Spatially restricted immune and microbiota-driven adaptation of the gut

Abstract

The intestine is characterized by an environment in which host requirements for nutrient and water absorption are consequently paired with the requirements to establish tolerance to the outside environment. To better understand how the intestine functions in health and disease, large efforts have been made to characterize the identity and composition of cells from different intestinal regions^1-8. However, the robustness, nature of adaptability and extent of resilience of the transcriptional landscape and cellular underpinning of the intestine in space are still poorly understood. Here we generated an integrated resource of the spatial and cellular landscape of the murine intestine in the steady and perturbed states. Leveraging these data, we demonstrated that the spatial landscape of the intestine was robust to the influence of the microbiota and was adaptable in a spatially restricted manner. Deploying a model of spatiotemporal acute inflammation, we demonstrated that both robust and adaptable features of the landscape were resilient. Moreover, highlighting the physiological relevance and value of our dataset, we identified a region of the middle colon characterized by an immune-driven multicellular spatial adaptation of structural cells to the microbiota. Our results demonstrate that intestinal regionalization is characterized by robust and resilient structural cell states and that the intestine can adapt to environmental stress in a spatially controlled manner through the crosstalk between immunity and structural cell homeostasis.

Extended Data Fig. 1.. Experiential and computational construction of the transcriptional landscape of the intestine.

a, Hematoxylin and eosin (H&E) stain image of the partitioned intestine. b, Boxplots showing the number of genes detected in each spot on each Visium slide (the center line is the median; box limits are the upper and lower quartiles; and whiskers show 1.5 times the interquartile range from the box). The line on the secondary Y-axis shows the number of spots with tissue on each Visium slide. (For intestinal regions, data is shown for n=3 SPF and GF mice and n=2 FMT mice. For DSS and light/dark cycle, data from n=1 SPF or GF mouse is shown). c, Schematic of experimental design (created with R, Adobe Illustrator and BioRender.com). d, Expression of Epcam (left) and Tagln (right) in each Visium spot on the unrolled and aligned axes. e, Clusters of Visium spots (Louvain algorithm with clustering resolution =0.5) shown on the original Visium slide (top) and the unrolled and aligned axes (bottom). f, Cluster annotation of spots along the serosa-epithelium axis (left). Dot plot (right) of marker genes for each annotated cluster (top 20 genes in each cluster ranked by Wilcoxon rank sum test p-values; all of them have adjusted p-value<0.05; expressed in >50% within the cluster and <30% in other clusters). g, Module score for each cell type (Methods) in different tissue layers.

Extended Data Fig. 2.. Biological circuit maps.

a, Top 10 Gene Ontology (GO) terms (left, Biological Processes; right, Molecular Functions) enriched for marker genes of each tissue (top 100 marker genes ranked by Wilcoxon test p-value; all have adjusted p-value<0.05; enriched GOs are significant with adjusted p-value<0.05 by Fisher’s exact test). b, Spatial heatmap showing the expression (Z-score) of the upregulated SLC transporter genes in Fig. 1c. The heatmap columns are arranged based on the coordinates of the unrolled axes aligned across three replicates. The network to the right connects the SLC transporters with their known ligands. c, Dot plot showing the expression of regionally variable curated GPCRs (upregulated in at least one section of SI or colon). d, Dot plots showing the expression of disease risk-associated nuclear receptors. e, Dot plot showing the expression of all fine mapped IBD risk genes irrespective of regional enrichment. f, Dot plot showing the expression of regionally variable (upregulated in at least one section of SI or colon) monogenic IBD genes with average expression >0.6 (normalized and log transformed).

Extended Data Fig. 3.. Biological circuit maps and distal region shared gene expression.

a-b, Dot plots showing the expression of disease risk-associated genes: (a) transcription factors (b) along the intestine. Only regionally variable genes and with average expression >0.6 (normalized and log transformed) in at least one segment of SI or colon were shown. c, Expression of regionally variable transcription factors (expressed in >30% in any one region but <5% in any other regions) along the unrolled axis (n=3 biological replicates). Heatmaps on the left summarize the average scaled expression of genes along the serosa-to-epithelium axis (only spots with scaled expression >0.5 considered). d, Expression of solute carrier family transporters along the intestinal length. e, Scaled expression of Onecut2, Hoxb13, Tmprss2 along the intestine of SPF mice (n=3). Lines depict the locally weighted scatterplot smoothing curves.

