Meet e[datascientist]™

Explore and traverse ever-growing quantities of data in conversation with a context-specific multi-layer hypergraph. Easily navigate complex relationships between data and knowledge layers and entities. 

Perform intuitive, guided statistical data exploration, mining and analysis. Characterize life sciences data, understand distributions, associations, correlations and key patterns. Formulate hypotheses, select and utilize appropriate statistical tools for analysis.

Generate, formulate and explore questions, conjectures and hypotheses. Test previously unexplored associations in data. Conduct causal analysis given specific hypotheses and datasets. Navigate the knowledge graph to explore hypothesis-driven data interactions and generate multi-causal explanations.

Multi-criteria decision making framework to define, select and prioritize virtual cohorts. Create virtual cohorts and apply customizable valuation models for prioritization. Perform meta-analysis and downstream cohort data exploration. Generate and export interactive reports.

Multi-criteria decision making framework to select, prioritize and optimize targets. Collaboratively apply and modify valuation models to prioritize targets. Downstream target data exploration, prioritization model tuning and enhancement, and report generation.

Compose, import, maintain and share pipelines specific to many data types, and run pre-configured or customized data pipelines on platform. Visualize and tune pipelines via the knowledge graph, revealing previously unknown relationships in the data.

Accelerate the time to evidence, assemble and repurpose evidence to support claims and meet emerging regulatory requirements. Collaborate across departments to enable joint and traceable decision making. Verify and validate the claim generation process.

Systematize and automate data curation. Semantically enrich and contextualize data. Structure data and knowledge entities and relationships on the multi-layer hypergraph. Achieve data governance by design through adherence to reference data and ontologies.

Collaborative multi-criteria decision making engine to select, prioritize and optimize understanding of entity relationships. Customize automated data-driven valuation models to capture and test provisional hypotheses.

Recommendations and guidance through the entire statistical thinking process. Formulate appropriate hypothesis tests and select relevant statistical tools based on data types and structure on the multi-layer hypergraph.