AMPA-receptor specific biogenesis complexes control synaptic transmission and intellectual ability

Abstract

AMPA-type glutamate receptors (AMPARs), key elements in excitatory neurotransmission in the brain, are macromolecular complexes whose properties and cellular functions are determined by the co-assembled constituents of their proteome. Here we identify AMPAR complexes that transiently form in the endoplasmic reticulum (ER) and lack the core-subunits typical for AMPARs in the plasma membrane. Central components of these ER AMPARs are the proteome constituents FRRS1l (C9orf4) and CPT1c that specifically and cooperatively bind to the pore-forming GluA1-4 proteins of AMPARs. Bi-allelic mutations in the human FRRS1L gene are shown to cause severe intellectual disability with cognitive impairment, speech delay and epileptic activity. Virus-directed deletion or overexpression of FRRS1l strongly impact synaptic transmission in adult rat brain by decreasing or increasing the number of AMPARs in synapses and extra-synaptic sites. Our results provide insight into the early biogenesis of AMPARs and demonstrate its pronounced impact on synaptic transmission and brain function.

Figure 1. Identification of distinct populations of AMPAR assemblies in the rat brain.

(a) Heat map indicating the molar abundance of AMPAR constituents determined in APs with various ABs targeting GluA1-4 (mixture of anti-GluA ABs), FRRS1l (anti-FRRS1l-a, anti-FRRS1l-b) and TARPs 2, 3, 4, 8 (anti-TARP-a, anti-TARP-b, anti-TARP-c) in membrane fractions from total rat brain solubilized with CL-47. Note the distinct subgroups of constituents co-purified with the pore-forming GluA1-4 proteins in anti-FRRS1l and anti-TARP APs highlighted by red boxes. Annotations on the right reflect molecular architecture and/or subcellular localization reported in literature or public databases. (b) Relative amounts of AMPAR constituents determined in two-step APs schematized on the right from CL-47 solubilized membrane fractions of total adult rat brains. Bars in red and blue depict the amount of AMPAR constituents in a target-depleting anti-FRRS1l AP (red bars, mean±s.d. of three measurements) and a subsequent target-depleting anti-GluA AP (blue), each determined as fraction of its summed protein amounts in the two APs. Brown bars illustrate relative amounts of AMPAR constituents (mean±s.d. of three measurements) in an anti-FRRS1l AP using the flow through of a target-depleting anti-GluA AP as input divided by the summed protein amount determined for any constituent in both APs from rat membranes. Note co-assembly of FRRS1l with GluA1-4 and only a subset of AMPAR proteome constituents.

Figure 2. Specific co-assembly of FRRS1l and CPT1c into AMPAR complexes with distinct subunit composition.

(a) Amounts of proteins specifically co-purified in APs with four different anti-FRRS1l ABs (upper panel) and two different anti-CPT1c ABs (lower panel) normalized to the amount of purified FRRS1l or CPT1c, respectively (red bar). Data are mean±s.d. of five (four ABs, one AB mixture, see Methods section) and three (two ABs, one AB mixture) independent APs, respectively. (b) Protein abundance ratios (mean±s.e.m. of four measurements) determined for the indicated proteome constituents in anti-GluA1-4 APs from brain membrane fractions prepared from both WT and CPT1c knockout mice (normalized to GluA1-4). Note the pronounced decrease of CPT1c, FRRS1l and Sac1 in AMPARs from knockout animals. Dashed line indicating 50% reduction in protein amount is shown for orientation; asterisks denote statistical significance for protein amounts being different between WT and KO (**, ***P values of 0.01 and 0.001 for Students’ t-test, respectively).

Figure 3. Mutations in FRRS1l identified as disease causing in patients with severe intellectual disability.

(a) Pedigree (and genotypes) of the three different families detailed in the text. Affected patients are indicated by filled symbol; slashes refer to deceased individuals. (b) Schematic representation of the FRRS1l protein (as given in the UniProtKB/Swiss-Prot database) together with the alterations identified in the indicated families and alignment of the primary sequence stretch around lysine 155 (K155) across species. TM is a predicted transmembrane domain. (c) Summary of the clinical features observed in the patients from families A–C. MA denotes mental age, NA means not investigated.

Figure 4. Assembly of WT and mutant FRRS1l with CPT1c and significance for ER localization and association with GluA proteins.

(a) Input and eluates of anti-GluA1 and anti-FRRS1l APs separated by SDS–PAGE and western blot probed for the indicated proteins. Note strong cooperativity of FRRS1l and CPT1c binding to AMPARs. (b) Representative confocal fluorescence images of tsA-201 cells expressing FRRS1l alone (upper left) or together with CPT1a (middle and lower left) or CPT1c (right); fluorescence staining as indicated by the colour coding (with anti-FRRS1l-a, anti-CPT1a or anti-CPT1c). Scale bar is 10 μm. Note marked re-distribution of FRRS1l upon co-expression of CPT1c from plasma membrane to intracellular membranes (FRRS1l staining: 93% (of 501 cells co-expressing FRRS1l and CPT1c) intracellular only, 6.8% intracellular and plasma membrane, 0.2% plasma membrane only). (c) Left: SDS–PAGE separation of membrane preparations from brain and culture cells (expressing the indicated proteins) western blot probed with anti-FRRS1l-a. Marks on the right refer to the distinct MW bands, red denotes FRRS1l with additional mass introduced by the HA-6His tag (Supplementary Fig. 6). Right: CID MS/MS spectrum of the indicated FRRS1l peptide carrying an ethanolamine moiety at αS317 as a specific marker for GPI-anchoring (Supplementary Fig. 6). Inset: Scheme highlighting the hydrophobic domain and relevant residues in the C-terminus of FRRS1l. (d) Input and eluates of anti-GluA1 APs separated by SDS–PAGE and western blot probed for the indicated proteins. Note the reduction or failure of the mutant FRRS1l proteins to assemble with the GluA proteins.

