{"gene":"GABRG2","run_date":"2026-06-09T23:54:44","timeline":{"discoveries":[{"year":2009,"finding":"The GABRG2 Q351X (Q390X in full-length protein) nonsense mutation causes dominant-negative suppression of wild-type GABAA receptors in addition to loss-of-function. The mutant γ2(Q351X) subunit is retained in the ER and oligomerizes with wild-type α1 and β2/γ2 subunits, trapping them in the ER and subjecting them to ERAD via the ubiquitin-proteasome system. Pulse-chase experiments showed enhanced degradation of wild-type α1 subunits within 1 h of translation when co-expressed with the mutant subunit.","method":"Pulse-chase radiolabeling, co-immunoprecipitation, immunoblotting, patch-clamp electrophysiology in HEK293 cells","journal":"The Journal of neuroscience","confidence":"High","confidence_rationale":"Tier 1–2 / Strong — multiple orthogonal methods (pulse-chase, Co-IP, electrophysiology) in a focused mechanistic study","pmids":["19261880"],"is_preprint":false},{"year":2012,"finding":"The intronic GABRG2 mutation IVS6+2T→G abolishes normal intron 6 splicing, activates a cryptic splice site, generates partial intron 6 retention with a frameshift creating a premature termination codon (PTC). The resultant mutant mRNA is partially degraded by NMD; undegraded mRNA is translated to a stable truncated γ2-PTC subunit containing exons 1–6 plus a novel 29 aa C-terminal tail. This truncated subunit is retained in the ER, does not reach the cell surface, but does oligomerize with α1 and β2 subunits, exerting a dominant-negative effect on αβγ2 receptor assembly.","method":"Bacterial artificial chromosome (BAC) constructs expressed in HEK293T cells and transgenic mice; mRNA splicing analysis; NMD assay; surface biotinylation; immunoblotting; co-immunoprecipitation","journal":"The Journal of neuroscience","confidence":"High","confidence_rationale":"Tier 1–2 / Strong — reconstitution in both HEK293T cells and transgenic mice, multiple orthogonal methods","pmids":["22539854"],"is_preprint":false},{"year":2012,"finding":"The GABRG2 Q40X nonsense mutation generates a premature termination codon that activates NMD, degrading the γ2 mRNA. Residual undegraded mRNA is translated to a truncated peptide (likely the signal peptide) that is cleaved further. Mutant γ2(Q40X) subunits fail to assemble into functional receptors, reducing GABA-evoked currents. Gentamicin-induced stop-codon readthrough partially restores full-length γ2 subunit synthesis and surface expression, with rescued subunits incorporating into functional GABAA receptors.","method":"BAC minigene NMD assay, immunoblotting, surface biotinylation, whole-cell patch-clamp recording in HEK cells","journal":"Neurobiology of disease","confidence":"High","confidence_rationale":"Tier 1–2 / Strong — in vitro reconstitution with multiple orthogonal methods including electrophysiology and surface biotinylation","pmids":["22750526"],"is_preprint":false},{"year":2013,"finding":"GABRG2 nonsense mutations located outside the last exon activate NMD to varying degrees, producing truncated γ2 subunits with different stabilities, degradation rates, and degrees of polyubiquitin conjugation. The intracellular concentration of trafficking-deficient truncated subunits correlates in a concentration-dependent manner with suppression of wild-type GABAA receptor surface expression, ER stress levels, and epilepsy severity. A last-exon nonsense mutation that does not activate NMD produces a more stable truncated protein associated with more severe dominant-negative suppression.","method":"NMD minigene assay, 35S radiolabeling pulse-chase, flow cytometry, immunoblotting, whole-cell recordings, immunohistochemistry in non-neuronal cells and neurons","journal":"Annals of neurology","confidence":"High","confidence_rationale":"Tier 1–2 / Strong — multiple orthogonal methods across multiple mutations in a single systematic study","pmids":["23720301"],"is_preprint":false},{"year":2014,"finding":"Three GABRG2 missense mutations at the γ+/β− subunit interface (R82Q, P83S, N79S) differentially impair GABAA receptor assembly. R82Q and P83S reduce α1β2γ2 receptor surface expression due to impaired pentamer assembly, ER retention, and degradation, while N79S only minimally alters receptor trafficking. Structural modeling predicted increased conformational variability at assembly motifs for R82Q and P83S but not N79S. Lower temperature (30°C) partially rescued surface and total γ2 subunit levels for all three, suggesting these mutations impair protein folding/stability.","method":"Flow cytometry, immunoblotting, patch-clamp electrophysiology, structural modeling, temperature-rescue experiment in HEK293T cells","journal":"Neurobiology of disease","confidence":"High","confidence_rationale":"Tier 1–2 / Strong — multiple orthogonal methods (electrophysiology, flow cytometry, structural modeling) across three mutations","pmids":["24798517"],"is_preprint":false},{"year":2014,"finding":"The GABRG2 R177G missense mutation causes ER retention and ERAD of mutant γ2L(R177G) subunits, decreasing GABAA receptor surface expression and GABA-evoked whole-cell currents. With heterozygous expression, wild-type γ2L subunits possess a competitive advantage over mutant subunits for receptor assembly and forward trafficking. Cycloheximide chase showed R177G primarily destabilizes an intracellular pool of unassembled γ2L subunits. Molecular modeling indicated disruption of intrasubunit salt bridges destabilizes secondary/tertiary structure.","method":"Electrophysiology, flow cytometry, immunoblotting, cycloheximide chase, molecular modeling in HEK293T cells","journal":"Neurobiology of disease","confidence":"High","confidence_rationale":"Tier 1–2 / Strong — multiple orthogonal methods (electrophysiology, flow cytometry, structural modeling) in a focused study","pmids":["24874541"],"is_preprint":false},{"year":2014,"finding":"GABRG2 R136* premature termination mutation produces a truncated γ2 subunit with reduced cell-surface and total expression. When co-expressed with α1 and β2 subunits in HEK293T cells, GABA-evoked currents were reduced. The truncated subunit accumulated intracellularly in aggregates surrounding the nucleus and ER, indicating compromised receptor trafficking.","method":"In vitro expression in HEK293T cells, immunoblotting, flow cytometry, patch-clamp electrophysiology, confocal imaging","journal":"Neurobiology of disease","confidence":"Medium","confidence_rationale":"Tier 2 / Moderate — single lab, multiple orthogonal methods","pmids":["24407264"],"is_preprint":false},{"year":2014,"finding":"The GABRG2 Q40X mutation in Dravet syndrome patients produces a mutant γ2 subunit that, when expressed in HEK cells, inhibits intracellular trafficking of co-expressed GABAA receptor subunits α1 and β2, retaining them in the ER. In neurons, the mutant γ2 subunit also impaired axonal transport of α1 and β2 subunits. Electrophysiological studies confirmed reduced GABA-induced currents with reconstituted mutant receptors.","method":"Electrophysiology, immunohistochemistry, microinjection in HEK cells, immunohistochemistry in neurons","journal":"Epilepsy research","confidence":"Medium","confidence_rationale":"Tier 2–3 / Moderate — multiple methods including neuronal experiments, single lab","pmids":["24480790"],"is_preprint":false},{"year":2015,"finding":"In Gabrg2+/Q390X knock-in mice, the mutant γ2(Q390X) subunit accumulates and aggregates intracellularly in neurons, activates caspase 3, and causes widespread age-dependent neurodegeneration beyond impairing inhibitory neurotransmission. This links epilepsy-associated ion channel mutations to neurodegenerative mechanisms via mutant protein accumulation.","method":"Gabrg2+/Q390X knock-in mouse model; immunoblotting; immunohistochemistry; caspase 3 activation assay","journal":"Nature neuroscience","confidence":"High","confidence_rationale":"Tier 2 / Strong — in vivo knock-in model with multiple orthogonal mechanistic readouts","pmids":["26005849"],"is_preprint":false},{"year":2016,"finding":"Comparison of Gabrg2+/Q390X knock-in (KI) and Gabrg2+/- knockout (KO) mice showed that the dominant-negative KI mutation causes neuronal accumulation of mutant γ2 subunits, reduced wild-type subunit expression at dendrites and synapses, more severe seizures, and behavioral comorbidities. In contrast, KO mice (simple haploinsufficiency) showed no intracellular accumulation and unaffected biogenesis of remaining wild-type subunits. This establishes that dominant-negative suppression rather than haploinsufficiency drives the severe epileptic encephalopathy phenotype.","method":"Immunoblotting, immunohistochemistry, behavioral testing, EEG in knock-in vs. knockout mouse models","journal":"Human molecular genetics","confidence":"High","confidence_rationale":"Tier 2 / Strong — genetic epistasis using two mouse models with multiple orthogonal methods, direct head-to-head comparison","pmids":["27340224"],"is_preprint":false},{"year":2016,"finding":"Multiple de novo GABRG2 missense mutations (A106T, I107T, P282S, R323W, F343L, R323Q) associated with epileptic encephalopathies reduce α1β2γ2L GABAA receptor surface expression with altered subunit stoichiometry and/or decrease GABA-evoked whole-cell current amplitudes when expressed in HEK293T cells, though with different levels of reduction for each mutation.","method":"Patch-clamp recording, immunoblotting, confocal imaging, structural modeling in HEK293T cells","journal":"Brain","confidence":"High","confidence_rationale":"Tier 1–2 / Strong — multiple orthogonal methods across six mutations in a systematic study","pmids":["27864268"],"is_preprint":false},{"year":2016,"finding":"Three GABRG2 nonsense mutations (R136*, Q390*, W429*) associated with epilepsies of different severities produce truncated subunits with no to minimal surface expression and differentially reduced GABA-evoked current amplitudes. Structural modeling showed that different truncated subunits adopt different conformations with different surface hydrophobicities and different tendencies to dimerize with wild-type subunit binding partners, correlating with disease severity.","method":"Flow cytometry, biochemical assays, lifted whole-cell patch-clamp recording, structural modeling","journal":"Scientific reports","confidence":"Medium","confidence_rationale":"Tier 2 / Moderate — multiple orthogonal methods, single lab","pmids":["27762395"],"is_preprint":false},{"year":2011,"finding":"The GABRG2 K289M mutation (GEFS+ associated) accelerates GABAA receptor deactivation and reduces inhibitory synaptic transmission. Upon temperature elevation, the K289M mutation enhances membrane diffusion of synaptic GABAA receptors via a mechanism dependent on neuronal activity (blocked by glutamate receptor antagonists and mimicked by 4-aminopyridine), causing escape of receptors from synapses and further reduction of GABAergic inhibition. This effect was not observed in neurons expressing wild-type γ2.","method":"Single-particle tracking, miniature IPSC recording, confocal imaging in cultured neurons","journal":"Cerebral cortex","confidence":"Medium","confidence_rationale":"Tier 2 / Moderate — single lab with single-particle tracking and electrophysiology, two orthogonal methods","pmids":["21908847"],"is_preprint":false},{"year":2012,"finding":"A GABRG2 frameshift mutation (c.1329delC; γ2S(S443delC)) produces an elongated, modified carboxy-terminus. The mutant subunit is translated as a stable, larger protein that is retained in the ER without surface expression. Co-expression with α1 and β2 in HEK293T cells produced GABA-evoked currents comparable to α1β2 receptors (lacking γ2), demonstrating that the mutant subunit cannot incorporate into functional αβγ2 receptors (haploinsufficiency with possible dominant-negative component).","method":"Immunoblotting, flow cytometry, patch-clamp electrophysiology in HEK293T cells","journal":"Neurobiology of disease","confidence":"Medium","confidence_rationale":"Tier 2 / Moderate — multiple orthogonal methods in single lab","pmids":["23069679"],"is_preprint":false},{"year":2019,"finding":"In Gabrg2+/Q390X knock-in mice, impaired GABAergic neurotransmission in the central nucleus of the amygdala (CeA), but not the basolateral amygdala, underlies comorbid anxiety. Reduced GABAA receptor subunit expression in CeA was due to the GABRG2 loss-of-function mutation. Chemogenetic activation or inactivation of inhibitory neurons in CeA modulated anxiety-like behaviors, and pharmacological enhancement of γ2 subunit-containing receptors relieved anxiety.","method":"Brain slice recordings, subcellular fractionation, Western blot, immunohistochemistry, confocal microscopy, behavior testing, chemogenetics (DREADDs) in knock-in and knockout mice","journal":"Epilepsia","confidence":"High","confidence_rationale":"Tier 2 / Strong — multiple orthogonal methods including chemogenetic rescue in vivo","pmids":["31087664"],"is_preprint":false},{"year":2020,"finding":"In Gabrg2+/Q390X knock-in mice (but not Gabrg2+/- knockout mice), pro-inflammatory cytokines TNF-α, IL-1β, and IL-6 are elevated in multiple brain regions throughout development. The underlying basis is chronic accumulation of the misfolded mutant γ2(Q390X) subunit protein causing ER stress. Pharmacological induction of ER stress upregulated cytokines in wild-type and KO but not KI mice. Cytokine elevation was independent of seizure occurrence, as it was also observed in cultured neurons.","method":"ELISA, immunoprecipitation, nuclei purification, immunoblot, immunohistochemistry, confocal microscopy in knock-in vs. knockout mice and cultured neurons","journal":"Epilepsia","confidence":"High","confidence_rationale":"Tier 2 / Strong — multiple orthogonal methods with appropriate controls (KO comparison, ER stress pharmacology, neuronal cultures)","pmids":["32944937"],"is_preprint":false},{"year":2016,"finding":"In Gabrg2+/Q390X knock-in mice, synaptic GABAA receptors are reduced while intracellular non-functional γ2(Q390X) subunits accumulate in brainstem nuclei associated with respiratory function (nucleus tractus solitarius, pre-Bötzinger complex, Kölliker-Fuse nuclei). This impaired GABAergic transmission in cardiorespiratory brainstem nuclei is proposed as a mechanism for SUDEP in Dravet syndrome/GEFS+.","method":"Subcellular