Neuromodulation of thought: flexibilities and vulnerabilities in prefrontal cortical network synapses

Abstract

This review describes unique neuromodulatory influences on working memory prefrontal cortical (PFC) circuits that coordinate cognitive strength with arousal state. Working memory arises from recurrent excitation within layer III PFC pyramidal cell NMDA circuits, which are afflicted in aging and schizophrenia. Neuromodulators rapidly and flexibly alter the efficacy of these synaptic connections, while leaving the synaptic architecture unchanged, a process called dynamic network connectivity (DNC). Increases in calcium-cAMP signaling open ion channels in long, thin spines, gating network connections. Inhibition of calcium-cAMP signaling by stimulating α2A-adrenoceptors on spines strengthens synaptic efficacy and increases network firing, whereas optimal stimulation of dopamine D1 receptors sculpts network inputs to refine mental representation. Generalized increases in calcium-cAMP signaling during fatigue or stress disengage dlPFC recurrent circuits, reduce firing and impair top-down cognition. Impaired DNC regulation contributes to age-related cognitive decline, while genetic insults to DNC proteins are commonly linked to schizophrenia.

Figure 1

A. The reciprocal, parallel, visual and auditory cortical networks connecting with dlPFC. More ventral PFC regions connect with limbic areas subserving emotion (not shown). This figure is based on the work of Goldman-Rakic, as summarized in Arnsten, 2003 (Arnsten, 2003). B. The oculomotor delayed response (ODR) test of spatial working memory. For each trial, the monkey fixates on a central point, initiating the brief presentation (0.5s) of a cue in 1 of 8 locations. A delay period ensues (2.5–8s) in which the monkey must remember the spatial location until the fixation point extinguishes, and the monkey must make a saccade to the correct location to receive juice reward. The cued position randomly changes over hundred of trials, thus generating high levels of proactive interference. C. Cue, Delay and Response cells recorded from area 46 of the monkey dlPFC as a monkey performs the ODR task, and the corresponding microcircuitry thought to underlie physiological responses. (Goldman-Rakic, 1995). Cue cells fire during the presentation of the cue and stop firing during the Delay period. Delay cells often fire to the cue (and/or to the saccadic response), but are noted for their ability to maintain persistent firing across the delay period. Delay cells are usually spatially tuned, firing across the delay period for the neuron’s preferred direction, but decreasing firing for all other nonpreferred directions (the preferred direction for this Delay cell is indicated by a red asterisk). The microcircuits underlying Delay cell firing reside in deep layer III (and possibly in layer V as well) and are described in detail in the text. In contrast to Delay cells, Response cells are often inhibited during the delay period and instead fire leading up to, during, and/or after the motor response, initiating action and/or providing feedback. These neurons are thought to reside in layer V.

Figure 2

A highly schematized diagram of the interactions between recurrent, representational circuits in PFC with the sensory association cortices to create the “mental sketch pad”, illustrating the differences between long thin spines in PFC serving the gating processes of DNC, and the thin-type spines that change to mushroom-type to store long-term changes in synaptic efficacy (e.g. traditional neuroplastic changes in sensory cortex and subcortical structures). Neuromodulators shape both processes, but in fundamentally different ways. The sensory cortices provide the PFC with “bottom-up” sensory information, while PFC networks provide “top-down” regulation over the sensory cortex to retrieve stored memories and to guide sensory processing. For example, PFC inputs may enhance the processing of a nonsalient but relevant stimulus (shown), or inhibit the processing of distractors via projections to GABAergic interneurons ((Barbas et al., 2005), not shown). Plasticity occurs in the PFC as well, but is not illustrated for the sake of clarity. Inspired by Fuster, 1997 (Fuster, 1997).

Figure 3

Working model of the modulatory events contributing to DNC. A. DNC mechanisms engage long, thin spines with narrow neck segments that confine a minute cytosolic volume to subserve biochemical/electrical compartmentalization. DNC spines emanate from high-order dendrites, including the basal dendrites, as the one shown in layer III of monkey dlPFC (pseudocolored yellow). The spine neck is immunoreactive for PDEA (indicated by green arrowheads, and by green ovals in inset), positioned to regulate cAMP in the spine’s bottleneck. Asterisk marks the spine apparatus. Scale bar, 200 nm. B. A schematic illustration of the Ca⁺²-cAMP signaling events that weaken synaptic efficacy in layer III, long, thin spines. C. A schematic illustration of the Ca⁺²-cAMP signaling events that strengthen synaptic efficacy in layer III, long, thin spines. Please note that nicotinic α7 receptors have been documented on spines in rodent PFC (Duffy et al., 2009), but have not been studied in primate. See text for abbreviations.

Figure 4

cAMP signaling in primate dlPFC differs from traditional neuroplasticity. A and B. Dendritic spines in monkey layer III dlPFC sequester cAMP-gated HCN channels (red arrowheads), positioned to translate cAMP “hot spots” to network connectivity patterns. HCN channels are found in the spine neck (A) and in the perisynaptic membranes flanking excitatory (network) synapses (B), positioned to gate impulses to the parent dendrite. C. PDE4A, which hydrolyzes cAMP and terminates its actions, presents an identical expression pattern in the neck region (green arrowheads); please see also Figure 3A. A–C adapted from (Paspalas et al., 2012). D. KCNQ potassium channels are also expressed in dlPFC spines, and are shown here in perisynaptic and extrasynaptic membranes (red arrowheads). Asterisks mark spine apparata; arrows point to excitatory-like synapses. Scale bars, 100 nm. E. Increased cAMP signaling reduces dlPFC Delay cell firing. Iontophoresis of the PDE4 inhibitor, etazolate (25 nA), onto a dlPFC Delay cell rapidly reduces task-related firing in a monkey performing a working memory task. F. Population response of 8 Delay cells with delay-related firing under control conditions (blue trace), that is markedly reduced by iontophoresis of etazolate (red trace). Blockade of HCN channels with co-iontophoresis of ZD7288 (10 nA, green trace) restores normal firing patterns, demonstrating physiological interactions between HCN channels and cAMP signaling in the primate dlPFC. Adapted from (Wang et al., 2007).

