Slow changes in Ca2+ cause prolonged release from GABAergic retinal amacrine cells

The timing of neurotransmitter release from neurons can be modulated by many presynaptic mechanisms. The retina uses synaptic ribbons to mediate slow graded glutamate release from bipolar cells that carry photoreceptor inputs. However, many inhibitory amacrine cells, which modulate bipolar cell output, spike and do not have ribbons for graded release. Despite this, slow glutamate release from bipolar cells is modulated by slow GABAergic inputs that shorten the output of bipolar cells, changing the timing of visual signaling. The time course of light-evoked inhibition is slow due to a combination of receptor properties and prolonged neurotransmitter release. However, the light-evoked release of GABA requires activation of neurons upstream from the amacrine cells, so it is possible that prolonged release is due to slow amacrine cell activation, rather than slow inherent release properties of the amacrine cells. To test this idea, we directly activated primarily action potential-dependent amacrine cell inputs to bipolar cells with electrical stimulation. We found that the decay of GABA C receptor-mediated electrically evoked inhibitory currents was significantly longer than would be predicted by GABA C receptor kinetics, and GABA release, estimated by deconvolution analysis, was inherently slow. Release became more transient after increasing slow Ca2+ buffering or blocking prolonged L-type Ca2+ channels and Ca2+ release from intracellular stores. Our results suggest that GABAergic amacrine cells have a prolonged buildup of Ca2+ in their terminals that causes slow, asynchronous release. This could be a mechanism of matching the time course of amacrine cell inhibition to bipolar cell glutamate release.