Dendritic targeting in the leg neuropil of Drosophila: the role of midline signalling molecules in generating a myotopic map

Abstract

Neural maps are emergent, highly ordered structures that are essential for organizing and presenting synaptic information. Within the embryonic nervous system of Drosophila motoneuron dendrites are organized topographically as a myotopic map that reflects their pattern of innervation in the muscle field. Here we reveal that this fundamental organizational principle exists in adult Drosophila, where the dendrites of leg motoneurons also generate a myotopic map. A single postembryonic neuroblast sequentially generates different leg motoneuron subtypes, starting with those innervating proximal targets and medial neuropil regions and producing progeny that innervate distal muscle targets and lateral neuropil later in the lineage. Thus the cellular distinctions in peripheral targets and central dendritic domains, which make up the myotopic map, are linked to the birth-order of these motoneurons. Our developmental analysis of dendrite growth reveals that this myotopic map is generated by targeting. We demonstrate that the medio-lateral positioning of motoneuron dendrites in the leg neuropil is controlled by the midline signalling systems Slit-Robo and Netrin-Fra. These results reveal that dendritic targeting plays a major role in the formation of myotopic maps and suggests that the coordinate spatial control of both pre- and postsynaptic elements by global neuropilar signals may be an important mechanism for establishing the specificity of synaptic connections.

Figure 1. Birth-order dependent projections of lineage 15 in adult Drosophila.

(A) Axonal projections of neuroblast clone of lineage 15 motoneurons revealing the three areas innervated in the prothoracic leg. (B) Motoneuron born following heatshock at 48 h AH innervates the pre-tarsal flexor muscle group located in the proximal femur (red arrow). (C) Motoneuron born following heatshock at 96 h AH innervates muscle groups located in the distal tibia (yellow arrow). (D) Cartoon showing segments of prothoracic leg including coxa (c), trochanter (t), femur (f), tibia (ti), and tarsi (ta) and the position of muscle groups innervated by motoneurons born at 48 (red) and 96 h AH (yellow). (E) The central projections of a neuroblast clone of lineage 15. Cell bodies located in a superficial cellular cortex surrounding a dense fibrous neuropil. The primary neurites of lineage 15 enter the anterior cortex and arborize extensively throughout the neuropil. In the anterior leg neuropil dendrites cover lateral territories extending a few processes towards medial territories (arrowhead); in the posterior neuropil, large dendritic branches extend towards and cross the midline and project into the contralateral leg neuropil. The midline (ML) and the lateral edge (LE) were determined by neuroglian staining. Scale bar = 20 µm. (F) Motoneurons born at 48 h AH elaborate their dendrites in medial (M), intermediate (I), and lateral (L) territories. A major posterior branch projects crosses the midline into the contralateral leg neuropil. (G) The dendrites of motoneurons born at 96 h AH are restricted to the intermediate and lateral territories of the leg neuropil. (H) Cartoon showing the organization of the central projections of two leg motoneurons in the prothoracic neuromere. The dendritic fields of 48 h (red) and 96 h AH (yellow) motoneurons within leg neuropil (light gray) surrounded by a cellular cortex (circles). A refers to anterior. Arrow shows the position of paired bundles of lineage 2. (I) Anti-neuroglian staining reveals bundles of adult specific lineages (arrow) and fibrous neuropil in the prothoracic neuromere. The lines indicate the midline and the lateral edge of the leg neuropil in the right hemineuromere. (J) Plot profile histogram reveals the distribution of the dendritic arborizations of eight 48 h AH single motoneurons (red) and eight 96 h AH cells (yellow) within the leg neuropil. The mean centre of arbor mass for eight neurons is denoted by a coloured circle for each subtype and the standard error of each experimental condition and statistical significance between groups *** p<0.001. Arrowheads represent the 33^rd percentile for each subtype. SGV, scaled grey value. Scale bar in G applies to F. Scale bars = 20 µm. (K) Cartoon of thoracicoabdominal complex. Blue box indicates right prothoracic hemineuromere.

Figure 2. Central projections of leg motoneurons acquire their subtype-specific morphology by targeted dendritic growth.

