Hematopoiesis and T-cell specification as a model developmental system

Abstract

The pathway to generate T cells from hematopoietic stem cells guides progenitors through a succession of fate choices while balancing differentiation progression against proliferation, stage to stage. Many elements of the regulatory system that controls this process are known, but the requirement for multiple, functionally distinct transcription factors needs clarification in terms of gene network architecture. Here, we compare the features of the T-cell specification system with the rule sets underlying two other influential types of gene network models: first, the combinatorial, hierarchical regulatory systems that generate the orderly, synchronized increases in complexity in most invertebrate embryos; second, the dueling 'master regulator' systems that are commonly used to explain bistability in microbial systems and in many fate choices in terminal differentiation. The T-cell specification process shares certain features with each of these prevalent models but differs from both of them in central respects. The T-cell system is highly combinatorial but also highly dose-sensitive in its use of crucial regulatory factors. The roles of these factors are not always T-lineage-specific, but they balance and modulate each other's activities long before any mutually exclusive silencing occurs. T-cell specification may provide a new hybrid model for gene networks in vertebrate developmental systems.

Keywords: commitment; gene regulatory networks; lineage hierarchy; transcription factors.

Figure 1

Overview of mouse T cell development. (A) Stages of T cell development and regulatory genes active at different stages. Upper schematic: progression of stages from thymic entry to completion of TCR rearrangement in DP stage. For cell-surface markers used to define stages, see recent reviews (35, 36). The β-selection transition, in which DN3a cells pass quickly through the DN3b, DN4, and immature single positive (Imm SP) stages before arriving at the DP stage, is only triggered in cells that have successfully rearranged their Tcrb gene loci to express an in-frame TCRβ protein. To focus on steps leading to confirmation of T-cell identity, the figure omits alternative branches of T-cell development leading the TCRγδ cells and the positive and negative selection events that lead to functional sub-specialization after successful rearrangement of the Tcra locus to express TCRαβ dimers in the DP stage. Transcription factors and growth factor receptors listed are chosen as those known to play functional roles in aspects of normal or leukemic T cell development (see (35, 36)). Gene names in parentheses denote expression at at lower levels or lower activity states than in stages where they are listed without parentheses. (B) Relationship of T-cell precursors to other hematopoietic fates. The figure presents a compromise view of the main inputs to the T-cell pathway relative to MPPs, LMPPs, and myeloid or erythroid-committed cell types. The yellow background and boldface type highlight stages that are in the pathway to generate T cells. For simplicity, pathways leading to eosinophils, basophils, and mast cells and the complexities of precursor relationships in the Innate Lymphoid Cell (ILC)—Natural Killer (NK) and Dendritic cell (DC) pathways are omitted. As described in the text, the roles of certain restricted progenitors in the erythromyeloid lineages are still controversial (dashed arrows). The main pathways indicated here are supported by recent single-cell analyses (55, 56).

Figure 2

Broadly combinatorial use of key transcription factors in specifying distinct hematopoietic cell fates. A schematic view is presented of mouse hematopoiesis, superimposed by the overlapping domains of activity of PU.1 (blue), GATA family factors (GATA-1, GATA-2, or GATA-3, red), C/EBP family factors (violet, graded to indicate dosage relative to PU.1), E proteins (E2A and/or HEB, yellow), TCF family factors (TCF-1/LEF-1, orange), and EBF1+Pax5 (B lineage specific, green). Whereas C/EBP family factors do not appear to overlap with the domains of E proteins and TCF-1/LEF-1, and the EBF1+Pax5 combination is restricted to a single cell type, there is extensive variation in the combinations of GATA, PU.1, C/EBP, E proteins, and TCF-1/LEF-1 that are allowed to distinguish the other cell fates shown. Eryth=erythrocyte. Meg=megakaryocyte. Eos=eosinophil. Baso=basophil. Neut=neutrophil. Mac=macrophage. DC=dendritic cell. ILC=innate lymphoid cell. NK=natural killer. ProT= T-cell precursor up to commitment (during period of PU.1 expression).

Figure 3

Contrast between the timings of myeloid exclusion relative to alternative lymphoid fate exclusion in the lineages leading to T cells and B cells. Top: developmental potentials demonstrable in T-cell precursors at different stages. Bottom: developmental potentials demonstrable in B-cell precursors at different stages. Figure focuses on data from defined in vitro systems where the clone sizes and cloning frequencies can be measured, rather than in vivo systems where migration bias and differential proliferation may also contribute to outcomes. In each case, to demonstrate non-T (top) or non-B (bottom) potential, cells are transferred to conditions that selectively favor manifestation of these alternative options. Data for T cell developmental alternatives are from refs. (, –81, 94, 98). Data for B cell developmental alternatives are from refs. (73, 75, 178, 179). Not shown are potentials for mast cell and innate lymphoid cell type 2 development, which have also been seen in DN2 T-cell precursors (132, 180).