Figure 5

HCN channels are co-expressed with a constellation of cAMP-related molecules in layer III spines of the monkey dlPFC. A–C. Label for HCN channels (red arrowheads) on spine membranes overlaps with label for α2A-ARs (A, green arrowheads) that inhibit cAMP production, PDE4A that catabolizes cAMP (B; green arrowheads; spine is pseudocolored yellow) and DISC1 that regulates PDE4 activity (C, green arrowheads). HCN channels also co-localize with D1Rs that elevate cAMP (see Fig. 8F). Asterisks mark spine apparata; arrows point to excitatory-like synapses. Scale bars, 200 nm. Adapted from (Paspalas et al., 2012; Wang et al., 2007). D. Local increases in cAMP signaling in dlPFC caused by iontophoresis of the α2-AR antagonist, yohimbine (15 nA) markedly reduce Delay cell firing in monkeys performing a working memory task. Blockade of HCN channels with co-iontophoresis of ZD7288 (10 nA) restores normal firing patterns, demonstrating physiological interactions between HCN channels and α2A-ARs in the primate dlPFC. Adapted from (Wang et al., 2007).

Figure 6

A. Hypothetical coordination of arousal state and PFC cognitive abilities based on alterations in layer III dlPFC network gating by increasing levels of catecholamines. NE stimulation of α2A-AR enhances network firing by increasing synaptic efficacy for inputs from neurons with similar preferred directions. Conversely, moderate levels of DA D1R stimulation sculpt network inputs from dissimilar neurons by decreasing synaptic efficacy. D1R sculpting actions may be helpful for some PFC cognitive operations, e.g. working memory for a precise spatial location, but may be harmful when wide network inputs are needed, e.g. creative solutions or attentional set-shifting. High levels of NE and DA release during stress disconnect all network inputs through α1-AR and high levels of D1R, respectively, switching control of behavior and thought to more primitive brain regions. α1-AR activation of PKC signaling during stress may uncouple α2A-ARs and diminish their beneficial actions (see text). B. Iontophoresis of a low dose of D1R agonist onto dlPFC Delay cells sharpens their spatial tuning (red trace), decreasing neuronal delay-related firing following cues for the neurons’ nonpreferred directions (θ≠0), but having no effect on delay-related firing following cues for the neurons’ preferred direction (θ=0). These sculpting actions are most evident in neurons with noisy firing under control conditions (blue trace). From (Vijayraghavan et al., 2007).

Figure 7

Changes in DNC regulation with advancing age weaken synaptic efficacy and contribute to reductions in the persistent dlPFC Delay cell firing underlying working memory. A. Deep layer III neuropil in the dlPFC of a young (9yo) vs. an aged (29yo) monkey. White and green circles mark unlabeled and α2A-AR-labeled dendritic spines, respectively. Please note that spine density for both categories decreases with age. The reduction in α2A-AR-labeling is consistent with autoradiographic measures of reduced α2A-AR expression in the aged monkey dlPFC (Bigham and Lidow, 1995; Moore et al., 2005). B. The persistent firing of dlPFC Delay cells during a spatial working memory task markedly declines with advancing age. Blue=firing for the neurons’ preferred direction; dark red=firing for the neurons’ nonpreferred direction. From (Wang et al., 2011a). C. The persistent firing of aged dlPFC neurons was significantly increased by iontophoresis of the α2A-AR agonist, guanfacine, which inhibits cAMP signaling. Adapted from (Wang et al., 2011a). D. A schematic representation of some of the changes in DNC signaling in layer III spines with advancing age that lead to disinhibition of Ca⁺²-cAMP signaling. See text for detailed description.

Figure 8

Some of the changes in DNC proteins associated with schizophrenia. A. Schematic summary showing that a number of proteins that normally serve to strengthen synaptic efficacy, e.g. by regulating Ca⁺²-cAMP signaling, are lost or weakened in schizophrenia. B and C. Dendritic spines in layer III of the monkey dlPFC express proteins that regulate Ca⁺²-cAMP signaling: B. RGS4 (green arrowheads) is found perisynaptically, positioned to regulate mGluR1α/mGluR5 signaling. C. PDE4A (green arrowhead) is found on the spine membrane with DISC1 (green double arrowheads), which likely tethers the enzyme to the correct subcellular locus. Adapted from (Paspalas et al., 2012; Paspalas et al., 2009) D and E. Proteins that generate Ca⁺²-cAMP signaling are localized in layer III spines in the monkey dlPFC. Stimulation of mGluR1α (D, red arrowheads) can mobilize Ca⁺² from the spine’s internal stores (i.e. the spine apparatus). Adapted from (Muly et al., 2003) with permission from C. Muly. The D1Rs, which elevate cAMP signaling, are colocalized with cAMP-gated HCN channels favoring their open state. An oblique section through a synapse in F (the synaptic disk is drawn as a white oval) demonstrates perisynaptic localization for both proteins (HCN channels, red arrowheads; D1Rs, red double arrowheads). Asterisks mark spine apparata; arrows point to excitatory-like synapses. Scale bars, 100 nm.