Exposure to Mycobacterium remodels alveolar macrophages and the early innate response to Mycobacterium tuberculosis infection

Abstract

Alveolar macrophages (AMs) play a critical role during Mycobacterium tuberculosis (Mtb) infection as the first cells in the lung to encounter bacteria. We previously showed that AMs initially respond to Mtb in vivo by mounting a cell-protective, rather than pro-inflammatory response. However, the plasticity of the initial AM response was unknown. Here, we characterize how previous exposure to Mycobacterium, either through subcutaneous vaccination with Mycobacterium bovis (scBCG) or through a contained Mtb infection (coMtb) that mimics aspects of concomitant immunity, impacts the initial response by AMs. We find that both scBCG and coMtb accelerate early innate cell activation and recruitment and generate a stronger pro-inflammatory response to Mtb in vivo by AMs. Within the lung environment, AMs from scBCG vaccinated mice mount a robust interferon-associated response, while AMs from coMtb mice produce a broader inflammatory response that is not dominated by Interferon Stimulated Genes. Using scRNAseq, we identify changes to the frequency and phenotype of airway-resident macrophages following Mycobacterium exposure, with enrichment for both interferon-associated and pro-inflammatory populations of AMs. In contrast, minimal changes were found for airway-resident T cells and dendritic cells after exposures. Ex vivo stimulation of AMs with Pam3Cys, LPS and Mtb reveal that scBCG and coMtb exposures generate stronger interferon-associated responses to LPS and Mtb that are cell-intrinsic changes. However, AM profiles that were unique to each exposure modality following Mtb infection in vivo are dependent on the lung environment and do not emerge following ex vivo stimulation. Overall, our studies reveal significant and durable remodeling of AMs following exposure to Mycobacterium, with evidence for both AM-intrinsic changes and contributions from the altered lung microenvironments. Comparisons between the scBCG and coMtb models highlight the plasticity of AMs in the airway and opportunities to target their function through vaccination or host-directed therapies.

Fig 1. Prior exposure to Mycobacterium leads to faster activation and innate cell recruitment following aerosol Mtb challenge.

Control, scBCG, and coMtb mice, 8 weeks following exposure, challenged with standard low-dose H37Rv. Lungs collected on day 10, 12, and 14 post-infection. A) AM MHC II MFI. B) Total numbers of MDMs, PMN, DC, and Ly6C⁺CD11b⁺ monocytes. C) AM viability (% Zombie Violet-). D) Total numbers of CD44⁺ CD4⁺ T cells, ESAT6-tetramer⁺ CD4⁺ T cells, CD44⁺ CD8⁺ T cells, and TB10.4-tetramer⁺ CD8⁺ T cells. Mean +/- SEM, 5 mice per group, representative of 3 independent experiments. One-way ANOVA with Tukey post-test. * p< 0.05, **p< 0.01, ***p < 0.001. B, C) *, **, and *** scBCG or coMtb vs control; +, ++ scBCG vs coMtb.

Fig 2. Mycobacterium exposure alters the alveolar macrophage transcriptional response to Mtb infection in vivo.

Bulk RNA-seq profiles of Mtb-infected AMs 24 hours following high-dose mEmerald-H37Rv infection. Gene expression changes are compared to respective naïve samples: Mtb-inf control vs naïve control; Mtb-inf scBCG vs naïve scBCG; Mtb-inf coMtb vs naïve coMtb (controls- reported in Rothchild et al, 2019 [10]; coMtb- reported in Nemeth et al, 2020 [25]). A) Principal Component Analysis using DEG (|fold change| > 2, FDR< 0.05) in Mtb-infected AMs compared to respective naïve AMs (control, scBCG, or coMtb). B) Venn Diagram and Intersection plot of overlap in up-regulated DEG between the 3 conditions. C) Gene Set Enrichment Analysis of 50 Hallmark Pathways. Pathways shown have |NES| > 1.5 and FDR< 0.05 for at least one of the conditions. * FDR< 0.05, **FDR< 0.01, ***FDR< 0.001. D) Heatmap of 131 original in vivo DEG at 24 hours in Mtb-infected AM (left), Interferon Stimulated Genes, derived from macrophage response to IFNα (fold change >2, p-value < 0.01) Mostafavi et al, 2016 [30] (center-left), IL6 JAK STAT3 hallmark pathway (center-right) and selected coMtb signature genes (right, *FDR< 0.05, FC> 2). E) Scatterplots depicting fold change (log₂) for Mtb-infected AMs over naïve AMs for scBCG versus coMtb. Highlighted pathways: Nrf2-associated genes out of 131 original in vivo DEG (56 genes, purple), shared leading edge genes for scBCG Interferon Alpha Response and Interferon Gamma Response pathways (61 genes, orange), and leading edge genes for coMtb IL6 JAK STAT3 pathway (23 genes, green). Compiled from 4 independent experiments per condition for control, 2 independent experiments per condition for scBCG and coMtb.

Fig 3. Mycobacterium exposure modifies the alveolar macrophage phenotype in the airway pre-challenge.

