REVEAL Multi-omics
REVEAL Multi-omics

Increase the tick-rate of decision-making with the entirety of therapeutic area biomarker development data FAIRLY organized in a multi-omics data commons.


“Now we can flexibly load all the different data types and studies in one place which allows all the scientists to browse through that and use that to drive their decision-making…. it’s 10-15x faster than the older PostgreSQL and MySQL schema that we were working with.”

Computational Biologist, Top 5 Pharma

REVEAL Multi-omics delivers:
  • Agility: Scientists get answers in minutes from REVEAL vs. days retrieving data from files, data lakes, and silo’d databases. Data is curated once, creating a single-point-of-truth resource for all. Users “query multiple data sets at one go”.
  • Scalability: Incorporate an unlimited number of proprietary and public data sets and reference data without slowing query responsiveness as data volumes grow.
  • Extensibility: Add new data types. Deploy any R, Python library functions.
  • Cost-effectiveness: Reduce TCO, including operational and data storage costs. We are driven to optimize algorithm performance to increase performance and reduce costs, year over year.
  • Reproducibility: Version raw, QA’d, and processed data as well as algorithm versions and machine-learning models. Guaranteed data integrity and security in a transaction safe and secure multi-user environment.
  • Scientific Results: REVEAL produced greater support for hypotheses with data from multiple studies.
Multi-Omics > Better Decisions

Multi-omics infographic

Relevant Publications and Posters
Speeding Up and Reducing Costs for Genomic Analysis with an Automated Distributed Task Service: a Comparison of REVEAL™: Biobank with Databricks’ Hail and Glow » FULL ARTICLE
Predicting Significance of Unknown Variants in Glial Tumors Through Sub-Class Enrichment » FULL ARTICLE