AutoEPG: software for the analysis of electrical activity in the microcircuit underpinning feeding behaviour of Caenorhabditis elegans

Abstract

Background: The pharyngeal microcircuit of the nematode Caenorhabditis elegans serves as a model for analysing neural network activity and is amenable to electrophysiological recording techniques. One such technique is the electropharyngeogram (EPG) which has provided insight into the genetic basis of feeding behaviour, neurotransmission and muscle excitability. However, the detailed manual analysis of the digital recordings necessary to identify subtle differences in activity that reflect modulatory changes within the underlying network is time consuming and low throughput. To address this we have developed an automated system for the high-throughput and discrete analysis of EPG recordings (AutoEPG).

Methodology/principal findings: AutoEPG employs a tailor made signal processing algorithm that automatically detects different features of the EPG signal including those that report on the relaxation and contraction of the muscle and neuronal activity. Manual verification of the detection algorithm has demonstrated AutoEPG is capable of very high levels of accuracy. We have further validated the software by analysing existing mutant strains with known pharyngeal phenotypes detectable by the EPG. In doing so, we have more precisely defined an evolutionarily conserved role for the calcium-dependent potassium channel, SLO-1, in modulating the rhythmic activity of neural networks.

Conclusions/significance: AutoEPG enables the consistent analysis of EPG recordings, significantly increases analysis throughput and allows the robust identification of subtle changes in the electrical activity of the pharyngeal nervous system. It is anticipated that AutoEPG will further add to the experimental tractability of the C. elegans pharynx as a model neural circuit.

Figure 1. A typical EPG pump with annotated spikes.

‘e’ is the small excitatory spike (previously designated E1 [9]), caused by MC activation , ; ‘E’ is the large excitatory spike (previously designated E2 [9]), corresponding to rapid muscle contraction ; ‘P’ are the small negative spikes, caused by M3 activation ; ‘R’ is the large negative spike (previously designated R1 [9]), corresponding to rapid relaxation of the corpus muscle and ‘r’ is the small negative spike (previously designated R2 [9]), corresponding to relaxation of the terminal bulb .

Figure 2. Overview of the AutoEPG system.

A) A labeled screenshot of the AutoEPG graphical user interface. An example of an EPG recorded from a wild-type N2 worm is shown to demonstrate the capabilities of the interface. Briefly, after 6.2 min of recording in Dent's saline 100nM 5-HT, a potent stimulator of pharyngeal pumping, was applied. The entire recording is displayed in the navigation window and the time point at which 5-HT was applied is indicated by the black arrow (this was added retrospectively). The region of the trace consisting of 1 min immediately prior to 5-HT application and 2 min after application is easily selected in the navigation window (highlighted in green by AutoEPG). This selected region is displayed in the annotation window, where the algorithm annotation of the recording can be viewed. The highlighted region selected can be altered by simply clicking and dragging the left and right edges of the green box in the navigation window, or by clicking on the highlighting box and dragging it left or right with the mouse. Figure 2A Insert. An EPG waveform as it would appear having been annotated by the AutoEPG algorithm B) A cartoon illustrating the editing functions available in AutoEPG. C) Screenshots of the statistics that can be performed using AutoEPG. The pump rate, R-E interval, pump duration, P-peaks/pump and R/E-ratio/pump are displayed for the region of the recording selected in the navigation window in Figure 2A. The default of the statistics functions is to display data for the entire recording. However, when a region is selected in the navigation window the statistics function updates itself to display the statistics for the region of interest. In each case the black arrow indicates the time point at which 100nM 5-HT was applied (this has been added retrospectively). The groups of pumps statistic was performed on the first 2 minutes of the 5-HT application. The user-modifiable preferences of the statistics pump-rate and groups of pumps are outlined in red. In the case of pump duration, P-peaks and R/E-ratios each bar in the graphical output represents a single pump, with time on the x-axis. In the case of pump rate the user-modifiable preference ‘Window size (sec)’ refers to the time base used to plot the instantaneous rate, i.e if the size of window is set to 10 seconds as in this example, the pumps/sec will be calculated for each consecutive 10 sec ‘window’ of the trace. In the case of groups of pumps in this example the time interval has been set to 200 msec (i.e. consecutive pumps that occur within 200 msec of each other will be classified by AutoEPG as belonging to the same group). The analysis can be performed on the ‘Current View’ which is the region selected in the navigation window or on the entire trace by selecting ‘All.’

Figure 3. An R spike indicating how the amplitude measurement was made.

Figure 4. A pump filtered using two filters with different cut-off frequencies.

A. The raw signal (unfiltered). B. The signal after being filtered with the 200 Hz cut-off filter. C. The signal after being filtered with the 100 Hz cut-off filter.

Figure 5. Two EPG pumps recording from wild-type, N2, showing the different temporal positioning of the ‘r’ spike within the EPG waveform.

A. In this example the temporal distance between the R and r spike is small, thus the r spike is not distinct but instead appears as a small deflection upon the rising slope of the R-spike. B. In this example the temporal distance between R and r spikes is greater and so the r spike appears completely detached from the R spike.

Figure 6. slo-1(js379) animals have an altered pattern of pharyngeal activity.

A. Representative EPG recordings made from an N2 (wild-type) and slo-1(js379) worm perfused with saline at a rate of 4 ml/min within 2–3 min of the dissection. B. The time-base of the EPG recordings shown in A have been expanded so that individual pumps can be discerned, further highlighting the ‘bursting’ pattern of activity of slo-1(js379) animals. C. Inter-pump interval distribution of pumping activity in N2 and slo-1(js379) animals from 5 min of recording each. The intervals were divided into four groups and then further subdivided into smaller bins as follows: Up-to 1 second (100 msec); from 1–20 seconds (1 second); from 20–50 seconds (10 seconds) and >50 seconds. Note the high number of short intervals (0–300 msec) in slo-1(js379) compared to N2.

Figure 7. The rescue of slo-1(js379) pharyngeal phenotypes using either pharyngeal muscle or pan-neuronal specific rescue constructs.

EPG recordings were made in Dent's saline from wild-type N2, slo-1(js379) and slo-1(js379) animals expressing slo-1a either in the pharyngeal muscle or in the pharyngeal nervous system. In this comparison the first minute of the recordings made from each strain were analysed using AutoEPG. The following features were measured: A. Pump groups; B. Average pump duration; C. Average R/E ratio and D. Average number of P-peaks/pump. The number of individuals' tested for each strain, together with the number of individual pumps (P) was as follows: N2, N = 16, P = 358; slo-1(js379), N = 21, P = 556; slo-1(js379)Ex[Psnb-1::slo-1a], N = 5, P = 90 and slo-1(js379)Ex[Pmyo-2::slo-1a], N = 7, P = 232. (Two tailed, unpaired t-tests were used to compare transgenic lines to N2, wild-type; Asterisks: *p<0.05 **p<0.01, ***p<0.001; graphs show the mean±SEM).