GIGYF1 disruption associates with autism and impaired IGF-1R signaling

Abstract

Autism spectrum disorder (ASD) represents a group of neurodevelopmental phenotypes with a strong genetic component. An excess of likely gene-disruptive (LGD) mutations in GIGYF1 was implicated in ASD. Here, we report that GIGYF1 is the second-most mutated gene among known ASD high-confidence risk genes. We investigated the inheritance of 46 GIGYF1 LGD variants, including the highly recurrent mutation c.333del:p.L111Rfs*234. Inherited GIGYF1 heterozygous LGD variants were 1.8 times more common than de novo mutations. Among individuals with ASD, cognitive impairments were less likely in those with GIGYF1 LGD variants relative to those with other high-confidence gene mutations. Using a Gigyf1 conditional KO mouse model, we showed that haploinsufficiency in the developing brain led to social impairments without significant cognitive impairments. In contrast, homozygous mice showed more severe social disability as well as cognitive impairments. Gigyf1 deficiency in mice led to a reduction in the number of upper-layer cortical neurons, accompanied by a decrease in proliferation and increase in differentiation of neural progenitor cells. We showed that GIGYF1 regulated the recycling of IGF-1R to the cell surface. KO of GIGYF1 led to a decreased level of IGF-1R on the cell surface, disrupting the IGF-1R/ERK signaling pathway. In summary, our findings show that GIGYF1 is a regulator of IGF-1R recycling. Haploinsufficiency of GIGYF1 was associated with autistic behavior, likely through interference with IGF-1R/ERK signaling pathway.

Keywords: Genetics; Molecular genetics; Neurodevelopment; Neurological disorders; Neuroscience.

Figure 1. Pattern, distribution, and inheritance of GIGYF1 heterozygous LGD mutations in humans.

(A) Mutation pattern of GIGYF1 likely gene-disruptive variants (LGD variants) identified in SPARK and/or SSC cohorts (above) and through GeneMatcher (below) on a gene model. (B) Ranked mutation frequency of LGD variants in 102 high-confidence genes identified in Satterstrom et al. (7). (C) Pedigrees with the recurrent variant p.L111Rfs*234 identified in the SPARK and SSC cohorts. +/+, WT; +/–, heterozygous. Families with untransmitted or de novo GIGFY1 LGD variants only in unaffected family members are indicated by the square outline. Solid circles or squares represent individuals with an ASD diagnosis. Numbers above each pedigree are SPARK family designations; red +/- indicate individuals with mutations. (D) The recurrent LGD locus p.L111Rfs*234 shows abnormal localization in mouse primary-cultured neurons. The WT plasmid is mainly located in the cytoplasm; however, the mutant plasmid is exclusively located in the nuclei. Scale bars: 10 μm, 2 μm for zoom image.

Figure 2. Phenotypic correlation of GIGYF1 heterozygous LGD mutations.

(A) Comparison of the SCQ and RBS-R scores in children with ASD with GIGYF1 LGD variants and all children with ASD in SPARK. (B) Comparison of cognitive impairment (CI) occurrence rate among children with ASD with GIGYF1 LGD variants, children with ASD with LGD variants in known high-confidence genes, and all SPARK children with ASD. (C) Comparison of the frequency of behavior problems, developmental delays, and neuropsychiatric problems between children with ASD with and without GIGYF1 LGD variants. The details of specific phenotype items for each phenotype group in the plot are described in Supplemental Table 9. (D) Comparison of developmental delay occurrence rate among children without ASD with GIGYF1 LGD variants and all children without ASD in SPARK. (E) Down sampling analysis of SRS t score in siblings without ASD from the SSC cohort. (F) Comparison of the frequency of behavior problems, developmental delay, and neuropsychiatric problems between nonASD parents with and without GIGYF1 LGD variants. The details of specific phenotype items for each phenotype group in the plot are described in Supplemental Table 9.

Figure 3. KO and haploinsufficiency of Gigyf1 in the developing mouse brain results in autism-like behaviors.

