Revolutionary Automated Data Curation Platform Launches as a 'Best of Show' Finalist at BioIT World 2017

Eagle Genomics, the smart data management company for life sciences, is today announcing the commercial launch of eaglecurate, a product set to revolutionize the time and resource intensive process of data curation. The platform has been named a Best of Show Finalist at BioIT World, the third year in a row the company has achieved such an award, winning last year’s Best of Show with eaglediscover.

Data curation is the single most significant bottleneck impeding progress towards data driven innovation at scale in Life Sciences R&D today. As scientific data generation accelerates and as data volumes increase, the current industry approach, employing costly armies of expert human biocurators, will present an ever more significant challenge.

eaglecurate addresses this challenge through automation of the data curation process and the automated semantic enrichment of curated data sets. This will drive dramatic productivity improvements in the innovation process and the targeted use of data assets for relevant analysis. eaglecurate is the latest addition to the company’s award winning “Automated Data Scientist” smart data management platform, putting data science at the fingertips of life sciences researchers and bridging the divide between data and new scientific insight.

Building on the foundations of the Best of Show award-winning eaglediscover product, eaglecurate enables value-driven data curation. It’s launch represents the maturation of many years of experience and thorough ethnographic observations of how biocurators actually work. When biocuration is focused on semantic enrichment, it is mainly a contextual activity that consists in constructing an “entailment mesh” of data sources, context and underlying entities of interest, rather than merely structural or syntaxical transformation. “Context” is often tacit and implicit in the mind of the biocurator and in the case of life sciences data it consists often in the experimental and design studies used to generate data.

By combining advanced machine learning and data measurement capabilities, eaglecurate allows for reverse-engineering of data into a graphical representation of the context, in the form of a process-oriented graph. The graph represents the experimental processes, study designs, observational studies and assays, etc., employed to generate the data. eaglecurate delivers a self-service platform to biocurators, bioinformaticians and scientists for curating their datasets by exploiting this sophisticated graph structure connecting process-elements and artefacts that, at the same time, provides executive management with an advanced dashboard for oversight enabling data governance by design.

According to Abel Ureta-Vidal, CEO of Eagle Genomics “eaglecurate is a truly innovative milestone towards automated data curation. It is the latest module of our smart data management platform bringing us closer to our vision and providing a conversational interface allowing the scientists to “talk” with their data.”