fractionation, immunoblotting, immunohistochemistry in knock-in vs. knockout mouse brainstem nuclei","journal":"Epilepsy research","confidence":"Medium","confidence_rationale":"Tier 2 / Moderate — direct fractionation and regional expression analysis in mouse model, single lab","pmids":["27131289"],"is_preprint":false},{"year":2017,"finding":"Crossing Gabrg2+/Q390X knock-in mice with BAC transgenic mice overexpressing wild-type HA-tagged human γ2 subunits increased wild-type γ2, α1, and β2/3 subunit expression, increased mIPSC amplitudes in layer VI cortical neurons, reduced thalamocortical network oscillations, and raised PTZ seizure threshold. This demonstrates that seizures in this dominant-negative GABRG2 epilepsy model can be rescued by overexpression of wild-type γ2 subunits.","method":"Western blot, immunohistochemistry, whole-cell patch-clamp recording (mIPSC), thalamocortical slice recording, PTZ seizure threshold testing in mice","journal":"Epilepsia","confidence":"High","confidence_rationale":"Tier 2 / Strong — genetic rescue experiment with multiple orthogonal functional readouts","pmids":["28586508"],"is_preprint":false},{"year":2023,"finding":"4-Phenylbutyrate (PBA) reduces mutant γ2(Q390X) subunit protein aggregates, enhances trafficking of wild-type GABAA receptor subunits to the membrane, increases GABA-evoked current amplitudes in HEK293T cells and neurons bearing the γ2(Q390X) subunit, reduces ER stress caused by the mutant subunit, and mitigates seizures and EEG abnormalities in Gabrg2+/Q390X mice. The mechanism is proteostasis modulation (facilitation of wild-type receptor folding and membrane trafficking) rather than direct channel modulation.","method":"Biochemical differential allele tagging, live brain slice surface biotinylation, microsome isolation, patch-clamp recordings, video-EEG in Gabrg2+/Q390X knock-in mice and HEK293T cells","journal":"Epilepsia","confidence":"High","confidence_rationale":"Tier 1–2 / Strong — multiple orthogonal in vitro and in vivo methods including live slice biotinylation and EEG","pmids":["37746768"],"is_preprint":false},{"year":2024,"finding":"The ERAD-associated E3 ubiquitin ligase HRD1 is a modulator of both wild-type and mutant γ2(Q390X) subunit expression. Overexpressing or knocking down HRD1 dose-dependently alters γ2(Q390X) subunit levels. Zonisamide, which upregulates HRD1, partially rescues surface trafficking of GABAA receptors otherwise sequestered in the ER by the dominant-negative γ2(Q390X) subunit, and reduces seizures in Gabrg2+/Q390X mice. ER chaperones BiP and calnexin total expression were unchanged in γ2(Q390X) models.","method":"Immunoblotting, overexpression/knockdown in HEK293T cells, seizure monitoring in Gabrg2+/Q390X mice","journal":"International journal of molecular sciences","confidence":"Medium","confidence_rationale":"Tier 2 / Moderate — single lab, multiple biochemical methods with in vivo pharmacological validation","pmids":["38731820"],"is_preprint":false},{"year":2021,"finding":"Neocortex- and hippocampus-specific conditional knockout of Gabrg2 (Cre/loxP system) in heterozygous mice produces temperature-dependent myoclonic jerks, generalized tonic-clonic seizures, increased anxiety, spontaneous seizures, and neuronal loss in cortical layers V-VI and hippocampus, demonstrating that GABRG2 expression specifically in neocortex and hippocampus is required to prevent febrile seizure-like phenotypes.","method":"Cre/loxP conditional knockout, cortical EEG, behavioral testing, histology","journal":"Cell death & disease","confidence":"Medium","confidence_rationale":"Tier 2 / Moderate — clean cell-type-specific KO with defined phenotypic readouts, single lab","pmids":["34050134"],"is_preprint":false},{"year":2006,"finding":"A novel GABRG2 mutation associated with febrile seizures alters GABAA receptor current desensitization kinetics and reduces benzodiazepine enhancement of mutant receptors, as demonstrated by electrophysiological studies of recombinant receptors.","method":"Electrophysiology of recombinant receptors","journal":"Neurology","confidence":"Medium","confidence_rationale":"Tier 1 / Weak — electrophysiological reconstitution but abstract provides limited detail about the specific mutation and methods","pmids":["16924025"],"is_preprint":false},{"year":2021,"finding":"GABRG2 T90R and P342L de novo variants identified in Dravet syndrome patients primarily cause trafficking defects when expressed in recombinant α1β2γ2 GABAA receptors, in contrast to GABRA1 and GABRB2 Dravet syndrome variants which mainly cause gating defects. This suggests variant-subunit-specific mechanisms even within the same pentameric receptor.","method":"Patch-clamp electrophysiology, immunoblotting, confocal imaging in HEK293T cells","journal":"Brain communications","confidence":"Medium","confidence_rationale":"Tier 2 / Moderate — multiple orthogonal methods, single lab, part of a larger study comparing multiple subunits","pmids":["34095830"],"is_preprint":false},{"year":2022,"finding":"Three rare GABRG2 variants (T90M, T317N, Q217X) in sleep-related hypermotor epilepsy patients impair GABAA receptor function by distinct mechanisms: T90M and T317N decrease GABA-evoked currents by impairing surface expression and/or ER retention and channel gating defects, while Q217X reduces synaptic clustering and distribution of GABAA receptors.","method":"Electrophysiology, Western blot, flow cytometry, confocal microscopy in neuronal and non-neuronal cells","journal":"Journal of neurology","confidence":"Medium","confidence_rationale":"Tier 2 / Moderate — multiple orthogonal methods, single lab","pmids":["35486215"],"is_preprint":false},{"year":2020,"finding":"In transgenic zebrafish overexpressing GABRG2(F343L), spontaneous seizure-like behaviors occur and can be reduced by suberanilohydroxamic acid (SAHA), a broad HDAC inhibitor. RNA sequencing showed 524 differentially expressed genes including upregulation of 33 protein-processing genes, with protein network analysis identifying HDACs as potential therapeutic targets.","method":"Transgenic zebrafish model, automated locomotion tracking, field potential recording, RNA sequencing","journal":"Annals of translational medicine","confidence":"Medium","confidence_rationale":"Tier 2 / Moderate — in vivo zebrafish model with transcriptomic and pharmacological validation, single lab","pmids":["33437759"],"is_preprint":false},{"year":2022,"finding":"Transgenic zebrafish overexpressing GABRG2(F343L) display not only postsynaptic defects (altered GABAA receptor subunit expression) but also presynaptic deficits as revealed by synaptic protein expression analysis and synapse ultrastructure examination, expanding the GABAergic epilepsy paradigm from channelopathy to synaptopathy.","method":"Western blot, whole-mount in situ hybridization, synaptic protein expression analysis, electron microscopy for synapse ultrastructure in transgenic zebrafish","journal":"Human molecular genetics","confidence":"Medium","confidence_rationale":"Tier 2 / Moderate — ultrastructural and molecular analysis in vivo zebrafish model, single lab","pmids":["34957497"],"is_preprint":false},{"year":2025,"finding":"Functional characterization of GABRG2 variants reveals both loss-of-function (LoF) and gain-of-function (GoF) mechanisms. Null variants cause milder epilepsy phenotypes (haploinsufficiency), missense LoF variants cause intermediate phenotypes with more frequent DD/ID and psychiatric features, while GoF variants (e.g., A106T) cause severe DEE with early onset at 2 months. Electrophysiological measurements of missense variants in a cohort of 44 individuals (35 variants) confirmed that 9 caused LoF, 3 caused GoF, and 5 did not alter function.","method":"Electrophysiological recordings of recombinant receptors, systematic clinical data collection","journal":"Neurology","confidence":"Medium","confidence_rationale":"Tier 2 / Moderate — systematic electrophysiological characterization across 17 missense variants, single study","pmids":["40570274"],"is_preprint":false},{"year":2025,"finding":"The recurrent GABRG2 p.(Ala106Thr) variant confers gain-of-function by facilitating a hydrogen bond between the extracellular and transmembrane domains, as shown by electrophysiological recordings and structural homology modeling. A different variant at the same residue, p.(Ala106Pro), was functionally neutral. This structural mechanism explains the severe DEE associated with this recurrent variant.","method":"Electrophysiological recordings, homology-based structural modeling","journal":"Epilepsia","confidence":"Medium","confidence_rationale":"Tier 2 / Moderate — electrophysiology plus structural modeling, comparison of two variants at same residue provides internal control","pmids":["41351427"],"is_preprint":false},{"year":2022,"finding":"Electroacupuncture at PC6 regulates alternative splicing of GABRG2 via the splicing factor NOVA1. Ischemia-reperfusion decreased NOVA1 expression; electroacupuncture rescued NOVA1 levels. In dorsal root ganglion cells, NOVA1 was shown to regulate alternative splicing of GABRG2 specifically on exon 9, which contains an important phosphorylation site.","method":"In vivo rat model, EMG recordings, transcriptomic dataset analysis, in vitro DRG cell experiments, RT-PCR","journal":"Journal of cardiovascular translational research","confidence":"Low","confidence_rationale":"Tier 3 / Weak — single lab, limited mechanistic detail in abstract, indirect readout","pmids":["35377129"],"is_preprint":false},{"year":2025,"finding":"In Gabrg2 conditional knockout mice subjected to hyperthermia, ER stress via PERK signaling pathway activation reduces surface expression of GABRG2 on layer 5 pyramidal neurons. This impairs vesicle transport and is associated with increased mEPSC, decreased mIPSC, and reduced dendritic spine density and complexity in L5 pyramidal neurons. ITPR3 and cytosolic GABRG2 protein expression increased while membrane GABRG2 decreased.","method":"Patch-clamp electrophysiology (mEPSC, mIPSC), dendritic morphology analysis, Western blot, immunohistochemistry in conditional knockout mice","journal":"iScience","confidence":"Medium","confidence_rationale":"Tier 2 / Moderate — multiple electrophysiological and biochemical methods in conditional knockout mouse model, single lab","pmids":["41537003"],"is_preprint":false}],"current_model":"GABRG2 encodes the γ2 subunit of GABAA receptors, which is critical for receptor trafficking, synaptic clustering, and chloride channel function; epilepsy-associated mutations reduce surface GABAA receptor expression through mechanisms including NMD-mediated mRNA decay, ER retention and ERAD, dominant-negative trapping of wild-type partnering subunits (α1, β2) in the ER via oligomerization, intracellular aggregation causing ER stress and neurodegeneration, and altered channel gating—with rare gain-of-function mutations also identified—and the severity of the resulting epilepsy syndrome correlates with the extent of functional GABAA receptor reduction and the degree of dominant-negative suppression versus simple haploinsufficiency."},"narrative":{"mechanistic_narrative":"GABRG2 encodes the γ2 subunit of the pentameric GABAA receptor, the principal mediator of fast inhibitory neurotransmission, where it is required for assembly, synaptic clustering, and surface trafficking of functional α1β2γ2 chloride channels [PMID:24480790, PMID:23069679]. The dominant disease paradigm is that mutant γ2 subunits exert pathogenic effects beyond simple loss of function: nonsense, frameshift, and missense mutations are retained in the ER, fail to reach the surface, and oligomerize with wild-type α1 and β2/γ2 partners to trap them in the ER and target them for ERAD via the ubiquitin-proteasome system, producing dominant-negative suppression of wild-type receptors [PMID:19261880, PMID:22539854, PMID:24480790]. The intracellular concentration of trafficking-deficient truncated subunit scales with the degree of wild-type surface suppression, ER stress, and epilepsy severity, with nonsense mutations escaping NMD (e.g. last-exon variants) producing the most stable and most strongly dominant-negative proteins [PMID:23720301, PMID:27762395]. In knock-in mice, the dominant-negative Q390X allele drives intracellular aggregation, caspase-3 activation and age-dependent neurodegeneration, elevation of pro-inflammatory cytokines through ER stress, and severe seizures with comorbid anxiety and respiratory-nucleus dysfunction—phenotypes absent in haploinsufficient knockouts, establishing dominant-negative suppression rather than haploinsufficiency as the driver of severe epileptic encephalopathy [PMID:26005849, PMID:27340224, PMID:32944937, PMID:27131289]. Missense mutations act through distinct biophysical routes including impaired pentamer assembly and folding (rescuable at lower temperature), altered desensitization and deactivation gating, reduced benzodiazepine modulation, and activity-dependent escape of receptors from synapses, while a subset of recurrent variants (e.g. A106T) confer gain-of-function by stabilizing inter-domain contacts [PMID:24798517, PMID:21908847, PMID:16924025, PMID:40570274, PMID:41351427]. The disorder is thus a proteostasis-sensitive channelopathy: enhancing wild-type γ2 expression, promoting mutant folding/trafficking with 4-phenylbutyrate, or upregulating the ERAD E3 ligase HRD1 each restore surface receptors and reduce seizures [PMID:28586508, PMID:37746768, PMID:38731820].","teleology":[{"year":2006,"claim":"Established that GABRG2 mutations can act through altered channel biophysics rather than expression alone, linking the γ2 subunit to febrile seizures via gating and pharmacology changes.","evidence":"Electrophysiology of recombinant receptors carrying a febrile-seizure variant","pmids":["16924025"],"confidence":"Medium","gaps":["Specific mutation and quantitative kinetics underspecified","No surface-expression or trafficking data","No in vivo confirmation"]},{"year":2009,"claim":"Resolved how a truncating mutation causes more than haploinsufficiency, showing the mutant γ2 subunit traps wild-type partners in the ER for ERAD—defining the dominant-negative mechanism.","evidence":"Pulse-chase, co-IP, and patch-clamp in HEK293 cells for Q351X/Q390X","pmids":["19261880"],"confidence":"High","gaps":["Did