Integrated molecular imaging reveals tissue heterogeneity driving host-pathogen interactions

Abstract

Diseases are characterized by distinct changes in tissue molecular distribution. Molecular analysis of intact tissues traditionally requires preexisting knowledge of, and reagents for, the targets of interest. Conversely, label-free discovery of disease-associated tissue analytes requires destructive processing for downstream identification platforms. Tissue-based analyses therefore sacrifice discovery to gain spatial distribution of known targets or sacrifice tissue architecture for discovery of unknown targets. To overcome these obstacles, we developed a multimodality imaging platform for discovery-based molecular histology. We apply this platform to a model of disseminated infection triggered by the pathogen Staphylococcus aureus, leading to the discovery of infection-associated alterations in the distribution and abundance of proteins and elements in tissue in mice. These data provide an unbiased, three-dimensional analysis of how disease affects the molecular architecture of complex tissues, enable culture-free diagnosis of infection through imaging-based detection of bacterial and host analytes, and reveal molecular heterogeneity at the host-pathogen interface.

Fig. 1. Nutrient stress responses in murine tissue abscesses revealed by 3D BLI

(A) BLI of mice (n = 5) infected 4 days before with S. aureus Newman pisdI.Xen1, in which the luxABCDE operon is under control of the iron starvation–responsive isdI promoter. Scale indicates luminescence in photons s⁻¹ cm⁻² sr⁻¹. Luminescent signal in the right eye reflects the site of inoculation. (B) A surface topography of the leftmost mouse in (A) was generated using the IVIS200 3D platform. Note that the tail and limbs fail to generate a topographic image in this analysis. Red pixels correspond to the depth and location of bioluminescent signal. Scale indicates luminescence value in photons s⁻¹. A, anterior; P, posterior; L, left; R, right. (C) Transverse MRI images of the torso (including the kidneys) of the leftmost mouse in (A), co-registered to the 3D BLI data. Four representative images are depicted. Arrows depict abscesses without luminescence. V, ventral; D, dorsal; L, left; R, right. White bar represents 1-mm scale. (D) The rightmost image in (C) tilted in the Z plane to demonstrate luminescence in 3D. (E) The mouse was sectioned transversely, and digital images of each section were obtained. This blockface image volume was co-registered to the 3D BLI data. Four representative images are depicted, corresponding to the four images in (C). Arrows depict abscesses without luminescent signal. White bar represents 1-mm scale. (F) The rightmost image in (E) tilted in the Z plane to demonstrate luminescence in 3D. See also movies S1 to S3.

Fig. 2. Visualization of the bacterial nidus demonstrates equivalent bacteria across tissue abscesses

Serial transverse sections of a mouse intravenously infected with S. aureus Newman pisdI.Xen1 were subjected to downstream imaging, reserved for future analyses, or stained with H&E. (A and B) Two representative H&E sections at 1× (left) and 10× (a + b), 6× (c), or 5× (d) zoom (middle). Black bars represent 1-mm scale. White arrowheads delineate tissue abscesses. Black asterisks indicate intestinal tissue. White asterisks denote paravertebral skeletal muscle. The symbol “#” denotes hepatic parenchyma. Yellow boxes indicate areas chosen for magnification, which are annotated with lowercase letters (a to d). Black arrowheads delineate the bacterial nidus within each abscess. The corresponding blockface images are shown at far right, with bioluminescent signal overlaid. The bioluminescent signal is depicted as a yellow sphere outlined in orange. Yellow boxes on the blockface images correspond to the same abscesses on H&E sections.

Fig. 3. Characterization of inflammation-associated shifts in element distribution by LA-ICP-MS

LA-ICP-MS performed on serial transverse sections of the right kidney from a mouse infected with S. aureus Newman pisdI.Xen1. (A) A representative blockface image illustrating element distribution and abundance surrounding an abscess. LA-ICP-MS data integrated with the blockface volume and co-registered images for BLI, calcium (Ca), copper (Cu), iron (Fe), manganese (Mn), phosphorous (P), magnesium (Mg), and zinc (Zn). The intensity of the color signal indicates relative abundance of the element in arbitrary units. White arrows outline the entire abscess under study. The bioluminescent signal is depicted as a yellow sphere outlined in orange. Insets: Enlarged images showing only the abscess and immediate surrounding tissue. White bar represents 1-mm scale. (B) The blockface volume oriented obliquely for each element throughout the kidney. Heat maps depict minimum and maximum threshold values in arbitrary units. Elements are grouped according to similar patterns. An integrated image displaying all elements co-registered to the blockface volume is shown in the top left panel. (C) The elemental imaging volume for iron (Fe) encompassing the infected right murine kidney is co-registered to the blockface and BLI images. Two different images representing rotation around the Y axis demonstrating iron distribution (in yellow) relative to the BLI signal (in red) for bacterial iron starvation are shown. White and black arrowheads depict corresponding abscesses in (D). (D) 2D planar views of the annotated abscesses in (C) with panels for BLI signal (yellow sphere outlined in orange) and Fe elemental imaging (orange heat map). White and black arrowheads depict corresponding abscesses in (C). See also movies S4 and S5.

