A Pipeline for Volume Electron Microscopy of the Caenorhabditis elegans Nervous System

Abstract

The "connectome," a comprehensive wiring diagram of synaptic connectivity, is achieved through volume electron microscopy (vEM) analysis of an entire nervous system and all associated non-neuronal tissues. White et al. (1986) pioneered the fully manual reconstruction of a connectome using Caenorhabditis elegans. Recent advances in vEM allow mapping new C. elegans connectomes with increased throughput, and reduced subjectivity. Current vEM studies aim to not only fill the remaining gaps in the original connectome, but also address fundamental questions including how the connectome changes during development, the nature of individuality, sexual dimorphism, and how genetic and environmental factors regulate connectivity. Here we describe our current vEM pipeline and projected improvements for the study of the C. elegans nervous system and beyond.

Keywords: C. elegans; connectome; high-pressure freezing; nervous system; volume electron microscopy.

FIGURE 1

A pipeline for C. elegans connectome reconstruction using vEM. Samples are fixed using high-pressure freezing and freeze substitution, embedded in plastic then cut into ultrathin serial sections before imaging on an electron microscope. Images are stitched together into a 3D volume, and neurons are identified and traced throughout the dataset by skeleton tracing using CATMAID. Synapses are annotated by three independent annotators to obtain the connectome. Volumetric reconstruction, which yields topographical information of cells and neurons, is facilitated by computational filling followed by manual proofreading using VAST.

FIGURE 2

High-pressure freezing improves preservation of ultrastructure. (A) The dorsal cord of an adult prepared using the slow chemical fixation protocol (White et al., 1978). The DD motor neuron is making a neuromuscular junction to dorsal muscle cells. (B) The dorsal cord of an adult fixed using high-pressure freezing and imaged using TEM. The DD motor neuron is making a neuromuscular junction to dorsal muscle cells. (C) The ventral nerve cord of a chemically fixed first stage (L1) C. elegans larva (White et al., 1978). The DD axon makes a NMJ to the ventral muscle cell (M). (D) A TEM micrograph of the ventral nerve cord of a high-pressure frozen first stage larva (L1) at similar region, where DD makes a NMJ to the ventral muscle cell. The advent of high-pressure freezing allows better preserved neurite morphology, synapse structure, and extracellular space, facilitating connectomic and topological analyses of the C. elegans nervous system. Scale bar 1 μm. Panel (A) was reprinted with permission from White et al. (1978). Panel (C) a scan of the micrograph used in White et al. (1978), hosted by the WormImage Consortium (www.wormimage.org).

FIGURE 3

High-pressure freezing of C. elegans. (A) To pack the carrier with worms, our preferred method is to swipe it across a densely packed lawn of worms and bacteria. After swiping, the worm-bacteria mixture is spread across the cavity of the carrier with tweezers or a worm pick (a thin platinum wire mounted to a holder), the lid put in place, and the sample immediately high-pressure frozen. The entire process takes less than 30 s. (B) A carrier when it is packed. It is filled just right, without air bubbles. The smallest cavity for freezing is used, as freezing efficiency decreases with increasing depth. (C) A carrier packed with a mixed-staged larva after high-pressure freezing, freeze substitution, and resin infiltration. This carrier has retained the “cake” of worms, but much of the time the cake floats out. One can see how densely the worms are packed by the swiping method. (D) Worms are separated from the cake and individually embedded and cured in plastic blocks. Well-packed carriers as shown in panel (C) can yield hundreds of intact worm samples.

BOX 1

Some freeze substitution protocols for C. elegans volume EM. Both (A) and (B) are effective protocols for ultrastructural preservation (Weimer, 2006).

BOX 2

A collection of sectioning strategies for vEM. vEM using non-block face imaging (TEM and SEM) requires collecting large unbroken series of serial sections. There are multiple ways of making the process less error-prone, each with its own merit. One simply has to choose which process works best for them, or devise their own strategy. ¹Gay and Anderson (1954);²Westfall and Healy (1962); ³Fahrenbach Wolf (1984);⁴Galey and Nilsson (1966); ⁵Mironov et al. (2008);⁶Anderson and Brenner (1971);⁷Rowley and Moran (1975); ⁸Abad (1988); ⁹Wells (1974); ¹⁰Mironov et al. (2008); ¹¹Stevens et al. (1980); ¹²Hall (1995); ¹³Schalek et al. (2012);¹⁴Micheva and Smith (2007); ¹⁵Burel et al. (2018); ¹⁶Leica Microsystems, Germany.

