The massive amount of COVID-19 research being published requires new tools

With COVID-19 scientific literature being published at the rate of 4,000+ articles per week, it is nearly impossible for researchers to keep up with this rapidly evolving stream of technical data.  The US Government recognized the problem and, earlier this year, released the COVID-19 Open Research Dataset (CORD-19), to give researchers access to a comprehensive machine-readable Coronavirus literature collection. Still, simply searching on keywords is time-consuming.

In response to this, we created an advanced NLP application to (1) help scientists quickly find the important information that they might otherwise miss (or never get to) and (2) to provide new insights about relationships between things like human and viral genes and proteins, cell types, and subcellular structures.

Giving scientists a new way to look at scientific literature

Building on OmniScience’s NLP platform we created a COVID-19 research tool that we think will be powerful because it:

• incorporates COVID-19 specific dictionaries with all the alternative synonyms to identify genes and proteins that may have multiple names in the literature,
• creates beautiful and intuitive data visualizations to view relationships between biological entities, with an emphasis on entities’ impact on one another’s biological function,
• has a novel AI Summary feature so one can quickly read the most important points across multiple publications on a given search topic,
• uses cloud architecture to automate the processing and retrieval of data ensuring up-to-date information.  
  

We couldn’t have done this without our amazing, purpose-driven team

We would like to extend a special thank you to our team for the dedication, excellence, and expertise contributed to the development of this application.