Fig. 4. MS imaging delineates bacterial and host proteins at the infectious interface

MALDI IMS performed on serial transverse sections of the region of tissue encompassing the right kidney in a mouse infected with S. aureus 4 days before. A spectral peak at m/z = 10,164, subsequently identified as the S100A8 subunit of the heterodimeric protein calprotectin, colocalized with abscesses when MALDI IMS data were co-registered to blockface imaging (A) or MRI (B). Three representative sections are shown. Insets: Enlarged image showing only the right kidney. White bars represent 1-mm scale. (C) Obliquely oriented serial transverse blockface images with overlaid MALDI IMS data to depict the 3D orientation of S100A8 (m/z = 10,164). Heat map depicts minimum and maximum threshold values in arbitrary units. (D) Blockface images overlaid with MALDI IMS for m/z = 3006 (subsequently identified as δ-hemolysin) and m/z = 6888 (subsequently identified as CsbD-like protein), which are bacterial proteins colocalizing to the nidus within an abscess. Two representative blockface sections are shown. White bar represents 1-mm scale. Insets: Enlarged images showing only the abscess and immediately surrounding tissue. See also movies S6 to S8.

Fig. 5. Molecular histology of tissue microanatomy by MALDI IMS

(A) H&E mid-thoracic transverse section of a mouse infected with S. aureus 4 days before. White arrows delineate tissue abscesses. Black asterisks indicate intestinal tissue. White asterisks denote paravertebral skeletal muscle. The symbol “#” denotes hepatic parenchyma. (B) MALDI IMS performed on an entire transverse mouse section, corresponding to the H&E section in (A), using a Fourier transform ion cyclotron resonance (FTICR) MS. (C) A spectral peak at m/z 3006.646, localized to the bacterial nidi within several abscesses, was subsequently identified as δ-hemolysin. Additional spectral peaks are overlaid to highlight different regions of the transverse mouse section, including (D) m/z 3454.771 in the outer medulla of the kidneys, (E) m/z 4116.946 in the gastrointestinal tract, (F) a spectral peak at m/z 5082.547 that localizes to the abscess regions and was subsequently identified as the doubly charged form of the S100A8 subunit of the heterodimeric protein calprotectin, (G) m/z 5653.720, subsequently identified as histone H4, in the kidneys and liver, and (H) m/z 5921.093 in muscle. All proteins are in the 2+ charge state.

Fig. 6. Integrating MALDI IMS and LA-ICP-MS reveals spatial orientation of the metal-binding host protein calprotectin in relation to nutrient metals in infected mouse tissues

(A to C) Four representative blockface images (left to right) with integration of MALDI IMS signal for the S100A8 subunit of calprotectin (CP) (m/z = 10,164, blue) and LA-ICP-MS signal (orange-yellow) for calcium (Ca; A), manganese (Mn; B), and zinc (Zn; C). Insets: Enlarged images of the kidney and immediate surrounding tissue. (D) The MALDI IMS imaging volume for calprotectin encompassing the infected right kidney was co-registered to the LA-ICP-MS imaging volume for Ca, Mn, or Zn, displayed obliquely to delineate calprotectin and element distribution throughout the kidney. Heat maps depict minimum and maximum values in arbitrary units. See also movie S9.

Fig. 7. Analysis of the bacterial nidus within tissue abscesses by MALDI IMS demonstrates a paucity of calprotectin signal

(A and B) Two representative blockface images co-registered to MALDI IMS data for S100A8 (left), δ-hemolysin (middle), or both signals (right). White bar represents 1-mm scale. (C) Co-registration of MALDI IMS data for both S100A8 (blue) and δ-hemolysin (red) with blockface imaging across the entire infected kidney from one mouse infected with S. aureus 4 days before. Three representative images are shown. See also movie S10.