Specification of tissue-resident macrophages during organogenesis

Abstract

Tissue-resident macrophages support embryonic development and tissue homeostasis and repair. The mechanisms that control their differentiation remain unclear. We report here that erythro-myeloid progenitors in mice generate premacrophages (pMacs) that simultaneously colonize the whole embryo from embryonic day 9.5 in a chemokine-receptor-dependent manner. The core macrophage program initiated in pMacs is rapidly diversified as expression of transcriptional regulators becomes tissue-specific in early macrophages. This process appears essential for macrophage specification and maintenance, as inactivation of Id3 impairs the development of liver macrophages and results in selective Kupffer cell deficiency in adults. We propose that macrophage differentiation is an integral part of organogenesis, as colonization of organ anlagen by pMacs is followed by their specification into tissue macrophages, hereby generating the macrophage diversity observed in postnatal tissues.

Fig. 1. A core macrophage program is initiated simultaneously in pMacs in all tissues

(A) Summary of surface phenotype used for EMPs, pMacs, and macrophages. (B) Scorecard visualization of differentially upregulated genes (DESeq2 Wald test, adjusted p-value < 0.05, BH-correction) in pMacs (E9.5 and E10.25) in comparison to EMPs. The table shows the relative enrichment of differentially upregulated genes in pMacs across cell types and tissues (y-axis) and developmental time points (x-axis, from E9 to P21). See Table S1, Fig. S1, and Methods for details of the scorecard. (C) May-Gruenwald-Giemsa stained cytospin preparations of sorted EMPs, pMacs and early macrophages from yolk sac (YS), head, limbs and fetal liver (FL) at E10.25 and E12.5. n=3 independent experiments. (D) tSNE plot of scRNA-seq data showing distribution of CD45^low/+ cells from E10.25 embryos into three clusters (see also Fig. S2). Cluster distribution based on DBScan is overlaid onto the graph. (E) Superimposition of EMP-, pMac-, or macrophage-specific signatures defined by the bulk RNA sequencing on the tSNE plot shown in D. (F) tSNE plot as in (D) overlaid with the relative expression values for Kit and Maf.

Fig. 2. Differentially expressed genes during differentiation from EMP to macrophage

(A) (upper panel) Developmental pseudotime diagram (q-value<0.05) showing down regulation of EMP-specific genes (differentially expressed compared to the macrophage and pMac cluster, p-value<0.05, FC>1.4) over the differentiation path from EMP to pMacs and macrophages. (lower panel) Similar plot depicting macrophage-specific genes significantly regulated over pseudotime (q-value<0.05) and differentially expressed compared to the EMP and pMac cluster (p-value<0.05, FC>1.4)). See Fig. S2G. (B) Heatmap representation of selected genes differentially regulated between EMPs vs. pMacs and EMPs vs. early macrophages in bulk RNA-seq analysis. Black boxes were drawn around those samples used for differential expression analysis. See also Table S1, S2.

Fig. 3. EMP-derived pMacs colonize the embryo to generate macrophages

(A) Flow cytometry analysis of E10.25 Csf1r^MeriCreMer; Rosa26^LSL-YFP (OH-TAM at E8.5) tissues showing expression of Il4ra, Il13ra1, CD16.2, CD64, Ifngr, Tnfr2, Tim4, and CD206 on YFP⁺ Kit⁺ progenitors, pMacs, and macrophages. MFI: mean fluorescent intensity. Data are representative of n=4 independent experiments with 4-6 embryos per marker. See also Fig. S3A. (B) Quantification of immunostainings on cryosection from E10.25 Csf1r^MeriCreMer; Rosa26^LSL-YFP embryos, pulse-labeled with OH-TAM at E8.5 with antibodies against YFP, Iba1 and CD16/32, Dectin-1, Trem2, F4/80, CD206 or Granulin. n=2-4 embryos and 2 sections per embryo per marker. See Fig. S4. (C) tSNE plot as in (1D) overlaid with the relative expression values for Tnfrsf11a and Cx3cr1. (D) YFP labeling efficiency of Tnfrsf11a^Cre+; Rosa26^LSL-YFP in pMacs and F4/80⁺ macrophages in YS and whole embryo at E10.25, fetal liver HSCs (long term (LT, Lin⁻Kit⁺Sca1⁺CD150⁺CD48⁻), short term (ST, Lin⁻Kit⁺Sca1⁺CD150⁻CD48⁻) and multipotent progenitor (MPP, Lin⁻Kit⁺Sca1⁺CD150⁻CD48⁺)) and tissue macrophages at E14.5 and 6 weeks, and blood leukocytes (B-cells (CD19⁺), T-cells (CD19⁻Ly6G⁻CD115⁻CD3⁺), NK cells (CD19⁻Ly6G⁻CD115⁻CD3⁻NKp46⁺), neutrophils (CD19⁻Ly6G⁺) and Ly6C^hi monocytes (CD19⁻CD115⁺Ly6G⁻Ly6C^hi), and tissue CD11b^high myeloid cells from 6 week-old mice. Circles represent individual mice. n=4 independent experiments. See Fig. S5.

