Transgenic mouse models enabling photolabeling of individual neurons in vivo

Abstract

One of the biggest tasks in neuroscience is to explain activity patterns of individual neurons during behavior by their cellular characteristics and their connectivity within the neuronal network. To greatly facilitate linking in vivo experiments with a more detailed molecular or physiological analysis in vitro, we have generated and characterized genetically modified mice expressing photoactivatable GFP (PA-GFP) that allow conditional photolabeling of individual neurons. Repeated photolabeling at the soma reveals basic morphological features due to diffusion of activated PA-GFP into the dendrites. Neurons photolabeled in vivo can be re-identified in acute brain slices and targeted for electrophysiological recordings. We demonstrate the advantages of PA-GFP expressing mice by the correlation of in vivo firing rates of individual neurons with their expression levels of the immediate early gene c-fos. Generally, the mouse models described in this study enable the combination of various analytical approaches to characterize living cells, also beyond the neurosciences.

Figure 1. The nuclear localization signal enriches PA-GFP at the soma.

A: PA-GFP or PA-GFP::NLS were co-expressed with tdTomato in primary cortical neuronal cultures. PA-GFP was photoactivated at the soma (red circle). Images were taken before (−1 min), directly after (+5 min) and 30 min (+30 min) after photolabeling. Representative images in the red and green fluorescence channel for PA-GFP and for PA-GFP::NLS expressing neurons are shown for several time points. Same gamma correction was applied to all monochrome images to visualize also relatively low fluorescence intensities of the dendrites. Pseudocolor images display ratio of intensities in green and red channels. B: The mean fluorescence ratio at the soma of green and red channels before, directly after and 30 min after photolabeling indicates higher labeling efficacy in neurons expressing PA-GFP::NLS. C: Decay of photolabel intensity at the soma quantified as normalized PA-GFP fluorescence at the soma 30 min after photolabeling.

Figure 2. Genetic strategies for the generation of PA-GFP::NLS expressing mice.

A: Schematic of the construct used for the generation of transgenic mice expressing PA-GFP::NLS under the control of the Thy1.2 promoter (left). ‘FW’, ‘RV’ indicates the location of binding sites of forward and reverse primers used for genotyping yielding a 570 bp PCR product. Representative image of a gel electrophoresis of products obtained from a genotyping PCR from a transgenic mouse (Tg) and a wild type (WT) mouse (right). B: Schematic diagram of the PA-GFP::NLS knock in strategy into the Rosa26 locus. After Cre-mediated recombination of loxP sites a stop cassette (lacZ::neo) is excised and leads to expression of PA-GFP::NLS under the control of the ubiquitous active CAGGS (CAG) promoter. ‘FW’, ‘RV1’ and ‘RV2’ indicates the location of binding sites of primers used for genotyping yielding a 585 bp or 680 bp PCR product for the wild type or knock in allele respectively. ‘Probe’ indicates the binding site for probe used for southern blot analysis after HindIII digestion of genomic DNA, resulting in the labeling of a 4.4 kb or 5.8 kb band in the southern blot. Representative southern blot shown for a wild type (WT) and heterozygous (het) mouse (bottom left). Representative image of a gel electrophoresis of products obtained from a genotyping PCR from a heterozygous mouse (het) and a wild type (WT) mouse (bottom right).

Figure 3. Expression patterns of PA-GFP::NLS in the transgenic mouse lines.

A: Coronal brain sections of the Thy1.2#5 (left) and the Thy1.2#6 (right) lines immunohistochemically stained for PA-GFP. Neocortical layers are indicated by dashed lines in the higher-magnification images. B: Examples of sections stained for PA-GFP/NeuN/CamKII (left) and PA-GFP/NeuN/GABA (right). C: Quantification of cell type-specific expression of PA-GFP::NLS in the Thy1.2#5 (left) and the Thy1.2#6 (right) line. Neocortical layers are indicated by dashed lines on representative triple-stained coronal sections. Bar graphs represent fraction of NeuN and CamKII or NeuN and GABA double positive neurons that also express PA-GFP for all 6 cortical layers.