Single z-projections of leg motoneurons born following heatshocks at 48 h AH (A–E) and 96 h AH (F–J) (n = 4 for each). (A, F) At 20 h APF filopodia can be seen on the primary neurites of both neurons. (B, G) At 30 h APF the 48 h AH neuron generates filopodia and small branches that extend into the intermediate territory; a similar quantity of branches can be seen on the 96 h AH neuron in two growth zones at the lateral edge of the neuropil. (C, H) By 40 h APF the dendrites of both neurons have increased in size and higher order branches are beginning to be established. The 48 h AH neuron elaborates a branch on the anterior part of the primary neurite and also at two sites where the posterior branches will form. The 96 h AH cell has branches projecting to the anterior and posterior at the lateral edge of the neuropil. (D, I) By 60 h APF both neurons have increased their number of higher order branches. The major posterior branch in the 48 h AH neuron has reached the midline but not crossed it. The 96 h AH cell covers a large part of the lateral neuropil; many branches orient towards the midline but these never extend into medial territories. (E, J) At 80 h APF the morphology of both neurons are indistinguishable from those seen in the adult. Anterior is up. The relative positions of the midline (ML) and lateral edge (LE) of neuropil were determined by neuroglian staining. Scale bar = 20 µm.

Figure 3. Localization of midline signalling molecules in the thoracic nervous system during the pupal-adult transition.

(A) Detergent based antibody staining against Slit shows expression in midline cells at 48 h APF. (B) Detergent-free immunocytochemistry reveals robust extracellular Slit staining at the midline and within the developing neuropil at 48 h APF in the ventral nerve cord. (C) Conditionally removing Slit using RNAi. Following a knockdown of Slit, using Slit-GAL4 to drive UAS-Slit RNAi, we observed a lack of Slit staining in the developing neuropil using detergent-free immunocytochemistry. (D) Immunocytochemistry reveals Robo expression throughout all thoracic neuropils at 48 h APF. Note absence of staining at the midline. (E) Anti-myc staining reveals the localization of NetrinB in midline glia at 48 h APF, in a NetrinB-myc allele. (F) Ectopic expression of Robo::myc fusion protein in single-cell clone reveals that Robo can be localized in dendrites of leg motoneurons. (G) Ectopic expression of Fra::myc fusion protein in a single-cell motoneuron clone. Anterior is up. Scale bar applies to F and G = 20 µm.

Figure 4. Slit-Robo signalling mediates dendritic targeting of motoneurons within the medio-lateral axis of the leg neuropil.

(A) Motoneurons born following heatshocks at 48 h AH elaborate dendrites across all three neuropil territories and send a large posterior branch toward the midline. (B) Robo null clone generated at 48 h AH generates ectopic dendritic projections near the midline at the posterior region of the neuropil (arrowhead). (C) Robo gain of function clones generated at 48 h AH lack the midline crossing event in the posterior region of the neuropil. (D) Misexpression of Comm in motoneurons generated at 48 h AH clones results in inappropriate growth of dendrites towards medial regions of the neuropil. (E) Motoneurons born following a heatshock at 96 h AH elaborate dendrites in intermediate and lateral territories within the leg neuropil. (F) Robo null clones generated at 96 h AH show medial shifts in the distribution of their dendrites. (G) Misexpression of Robo in 96 h AH clones results in dendrites being shifted away from the midline into very lateral neuropil territories. (H) Misexpression of Comm in the 96 h AH clones results in dendrites that span the medio-lateral axis of the neuropil. (I–P) Plot profile graphs to reveal the distribution of dendrites along the medio-lateral axis within the leg neuropil (n = 8 for each genotype). The mean centre of arbor mass (circle) for the dendritic arbors and the standard error of each experimental condition and the statistical significance between groups are also shown. Triangles denote the 33^rd percentile for each group. Scale bar = 20 µm. * p<0.05, ** p<0.01, and *** p<0.001.

Figure 5. Netrin-Fra signalling mediates dendritic targeting of motoneurons within the medio-lateral axis of leg neuropil.