not identify the specific ERAD ubiquitin ligase","In vitro HEK system only at this stage","Quantitative contribution to epilepsy severity not established"]},{"year":2012,"claim":"Demonstrated that distinct mutation classes (intronic splice, early nonsense) converge on NMD-mediated mRNA decay plus translation of stable trafficking-deficient truncated subunits that still oligomerize dominant-negatively, and that stop-codon readthrough can partially rescue surface expression.","evidence":"BAC minigene NMD assays, surface biotinylation, co-IP, electrophysiology, and transgenic mice; gentamicin readthrough for Q40X","pmids":["22539854","22750526"],"confidence":"High","gaps":["Readthrough efficiency too low for therapeutic relevance","Variable NMD escape across variants not yet systematized","Neuronal consequences not fully resolved"]},{"year":2013,"claim":"Unified the mutation spectrum by showing that the intracellular concentration of trafficking-deficient truncated subunit determines, in a dose-dependent manner, the degree of wild-type suppression, ER stress, and clinical severity—explaining genotype-phenotype correlation.","evidence":"NMD minigene assays, pulse-chase, flow cytometry, electrophysiology, and IHC across multiple nonsense mutations","pmids":["23720301"],"confidence":"High","gaps":["Correlation established in cells, not in patient brain","Threshold for pathogenicity not quantified in vivo"]},{"year":2014,"claim":"Defined the structural basis of missense pathogenicity, distinguishing assembly/folding defects at the γ+/β− interface and salt-bridge-disrupting mutations from variants causing intracellular aggregation, and showed wild-type subunits competitively outcompete mutants for assembly.","evidence":"Flow cytometry, immunoblotting, electrophysiology, cycloheximide chase, confocal imaging, and structural modeling in HEK293T cells (R82Q/P83S/N79S, R177G, R136*); neuronal axonal transport for Q40X","pmids":["24798517","24874541","24407264","24480790"],"confidence":"High","gaps":["Temperature/competition rescue not translated in vivo","Aggregate composition uncharacterized","Mechanism of synaptic versus somatic trafficking block incompletely separated"]},{"year":2015,"claim":"Established in vivo that a dominant-negative allele links an ion-channel mutation to neurodegeneration, showing mutant subunit aggregation activates caspase-3 and causes age-dependent neuronal loss beyond impairing inhibition.","evidence":"Gabrg2+/Q390X knock-in mice with immunoblotting, IHC, and caspase-3 assays","pmids":["26005849"],"confidence":"High","gaps":["Apoptotic pathway upstream of caspase-3 not fully mapped","Cell types most vulnerable not exhaustively defined"]},{"year":2016,"claim":"Settled the haploinsufficiency-versus-dominant-negative debate by direct knock-in versus knockout comparison, proving intracellular accumulation and reduced wild-type synaptic subunit expression—not loss of one allele—drives severe encephalopathy; also extended pathology to respiratory brainstem nuclei and broadened the missense/nonsense variant catalogue.","evidence":"Head-to-head KI vs KO mouse phenotyping (immunoblot, IHC, EEG, behavior, brainstem fractionation); systematic variant characterization in HEK293T cells","pmids":["27340224","27864268","27762395","27131289"],"confidence":"High","gaps":["SUDEP mechanism inferred from regional expression, not direct cardiorespiratory failure recordings","Stoichiometry changes for some missense variants not fully resolved"]},{"year":2017,"claim":"Provided proof-of-principle that the dominant-negative deficit is reversible, showing transgenic overexpression of wild-type γ2 restores subunit expression, mIPSCs, and raises seizure threshold in knock-in mice.","evidence":"BAC transgenic rescue cross with Western blot, IHC, mIPSC and thalamocortical slice recording, and PTZ seizure testing","pmids":["28586508"],"confidence":"High","gaps":["Genetic overexpression not directly translatable to therapy","Does not clear pre-existing mutant aggregates"]},{"year":2019,"claim":"Mapped circuit-level origins of comorbidity, localizing anxiety to impaired GABAergic transmission in the central amygdala and showing chemogenetic and pharmacological manipulation of this inhibition modulates the phenotype.","evidence":"Slice recordings, fractionation, IHC, behavior, and DREADD chemogenetics in knock-in/knockout mice","pmids":["31087664"],"confidence":"High","gaps":["Other comorbidity circuits not mapped","Link between molecular ER pathology and circuit deficit indirect"]},{"year":2020,"claim":"Connected ER stress from misfolded mutant subunit to neuroinflammation, showing chronic accumulation elevates TNF-α, IL-1β, and IL-6 independently of seizures and specifically in knock-in but not knockout mice.","evidence":"ELISA, IP, immunoblot, IHC with ER-stress pharmacology in KI vs KO mice and cultured neurons; zebrafish F343L overexpression as a complementary in vivo model","pmids":["32944937","33437759"],"confidence":"High","gaps":["Cellular source of cytokines not pinpointed","Causal contribution of inflammation to seizures versus bystander effect unresolved"]},{"year":2022,"claim":"Refined mechanism heterogeneity, showing GABRG2 Dravet variants are predominantly trafficking-defective (unlike gating-defective GABRA1/GABRB2 variants), that distinct SHE variants act via ER retention, gating, or clustering defects, and extending pathology to presynaptic synaptopathy.","evidence":"Electrophysiology, immunoblot, flow cytometry, confocal imaging in HEK293T/neuronal cells; zebrafish ultrastructure and synaptic protein analysis","pmids":["34095830","35486215","34957497"],"confidence":"Medium","gaps":["Presynaptic deficit mechanism in a postsynaptic-subunit disease unexplained","Single-lab variant cohorts"]},{"year":2023,"claim":"Validated proteostasis modulation as a therapeutic strategy, showing 4-phenylbutyrate reduces mutant aggregates, restores wild-type trafficking, lowers ER stress, and mitigates seizures—acting on folding rather than the channel itself.","evidence":"Differential allele tagging, live-slice surface biotinylation, microsome isolation, patch-clamp, and video-EEG in Gabrg2+/Q390X mice and HEK293T cells","pmids":["37746768"],"confidence":"High","gaps":["PBA molecular target not defined","Durability and dosing for chronic disease unknown"]},{"year":2024,"claim":"Identified a specific ERAD effector, HRD1, as a dose-dependent modulator of mutant γ2 levels and showed pharmacological HRD1 upregulation (zonisamide) rescues surface trafficking and reduces seizures.","evidence":"Overexpression/knockdown and immunoblotting in HEK293T cells with seizure monitoring in Gabrg2+/Q390X mice","pmids":["38731820"],"confidence":"Medium","gaps":["Direct HRD1–γ2 ubiquitination not demonstrated biochemically","Zonisamide effect on HRD1 may be indirect","BiP/calnexin unchanged but broader chaperone network unprobed"]},{"year":2025,"claim":"Established a bidirectional functional spectrum, showing systematic electrophysiology resolves loss-of-function, neutral, and gain-of-function variants, with the recurrent A106T gain-of-function variant explained structurally by a stabilizing inter-domain hydrogen bond; also linked hyperthermia-induced PERK ER stress to reduced surface γ2 and synaptic imbalance.","evidence":"Electrophysiology of recombinant receptors with clinical correlation; homology structural modeling; conditional-knockout mouse hyperthermia model with patch-clamp and morphology","pmids":["40570274","41351427","41537003"],"confidence":"Medium","gaps":["Gain-of-function variants a minority and mechanistically distinct from dominant-negative paradigm","PERK pathway causality vs correlation in temperature sensitivity not fully isolated"]},{"year":null,"claim":"How the proteostasis machinery is wired to γ2 quality control beyond HRD1, and whether trafficking-restoration or anti-inflammatory strategies can be combined for durable seizure and neurodegeneration prevention, remains unresolved.","evidence":"","pmids":[],"confidence":"Medium","gaps":["Full ERAD/chaperone interactome for γ2 undefined","No clinical translation of PBA/zonisamide/readthrough","Mechanistic basis of presynaptic and neuroinflammatory contributions incompletely linked to molecular pathology"]}],"mechanism_profile":{"molecular_activity":[{"term_id":"GO:0005215","term_label":"transporter activity","supporting_discovery_ids":[0,2,7,13]},{"term_id":"GO:0005198","term_label":"structural molecule activity","supporting_discovery_ids":[0,4,13]},{"term_id":"GO:0060089","term_label":"molecular transducer activity","supporting_discovery_ids":[12,21,26]}],"localization":[{"term_id":"GO:0005886","term_label":"plasma membrane","supporting_discovery_ids":[1,2,12,13]},{"term_id":"GO:0005783","term_label":"endoplasmic reticulum","supporting_discovery_ids":[0,1,4,5,6,7]},{"term_id":"GO:0005634","term_label":"nucleus","supporting_discovery_ids":[6]}],"pathway":[{"term_id":"R-HSA-112316","term_label":"Neuronal System","supporting_discovery_ids":[12,17,20]},{"term_id":"R-HSA-8953897","term_label":"Cellular responses to stimuli","supporting_discovery_ids":[15,29]},{"term_id":"R-HSA-392499","term_label":"Metabolism of proteins","supporting_discovery_ids":[0,1,19]}],"complexes":["GABAA receptor (α1β2γ2 pentamer)"],"partners":["GABRA1","GABRB2","HRD1"],"other_free_text":[]}},"prefetch_data":{"uniprot":{"accession":"P18507","full_name":"Gamma-aminobutyric acid receptor subunit gamma-2","aliases":["GABA(A) receptor subunit gamma-2","GABAAR subunit gamma-2"],"length_aa":475,"mass_kda":55.2,"function":"Gamma subunit of the heteropentameric ligand-gated chloride channel gated by gamma-aminobutyric acid (GABA), a major inhibitory neurotransmitter in the brain (PubMed:14993607, PubMed:16412217, PubMed:23909897, PubMed:2538761, PubMed:25489750, PubMed:27864268, PubMed:29950725, PubMed:30602789). GABA-gated chloride channels, also named GABA(A) receptors (GABAAR), consist of five subunits arranged around a central pore and contain GABA active binding site(s) located at the alpha and beta subunit interface(s) (PubMed:29950725, PubMed:30602789). When activated by GABA, GABAARs selectively allow the flow of chloride anions across the cell membrane down their electrochemical gradient (PubMed:14993607, PubMed:16412217, PubMed:2538761, PubMed:27864268, PubMed:29950725, PubMed:30602789). Gamma-2/GABRG2-containing GABAARs are found at both synaptic and extrasynaptic sites (By similarity). Chloride influx into the postsynaptic neuron following GABAAR opening decreases the neuron ability to generate a new action potential, thereby reducing nerve transmission (By similarity). GABAARs containing alpha-1 and beta-2 or -3 subunits exhibit synaptogenic activity; the gamma-2 subunit being necessary but not sufficient to induce rapid synaptic contacts formation (PubMed:23909897, PubMed:25489750). Extrasynaptic gamma-2-containing receptors contribute to the tonic GABAergic inhibition (By similarity). GABAARs function also as histamine receptor where histamine binds at the interface of two neighboring beta subunits and potentiates GABA response in a gamma-2 subunit-controlled manner (By similarity)","subcellular_location":"Postsynaptic cell membrane; Cell membrane; Cell projection, dendrite; Cytoplasmic vesicle membrane","url":"https://www.uniprot.org/uniprotkb/P18507/entry"},"depmap":{"release":"DepMap","has_data":true,"is_common_essential":false,"resolved_as":"","url":"https://depmap.org/portal/gene/GABRG2","classification":"Not Classified","n_dependent_lines":0,"n_total_lines":1208,"dependency_fraction":0.0},"opencell":{"profiled":false,"resolved_as":"","ensg_id":"","cell_line_id":"","localizations":[],"interactors":[],"url":"https://opencell.sf.czbiohub.org/search/GABRG2","total_profiled":1310},"omim":[{"mim_id":"621120","title":"DELTA-LIKE NONCANONICAL NOTCH LIGAND 2; DLK2","url":"https://www.omim.org/entry/621120"},{"mim_id":"618396","title":"DEVELOPMENTAL AND EPILEPTIC ENCEPHALOPATHY 74; DEE74","url":"https://www.omim.org/entry/618396"},{"mim_id":"607681","title":"FEBRILE SEIZURES, FAMILIAL, 8; FEB8","url":"https://www.omim.org/entry/607681"},{"mim_id":"607208","title":"DRAVET SYNDROME; DRVT","url":"https://www.omim.org/entry/607208"},{"mim_id":"605493","title":"TRIPARTITE MOTIF-CONTAINING PROTEIN 3; TRIM3","url":"https://www.omim.org/entry/605493"}],"hpa":{"profiled":true,"resolved_as":"","reliability":"","locations":[],"tissue_specificity":"Group enriched","tissue_distribution":"Detected in some","driving_tissues":[{"tissue":"brain","ntpm":40.7},{"tissue":"retina","ntpm":10.3}],"url":"https://www.proteinatlas.org/search/GABRG2"},"hgnc":{"alias_symbol":[],"prev_symbol":[]},"alphafold":{"accession":"P18507","domains":[{"cath_id":"2.70.170.10","chopping":"62-270","consensus_level":"high","plddt":94.3393,"start":62,"end":270},{"cath_id":"1.20.58.390","chopping":"273-363_454-465","consensus_level":"high","plddt":92.6852,"start":273,"end":465}],"viewer_url":"https://alphafold.ebi.ac.uk/entry/P18507","model_url":"https://alphafold.ebi.ac.uk/files/AF-P18507-F1-model_v6.cif","pae_url":"https://alphafold.ebi.ac.uk/files/AF-P18507-F1-predicted_aligned_error_v6.png","plddt_mean":77.19},"mouse_models":{"mgi_url":"https://www.informatics.jax.org/marker/summary?nomen=GABRG2","jax_strain_url":"https://www.jax.org/strain/search?query=GABRG2"},"sequence":{"accession":"P18507","fasta_url":"https://rest.uniprot.org/uniprotkb/P18507.fasta","uniprot_url":"https://www.uniprot.org/uniprotkb/P18507/entry","alphafold_viewer_url":"https://alphafold.ebi.ac.uk/entry/P18507"}},"corpus_meta":[{"pmid":"12117362","id":"PMC_12117362","title":"A splice-site mutation in GABRG2 associated with childhood absence epilepsy and febrile convulsions.","date":"2002","source":"Archives of neurology","url":"https://pubmed.ncbi.nlm.nih.gov/12117362","citation_count":222,"is_preprint":false},{"pmid":"16924025","id":"PMC_16924025","title":"A novel GABRG2 mutation associated with febrile seizures.","date":"2006","source":"Neurology","url":"https://pubmed.ncbi.nlm.nih.gov/16924025","citation_count":120,"is_preprint":false},{"pmid":"27367160","id":"PMC_27367160","title":"Molecular Pathogenic Basis for GABRG2 Mutations Associated With a Spectrum of Epilepsy Syndromes, From Generalized Absence Epilepsy to Dravet