A genetic-epigenetic interplay at 1q21.1 locus underlies CHD1L-mediated vulnerability to primary progressive multiple sclerosis

Abstract

Multiple Sclerosis (MS) is a heterogeneous inflammatory and neurodegenerative disease with an unpredictable course towards progressive disability. Treating progressive MS is challenging due to limited insights into the underlying mechanisms. We examined the molecular changes associated with primary progressive MS (PPMS) using a cross-tissue (blood and post-mortem brain) and multilayered data (genetic, epigenetic, transcriptomic) from independent cohorts. In PPMS, we found hypermethylation of the 1q21.1 locus, controlled by PPMS-specific genetic variations and influencing the expression of proximal genes (CHD1L, PRKAB2) in the brain. Evidence from reporter assay and CRISPR/dCas9 experiments supports a causal link between methylation and expression and correlation network analysis further implicates these genes in PPMS brain processes. Knock-down of CHD1L in human iPSC-derived neurons and knock-out of chd1l in zebrafish led to developmental and functional deficits of neurons. Thus, several lines of evidence suggest a distinct genetic-epigenetic-transcriptional interplay in the 1q21.1 locus potentially contributing to PPMS pathogenesis.

Fig. 1. Workflow of the study.

MS multiple sclerosis, PPMS primary progressive MS, SPMS secondary progressive MS, RRMS relapsing-remitting MS, SNP single nucleotide polymorphism, meQTL and eQTL methylation and expression quantitative trait loci, SWE Swedish cohort, ITA Italian cohort, META meta-analysis of the SWE and ITA cohorts.

Fig. 2. Hypermethylation of the 1q21.1 locus in primary progressive multiple sclerosis patients.

a Genomic annotation of the identified differentially methylated region (DMR) in 1q21.1, including 450K and pyrosequenced CpG probes and regulatory features, i.e. CpG island (CGI) and chromatin state segmentation by hidden Markov model (ChromHMM) from ENCODE/Broad. b Dot plot and violin plot of DNA methylation differences at the identified DMR on chromosome 1: 146549909–146551201 (hg19) in PPMS (n = 4) compared to RRMS (n = 120), SPMS (n = 16), and HC (n = 139), obtained using Illumina 450K in cohort 1. c Replication of methylation (mean ± SEM) at 7 CpGs (CpG 1–7, including four 450 K probes) in an independent cohort (n_RRMS = 48, n_PPMS = 36, non-parametric two-sided Mann–Whitney U test) using pyrosequencing. MS multiple sclerosis, PPMS primary progressive MS, RRMS relapsing-remitting MS, SPMS secondary progressive MS, HC healthy controls, BOMS bout-onset MS, hiPSC human induced pluripotent stem cells, DNase HS DNase I hypersensitive sites, Txn factor ChIP transcription factor chromatin immunoprecipitation. Source data are provided as a Source Data file.

Fig. 3. Genetic control of methylation and gene expression in the 1q21.1 locus.

a Genomic and functional annotation of the methylation-controlling SNPs. Linkage disequilibrium (LD) is indicated by shades of red and clustering of SNPs is based on high LD between SNPs (R² > 0.8). Colored circles show SNP effects on DMR methylation: size positively correlates with significance (–log10 P-value) and blue and red colors represent negative and positive effects of the minor allele, respectively. Gene location and regulatory features, i.e. CpG island (CGI) and chromatin state segmentation (ChromHMM), from ENCODE/Broad. b Association between genetic variation at the extended locus (upper panel) and DNA methylation in blood at CpG 4 of the 1q21.1 DMR, obtained using meQTL analysis in cohort 2 (n = 82). Significance is represented as –log10 (P-value). Association of the two strongest variants rs1969869 and rs4950357 with CpG 4 (as an example, lower panel). CpG codes are presented in Fig. 2c. c Effects of SNPs within each SNP cluster on DNA methylation at 1q21.1 DMR in the brain (using xQTL serve platform) with only significant associations displayed in colors, blue and red colors representing negative and positive effect of the minor allele, respectively (left panel) and association between genetic variation in the extended locus and DNA methylation at cg02487331 (CpG 7) (right panel). Significance is represented as –log10 (P-value). * Indicates strong LD with rs21327 (R² > 0.7). d. Association between genetic variation, DNA methylation (using xQTL serve platform), and gene expression (using GTEx database) in the extended locus for SNPs tagging four variants (LD blocks) displaying significant association with PPMS in the meta-analysis of Swedish (SWE) and Italian (ITA) cohorts. Green and orange colors reflect protective and risk effects on PPMS risk conferred by the genetic variants, respectively. Blue and red colors represent the negative and positive effects of the minor allele, respectively, on methylation or expression. NA not available, NS not significant. The data shown in this panel are available in Supplementary Data 7 (meQTL, eQTL) and 8 (genetic analysis). A linear regression model with a Bonferroni-corrected or FDR-adjusted threshold of 0.05 was used for all the statistical tests.