Single-cell RNA-sequencing of BAL samples from control, scBCG, and coMtb mice pre-aerosol challenge. A) Compiled scRNAseq data for all BAL samples, highlighted by major clusters, annotated based on closest Immgen sample match. B) Highlighting of the two clusters used for macrophage subcluster analysis. C) The 11 clusters generated by the macrophage subcluster analysis, separated by condition. D) Expression of major macrophage-specific markers: Siglecf, Mertk, Fcgr1, Lyz2, Itgam (CD11b), and Itgax (CD11c). E-I) Relative frequency of each macrophage subcluster by condition. (violin plots by cluster) Expression level of representative genes distinguished by that cluster compared to other clusters. One-way ANOVA with Tukey post-test, * p< 0.05. (3-way violin plots by condition) Differentially expressed genes within Clusters 2, 7, and 3 between control vs scBCG vs coMtb samples. Wilcoxon Rank Sum Test, Bonferroni adjusted p-value. *adj-p< 0.05, **adj-p< 0.01, ***adj-p< 0.001. J) Pseudotime analysis (Monocle3) with starting node at the largest cluster in control, Cluster 0 (top) and at the cluster of proliferating cells, Cluster 4,9 (bottom). K) ISG Module Score by cluster. Module derived from macrophage response to IFNα (fold change> 2, p-value< 0.01) (Mostafavi et al, 2016) [30]. Data is compiled from two independent experiments (circle, triangle) with 3 conditions each for a total of 6 samples.

Fig 4. Airway T cell and dendritic cell profiles following Mycobacterium exposure.

Single-cell RNA-sequencing of BAL samples from control, scBCG, and coMtb mice pre-aerosol challenge. A) Compiled scRNAseq data for all BAL samples, with T cell and dendritic cell clusters highlighted. B) Relative frequency of T cells and DCs. C-F) T cell subcluster analysis. C) T cell subclusters compiled and split by condition. Annotations made following Immgen profile matches and manual marker inspection. D) Relative frequency of Clusters 0–4 for each condition. E) UMAP gene expression plot for general T cell markers. F) UMAP gene expression plot cluster-specific markers split by condition. G-J) Dendritic cell subcluster analysis. G) Dendritic cell subcluster, colored by each of 3 different clusters. H) Relative frequency of Clusters 0–2 for each condition. I) Violin plots for cluster-specific markers and genes of interest. J) Differentially expressed genes in Cluster 0 split by condition. *adj-p< 0.05, **adj-p< 0 .01, ***adj-p< 0.001, Wilcoxon Rank Sum Test, Bonferroni adjusted p-values. Data is compiled from two independent experiments with 3 conditions each for a total of 6 samples.

Fig 5. Cell-intrinsic remodeling of alveolar macrophages following Mycobacterium exposure.

A) AM isolation 8 weeks following scBCG or coMtb exposure. AMs were stimulated with Pam3Cys (10 ng/ml), LPS (10 ng/ml), and H37Rv (effective MOI ~2:1) for 6 hours (RNA-seq) or 20 hours (flow cytometry). B-D) Gene expression changes measured by bulk RNA-seq for stimulated AMs compared to respective unstimulated AMs (i.e., LPS-stim control AM vs unstim control AM; LPS-stim scBCG AM vs unstim scBCG AM; LPS-stim coMtb AM vs unstim coMtb AM). B) Scatterplots, log₂ fold change gene expression for stimulated to unstimulated AMs for each condition (control, scBCG, coMtb). Differentially expressed genes (DEG) are highlighted for one or both conditions (|Fold change| > 2, FDR< 0.05 for Pam3Cys and LPS; |Fold change| > 2, FDR< 0.2 for H37Rv). C) Scatterplots, log₂ fold change gene expression for H37Rv-stimulated to unstimulated scBCG versus coMtb AMs. Genes highlighted derived from gene sets in Fig 2E. Nrf2-associated genes (56 genes, purple), Interferon Alpha/ Gamma Response (61 genes, orange), and IL6 JAK STAT3 (23 genes, green). D) Gene Set Enrichment Analysis results for 50 HALLMARK pathways. Pathways shown have NES> 1.5 and FDR< 0.05 for at least one of the conditions. *FDR< 0.05, **FDR< 0.01, ***FDR< 0.001. E) Gating strategy and MHC II and TNF histograms for coMtb AMs, no stimulation versus LPS. F-G) MHC II and TNF MFI in control, scBCG, and coMtb AMs after 20 hours of LPS stimulation. *p< 0.05, **p< 0.01, ***p< 0.001, One-way ANOVA with Tukey post-test.

Fig 6. Mycobacterium exposure licenses an interferon-dependent response to H37Rv by alveolar macrophages.

Gene expression changes measured by bulk RNA-seq for Mtb-infected AMs compared to respective unstimulated AMs (i.e., Mtb-inf control AM vs unstim control AM; Mtb-inf scBCG AM vs unstim scBCG AM; Mtb-inf coMtb AM vs unstim coMtb AM). A) Gene expression for control, scBCG, and coMtb AMs, 6 hour H37Rv infection ex vivo, log₂ fold change (Mtb-infected/uninfected). IFN-dependent genes (339 total) and IFN-independent genes (352 total) based on WT vs IFNAR^-/- BMDM bulk RNA-seq dataset (Olson et al, 2021) (see Methods section). B) Gene expression for control, scBCG, and coMtb AMs, 24 hour in vivo H37Rv infection, Mtb-infected sorted, log₂ fold change (Mtb-infected/uninfected) for the same IFN-dependent and IFN-independent gene sets in (A). Grey bars indicate N.D. Normalized Enrichment Score (NES) calculated by GSEA for two data sets alongside Hallmark Pathways. +FDR< 0.05, ++FDR< 0.01, +++FDR< 0.001.