Participants’ age at assessment, sex, and CNV origin (inherited or de novo) are shown in Table 2A and demographic information for the comparison groups used for the methylation analyses is provided in Table 2B. The cognitive and behavioral, and medical phenotypic characteristics of each participant are summarized in Table 3.

Atypical deletion individual 1 (Atyp Del1) is one of a dizygotic twin pair; her same-sex twin does not have a deletion at 7q11.23. Clinical assessment using the Differential Ability Scales-II (DAS-II)30 identified a similar pattern of relative strengths and weaknesses as is typical for classic WBS, in the context of a considerably higher level of overall ability. Verbal and nonverbal reasoning ability were within the average range for the general population, with spatial ability in the borderline range. A similar pattern of relative strengths and weaknesses was observed in the fraternal same-sex twin, suggesting that the relative weakness in spatial skills is likely familial. However, the unaffected twin’s overall intellectual ability (DAS-II30 General Conceptual Ability (GCA)) was 15 points higher.

Based on parental responses on the Social Responsiveness Scale-2 (SRS-2)31, Atyp Del1 was found to have social pragmatic abilities within the average range for children with WBS (considerably more limited than children her age in the general population). Parental rating on the Conners Early Childhood (EC)32 Inattention/Hyperactivity scale was within the average range for children with classic WBS (significantly more difficulty than children her age in the general population). The unaffected twin scored in the average range for children in the general population on both measures. Based on the Anxiety Disorders Interview Schedule for DSM-IV Parent (ADIS-P)33 interview, Atyp Del1 also had sensitivity to loud noises. Overall, this individual’s cognitive phenotype was similar to that of children with classic WBS, although her difficulty with spatial skills may be familial rather than deletion-related and her overall intellectual ability was higher than expected for classic WBS.

On physical examination, Atyp Del1 was found to have facial features characteristic of WBS. Review of medical records indicated hyperopia, a history of chronic otitis media, a ventricular septal defect, and gastroesophageal reflux as an infant.

Atypical deletion individual 2 (Atyp Del2) showed a similar pattern of relative strengths and weaknesses to those observed in the classic WBS comparison group; however, her spatial ability was higher than that of any child her age in the classic WBS group. Her overall intellectual ability (DAS-II30 GCA) was considerably higher than that of the classic WBS group of children her age. Her SRS-231 T-scores indicated similar levels of pragmatic difficulty as children with classic WBS her age, and her Conners Comprehensive Behavior Rating Scales (CBRS)34 T-scores for the ADHD-Predominantly Inattentive and ADHD-Predominantly Hyperactive/Impulsive scales were within the average range for individuals with classic WBS her age. Based on the ADIS-P31 interview, she was sensitive to loud noises. Thus, her behavioural and cognitive phenotype was similar to that of same-aged children with classic WBS, although her overall intellectual ability and spatial ability were higher than expected for children with classic WBS.

Physical examination revealed facial features characteristic of WBS and a tremor. Review of medical records indicated that Atyp Del2 had mild supravalvar aortic stenosis and a multicystic dysplastic kidney.

Atypical deletion individual 3 (Atyp Del3) had a DAS-II30 GCA within the average range for children in the general population, despite a considerably lower socioeconomic status than most children in the WBS comparison group. He did not exhibit the characteristic pattern of relative strengths and weaknesses seen in classic WBS; instead, he showed a flat profile, with his spatial cluster standard score non-significantly higher than his verbal and nonverbal reasoning standard scores. Based on the SRS-231, his social-pragmatic abilities were considerably stronger than those of children with classic WBS his age. Parental ratings on the Conners CBRS34 indicated that he had considerably more symptoms of ADHD-Predominantly Hyperactive/Impulsive but considerably fewer symptoms of ADHD-Predominantly Inattentive than is characteristic of children with classic WBS his age. This child did not show overlap with the common cognitive or behavioral features of the WBS comparison group.

On physical examination, Atyp Del3 had microcephaly and short stature. Review of medical records indicated difficulty gaining weight, gastroesophageal reflux, and chronic constipation. These characteristics are consistent with the WBS medical phenotype, although unlike most children with classic WBS, Atyp Del3 did not have any heart disease.

