Promote a data-driven culture — securely streamline on-demand access to data and faster analysis. Store and share your useful data artifacts (UDATs) from one platform.
A single platform for data management and analysis
Accessible, reusable data products
- Turn data sources, data files, and metadata into accessible data products
- Manage multiple data products in one platform. Reduce data inconsistency and duplications.
- Integrate public data with proprietary data
- As new data arises, you can rapidly develop and use new data products
- Data products are updated on your preferred schedule, keeping your data and analyses current, versioned and reproducible
- Each data product comes with analysis apps which are tailored to that dataset
On-demand analysis apps
- Gain autonomy over your data analysis process within a guided environment
- Confidently ask and answer your own questions by running, iterating, and re-running analyses in your own terms
- Perform simple and advanced statistical analysis without learning to code
- Use and reuse R & Python scripts created by your data scientists as analysis apps
See the Algorithms
See Apps for Life Sciences
See Apps for Healthcare
Parameterize without coding
- Design a cohort dynamically – observe the changes in your cohort size with every selection
- Analyze your cohorts using point-and-click parameter selection
- Use the search function to easily find your parameter of interest from large collections
- Instantly iterate on analysis by modifying your previous set of parameters to generate a new set of results
Accessible useful data artifacts (UDATs)
- UDATs are digital objects create when you or an algorithm analyze the data
- Examples of UDATs are cohorts, analysis results, and groups of variables that represent gene signatures or risk scores
- UDATs are automatically saved with provenance, making them easy to reproduce and use in subsequent analyses
Collaboration
- Re-run analyses from UDATs and share them with anyone on your team
- Sharing reduces redundant work
- UDATs support data-driven decisions, maximizing productivity and efficiency
- The transparent and executable history facilitates retention of institutional knowledge
Data Product Examples
TCGA Pan-Cancer Atlas And The Immune Landscape Of Cancer
This data product is a combination of data from two sources: TCGA Pan-Cancer Atlas and the Immune Landscape of Cancer. It has 10,967 samples from 33 cancer types.
COVID-19 Synthetic Data
This data product contains synthetic patient data mimicking a population tested for COVID-19.
Analysis App Examples
Cox Survival
Perform a cox regression survival analysis for the specified cohort.
Python Integration
Turn Python models and visualizations into analysis apps.
Analysis Result Examples
R Integration
Python Integration
UMAP & Clustering
Cox Survival
Pathway Analysis
Descriptive Statistics
ON-DEMAND WEBINAR
AWS Tech Talk For NIH:
An Introduction To Tag.bio
Learn how major Pharma companies and university health systems improve value-based care, drive the future of precision medicine, and promote collaboration (without explicitly moving data around).
How to Run an Analysis
Running an analysis in Tag.bio is as simple as choosing a data product, selecting an analysis app, setting the parameters, and hitting “run”.
“I feel like a data superhero!”
– Michelle Mourad, MD,
Vice Chair of Clinical Affairs and Value, Department of Medicine,
Medical Director, Transitions in Care, UCSF Health
