The ENIGMA Consortium: large-scale collaborative analyses of neuroimaging and genetic data

Abstract

The Enhancing NeuroImaging Genetics through Meta-Analysis (ENIGMA) Consortium is a collaborative network of researchers working together on a range of large-scale studies that integrate data from 70 institutions worldwide. Organized into Working Groups that tackle questions in neuroscience, genetics, and medicine, ENIGMA studies have analyzed neuroimaging data from over 12,826 subjects. In addition, data from 12,171 individuals were provided by the CHARGE consortium for replication of findings, in a total of 24,997 subjects. By meta-analyzing results from many sites, ENIGMA has detected factors that affect the brain that no individual site could detect on its own, and that require larger numbers of subjects than any individual neuroimaging study has currently collected. ENIGMA's first project was a genome-wide association study identifying common variants in the genome associated with hippocampal volume or intracranial volume. Continuing work is exploring genetic associations with subcortical volumes (ENIGMA2) and white matter microstructure (ENIGMA-DTI). Working groups also focus on understanding how schizophrenia, bipolar illness, major depression and attention deficit/hyperactivity disorder (ADHD) affect the brain. We review the current progress of the ENIGMA Consortium, along with challenges and unexpected discoveries made on the way.

Fig. 1

Steps involved in a genome-wide association study. A heritable brain measure (or “phenotype”) - which could be binary, such as a disease state, or continuous, such as the intracranial volume (ICV) - is extracted from brain imaging scans from a large group of people. To determine if there is any statistical association between this brain measure and the inter-subject variations at a single SNP, the genetic variations among individuals can be assessed at a single location along the genome, and correlated with differences in the trait of interest (here, ICV). Genome-wide association scans involve an unbiased search across the whole genome to discover novel genetic loci associated with the trait. Testing a million or more SNPs requires a strict multiple comparisons correction threshold, to avoid reporting spurious results; normally, credible findings have to achieve a significance value more extreme than p < 10⁻⁸. The so-called “Manhattan plot” on the right (by analogy with the Manhattan skyline in New York) displays the −log₁₀ of the p-value for associations between the brain measure and genetic variation at each position along the genome; the higher the point on the plot, the more likely it is that an association exists. Of course, it is important not to see genome-wide significance as a “binary state”, whose conditions are either fulfilled or not—but rather a measure of the level of evidence for a genetic association. Findings in these plots must typically be replicated in several independent cohorts before they are considered credible or generalizable

Fig. 2

ENIGMA founding sites. The first ENIGMA project (Stein et al. 2012) was initiated in 2009, by a consortium of research groups worldwide involved in neuroimaging and genetics. Several existing consortia and research networks are taking part, including IMAGEN, EPIGEN, SYS, FBIRN, and ADNI. Many of these efforts pre-dated ENIGMA and continue today; each conducts its own projects in addition to their collaborative work within ENIGMA. ADNI collects data at 58 sites around the U.S.; for clarity, not all data collection sites are shown here. Each symbol represents a site contributing to ENIGMA, as of June 2013

Fig. 3

Forest plots from the ENIGMA1 study (adapted from Stein et al. 2012). Forest plots are a graphical display designed to illustrate the relative strength of an effect in different cohorts. In the left panel, we show the effect of the genetic variant at rs7294919 on the hippocampal volume, in a range of cohorts in ENIGMA. In ADNI, for example, the confidence interval on the effect overlaps zero, which means that there is no evidence to reject the hypothesis of no effect, if only that cohort were considered. The “ENIGMA Discovery” line combines the effects of all cohorts above it. At the bottom of the figure, the meta-analysis of all effects above the line includes data from another large consortium, CHARGE, and several replication samples. The area of each square is proportional to the study’s weight in the meta-analysis. The right panel shows a similar plot for the effect on intracranial volume of the common genetic variant at rs10784502. It is not necessary for the effect to be detected in all cohorts for the meta-analysis to support the effect. The abbreviations denote the names of the different cohorts in ENIGMA (please see Stein et al. , for details). [Adapted, with permission, from Stein et al., Nature Genetics, April 15 2012]

Fig. 4

A meta-analysis of tract-wise heritability, by the ENIGMA-DTI working group, showed most tracts in the brain are moderately to highly heritable across cohorts of different ethnicities, even though they were imaged with different parameters. The “skeleton” of the white matter, reconstructed using a widely used DTI analysis program called “tract-based spatial statistics” (TBSS; Smith et al. 2006), is shown in purple for reference. The corticospinal tract (in light blue) was the least heritable region of interest and therefore, will not be carried forward as a phenotype in an initial GWAS of DTI-FA measures. Other methods for phenotype selection and prioritization are summarized in Table 1

Fig. 5

Locations of the ENIGMA Working Groups. After ENIGMA’s first project was completed (ENIGMA1; Stein et al. 2012), large amounts of brain imaging data had been analyzed from patients with a variety of psychiatric disorders. Working groups (WGs) were formed to understand the effects on the brain of bipolar disorder, major depressive disorder (MDD), schizophrenia, by pooling and comparing data from many neuroimaging centers. These groups are open to any researchers who have collected MRI scans from patients with these illnesses. No genetic data is needed to join. In fact, most projects study factors that might influence how these disorders affect the brain—medications, geographic factors, and the age and gender of the patient. A further working group focuses on diffusion tensor imaging, which assesses white matter integrity; current projects relate DTI measures to individual differences in cognition and genetic make-up. The institutions in the working groups, as of June 2013, are shown on the map (see color key, inset)