Fig. 4. Functional impact of methylation at the 1q21.1 DMR on gene expression.

a, b Promoter (a) and enhancer (b) activity of the DMR, using CpG-free promoter-free (SEAP) and promoter-containing (Lucia) reporter gene vectors, respectively. Constructs in direct or inverted orientation of DNA segments derived from individuals varying according to the genotype at rs1969869 were partially or fully methylated using HhaI and M.SssI enzymatic treatment, respectively. Results show relative activity ±SEM of SEAP (two experimental replicates, n = 6) or Lucia (three experimental replicates, n = 10) normalized against Renilla (2-way ANOVA with Bonferroni correction for multiple comparisons). c Schematic representation of the experimental design for gRNAs screen in HEK293T cells including the features of the constructs and gRNA locations. d Heatmap of the DNA methylation levels in successfully transfected (GFP positive) HEK293T cells three days following co-transfection of dCas9-TET1 with single or combined gRNAs in comparison to control conditions, deactivated TET1 (TET1-IM), non-targeting gRNA (ntgRNA) and non-transfected cells. e Schematic representation of the experimental design for functional investigation in SH-SY5Y cells. f DNA methylation levels in SH-SY5Y cells following delivery of dCas9-TET1-, gRNA2- and gRNA3-containing lentiviruses. Methylation percentages represent the mean ± SD of three experiments (2-way ANOVA followed by Turkey’s multiple comparisons test). g Experiment showing expression of CHD1L, PRKAB2, PDIA3P1, and FMO5 genes relative to GAPDH transcript levels, quantified using RT-qPCR. The expression levels represent the average of at least three experiments (mean ± SD, two-tailed Student’s t-test). n.s, non-significant. Source data are provided as a Source Data file.

Fig. 5. Implication of CHD1L and PRKAB2 genes in PPMS brain pathology.

a Schematic representation of the correlation network analysis using bulk MS brain transcriptome. The different steps are depicted from left to right: correlation matrix containing gene-gene pairwise Spearman correlations; illustration of the permutation test filtered correlation network surviving an FDR P-value < 0.05 and the planar maximally filtering to convert the scale-free network to be able to overlay on a plane spherical surface, reducing the network to 0.5 million interactions among 27,509 genes and, finally; representation of the multiscale clustering of the network resulting into 757 non-overlapping clusters. b Heatmap of the correlation coefficients of all 757 non-overlapping modules (left) and the three modules surviving correlation FDR P-value < 0.05 (right) to each tested phenotypic trait (n_PPMS = 5, n_SPMS = 7 and n_{non-neurological controls} = 10), with red gradient colors representing negative (not significant) to positive (significant) correlation. Spearman correlation is applied on every gene pair and P-values were adjusted for multiple comparisons by FDR ( < 0.05). c Representation of the three modules (left), the closest neighbors to candidate genes in each module (middle), and Gene Ontology findings, i.e. Disease and Biological functions, obtained using Ingenuity Pathway Analysis (Fisher’s exact test, P-value < 0.05). MS multiple sclerosis, PPMS primary progressive MS, SPMS secondary progressive MS, NNC non-neurological controls.

Fig. 6. Functional impact of low CHD1L expression in neurons and oligodendrocytes.

a Schematic of zebrafish experimental design. b Dorsal view of control and chd1l+/− larvae at 4 dpf stained with acetylated tubulin. Barplot of the inter-tecta axonal tract projections count of 4 dpf control and chd1l+/− larvae (Wilcoxon test, mean ± SEM, n = 3 replicate/genotype, 30 larvae/replicate). c Dorsal view of Tg(olig2:EGFP);chd1l+/+ and Tg(olig2:EGFP);chd1l+/− at 3 dpf with the hindbrain used for olig2-positive cells count outlined in yellow. Barplot of the number of olig2-positive cells per µm2 in the hindbrain of Tg(olig2:EGFP);chd1l+/+ and Tg(olig2:EGFP);chd1l+/− larvae at 3 dpf (Wilcoxon test, mean ± SEM, n = 3 replicate/genotype, 12–20 larvae/replicate). d Lateral view of the spinal cord of Tg(olig2:EGFP);chd1l+/+ and Tg(olig2:EGFP);chd1l+/− larvae at 3 dpf. Barplot of the number of olig2-positive cells migrating dorsally from the spinal cord of Tg(olig2:EGFP);chd1l+/+ and Tg(olig2:EGFP);chd1l+/− larvae at 3 dpf (Student’s T-test, mean ± SEM, n = 3 replicate/genotype, 15–20 larvae/replicate). e Schematics of iPSCs experimental design. f Representative confocal images of markers of neuroectodermal NPCs (PAX6, SOX1) and differentiated neurons (MAP2, SYN1), all performed in duplicates in three independent subject lines. g qPCR data of CHD1L, EOMES, SATB2, CTIP2 and DCX transcripts in non-targeting (NT) and CHD1L knock-down (KD) neurons. Box plots indicate the median (line), 25th and 75th percentile (box), min and max (whiskers). All data points correspond to experimental duplicates in three independent subject lines (different colors, two-sided Mann–Whitney U test). h Quantification of neurite length (μm) and synaptic density in NT and KD neurons (two-sided Mann–Whitney U test). i Quantification of background-corrected changes in calcium-sensitive dye fluorescent intensity in NT and CHD1L KD neurons. A representative confocal image is shown. Data points correspond to averaged active regions (ROIs, 10 cells) per field of view (two-sided Mann–Whitney U test). Five to six fields of view were included for each subject line and condition. j Representative calcium imaging traces from NT and CHD1L KD neurons (3 ROIs). A anterior, P posterior, dpf days post-fertilization, NT non-targeting siRNA, KD CHD1L-targeting siRNA. n.s non-significant. Source data are provided as a Source Data file.