Cryotomography of budding influenza A virus reveals filaments with diverse morphologies that mostly do not bear a genome at their distal end

Abstract

Influenza viruses exhibit striking variations in particle morphology between strains. Clinical isolates of influenza A virus have been shown to produce long filamentous particles while laboratory-adapted strains are predominantly spherical. However, the role of the filamentous phenotype in the influenza virus infectious cycle remains undetermined. We used cryo-electron tomography to conduct the first three-dimensional study of filamentous virus ultrastructure in particles budding from infected cells. Filaments were often longer than 10 microns and sometimes had bulbous heads at their leading ends, some of which contained tubules we attribute to M1 while none had recognisable ribonucleoprotein (RNP) and hence genome segments. Long filaments that did not have bulbs were infrequently seen to bear an ordered complement of RNPs at their distal ends. Imaging of purified virus also revealed diverse filament morphologies; short rods (bacilliform virions) and longer filaments. Bacilliform virions contained an ordered complement of RNPs while longer filamentous particles were narrower and mostly appeared to lack this feature, but often contained fibrillar material along their entire length. The important ultrastructural differences between these diverse classes of particles raise the possibility of distinct morphogenetic pathways and functions during the infectious process.

Figure 1. Influenza filaments budding from MDCK cells at 24 hours post-infection.

(A) Immunofluorescence shows staining with DAPI (blue), NP (green - B), Actin (red - C) and HA (pink - D). (E) Merged view of channels shown in panels A–D. (F) Close up view of the region indicated by a white rectangle in panel E, revealing budding of filaments of different lengths and morphology and in particular bulbous heads at the distal ends.

Figure 2. Time course immunofluorescence imaging of filament formation in MDCK cells infected with Influenza A/Udorn/72.

DAPI was used to stain cell nuclei (blue) while phalloidin was used to detect actin (red). Monoclonal antibodies were used to detect viral proteins; NP is shown in green and HA is shown in white. Budding virus is seen from as early as 6 hours post infection. From 8 hours we can see long filaments and Archetti bodies at the cell surface.

Figure 3. Close up view of filament formation at 8 hours (A) and 10 hours (B) post-infection showing the presence of bulbous termini at the end of some long filaments (C, D) and (G, H) indicated with a yellow box.

Many filaments were also seen that did not show stronger fluorescence at their termini, indicating that they were probably not Archetti bodies (E, F orange boxes). See also movie S1.

Figure 4. Cryomicroscopy and tomography of influenza A/Udorn/72 infected cells.

(A) Low magnification cryomicrograph of a long filament and Archetti body attached to a cell edge (red line). (B) A slice through a tomogram of the Archetti body shown in (A) reveals that the head was largely devoid of content. (C) Filaments over 10 µm long attached to a cell (red line). See also Movie S2 and figures S4 and S5.

Figure 5. Segmentation of an Archetti body.

(A) Stereo images of a segmented and isosurface rendered terminal varicosity, viewed perpendicular to the vitreous ice layer and (B) at 55° to the viewing direction in (A). Density within the bulb showed single or paired sheets (pink, green, orange, light blue, yellow) in close proximity to the membrane (grey). These features were attributed to M1. The gold fiducial markers (mustard) trace the outside edge and extent of the particle. (C) A slice through the same tomogram illustrating the presence of M1 density closely associated with the particle envelope. (D and E) Transverse sections showing that these features appear bracket shaped (black arrow) and are most likely tubes, supporting the view that these are composed of M1. See also Movie S3.

Figure 6. Cell associated long filamentous structures.

(A) Tomogram showing a large terminal varicosity and two filamentous particles that appear to contain RNPs at their ends (Insets 1 and 3). An extended helical structure is also seen, possibly M1 (Insets 1 and 2). (B, C) Archetti bodies and the majority of filamentous structures were seen not to have ordered arrangements of RNP at their ends. (D) A filamentous virion containing an extended helical structure that may be M1. See also movie S4.

Figure 7. Tomograms of purified A/Udorn/72 virions (A).

Three distinct morphologies were observed: short-rods (B), longer filaments (C) and spherical virions (D). Length and diameter measurements from 96 particles were plotted (E) showing that filamentous particles had a narrower diameter compared to the shorter rod-shaped particles (that we term bacilliform virions). Long filaments that extended beyond the field of view were plotted with a filled square. Spherical virion dimensions (those with an axial ratio <1.2) were plotted with a hollow circle. See also movie S5 and figures S6 and S7.

Figure 8. RNP arrangement and other internal components in the various classes of virions.

(A) Transverse sections through bacilliform particles revealed the characteristic arrangement of RNPs. (B) Longitudinal section of the particle in (A) showed three RNPs lying side-by-side. (C) Such views were commonly observed with particles oriented parallel to the ice layer and transverse sections through these particles (D) showed the 7+1 arrangement of RNPs. (E, F) Longer bacilliform particles had RNPs at one end while longer filaments (G) were sometimes sparsely packed but more frequently contained fibrillar material along their entire length (longitudinal and transverse sections are shown H–K). In some cases the internal density appeared as straight rods (H, I) while in others it appeared to be wound around itself (J, K). Tomogram sections perpendicular to the ice layer were harder to interpret owing to the missing wedge; an imaging artefact associated with tomographic data acquisition (B, D, I and K). (I and K) Sections through the narrow filaments do not show the RNP morphology seen in comparable views of bacilliform particles (A and D). This feature was infrequently seen at the termini of cell-associated filaments and in our data seen only once in tomograms of purified filaments (L). See also movie S5.