Extended Data Fig. 4.. The steady state intestinal spatial landscape is robust.

a, Average log FC of gene expression comparing SPF and GF animals (absolute value >0.1). Genes that are prevalent in SPF (top, expressed in >20% of the SPF but <20% of GF Visium spots) or GF (bottom, expressed in >20% of the GF but <20% of SPF Visium spots) were highlighted in color. b, Prevalence (% expressed per Visium spot) of genes in each region. Highlighted genes with high log2FC in expression between SPF and GF mice (absolute average log2 FC >1). c, Dot plot of expression of select genes by region and condition. de, Expression of Mbl2 (d) and S100g (e) along the intestine of SPF, GF and FMT mice. Biological replicates are shown for each condition (SPF and GF, n=3; FMT n=2). f, Examples of genes that exhibit expression gradients along the unified X axis in the SI (Guca2a, top) and colon (Hmgcs2, bottom). g, Scatter plots showing the concordance (Pearson correlation, r) of spatial association (the Spearman correlation between the proximal-distal axis and gene expression) across biological replicates (n=3 SPF, n=3 GF, n=2 FMT). Points show the spatial association of an expressed gene and lines represent the fitted linear regression curve. Examples shown in panel f are highlighted in the corresponding panels (circle - Guca2a; triangle - Hmgcs2) h, Expression of the circadian clock associated genes Nr1d1 and Per2 in the colon of SPF and GF mice measured during the light or dark cycle (n=1 per condition). i, Scatter plots showing concordance of spatial association between animals studied during the light or dark cycle (n=1 for each cycle).

Extended Data Fig. 5.. Identification and characterization of spatial niches in the small and large intestine.

a-c, Clustering of SI Visium data (resolution=0.2). (a) UMAPs showing the clustering. (b) Boxplots showing the fraction of each cluster. Box limits are the upper and lower quartiles; and whiskers are 1.5 times the interquartile range from the box (3 biological replicates per box). (c) Expression of marker genes for each cluster. d-e, Clustering of colon Visium data (resolution=0.8). (d) UMAPs showing the clustering. (e) Expression of marker genes for each cluster. f, Spatial distribution of each cluster on one example of SPF colon. g, Top 10 Gene Ontology (GO) terms (Biological Processes) enriched for marker genes of each colon section (top 500 maker genes ranked by Wilcoxon test p-value; all of them have adjusted p-value<0.05; enriched GOs are significant with adjusted p-value<0.05 by Fisher’s exact test). h, Spatial expression of C2 enriched, microbiota induced genes Ang4, Retnlb, Itln1, and Pnliprp2 on SPF colon tissue from 3 mice (top down).

Extended Data Fig. 6. Spatial characterization of DSS-induced inflammation over time.

a, Schematic of experimental design (n=1 at each time point, (created with BioRender.com)). b, Recovery of DSSdisrupted gene expression across time. Genes that are differentially expressed (absolute log2 FC >1) in the D12 DSS-treated mouse are shown. c, Top 10 Gene Ontology (GO) terms (Biological Processes) enriched for upregulated genes in each colon section of the D12 mouse compared to the sham (top 500 maker genes ranked by Wilcoxon test p-value; all have adjusted p-value<0.05; enriched GOs are significant with adjusted p-value<0.05 by Fisher’s exact test). d, Marker genes for each cluster shown in Fig. 3b (resolution = 0.3) obtained from colon samples across all time points. e, Expression of example marker genes for the epithelial cluster (cluster 8) (Clca4b and Ido1) and the mucosal cluster (cluster 10) (Il1b and Il11) in colon samples across all time points. White boxes indicate regions with residual expression at later time points. f, Volcano plot of DEGs comparing Ido1-positive spots (log transformed expression >2; Wilcoxon test) and Ido1-negative spots in cluster 8. g, Proximal (top), middle (middle), and distal colon (bottom) specific gene module scores plotted on swiss rolls at different stages of recovery.

Extended Data Fig. 7.. Single-cell characterization of the proximal, middle, and distal regions of the colon in SPF, GF, and FMT mice.

a, Schematic of the different regions of the colon showing anatomical location of the middle colon in the visceral cavity (left) and the delineation of the proximal, middle, and distal colon (middle). Regions A to D as they were partitioned for scRNA-seq are then shown (right). b, UMAP of single-cell transcriptomics showing 99 annotated cell subsets. b, Number of cells of each major cell lineage captured by the single-cell dataset. c-e, UMAPs of enterocyte (c), fibroblast (d) and goblet cell (e) lineages.