Atypical duplication individual 1 (Atyp Dup1) was born prematurely. He had developmental delay, most likely due to prematurity. His Speech Sound Disorder, which was not of the type associated with classic Dup7, also likely was due to prematurity. Unlike the classic Dup7 comparison group, this individual’s SRS-231 Social Motivation T-score was in the average range for children in the general population, as were his social-pragmatic abilities overall. Based on the Conners EC32, his level of inattention/hyperactivity symptoms was average for the general population. He was classified as non-spectrum based on the Autism Diagnostic Observation Schedule-2 (ADOS-2) classification35 and clinical diagnosis. Other than developmental delay, his cognitive and behavioral phenotypes did not overlap with classic Dup7.

Physical examination revealed strabismus, joint laxity, and Developmental Coordination Disorder. He had mild cerebral palsy, likely due to prematurity. Review of medical records showed a history of hypospadias and cryptorchidism. He did not have facial features or other medical characteristics associated with classic Dup7.

Atypical duplication individual 2 (Atyp Dup2) performed in the average range for children her age with classic Dup7 on the DAS-II30 verbal, nonverbal reasoning, and spatial clusters and for overall intellectual ability. She also had a Speech Sound Disorder that overlapped with that associated with classic Dup7 and was diagnosed with Social Phobia based on ADIS-P interview33. Based on the SRS-231, her level of social-pragmatic difficulties was typical for children with classic Dup7 her age. Her inattentive/hyperactive symptoms as measured by the Conners EC30 were at the level expected for children her age in the general population. She was classified as non-spectrum based on the ADOS-2 classification35 and clinical diagnosis.

Physical examination revealed facial features characteristic of children with Dup7, macrocephaly, hypotonia, and Developmental Coordination Disorder. Her parents reported that she had a high pain tolerance and a sleep disorder.

Atypical duplication 3 (Atyp Dup3) had a DAS-II30 GCA in the above average range for the general population. Her standard scores (SSs) for all three of the DAS-II core clusters were in the average to above average range for the general population. She was diagnosed with a Speech Sound Disorder pattern characteristic of children with classic Dup7. Her social-pragmatic skills as measured by the SRS-231 and her inattention/hyperactivity symptoms as measured by the Conners EC32 were in the average range for the general population. She was classified as non-spectrum based on the ADOS-2 classification35 and clinical diagnosis.

Physical examination revealed facial features typical of classic Dup7. She also had hypotonia. Review of medical records indicated that she had chronic constipation.

Previous analyses of DNA methylation in cohorts of children with classic WBS, children with classic Dup7, and typically developing (TD) controls identified genome-wide dose-dependent changes to DNA methylation19. Each individual analyzed in our previous study harbored a typical 7q11.23 deletion or duplication (concordant breakpoints) and classic phenotype; therefore, our previous study could not elucidate which gene(s) within this region could be contributing to the methylation changes we observed. To better understand the molecular mechanism accounting for the methylation changes we detected, we recruited several individuals with rare, atypical deletions or duplications of the 7q11.23 region (Table 1), generated DNA methylation profiles, and compared them to those reported previously19. An overview of the CNVs analyzed in this study is shown in Fig. 1. This proof-of-principle study was employed to determine if a small number of rare deletions and duplications could aid in elucidating the genes contributing to aberrant DNA methylation in disorders of 7q11.23 CNV.

Shown is an overview of the atypical deletion and duplication participants identified in our study. Red bars indicate deletions and blue indicate duplications. 7q11.23 CNVs were identified by chromosomal microarray analysis (CMA) and confirmed by qPCR, using a standard panel of genes across the region. The proximal breakpoint of atypical duplication 3 (Atyp Dup3) was found to be more proximal by qPCR than what was reported by CMA. The region shown as duplicated by qPCR is marked by a dashed line. All other breakpoints were concordant between CMA and qPCR. Included is a representative WBS deletion and the reciprocal duplication characteristic of Dup7.