Syndrome.","date":"2016","source":"JAMA neurology","url":"https://pubmed.ncbi.nlm.nih.gov/27367160","citation_count":105,"is_preprint":false},{"pmid":"27864268","id":"PMC_27864268","title":"De novo GABRG2 mutations associated with epileptic encephalopathies.","date":"2016","source":"Brain : a journal of neurology","url":"https://pubmed.ncbi.nlm.nih.gov/27864268","citation_count":91,"is_preprint":false},{"pmid":"26005849","id":"PMC_26005849","title":"The human epilepsy mutation GABRG2(Q390X) causes chronic subunit accumulation and neurodegeneration.","date":"2015","source":"Nature neuroscience","url":"https://pubmed.ncbi.nlm.nih.gov/26005849","citation_count":82,"is_preprint":false},{"pmid":"19261880","id":"PMC_19261880","title":"The GABRG2 mutation, Q351X, associated with generalized epilepsy with febrile seizures plus, has both loss of function and dominant-negative suppression.","date":"2009","source":"The Journal of neuroscience : the official journal of the Society for Neuroscience","url":"https://pubmed.ncbi.nlm.nih.gov/19261880","citation_count":79,"is_preprint":false},{"pmid":"35718920","id":"PMC_35718920","title":"Molecular and clinical descriptions of patients with GABAA receptor gene variants (GABRA1, GABRB2, GABRB3, GABRG2): A cohort study, review of literature, and genotype-phenotype correlation.","date":"2022","source":"Epilepsia","url":"https://pubmed.ncbi.nlm.nih.gov/35718920","citation_count":72,"is_preprint":false},{"pmid":"18566737","id":"PMC_18566737","title":"SCN1A, SCN1B, and GABRG2 gene mutation analysis in Chinese families with generalized epilepsy with febrile seizures plus.","date":"2008","source":"Journal of human genetics","url":"https://pubmed.ncbi.nlm.nih.gov/18566737","citation_count":56,"is_preprint":false},{"pmid":"14738422","id":"PMC_14738422","title":"Generalized epilepsy with febrile seizures plus (GEFS+): clinical spectrum in seven Italian families unrelated to SCN1A, SCN1B, and GABRG2 gene mutations.","date":"2004","source":"Epilepsia","url":"https://pubmed.ncbi.nlm.nih.gov/14738422","citation_count":49,"is_preprint":false},{"pmid":"27340224","id":"PMC_27340224","title":"Differential molecular and behavioural alterations in mouse models of GABRG2 haploinsufficiency versus dominant negative mutations associated with human epilepsy.","date":"2016","source":"Human molecular genetics","url":"https://pubmed.ncbi.nlm.nih.gov/27340224","citation_count":46,"is_preprint":false},{"pmid":"24061200","id":"PMC_24061200","title":"GABRG2, rs211037 is associated with epilepsy susceptibility, but not with antiepileptic drug resistance and febrile seizures.","date":"2013","source":"Pharmacogenetics and genomics","url":"https://pubmed.ncbi.nlm.nih.gov/24061200","citation_count":41,"is_preprint":false},{"pmid":"24798517","id":"PMC_24798517","title":"Three epilepsy-associated GABRG2 missense mutations at the γ+/β- interface disrupt GABAA receptor assembly and trafficking by similar mechanisms but to different extents.","date":"2014","source":"Neurobiology of disease","url":"https://pubmed.ncbi.nlm.nih.gov/24798517","citation_count":38,"is_preprint":false},{"pmid":"22750526","id":"PMC_22750526","title":"The GABRG2 nonsense mutation, Q40X, associated with Dravet syndrome activated NMD and generated a truncated subunit that was partially rescued by aminoglycoside-induced stop codon read-through.","date":"2012","source":"Neurobiology of disease","url":"https://pubmed.ncbi.nlm.nih.gov/22750526","citation_count":36,"is_preprint":false},{"pmid":"15772696","id":"PMC_15772696","title":"Haplotype association between GABAA receptor gamma2 subunit gene (GABRG2) and methamphetamine use disorder.","date":"2005","source":"The pharmacogenomics journal","url":"https://pubmed.ncbi.nlm.nih.gov/15772696","citation_count":35,"is_preprint":false},{"pmid":"23720301","id":"PMC_23720301","title":"Trafficking-deficient mutant GABRG2 subunit amount may modify epilepsy phenotype.","date":"2013","source":"Annals of neurology","url":"https://pubmed.ncbi.nlm.nih.gov/23720301","citation_count":35,"is_preprint":false},{"pmid":"34095830","id":"PMC_34095830","title":"Dravet syndrome-associated mutations in GABRA1, GABRB2 and GABRG2 define the genetic landscape of defects of GABAA receptors.","date":"2021","source":"Brain communications","url":"https://pubmed.ncbi.nlm.nih.gov/34095830","citation_count":35,"is_preprint":false},{"pmid":"24407264","id":"PMC_24407264","title":"A novel GABRG2 mutation, p.R136*, in a family with GEFS+ and extended phenotypes.","date":"2014","source":"Neurobiology of disease","url":"https://pubmed.ncbi.nlm.nih.gov/24407264","citation_count":34,"is_preprint":false},{"pmid":"24480790","id":"PMC_24480790","title":"Association of nonsense mutation in GABRG2 with abnormal trafficking of GABAA receptors in severe epilepsy.","date":"2014","source":"Epilepsy research","url":"https://pubmed.ncbi.nlm.nih.gov/24480790","citation_count":34,"is_preprint":false},{"pmid":"24874541","id":"PMC_24874541","title":"GABAA receptor biogenesis is impaired by the γ2 subunit febrile seizure-associated mutation, GABRG2(R177G).","date":"2014","source":"Neurobiology of disease","url":"https://pubmed.ncbi.nlm.nih.gov/24874541","citation_count":33,"is_preprint":false},{"pmid":"17162195","id":"PMC_17162195","title":"Association of GABRG2 polymorphisms with idiopathic generalized epilepsy.","date":"2007","source":"Pediatric neurology","url":"https://pubmed.ncbi.nlm.nih.gov/17162195","citation_count":31,"is_preprint":false},{"pmid":"22539854","id":"PMC_22539854","title":"The intronic GABRG2 mutation, IVS6+2T->G, associated with childhood absence epilepsy altered subunit mRNA intron splicing, activated nonsense-mediated decay, and produced a stable truncated γ2 subunit.","date":"2012","source":"The Journal of neuroscience : the official journal of the Society for Neuroscience","url":"https://pubmed.ncbi.nlm.nih.gov/22539854","citation_count":31,"is_preprint":false},{"pmid":"21908847","id":"PMC_21908847","title":"A human mutation in Gabrg2 associated with generalized epilepsy alters the membrane dynamics of GABAA receptors.","date":"2011","source":"Cerebral cortex (New York, N.Y. : 1991)","url":"https://pubmed.ncbi.nlm.nih.gov/21908847","citation_count":31,"is_preprint":false},{"pmid":"22239287","id":"PMC_22239287","title":"Role of MDR1 C3435T and GABRG2 C588T gene polymorphisms in seizure occurrence and MDR1 effect on anti-epileptic drug (phenytoin) absorption.","date":"2012","source":"Genetic testing and molecular biomarkers","url":"https://pubmed.ncbi.nlm.nih.gov/22239287","citation_count":29,"is_preprint":false},{"pmid":"27066572","id":"PMC_27066572","title":"Novel GABRG2 mutations cause familial febrile seizures.","date":"2015","source":"Neurology. Genetics","url":"https://pubmed.ncbi.nlm.nih.gov/27066572","citation_count":28,"is_preprint":false},{"pmid":"23069679","id":"PMC_23069679","title":"Impaired surface αβγ GABA(A) receptor expression in familial epilepsy due to a GABRG2 frameshift mutation.","date":"2012","source":"Neurobiology of disease","url":"https://pubmed.ncbi.nlm.nih.gov/23069679","citation_count":27,"is_preprint":false},{"pmid":"20485450","id":"PMC_20485450","title":"Mutational analysis of GABRG2 in a Japanese cohort with childhood epilepsies.","date":"2010","source":"Journal of human genetics","url":"https://pubmed.ncbi.nlm.nih.gov/20485450","citation_count":24,"is_preprint":false},{"pmid":"26452361","id":"PMC_26452361","title":"Contribution of GABRG2 Polymorphisms to Risk of Epilepsy and Febrile Seizure: a Multicenter Cohort Study and Meta-analysis.","date":"2015","source":"Molecular neurobiology","url":"https://pubmed.ncbi.nlm.nih.gov/26452361","citation_count":22,"is_preprint":false},{"pmid":"12759178","id":"PMC_12759178","title":"Failure to find causal mutations in the GABA(A)-receptor gamma2 subunit (GABRG2) gene in Japanese febrile seizure patients.","date":"2003","source":"Neuroscience letters","url":"https://pubmed.ncbi.nlm.nih.gov/12759178","citation_count":22,"is_preprint":false},{"pmid":"28505490","id":"PMC_28505490","title":"Heat induced temperature dysregulation and seizures in Dravet Syndrome/GEFS+ Gabrg2+/Q390X mice.","date":"2017","source":"Epilepsy research","url":"https://pubmed.ncbi.nlm.nih.gov/28505490","citation_count":20,"is_preprint":false},{"pmid":"28586508","id":"PMC_28586508","title":"Overexpressing wild-type γ2 subunits rescued the seizure phenotype in Gabrg2+/Q390X Dravet syndrome mice.","date":"2017","source":"Epilepsia","url":"https://pubmed.ncbi.nlm.nih.gov/28586508","citation_count":20,"is_preprint":false},{"pmid":"31004928","id":"PMC_31004928","title":"Novel variants and phenotypes widen the phenotypic spectrum of GABRG2-related disorders.","date":"2019","source":"Seizure","url":"https://pubmed.ncbi.nlm.nih.gov/31004928","citation_count":20,"is_preprint":false},{"pmid":"21983990","id":"PMC_21983990","title":"GABRG2 gene polymorphisms in Egyptian children with simple febrile seizures.","date":"2011","source":"Indian journal of pediatrics","url":"https://pubmed.ncbi.nlm.nih.gov/21983990","citation_count":20,"is_preprint":false},{"pmid":"36979350","id":"PMC_36979350","title":"GABRG2 Variants Associated with Febrile Seizures.","date":"2023","source":"Biomolecules","url":"https://pubmed.ncbi.nlm.nih.gov/36979350","citation_count":18,"is_preprint":false},{"pmid":"15955415","id":"PMC_15955415","title":"Mutation screen of GABRA1, GABRB2 and GABRG2 genes in Japanese patients with absence seizures.","date":"2005","source":"Neuroscience letters","url":"https://pubmed.ncbi.nlm.nih.gov/15955415","citation_count":17,"is_preprint":false},{"pmid":"23140995","id":"PMC_23140995","title":"GABRG2 rs211037 polymorphism and epilepsy: a systematic review and meta-analysis.","date":"2012","source":"Seizure","url":"https://pubmed.ncbi.nlm.nih.gov/23140995","citation_count":16,"is_preprint":false},{"pmid":"27762395","id":"PMC_27762395","title":"Differential protein structural disturbances and suppression of assembly partners produced by nonsense GABRG2 epilepsy mutations: implications for disease phenotypic heterogeneity.","date":"2016","source":"Scientific reports","url":"https://pubmed.ncbi.nlm.nih.gov/27762395","citation_count":16,"is_preprint":false},{"pmid":"29379546","id":"PMC_29379546","title":"GABRG2 C588T gene polymorphisms might be a predictive genetic marker of febrile seizures and generalized recurrent seizures: a case-control study in a Romanian pediatric population.","date":"2016","source":"Archives of medical science : AMS","url":"https://pubmed.ncbi.nlm.nih.gov/29379546","citation_count":16,"is_preprint":false},{"pmid":"27131289","id":"PMC_27131289","title":"Altered GABAA receptor expression in brainstem nuclei and SUDEP in Gabrg2(+/Q390X) mice associated with epileptic encephalopathy.","date":"2016","source":"Epilepsy research","url":"https://pubmed.ncbi.nlm.nih.gov/27131289","citation_count":15,"is_preprint":false},{"pmid":"28460589","id":"PMC_28460589","title":"Expanding the phenotypic spectrum of GABRG2 variants: a recurrent GABRG2 missense variant associated with a severe phenotype.","date":"2017","source":"Journal of neurogenetics","url":"https://pubmed.ncbi.nlm.nih.gov/28460589","citation_count":15,"is_preprint":false},{"pmid":"23287319","id":"PMC_23287319","title":"Lack of association between rs211037 of the GABRG2 gene and juvenile myoclonic epilepsy in Brazilian population.","date":"2012","source":"Neurology India","url":"https://pubmed.ncbi.nlm.nih.gov/23287319","citation_count":14,"is_preprint":false},{"pmid":"33437759","id":"PMC_33437759","title":"The GABRG2 F343L allele causes spontaneous seizures in a novel transgenic zebrafish model that can be treated with suberanilohydroxamic acid (SAHA).","date":"2020","source":"Annals of translational medicine","url":"https://pubmed.ncbi.nlm.nih.gov/33437759","citation_count":14,"is_preprint":false},{"pmid":"12694927","id":"PMC_12694927","title":"No evidence of GABRG2 mutations in severe myoclonic epilepsy of infancy.","date":"2003","source":"Epilepsy research","url":"https://pubmed.ncbi.nlm.nih.gov/12694927","citation_count":14,"is_preprint":false},{"pmid":"34050134","id":"PMC_34050134","title":"Neocortex- and hippocampus-specific deletion of Gabrg2 causes temperature-dependent seizures in mice.","date":"2021","source":"Cell death & disease","url":"https://pubmed.ncbi.nlm.nih.gov/34050134","citation_count":12,"is_preprint":false},{"pmid":"31087664","id":"PMC_31087664","title":"Molecular basis for and chemogenetic modulation of comorbidities in GABRG2-deficient epilepsies.","date":"2019","source":"Epilepsia","url":"https://pubmed.ncbi.nlm.nih.gov/31087664","citation_count":12,"is_preprint":false},{"pmid":"31022638","id":"PMC_31022638","title":"The therapeutic effect of stiripentol in Gabrg2+/Q390X mice associated with epileptic encephalopathy.","date":"2019","source":"Epilepsy research","url":"https://pubmed.ncbi.nlm.nih.gov/31022638","citation_count":12,"is_preprint":false},{"pmid":"24776921","id":"PMC_24776921","title":"Association study of GABRG2 polymorphisms with suicidal behaviour in schizophrenia patients with alcohol use disorder.","date":"2014","source":"Neuropsychobiology","url":"https://pubmed.ncbi.nlm.nih.gov/24776921","citation_count":12,"is_preprint":false},{"pmid":"32944937","id":"PMC_32944937","title":"Endoplasmic reticulum stress increases inflammatory cytokines in an epilepsy mouse model Gabrg2+/Q390X knockin: A link between genetic and acquired epilepsy?","date":"2020","source":"Epilepsia","url":"https://pubmed.ncbi.nlm.nih.gov/32944937","citation_count":12,"is_preprint":false},{"pmid":"16256272","id":"PMC_16256272","title":"Mutations in GABRA1, GABRA5, GABRG2 and GABRD receptor genes are not a major factor in the pathogenesis of familial focal epilepsy preceded by febrile seizures.","date":"2005","source":"Neuroscience letters","url":"https://pubmed.ncbi.nlm.nih.gov/16256272","citation_count":12,"is_preprint":false},{"pmid":"32056912","id":"PMC_32056912","title":"Interactions of the GABRG2 polymorphisms and childhood trauma on suicide attempt and related traits in depressed patients.","date":"2020","source":"Journal of affective disorders","url":"https://pubmed.ncbi.nlm.nih.gov/32056912","citation_count":11,"is_preprint":false},{"pmid":"32418750","id":"PMC_32418750","title":"GABRG2 Deletion Linked to Genetic