Figure 4

Dynamic control of PU.1 activity levels in different hematopoietic lineages. Schematic of relative protein or RNA levels at different stages of development in five different pathways of hematopoietic development. For B, neutrophil and macrophage data, see (58). Although both T cells and erythroid cells silence PU.1 expression, PU.1 is specifically required for the T-cell developmental pathway to initiate, whereas it is not required for erythroid cell generation (134).

Figure 5

T cell precursors in the thymus begin by expressing PU.1. Data from experiments using thymocytes from progeny of a PU.1-GFP reporter mouse (59) crossed with a Bcl11b-mCherry reporter mouse (K. K. H. Ng, H. Y. Kueh, and M. A. Yui, unpublished), in which activation of the T-cell specific Bc11b gene in DN2 stage identifies cells definitively as T-cell precursors. (A) Gating of immature T-cell precursors to separate ETP, DN2a, DN2b, DN3(a), and DN4 cells. (B) Expression of PU.1-GFP relative to Bcl11b-mCherry in the indicated populations of cells from panel A. Note that the level of GFP from this PU.1 reporter is always low in early T cells, but the pattern of expression perfectly fits the measured PU.1 RNA and protein expression patterns determined by realtime PCR, RNA-seq, and intracellular staining (78, 137). The upregulation of the Bcl11b-mCherry reporter is further used to distinguish the earlier DN2a cells (Bcl11b-mCherry-negative) from the later ones beginning to express Bcl11b (Bcl11b-mCherry positive). (C) Quantitation of PU.1-GFP levels in T-cell precursors as they activate the T-lineage specific reporter Bcl11b-mCherry. Points graphed show Mean Fluorescent Intensities for both markers at the indicated stages, from results in (B). Note that when Bcl11b is first turned on, the cells are still expressing PU.1 comparably to ETP cells. Results are representative of three independent experiments.

Figure 6

Gene expression effects of Bcl11b deletion in the context of DN2a to DN2b progression. (A) Heat map of RNA-seq phenotype of Bcl11b^−/− DN2a-like pro-T cells, compared with true DN2a cells and true DN2b cells. Bcl11b^−/− cells were prepared as in ref. (162), and compared by RNA-seq with DN2a and DN2b cells as in ref. (137). Bcl11b-deficient cells mimic DN2a cells with respect to up- and down-regulation of different groups of genes (DN2a-like 1, DN2a-like 2) more than they mimic DN2b cells (DN2b-like 1, DN2b-like 2), since the DN2a-like groups contain more genes than the DN2b-like groups; but the phenotype is clearly split. Also note the top group of genes (“Bcl11b-deficiency specific”) which are strongly expressed in the mutant cells but not expressed in either normal control. (B) Quantitation of effects of Bcl11b deletion on expression of specific genes, from RNA-seq analyses. Each gene is compared in expression levels between DN2a cells and Bcl11b-deficient cells (left bars), and between DN2b cells and Bcl11b-deficient cells (right bars), with the colors showing whether the expression is higher in the wildtype cells (light, dark blue) or the mutant cells (red, orange). Differential expression is shown as fold difference on a log₂ scale from −6 to +6. Where differences exceed |2⁶| fold, for Cd2, Il2rb and Fcgr3, the value (log₂) is provided numerically. Similar results for these genes have been obtained in >4 independent experiments (J. A. Zhang, W. Zeng, L. Li, A. Mortazavi, E. V. Rothenberg, unpublished).

Figure 7

Different types of combinatoriality for transcription factor action in T-cell specification: two theoretical possibilities. Different gene expression patterns of cells at different stages are shown as a trajectory from an initial gene expression pattern at one point in a three-principal-component space to a final gene expression pattern at another point (thick dark blue arrows). Two models are shown in which the effects of different transcription factors on gene expression are shown as different colored vectors propelling the cells’ gene expression profiles along this path, where the individual roles of the factors differ. (A) A model in which all factors promote the T-cell program faithfully (vectors all parallel to the main trajectory), but in which participating factors are required to work in AND logic to drive developmental progression from start to finish. Left, parallel but stage-dependent effects of factors push cells along the unique trajectory of gene expression change. Right, if factor represented by magenta vector is removed, development halts but is still on the canonical track. Green and yellow vectors, and part of the light blue vector, are depicted as thin arrows in this case to indicate the constraint that these factors cannot work when the magenta factor is absent. (B) An alternative model in which individual vectors do not simply work to promote the T cell fate (not individually parallel to main path), but all have a component that can contribute to the main path and/or counteract another factor’s tendency to deviate from the main path. Although the panel shows the arrows operating sequentially to show their individual directions more clearly, note that this model also works well if they often act in combinations in overlapping time frames like the factors in A. Left, under normal conditions the resultant of adding the disparate transcription factor activities together pushes the cells along the main path. Right, if factor represented by magenta vector is removed, vector addition still advances the cell to change its gene expression pattern, but now it no longer follows the T-cell path.