by
Shan V. Andrews;
Brooke Sheppard;
Gayle C. Windham;
Laura A. Schieve;
Diana E. Schendel;
Lisa A. Croen;
Pankaj Chopra;
Reid S. Alisch;
Craig J. Newschaffer;
Stephen Warren;
Andrew P. Feinberg;
M. Danielle Fallin;
Christine Ladd-Acosta
Background: Several reports have suggested a role for epigenetic mechanisms in ASD etiology. Epigenome-wide association studies (EWAS) in autism spectrum disorder (ASD) may shed light on particular biological mechanisms. However, studies of ASD cases versus controls have been limited by post-mortem timing and severely small sample sizes. Reports from in-life sampling of blood or saliva have also been very limited in sample size and/or genomic coverage. We present the largest case-control EWAS for ASD to date, combining data from population-based case-control and case-sibling pair studies. Methods: DNA from 968 blood samples from children in the Study to Explore Early Development (SEED 1) was used to generate epigenome-wide array DNA methylation (DNAm) data at 485,512 CpG sites for 453 cases and 515 controls, using the Illumina 450K Beadchip. The Simons Simplex Collection (SSC) provided 450K array DNAm data on an additional 343 cases and their unaffected siblings. We performed EWAS meta-analysis across results from the two data sets, with adjustment for sex and surrogate variables that reflect major sources of biological variation and technical confounding such as cell type, batch, and ancestry. We compared top EWAS results to those from a previous brain-based analysis. We also tested for enrichment of ASD EWAS CpGs for being targets of meQTL associations using available SNP genotype data in the SEED sample. Findings: In this meta-analysis of blood-based DNA from 796 cases and 858 controls, no single CpG met a Bonferroni discovery threshold of p < 1.12 × 10- 7. Seven CpGs showed differences at p < 1 × 10- 5and 48 at 1 × 10- 4. Of the top 7, 5 showed brain-based ASD associations as well, often with larger effect sizes, and the top 48 overall showed modest concordance (r = 0.31) in direction of effect with cerebellum samples. Finally, we observed suggestive evidence for enrichment of CpG sites controlled by SNPs (meQTL targets) among the EWAS CpG hits, which was consistent across EWAS and meQTL discovery p value thresholds. Conclusions: No single CpG site showed a large enough DNAm difference between cases and controls to achieve epigenome-wide significance in this sample size. However, our results suggest the potential to observe disease associations from blood-based samples. Among the seven sites achieving suggestive statistical significance, we observed consistent, and stronger, effects at the same sites among brain samples. Discovery-oriented EWAS for ASD using blood samples will likely need even larger samples and unified genetic data to further understand DNAm differences in ASD.
Fragile X-associated primary ovarian insufficiency (FXPOI) occurs in about 20% of women who carry a premutation allele (55-200 CGG repeats). These women develop hypergonadotropic hypogonadism and have secondary amenorrhea before age 40. A non-linear association with repeat size and risk for FXPOI has been seen in multiple studies women with a premutation: those with a mid-range of repeats are at highest risk (~70-100 CGG repeats). Importantly, not all carriers with 70-100 repeats experience FXPOI. We investigated whether AGG interruptions, adjusted for repeat size, impacted age at secondary amenorrhea. We have reproductive history information and AGG interruption data on 262 premutation women: 164 had an established age at amenorrhea (AAA) (for some, age at onset of FXPOI) or menopause, 16 had a surgery involving the reproductive system such as a hysterectomy, and 82 women were still cycling at the last interview. Reproductive status was determined using self-report reproductive questionnaires and interviews with a reproductive endocrinologist. For each of these 262 women, FMR1 repeat size and number of AGG interruptions were determined. We confirmed the association of repeat size with AAA or menopause among women with a premutation. As expected, both premutation repeat size and the quadratic form of repeat size (i.e., squared term) were significant in a survival analysis model predicting AAA (p < 0.0001 for both variables). When number of AGG interruptions was added to the model, this variable was not significant (p = 0.59). Finally, we used a regression model based on the 164 women with established AAA to estimate the proportion of variance in AAA explained by repeat size and its squared term. Both terms were again highly significant (p < 0.0001 for both), but together only explained 13% of the variation in AAA. The non-linear association between AAA and FMR1 repeat size has been described in several studies. We have determined that AGG interruption pattern does not contribute to this association. Because only 13% of the variation is described using repeat size, it is clear that further research of FXPOI is needed to identify other factors that affect the risk for FXPOI.
by
Craig A. Erickson;
Walter Kaufmann;
Dejan B. Budimirovic;
Ave Lachiewicz;
Barbara Haas-Givler;
Robert M. Miller;
Jayne Dixon Weber;
Leonard Abbeduto;
David Hessl;
Randi J. Hagerman;
Elizabeth Berry-Kravis
Preclinical studies using animal models of fragile X syndrome have yielded several agents that rescue a wide variety of phenotypes. However, translation of these treatments to humans with the disorder has not yet been successful, shedding light on a variety of limitations with both animal models and human trial design. As members of the Clinical Trials Committee of the National Fragile X Foundation, we have discussed a variety of recommendations at the level of preclinical development, transition from preclinical to human projects, family involvement, and multi-site trial planning. Our recommendations are made with the vision that effective new treatment will lie at the intersection of innovation, rigorous and reproducible research, and stakeholder involvement.