Elevated levels of FMRP-target MAP1B impair human and mouse neuronal development and mouse social behaviors via autophagy pathway

Abstract

Fragile X messenger ribonucleoprotein 1 protein (FMRP) binds many mRNA targets in the brain. The contribution of these targets to fragile X syndrome (FXS) and related autism spectrum disorder (ASD) remains unclear. Here, we show that FMRP deficiency leads to elevated microtubule-associated protein 1B (MAP1B) in developing human and non-human primate cortical neurons. Targeted MAP1B gene activation in healthy human neurons or MAP1B gene triplication in ASD patient-derived neurons inhibit morphological and physiological maturation. Activation of Map1b in adult male mouse prefrontal cortex excitatory neurons impairs social behaviors. We show that elevated MAP1B sequesters components of autophagy and reduces autophagosome formation. Both MAP1B knockdown and autophagy activation rescue deficits of both ASD and FXS patients' neurons and FMRP-deficient neurons in ex vivo human brain tissue. Our study demonstrates conserved FMRP regulation of MAP1B in primate neurons and establishes a causal link between MAP1B elevation and deficits of FXS and ASD.

Fig. 1. Elevated MAP1B level leads to impaired dendritic development and altered electrophysiology of human neurons.

a Experimental scheme for assessing MAP1B levels in ex vivo human cortical slices with FMRP knockdown (shFMR1). CP cortical plate, SP sub plate, IZ intermediate zone, SVZ subventricular zone, VZ ventricular zone, LV lentivirus, shRNA small hairpin RNA, DIV days in vitro. b Representative confocal images of neurons expressing shRNA-mCherry (red), MAP1B (white) in lentivirus-infected cortical slices. Scale bars: 20 μm. c MAP1B intensity in mCherry+ neurons in human cortical slices. Two-tailed, unpaired Student’s t-test, p = 0.0058. N = 3 individual cortices. d Experimental strategy for targeted activation of endogenous MAP1B gene expression using an inducible idCas9A-H9 ESC line. DOX Doxycycline. e Representative confocal images (from three independent experiments) and traces of GFP+/mCherry+ neurons. Scale bar, 10 μm. f Sholl analysis of MAP1B-EE (LV-sgMAP1B) and control (LV-sgCtrl) neuron. MANOVA, F _(1,141) = 13.990, p < 0.001. Ctrl: n = 73 neurons, MAP1B-EE: n = 70 neurons from three differentiations, N = 1. g Total dendritic length. Two-tailed, unpaired Student’s t-test, p < 0.0001. Ctrl: n = 73 neurons, MAP1B-EE: n = 70 neurons from three differentiations, N = 1. h Representative raster plots showing 120 s of activity of neurons. Black lines are spikes and blue lines are bursts. i, j Quantifications of neuronal mean firing rate, p = 0.0295 (i) and number of bursts, p = 0.0087 (j) recorded by MEA. Two-tailed, unpaired Student’s t-test. Ctrl: n = 42 individual wells, MAP1B-EE: n = 38 individual wells from three differentiations, N = 1. k Representative traces showing current injection-evoked action potentials recorded from GFP+/mCherry+ neurons. l Quantification of the rheobase current threshold of neurons. Two-tailed, unpaired Student’s t-test, p = 0.0087. Ctrl: n = 9 neurons, MAP1B-EE: n = 10 neurons from at least five differentiations, N = 1. m Representative traces of mEPSC recorded from GFP+/mCherry+ neurons. n, o Cumulative probability of inter-event intervals and amplitudes of mEPSCs. Two-sided, Mann–Whitney Rank Sum test, p < 0.0001. (Inset: mean mEPSC frequency, p = 0.0221 and amplitude, p < 0.0001. Two-sided, unpaired Student’s t-test). n = 30 neurons from five differentiations, N = 1. Error bars: mean ± s.e.m. Source data are provided as a Source Data file.

