Divisional history and hematopoietic stem cell function during homeostasis

Abstract

We investigated the homeostatic behavior of hematopoietic stem and progenitor cells (HSPCs) temporally defined according to their divisional histories using an HSPC-specific GFP label-retaining system. We show that homeostatic hematopoietic stem cells (HSCs) lose repopulating potential after limited cell divisions. Once HSCs exit dormancy and accrue divisions, they also progressively lose the ability to return to G0 and functional activities associated with quiescent HSCs. In addition, dormant HSPCs phenotypically defined as multipotent progenitor cells display robust stem cell activity upon transplantation, suggesting that temporal quiescence is a greater indicator of function than cell-surface phenotype. Our studies suggest that once homeostatic HSCs leave dormancy, they are slated for extinction. They self-renew phenotypically, but they lose self-renewal activity. As such, they question self-renewal as a characteristic of homeostatic, nonperturbed HSCs in contrast to self-renewal demonstrated under stress conditions.

Figure 1

Characterization of Stem/Progenitor Cells in 34/H2B Mice (A) Percentage of GFP-positive cells in BM compartments of 34/H2B mice. Mean ± SD; n = 3 mice. (B) GFP histograms of BM compartments in LSK cells before (top) and after (bottom) Dox treatment (12 weeks, chase). (C) Cell-cycle profiles of LSK cells before and after Dox treatment (12 weeks). All LSK (left), gating for GFP+LSK (middle), GFP+LSK (right). Upper panels, before Dox; lower panels, after Dox. G₀ Py^lowHo^2N, G₁ Py^hiHo^2N, S/G₂/M Py^hiHo ^{> 2N-4N}. (D) LTC-IC assay of GFP-positive or negative LSK cells. cfus were normalized to the amount derived from 100 cells initiating the LTC. Mean ± SD; n = 3 separate cultures. (E) LTC-CAFC assay of GFP-positive or negative LSK cells. The frequency of CAFCs was normalized to the amount derived from 100 cells initiating the LTC. (F) Peripheral blood leukocyte (PBL) chimerism (%CD45.2+ donor-derived cells) 8 months after transplant of GFP-positive and negative LSK cells isolated after 10 weeks chase. 5, 15, 45, 135, or 405 cells were transplanted into SJL mice together with 400,000 SJL BM. Each circle represents an individual mouse (3–5 mice/cell dose). Mice with <1.0% CD45.2+ cells were considered negative. See also Figure S1.

Figure 2

HSC Activity Correlates with Divisional History (A) After 12 weeks chase, the LSK GFP histogram (red line) was divided into five fractions from low- to high-GFP retention. Prior to chase, 90% of LSK cells were in the GFP 3 and GFP 4 fractions (green line). Dotted gray line, H2BGFP control. (B) Chimerism 5 weeks and 3 and 6.5 months posttransplantation of LSK cells isolated from each GFP level. One hundred cells from each fraction were transplanted into 4–6 SJL-recipient mice together with 200,000 SJL-competitor BM cells. Data are derived from one of two transplant experiments with consistent results. Each circle represents an individual mouse. (C) Donor reconstitution to each lineage at 3 months after transplant. Mean ± SD; n = 4–6 mice. (D) Donor reconstitution to each lineage at 3.5 months postsecondary transplantation of pooled BM (2 × 10⁶) from primary recipient mice from each GFP group from two transplant experiments. Three to five SJL mice were transplanted per group. Mean ± SD; n = 3–5 mice. (E) cfu assay of LSKCD48− cells at each GFP level; colonies per 100 cells; mean ± SD; n = 3 separate cultures. (F) LD-CAFC assay of LSKCD48− cells at each GFP level. (G) LTC-IC assay of LSKCD48− cells at each GFP level; cfus were normalized to the amount derived from 100 cells initiating the LTC. Mean ± SD; n = 3 separate cultures. (H) LTC-CAFC assay of LSKCD48− cells at each GFP level; frequency of CAFCs was normalized to the amount derived from 100 cells initiating the LTC. Significance of donor contribution to total PBL (C and D) and of total colony numbers (G) by Student’s t test; ^∗p < 0.05; ^∗∗p < 0.01. See also Figure S2.