The distal breakpoint of both the classic WBS deletion and the Dup7 duplication lie within a flanking low copy repeat, making it hard to determine whether CNV of this region includes the full GTF2I gene. The distal breakpoints of three of the atypical CNVs also lie within the low copy repeats making accurate determination of the exact boundary impossible by microarray or qPCR. To help determine whether GTF2I was impacted in these participants, expression analysis of GTF2I was carried out by real-time qPCR. Participants with deletion of GTF2I (Atyp Del1 and Atyp Del2) showed transcript levels that were consistent with those seen in individuals with WBS. Participants Atyp Del3 and Atyp Dup1 who had two genomic copies of GTF2I showed corresponding transcript levels similar to the control group with no 7q11.23 CNV (Supplementary Table 2). Participant Atyp Dup3, with only a partial duplication of GTF2I encompassing the first few exons, also showed GTF2I transcript levels similar to the control group when primers within the non-duplicated region of the gene were used.

To determine whether expression of genes within the common 7q11.23 CNV that have the potential to affect DNA methylation (BAZ1B, BCL7B, or BUD23) were altered by nearby genomic rearrangements, transcript levels were assessed in the three participants with CNVs that did not change the copy number of these genes (Atyp Del1, Atyp Del2, and Atyp Dup1). All three participants had transcript levels that were similar to those from control participants, and distinctly different from individuals with WBS or Dup7.

Overall, expression analysis of GTF2I as well as genes within the common 7q11.23 CNV that could affect DNA methylation (BAZ1B, BCL7B, BUD23), support the findings from genomic copy number analysis.

Principal component analysis (PCA) of DNA methylation data from all participants, including technical replicates, indicated that each atypical rearrangement exhibited a different DNA methylation profile, suggesting that the differing genotypes are driving changes to DNA methylation profiles (Fig. 2a). Analysis of all samples, including technical replicates, confirmed that the results were not confounded by batch effects (Fig. 2a). Re-analyses of previously generated data19 in conjunction with new data from participants with atypical 7q11.23 CNV again resulted in the clustering of the WBS group separate from the Dup7 group, which were separate from the TD controls (Fig. 2a). Notably, the DNA methylation patterns of several atypical participants appeared to cluster with their respective syndromic cohort. Atyp Dup2 and Atyp Dup3 (both technical replicates 1 and 2) clustered closely with the classic Dup7 cohort, whilst both Atyp Del1 and Atyp Del2 fell between TD controls and the classic WBS cluster. Atyp Dup1 clustered closely with TD controls, and Atyp Del3 was closer to the TD controls than the WBS cluster but did appear noticeably different from the TD group (Fig. 2a).

a PCA of methylation profiles. Methylation profiles from the six participants with atypical 7q11.23 deletions (purple) or duplications (orange) are shown alongside those from children with classic WBS (blue), children with classic Dup7 (green) and typically developing (TD) children (gray). Technical replicates (two from each group) are noted with their relative batch in parentheses. b Multi-dimensional scaling (MDS) plot of the top 1000 most variable positions across all individuals. Three distinct clusters are resolved representing children with WBS (blue), children with Dup7 (green), and TD children (gray). Participants with atypical CNVs differentially cluster with the classic WBS, classic Dup7 and TD groups in a genotype-dependent manner.

Atyp Del2 and Atyp Del3 did not clearly cluster with either TD controls or the WBS cluster, suggesting that the shared deletion of telomeric genes at 7q11.23 contributes to changes in DNA methylation but may not be sufficient to replicate the entire methylation profile. To better understand the contribution of these genes to larger gains and losses of DNA methylation, we assessed the top 1000 most variable positions using multi-dimensional scaling (MDS; Fig. 2b). Technical replicates were first removed, and the entire batch reanalyzed; this was to ensure that the results of this small study were not skewed by the inclusion of similar samples. Analysis of these positions again replicated the distinct clustering of WBS, Dup7, and TD control cohorts, validating this approach. Atypical participants now clustered in a much clearer genotype-dependent manner; Atyp Dup1 was indistinguishable from controls, Atyp Dup2 and Atyp Dup3 clustered with the classic Dup7 group, Atyp Del3 clustered closer to the TD controls, and Atyp Del1 and Atyp Del2 again clustered between WBS group and TD controls but closer to the classic WBS group (Fig. 2b).