(A) Three-chamber test. The time spent with object (O), stranger 1 (S1) and stranger 2 (S2) was compared. The preference indexes were compared. n = 21 (Gigyf1^fl/fl), 19 (cHET), 20 (cKO). Statistical data were analyzed using 1-way ANOVA and 2-tailed Student’s t test. (B) Marble burying test. The percentage of marbles buried by each mouse was compared. Statistical data were analyzed using 1-way ANOVA. (C) Digging, rearing, and grooming test. The numbers of digging, rearing, and grooming incidences of the different groups of mice were compared. n = 20 (Gigyf1^fl/fl), 19 (cHET), 19 (cKO). Statistical data were analyzed using 1-way ANOVA. (D) Elevated plus-maze test. The time and the total distance in open and closed arms were compared. n = 19 (Gigyf1^fl/fl), 19 (cHET), 20 (cKO). Statistical data were analyzed using 1-way ANOVA. (E) Open field test. The total distance and center duration were compared. n = 21 (Gigyf1^fl/fl), 19 (cHET), 19 (cKO). Statistical data were analyzed using 1-way ANOVA. (F) Light-dark box test. The preference indexes to dark box were compared. n = 19 (Gigyf1^fl/fl), 19 (cHET), 20 (cKO). Statistical data were analyzed using 1-way ANOVA. (G) Morris water maze test. The escape latency in the learning phase, the number of exact crossings over the previously hidden platform in the probe phase, the swim speed, and the time and distance in the target quadrant in the probe phase were compared. n = 22 (Gigyf1^fl/fl), 19 (cHET), 20 (cKO). Statistical data were analyzed using 1-way and 2-way ANOVA. (H) Novel-object recognition test. Total exploration time and discrimination index were compared. n = 20 (Gigyf1^fl/fl), 18 (cHET), 19 (cKO). Statistical data were analyzed using 1-way ANOVA and 2-tailed Student’s t test. All data are represented as mean ± SEM. *P < 0.05, **P < 0.01, ***P < 0.001, ****P < 0.0001. cHET, Gigyf1^f/w-CreNestin; cKO,Gigyf1^fl/fl-CreNestin.

Figure 4. Gigyf1 disruption in the developing brain disturbs neurogenesis.

(A) Quantitative comparison of brain weight, cortical anterior-dorsal (A-D) length, anterior-posterior (A-P) length, and area in Gigyf1^fl/fl (n = 11), cHET (n = 10), and cKO (n = 6) mice at P2. (B) Littermate cortices stained with Satb2 from Gigyf1^fl/fl (n = 4), cHET (n = 4), and cKO (n = 3) mice at E18.5. Satb2⁺ cells per 100 μm of apical surface in L2–L4 were compared. (C) Littermate cortices stained with Brn2 from Gigyf1^fl/fl (n = 4), cHET (n = 4), and cKO (n = 3) mice at E18.5. Brn2⁺ cells per 100 μm of apical surface in L2–L4 were compared. (D) Littermate cortices stained with Tbr1 and Ctip2 from Gigyf1^fl/fl (n = 4), cHET (n = 4), and cKO (n = 3) mice at E18.5. Ctip2⁺ cells and Tbr1⁺ cells per 100 μm in L5 and L6 were compared. (E) Comparison of Pax6⁺ RGC (VZ) and Tbr2⁺ IPC (SVZ) populations per 100 μm of apical surface in Gigyf1^fl/fl (n = 3), cHET (n = 3), and cKO (n = 3) mice at E14.5. (F) Comparison of Edu⁺ (SVZ) population, Ph3⁺ and Pax6⁺Ph3⁺ (VZ) population, Pax6⁺Edu⁺/Pax6⁺ proportion of apical surface from Gigyf1^fl/fl (n = 3), cHET (n = 3), and cKO (n = 3) mice at E14.5. (G) Ki67 and Edu antibodies after 24 hour Edu pulse at E13.5. All cells that exited the cell cycles (Edu⁺/Ki 67^–) were counted. The percentage of total Edu⁺ cells evaluated 24 hours after injection was analyzed. (H) S phase sequential labeling analysis of NPCs. EdU-Brdu double-stained cortical sections at E14.5 are shown. S phase durations were calculated (Ts=Ti/(Lcells/Scells)) and compared. All statistics were performed by 1-way ANOVA. Scale bars represent 50 μm. All data are represented as mean ± SEM. *P < 0.05, **P < 0.01, ***P < 0.001, ****P < 0.0001.

