probesets rich in genes associated with extracellular matrix and connective tissue, tumor invasion and malignancy. Tissue groups: AC, adult colon; CRC, human CRC. Staging: nAC, normal colon; Dukes A-D, human tumors obtained from individuals. Clusters C11-C17 labeled to the right of the heatmap correspond to the K-means functional clusters listed in Table 3.

Figure 6

Both human CRCs and mouse colon tumors reactivate an embryonic gene signature. When human and murine tumors are compared, they both broadly re-express an embryonic gene expression pattern. Gene expression profiles from the mouse tumor models and human CRC samples were combined into a single non-redundant gene ortholog genome table structure and subjected to comparative profile analysis. Informative probe-sets from human and mouse platforms were selected, mapped to corresponding ortholog genes, and used to populate a table in which normalized expression for each gene is relative to normal adult colon. (a) Heatmap plot for all cross-species gene orthologs both present and successfully measured on both the Affymetrix Hg-U133 and Vanderbilt Mouse NIA 20 K microarrays (n = 8,621 features). This representation suggests that a large number of human CRC signatures exhibit similar behaviors in the mouse tumors and during embryonic mouse colon development (sidebar: 1,080 (red) and 431 (green) gene lists from (b)). (b) Based on results in (a), four separate gene lists were generated with criteria of over- or under-expression in development or over-expression or under-expression in human CRCs (2,718, 2,365, 2,212, and 737, respectively, with the overlaps shown as a sidebar in (a); red, 1,080 transcripts, and green, 431 transcripts). Genes over-expressed and under-expressed in embryonic mouse colon and human CRCs were found to be over-represented as determined by Fisher's exact test analysis (*p < 7 × 10^-88, **p < 1 × 10^-76, ***p < 5 × 10^-4, ****p < 1 × 10^-76). (c) Heatmap plot of all genes co-regulated in human CRCs and during early (ED) and late (LD) mouse embryonic colon development (n = 2,216 features). Six predominant clusters (C18-C23) characterize the transcriptional relationship between human CRC and mouse colon tumor models and embryonic development. Two clusters (C20 and 21) primarily distinguish human CRCs from murine tumors (A, M, S and T). For example, CRC up-regulated transcripts that are either developmentally up- or down-regulated are represented by cluster C22 (n = 860 features) and clusters C21/C23 (n = 142 features), respectively. Conversely, CRC down-regulated transcripts that are either down- or up-regulated during development are shown in clusters C18/C19 (n = 258 features) and cluster C20 (n = 42 features), respectively. Interestingly, while approximately 80% and approximately 60% of genes up- and down-regulated in both human CRCs and mouse development were also up- and down-regulated in tumors from the various mouse models, several clusters provide very interesting exceptions: cluster C20 comprises genes down-regulated in human CRCs that are routinely over-expressed in mouse tumors and development; cluster C21 comprises genes robustly expressed in human CRC that are rarely expressed in embryonic colon or murine tumors. Sample groups: ED, early development (E13.5-E15.5); LD, late development (E16.5-E18.5); A, AOM-induced; M, Apc^Min/+; T, Tgfb1^-/-; Rag2^-/-; S, Smad3^-/-. Tissue groups: AC, adult colon; CRC, human CRC. Staging: nAC, normal colon.

Figure 7

The up-regulated signature in tumors from Apc^Min/+ (M) and AOM (A) models (cluster C6, Figure 2) is enriched with genes associated with the activation of the canonical WNT signaling pathway, as determined by nuclear β-catenin positivity. (a) Schematic diagram of the canonical WNT signaling pathway showing elements present in cluster C6 (gene symbols with gray background). Key elements of this pathway (Ctnnb1, Lef1, Tcf and Myc) are outlined in blue. (b) Relative gene expression for MYC and SOX4 is plotted for individual murine and human tumors. The relative expression level of MYC and SOX4 is normalized to adult colon. Note that whereas Sox4, a canonical WNT target gene, is expressed at high levels in all human CRCs, A/M tumors and during embryonic mouse colon development, it is not expressed in Smad3^-/- (S) and Tgfb1^-/-; Rag2^-/- (T) tumors (black). In contrast, MYC is over-expressed in all human and murine tumors and during colonic embryonic development (red), irrespective of the activation of canonical WNT signaling, as determined by nuclear β-catenin positivity (Figure 2). Tissue groups: as above and: nAC-m, normal adult mouse colon; nAC-h, normal adult human colon; Dev, developing mouse colon.

Figure 8

An integrated view of colon cancer transcriptional programs provides novel insight into neoplasia. Murine colon tumor adenomas and human CRCs both show adoption and dysregulation of signatures tightly controlled during embryonic mouse colon development. The use of etiologically distinct mouse models of colon cancer allows for the identification of models that resemble different stages of embryonic mouse colon development and that are recapitulated by specific tumor types. (a) All tumors exhibit large-scale activation of developmental patterns. Nuclear β-catenin-positive (Apc^Min/+ and AOM) tumors map more strongly to early development stages during (more proliferative, less differentiated), whereas nuclear β-catenin-negative (Tgfb1^-/-; Rag2^-/- and Smad3^-/-) tumors map more strongly to later stages consistent with increased epithelial differentiation. (b) Overall representation of the relationship of mouse colon tumor models and human CRC to development and non-developmental expression patterns. Gene expression clusters mapped to the progression of adenomatous and carcinomatous transformation identified in Figures 5 and 6 are shown as the clusters of genes whose expression is either gained or lost associated with the stage of progression. For example normal development could be considered as 'subverted' if there is an absence of expression of genes normally expressed at high level in the developing colon that fail to be expressed in tumors (for example, C18, C19), or that are activated in tumor but not normally expressed in development (C20). Upregulated clusters are enriched for genes with known oncogenic functions and down-regulated clusters for genes associated with tumor suppression. Both mouse colon tumor models and human CRC share in the activation of embryonic colon expression (C22), or partially overlap (C23, dotted lines) the loss or repression of adult differentiation-associated genes (C19), and the loss of tumor suppressor genes (C18). Many human CRCs also lack the expression of additional tumor suppressor programs and gain the expression of oncogenes that are not over-expressed during normal developmental morphogenesis (C21).