GEP analysis validates high risk MDS and acute myeloid leukemia post MDS mice models and highlights novel dysregulated pathways

Abstract

Background: In spite of the recent discovery of genetic mutations in most myelodysplasic (MDS) patients, the pathophysiology of these disorders still remains poorly understood, and only few in vivo models are available to help unravel the disease.

Methods: We performed global specific gene expression profiling and functional pathway analysis in purified Sca1+ cells of two MDS transgenic mouse models that mimic human high-risk MDS (HR-MDS) and acute myeloid leukemia (AML) post MDS, with NRASD12 and BCL2 transgenes under the control of different promoters MRP8NRASD12/tethBCL-2 or MRP8[NRASD12/hBCL-2], respectively.

Results: Analysis of dysregulated genes that were unique to the diseased HR-MDS and AML post MDS mice and not their founder mice pointed first to pathways that had previously been reported in MDS patients, including DNA replication/damage/repair, cell cycle, apoptosis, immune responses, and canonical Wnt pathways, further validating these models at the gene expression level. Interestingly, pathways not previously reported in MDS were discovered. These included dysregulated genes of noncanonical Wnt pathways and energy and lipid metabolisms. These dysregulated genes were not only confirmed in a different independent set of BM and spleen Sca1+ cells from the MDS mice but also in MDS CD34+ BM patient samples.

Conclusions: These two MDS models may thus provide useful preclinical models to target pathways previously identified in MDS patients and to unravel novel pathways highlighted by this study.

Fig. 1

a Schematic representation of the HR-MDS mouse model. The characteristics of this model have previously been published ^[24-26;29]. b Decrease of the HR-MDS mice survival compared to its single transgenic mice founders, _MRP8NRASD12 and _tethBCL-2 transgenic mice; c Increased level of Lin-Sca1+-cKit+ (LSK) cells in the BM; d Increased apoptosis in the liver and spleen seen by whole body SPECT using ⁹⁹Tc-Annexin (liver and spleen region located above the kidneys); e The disease can be transplanted in normal FVB/N irradiated syngeneic mice with either the Sca1+ cells of the spleen or BM of the HR-MDS mice resulting in 15 % blast infiltration in the BM blasts as in HR-MDS mice^[24-26;29]

Fig. 2

a Venn diagrams of co-expressed and uniquely dysregulated genes compared to control FVB/N mice in the HR-MDS, _MRP8NRASD12, and _tethBCL-2 transgenic mice; b Heat map of the down- and upregulated genes performed on the Sca1+ cells of HR-MDS (n = 3) compared to control FVB/N (n = 3) mice; c Distribution in % of the significantly dysregulated genes in the KEGG David annotation pathways; d Analysis of the differentially expressed genes (i.e., upregulated in the HR-MDS transgenic mice and downregulated in the founder mice and vice versa). Genes in regular font are expressed at lower levels and genes in bold font are expressed in higher levels. Examples of microarray data are shown for each intersection; e Validation of microarray data. qRT-PCR fold change of angpt1 and abcb4 gene expression in the BM and spleen cells of a different set of HR-MDS mice

Fig. 3

Schematic representation of dysregulated energy metabolism pathways. Dysregulated pathways are noted in red, if upregulated, and in green, if downregulated. a HR-MDS; b AML post MDS

Fig. 4

qRT-PCR validation of the GEP microarray data (blue) in Sca1+ cells purified from BM or spleen of another set of HR-MDS mice (two different hues of orange), and CD34+ cells purified from MDS patients (green) compared to FBV/N or CD34 BM cells, respectively. Data expressed as fold change of expression of several genes of three pathways shown (angpt1 (signal transduction); cox4i1 and ndufv2 (oxidative metabolism); sdc1 (DNA processing)). qRT-PCR fold changes shown here are represented as the average of three experiments

Fig. 5

a Schematic representation of the AML post MDS mouse model. The characteristics of these models have previously been published ^[24-26;29]; b Decrease of the survival of AML post MDS mice compared to the survival of the funders, _MRP8NRASD12 and _MRP8hBCL-2; c Increased level of Lin-Sca1+-cKit+ (LSK) cells in the BM; d Decreased level of apoptosis in the liver by whole body SPECT using ⁹⁹Tc-Annexin (liver and spleen region located above the kidneys); e Validation of microarray data: Decreased levels of MEK isoforms in the AML post MDS spleen cells compared to FVB/N control mice by the nanofluidic proteomic analysis; f The disease can be transplanted in normal FVB/N irradiated syngeneic mice with either the Sca1+ cells of the spleen or BM of the AML post MDS mice resulting in 54 % blast infiltration in the BM blasts as in AML post MDS mice.^[24-26;29]

Fig. 6

a Venn diagrams of co-expressed and uniquely dysregulated genes compared to control FVB/N mice in the AML post MDS, _MRP8NRASD12 and _MRP8hBCL-2 transgenic mice; b Heat Map of GEP performed on the Sca1+ cells of AML post MDS mice (n = 3) compared to control FVB/N mice (n = 3); c Distribution in % of the significantly dysregulated genes in the KEGG DAVID annotation pathways; d Analysis of the differentially expressed (i.e., upregulated in the AML post MDS transgenic mice and downregulated in the founder mice and vice versa). Genes in regular font are expressed at lower levels and genes in bold font are expressed in higher levels. Examples of microarray data are shown for each intersection

Fig. 7

a Frequency in percent of the most significant pathways dysregulated (up- or downregulated) in the two MDS mice models; b Schematic summary of the dysregulated pathways noted in the two MDS mice models. Upregulated pathways (gray boxes), downregulated pathways (white boxes)