The University of North Carolina at Greensboro Sept. 10 announced that Dr. Prashanti Manda, assistant professor of informatics and analytics, has been awarded a five-year, $500,000 National Science Foundation CAREER award for a new project aimed at addressing one of the biggest challenges in the field of biology: data.
Biologists have a lot of data, but it isn’t always represented in formats that facilitate scientific inquiry and analysis. Manda, an Indian American computer scientist who focuses on bioinformatics, aims to develop algorithms that will allow scientists to recognize important biological concepts from literature more effectively, the university said.
Manda works with biological ontologies, or hierarchical classifications that give scientists a way to represent and catalog their findings.
Curators in biology labs spend a lot of time translating findings into ontology-based representations that are then cataloged in databases and made accessible to scientists across the globe, UNCG said in a report.
The problem with this current model? It’s incredibly tedious and time consuming, and there’s so much biological research being published. This has created a bottleneck of data, meaning that databases aren’t as updated as they should be, and therefore scientists don’t have access to critical new findings, the report added.
Manda’s solution is to develop a text-mining machine that will automate – and expedite – this process. The goal is to create algorithms that can “read” new research and identify ontological concepts with near-human accuracy, it said.
“We aren’t saying we can replace humans, and we don’t intend to, but we want to get as close to a human’s perception as possible,” said Manda in the report. “We hope that these methods will supplement human labor and free up curators to focus on other important data collection and analysis work.”
The first step of the project is to develop the algorithms. The second step is to figure out how to best evaluate effectiveness. The project is based on joint preliminary work performed in collaboration with Dr. Somya Mohanty in the Department of Computer Science, according to UNC-Greensboro.
Ultimately, this research could have big implications not just for the field of bioinformatics, but for biology and science as a whole, the report said.
“There are extremely important applications,” said Manda. “For example, human diseases can be represented using ontology concepts. We can use these computational methods to pinpoint disease models that may be related, and this data can also be used to help diagnose rare diseases. When I solve the bottleneck issue, that will mean we can have more of this data available. Papers published in 2020 can be analyzed in 2020. We don’t have to operate on old information.”
CAREER awards are prestigious grants designed to support early-career faculty who have the potential to serve as academic role models in research and education and to lead advances in the mission of their department or organization.