Beyond the Exome: The Non-coding Genome and Enhancers in Neurodevelopmental Disorders and Malformations of Cortical Development

Abstract

The development of the human cerebral cortex is a complex and dynamic process, in which neural stem cell proliferation, neuronal migration, and post-migratory neuronal organization need to occur in a well-organized fashion. Alterations at any of these crucial stages can result in malformations of cortical development (MCDs), a group of genetically heterogeneous neurodevelopmental disorders that present with developmental delay, intellectual disability and epilepsy. Recent progress in genetic technologies, such as next generation sequencing, most often focusing on all protein-coding exons (e.g., whole exome sequencing), allowed the discovery of more than a 100 genes associated with various types of MCDs. Although this has considerably increased the diagnostic yield, most MCD cases remain unexplained. As Whole Exome Sequencing investigates only a minor part of the human genome (1-2%), it is likely that patients, in which no disease-causing mutation has been identified, could harbor mutations in genomic regions beyond the exome. Even though functional annotation of non-coding regions is still lagging behind that of protein-coding genes, tremendous progress has been made in the field of gene regulation. One group of non-coding regulatory regions are enhancers, which can be distantly located upstream or downstream of genes and which can mediate temporal and tissue-specific transcriptional control via long-distance interactions with promoter regions. Although some examples exist in literature that link alterations of enhancers to genetic disorders, a widespread appreciation of the putative roles of these sequences in MCDs is still lacking. Here, we summarize the current state of knowledge on cis-regulatory regions and discuss novel technologies such as massively-parallel reporter assay systems, CRISPR-Cas9-based screens and computational approaches that help to further elucidate the emerging role of the non-coding genome in disease. Moreover, we discuss existing literature on mutations or copy number alterations of regulatory regions involved in brain development. We foresee that the future implementation of the knowledge obtained through ongoing gene regulation studies will benefit patients and will provide an explanation to part of the missing heritability of MCDs and other genetic disorders.

Keywords: bioinformatics; cis-regulatory elements; enhancers; epigenome; functional genomics; gene regulation; malformations of cortical development; massively parallel reporter assays.

FIGURE 1

Regulatory enhancer-promoter interactions are restricted within the topological associating domain (TAD) region. The genome (here represented as a black line) is tightly packaged and organized in TADs established by the binding of CTCF to insulator elements, followed by dimerization and interaction with the cohesin complex. In order to establish the enhancer-promoter loops required for transcriptional regulation, enhancers and their target gene should reside in the same TAD. These regulatory loops are formed by the dimerization of YY1 and its interaction with cohesin. In the enlargement is a simplified scheme of transcription initiation (the size does not reflect the actual dimension of each component). Transcription factors (TFs) bind on the enhancer element while the pre-initiation complex formed by the RNA Pol II and the general TFs assembles at the promoter region. Mediator establishes the connection between enhancer and promoter via interactions with TF and components of the transcription preinitiation complex, without binding to DNA. Mediator regulates the phosphorylation of the RNA Pol II in order to release it from the promoter and start transcription.

FIGURE 2

Overview of the main techniques currently used to identify putative enhancer sequences and their interacting genes. (A) Schematic drawing of an TF-bound enhancer, located in nucleosome depleted DNA from which eRNA is transcribed. Below are representative genome browser tracks shown, illustrating expected profiles for the same genetic region. Histone-ChIP-seq is illustrative for marks such as H3K27ac and H3K4me1. (B) Cartoon representing the main steps of the workflow of Chromosome conformation capture technologies: nuclei are cross-linked, chromatin is then digested and re-ligated by proximity ligation. The two stretches of DNA that are normally located far away from each other (yellow and green), are now ligated together and can be tested by PCR or sequencing. In the bottom part is indicated the output of the experiment, with which TADs and enhancer-promoter interactions can be identified.

FIGURE 3

Methods for functional identification of enhancers. (A) Massively parallel reporter assays (MPRA) to test enhancer activity in an episomal setup. The putative enhancer sequence is cloned upstream a minimal promoter that drives the expression of a reporter gene and a unique barcode. (B) With STARR-seq the putative enhancer sequence is cloned downstream the reporter gene and upstream of the polyA signal. When the enhancer sequence is active, it can drive the expression of the reporter (green) and of itself. In both MPRA and STARR-seq the mRNA is sequenced to identify the active enhancers. (C) Cas9 can be used to knock out an enhancer at the endogenous genomic locus to assess its effect on the target gene transcription. (D) A catalytically inactive Cas9 (dCas9) can be fused with activators (A: VP64; TET1; p300) or repressors (R: KRAB; SID4X; DNMT3A; KDM1A). (E) Cas9 screens can be combined with high-throughput screenings by targeting Cas9 expressing cells with a lentiviral library of gRNA at a low MOI. By doing so, each cell will express a single gRNA and by different selections, such as drug resistance or reporter gene expression, it is possible to investigate the effect of the ablation of a large number of putative enhancers on gene expression in parallel.

FIGURE 4

Overlap between brain enhancer databases. (A) Venn diagram showing the overlap between brain enhancers (in genome build hg19) from different databases: VISTA (n = 542) (Visel et al., 2007), dbSUPER (n = 6002) (Khan and Zhang, 2016), FANTOM5 (n = 639) (Andersson et al., 2014), PsychENCODE (n = 46731; the 46735 enhancers mentioned in the text are in genome build hg38 and the difference of four loci is due to liftover to hg19) (Amiri et al., 2018) and EnhancerAtlas 2.0 (n = 49925) (Gao et al., 2016). (B) Venn diagram showing the overlap between ChIP-seq peaks for H3K27ac from adult brain, as identified in three studies: Sun (n = 56503) (Sun et al., 2016), Vermunt (n = 83553) (Vermunt et al., 2014), and Wang (n = 124437) (Wang D. et al., 2018). The intersection between different sources (in the same order as above) was performed using bedops and bedtools. In both graphs, the minimum overlap of a single nucleotide is required.