Figure 4. Photolabeling of neurons in vivo.

A: Two-photon images of individual neurons consecutively photolabeled in vivo. Nearby neurons can be labeled with high precision. The time interval between photolabeling of single cells was ∼1 min. The imaging depth was ∼150 µm B: Bulk labeling of neurons in a cross shaped ROI. C: Side view of an image stack showing the same neurons displayed in (B). Note, only neurons in the plane of activation were photolabeled. D: Intensity of the photolabel at the soma at various time points after photolabeling. Points represent individual measurements (n = 4−9 measurements from 30 neurons). Red line indicates double exponential fit to the fluorescence decay. Individual photolabeled neurons can be found for more than one day. E: Re-labeling of previously photolabeled neurons. Lines represent normalized fluorescence intensity at the soma of individual neurons directly after initial photolabeling, after more than 24 hours and directly after second photolabeling.

Figure 5. Photolabeling reveals dendritic morphology.

A: Maximum intensity projection of an image stack taken in vivo of a previously photolabeled neuron (left). Side projection of the stack (middle) and in silico reconstruction of the neuron (right). B: Side projection of another putative pyramidal cell (left) and reconstruction (right). C: Side projection of an image stack taken in vivo of a putative interneuron (left) and reconstruction (right). All scale bars indicate 100 µm (see also Figure S3).

Figure 6. Identification of in vivo photolabeled neurons in the brain slice preparation.

A: Composite fluorescence and DIC image of a brain slice containing a neuron previously photolabeled in vivo targeted with a patch pipette. B: Patch-clamp current-clamp recording of the membrane potential of the neuron shown in A in response to hyper- and depolarizing current injections.

Figure 7. Measurement of illumination fields of optical fibers using in vivo photolabeling.

A: Photographs of the tips of the two optical fibers used in the experiments (left, top and bottom). Confocal images of brain sections counter-stained with SYTO60 (red) with fields of photoconverted PA-GFP (green) at the end of the lesion induced by fiber implantation (dotted white lines) (right, top and bottom). Cross-like horizontal lines indicate location of fluorescence measurements for line plots. B: Line plots of averaged normalized fluorescence along the horizontal and vertical lines shown in (A). Data from 6 mice implanted with the fiber with a flat tip and 5 mice implanted with beveled tip fiber. Error bars represent SEM.

Figure 8. Correlation of single cell in vivo activity levels with Fos expression.

A: Example traces of fluorescence measurements of auditory cortex neurons bulk labeled in vivo with the calcium indicator Rhod2. B: The fluorescence transients during spontaneously occurring population bursts were averaged for each neuron in the population and sorted by their amplitude. Arrows indicate corresponding averages for the traces shown in (A). C: Experimental workflow. 1: Calcium imaging of a neuronal population. The green circles mark simultaneously recorded neurons and the red line depicts the scan line used for fast imaging of activity. Arrows show neurons which were photolabeled following an online analysis of their activity levels. Red arrows indicate neurons re-identified in vitro, white arrows indicate neurons which could not be re-identified. 2: Image taken in vivo of neurons photolabeled after calcium imaging. 3: Same neurons shown in (2) re-identified after preparation of fixed brain slices. 4: Immunohistochemical detection of Fos in the same brain slice shown in (3). D: Examples of the PA-GFP signal and corresponding Fos label in fixed brain slices previously selected in vivo for high spontaneous activity levels. E: Examples of the PA-GFP signal and corresponding Fos label in fixed brain slices previously selected in vivo for low spontaneous activity levels. Numbers in panels D, E indicate the corresponding z-scores of Fos levels. F: Individual and average z-scores of neurons being either in the top or bottom 20% of spontaneously active neurons. Error bars represent SEM.