Characterization of HTT inclusion size, location, and timing in the zQ175 mouse model of Huntington's disease: an in vivo high-content imaging study

Abstract

Huntington's disease (HD) is an autosomal dominant neurodegenerative disorder caused by a CAG trinucleotide repeat expansion in the huntingtin gene. Major pathological hallmarks of HD include inclusions of mutant huntingtin (mHTT) protein, loss of neurons predominantly in the caudate nucleus, and atrophy of multiple brain regions. However, the early sequence of histological events that manifest in region- and cell-specific manner has not been well characterized. Here we use a high-content histological approach to precisely monitor changes in HTT expression and characterize deposition dynamics of mHTT protein inclusion bodies in the recently characterized zQ175 knock-in mouse line. We carried out an automated multi-parameter quantitative analysis of individual cortical and striatal cells in tissue slices from mice aged 2-12 months and confirmed biochemical reports of an age-associated increase in mHTT inclusions in this model. We also found distinct regional and subregional dynamics for inclusion number, size and distribution with subcellular resolution. We used viral-mediated suppression of total HTT in the striatum of zQ175 mice as an example of a therapeutically-relevant but heterogeneously transducing strategy to demonstrate successful application of this platform to quantitatively assess target engagement and outcome on a cellular basis.

Fig 1. Workflow of high content imaging for ex vivo phenotypic characterization.

Mouse brain sections fluorescently stained for up to three target proteins were aligned and mounted in glass-bottom multi-well plates suitable for high content imaging. Using an automated imaging setup (Opera, PerkinElmer) up to 600 high resolution confocal images per brain section were acquired. Automated multi-parametric analysis was applied to every single image to generate comprehensive quantitative data sets for each section describing numbers, subcellular structures, morphology and intensities for stained subpopulation of cells.

Fig 2. Time course of mHTT inclusions appearance in the striatum and cortex of zQ175 mice.

Brain samples from 3–12 months old zQ175 heterozygous mice were stained for mHTT inclusions (bright spots) by EM48-ir and imaged on the Opera high content microscope. A progressive increase in EM48 signal in both striatal and cortical brain regions was clearly visible with age. mHTT inclusions as indicated by EM48-ir puncta appeared earlier and with higher abundance in the striatum as compared to cortex.

Fig 3. Illustration of inclusion quantification in the striatum of zQ175 mice.

Micrographs showing image segmentation strategy for the automated analysis of mHTT inclusion numbers, localization and size in the striatum. (A) Coronal brain sections were co-immunostained for detection of DAPRPP-32 and mHTT and image acquisition of striatal and cortical regions was performed with the Opera (PerkinElmer Inc.). (B) Multi-field images were acquired using 40x objective lens corresponding to the region of interest for subcellular resolution. (C) Area of cell nuclei was determined based on the DAPI signal using a sliding parabola filter for background correction. (D) Medium spiny neurons were identified using nuclear intensity of DARPP-32 staining (green). (E) An extranuclear region was defined with 10 pixels spacing to the nuclear region. Numbers of mHTT nuclear and extranuclear inclusions in medium spiny neurons (MSNs) were quantified based on EM48 signal.

Fig 4. Quantification of nuclear and extranuclear EM48-ir inclusions in the striatum and cortex of zQ175 heterozygous mice.

Brain sections of zQ175 heterozygous mice up to 12 months of age were subjected to immunohistochemical staining for DARPP-32 and EM48, followed by the analysis of inclusion number, size and distribution. (A) In the striatum the number of nuclear mHtt inclusions are significantly increase between 3 and 4 month of age and between 6 to 8 months, reaching a plateau at 12 month. (B) Striatal nuclear inclusions increase steadily in size from 4 to 12 months of age with a significant increase occurring between 6 and 8 months. (D) Nuclear mHtt inclusions in the cortex show a delayed kinetics with a significant increase in number observed among 6, 8, and 12 months of age and (E) a significant increase in size from 8 to 12 months of age. The number of extranuclear inclusions was normalized to the total area of cells measured and reported as density values. The density of extranuclear inclusions significantly increased between 4 and 8 months of age in the striatum (C) and between 6 and 8 months of age in the cortex (F). Data are displayed as dot plots with mean +/- SD. Statistical analysis was performed using standard ANOVA and Sidak’s multiple comparisons’ test. For every age an n of 8 animals with 6 sections per animal were used for quantitation; *p<0.05; **p<0.01; ***p<0.001.

Fig 5. Inclusion appearance in various cortical and striatal regions in zQ175 heterozygous mice.

