Insulin receptor sensitization restores neocortical excitation/inhibition balance in a mouse model of autism

Abstract

Background: Met receptor tyrosine kinase regulates neurogenesis, differentiation, migration, connectivity, and synaptic plasticity. The human Met gene has been identified as a prominent risk factor for autism spectrum disorder (ASD). Met gene-altered mice serve as useful models for mechanistic studies of ASD. Inactivation of Met in excitatory cortical neurons in mice (Emx1^cre/Met^flox mice) yields a phenotype in which significantly decreased GABA_A receptor-mediated inhibition shifts the excitation/inhibition (E/I) balance toward excitation in the somatosensory cortex. Further, unlike that seen in wild-type mice, insulin does not increase inhibition in the mutant cortex, suggesting that one of the consequences of kinase inactive Met gene could be desensitization of insulin receptors. To test this hypothesis, we investigated the effects of insulin receptor sensitizer, pioglitazone, on inhibition in the somatosensory thalamocortical circuitry.

Methods: We used whole-cell patch clamp electrophysiology and analyzed excitatory and inhibitory responses of cortical layer IV excitatory cells following stimulation of their thalamic input in thalamocortical pathway intact brain slices. We applied insulin alone and insulin + a thiazolidinedione, pioglitazone (PIO), to test the effects of sensitizing insulin receptors on inhibitory responses mediated by GABA_A receptors in the somatosensory cortex of Emx1^cre/Met^flox mice.

Results: In WT brain slices, application of insulin together with PIO did not enhance the effect of insulin alone. In contrast, PIO application induced a much larger inhibition than that of insulin alone in Met-defective cortex. Thus, insulin resistance of GABA_A receptor-mediated response in Met mutant mice may result from desensitized insulin receptors.

Conclusions: Sporadic clinical studies reported improved behavioral symptoms in children with autism following PIO treatment. We show that PIO can aid in normalization of the E/I balance in the primary somatosensory cortex, a potential physiological mechanism underlying the positive effects of PIO treatment.

Keywords: Barrel cortex; GABAA receptors; Homeostatic plasticity; Met receptor tyrosine kinase; Pioglitazone; Thalamocortical circuitry.

Fig. 1

Insulin and pioglitazone treatment effects on the E/I ratio in WT brain slices. a–c Membrane depolarization characteristically leads to regular spiking of layer IV excitatory neurons. This characteristic is evident in control (WT) slices, and after application of insulin (WT I), or insulin + pioglitazone (WT I + P). d EPSP-IPSP sequence following VB stimulation. At − 60 mV, the IPSP does not hyperpolarize below − 60 mV (upper trace). The IPSP polarity reverses at − 80 mV, around GABA_A receptor reversal potential (lower trace). e 500 nM insulin application results in an increase of IPSP that hyperpolarized below base line at − 60 mV (upper trace). The IPSP is mediated by GABA_A receptor, because it reverses at − 80 mV (lower trace). f Addition of pioglitazone to insulin application does not lead to any notable change. g–i Representative records of GABA_A receptor- and AMPA receptor-mediated currents under control, insulin, and insulin + pioglitazone application conditions. HP holding potential. j The averaged AMPA/GABA (E/I) ratios under the three conditions. Note that insulin application significantly reduces the E/I ratio; addition of pioglitazone does not change insulin effects alone. k Box and whisker plots showing the population distribution

Fig. 2

Insulin-induced increased inhibition. a–c Example records of GABA_A receptor-mediated sIPSCs. HP holding potential. d Cumulative fraction curves of the sIPSC amplitudes show that the amplitude distribution for insulin (WT I) and insulin + pioglitazone (WT I + P) are shifted to the right (larger amplitude), indicating that both conditions increase the amplitude of sIPSCs compared to no drug controls. e The average amplitude of sIPSCs is higher with either drug application condition compared to the controls, but not different between the two drug application conditions. f Box and whisker plots showing the population distribution

Fig. 3

Insulin and pioglitazone treatment effects on the E/I ratio in Met-EMx1 brain slices. a–c Regular spiking of layer IV excitatory neurons in control (Met-EMx1) slices, and after application of insulin (Met-EMx1 I), or insulin + pioglitazone (Met-EMx1 I + P). d, g In mutant brain slices, stimulation of VB induced mainly an EPSP without a clear cut IPSP. Isolated AMPA receptor- and GABA_A receptor-mediated currents reveal small IPSC. e, h Application of insulin (Met-EMx1 I) did not change the magnitude of GABA_A receptor-mediated response. f, i Addition of pioglitazone to insulin application dramatically increased GABA_A receptor-mediated inhibition. j The averaged AMPA/GABA (E/I) ratio is similar between no drug treatment and insulin alone treatment conditions, but application of pioglitazone along with insulin dramatically changed this ratio. k Box and whisker plots showing the population distribution

Fig. 4

Insulin sensitization-increased inhibition in Met-EMx1 brain slices. a–c Example records of GABA_A receptor-mediated sIPSCs in Met-EMx1 cortical neurons without drug application, and with insulin alone (I) or insulin + pioglitazone (I + P) applications. d Cumulative fraction curves of the sIPSC amplitudes show a significant shift of the amplitude distribution for insulin + pioglitazone condition compared to no drug treatment (Met-EMx1) or insulin treatment (Met-EMx1 I) alone. e The average amplitude of sIPSCs is much higher following insulin receptor sensitization with pioglitazone. f Box and whisker plots showing the population distribution