Previous analyses of DNA methylation identified a dose-dependent profile consisting of a small number of CpG sites that could distinguish individuals with WBS, TD controls, and individuals with Dup719. This strategy was re-employed in this study to better understand how the atypical participants grouped across highly distinguishing CpG sites. Analysis of 185 CpG sites that are significantly differentially methylated in both WBS and Dup7 cohorts again clearly distinguished each cohort (Fig. 3). Hierarchical clustering grouped both Atyp Del1 and Atyp Del2 with the WBS cohort, whilst Atyp Dup2 and Atyp Dup3 clustered with the Dup7 cohort (Fig. 3a). Atyp Del3 and Atyp Dup1 both clustered with TD controls; however, Atyp Del3 is noted as having a methylation profile distinct from the other groups (Fig. 3a).

a Heatmap with hierarchical clustering across 185 CpG sites found to be significantly differentially methylated in both the WBS to TD and Dup7 to TD comparisons and (b) MDS plot of the same data replicates the profile generated by hierarchical clustering.

Across several clusters of CpG sites in the heatmap, Atyp Del3 demonstrated a methylation pattern similar to the WBS group, suggesting that although deletion of the centromeric end is not sufficient to replicate the global methylation pattern observed in WBS participants, there is likely some contribution of the centromeric genes to aberrant DNA methylation (Fig. 3a). Without a second atypical participant sharing the same or similar deletion as Atyp Del3, it is difficult to draw firm conclusions from the methylation profile of this single participant. A MDS plot of the same data replicated these findings and produced an overall profile similar to that observed across the top 1000 most variable positions (Fig. 3b).

The methylation profile across the top 500 most differentially methylated (DM) CpG sites in each cohort were evaluated. Both absolute differential methylation (topmost differentially methylated sites) and the top 250 hyper- and 250 hypomethylated CpG sites were assessed. Hierarchical clustering produced variable results within the WBS to TD comparison, with clustering across the top 500 most differentially methylated CpGs resulting in all atypical deletion participants clustering with TD controls (Supplementary Fig. 1A); however, the associated MDS plot again demonstrated Atyp Del1 and Atyp Del2 clustering between WBS and TD groups (Supplementary Fig. 1B). Analysis of the top 250 most hyper- and 250 most hypomethylated CpGs in the WBS to TD comparison clearly clustered Atyp Del1 and Atyp Del2 with the WBS cohort and Atyp Del3 with TD controls, consistent with all previous analyses (Supplementary Fig. 1C, D). This apparent discrepancy may be due to technical differences between hierarchical clustering and MDS analyses or may suggest a specific influence of the genes encompassed within Atyp Del1 and Atyp Del2 to the more numerous hypomethylated CpGs captured within the top 250 hyper- and 250 hypomethylated CpGs.

The methylation profiles generated from the Dup7 to TD comparison again consistently clustered Atyp Dup2 and Atyp Dup3 with the Dup7 cohort, and Atyp Dup1 with TD controls, regardless of which CpG sites were assessed, consistent with all previous approaches to analysis (Supplementary Fig. 2). These analyses replicate the results observed across the top 1000 most variable positions and the top discriminating CpG sites, supporting the conclusion that atypical deletion or duplication of this region can produce distinct methylation profiles.

Validation of methylation levels was performed across selected CpG sites from the two top-most DM genes from our initial study (ANKRD30B and RFPL2)19, using targeted pyrosequencing. The correlations between methylation levels detected by microarray and by pyrosequencing were very high, and differences between atypical participants could be resolved (Supplementary Fig. 3). Overall, the pyrosequencing data supported the global DNA methylation patterns for each of the participants with atypical 7q11.23 CNV.

In total, three different methods of assessing DNA methylation have demonstrated that the participants with atypical 7q11.23 deletions and duplications have methylation profiles that differ by genotype. All three methods suggest that genes at the telomeric end of 7q11.23 contribute to the larger changes in DNA methylation observed in our cohort, although a smaller contribution of genes toward the centromeric end is also likely.