Fig. 2. 5q13.2trip ASD patient iPSC-derived neurons exhibit morphological and physiological deficits.

a A schematics showing 5q13.2 triplication in the ASD patient. Blue boxes: genes affected. b mRNA levels in fibroblasts of the ASD patient and his mother (Ctrl). Two-tailed, unpaired Student’s t-test. MAP1B: p < 0.0001; MRP27: p < 0.0001; PTCD2: p = 0.0002; ZNF366: p = 0.0016. n = 3 technical replicates, N = 1. c Experimental scheme for analyzing ASD patient neurons. d Western blot analysis of MAP1B levels. GAPDH: loading control. One-way ANOVA with Dunnett post hoc tests, p = 0.0284. e Representative confocal images (from three independent experiments) and Neurolucida traces of GFP+ neurons. Scale bar, 10 μm. f Sholl analysis of ASD patient neurons with (shMAP1B) or without (shNC) MAP1B knockdown. MANOVA, F _(1,140) = 12.001, p < 0.001. g Total dendritic length. Two-tailed, unpaired Student’s t-test, p < 0.0001. For (f) and (g), shNC: n = 70 neurons, shMAP1B: n = 72 neurons from three differentiations, N = 1. h Representative raster plots. i Neuronal mean firing rate. Two-tailed, unpaired Student’s t-test, p < 0.0001. Ctrl: n = 38 wells, MAP1B-EE: n = 25 wells from 3 differentiations, N = 1. j Number of bursts. Two-tailed, unpaired Student’s t-test, p = 0.0010. Only the wells with bursting activity were analyzed for burst-related parameters, shNC: n = 23 wells, shMAP1B: n = 20 wells from three differentiations, N = 1. k Representative traces showing current injection-evoked action potentials. l Rheobase current threshold. Two-tailed, unpaired Student’s t-test, p = 0.0160. shNC: n = 6 neurons, shMAP1B: n = 6 neurons from at least four differentiations, N = 1. m Representative traces of mEPSCs. n, o Cumulative probability of interevent intervals and amplitudes of mEPSCs. Two-sided, Mann–Whitney Rank Sum test, p < 0.0001. (Inset: mean mEPSC frequency, p = 0.0472 and amplitude, p < 0.0001. Two-sided, unpaired Student’s t-test). shNC: n = 30 neurons, shMAP1B: n = 28 neurons from three differentiations, N = 1. Error bars reflect mean ± s.e.m. Source data are provided as a Source Data file.

Fig. 3. Elevated MAP1B level leads to autism-like behaviors.

a Population gene expression levels of MAP1B transcripts in the dorsal lateral prefrontal cortical region (BA9) among several psychiatric disorders and healthy controls collected by PsychENCODE Consortium. Y-axis: Gene expression value of MAP1B mRNA (RNA-seq TPM). ASD autism spectrum disorder (n = 31). BPD bipolar disorder (N = 172). SCZ schizophrenia (N = 497). CTR, health (N = 1166). The gene expression levels of MAP1B in ASD are significantly higher than others by one-side t-test. p < 8.66e-7 for CTR, p < 1.42e-3 for SCZ, and p < 4.83e-8 for BPD. b Experimental strategy for assessing cognitive functions of targeted Map1b gene activation in CAMK2A-expressing excitatory neurons in the PFC of mice. Activation of endogenous Map1b gene in the PFC was achieved through stereotaxic injection of AAV expressing Map1b-targeting guide RNA (AAV8-sgMap1b-hSyn1-flex-mCherry) and AAV expressing Cre driven by Camk2a promoter (AAV9-pCamK2a-GFP-Cre) into the medial PFC of dCas9Activator mice. c Representative confocal images of neurons in the prefrontal cortex (PFC) expressing GFP-Cre (green), sgRNA-mCherry (red), MAP1B (white) in AAV-injected dCas9Activator mice, assessed after behavioral tests. Scale bars: 10 μm. d Quantification of MAP1B intensity in GFP+/mCherry+ neurons in mPFC. Two-tailed, unpaired Student’s t-test, p = 0.0045. N = 4 individual mice. e Experimental scheme of testing social interest (SI) and social novelty (SN). f, g MAP1B-EE mice exhibited reduced social interest (SI, f), p = 0.0195 and social recognition (SN, g), p = 0.0090. Two-tailed, unpaired Student’s t-test. sgCtrl: N = 8 mice, sgMap1b: N = 7 mice. Data are presented as box plot in (a) (center line, median; box limits, upper and lower quartiles; whiskers, min to max). Data are presented as mean ± s.e.m in other panels. Source data are provided as a Source Data file.