(A) Using an automated microscope, whole mouse brain sections were scanned by high resolution multi-image acquisition. Individual images were assigned to distinct areas within the cortex including the cingulate cortex (ccx) and motor cortex (mcx), or within the striatum, including dorsal (d)/ventral (v) and medial (m)/lateral (l) parts to allow region-specific automated multiparametric analysis. (B) Region-specific analysis in the striatum of nuclear mHTT inclusions in MSNs. Inclusion number was found to be significantly higher in lateral quadrants (ld and lv) than in medial ventral quadrant at 8 and 12 months old zQ175 mice. (C, D) Subregion specific analysis in the cortex showing quantification of the number of nuclear (C) and extranuclear (D) mHTT inclusions in the cingulate and motor cortex over time. A significantly higher number of inclusions were detected in the ccx compared to mcx region in zQ175 heterozygous mice at 12 months of age. Data are displayed as mean +/-SD. Statistical analysis was performed by two-way ANOVA and Sidak’s multiple comparisons’ test. Mean values were calculated for every age and region using an n of 8 animals with 6 sections per animal; *p<0.05; **p<0.01; ***p<0.001.

Fig 6. Image texture parameter “granularity” for analysis of early mHTT aggregation.

(A) Image analysis strategy for early aggregation parameter “granularity”. The area of cell nuclei was detected based on the DAPI signal. The spatial pattern of pixel intensities of nuclear EM48-ir signal was analyzed and a granularity index indicating formation of small EM48-ir inclusion species was calculated using the SER (Spots) texture algorithm (Acapella, PerkinElmer). Brain sections from 2–12 months old zQ175 heterozygote mice were immunolabelled for DARPP-32 and EM48. The “granularity” index in the striatum and cortex was used to detect and monitor early changes in mHTT distribution and signal clustering. (B) A significant increase in the nuclear EM48 “granularity” in the striatum was observed from 2 to 6 months of age followed by a significant decrease from 6 to 12 months. (C) In the cortex, a significant increase in EM48 granularity was observed from 6 to 12 months. Data are displayed as dot plots with mean +/-SD. Statistical analysis performed using standard ANOVA and Sidak’s multiple comparisons’ test. For every age an n of 8 animals with 6 sections per animal were used for quantitation; *p<0.05; **p<0.01; ***p<0.001.

Fig 7. Illustration of pan HTT analysis in zQ175 and HTT conditional knockdown animals.

(A) Representative images depicting MAB2174-ir in the cortex and striatum of wild type and Htt conditional knockdown mice (htt-RNAi). (B) Illustration showing the image segmentation for quantifying cytoplasmic endogeneous HTT expression in neurons. Nuclear area was selected based on the DAPI signal. NeuN staining was used to identify neurons and to define the cytoplasmic region. Within this region, HTT levels were quantified by determining mean pixel intensity of MAB2174 antibody staining. Due to variability in staining intensity, MAB2174 signals were corrected for mean fluorescent intensities of a reference region around the cytoplasmic region. (C) Quantification of MAB2174 pan HTT staining in the cortex and striatum of wild type and htt-RNAi mice. In both brain regions, MAB2174-ir was below 50% as compared to wild type controls. Data are displayed as bar graphs with mean +/-SD. Mean values were calculated from 1 (striatum) or 2 (cortex) animals with an n of 3 sections per animal.

Fig 8. Modulation of HTT levels, as evidenced by MAB2174 and EM48 immunoreactivity in the striatum of zQ175 heterozygous mice by AAV2 viruses expressing HTT-targeting shRNAs.

AAV2 viruses encoding GFP and shRNAs directed against HTT were injected in the right ventricle of neonate zQ175 heterozygous mice. At 4 months of age, mice were euthanized and analysed for HTT inclusions and HTT cytoplasmic levels. Representative images showing DARPP-32, mHTT IHC staining (A) or DARPP-32, HTT (MAB2174) IHC staining (B) in the GFP positive striatal region transduced with AAV2 encoding shRNA against HTT (mHtt-sh#2 and mHtt-sh#4) or non-target control shRNAs (shC004). Quantitative analysis of mHTT inclusions (C) and MAB2174-ir intensity (D) in GFP positive cells of the striatum: mHtt targeting shRNA led to a significant decrease in the number of nuclear HTT EM48-ir inclusions and MAB2174-ir HTT cytoplasmic levels in comparison to the control AAV/shC004. Data are displayed as bar graphs with mean +/-SD. Statistical analysis was performed using standard ANOVA and Sidak’s multiple comparisons’ test. For every group an n of 4 animals with 3 sections per animal were used for quantitation; p<0.05; **p<0.01; ***p<0.001.