Epilepsy with Febrile Seizures Plus Affects the Expression of GABAA Receptor Subunits and Other Genes at Different Temperatures.","date":"2020","source":"Neuroscience","url":"https://pubmed.ncbi.nlm.nih.gov/32418750","citation_count":11,"is_preprint":false},{"pmid":"37746768","id":"PMC_37746768","title":"4-Phenylbutyrate promoted wild-type γ-aminobutyric acid type A receptor trafficking, reduced endoplasmic reticulum stress, and mitigated seizures in Gabrg2+/Q390X mice associated with Dravet syndrome.","date":"2023","source":"Epilepsia","url":"https://pubmed.ncbi.nlm.nih.gov/37746768","citation_count":10,"is_preprint":false},{"pmid":"25573302","id":"PMC_25573302","title":"Variants in SELL, MRPS36P2, TP63, DDB2, CACNA1H, ADAM19, GNAI1, CDH13 and GABRG2 interact to confer risk of acne in Chinese population.","date":"2015","source":"The Journal of dermatology","url":"https://pubmed.ncbi.nlm.nih.gov/25573302","citation_count":10,"is_preprint":false},{"pmid":"33650258","id":"PMC_33650258","title":"Analysis of GABRG2 C588T polymorphism in genetic epilepsy and evaluation of GABRG2 in drug treatment.","date":"2021","source":"Clinical and translational science","url":"https://pubmed.ncbi.nlm.nih.gov/33650258","citation_count":9,"is_preprint":false},{"pmid":"35486215","id":"PMC_35486215","title":"Rare variants in GABRG2 associated with sleep-related hypermotor epilepsy.","date":"2022","source":"Journal of neurology","url":"https://pubmed.ncbi.nlm.nih.gov/35486215","citation_count":9,"is_preprint":false},{"pmid":"34552348","id":"PMC_34552348","title":"Genetic Polymorphism of GABRG2 rs211037 is Associated with Drug Response and Adverse Drug Reactions to Valproic Acid in Chinese Southern Children with Epilepsy.","date":"2021","source":"Pharmacogenomics and personalized medicine","url":"https://pubmed.ncbi.nlm.nih.gov/34552348","citation_count":9,"is_preprint":false},{"pmid":"34957497","id":"PMC_34957497","title":"An epileptic encephalopathy associated GABRG2 missense mutation leads to pre- and postsynaptic defects in zebrafish.","date":"2022","source":"Human molecular genetics","url":"https://pubmed.ncbi.nlm.nih.gov/34957497","citation_count":8,"is_preprint":false},{"pmid":"22572707","id":"PMC_22572707","title":"Investigation of the role of the GABRG2 gene variant in migraine.","date":"2012","source":"Journal of the neurological sciences","url":"https://pubmed.ncbi.nlm.nih.gov/22572707","citation_count":8,"is_preprint":false},{"pmid":"40570274","id":"PMC_40570274","title":"Phenotypic Spectrum in Individuals With Pathogenic GABRG2 Loss- and Gain-of-Function Variants.","date":"2025","source":"Neurology","url":"https://pubmed.ncbi.nlm.nih.gov/40570274","citation_count":7,"is_preprint":false},{"pmid":"38731820","id":"PMC_38731820","title":"Modulating Endoplasmic Reticulum Chaperones and Mutant Protein Degradation in GABRG2(Q390X) Associated with Genetic Epilepsy with Febrile Seizures Plus and Dravet Syndrome.","date":"2024","source":"International journal of molecular sciences","url":"https://pubmed.ncbi.nlm.nih.gov/38731820","citation_count":7,"is_preprint":false},{"pmid":"27871023","id":"PMC_27871023","title":"Association of a novel GABRG2 splicing variation and a PTGS2/COX-2 single nucleotide polymorphism with Taiwanese febrile seizures.","date":"2016","source":"Epilepsy research","url":"https://pubmed.ncbi.nlm.nih.gov/27871023","citation_count":7,"is_preprint":false},{"pmid":"39143639","id":"PMC_39143639","title":"GABRG2 mutations in genetic epilepsy with febrile seizures plus: structure, roles, and molecular genetics.","date":"2024","source":"Journal of translational medicine","url":"https://pubmed.ncbi.nlm.nih.gov/39143639","citation_count":6,"is_preprint":false},{"pmid":"31321301","id":"PMC_31321301","title":"Human GABRG2 generalized epilepsy: Increased somatosensory and striatothalamic connectivity.","date":"2019","source":"Neurology. Genetics","url":"https://pubmed.ncbi.nlm.nih.gov/31321301","citation_count":6,"is_preprint":false},{"pmid":"39053637","id":"PMC_39053637","title":"Preliminary study on the mechanism of SAHA in the treatment of refractory epilepsy induced by GABRG2(F343L) mutation.","date":"2024","source":"Biochemical pharmacology","url":"https://pubmed.ncbi.nlm.nih.gov/39053637","citation_count":6,"is_preprint":false},{"pmid":"27293336","id":"PMC_27293336","title":"Mutations in GABRG2 receptor gene are not a major factor in the pathogenesis of mesial temporal lobe epilepsy in Indian population.","date":"2016","source":"Annals of Indian Academy of Neurology","url":"https://pubmed.ncbi.nlm.nih.gov/27293336","citation_count":6,"is_preprint":false},{"pmid":"36425336","id":"PMC_36425336","title":"GABRG2 C588T Polymorphism Is Associated with Idiopathic Generalized Epilepsy but Not with Antiepileptic Drug Resistance in Pakistani Cohort.","date":"2022","source":"BioMed research international","url":"https://pubmed.ncbi.nlm.nih.gov/36425336","citation_count":6,"is_preprint":false},{"pmid":"37703949","id":"PMC_37703949","title":"Epilepsy plus blindness in microdeletion of GABRA1 and GABRG2 in mouse and human.","date":"2023","source":"Experimental neurology","url":"https://pubmed.ncbi.nlm.nih.gov/37703949","citation_count":5,"is_preprint":false},{"pmid":"38357846","id":"PMC_38357846","title":"Differential inflammation responses determine the variable phenotypes of epilepsy induced by GABRG2 mutations.","date":"2024","source":"CNS neuroscience & therapeutics","url":"https://pubmed.ncbi.nlm.nih.gov/38357846","citation_count":5,"is_preprint":false},{"pmid":"27889765","id":"PMC_27889765","title":"Contribution of Common Variants in GABRG2, RELN and NRG3 and Interaction Networks to the Risk of Hirschsprung Disease.","date":"2016","source":"Cellular physiology and biochemistry : international journal of experimental cellular physiology, biochemistry, and pharmacology","url":"https://pubmed.ncbi.nlm.nih.gov/27889765","citation_count":5,"is_preprint":false},{"pmid":"37536979","id":"PMC_37536979","title":"Precision medicine: Vinpocetine as a potential treatment for GABRG2-related epilepsy.","date":"2023","source":"Epileptic disorders : international epilepsy journal with videotape","url":"https://pubmed.ncbi.nlm.nih.gov/37536979","citation_count":5,"is_preprint":false},{"pmid":"20098824","id":"PMC_20098824","title":"The GABA(A)-receptor γ2 (GABRG2) gene in obsessive-compulsive disorder.","date":"2009","source":"Revista brasileira de psiquiatria (Sao Paulo, Brazil : 1999)","url":"https://pubmed.ncbi.nlm.nih.gov/20098824","citation_count":5,"is_preprint":false},{"pmid":"35377129","id":"PMC_35377129","title":"Electroacupuncture at PC6 (Neiguan) Attenuates Angina Pectoris in Rats with Myocardial Ischemia-Reperfusion Injury Through Regulating the Alternative Splicing of the Major Inhibitory Neurotransmitter Receptor GABRG2.","date":"2022","source":"Journal of cardiovascular translational research","url":"https://pubmed.ncbi.nlm.nih.gov/35377129","citation_count":5,"is_preprint":false},{"pmid":"34080406","id":"PMC_34080406","title":"Association of rs211037 GABRG2 gene polymorphism with susceptibility to idiopathic generalized epilepsy.","date":"2021","source":"Medicinski glasnik : official publication of the Medical Association of Zenica-Doboj Canton, Bosnia and Herzegovina","url":"https://pubmed.ncbi.nlm.nih.gov/34080406","citation_count":4,"is_preprint":false},{"pmid":"34557020","id":"PMC_34557020","title":"The Effects of Gene Variations of GABRA2, GABRB1, GABRG2, GAD1 and SLC1A3 on Patients with Propofol During Anesthesia Induction.","date":"2021","source":"Pharmacogenomics and personalized medicine","url":"https://pubmed.ncbi.nlm.nih.gov/34557020","citation_count":4,"is_preprint":false},{"pmid":"39052185","id":"PMC_39052185","title":"Repetitive Transcranial Magnetic Stimulation-Mediated Neuroprotection in the 5xFAD Mouse Model of Alzheimer's Disease Through GABRG2 and SNAP25 Modulation.","date":"2024","source":"Molecular neurobiology","url":"https://pubmed.ncbi.nlm.nih.gov/39052185","citation_count":4,"is_preprint":false},{"pmid":"18175077","id":"PMC_18175077","title":"GEFS+ is not related to the most common mutations of SCN1B, SCN1A and GABRG2 in two Tunisian families.","date":"2008","source":"Neurological sciences : official journal of the Italian Neurological Society and of the Italian Society of Clinical Neurophysiology","url":"https://pubmed.ncbi.nlm.nih.gov/18175077","citation_count":4,"is_preprint":false},{"pmid":"40000820","id":"PMC_40000820","title":"Insight into molecular and mutational scrutiny of epilepsy associated gene Gabrg2 leading to novel computer-aided drug designing.","date":"2025","source":"Scientific reports","url":"https://pubmed.ncbi.nlm.nih.gov/40000820","citation_count":3,"is_preprint":false},{"pmid":"41053028","id":"PMC_41053028","title":"A knock-in mouse model for GABRG2-related epileptic encephalopathy displays spontaneous generalized seizures and cognitive impairment.","date":"2025","source":"Cell death discovery","url":"https://pubmed.ncbi.nlm.nih.gov/41053028","citation_count":2,"is_preprint":false},{"pmid":"37632399","id":"PMC_37632399","title":"A novel GABRG2 variant in Sunflower syndrome: A case report and video EEG monitoring.","date":"2023","source":"Epileptic disorders : international epilepsy journal with videotape","url":"https://pubmed.ncbi.nlm.nih.gov/37632399","citation_count":2,"is_preprint":false},{"pmid":"19065515","id":"PMC_19065515","title":"[Analysis of the GABRG2 gene mutation in a Chinese family with generalized epilepsy with febrile seizures plus].","date":"2008","source":"Zhonghua yi xue yi chuan xue za zhi = Zhonghua yixue yichuanxue zazhi = Chinese journal of medical genetics","url":"https://pubmed.ncbi.nlm.nih.gov/19065515","citation_count":2,"is_preprint":false},{"pmid":"29929832","id":"PMC_29929832","title":"Mutational screening of GABRG2 gene in Pakistani population of Punjab with generalized tonic clonic seizures and children with childhood absence epilepsy.","date":"2018","source":"Journal of the Chinese Medical Association : JCMA","url":"https://pubmed.ncbi.nlm.nih.gov/29929832","citation_count":2,"is_preprint":false},{"pmid":"41193790","id":"PMC_41193790","title":"Beyond Impaired GABAergic Signaling: Inflammation and Metabolic Dysfunction in Genetic Epilepsy Induced by GABRG2 Mutation.","date":"2025","source":"Molecular neurobiology","url":"https://pubmed.ncbi.nlm.nih.gov/41193790","citation_count":1,"is_preprint":false},{"pmid":"40849687","id":"PMC_40849687","title":"The Functional Interplay among GAD2, GABRG2, and CACNA1G Genes in Cancers.","date":"2025","source":"Asian Pacific journal of cancer prevention : APJCP","url":"https://pubmed.ncbi.nlm.nih.gov/40849687","citation_count":1,"is_preprint":false},{"pmid":"41146305","id":"PMC_41146305","title":"Association of GABRG2 gene polymorphisms with idiopathic generalized epilepsy in Egyptian children: a case-control study.","date":"2025","source":"European journal of medical research","url":"https://pubmed.ncbi.nlm.nih.gov/41146305","citation_count":1,"is_preprint":false},{"pmid":"11328646","id":"PMC_11328646","title":"Complete genomic sequence of 195 Kb of human DNA containing the gene GABRG2.","date":"2000","source":"DNA sequence : the journal of DNA sequencing and mapping","url":"https://pubmed.ncbi.nlm.nih.gov/11328646","citation_count":1,"is_preprint":false},{"pmid":"38176934","id":"PMC_38176934","title":"Association between GABRG2 Gene Single Nucleotide Polymorphisms and Susceptibility to Ischemic Stroke in a Chinese Population.","date":"2023","source":"Journal of integrative neuroscience","url":"https://pubmed.ncbi.nlm.nih.gov/38176934","citation_count":0,"is_preprint":false},{"pmid":"41351427","id":"PMC_41351427","title":"Early neurological symptoms and epilepsy outcomes in individuals with the recurrent GABRG2 p.(Ala106Thr) gain-of-function variant: Structural and phenotypic insights.","date":"2025","source":"Epilepsia","url":"https://pubmed.ncbi.nlm.nih.gov/41351427","citation_count":0,"is_preprint":false},{"pmid":"36221407","id":"PMC_36221407","title":"The likelihood approach for potential role of \"GABRG2 (C588T, C315T) gene polymorphisms\" on the poor response to carbamazepine therapy in Pakhtun population of Pakistan.","date":"2022","source":"Medicine","url":"https://pubmed.ncbi.nlm.nih.gov/36221407","citation_count":0,"is_preprint":false},{"pmid":"39297975","id":"PMC_39297975","title":"Genetic predisposition of suicidal behavior: variants in GRIN2B, GABRG2, and ODC1 genes in attempted and completed suicide in two Balkan populations.","date":"2024","source":"European archives of psychiatry and clinical neuroscience","url":"https://pubmed.ncbi.nlm.nih.gov/39297975","citation_count":0,"is_preprint":false},{"pmid":"41537003","id":"PMC_41537003","title":"Increased excitability of layer 5 neocortical pyramidal neurons and its contribution to seizure activity in Gabrg2 gene-deficient mice.","date":"2025","source":"iScience","url":"https://pubmed.ncbi.nlm.nih.gov/41537003","citation_count":0,"is_preprint":false},{"pmid":"40811894","id":"PMC_40811894","title":"Phenotypic variation in a family with GABRG2-related epilepsy caused by a novel missense variant.","date":"2025","source":"Seizure","url":"https://pubmed.ncbi.nlm.nih.gov/40811894","citation_count":0,"is_preprint":false},{"pmid":"41031595","id":"PMC_41031595","title":"Mass Spectrometry Imaging Reveals the Distribution of a GABRG2 Targeting Antisense Oligonucleotide and Its Functional Effect in Rat Brain.","date":"2025","source":"ACS chemical neuroscience","url":"https://pubmed.ncbi.nlm.nih.gov/41031595","citation_count":0,"is_preprint":false},{"pmid":null,"id":"bio_10.1101_2025.11.24.690161","title":"Sex and experience dependent regulation of synaptic protein turnover","date":"2025-11-25","source":"bioRxiv","url":"https://doi.org/10.1101/2025.11.24.690161","citation_count":0,"is_preprint":true},{"pmid":null,"id":"bio_10.1101_2024.12.30.24319794","title":"Gene-Burden Meta-Analysis of 748,879 Individuals Identifies LGI1-ADAM23 Protein Complex Association with Epilepsy","date":"2024-12-31","source":"bioRxiv","url":"https://doi.org/10.1101/2024.12.30.24319794","citation_count":0,"is_preprint":true}],"cost":{"stage1":{"model":"claude-sonnet-4-6","input_tokens":51714,"output_tokens":7939,"usd":0.137113,"stage1_stop_reason":"end_turn"},"stage2":{"model":"claude-opus-4-8","input_tokens":17706,"output_tokens":5259,"usd":0.110003,"stage2_stop_reason":"end_turn"},"total_usd":0.247116,"stage1_batch_id":"msgbatch_01AsR7g8dGTEiEw9U83bJeWn","stage2_batch_id":"msgbatch_01YV5ZyxtFNUZEjxRcpd9jzb","note":"batch pricing = 50% of standard"},"stage1_raw":"```json\n{\n  \"discoveries\": [\n    {\n      \"year\": 2009,\n      \"finding\": \"The GABRG2 Q351X (Q390X in full-length protein) nonsense mutation causes dominant-negative suppression of wild-type GABAA receptors in addition to loss-of-function. The mutant γ2(Q351X) subunit is retained in the ER and oligomerizes with wild-type α1 and β2/γ2 subunits, trapping them in the ER and subjecting them to ERAD via the ubiquitin-proteasome system. Pulse-chase experiments showed enhanced degradation of wild-type α1 subunits within 1 h of translation when co-expressed with the mutant subunit.