Landing Image

HOPE Consortium
Healthy Outcomes of Pregnancy for Everyone through Science, Partnership, and Equity

 

 

The HOPE Accelerator is a data collection, analysis and visualization platform that allows consortium partners to share data seamlessly and securely while taking advantage of state-of-the-art anaytic and data visualization capabilities.

The HOPE Accelerator was built by Omics Data Automation (ODA) Inc. for the HOPE Collaborative. Partners are able to combine different kinds of data (clinical, molecular, survey, geographical) from one or multiple studies. The platform is designed to boost progress by offering a place where data from multiple studies can be combined, analyzed and visualized. No identifying information for participants is kept within the system, which insures that information is shared without any compromise to privacy.

 

 

Combining Data

Through the HOPE Accelerator, investigators can combine (pool) data from multiple studies to look for common patterns and trends. We do this by establishing an initial data footprint (data type, format, units) from the core study. Then, subsequent data is tested and translated to fit into that initial footprint.

Once completed, investigators are able to look at patterns across multiple studies using either a dashboard, standardized reports, by using Python or R in an embedded notebook environment or a 3D data explorer.

HOPE Accelerator Flow

Example Dashboard

 

Data and Standardized Reports

For large studies like the HOPE COVID-19 study, a study dashboard can be created in the HOPE Accelerator that will allow the investigator and study team to track the number of participants in the study overall and by grouping. 

Data can also be translated into standardized reports that capture data that the study team wants to be able to track and highlight on an ongoing basis.

 

 

 

2D Analyses Using Notebook

The HOPE Accelerator includes embedded coding languges like Python and R. This capability allows investigators to carry out all analyses that these coding languages allow and visualize the results within the platform.

The HOPE Accelerator also allows for supervised and unsupervised machine learning and artificial intelligence, which allows investigators to look for patterns in large sets of complex data.

 

Heat Map

pregnant Black woman with face mask

 

3D Exploration

Using the HOPE Accelerator, investigators are able to explore relationships between multiple types of data, across multiple participants, and across time.

The 3D tool tags clinical, laboratory and molecular data and then visualizes that information.

Investigators are able to drive through the 3D tool using an embedded graphics interface. This capability allows investigators to identify potential relationships and then explore them using the embedded network tools. This allows for rapid discovery.

 

 

 

Looking at Data Accross Time

Using the HOPE Accelerator and the 3D explorer, investigators are able to look at participant data over time. Looking at longitudinal data through a 3D perspective allows patterns to be quickly identified and explored.

Investigators are able to identify potentially important patterns in minutes rather than in the days and weeks that identification of promising targets would take using only analysis tools.

light design

pregnant Black woman with face mask

 

Exploring Geographic Patterns

Using the HOPE Accelerator platform, investigators are able to identify signals in the data that may be specific to certain geographies.

Participant data can be overlaid onto maps at a neighborhood, city, state, or country level.

The visualization tool provides clues that can be further investigated in the notebook environment or using other platforms like ArcGIS via the use of data download.