Genetic Dissection of Neural Circuits: A Decade of Progress

Abstract

Tremendous progress has been made since Neuron published our Primer on genetic dissection of neural circuits 10 years ago. Since then, cell-type-specific anatomical, neurophysiological, and perturbation studies have been carried out in a multitude of invertebrate and vertebrate organisms, linking neurons and circuits to behavioral functions. New methods allow systematic classification of cell types and provide genetic access to diverse neuronal types for studies of connectivity and neural coding during behavior. Here we evaluate key advances over the past decade and discuss future directions.

Figure 1. Binary Expression and Intersectional Strategies

(A–B) Transcription-based binary expression systems. In the driver transgenes, coding sequences for the transcription factor GAL4 (A) and tTA (B) are driven from a cell type-specific promoter (S). In the responder transgenes, the coding sequence of the effector (E) is driven by promoters that contain binding sites of the transcription factors in the driver transgenes, UAS (A) and TRE (B). Note that tTA/TRE system can be further regulated by the drug Dox. (C–D) Recombinase-based binary expression systems. In the driver transgenes, coding sequences for the recombinase Cre (C) and Flp (D) are driven from a cell type-specific promoter (S). In the responder transgenes, the effector is only expressed after Cre or Flp acts on the loxP or FRT sites to invert the intervening sequence (C), or to remove the transcription stop between the ubiquitous promoter (U) and the coding sequence of the effector (D). Note that both strategies can be applied to Flp/FRT- and Cre/loxP- mediated activation. The inversion strategy (C, where the recombinase recognition sites are in opposite direction as indicated by the triangles) utilizes two variants of recombinase recognition sites (here loxP and loxP*) that can only support recombination between the same variant. This strategy is termed FLEx (Schnutgen et al., 2003). (E) Overlapping expression driven from promoter A (orange) and B (blue) creates three patterns, X, Y, and Z, which can be accessed by intersectional strategies in F and G. (F) Intersectional strategies based on two recombinases driven from promoters A and B. In the “A AND B” strategy, the effector is only expressed after Flp- and Cre-mediated recombination both occur, removing the two intervening transcriptional stops. In the “A NOT B” strategy, the action of Flp removes the stop and thus activates the effector, whereas the action of Cre deletes the coding sequence of the effector, thus inactivates it. The “B NOT A” strategy is similar to the “A NOT B” strategy except that the FRT and loxP sites are switched. (G) AND gate can also be achieved by combining a recombinase and a transcription system.

Figure 2. Targeting Neurons based on Patterns of Endogenous Gene Expression

(A) In the classic knockin strategy, the targeting construct (containing the “2A-Cre” insertion right before the stop codon in this example) is introduced into the embryonic stem (ES) cells. Targeted ES cells (usually selected by a drug resistant gene not shown) are injected into blastocysts, which produce chimera mice for screening of germline transmission in a subsequent generation. (B) In CRISPR/Cas9-mediated gene editing, a mixture of 1) guide RNA (gRNA), 2) Cas9 protein, and 3) donor DNA is injected into the pronuclei of fertilized eggs (zygotes). 1) and 2) create double-strand breaks in regions of DNA specified by gRNA sequence, and homology-directed repair utilizes the donor DNA sequence to repair the breaks, creating transgenic animals with desired knockin allele as (A). Cas9 protein can also be replaced by Cas9 mRNA, or by the use of a transgenic animal where Cas9 is expressed in germ cells.

Figure 3. Targeting Neurons based on Projection and Activity

(A) Schematic for targeting neurons based on their projection. In this example, an AAV that expresses a Cre-dependent effector is injected into the region of interest, and a Cre-expressing virus that transduces axon terminals is injected into one of the target fields. Only neurons that project to that target field will express the effector (red). (B) In the Fos-tTA strategy, tTA is driven from the Fos promoter such that it will be expressed in activated neurons (lightening bulb). When Dox is removed from water/food, the effector is expressed in these activated neurons. When the animal is returned to Dox-containing water/food, no new activated neurons will express the effector, but the effectors expressed during the Dox off period persists for a few days. (C) In the Fos-2A-CreER strategy (TRAP2; see Allen et al., 2017), neurons activated during the 4-hydroxytamoxifen (4-OHT) period have the potential to undergo Cre/loxP-mediated recombination, resulting in permanent reporter expression.