Fig. 4. Elevated MAP1B level leads to autophagy deficits in mouse neurons.

a Experimental scheme for assessing the autophagy in MAP1B-EE neurons. Hippocampal neurons were isolated from dCas9Activator mice and infected with LV-Cre-GFP and LV-sgRNA-mCherry. b Representative confocal images of neurons infected with either sgMap1b (MAP1B-EE) or sgCtrl (Control) expressing Cre-GFP (green), sgRNA-mCherry (red), LC3 (white). Scale bars, 10 μm. c LC3 intensity. Two-tailed, unpaired Student’s t-test with unequal variances, p = 0.0476. Ctrl: N = 3 independent biological replicates. d Sample Western blot analysis of mouse neurons with MAP1B-EE (LV-sgMap1b infected) and controls (sgCtrl). e Quantitative analysis of LC3-I: p = 0.1597; LC3-II: p = 0.0297; LC3-II/I (LC3-II/LC3-I): p = 0.0434; two-tailed, unpaired Student’s t-test with unequal variances. f Sample Western blot analysis of hippocampal neurons with MAP1B-EE and controls treated with BafA1 or vehicle. g Quantitative analysis of proteins treated with BafA1 before harvest. LC3I: p = 0.1359; LC3-II: p = 0.0049; LC3-II/I: p = 0.0107; two-tailed, unpaired Student’s t-test with unequal variances. For (e) and (g), protein amounts were normalized to GAPDH and subsequently normalized to control cells. N = 3 biological replicates. h, i Experimental scheme for assessing autophagy flux. Hippocampal neurons from dCas9Activator mice were transfected with an autophagy reporter (CAG-mCherry/GFP/LC3-IRES-Cre) together with either sgCtrl or sgMap1b. j Representative confocal images of autophagy reporter-transfected cells showing autophagosomes (yellow puncta) and autophagolysosomes (red puncta) in neurons. Scale bars, 10 μm. k–n Number of total puncta, p = 0.0038 (k), autophagosomes, p = 0.0188 (l), and autophagolysosomes, p = 0.0035 (m), and calculated ratio of autophagolysosomes over total puncta, p = 0.3070 (n). Quantification of puncta was done after 3D reconstruction, two-tailed, unpaired Student’s t-test was used. N = 3 biological replicates. o Representative confocal images of p62 (white) puncta localized in hippocampal neurons. Scale bars, 10 μm. p Quantification of p62 puncta was done after 3D reconstruction. Two-tailed, unpaired Student’s t-test, p = 0.0026. N = 3 biological replicates. All data are presented as mean ± s.e.m. Source data are provided as a Source Data file.

Fig. 5. Elevated MAP1B leads to autophagy deficits in human and macaque neurons.