\",\n      \"method\": \"Pulse-chase radiolabeling, co-immunoprecipitation, immunoblotting, patch-clamp electrophysiology in HEK293 cells\",\n      \"journal\": \"The Journal of neuroscience\",\n      \"confidence\": \"High\",\n      \"confidence_rationale\": \"Tier 1–2 / Strong — multiple orthogonal methods (pulse-chase, Co-IP, electrophysiology) in a focused mechanistic study\",\n      \"pmids\": [\"19261880\"],\n      \"is_preprint\": false\n    },\n    {\n      \"year\": 2012,\n      \"finding\": \"The intronic GABRG2 mutation IVS6+2T→G abolishes normal intron 6 splicing, activates a cryptic splice site, generates partial intron 6 retention with a frameshift creating a premature termination codon (PTC). The resultant mutant mRNA is partially degraded by NMD; undegraded mRNA is translated to a stable truncated γ2-PTC subunit containing exons 1–6 plus a novel 29 aa C-terminal tail. This truncated subunit is retained in the ER, does not reach the cell surface, but does oligomerize with α1 and β2 subunits, exerting a dominant-negative effect on αβγ2 receptor assembly.\",\n      \"method\": \"Bacterial artificial chromosome (BAC) constructs expressed in HEK293T cells and transgenic mice; mRNA splicing analysis; NMD assay; surface biotinylation; immunoblotting; co-immunoprecipitation\",\n      \"journal\": \"The Journal of neuroscience\",\n      \"confidence\": \"High\",\n      \"confidence_rationale\": \"Tier 1–2 / Strong — reconstitution in both HEK293T cells and transgenic mice, multiple orthogonal methods\",\n      \"pmids\": [\"22539854\"],\n      \"is_preprint\": false\n    },\n    {\n      \"year\": 2012,\n      \"finding\": \"The GABRG2 Q40X nonsense mutation generates a premature termination codon that activates NMD, degrading the γ2 mRNA. Residual undegraded mRNA is translated to a truncated peptide (likely the signal peptide) that is cleaved further. Mutant γ2(Q40X) subunits fail to assemble into functional receptors, reducing GABA-evoked currents. Gentamicin-induced stop-codon readthrough partially restores full-length γ2 subunit synthesis and surface expression, with rescued subunits incorporating into functional GABAA receptors.\",\n      \"method\": \"BAC minigene NMD assay, immunoblotting, surface biotinylation, whole-cell patch-clamp recording in HEK cells\",\n      \"journal\": \"Neurobiology of disease\",\n      \"confidence\": \"High\",\n      \"confidence_rationale\": \"Tier 1–2 / Strong — in vitro reconstitution with multiple orthogonal methods including electrophysiology and surface biotinylation\",\n      \"pmids\": [\"22750526\"],\n      \"is_preprint\": false\n    },\n    {\n      \"year\": 2013,\n      \"finding\": \"GABRG2 nonsense mutations located outside the last exon activate NMD to varying degrees, producing truncated γ2 subunits with different stabilities, degradation rates, and degrees of polyubiquitin conjugation. The intracellular concentration of trafficking-deficient truncated subunits correlates in a concentration-dependent manner with suppression of wild-type GABAA receptor surface expression, ER stress levels, and epilepsy severity. A last-exon nonsense mutation that does not activate NMD produces a more stable truncated protein associated with more severe dominant-negative suppression.\",\n      \"method\": \"NMD minigene assay, 35S radiolabeling pulse-chase, flow cytometry, immunoblotting, whole-cell recordings, immunohistochemistry in non-neuronal cells and neurons\",\n      \"journal\": \"Annals of neurology\",\n      \"confidence\": \"High\",\n      \"confidence_rationale\": \"Tier 1–2 / Strong — multiple orthogonal methods across multiple mutations in a single systematic study\",\n      \"pmids\": [\"23720301\"],\n      \"is_preprint\": false\n    },\n    {\n      \"year\": 2014,\n      \"finding\": \"Three GABRG2 missense mutations at the γ+/β− subunit interface (R82Q, P83S, N79S) differentially impair GABAA receptor assembly. R82Q and P83S reduce α1β2γ2 receptor surface expression due to impaired pentamer assembly, ER retention, and degradation, while N79S only minimally alters receptor trafficking. Structural modeling predicted increased conformational variability at assembly motifs for R82Q and P83S but not N79S. Lower temperature (30°C) partially rescued surface and total γ2 subunit levels for all three, suggesting these mutations impair protein folding/stability.\",\n      \"method\": \"Flow cytometry, immunoblotting, patch-clamp electrophysiology, structural modeling, temperature-rescue experiment in HEK293T cells\",\n      \"journal\": \"Neurobiology of disease\",\n      \"confidence\": \"High\",\n      \"confidence_rationale\": \"Tier 1–2 / Strong — multiple orthogonal methods (electrophysiology, flow cytometry, structural modeling) across three mutations\",\n      \"pmids\": [\"24798517\"],\n      \"is_preprint\": false\n    },\n    {\n      \"year\": 2014,\n      \"finding\": \"The GABRG2 R177G missense mutation causes ER retention and ERAD of mutant γ2L(R177G) subunits, decreasing GABAA receptor surface expression and GABA-evoked whole-cell currents. With heterozygous expression, wild-type γ2L subunits possess a competitive advantage over mutant subunits for receptor assembly and forward trafficking. Cycloheximide chase showed R177G primarily destabilizes an intracellular pool of unassembled γ2L subunits. Molecular modeling indicated disruption of intrasubunit salt bridges destabilizes secondary/tertiary structure.\",\n      \"method\": \"Electrophysiology, flow cytometry, immunoblotting, cycloheximide chase, molecular modeling in HEK293T cells\",\n      \"journal\": \"Neurobiology of disease\",\n      \"confidence\": \"High\",\n      \"confidence_rationale\": \"Tier 1–2 / Strong — multiple orthogonal methods (electrophysiology, flow cytometry, structural modeling) in a focused study\",\n      \"pmids\": [\"24874541\"],\n      \"is_preprint\": false\n    },\n    {\n      \"year\": 2014,\n      \"finding\": \"GABRG2 R136* premature termination mutation produces a truncated γ2 subunit with reduced cell-surface and total expression. When co-expressed with α1 and β2 subunits in HEK293T cells, GABA-evoked currents were reduced. The truncated subunit accumulated intracellularly in aggregates surrounding the nucleus and ER, indicating compromised receptor trafficking.\",\n      \"method\": \"In vitro expression in HEK293T cells, immunoblotting, flow cytometry, patch-clamp electrophysiology, confocal imaging\",\n      \"journal\": \"Neurobiology of disease\",\n      \"confidence\": \"Medium\",\n      \"confidence_rationale\": \"Tier 2 / Moderate — single lab, multiple orthogonal methods\",\n      \"pmids\": [\"24407264\"],\n      \"is_preprint\": false\n    },\n    {\n      \"year\": 2014,\n      \"finding\": \"The GABRG2 Q40X mutation in Dravet syndrome patients produces a mutant γ2 subunit that, when expressed in HEK cells, inhibits intracellular trafficking of co-expressed GABAA receptor subunits α1 and β2, retaining them in the ER. In neurons, the mutant γ2 subunit also impaired axonal transport of α1 and β2 subunits. Electrophysiological studies confirmed reduced GABA-induced currents with reconstituted mutant receptors.\",\n      \"method\": \"Electrophysiology, immunohistochemistry, microinjection in HEK cells, immunohistochemistry in neurons\",\n      \"journal\": \"Epilepsy research\",\n      \"confidence\": \"Medium\",\n      \"confidence_rationale\": \"Tier 2–3 / Moderate — multiple methods including neuronal experiments, single lab\",\n      \"pmids\": [\"24480790\"],\n      \"is_preprint\": false\n    },\n    {\n      \"year\": 2015,\n      \"finding\": \"In Gabrg2+/Q390X knock-in mice, the mutant γ2(Q390X) subunit accumulates and aggregates intracellularly in neurons, activates caspase 3, and causes widespread age-dependent neurodegeneration beyond impairing inhibitory neurotransmission. This links epilepsy-associated ion channel mutations to neurodegenerative mechanisms via mutant protein accumulation.\",\n      \"method\": \"Gabrg2+/Q390X knock-in mouse model; immunoblotting; immunohistochemistry; caspase 3 activation assay\",\n      \"journal\": \"Nature neuroscience\",\n      \"confidence\": \"High\",\n      \"confidence_rationale\": \"Tier 2 / Strong — in vivo knock-in model with multiple orthogonal mechanistic readouts\",\n      \"pmids\": [\"26005849\"],\n      \"is_preprint\": false\n    },\n    {\n      \"year\": 2016,\n      \"finding\": \"Comparison of Gabrg2+/Q390X knock-in (KI) and Gabrg2+/- knockout (KO) mice showed that the dominant-negative KI mutation causes neuronal accumulation of mutant γ2 subunits, reduced wild-type subunit expression at dendrites and synapses, more severe seizures, and behavioral comorbidities. In contrast, KO mice (simple haploinsufficiency) showed no intracellular accumulation and unaffected biogenesis of remaining wild-type subunits. This establishes that dominant-negative suppression rather than haploinsufficiency drives the severe epileptic encephalopathy phenotype.\",\n      \"method\": \"Immunoblotting, immunohistochemistry, behavioral testing, EEG in knock-in vs. knockout mouse models\",\n      \"journal\": \"Human molecular genetics\",\n      \"confidence\": \"High\",\n      \"confidence_rationale\": \"Tier 2 / Strong — genetic epistasis using two mouse models with multiple orthogonal methods, direct head-to-head comparison\",\n      \"pmids\": [\"27340224\"],\n      \"is_preprint\": false\n    },\n    {\n      \"year\": 2016,\n      \"finding\": \"Multiple de novo GABRG2 missense mutations (A106T, I107T, P282S, R323W, F343L, R323Q) associated with epileptic encephalopathies reduce α1β2γ2L GABAA receptor surface expression with altered subunit stoichiometry and/or decrease GABA-evoked whole-cell current amplitudes when expressed in HEK293T cells, though with different levels of reduction for each mutation.\",\n      \"method\": \"Patch-clamp recording, immunoblotting, confocal imaging, structural modeling in HEK293T cells\",\n      \"journal\": \"Brain\",\n      \"confidence\": \"High\",\n      \"confidence_rationale\": \"Tier 1–2 / Strong — multiple orthogonal methods across six mutations in a systematic study\",\n      \"pmids\": [\"27864268\"],\n      \"is_preprint\": false\n    },\n    {\n      \"year\": 2016,\n      \"finding\": \"Three GABRG2 nonsense mutations (R136*, Q390*, W429*) associated with epilepsies of different severities produce truncated subunits with no to minimal surface expression and differentially reduced GABA-evoked current amplitudes. Structural modeling showed that different truncated subunits adopt different conformations with different surface hydrophobicities and different tendencies to dimerize with wild-type subunit binding partners, correlating with disease severity.\",\n      \"method\": \"Flow cytometry, biochemical assays, lifted whole-cell patch-clamp recording, structural modeling\",\n      \"journal\": \"Scientific reports\",\n      \"confidence\": \"Medium\",\n      \"confidence_rationale\": \"Tier 2 / Moderate — multiple orthogonal methods, single lab\",\n      \"pmids\": [\"27762395\"],\n      \"is_preprint\": false\n    },\n    {\n      \"year\": 2011,\n      \"finding\": \"The GABRG2 K289M mutation (GEFS+ associated) accelerates GABAA receptor deactivation and reduces inhibitory synaptic transmission. Upon temperature elevation, the K289M mutation enhances membrane diffusion of synaptic GABAA receptors via a mechanism dependent on neuronal activity (blocked by glutamate receptor antagonists and mimicked by 4-aminopyridine), causing escape of receptors from synapses and further reduction of GABAergic inhibition. This effect was not observed in neurons expressing wild-type γ2.\",\n      \"method\": \"Single-particle tracking, miniature IPSC recording, confocal imaging in cultured neurons\",\n      \"journal\": \"Cerebral cortex\",\n      \"confidence\": \"Medium\",\n      \"confidence_rationale\": \"Tier 2 / Moderate — single lab with single-particle tracking and electrophysiology, two orthogonal methods\",\n      \"pmids\": [\"21908847\"],\n      \"is_preprint\": false\n    },\n    {\n      \"year\": 2012,\n      \"finding\": \"A GABRG2 frameshift mutation (c.1329delC; γ2S(S443delC)) produces an elongated, modified carboxy-terminus. The mutant subunit is translated as a stable, larger protein that is retained in the ER without surface expression. Co-expression with α1 and β2 in HEK293T cells produced GABA-evoked currents comparable to α1β2 receptors (lacking γ2), demonstrating that the mutant subunit cannot incorporate into functional αβγ2 receptors (haploinsufficiency with possible dominant-negative component).\",\n      \"method\": \"Immunoblotting, flow cytometry, patch-clamp electrophysiology in HEK293T cells\",\n      \"journal\": \"Neurobiology of disease\",\n      \"confidence\": \"Medium\",\n      \"confidence_rationale\": \"Tier 2 / Moderate — multiple orthogonal methods in single lab\",\n      \"pmids\": [\"23069679\"],\n      \"is_preprint\": false\n    },\n    {\n      \"year\": 2019,\n      \"finding\": \"In Gabrg2+/Q390X knock-in mice, impaired GABAergic neurotransmission in the central nucleus of the amygdala (CeA), but not the basolateral amygdala, underlies comorbid anxiety. Reduced GABAA receptor subunit expression in CeA was due to the GABRG2 loss-of-function mutation. Chemogenetic activation or inactivation of inhibitory neurons in CeA modulated anxiety-like behaviors, and pharmacological enhancement of γ2 subunit-containing receptors relieved anxiety.