Extended Data Fig. 8.. Single-cell coupled with spatial transcriptomics reveals spatially restricted structural cell subsets and spatially restricted adaptations to the microbiota.

a, Estimated abundance (Cell2location on Visium samples from 3 biological replicates; cells with abundance lower than 0.5 or one standard deviation from the mean for each cell type are removed) of spatially variable structural cell subsets (the center line is the median; box limits are the upper and lower quartiles; and whiskers are 1.5 times the interquartile range). b, Distribution of spatially variable structural cell subsets mapped onto space for colon tissue (Xenium). c-d, Spatial heatmaps showing the counts of cell types (Z-score) assigned to the Xenium sample of SPF mouse colon. The heatmap columns are arranged based on the coordinates of the unrolled proximal-distal axis from left to right (c; summarized into 1000 bins) and projected serosa-mucosa axis (b; summarized into 50 bins). e, Expression of marker genes for enterocytes. f, Antibody staining of SLC9A3 protein (magenta) on colon tissue. Image is representative of n=3 biological replicates. g, Expression of marker genes for fibroblasts. h, Expression of marker genes for goblet cells. Nuclei are stained with DAPI (blue). i, UMAP of RNA velocity analysis of goblet cell subtypes.

Extended Data Fig. 9.. ILC2s are uniquely activated by the microbiota in the middle colon.

a, Number of DEGs between SPF and GF mice in immune cell populations from the single-cell data (stars mark the section without comparison due to low number of cells, N<30). b, Expression of genes from single-cell RNA-seq data of ILC2s from different regions of colon (A-D; proximal-distal). Data summarize pooling of SPF, GF, and FMT treated mice. c, Representative flow cytometric gating strategy for ILC2s and eosinophils isolated from mouse colon. This gating strategy was used for summary data presented in f, h, i, and j and Extended Data Fig.10c,e. Gating shown is from n=1 SPF mouse region B. d, Representative histograms showing expression of CD28 on the surface of ILC2s gated as in c for SPF (purple) and GF (black) mice from colon region B. e, Representative histograms for the expression of surface markers ST2, IL17RB, CD25, and CD127 from left to right on ILC2s from colon region B. f, Data summarizing the median fluorescence intensity (MFI) for surface markers in e on ILC2s from regions A to D in SPF (purple) and GF (black) mice. n=9 mice from 3 independent experiments for SPF and n=6 mice from 2 independent experiments for GF for ST2 and IL17RB. n=15 mice from 5 independent experiments for SPF and n=9 mice from 3 independent experiments for GF for CD25. n=12 mice from 4 independent experiments for SPF and n=9 mice from 3 independent experiments for GF for CD127. Box limits are the upper and lower quartiles with the middle line representing the median; and whiskers are 1.5 times the interquartile range from the box. g, Representative flow cytometric gating for IL-5 and IL-13 on ILC2s from colon region B gated as shown in b. Box limits are the upper and lower quartiles with the middle line representing the median; and whiskers are 1.5 times the interquartile range from the box. h, Data summarizing the frequency of ILC2s from colon regions A to D expressing IL-5, IL-13, or both from left to right in SPF (purple) and GF (black) mice. n=6 mice per group summarized from 2 independent experiments. i, Data summarizing the number of ILC2s recovered from colon regions A-D gated as in c in SPF (purple) and GF (black) mice. n=22 mice from 7 independent experiments for SPF and n=9 mice from 3 independent experiments for GF. j, Data summarizing MFI of CD28 on ILC2s isolated from GF colon region B following explant treatment with recombinant IL-33 and IL-25 (purple) or media control (black) for 12hrs. Data summarizing n=6 mice from 2 independent experiments. Box limits are the upper and lower quartiles with the middle line representing the median; and whiskers are 1.5 times the interquartile range from the box. k, Data summarizing the amount of IL-5 and IL-13 detected in pg/mL in supernatants from explants of colon tissue from GF colon region B treated with IL-33 and IL-25 as in j. Data summarizing n=6 mice from 2 independent experiments. Box limits are the upper and lower quartiles with the middle line representing the median; and whiskers are 1.5 times the interquartile range from the box. i, Data summarizing expression of selected middle colon genes by quantitative PCR from explants of GF colon region B treated with IL-4/5/13 for 6 hrs. Gene expression relative to the housekeeping gene Gapdh. n=4 mice representative of 2 independent experiments. Box limits are the upper and lower quartiles with the middle line representing the median; and whiskers are 1.5 times the interquartile range from the box.