a, b Analysis of LC3 intensity of human neurons with MAP1B-EE. Representative confocal images of human neurons (a) stained with dCas9-GFP (green), sgRNA-mCherry (red), and LC3 (white). Scale bars, 10 μm. b Two-tailed, unpaired Student’s t-test, p = 0.0155. n = 3 independent neuronal differentiations, N = 1. c Representative confocal images of neurons in ex vivo human cortical slices infected with LV-shRNA-mCherry (red) and stained with DAPI (blue) and LC3 (white). Scale bars: 20 μm. d Quantification of LC3 intensity in mCherry+ neurons in human cortical slices. Two-tailed, unpaired Student’s t-test, p < 0.0001. N = 3 individual cortices. e Representative confocal images of neurons in the rhesus macaque cortex expressing shRNA-mCherry (red), LC3 (white) in lentivirus-infected ex vivo macaque cortical slices. Scale bars: 20 μm. f Quantification of LC3 intensity in mCherry+ neurons in macaque cortical slices. Two-tailed, unpaired Student’s t-test, p = 0.0238. N = 3 individual cortices. g, h Analysis of LC3 intensity of 5q13.2trip ASD neurons with or without MAP1B knockdown. Representative confocal images (g) of neurons stained with DAPI (blue), shRNA-GFP (green) and LC3 (red). Scale bars, 10 μm. h Two-tailed, unpaired Student’s t-test, p = 0.0434. n = 3 independent neuronal differentiation, N = 1. Data are presented as mean ± s.e.m. Source data are provided as a Source Data file.

Fig. 6. Elevated MAP1B sequesters LC3 and prevents its lipidation in neurons.

a A schematic model showing that MAP1B-EE sequesters LC3-I and prevents its lipidation in neurons, leading to autophagy deficits. b Western blot analysis of HEK293T cells co-transfected with GFP-LC3, dCas9 Activator system, and either sgCtrl or sgMAP1B. MAP1B or ATG proteins interacted with GFP-LC3 were pulled down using an anti-GFP antibody and immunoprecipitation (IP) followed by detection using antibodies against MAP1B, and ATG7. Input, 1% of the total lysate. The samples derive from the same experiment and the gels/blots were processed in parallel. For quantification shown in c and d, protein amounts were normalized to GFP-LC3 and subsequently compared to control cells. c Quantitative analysis of MAP1B. Two-tailed unpaired Student’s t-test with unequal variances, p = 0.0104; n = 3 biologically independent transfections, N = 1. d Quantitative analysis of ATG7. Two-tailed unpaired Student’s t-test with unequal variances, p = 0.0008. n = 3 biologically independent transfections, N = 1. e Proximal Ligation Assay (PLA) analysis showing increased interaction between MAP1B and LC3 in MAP1B-EE mouse primary hippocampal neurons. The PLA signal (red) indicates close proximity of the antigens. Scale bar, 10 μm. f Quantification of PLA puncta showing MAP1B and LC3 interaction. p = 0.0134. Ctrl: N = 3 biological replicates. g PLA analysis showing reduced interaction between LC3 and ATG7 in MAP1B-EE mouse primary hippocampal neurons. Scale bar, 10 μm. h Quantification of PLA puncta showing LC3 and ATG7 interaction. p = 0.0034. N = 3 biological replicates. Quantifications in (f) and (h) were performed after 3D reconstruction and subsequently compared to control cells, two-tailed unpaired Student’s t-tests with unequal variances were used. All data are presented as mean ± s.e.m. Source data are provided as a Source Data file.

Fig. 7. Activation of autophagy rescues MAP1B-EE-induced neuronal deficits in human neurons.