FIGURE 4

Cutting serial sections for TEM. (A) A block face trimmed for cutting. The worm is oriented transversely in the center of the block face (white arrow). (B) Ribbons of 10–20 sections are picked up on formvar-coated slot grids. (C) A low magnification TEM image of a slot grid, 0.5 mm in diameter. The ribbon of section spans the slot, contributing to the formvar stability. (D) Many grids of serial sections, stored in a grid box, are ready for imaging.

FIGURE 5

Skeleton and volumetric reconstruction of the C. elegans nervous system. (A) A complete reconstruction of all nuclei (round balls) and all neuronal processes (blue cables) of a first larval stage C. elegans, achieved through skeleton tracing in CATMAID, and visualized with Blender. (B) A skeleton reconstruction of anterior DD-type motor neurons and the neuromodulatory neuron RID generated using CATMAID. Synaptic input and output are indicated by cyan and red spheres, respectively, and putative gap junctions in marked in dark purple. (C) Volumetric segmentation of part of a DD motor neuron and RID using TrakEM2, with intracellular ultrastructure segmented. (D) A cross-section of an L1 larva. Its nerve ring was fully reconstructed by volumetric segmentation. These segmentation profiles were generated by expanding skeleton seeds to a membrane probability map, followed by manual proofreading in VAST.

FIGURE 6

Chemical synapses and gap junctions in C. elegans. (A) A section of the first larva (L1) ventral ganglion neuropil imaged using SEM at 1 nm/pixel. Multiple chemical synapses are visible (white arrows) as well as a gap junction (white flat-ended line). (B) Enlarged view of the chemical synapse highlighted with a dashed box in panel (A). There is a presynaptic dense projection and a pool of synaptic vesicles, as well as some dense core vesicles further back in the neurite. This synapse is polyadic, releasing onto three neurons. (C) Enlarged view of the gap junction highlighted with a dashed box in panel (A). There is a relatively flat area of close apposition between the membranes.

FIGURE 7

Examples of synapse annotation with different degrees of subjectivity. (A) Serial sections through a large, confidently annotated polyadic synapse (from IL1VL to RIPL, RMDDL and body wall muscle BWM-VL01). This synapse spans these three sections, and beyond (not shown). (B) Serial sections through a very small synapse (from RIS to RIBL and RMDR). The annotation of this synapse is less confident that the one presented in panel (A). (C) Serial sections of a membrane swelling that is confidently annotated as not-a-synapse. A small density in the membrane of RIBL with sparse vesicles is not a presynaptic specialization. (D) Serial sections through a synapse showing the occasional subjectivity involved in defining postsynaptic partners. While all annotators agreed RMGL was a postsynaptic partner of RIGL, whether SAADL should be included as a postsynaptic partner was cause for debate. White arrowheads indicate the membrane of interest. Scale bars are 500 μm.

FIGURE 8

Neurons can be identified from 3D volumes. Electron micrographs showing snapshots of part of the ventral nerve cord from an animal at the end of the second larval stage, imaged using SEM at 2 nm/pixel. (A) A VD2 NMJ is pointing laterally toward a muscle arm. This example also “hits” a projection from the VA2 motor neuron, but it is not clear if receptors are present. Some other motor neurons are also labeled, to give a sense of the relative position within the nerve cord. (B) A VA2 NMJ is pointing more dorsally, releasing onto a muscle arm, a DD1 spine and VD2. (C) A VB2 NMJ is also pointed dorsally, releasing onto muscle, a DD1 spine and VD2. (D) A cartoon of most of the commissure bundles in C. elegans, available on WormAtlas (Altun et al., 2002–2018) and based on The Mind of a Worm (White et al., 1986). The positions, handedness and commissure bundle partners are known, and very stereotypic. Bundles of neuron processes are shown as red cables. The cell bodies are denoted with spheres, and also have stereotypic positions along the body of the worm and relative to each other.