Fig. 4. Tissue colonization by pMacs is Cx3cr1-dependent

(A) Expression of GFP and Dectin-1 in Cx3cr1^gfp/+ mice during development (E8.5-10.5) in Kit⁺ cells (CD45^low, Kit⁺), pMacs and macrophages. sp: somite pairs. Data are representative of n=9 independent experiments. Biological replicates have been aggregated per cell type, time point and tissue. (B) Flow cytometry analysis in Cx3cr1^+/− and Cx3cr1^−/− of pMacs and macrophages from yolk sac (YS), head, and caudal at E9.5 (upper panel) and liver, YS, head, and limbs at E10.5 (lower panel). Circles represent individual mice. Data are representative of n=6 independent experiments. P-values were calculated using Student’s t test. sp: somite pairs.

Fig. 5. Early specification of tissue-resident macrophages

(A) Flow cytometry analysis of Csf1r^MeriCreMer; Rosa26^LSL-YFP (OH-TAM at E8.5) liver, brain, lung and skin F4/80⁺ cells from postnatal mice (4 weeks old) showing expression of Il4ra, Il13ra1, Tnfr2, Ifngr, Dectin-1, CD64, Tim4, and CD206 (black dotted on whole population and green on YFP⁺ cells). Gray histograms show the fluorescence intensity of the FMO controls. (B, C) Scorecard analysis of all differentially upregulated genes in postnatal macrophages. The scorecards show the relative enrichment of each set of upregulated genes across each cell type (y-axis) and developmental time point (x-axis). See Methods for details of the score card. Numbers for each population indicate differentially up-regulated transcripts in postnatal (P2-P21) brain, liver, kidney, epidermis or lung macrophages when comparing one population vs. the others. See also Table S3. (D) Heatmap representing all differentially upregulated transcriptional regulators (2-fold change, adj. p-value<0.05, BH-correction) between postnatal macrophages from brain, liver, kidney, skin and lung macrophages, and their relative expression in tissue macrophages from E10.25 to P21.

Fig. 6. Tissue-specific macrophage signatures are not detected in pMacs

(A) Immunostaining with antibodies against Id1 or Id3 (red), F4/80 (cyan) and YFP (green) on cryosections from E10.25 Csf1r^MeriCreMer; Rosa26^LSL-YFP embryos (OH-TAM at E8.5) (upper panel). Nuclei are counterstained with DAPI (white). Scale bar represents 2 μm. (B) tSNE plots of scRNA-seq data from CD45^low/+ cells from E10.25 embryo showing co-expression of Id1, Id3, and Sall3. See Fig. S11. (C) PCA plot of scRNA-seq data of cells from cluster 2 (pMacs) with superimposed fetal tissue macrophage-specific signatures. See Fig. S11, Table S2 and methods.

Fig. 7. Id3 is important for Kupffer cells development

(A) Flow cytometry analysis of pMacs and macrophages in yolk sac (YS) and liver from E10.25 Id3^−/− and Id3^+/− embryos. Circles represent individual mice. n=3 independent experiments. (B) Flow cytometry analysis of F4/80⁺ macrophages in liver, brain and kidney from E14.5 and E18.5 Id3^−/− and Id3^+/− mice. Circles represent individual mice. n=4 independent experiments. (C) Immunostaining with antibodies against CD31 and F4/80 on liver cryosections from E14.5 Id3^−/− and Id3^+/−, and Tnfrsf11a^Cre−;Id3^f/+ and Tnfrsf11a^Cre+; Id3^f/f mice. The figure displays isovolume-rendered images. Bar graphs represent F4/80⁺ cells/mm². Circles represent individual images. n=3 independent experiments. (D) Flow cytometry analysis of F4/80⁺ macrophages in liver, brain and kidney from 4 week-old Id3^−/− and Id3^+/− mice. Circles represent individual mice. n=2 independent experiments. (E) Immunostaining with antibodies against CD31 and F4/80 on liver cryosections from 2 week-old Tnfrsf11a^Cre+;Id3^f/+ and Tnfrsf11a^Cre+; Id3^f/f mice. The figure displays isovolume-rendered images. Bar graphs represent F4/80⁺ cells/mm². Circles represent individual images. (F) Immunostaining with antibodies against Id3 (red), F4/80 (cyan) and YFP (green) on cryosections from on livers from 4 week-old Csf1r^MeriCreMer; Rosa26^LSL-YFP (OH-TAM at E8.5) mice. Nuclei are counterstained with DAPI (white). Scale bar represents 5 um. (G) Immunostaining with antibodies against F4/80 (green) phospho-histone 3 (PHis3, red) and DAPI (gray) on liver cryosections from 4 week-old Id3^−/− and Id3^+/− mice. Scale bar represents 10 um. Data are representative of 5 mice per genotype. Each dot represents the mean of PHis3⁺ cells (in %) of total F4/80⁺ found in 5 sampling areas (830 um²) for each individual liver. (H) Scatterplot comparison of gene expression of 3 week-old Id3^−/− and Id3^+/− Kupffer cells. Both axes (in log₂ scale) represent normalized gene expression values (average value from three Id3^+/− and two Id3^−/− replicates). Red circles mark the 3-fold cut-off in both directions in gene expression level. Top GO terms for genes enriched in either Id3^+/− or Id3^−/− are indicated. P-values were calculated using Student’s t test..See also Fig. S12.

Fig. 8. Graphic summary of the establishment of the core macrophage program and subsequent specification

Cx3cr1 is expressed in pMacs and is important for colonization of the embryo. Id3 is a liver macrophage-specific gene, which is essential for Kupffer cell development.