a, b Experimental scheme (a) and representative confocal images (from three independent experiments) and traces of GFP+ neurons (b) for assessing the effect of rapamycin (Rap) on 5q13.2trip ASD neurons. Scale bar, 10 μm. c Sholl analysis of ASD patient neurons treated with DMSO (Vehicle, Veh) or rapamycin (Rap, 300 nM). MANOVA, F _(1,58) = 27.747, p < 0.001. n = 30 cells from three independent neuronal differentiations, N = 1. d Total dendritic length. Two-tailed, unpaired Student’s t-test, p < 0.0001. n = 30 neurons from three independent neuronal differentiations, N = 1. e, f Experimental scheme (e) and representative raster plots (f) for accessing the electrophysiology of ASD patient neurons treated with rapamycin. g Quantifications of neuronal mean firing rate. Two-tailed, unpaired Student’s t-test, p = 0.0081. ASD Veh: n = 34 individual wells, ASD Rap: n = 17 individual wells from three individual neuronal differentiations, N = 1. h Number of bursts. Two-tailed, unpaired Student’s t-test, p = 0.3723. Only the wells with bursting activity were analyzed for burst-related parameters, ASD Veh: n = 26 individual wells; ASD Rap: n = 14 individual wells from three independent neuronal differentiations, N = 1. i Representative traces showing current injection-evoked action potentials recorded from patient neurons with or without rapamycin treatment. j Rheobase current threshold of ASD neurons with rapamycin treatment. Two-tailed, unpaired Student’s t-test, p = 0.0050. ASD Veh: n = 4 neurons, ASD Rap: n = 4 neurons from three independent neuronal differentiations, N = 1. k Representative traces of mEPSCs recorded from patient neurons with or without rapamycin treatment. l, m Cumulative probability of inter-event intervals and amplitudes of mEPSCs. Mann–Whitney Rank Sum test, p < 0.0001. (Inset: mean mEPSC frequency, p = 0.0229 and amplitude, p < 0.0001. Two-sided, unpaired Student’s t-test). ASD Veh: n = 27 neurons, ASD Rap: n = 23 neurons from three independent neuronal differentiations, N = 1. All error bars reflect mean ± s.e.m. Source data are provided as a Source Data file.

Fig. 8. Activation of autophagy rescues FMRP deficiency-induced neuronal deficits.

a Sholl analysis of FXS2 neurons with MAP1B knockdown. F _(1,63) = 20.697, p < 0.001, shNC n = 30 neurons, shMAP1B n = 35 neurons from three independent neuronal differentiations, N = 1. b Quantification of total dendritic length. Two-tailed, unpaired Student’s t-test, p < 0.0001, shNC n = 30 neurons, shMAP1B n = 35 neurons from three independent neuronal differentiations, N = 1. c Neuronal mean firing rate. Two-tailed, unpaired Student’s t-test, p = 0.0032. Ctrl2: n = 10 individual wells, FXS2: n = 24 individual wells from three independent neuronal differentiations, N = 1. d Mean firing rate in FXS2 neurons with MAP1B knockdown or rapamycin treatment. One-way ANOVA with Dunnett post hoc tests, shNC+Veh vs. shMAP1B+Veh: p = 0.0165; shNC+Veh vs. shNC+Rap: p = 0.0027. shNC Veh: n = 24 individual wells, shMAP1B Veh: n = 24 individual wells, shNC Rap: n = 22 wells from three independent neuronal differentiations, N = 1. e Representative confocal images of neurons expressing shRNA-mCherry (red), LC3 (white) in lentivirus-infected ex vivo human cortical slices. Scale bars: 20 μm. f LC3 intensity in mCherry+ neurons in human cortical slices. Two-way ANOVA with two-sided Bonferroni post hoc analysis for multiple comparisons: shNC+Veh vs. shFMR1+Veh: p = 0.0476; shFMR1+Veh vs. shFMR1+Rap: p = 0.0332. N = 3 individual cortices. g Representative confocal images (from three independent experiments) and Neurolucida traces of mCherry+ neurons. Scale bar, 10 μm. h Sholl analysis. MANOVA, shNC+Veh vs. shFMR1 Veh: F _(1,91) = 51.474, p < 0.001; shFMR1+Veh vs. shFMR1 Rap: F _(1,108) = 54.811, p < 0.001. i Total dendritic length of LV-shFMR1 or LV-shNC-infected neurons treated with Veh or Rap. Two-way ANOVA with two-sided Bonferroni post hoc analysis for multiple comparisons, shNC+Veh vs. shFMR1+Veh: p < 0.0001; shFMR1+Veh vs. shFMR1+Rap: p < 0.0001. For all data shown in (g, h), n = 49 (shNC+Veh) neurons; n = 54 neurons (shNC+Rap); n = 44 neurons (shFMR1+Veh); n = 66 neurons (shFMR1+Rap) from N = 3 individual cortices. All error bars reflect mean ± s.e.m. Source data are provided as a Source Data file.