• a giant leap forward
    in data curation

e[curate] is an innovative application that has injected significant efficiencies into the R&D process within the life sciences sector. With its ability to enrich existing data with quality metrics and semantics, it empowers scientists to spend less time finding their data and more time on analysis.
(Available May 2017)

How it works

The e[curate] platform will link and automatically annotate data sources or specific R&D data with the appropriate semantic content. Historically, automated curation has been a notoriously difficult process. This is because most semantic enrichment approaches are reliant solely on ontologies to provide domain-specific content. We enhance these methodologies with both process modelling to identify missing attributes and guide tag placement and data valuation to optimise the enrichment process against specific business objectives.

Business Benefits

Reduces time to discovery

e[curate] will dramatically reduce time to discovery and product development milestones

Increase in research productivity

We estimate an annual efficiency improvement for data scientists ranging from 15-70% with a median of 30%. This will effectively double a scientist’s available time over a maximum period of 3 years

Allows scientists to self-service their data needs

This innovative approach based on the Decision and Conversation Theory enables scientists to converse with the system thereby building understanding and context around experimental data. Users can interact with the curation process potentially introducing term or ontology refinements ‘on the fly’.

Facilitates collaboration and future scalability

Information gathering and integration using e[curate] becomes an experimental process that can be captured, shared, repeated and improved based on business output metrics and data valuation.

Module Features

Conversational Interface  »  for searching and “interacting” with the data in the catalogue.

Semantic Compass  » to enrich searches and promote understanding of biological questions.

Custom Reporting  » in support of different scientific R&D disciplines.

Data Governance support, » including data models, ontologies, data classification and downstream analytics.

Built-in A.I.  » using deep learning and machine learning technologies to predict, guide and support user behaviour, data discoverability and research aims.

Custom Widgets  » to serve different scientific domains or business environments.

Our Smart Data Management Platform

e[curate] is part of our proprietary software suite that bridges the entire process from the medical data through to insight.

automated data scientist logo