Extended Data Fig. 10.. ILC2s are required for the goblet cell adaptation to the microbiota in the middle colon in the steady state.

a, Representative flow cytometric gating strategy for total ILC2s isolated from mouse MLN. b, Experimental schematic (created with BioRender.com) for ILC2 depletion (left) and gating strategy and summary (right) of ILC2s from MLNs in control and Cre+ mice. n=4 mice per group and summarize 2 independent experiments. Unpaired two-sided t-test. Data are presented as the mean +− s.e.m. c, Data summarizing the number of eosinophils recovered from colon regions A-D gated as in Extended Data Fig. 9c for SPF (purple) and GF (black) mice. n=22 mice from 7 independent experiments for SPF and n=9 mice from 3 independent experiments for GF. Box limits are the upper and lower quartiles with the middle line representing the median; and whiskers are 1.5 times the interquartile range from the box. d, Representative histograms showing expression of SIGLEC-F on the surface of eosinophils gated as in Extended Data Fig. 9c for SPF (purple) and GF (black) mice from colon region B. e, Data summarizing MFI of SIGLEC-F on eosinophils recovered from GF colon regions A-D gated as in c in SPF (purple) and GF (black) mice. n=21 mice from 7 independent experiments for SPF and n=9 mice from 3 independent experiments for GF. Box limits are the upper and lower quartiles with the middle line representing the median; and whiskers are 1.5 times the interquartile range from the box. f, Experimental schematic (created with BioRender.com) for eosinophil depletion via anti-IL-5 administration (top) and gating strategy and summary (bottom) of eosinophils from MLNs in isotype and anti-IL-5-treated WT SPF mice. n=4 mice per group; data summarize 2 independent experiments. Unpaired two-sided t-test. Data are presented as the mean +− s.e.m. g, Antibody staining of ANG4 protein (green; Minimum display value = 10 and maximum display value = 30) on colon tissue from isotype and anti-IL-5 treated SPF mice showing enrichment in the C2 region in all conditions. Nuclei are stained with DAPI (gray; Minimum display value = 0 and maximum display value = 150). n=2 mice per group and images representative of 2 independent experiments. h, Expression of example middle colon genes in Xenium colon samples (n=2 mice for each condition). i, Difference in cell counts assigned to the Xenium colon samples between DT treated ROSA26^LSL-DTR and Nmur1i^Cre-eGFPROSA26^LSL-DTR mice (t statistic with pooled variance). Colon samples were binned into four bins following the way single-cell data were generated along the unrolled X axis. Boxplots display first and third quartiles.

Fig. 1 |. Mapping the spatial landscape of the intestine reveals regional and shared expression along the gut at steady state.

a, Expression along the unrolled axis of the top 30 enriched genes per region compared to other regions in SI (left) and colon (right), respectively (n=3 biological replicates). Heatmaps on the left edge summarize the average scaled expression of genes along the serosa-to-epithelium axis (only spots with scaled expression >0.5 considered). Swiss roll cartoon made in Adobe Illustrator. b, Upset plot showing the number of shared region enriched genes in each region (average log2 fold-change (log2FC) >0.25 and expressed in >30% of cells). Inset chord diagram shows the distribution of shared genes between SI and colon. c, Smoothed expression of solute carrier (Slc) transporter genes enriched in at least one region in both small and large intestine in b with proposed ligands on the right (n=3 biological replicates). D - duodenum, J1 - jejunum 2, J2 - jejunum 1, I - ileum, C1 - proximal colon, C2 - middle colon, C3 - distal colon.

Fig. 2 |. Spatial transcriptomics reveals a microbiota driven adaptation in the middle colon.

a, Scatter plots showing the log2FC of gene expression comparing SPF (X-axis) or FMT (Y-axis) against GF mice in proximal, middle and distal colon. Points colored by log2FC of expression in the indicated region compared to other two regions (genes with absolute log2FC >0.1 colored). Outliers of the two tails in each plot are shown in insets. b, Upregulated genes in C2 compared to C1 and C3 colored by log2FC for the comparison between SPF and GF animals (genes with absolute log2 FC >0.1 were colored). c, Antibody staining of ANG4 protein (green; Minimum display value = 7 and maximum display value = 25) on colon tissue from an SPF mouse showing enrichment in the C2 region. Nuclei stained with DAPI (gray; Minimum display value = 5 and maximum display value = 100). Processed using ImageJ and representative of n=5 biological replicates.