\",\n      \"method\": \"Brain slice recordings, subcellular fractionation, Western blot, immunohistochemistry, confocal microscopy, behavior testing, chemogenetics (DREADDs) in knock-in and knockout mice\",\n      \"journal\": \"Epilepsia\",\n      \"confidence\": \"High\",\n      \"confidence_rationale\": \"Tier 2 / Strong — multiple orthogonal methods including chemogenetic rescue in vivo\",\n      \"pmids\": [\"31087664\"],\n      \"is_preprint\": false\n    },\n    {\n      \"year\": 2020,\n      \"finding\": \"In Gabrg2+/Q390X knock-in mice (but not Gabrg2+/- knockout mice), pro-inflammatory cytokines TNF-α, IL-1β, and IL-6 are elevated in multiple brain regions throughout development. The underlying basis is chronic accumulation of the misfolded mutant γ2(Q390X) subunit protein causing ER stress. Pharmacological induction of ER stress upregulated cytokines in wild-type and KO but not KI mice. Cytokine elevation was independent of seizure occurrence, as it was also observed in cultured neurons.\",\n      \"method\": \"ELISA, immunoprecipitation, nuclei purification, immunoblot, immunohistochemistry, confocal microscopy in knock-in vs. knockout mice and cultured neurons\",\n      \"journal\": \"Epilepsia\",\n      \"confidence\": \"High\",\n      \"confidence_rationale\": \"Tier 2 / Strong — multiple orthogonal methods with appropriate controls (KO comparison, ER stress pharmacology, neuronal cultures)\",\n      \"pmids\": [\"32944937\"],\n      \"is_preprint\": false\n    },\n    {\n      \"year\": 2016,\n      \"finding\": \"In Gabrg2+/Q390X knock-in mice, synaptic GABAA receptors are reduced while intracellular non-functional γ2(Q390X) subunits accumulate in brainstem nuclei associated with respiratory function (nucleus tractus solitarius, pre-Bötzinger complex, Kölliker-Fuse nuclei). This impaired GABAergic transmission in cardiorespiratory brainstem nuclei is proposed as a mechanism for SUDEP in Dravet syndrome/GEFS+.\",\n      \"method\": \"Subcellular fractionation, immunoblotting, immunohistochemistry in knock-in vs. knockout mouse brainstem nuclei\",\n      \"journal\": \"Epilepsy research\",\n      \"confidence\": \"Medium\",\n      \"confidence_rationale\": \"Tier 2 / Moderate — direct fractionation and regional expression analysis in mouse model, single lab\",\n      \"pmids\": [\"27131289\"],\n      \"is_preprint\": false\n    },\n    {\n      \"year\": 2017,\n      \"finding\": \"Crossing Gabrg2+/Q390X knock-in mice with BAC transgenic mice overexpressing wild-type HA-tagged human γ2 subunits increased wild-type γ2, α1, and β2/3 subunit expression, increased mIPSC amplitudes in layer VI cortical neurons, reduced thalamocortical network oscillations, and raised PTZ seizure threshold. This demonstrates that seizures in this dominant-negative GABRG2 epilepsy model can be rescued by overexpression of wild-type γ2 subunits.\",\n      \"method\": \"Western blot, immunohistochemistry, whole-cell patch-clamp recording (mIPSC), thalamocortical slice recording, PTZ seizure threshold testing in mice\",\n      \"journal\": \"Epilepsia\",\n      \"confidence\": \"High\",\n      \"confidence_rationale\": \"Tier 2 / Strong — genetic rescue experiment with multiple orthogonal functional readouts\",\n      \"pmids\": [\"28586508\"],\n      \"is_preprint\": false\n    },\n    {\n      \"year\": 2023,\n      \"finding\": \"4-Phenylbutyrate (PBA) reduces mutant γ2(Q390X) subunit protein aggregates, enhances trafficking of wild-type GABAA receptor subunits to the membrane, increases GABA-evoked current amplitudes in HEK293T cells and neurons bearing the γ2(Q390X) subunit, reduces ER stress caused by the mutant subunit, and mitigates seizures and EEG abnormalities in Gabrg2+/Q390X mice. The mechanism is proteostasis modulation (facilitation of wild-type receptor folding and membrane trafficking) rather than direct channel modulation.\",\n      \"method\": \"Biochemical differential allele tagging, live brain slice surface biotinylation, microsome isolation, patch-clamp recordings, video-EEG in Gabrg2+/Q390X knock-in mice and HEK293T cells\",\n      \"journal\": \"Epilepsia\",\n      \"confidence\": \"High\",\n      \"confidence_rationale\": \"Tier 1–2 / Strong — multiple orthogonal in vitro and in vivo methods including live slice biotinylation and EEG\",\n      \"pmids\": [\"37746768\"],\n      \"is_preprint\": false\n    },\n    {\n      \"year\": 2024,\n      \"finding\": \"The ERAD-associated E3 ubiquitin ligase HRD1 is a modulator of both wild-type and mutant γ2(Q390X) subunit expression. Overexpressing or knocking down HRD1 dose-dependently alters γ2(Q390X) subunit levels. Zonisamide, which upregulates HRD1, partially rescues surface trafficking of GABAA receptors otherwise sequestered in the ER by the dominant-negative γ2(Q390X) subunit, and reduces seizures in Gabrg2+/Q390X mice. ER chaperones BiP and calnexin total expression were unchanged in γ2(Q390X) models.\",\n      \"method\": \"Immunoblotting, overexpression/knockdown in HEK293T cells, seizure monitoring in Gabrg2+/Q390X mice\",\n      \"journal\": \"International journal of molecular sciences\",\n      \"confidence\": \"Medium\",\n      \"confidence_rationale\": \"Tier 2 / Moderate — single lab, multiple biochemical methods with in vivo pharmacological validation\",\n      \"pmids\": [\"38731820\"],\n      \"is_preprint\": false\n    },\n    {\n      \"year\": 2021,\n      \"finding\": \"Neocortex- and hippocampus-specific conditional knockout of Gabrg2 (Cre/loxP system) in heterozygous mice produces temperature-dependent myoclonic jerks, generalized tonic-clonic seizures, increased anxiety, spontaneous seizures, and neuronal loss in cortical layers V-VI and hippocampus, demonstrating that GABRG2 expression specifically in neocortex and hippocampus is required to prevent febrile seizure-like phenotypes.\",\n      \"method\": \"Cre/loxP conditional knockout, cortical EEG, behavioral testing, histology\",\n      \"journal\": \"Cell death & disease\",\n      \"confidence\": \"Medium\",\n      \"confidence_rationale\": \"Tier 2 / Moderate — clean cell-type-specific KO with defined phenotypic readouts, single lab\",\n      \"pmids\": [\"34050134\"],\n      \"is_preprint\": false\n    },\n    {\n      \"year\": 2006,\n      \"finding\": \"A novel GABRG2 mutation associated with febrile seizures alters GABAA receptor current desensitization kinetics and reduces benzodiazepine enhancement of mutant receptors, as demonstrated by electrophysiological studies of recombinant receptors.\",\n      \"method\": \"Electrophysiology of recombinant receptors\",\n      \"journal\": \"Neurology\",\n      \"confidence\": \"Medium\",\n      \"confidence_rationale\": \"Tier 1 / Weak — electrophysiological reconstitution but abstract provides limited detail about the specific mutation and methods\",\n      \"pmids\": [\"16924025\"],\n      \"is_preprint\": false\n    },\n    {\n      \"year\": 2021,\n      \"finding\": \"GABRG2 T90R and P342L de novo variants identified in Dravet syndrome patients primarily cause trafficking defects when expressed in recombinant α1β2γ2 GABAA receptors, in contrast to GABRA1 and GABRB2 Dravet syndrome variants which mainly cause gating defects. This suggests variant-subunit-specific mechanisms even within the same pentameric receptor.\",\n      \"method\": \"Patch-clamp electrophysiology, immunoblotting, confocal imaging in HEK293T cells\",\n      \"journal\": \"Brain communications\",\n      \"confidence\": \"Medium\",\n      \"confidence_rationale\": \"Tier 2 / Moderate — multiple orthogonal methods, single lab, part of a larger study comparing multiple subunits\",\n      \"pmids\": [\"34095830\"],\n      \"is_preprint\": false\n    },\n    {\n      \"year\": 2022,\n      \"finding\": \"Three rare GABRG2 variants (T90M, T317N, Q217X) in sleep-related hypermotor epilepsy patients impair GABAA receptor function by distinct mechanisms: T90M and T317N decrease GABA-evoked currents by impairing surface expression and/or ER retention and channel gating defects, while Q217X reduces synaptic clustering and distribution of GABAA receptors.\",\n      \"method\": \"Electrophysiology, Western blot, flow cytometry, confocal microscopy in neuronal and non-neuronal cells\",\n      \"journal\": \"Journal of neurology\",\n      \"confidence\": \"Medium\",\n      \"confidence_rationale\": \"Tier 2 / Moderate — multiple orthogonal methods, single lab\",\n      \"pmids\": [\"35486215\"],\n      \"is_preprint\": false\n    },\n    {\n      \"year\": 2020,\n      \"finding\": \"In transgenic zebrafish overexpressing GABRG2(F343L), spontaneous seizure-like behaviors occur and can be reduced by suberanilohydroxamic acid (SAHA), a broad HDAC inhibitor. RNA sequencing showed 524 differentially expressed genes including upregulation of 33 protein-processing genes, with protein network analysis identifying HDACs as potential therapeutic targets.\",\n      \"method\": \"Transgenic zebrafish model, automated locomotion tracking, field potential recording, RNA sequencing\",\n      \"journal\": \"Annals of translational medicine\",\n      \"confidence\": \"Medium\",\n      \"confidence_rationale\": \"Tier 2 / Moderate — in vivo zebrafish model with transcriptomic and pharmacological validation, single lab\",\n      \"pmids\": [\"33437759\"],\n      \"is_preprint\": false\n    },\n    {\n      \"year\": 2022,\n      \"finding\": \"Transgenic zebrafish overexpressing GABRG2(F343L) display not only postsynaptic defects (altered GABAA receptor subunit expression) but also presynaptic deficits as revealed by synaptic protein expression analysis and synapse ultrastructure examination, expanding the GABAergic epilepsy paradigm from channelopathy to synaptopathy.\",\n      \"method\": \"Western blot, whole-mount in situ hybridization, synaptic protein expression analysis, electron microscopy for synapse ultrastructure in transgenic zebrafish\",\n      \"journal\": \"Human molecular genetics\",\n      \"confidence\": \"Medium\",\n      \"confidence_rationale\": \"Tier 2 / Moderate — ultrastructural and molecular analysis in vivo zebrafish model, single lab\",\n      \"pmids\": [\"34957497\"],\n      \"is_preprint\": false\n    },\n    {\n      \"year\": 2025,\n      \"finding\": \"Functional characterization of GABRG2 variants reveals both loss-of-function (LoF) and gain-of-function (GoF) mechanisms. Null variants cause milder epilepsy phenotypes (haploinsufficiency), missense LoF variants cause intermediate phenotypes with more frequent DD/ID and psychiatric features, while GoF variants (e.g., A106T) cause severe DEE with early onset at 2 months. Electrophysiological measurements of missense variants in a cohort of 44 individuals (35 variants) confirmed that 9 caused LoF, 3 caused GoF, and 5 did not alter function.\",\n      \"method\": \"Electrophysiological recordings of recombinant receptors, systematic clinical data collection\",\n      \"journal\": \"Neurology\",\n      \"confidence\": \"Medium\",\n      \"confidence_rationale\": \"Tier 2 / Moderate — systematic electrophysiological characterization across 17 missense variants, single study\",\n      \"pmids\": [\"40570274\"],\n      \"is_preprint\": false\n    },\n    {\n      \"year\": 2025,\n      \"finding\": \"The recurrent GABRG2 p.(Ala106Thr) variant confers gain-of-function by facilitating a hydrogen bond between the extracellular and transmembrane domains, as shown by electrophysiological recordings and structural homology modeling. A different variant at the same residue, p.(Ala106Pro), was functionally neutral. This structural mechanism explains the severe DEE associated with this recurrent variant.\",\n      \"method\": \"Electrophysiological recordings, homology-based structural modeling\",\n      \"journal\": \"Epilepsia\",\n      \"confidence\": \"Medium\",\n      \"confidence_rationale\": \"Tier 2 / Moderate — electrophysiology plus structural modeling, comparison of two variants at same residue provides internal control\",\n      \"pmids\": [\"41351427\"],\n      \"is_preprint\": false\n    },\n    {\n      \"year\": 2022,\n      \"finding\": \"Electroacupuncture at PC6 regulates alternative splicing of GABRG2 via the splicing factor NOVA1. Ischemia-reperfusion decreased NOVA1 expression; electroacupuncture rescued NOVA1 levels. In dorsal root ganglion cells, NOVA1 was shown to regulate alternative splicing of GABRG2 specifically on exon 9, which contains an important phosphorylation site.\",\n      \"method\": \"In vivo rat model, EMG recordings, transcriptomic dataset analysis, in vitro DRG cell experiments, RT-PCR\",\n      \"journal\": \"Journal of cardiovascular translational research\",\n      \"confidence\": \"Low\",\n      \"confidence_rationale\": \"Tier 3 / Weak — single lab, limited mechanistic detail in abstract, indirect readout\",\n      \"pmids\": [\"35377129\"],\n      \"is_preprint\": false\n    },\n    {\n      \"year\": 2025,\n      \"finding\": \"In Gabrg2 conditional knockout mice subjected to hyperthermia, ER stress via PERK signaling pathway activation reduces surface expression of GABRG2 on layer 5 pyramidal neurons. This impairs vesicle transport and is associated with increased mEPSC, decreased mIPSC, and reduced dendritic spine density and complexity in L5 pyramidal neurons. ITPR3 and cytosolic GABRG2 protein expression increased while membrane GABRG2 decreased.\",\n      \"method\": \"Patch-clamp electrophysiology (mEPSC, mIPSC), dendritic morphology analysis, Western blot, immunohistochemistry in conditional knockout mice\",\n      \"journal\": \"iScience\",\n      \"confidence\": \"Medium\",\n      \"confidence_rationale\": \"Tier 2 / Moderate — multiple electrophysiological and biochemical methods in conditional knockout mouse model, single lab\",\n      \"pmids\": [\"41537003\"],\n      \"is_preprint\": false\n    }\n  ],\n  \"current_model\": \"GABRG2 encodes the γ2 subunit of GABAA receptors, which is critical for receptor trafficking, synaptic clustering, and chloride channel function; epilepsy-associated mutations reduce surface GABAA receptor expression through mechanisms including NMD-mediated mRNA decay, ER retention and ERAD, dominant-negative trapping of wild-type partnering subunits (α1, β2) in the ER via oligomerization, intracellular aggregation causing ER stress and neurodegeneration, and altered channel gating—with rare gain-of-function mutations also identified—and the severity of the resulting epilepsy syndrome correlates with the extent of functional GABAA receptor reduction and the degree of dominant-negative suppression versus simple haploinsufficiency.