Figure 3

Phenotypic Analyses of HSPCs within Each GFP Dilution Fraction Phenotypic analyses of GFP LRCs contained within a specific HSPC phenotype population or as a phenotypic characterization of each GFP level after a 12-week Dox chase period. (A) The stacked bars are composed of the percentage of each GFP level that contributes to that specific HSPC phenotype as indicated. The percent of GFP4 cells in each phenotype is indicated on top of the bar graph. (B) The distribution of CD135 and CD34 subfractions of LSK cells in each GFP level. (C) The distribution of CD48 and CD150 subfractions of LSK cells in each GFP level. (D) The distribution of CD135 and CD34 subfractions of LSKCD48−CD150− cells in each GFP level. (E) The distribution of CD135 and CD34 subfractions of LSKCD48−CD150+ cells in each GFP level. Significance determined by Student’s t test for comparison of the primitive phenotype in each group (green bars); ^∗p < 0.05; ^∗∗p < 0.01; ^∗∗∗p < 0.001; mean ± SD; n = 3 to 4 mice per analysis. See also Figure S3.

Figure 4

Functional Analysis of GFP-High LRCs with Heterogeneous Expression of CD150 (A) Gating strategy for the isolation of CD150 Hi, Med, and Low subfractions of GFP-high LSKCD48− cells and the parent population. Cells were isolated after 13 weeks chase. (B) Chimerism at 5.5 weeks and 3 and 5 months posttransplantation of GFP-high LSKCD48− cells and the CD150 Hi, Med, and Low subfractions of those cells. One hundred cells per group were transplanted into each of 5–8 SJL mice together with 200,000 BM cells from SJL mice. Each circle represents an individual mouse. (C) Donor reconstitution to each lineage at 3 months post-primary transplantation; mean ± SD; n = 5–8 mice. (D) Chimerism 1 month after secondary transplantation of pooled BM (2 × 10⁶) from each group of primary recipient mice; four or five mice were transplanted per group. (E) Expression of Ndn, Fstl1, Tgm2, Ltbp3, Fscn, Trib3, and Meg3 by qPCR for CD150 Hi, Med, and Low fractions of GFP-high CD48−LSK cells (n = 3 assays from one sort). (F) Fluidigm gene-expression qPCR on 200 sorted LSKCD48− cells at varying GFP levels (left) or CD150 Hi, Med, and Low subfractions of LSKCD48− GFP4 cells (right). Results were normalized within each group separately. Data as mean ± SD; significance of donor contribution to total PBL (C and D) determined by Student’s t test; ^∗p < 0.05; ^∗∗∗p < 0.001; ^∗∗∗∗p < 0.0001. See also Figure S4.

Figure 5

Functional Analysis of CD34+ and CD34− Cells Isolated from GFP Hi and Low LSKCD135−CD48−CD150+ Cells (A) Isolation of CD34+ or CD34− subfractions from GFP Hi and Low LSKCD135−CD48−CD150+ cells. Lineage+CD135+CD48+ cells were first depleted and the remaining positive cells excluded. The four fractions were isolated after 17 weeks of chase. (B) LTC-IC assay of the above groups; cfus were normalized to the amount derived from 100 cells initiating the LTC (n = 3; separate cultures). (C) LTC-CAFC assay of above groups; CAFC frequency was normalized to the amount derived from 100 cells initiating the LTC. (D) Donor reconstitution in each lineage in total PBL 5 months posttransplantation; 30 cells from each of the above groups were transplanted to each of 3–5 SJL mice together with 200,000 BM from SJL mice. (E) Donor reconstitution in each lineage in total PBL 5.5 months post-secondary transplantation of BM pooled from primary recipient mice within each group; 3–4 mice/group transplanted with 2 × 10⁶ cells. (F) Donor chimerism in BM compartments 5 months after primary transplant. (G) Donor chimerism in BM compartments 5.5 month after secondary transplant. Each circle represents an individual mouse. Data as mean ± SD. Significance of total colonies (B), of donor contribution in total PBL (D and E), in each BM compartment (F and G) between GFP Hi and GFP Low groups, or in BM CD48−LSK and CD48−LSKCD150+ cells between CD34+ and CD34− GFP Hi (G, bottom panels) determined by Student’s t test; ^∗p < 0.05; ^∗∗p < 0.01; ^∗∗∗p < 0.001; ^∗∗∗∗p < 0.0001; ^{∗∗∗∗∗}p < 0.00001. See also Figure S5.

