EpiVar Browser: advanced exploration of epigenomics data under controlled access

Abstract

Motivation: Human epigenomic data has been generated by large consortia for thousands of cell types to be used as a reference map of normal and disease chromatin states. Since epigenetic data contains potentially identifiable information, similarly to genetic data, most raw files generated by these consortia are stored in controlled-access databases. It is important to protect identifiable information, but this should not hinder secure sharing of these valuable datasets.

Results: Guided by the Framework for responsible sharing of genomic and health-related data from the Global Alliance for Genomics and Health (GA4GH), we have developed an approach and a tool to facilitate the exploration of epigenomics datasets' aggregate results, while filtering out identifiable information. Specifically, the EpiVar Browser allows a user to navigate an epigenetic dataset from a cohort of individuals and enables direct exploration of genotype-chromatin phenotype relationships. Because individual genotypes and epigenetic signal tracks are not directly accessible, and rather aggregated in the portal output, no identifiable data is released, yet the interface allows for dynamic genotype-epigenome interrogation. This approach has the potential to accelerate analyses that would otherwise require a lengthy multi-step approval process and provides a generalizable strategy to facilitate responsible access to sensitive epigenomics data.

Availability and implementation: Online portal: https://computationalgenomics.ca/tools/epivar; EpiVar Browser source code: https://github.com/c3g/epivar-browser; bw-merge-window tool source code: https://github.com/c3g/bw-merge-window.

Figure 1.

EpiVar Browser architecture. The EpiVar Browser interacts with multiple data nodes on secure web servers, each of which can generate summary data box plots on-the-fly using sample bigWig files for a selected assay and genotype information (A). In this example, the generated plots reveal correlations between the rs12049454 SNP genotype and chromatin accessibility in both noninfected and flu-infected cells. Genotype groups with insufficient sample count are masked. The merged signal for the feature, stratified by genotype, can be visualized in the UCSC Genome Browser or an integrated igv.js browser instance (B)