\"\n}\n```","stage2_raw":"{\n  \"mechanistic_narrative\": \"GABRG2 encodes the γ2 subunit of the pentameric GABAA receptor, the principal mediator of fast inhibitory neurotransmission, where it is required for assembly, synaptic clustering, and surface trafficking of functional α1β2γ2 chloride channels [#7, #13]. The dominant disease paradigm is that mutant γ2 subunits exert pathogenic effects beyond simple loss of function: nonsense, frameshift, and missense mutations are retained in the ER, fail to reach the surface, and oligomerize with wild-type α1 and β2/γ2 partners to trap them in the ER and target them for ERAD via the ubiquitin-proteasome system, producing dominant-negative suppression of wild-type receptors [#0, #1, #7]. The intracellular concentration of trafficking-deficient truncated subunit scales with the degree of wild-type surface suppression, ER stress, and epilepsy severity, with nonsense mutations escaping NMD (e.g. last-exon variants) producing the most stable and most strongly dominant-negative proteins [#3, #11]. In knock-in mice, the dominant-negative Q390X allele drives intracellular aggregation, caspase-3 activation and age-dependent neurodegeneration, elevation of pro-inflammatory cytokines through ER stress, and severe seizures with comorbid anxiety and respiratory-nucleus dysfunction—phenotypes absent in haploinsufficient knockouts, establishing dominant-negative suppression rather than haploinsufficiency as the driver of severe epileptic encephalopathy [#8, #9, #15, #16]. Missense mutations act through distinct biophysical routes including impaired pentamer assembly and folding (rescuable at lower temperature), altered desensitization and deactivation gating, reduced benzodiazepine modulation, and activity-dependent escape of receptors from synapses, while a subset of recurrent variants (e.g. A106T) confer gain-of-function by stabilizing inter-domain contacts [#4, #12, #21, #26, #27]. The disorder is thus a proteostasis-sensitive channelopathy: enhancing wild-type γ2 expression, promoting mutant folding/trafficking with 4-phenylbutyrate, or upregulating the ERAD E3 ligase HRD1 each restore surface receptors and reduce seizures [#17, #18, #19].\",\n  \"teleology\": [\n    {\n      \"year\": 2006,\n      \"claim\": \"Established that GABRG2 mutations can act through altered channel biophysics rather than expression alone, linking the γ2 subunit to febrile seizures via gating and pharmacology changes.\",\n      \"evidence\": \"Electrophysiology of recombinant receptors carrying a febrile-seizure variant\",\n      \"pmids\": [\"16924025\"],\n      \"confidence\": \"Medium\",\n      \"gaps\": [\"Specific mutation and quantitative kinetics underspecified\", \"No surface-expression or trafficking data\", \"No in vivo confirmation\"]\n    },\n    {\n      \"year\": 2009,\n      \"claim\": \"Resolved how a truncating mutation causes more than haploinsufficiency, showing the mutant γ2 subunit traps wild-type partners in the ER for ERAD—defining the dominant-negative mechanism.\",\n      \"evidence\": \"Pulse-chase, co-IP, and patch-clamp in HEK293 cells for Q351X/Q390X\",\n      \"pmids\": [\"19261880\"],\n      \"confidence\": \"High\",\n      \"gaps\": [\"Did not identify the specific ERAD ubiquitin ligase\", \"In vitro HEK system only at this stage\", \"Quantitative contribution to epilepsy severity not established\"]\n    },\n    {\n      \"year\": 2012,\n      \"claim\": \"Demonstrated that distinct mutation classes (intronic splice, early nonsense) converge on NMD-mediated mRNA decay plus translation of stable trafficking-deficient truncated subunits that still oligomerize dominant-negatively, and that stop-codon readthrough can partially rescue surface expression.\",\n      \"evidence\": \"BAC minigene NMD assays, surface biotinylation, co-IP, electrophysiology, and transgenic mice; gentamicin readthrough for Q40X\",\n      \"pmids\": [\"22539854\", \"22750526\"],\n      \"confidence\": \"High\",\n      \"gaps\": [\"Readthrough efficiency too low for therapeutic relevance\", \"Variable NMD escape across variants not yet systematized\", \"Neuronal consequences not fully resolved\"]\n    },\n    {\n      \"year\": 2013,\n      \"claim\": \"Unified the mutation spectrum by showing that the intracellular concentration of trafficking-deficient truncated subunit determines, in a dose-dependent manner, the degree of wild-type suppression, ER stress, and clinical severity—explaining genotype-phenotype correlation.\",\n      \"evidence\": \"NMD minigene assays, pulse-chase, flow cytometry, electrophysiology, and IHC across multiple nonsense mutations\",\n      \"pmids\": [\"23720301\"],\n      \"confidence\": \"High\",\n      \"gaps\": [\"Correlation established in cells, not in patient brain\", \"Threshold for pathogenicity not quantified in vivo\"]\n    },\n    {\n      \"year\": 2014,\n      \"claim\": \"Defined the structural basis of missense pathogenicity, distinguishing assembly/folding defects at the γ+/β− interface and salt-bridge-disrupting mutations from variants causing intracellular aggregation, and showed wild-type subunits competitively outcompete mutants for assembly.\",\n      \"evidence\": \"Flow cytometry, immunoblotting, electrophysiology, cycloheximide chase, confocal imaging, and structural modeling in HEK293T cells (R82Q/P83S/N79S, R177G, R136*); neuronal axonal transport for Q40X\",\n      \"pmids\": [\"24798517\", \"24874541\", \"24407264\", \"24480790\"],\n      \"confidence\": \"High\",\n      \"gaps\": [\"Temperature/competition rescue not translated in vivo\", \"Aggregate composition uncharacterized\", \"Mechanism of synaptic versus somatic trafficking block incompletely separated\"]\n    },\n    {\n      \"year\": 2015,\n      \"claim\": \"Established in vivo that a dominant-negative allele links an ion-channel mutation to neurodegeneration, showing mutant subunit aggregation activates caspase-3 and causes age-dependent neuronal loss beyond impairing inhibition.\",\n      \"evidence\": \"Gabrg2+/Q390X knock-in mice with immunoblotting, IHC, and caspase-3 assays\",\n      \"pmids\": [\"26005849\"],\n      \"confidence\": \"High\",\n      \"gaps\": [\"Apoptotic pathway upstream of caspase-3 not fully mapped\", \"Cell types most vulnerable not exhaustively defined\"]\n    },\n    {\n      \"year\": 2016,\n      \"claim\": \"Settled the haploinsufficiency-versus-dominant-negative debate by direct knock-in versus knockout comparison, proving intracellular accumulation and reduced wild-type synaptic subunit expression—not loss of one allele—drives severe encephalopathy; also extended pathology to respiratory brainstem nuclei and broadened the missense/nonsense variant catalogue.\",\n      \"evidence\": \"Head-to-head KI vs KO mouse phenotyping (immunoblot, IHC, EEG, behavior, brainstem fractionation); systematic variant characterization in HEK293T cells\",\n      \"pmids\": [\"27340224\", \"27864268\", \"27762395\", \"27131289\"],\n      \"confidence\": \"High\",\n      \"gaps\": [\"SUDEP mechanism inferred from regional expression, not direct cardiorespiratory failure recordings\", \"Stoichiometry changes for some missense variants not fully resolved\"]\n    },\n    {\n      \"year\": 2017,\n      \"claim\": \"Provided proof-of-principle that the dominant-negative deficit is reversible, showing transgenic overexpression of wild-type γ2 restores subunit expression, mIPSCs, and raises seizure threshold in knock-in mice.\",\n      \"evidence\": \"BAC transgenic rescue cross with Western blot, IHC, mIPSC and thalamocortical slice recording, and PTZ seizure testing\",\n      \"pmids\": [\"28586508\"],\n      \"confidence\": \"High\",\n      \"gaps\": [\"Genetic overexpression not directly translatable to therapy\", \"Does not clear pre-existing mutant aggregates\"]\n    },\n    {\n      \"year\": 2019,\n      \"claim\": \"Mapped circuit-level origins of comorbidity, localizing anxiety to impaired GABAergic transmission in the central amygdala and showing chemogenetic and pharmacological manipulation of this inhibition modulates the phenotype.\",\n      \"evidence\": \"Slice recordings, fractionation, IHC, behavior, and DREADD chemogenetics in knock-in/knockout mice\",\n      \"pmids\": [\"31087664\"],\n      \"confidence\": \"High\",\n      \"gaps\": [\"Other comorbidity circuits not mapped\", \"Link between molecular ER pathology and circuit deficit indirect\"]\n    },\n    {\n      \"year\": 2020,\n      \"claim\": \"Connected ER stress from misfolded mutant subunit to neuroinflammation, showing chronic accumulation elevates TNF-α, IL-1β, and IL-6 independently of seizures and specifically in knock-in but not knockout mice.\",\n      \"evidence\": \"ELISA, IP, immunoblot, IHC with ER-stress pharmacology in KI vs KO mice and cultured neurons; zebrafish F343L overexpression as a complementary in vivo model\",\n      \"pmids\": [\"32944937\", \"33437759\"],\n      \"confidence\": \"High\",\n      \"gaps\": [\"Cellular source of cytokines not pinpointed\", \"Causal contribution of inflammation to seizures versus bystander effect unresolved\"]\n    },\n    {\n      \"year\": 2022,\n      \"claim\": \"Refined mechanism heterogeneity, showing GABRG2 Dravet variants are predominantly trafficking-defective (unlike gating-defective GABRA1/GABRB2 variants), that distinct SHE variants act via ER retention, gating, or clustering defects, and extending pathology to presynaptic synaptopathy.\",\n      \"evidence\": \"Electrophysiology, immunoblot, flow cytometry, confocal imaging in HEK293T/neuronal cells; zebrafish ultrastructure and synaptic protein analysis\",\n      \"pmids\": [\"34095830\", \"35486215\", \"34957497\"],\n      \"confidence\": \"Medium\",\n      \"gaps\": [\"Presynaptic deficit mechanism in a postsynaptic-subunit disease unexplained\", \"Single-lab variant cohorts\"]\n    },\n    {\n      \"year\": 2023,\n      \"claim\": \"Validated proteostasis modulation as a therapeutic strategy, showing 4-phenylbutyrate reduces mutant aggregates, restores wild-type trafficking, lowers ER stress, and mitigates seizures—acting on folding rather than the channel itself.\",\n      \"evidence\": \"Differential allele tagging, live-slice surface biotinylation, microsome isolation, patch-clamp, and video-EEG in Gabrg2+/Q390X mice and HEK293T cells\",\n      \"pmids\": [\"37746768\"],\n      \"confidence\": \"High\",\n      \"gaps\": [\"PBA molecular target not defined\", \"Durability and dosing for chronic disease unknown\"]\n    },\n    {\n      \"year\": 2024,\n      \"claim\": \"Identified a specific ERAD effector, HRD1, as a dose-dependent modulator of mutant γ2 levels and showed pharmacological HRD1 upregulation (zonisamide) rescues surface trafficking and reduces seizures.\",\n      \"evidence\": \"Overexpression/knockdown and immunoblotting in HEK293T cells with seizure monitoring in Gabrg2+/Q390X mice\",\n      \"pmids\": [\"38731820\"],\n      \"confidence\": \"Medium\",\n      \"gaps\": [\"Direct HRD1–γ2 ubiquitination not demonstrated biochemically\", \"Zonisamide effect on HRD1 may be indirect\", \"BiP/calnexin unchanged but broader chaperone network unprobed\"]\n    },\n    {\n      \"year\": 2025,\n      \"claim\": \"Established a bidirectional functional spectrum, showing systematic electrophysiology resolves loss-of-function, neutral, and gain-of-function variants, with the recurrent A106T gain-of-function variant explained structurally by a stabilizing inter-domain hydrogen bond; also linked hyperthermia-induced PERK ER stress to reduced surface γ2 and synaptic imbalance.\",\n      \"evidence\": \"Electrophysiology of recombinant receptors with clinical correlation; homology structural modeling; conditional-knockout mouse hyperthermia model with patch-clamp and morphology\",\n      \"pmids\": [\"40570274\", \"41351427\", \"41537003\"],\n      \"confidence\": \"Medium\",\n      \"gaps\": [\"Gain-of-function variants a minority and mechanistically distinct from dominant-negative paradigm\", \"PERK pathway causality vs correlation in temperature sensitivity not fully isolated\"]\n    },\n    {\n      \"year\": null,\n      \"claim\": \"How the proteostasis machinery is wired to γ2 quality control beyond HRD1, and whether trafficking-restoration or anti-inflammatory strategies can be combined for durable seizure and neurodegeneration prevention, remains unresolved.\",\n      \"evidence\": \"\",\n      \"pmids\": [],\n      \"confidence\": \"Medium\",\n      \"gaps\": [\"Full ERAD/chaperone interactome for γ2 undefined\", \"No clinical translation of PBA/zonisamide/readthrough\", \"Mechanistic basis of presynaptic and neuroinflammatory contributions incompletely linked to molecular pathology\"]\n    }\n  ],\n  \"mechanism_profile\": {\n    \"molecular_activity\": [\n      {\"term_id\": \"GO:0005215\", \"supporting_discovery_ids\": [0, 2, 7, 13]},\n      {\"term_id\": \"GO:0005198\", \"supporting_discovery_ids\": [0, 4, 13]},\n      {\"term_id\": \"GO:0060089\", \"supporting_discovery_ids\": [12, 21, 26]}\n    ],\n    \"localization\": [\n      {\"term_id\": \"GO:0005886\", \"supporting_discovery_ids\": [1, 2, 12, 13]},\n      {\"term_id\": \"GO:0005783\", \"supporting_discovery_ids\": [0, 1, 4, 5, 6, 7]},\n      {\"term_id\": \"GO:0005634\", \"supporting_discovery_ids\": [6]}\n    ],\n    \"pathway\": [\n      {\"term_id\": \"R-HSA-112316\", \"supporting_discovery_ids\": [12, 17, 20]},\n      {\"term_id\": \"R-HSA-8953897\", \"supporting_discovery_ids\": [15, 29]},\n      {\"term_id\": \"R-HSA-392499\", \"supporting_discovery_ids\": [0, 1, 19]}\n    ],\n    \"complexes\": [\n      \"GABAA receptor (α1β2γ2 pentamer)\"\n    ],\n    \"partners\": [\n      \"GABRA1\",\n      \"GABRB2\",\n      \"HRD1\"\n    ],\n    \"other_free_text\": []\n  }\n}","audit_flag":null,"evaluation":{"pairwise":"win","faith_supported":6,"faith_total":6,"faith_pct":100.0}}