Figure 6

Cell-Cycle Analysis and Functional Activity of G₀ LSKCD48−CD150+ Cells throughout the GFP Dilution Cascade (A) Cell-cycle profiles of total LSKCD48−CD150+ cells or those at GFP 0, GFP 1, GFP 2, GFP 3, and GFP 4 by DNA content (DAPI) versus Ki67 staining. Cell-cycle phases were determined as G₀ Ki67^lowDAPI^2N, G₁ Ki67^hiDAPI^2N, S/G₂/M Ki67^hiDAPI ^{> 2N-4N}. (B) Percentage of G₀, G₁, and S/G₂/M cells in total LSKCD48−CD150+ and those at GFP 0, GFP 1, GFP 2, GFP 3, and GFP 4 as determined by Ki67/DAPI staining (mean ± SD; n = 4 mice). Significance of G₀ cells determined by Student’s t test; ^∗p < 0.05; ^∗∗p < 0.01. (C) Isolation of viable G₀ LSKCD48−CD150+ cells after 12 weeks chase for in vitro assays. LSKCD48−CD150+ cells were sorted first, followed by Py/Ho staining. G₀ cells (Py^lowHo^2N lower left quadrant) were isolated and separated into GFP 0, GFP 2, GFP 3, and GFP 4 subfractions. (D) LTC-CAFC assay of G₀ LSKCD48−CD150+ cells at each GFP level. (E) LTC-IC assay of G₀ LSKCD48−CD150+ cells at each GFP level. Significance of total colonies determined by Student’s t test; ^∗p < 0.05; mean ± SD; n = 3 separate cultures.

Figure 7

A Divisional History Gene-Expression Signature, Expression Profiles, and Bioinformatic Analyses (A) Gene-expression signature heatmap correlated with divisional history. One hundred and eighty-one genes were progressively up- (108) or downregulated (73) in correlation with the GFP gradient. See also Table S3. Below, 40.7% of the 108 upregulated genes fall into three overlapping clusters: regulation of transcription, signal transduction, and cell-cell/matrix interaction (left). Venn diagram highlights transcription regulation genes as repressors including all five chromatin modification genes (right). See also Table S2. GTPase, guanosine triphosphatase. (B) Heatmaps displaying opposite expression patterns of Hlf and Cd34 throughout the GFP gradient. LSK and LSKCD48− cells with varying GFP levels were sorted either as single cells or in pools of 200 cells and analyzed with Fluidigm qPCR. All single cells with detectable signal are represented by a rectangle with data centralized to the median value among all cells and hierarchically clustered by centered correlation. Both the 200 and single-cell analyses display the same pattern. (C) Expression analysis of Meg3, Trib3, Vegfc, and Tgm2 from the upregulated signature. Analyses were done with LSK cells isolated at each GFP level after 12 weeks chase. All genes show a gradient of gene expression that increases as GFP label is retained. Data are mean ± SD; n = 6 from two sorts. (D) Expression analysis of selected cell-cycle genes. CD48−LSK cells with varying GFP levels were sorted in pools of 200 cells and analyzed with Fluidigm qPCR. (E) Single-cell expression analyses of Cdk4 and Cdk6. Heatmaps were assembled from Fluidigm qPCR for Cdk4 and Cdk6 in single LSK cells (left) and single LSKCD48− cells (right). Single cells were analyzed as in (B) above. There is a complete lack of expression of Cdk6 in GFP4 cells in both data sets. (F) TGF-β-pathway-related genes display varying levels of expression that correlates with GFP retention. A heatmap of microarray data derived from LSK cells isolated at discrete GFP levels from 0 to 4. ANOVA p values or P2B p values (^∗) are listed on the left. Also see Figures S6 and S7 and Supplemental Experimental Procedures for details.