Genetic and environmental risk factors in congenital heart disease functionally converge in protein networks driving heart development

Abstract

Congenital heart disease (CHD) occurs in ∼1% of newborns. CHD arises from many distinct etiologies, ranging from genetic or genomic variation to exposure to teratogens, which elicit diverse cell and molecular responses during cardiac development. To systematically explore the relationships between CHD risk factors and responses, we compiled and integrated comprehensive datasets from studies of CHD in humans and model organisms. We examined two alternative models of potential functional relationships between genes in these datasets: direct convergence, in which CHD risk factors significantly and directly impact the same genes and molecules and functional convergence, in which risk factors significantly impact different molecules that participate in a discrete heart development network. We observed no evidence for direct convergence. In contrast, we show that CHD risk factors functionally converge in protein networks driving the development of specific anatomical structures (e.g., outflow tract, ventricular septum, and atrial septum) that are malformed by CHD. This integrative analysis of CHD risk factors and responses suggests a complex pattern of functional interactions between genomic variation and environmental exposures that modulate critical biological systems during heart development.

Fig. 1.

Functional convergence versus direct convergence of CHD datasets. Risk and responder datasets are indicated by green, gold, and blue circles or ellipses, respectively. Numbers represent theoretical gene counts and are different for datasets with the same name in A and B. (A) Illustrates six risk and responder datasets with different genes that are all functionally converging on a predefined developmental program of the ventricular septum (black circle, containing a total of 278 genes). The example illustrates how different risk and responder datasets can contain many genes involved in a common polygenic developmental program (bolded black and red numbers), while only sparsely overlapping with each other (red numbers). (B) Theoretical example of direct convergence, where the risk and responder datasets can be directly overlapped to reveal a common subset of genes (red numbers).

Fig. 2.

Functional convergence of CHD risk and responder datasets in cardiac developmental networks. (A–C) Functional convergence was analyzed in predefined developmental programs (11), deduced from protein–protein interaction networks driving the development of the outflow tract (A), ventricular septum (B), and atrial septum (C). Circles represent gene-encoded proteins (gene names viewable with the Adobe zoom tool or at www.cbs.dtu.dk/suppl/dgf/). Lines represent protein–protein interactions. Colors indicate datasets of Mendelian risk genes, SNPs, or Mendelian responder genes (green), CNVs and translocations from cohort A or B (gold), or environmental target or responder genes (blue). Red circles indicate proteins belonging to more than one dataset.

Fig. 3.

Few genes are shared between CHD risk and responder datasets. Each panel shows all genes from any risk or responder dataset that overlaps with the gene set represented in the outflow tract (A), ventricular septum (B), and atrial septum (C) developmental network. Datasets are color coded as detailed in Fig. 2 and abbreviated as: SNPs, single nucleotide polymorphisms; MM, Mendelian mutations; MR, Mendelian responders; SVA and SVB, structural variants in cohorts A and B respectively; ET, environmental targets; ER, environmental responders. Despite the significant functional convergence between the risk and responder datasets in each of the networks (Fig. 2), only a few genes (highlighted in red) are identified in multiple risk datasets.

Fig. 4.

Pairwise comparisons of direct convergences of risk and responder datasets. Genes (Table 1) were compared using hypergeometric statistics to assess signficance of overlap between datasets of varying sizes and corrected for multiple testing. Shading denotes significant (red) or insignificant (grey) direct convergence. SNPs within Mendelian CHD genes and environmental target genes are not independent and were excluded (NA).

Fig. 5.

Risk and responder datasets are enriched for heart developmental genes. (A) Box-and whisker plots showing the fraction of genes shared between the individual risk and responder datasets (Tables 1 and 2) and each of the 19 cardiac developmental networks, compared with dataset-specific null distributions. Each dataset shows significant enrichment for heart developmental genes represented in one or more of the networks (P < 5.0e-4 to P = 0.016 for the individual datasets of risk or responder genes, respectively) after taking into account the size and composition of each dataset. Note that the enrichment of genes within structural variants identified in cohort A are replicated in an independent dataset from cohort B. (B) Analyses of control datasets of comparable complexity to the CHD risk and responder datasets showed no enrichment for genes within 19 heart developmental networks. Distributions are plotted as their median, first, and third quartile (box) and minimum and maximum (whiskers). Gray boxes, dataset-specific enrichment; white boxes, dataset-specific null distribution.