Figure 4. Cell Type-specific Axonal Projection and Collateralization Patterns

(A) Ground truth of the axonal projection patterns (right) of neuronal populations at a specific brain region (left). T₁–T₄: target regions 1–4. (B) Injecting AAV expressing Cre-dependent (FLEx^loxP) GFP into Cre transgenic mice can determine the axonal projection patterns of all Cre+ neurons at the AAV injection site. In this and all subsequent panels, unlabeled neurons are in grey, and their axons are omitted. (C) Injecting retrograde transducing canine adenovirus 2 (CAV) expressing Cre-dependent Flp at one of the targets, along with injecting AAV expressing Flp-dependent (FLEx^FRT) GFP at the cell body region of Cre transgenic mice, can determine the complete axon collateralization patterns of Cre+ neurons that project to a specific target region. (D) Replacing Flp-dependent GFP in (C) with Flp-dependent TVA and rabies glycoprotein (G), followed by RVdG at the cell body region enables trans-synaptic tracing of inputs (green) to Cre+ neurons that project to a specific output region, a strategy named cell-type-specific tracing the relationship between input and output (cTRIO).

Figure 5. Cell Type-specific Imaging

(A) Genetically encoded indicator of neural function is targeted to specific cell types (e.g. a local interneuron) for imaging. (B) The indicator is expressed in all neurons for imaging. One cell type (e.g. a subtype of pyramidal neuron) in addition is identified with a fluorescent marker (in this example a red fluorescent protein targeted to the nucleus). (C) The indicator is expressed in all projection neurons, but imaging is performed in the projection zone of one of the projection neuron types. (D) The indicator is expressed in all neurons for imaging. Cell types are identified post hoc using molecular analysis (e.g. multiplexed fluorescent in situ hybridization).

Figure 6. Cell Type-specific Electrophysiology

(A) Phototagging. GABAergic neurons express channelrhodopsin-2 (ChR2). Activating the ChR2-expressing neurons silences surrounding neurons. Right, extracellular recordings in the mouse motor cortex. Parvalbumin-positive, fast-spiking interneurons express ChR2, are thus activated by photostimulation. Photoactivating these neurons (IN) inhibits nearby pyramidal neurons (Pyr). (B) Identifying specific types of projection neurons by antidromic photostimulation. Recordings are performed from pyramidal neurons while photostimulating axons expressing ChR2 in a specific projection zone. Because of recurrent excitatory connections, both neurons with photoexcited axons and downstream neurons in the recorded area can show spikes that are time-locked to the photostimulus with short latencies. Identifying neurons with axons photoexcited in the projection zone requires the collision test, bottom left. Axonal photostimulation (vertical blue line) evokes an action potential with 5 ms latency (arrow head). The antidromic action potential fails to invade the soma if an orthodromic action potential precedes the photostimulus within 5 ms of the photostimulus (bottom four traces); under these conditions the orthodromic and antidromic action potentials collide (Economo et al., 2017). The absence of the antidromic action potential after an orthodromic action potential implies that the recorded neurons projects to the photostimulated brain region. Bottom right, raster plot for the neuron corresponding to the collision test on the left. Rows, behavioral trials; dots, action potentials; vertical lines, different trial epochs. (C) Targeted whole-cell recordings based on high-resolution microscopy. Right, recording from the Drosophila ellipsoid body during orienting behavior (Turner-Evans et al., 2017). Top trace, accumulated orientation. Bottom trace, membrane potential.

Figure 7. Circuit Response to Optogenetic Stimulation of Layer 6 Corticothalamic Neurons

(A) Schematic of the experiment. (B) Cre-dependent expression of red fluorescent protein in Ntsr1-cre mice. Expression is limited to thalamus-projecting layer 6 neurons. (C) Extracellular recordings in the primary visual cortex. Multi-unit responses with (blue) and without (black) layer 6 photostimulation. Left, raster plot, grouped by depth. Black bar: visual stimulus; blue bar: LED illumination. Right, normalized peristimulus time histogram; top: upper layers; bottom: layer 6. Hues of blue correspond to different photostimulus intensities (light, low; dark, high; black, unstimulated).