Figure 5. GIGYF1 KO disrupts IGF-1R/ERK pathway by regulation of IGF-1R recycling.

(A) Coimmunoprecipitation assay for GIGYF1 and IGF-1R in HEK293T cells. (B) Double immunofluorescence of GIGYF1 and IGF-1R in HeLa cells. Scale bars: 10 μm. Inset scale bars: 5 μm. (C) Immunoblots of the whole cell lysate showing levels of pIGF-1R, IGF-1R, pERK1/2, ERK1/2, pAkt, and Akt at different duration of IGF-1 stimulation. Statistical data were analyzed using 2-way ANOVA. (D) Immunoblots of the whole-cell lysates showing levels of pERK1/2, ERK1/2 in HEK293T GIGYF1 KO cells expressing mock empty vector (pCAGGS-IRES-GFP) or HA-GIGYF1. The relative levels of pERK1/2 to ERK1/2 were quantified by densitometry and analyzed using 2-way ANOVA. (E) Immunoblot of pERK1/2 and ERK1/2 in the whole-cell lysates at 7 minutes of IGF-1 stimulation. Statistic data were analyzed using 1-way ANOVA. (F) Immunoblots of biotin-labelled IGF-1R, total IGF-1R and TMEM98. Total IGF-1R-α levels of unbiotinylated cells were determined. The protein levels of surface IGF-1R, surface IGF-1R/total IGF-1R, and total IGF-1R were quantified by densitometry from 3 biological replicates. Statistical data were analyzed using 2-tailed Student’s t tests. (G) Immunoblots of biotin-labeled IGF-1R and total IGF-1R at different conditions in a surface biotinylation recycling assay. GIGYF1 KO HEK293T cells and control HEK293T cells (lanes 2–8) were surface labeled with sulfo-NHS-S-S-biotin. Cells (lanes 3–8) were incubated to endocytosis. The remaining surface biotin was cleaved with glutathione cleavage buffer (lanes 2–8). Cells were incubated for a second time to recycle (lanes 4–5 and 7–8), then the surface biotin was stripped for a second time (lanes 3–4 and 6–7). Lanes 5 and 8 were incubated to recycle without a second cleavage. The stage of biotinylation recycling assay for each lysate is indicated with + and –. (H) Working model of GIGYF1 regulation of IGF-1R/ERK pathway. All data are represented as mean ± SEM. *P < 0.05, **P < 0.01, ***P < 0.001, ****P < 0.0001. See complete unedited blots in the supplemental material.

Figure 6. Dysregulation of IGF-1R/ERK signaling in Gigyf1 deficiency mice.

(A) Immunoblots of pIgf-1r, Igf-1r, pErk1/2, Erk1/2, p27, cyclin D1, and Gigyf1 in lysates from brain cortical tissue of Gigyf1^fl/fl, cHET and cKO mice at E14.5. The relative levels of pIgf-1r/total Igf-1r, pErk-1r/total Erk, p27, and cyclin D1 were quantified by densitometry and compared using 1-way ANOVA. (B) Neurosphere formation assay. Neural progenitor cells are derived from Gigyf1^fl/fl, cHET and cKO embryos. Representative images of Gigyf1^fl/fl, cHET and cKO neurosphere are shown. Scale bar: 10 μm. (C) The diameters of Gigyf1^fl/fl, cHET, and cKO neurospheres were calculated and compared. Experiments were performed for 3 trials and the statistics are based on the average of each condition from different trials. Statistical data are analyzed using 1-way ANOVA and 2-tailed t test. All data are represented as mean ± SEM. *P < 0.05, **P < 0.01, ***P < 0.001, ****P < 0.0001.