Action control is mediated by prefrontal BDNF and glucocorticoid receptor binding

Abstract

Stressor exposure biases decision-making strategies from those based on the relationship between actions and their consequences to others restricted by stimulus-response associations. Chronic stressor exposure also desensitizes glucocorticoid receptors (GR) and diminishes motivation to acquire food reinforcement, although causal relationships are largely not established. We show that a history of chronic exposure to the GR ligand corticosterone or acute posttraining GR blockade with RU38486 makes rodents less able to perform actions based on their consequences. Thus, optimal GR binding is necessary for the consolidation of new response-outcome learning. In contrast, medial prefrontal (but not striatal) BDNF can account for stress-related amotivation, in that selective medial prefrontal cortical Bdnf knockdown decreases break-point ratios in a progressive-ratio task. Knockdown also increases vulnerability to RU38486. Despite the role of BDNF in dendritic spine reorganization, deep-layer spine remodeling does not obviously parallel progressive-ratio response patterns, but treatment with the Na(+)-channel inhibitor riluzole reverses corticosteroid-induced motivational deficits and restores prefrontal BDNF expression after corticosterone. We argue that when prefrontal neurotrophin systems are compromised, and GR-mediated hypothalamic-pituitary-adrenal axis feedback is desensitized (as in the case of chronic stress hormone exposure), amotivation and inflexible maladaptive response strategies that contribute to stress-related mood disorders result.

Fig. 1.

Reversal of CORT-induced habits by antidepressant treatment. (A) Rats were trained to lever-press for sucrose reinforcement; although antidepressant treatment increased response rates, all rats ultimately acquired the response. (B) Pairing sucrose with LiCl decreased sucrose consumption, and no group differences were identified. (C) At test, however, previously CORT-exposed rats showed insensitivity to outcome devaluation, but antidepressant treatment reinstated sensitivity after CORT. Rats administered amitriptyline alone also showed insensitivity to outcome devaluation. (D) CORT-exposed rats also failed to show sensitivity to degradation of the response-outcome contingency. Bars/symbols represent group means + SEM; *P ≤ 0.05,**P < 0.001.

Fig. 2.

Concurrent modification of instrumental decision-making and medial prefrontal BDNF. (A) As in rats, CORT exposure in mice did not impair instrumental response acquisition. (B) CORT exposure status also did not affect the development of conditioned taste aversion when the food outcome was repeatedly paired with LiCl. (C) As in rats, CORT-exposed mice failed, however, to modify instrumental decision-making based on the devaluation of the instrumental outcome. (D) In a separate group of mice, CORT did not impact responding during contingency degradation training, (E) but CORT-exposed mice failed to respond preferentially on the nondegraded aperture at test. (F) Break-point ratios achieved on a progressive-ratio schedule of reinforcement were also diminished. (Inset) Responding in extinction was unaffected. (G) Break-point ratios were predicted by prefrontal BDNF concentrations after CORT. (H) trkB and GLT-1 expression were also diminished after CORT. Representative blots are shown; a nonspecific band was not quantified. Bars represent group means (+SEM); symbols represent group means +SEM except in G, in which symbols represent individual animals. *P < 0.05, **P < 0.001.

Fig. 3.

Bdnf knockdown selectively modifies instrumental decision-making. (A) Bdnf was selectively knocked down in the mPFC; the largest and smallest GFP spreads are shown. GFP was detectable at least within the PL in all animals. (B) Knockdown reduced progressive-ratio break points. (C) PL Bdnf knockdown did not, however, affect responding during contingency degradation training or (D) during a subsequent choice test. (E and F) In contrast, administration of the GR antagonist immediately after the contingency degradation training (E) blocked preferential responding on the reinforced aperture during a subsequent choice test (F). (G) A subthreshold dose of RU38486 also impaired response-outcome decision-making in mice with concurrent PL Bdnf knockdown. Bars and symbols + SEM; n.s., not significant; *P < 0.05, **P < 0.001.

Fig. 4.

BDNF overexpression selectively modifies instrumental action. (A) Consistent with the perspective that PL BDNF is sufficient to regulate motivation but not sensitivity to contingency degradation, BDNF overexpression in CORT-exposed mice nearly doubled break points. (B) The same manipulation, however, failed to rescue sensitivity to response-outcome contingency degradation in CORT-exposed mice, and BDNF infusion in naïve animals also eliminated behavioral flexibility. Bars represent means + SEM; *P < 0.05, **P < 0.001.

Fig. 5.

Avolition is associated with mPFC BDNF, but not striatal BDNF or deep-layer PL dendritic spine morphology. (A) Summary of Figs 3 and 4. Although GR binding facilitates response-outcome learning, it does not obviously impact progressive-ratio responding; in contrast, PL BDNF is not sufficient to regulate response-outcome contingency learning, but it promotes responding on a progressive-ratio schedule of reinforcement. (B) Thus, pharmacological treatments that promote BDNF expression may restore motivation after CORT. Indeed, treatment with the Na⁺-channel inhibitor riluzole restored break-point ratios after CORT. (C) Riluzole concurrently increased PL BDNF expression after CORT, but CORT alone diminished BDNF to a comparable degree as viral-mediated Bdnf knockdown. (D) In contrast, dorsal striatal BDNF did not parallel break-point ratios: striatal BDNF was reduced by prefrontal knockdown, but increased after CORT, and riluzole had no additional effects. (E) Deep-layer PL dendritic spines were also modified, but again, not in parallel with break-point ratios: Dendritic spine length was blunted by CORT, but also by manipulations that did not reduce break points (e.g., food restriction). Sample dendrites are provided. (Scale bar = 10 μm.) Bars and symbols represent means + SEM; *P ≤ 0.05, **P < 0.001.