A Computational Model of Oxytocin Modulation of Olfactory Recognition Memory

Abstract

Social recognition in mammals depends on complex interactions between sensory and other brain areas as well as modulatory inputs by specific neuropeptides such as oxytocin (OXT). Social recognition memory specifically has been shown to depend among others on olfactory processing, and can be probed using methods similar to those used when probing non-social odor memory. We here use a computational model of two interconnected olfactory networks in the mouse, the olfactory bulb (OB) and anterior olfactory nucleus, to propose a mechanism for olfactory short-term recognition memory and its modulation in social situations. Based on previous experiments, we propose one early locus for memory to be the OB. During social encounters in mice, pyramidal cells in the anterior olfactory nucleus, themselves driven by olfactory input, are rendered more excitable by OXT release, resulting in stronger feedback to OB local interneurons. This additional input to the OB creates stronger dynamics and improves signal-to-noise ratio of odor responses in the OB proper. As a consequence, mouse social olfactory memories are more strongly encoded and their duration is modulated.

Keywords: anterior olfactory nucleus; computation; olfaction; oxytocin; plasticity; social odors.

Figure 1.

Model architecture. Simulated sensory neurons with broad responses to a chosen odorant make excitatory synapses onto PGs (inhibitory), ETs (excitatory), and MCs (output neurons) within a given glomerulus, conveying a common type of odor information to these neurons. MCs excite a large number of inhibitory GCs (via modifiable synapses) which in return convey inhibition only locally in one glomerular column. MCs project to 20% of AON Pyr cells, which excite each other through a dense network of association fibers (20% connectivity) and project back to OB interneurons in the glomerular (ETC; 10% connectivity) and GC layers (20% connectivity). OXT inputs modulate AON Pyr cell intrinsic properties.

Figure 2.

OXT modulation of AON Pyr cells. A, AON Pyr cell responses to a 1 s current injection in the model under control (top) and OXT (bottom) conditions. (cf. Oettl et al., 2016, their Fig. S2). B, Firing rates of AON Pyr cells as a function of activation in the model (cf. Oettl et al., 2016, their Fig. 4B). C, Example AON cell activity under control (C_i) and OXT (C_ii) conditions in response to simulated odor inputs. Lower trace shows OSN potential fluctuations.

Figure 3.

Modulation of OB odor responses by AON. A, MC firing rate during a single respiration cycle in response to odor stimulation under control and OXT (cf. Oettl et al., 2016, their Fig. 7B). B, MC firing rates normalized with respect to control (no OXT) conditions during spontaneous activity and odor-evoked activity (cf. Oettl et al., 2016, their Fig. 7). C, Example MC traces during respiration-modulated odor responses under control (No OXT; C_i) and OXT in the AON (C_ii) conditions. Note the decrease of spontaneous activity and increase in odor responsiveness. D, OB S/N modulation by AON OXT modulation. D_i, The average (+/− standard error) S/N for control and OXT simulations. D_ii, The average (+/− standard error) S/N for OXT and control simulations as a function of stimulus concentration (ratio of maximum odor concentration in the model). E, The graph shows the detection index (average +/− standard error) for odorants varying between 0.05 and 0.2 of the maximal stimulus concentration in the model. F, The graph shows the discrimination index (average +/− standard error) between two simulated odorants as a function of stimulus concentration.

Figure 4.

Odor object recognition in mice and in the computational model. A_i, Schematic representation of behavioral testing in mice. Mice are tested on a 60 ×60 cm platform on which odor stimuli are presented in Eppendorf tubes positioned in custom-made holders. Mice are left to investigate the odor for a period of 2 min. After a variable delay (5, 10, 15, 20, 25, or 30 min) mice are reintroduced on the platform with the familiar and a novel odor and investigation time in response to both is recorded. A_ii, Memory index (fraction of spend time investigating the novel odor) is shown as a function of the delay (average +/− standard error). Mice investigate the novel odor significantly more than the familiar odor after 5 and 10 min delays as indicated by asterisk. The graph shows average memory index ± SE. B_i, Example receptor neuron traces in response to short bouts of “investigation” in the model. B_ii, MC responses during the encoding trial when MC to GC synapses increase in an activity-dependent manner. Note that MC responses to the investigation bouts decrease over time. C, The evolution of average MC odor responses in the model during encoding (3–15 s) and during the delay (5–30 min) when no odors are presented.

Figure 5.

OXT modulation of AON increases plasticity and memory duration in the OB. A, Modulation of AON by OXT increases habituation in the OB. The graph shows average MC responses to odor stimulation in response to the habituated odor or a novel odor with (OXT) or without (NO OXT) modulation in the AON during encoding. During recovery (dis-habituation) MCs modulated in the presence of OXT recover to a lesser degree (note there is NO OXT during recovery). B, The graph shows changes in synaptic weights during habituation and dis-habituation phases with OXT during habituation (OXT) or control conditions (No OXT). C, The resulting memory index (responses to novel odor/sum of responses) shows that when OXT is simulated in the AON, model MCs respond significantly more to a novel than to the habituated odor for longer delays (up to 25 min) when OXT was present during the encoding phase. D, Summarizing scheme of the impaired loss of recognition memory without OXT receptor recruitment in the AON (left) and comparison of memory index in control (OXTR^wt) mice and mice with OXT receptors deleted in the AON (OXTR^DAON; from Oettl et al., 2016). Mice with OXTRs intact remembered the conspecific after a delay of 30 min, whereas mice with deleted OXTRs did not (similar to mice encoding non-social odors; Fig. 2A). Asterisk indicates a significant difference between responses to familiar and novel odors at that delay.