Figure 5. Subcellular localization of FRRS1l in neurons of the hippocampus.

(a) Confocal images of the hilar region of hippocampal slices prepared from adult rats and selected neurons therein triple stained with anti-FRRS1l, the ER-marker anti-Calnexin and the synapse marker anti-vGlut1. Graphs in the lower panel are fluorescence intensity scans of the annotated markers measured along the indicated lines on the confocal images of the selected neurons. (b) Electron micrographs showing immuno-reactivity for FRRS1l in somata (S) of CA1 pyramidal cells as detected by the pre-embedding immunogold method. Immunoparticles labelling FRRS1l were abundant over the endoplasmic reticulum (ER, arrows) but not on membranes of the Golgi complex (GC in lower panel). Particles (open arrowheads) occasionally appeared close to or at the somatic plasma membrane (PM, red line) targeted by boutons (b) of putative GABAergic neurons. Scale bar: 200 nm.

Figure 6. Alterations in EPSCs upon knockdown of FRRS1l in individual MFB–MC synapses.

(a) Representative action potential and EPSC traces determined by paired bouton recordings (upper inset) in hippocampal slices from MFB–MC synapses of an uninfected MC (control, left) or MCs transduced with sh-FRRS1l (middle) or sh-CPT1c (right). Current and time scaling as indicated. Grey lines are mono-exponential fits to the decay phase yielding time constants of 10.4 ms (control), 10.1 ms (sh-FRRS1l) and 10.1 ms (sh-CPT1c). Inset: Confocal fluorescence image of an uninfected (lower) and a sh-FRRS1l (fluorescence of GFP marker) transduced (upper) MC used for recordings (filled with biocytin, red fluorescence); framed images depict anti-FRRS1l staining of the two cells. Scale bar is 10 μm. (b) Summary plots of amplitudes (left) and decay time constants of the EPSCs determined in experiments as in a. Squares represent mean±s.e.m. of the experiments shown.

Figure 7. Decrease or increase of currents mediated by synaptic and extra-synaptic AMPARs upon knockdown and exogenous (over)expression of FRRS1l in distinct types of hippocampal neurons.

(a) Amplitude histograms determined from spontaneous EPSCs recorded in uninfected control or sh-FRRS1l-transduced MCs and in MCs with virally driven overexpression of FRRS1l (at −70 mV). Data are mean±s.e.m. of 129 (control), 68 (sh-FRRS1l) and 10 (overexpression) MCs. Inset: EPSCs from a control and a sh-FRRS1l-transduced MC. Current and time scaling as indicated. (b) Summary plot of EPSC amplitudes determined in MCs, interneurons (INs) and CA3 pyramidal cells (CA3 PCs) under control conditions (uninfected) or after transduction with the sh-RNAs indicated on the upper right. Data are mean±s.e.m. of 7–135 MCs, 11–77 INs and 18–61 CA3 PCs; EPSC amplitudes were normalized to the mean amplitude of the control cells. Note that reduction and increase in EPSC amplitude induced by knockdown and overexpression of FRRS1l occurred in all three types of hippocampal neurons. (c) Representative spontaneous EPSCs (left) and glutamate-evoked currents in a somatic outside-out (oo) patch both recorded successively either in an uninfected MC (control, black traces) or an MC transduced with sh-FRRS1l (red traces) in a hippocampal slice preparation. Current and time scaling as indicated. (d) Summary plot of relative amplitudes obtained for EPSCs and glutamate-evoked AMPAR currents in control MCs and MCs transduced with the indicated sh-RNAs. Data are mean±s.e.m. of 8 MCs for each condition.

Figure 8. Operation of FRRS1l/CPT1c complexes in AMPAR biogenesis in the ER.

(a) Left panel: Abundance ratios (mean±s.e.m. of four measurements) as in Fig. 2b determined in depleting GluA1-4 APs from neuronal cultures transduced with three additional sh-RNAs directed against distinct sequence stretches on FRRS1l or with sh-control. Note the different efficiencies of the three sh-FRRS1ls on both FRRS1l and the majority of core subunits and CPT1c. Right panel: correlation analysis of FRRS1l with GluA1-4 and the core subunits of AMPARs across AP data sets from different brain regions (data from ref. re-evaluated). Note that maximal correlation is observed between FRRS1l and the sum of all core subunits (red bar) rather than with the sum of GluAs or individual subunits. (b) Scheme summarizing the proposed role of FRRS1l as a ‘catalyst’ in AMPAR biogenesis and delivery of synaptic AMPARs. Newly synthesized GluA tetramers (GluA_tetra) co-assemble with FRRS1l–CPT1c complexes during early biogenesis in the ER. These GluA-FRRS1l/CPT1c complexes prepare subsequent co-assembly with the inner core subunits TARPs and CNIHs depicted as a short-lived intermediate priming complex (‘priming of assembly’). After binding of CNIHs/TARPs, FRRS1l–CPT1c complexes dissociate (arrow to the right), and the resulting GluA-CNIH/TARP assemblies represent AMPARs competent for ER exit (arrow to the left) and delivery to the plasma membrane. Stoichiometries were not implicated in neither of the illustrated protein assemblies.