(A) Motoneurons born following heatshocks at 48 h AH elaborate dendrites across all three neuropil territories and send a large posterior branch toward the midline. (B) In Fra null single-cell clones generated at 48 h AH the posterior dendritic branch fails to cross the midline and show an increase in the amount of arborization in the lateral regions of the neuropil. (C) Misexpression of Fra in single 48 h AH results in a redistribution of dendrites to both lateral and medial territories. (D) Motoneurons born at 96 h AH elaborate dendrites that target lateral territories within the leg neuropil. (E) In Fra null single-cell clones generated at 96 h AH the dendrites show no obvious change in dendrite position along the medio-lateral axis. (F) Misexpression of Fra in 96 h AH clones results in dendrites shifting towards medial territories. (G–J) Plot profile graphs to reveal the dendrite distribution along the medio-lateral axis within the leg neuropil (n = 8 for each genotype). The mean centre of mass (circle) for the dendritic arborizations for each genotype along the medio-lateral axis is shown on the line underneath the histogram. The standard error of each experimental condition and the statistical significance between groups is also shown. Triangles denote the 33^rd percentile for each group. Scale bar = 20 µm.

Figure 6. Slit and Netrin are required for motoneuron dendritic targeting.

(A) VGN9281-GAL4 expressing CD8::GFP. The motoneuron labelled by VGN9281-GAL4 targets dendrites to lateral territories of the leg neuropil. (B) VGN9281-GAL4 expressing CD8::GFP and Slit-RNAi. Expressing Slit-RNAi in the motoneuron has no effect on medio-lateral distribution of its dendrites. (C) Slit-GAL4 and VGN9281-GAL4 expressing CD8::GFP and Slit-RNAi. Reducing Slit protein in the midline cells results in dendrites of the VGN9281-GAL4 motoneuron being shifted into intermediate and medial territories. (D) Expressing CD8::GFP and NetrinB under the control of Slit-GAL4 and VGN9281-GAL4 does not change the medio-lateral position of the dendrites of the motoneuron. (E) VGN9281-GAL4 expressing CD8::GFP in NetABΔ background. The dendrites of the VGN9281-GAL4 motoneuron do not change position in a NetABΔ background. (F) E49-GAL4 expressing CD8::GFP reveals the bulk of the motoneurons of the prothoracic neuromere. The dendrites of the motoneurons that innervate the pretarsal flexor muscles approach and cross the midline. Boxed area detail shown in F'. (G) E49-GAL4 expressing CD8::GFP in a NetABΔ background reveals the dendrites of the pretarsal flexor muscle motoneurons fail to approach and cross the midline. Asterisk denotes anterior part of neuropil where dendrites fail to approach the midline. Boxed area detail shown in G'. (F') Detail from F. (G') Detail from G. Scale bars = 20 µm. Scale bar in E applies for A–E. Scale bar in G applies to F. Scale bar in G' applies to F'.

Figure 7. The positioning of leg motoneuron dendrites occurs independently of changes in dendritic mass.

(A) Detail of the proximal dendrites of the sensory neuron ddaC. WT, wild-type. (B) Detail of the proximal dendrites of the sensory neuron ddaC expressing Dp110 reveals an increase in branch complexity. (C) Analysis of cell body size in wild-type (blue) and DP110 expressing (red) ddaC neurons. (D) Sholl analysis of wild-type (blue) and DP110 expressing (red) ddaC neurons. (E) Motoneurons born at 96 h AH generate dendrites that target lateral neuropil territories. (F) Robo null (RoboLOF) clones generated at 96 h AH show medial shifts in the distribution of their dendritic fields. (G) Ecotopic expression of UAS-DP110 in 96 h AH clones results in dendritic arborizations that elaborate mainly in lateral territories of the neuropil with a few ectopic medial branches present in anterior and posterior neuropil. (H) Analysis of cell body size in wild-type (WT), RoboLOF, and UAS-DP110 96 h AH clones. (I–J) Plot profile graphs to reveal the distribution of dendrites along the medio-lateral axis within the leg neuropil (n = 8 for each genotype). The mean centre of mass (circle) for the dendrites of each genotype. The standard error of each experimental condition and the statistical significance between groups can also be seen. Triangles denote the 33^rd percentile for each group. (K) Dorsoventral projection of a wild-type dendritic arborization of a motoneuron born at 96 h AH. (L) Dorsoventral projection of a Robo LOF 96 h AH motoneuron. (M) Dorsoventral projection of a CommGOF 96 h AH motoneuron. (N) Dorsoventral projection of a DP110 GOF 96 h AH motoneuron. (K–N) Dorsal is up. Anterior to right. Scale bars = 20 µm.