Fig. 3 |. A model of spatiotemporal damage reveals the steady state spatial landscape and adaptations in the colon are resilient to inflammation.

a, Spatial association (Spearman correlation coefficient) for each gene along proximal-distal axis of the colon in mice treated with DSS and allowed to recover for varying amounts of time compared to non DSS treated mice (sham) (Pearson correlation, r). Points are expressed genes and lines represent the fitted linear regression curve. b, DSS disruption and recovery of spatial clusters derived from expression visualized on the UMAP (left) and swiss rolls (middle), coupled with tissue H&E staining (right). Images are representative of the exact tissue slice that was processed for Visium. DSS treatment and associated recovery period was conducted once per time-point. c, Expression of Ang4 on swiss rolls at different stages of recovery. d, Proximal, middle, and distal colonspecific gene module scores plotted along the unrolled axis of the colon at different stages of recovery. Fitted curve and shaded area represents the fitted locally estimated scatterplot smoother (LOESS) with 95% confidence interval, respectively. Day 0 curve shown as red lines overlaid on D12, D30, and D73 plots.

Fig. 4 |. Single cell RNA-seq coupled with spatial transcriptomics reveals spatially restricted structural cell neighborhoods and microbiota-driven adaptations.

a, Four regions of colon from which single-cell transcriptomics was generated (created with BioRender.com). Relative abundances of annotated cell types in the enterocyte (top), fibroblast (middle) and goblet cell (bottom) lineages (for SPF and GF, averaged for n=2 biological replicates for fibroblast and n=3 biological replicates for enterocyte and goblet cells and for FMT, averaged for n=2 biological replicates). Black borders indicate cell types unique to each region. b, Left: distribution of cell types in (a) assigned to the Xenium sample of SPF mouse colon. Region B enriched cell types highlighted with black border. Right: counts of spatially variable structural cell subsets along the bins (N=20) from proximal-to-distal axis of the colon in SPF and GF mice. Swiss roll cartoon made in Adobe Illustrator. c, Marker genes (average log2FC >0.1 compared to other cell types in the same lineage; Mature enterocytes II vs. other Mature enterocytes (top) Igfbp3+/Serpina3g-hi fibroblasts vs. other Igfbp3+ fibroblasts (middle) Retnlb/Ang4+ GCs vs. all other GCs (bottom). Top 50 genes ranked by average log2FC or highly specific to the cell type (log2FC in prevalence >1.5) are labeled.

Fig. 5 |. Immune-mediated control of spatially restricted structural cell adaptations to the microbiota.

a, Number of DEGs for immune cell types across regions of colon between SPF and GF mice (FDR<0.001, absolute log2 fold change > 0.5). b, Log2 fold change of DEGs for ILC2s in (a). c, Data summarizing median fluorescence intensity (MFI) of the surface protein marker CD28 on colonic ILC2s (A-D; proximal-distal) of SPF (purple) and GF (black) mice. n=15 mice from 5 independent experiments for SPF and n=9 from 3 independent experiments for GF. Boxplot displays first and third quartiles with the middle line representing the median, and whiskers show 1.5 times the interquartile range from the box. d, Antibody staining of ANG4 protein (green; Minimum display value = 10 and maximum display value = 30) on colon tissue from DT treated ROSA26^LSL-DTR (left, n=4 mice) and Nmur1i^Cre-eGFPROSA26^LSL-DTR (right, n=4 mice) mice showing loss of ANG4 in ILC2-depleted mice (right). Nuclei stained with DAPI (gray; Minimum display value = 0 and maximum display value = 150). Processed using ImageJ and representative of two independent experiments. e, Counts of spatially variable goblet cell subsets along the bins (N=20) from proximal-to-distal axis of the colon in DT treated ROSA26^LSL-DTR (left) and Nmur1i^Cre-eGFPROSA26^LSL-DTR (right) mice showing loss of Retnlb/Ang4+ GCs in ILC2-depleted mice. Swiss roll cartoons made in Adobe Illustrator.