NCATS Funding Opportunity Aimed at Building Computational “Brain” Prototype to Mine Disparate Data

Layers of nerve cells in the retina

This image captures the many layers of nerve cells in the retina. Credit: Wei Li, National Eye Institute, NIH

​NCATS announced that it is seeking applications to develop reasoning tool prototypes for its Biomedical Data Translator (Translator) program. Through a unique funding mechanism, candidates must complete a series of computational tasks in the first part of a three-step application process to access the complete funding opportunity announcement (FOA). The tasks, or “challenge,” are designed to provide important background and insights for building a biomedical reasoning tool prototype.

Through its Translator program, NCATS aims to develop a computational platform that brings together disconnected biomedical data types to reveal complex relationships that help scientists better understand disease behavior and biology, and develop treatment options.

Through this latest FOA, NCATS intends to fund up to three awards of approximately $1 million each to create Translator reasoning tool prototypes. The tool, or “brain,” will contain software algorithms needed to coordinate the different data sources and types to find relevant patterns and relationships among them and assemble the appropriate information to answer complex biomedical questions.

NCATS supports Translator through its Cures Acceleration Network (CAN), which enables high-risk, high-reward research funding and includes Other Transaction authority (OTA). OTA allows NCATS to employ innovative methods to support applications outside the normal National Institutes of Health funding approaches. This particular Translator “challenge” process will help ensure applicants have the requisite technical and problem-solving skills to develop a reasoning tool in a relatively short period of time. By successfully completing each challenge task, the applicant gains access to the next part of the FOA, and ultimately, the instructions for submitting the required concept letter which is due on Sept. 22, 2017.

“The challenge questions are aimed at attracting innovative, persistent individuals who can bring unique approaches to developing a Translator reasoning tool,” said Noel Southall, Ph.D., informatics, NCATS.

In recent years, the need for a tool like the Translator has become increasingly clear. Powerful new technologies are reshaping the landscape, enabling scientists to map and decipher the 3 billion chemical letters that make up the human genome. Electronic medical records contain warehouses of patient information and clinical databases house details on genomic and environmental variants that can affect disease susceptibility.

Despite the ever-growing amounts of data, researchers’ ability to make sense of them has not kept up. Ideally, scientists would easily mine different types of data from different sources to gain new insights into the causes of disease and the relationship between disease biology and clinical signs and symptoms. However, scientists frequently have a difficult time manually sifting through all of the data to make these connections.   

In fall 2016, NCATS funded research groups to determine the feasibility of building Translator. They currently are working together on “demonstration” projects aimed at assessing whether a biomedical data translator can be created.

“The currently funded teams are taking advantage of each other’s expertise and resources to determine the possibilities for Translator,” said Christine Colvis, Ph.D., NCATS Drug Development Partnership Programs director. “We expect the next stage of this research will bring these into clearer focus.”

Posted September 2017