Answering Biomedical Questions
RENCI scientists are supporting rapid exploration of data by building a COVID-19 version of their question-answering system called Reasoning Over Biomedical Objects linked in Knowledge Oriented Pathways (ROBOKOP).
ROBOKOP is a biomedical question-answering system based on a knowledge graph, meaning that it expresses data as a collection of nodes—such as genes and diseases—and edges that represent the relationships between the nodes. ROBOKOP uses multiple open biomedical databases to explore relationships between various biomedical data types. For example, it can be used to examine relationships between a disease and a drug and then explore which genes might be involved in that association.
RENCI scientists have created a special COVID instance of ROBOKOP by integrating the original knowledge graph with the CORD-19 literature co-occurrence graphs they developed, viral protein functions, and hand-curated symptom information. This combination will give scientists access to a vast amount of information about human genes, chemicals, and respiratory diseases and allow them to ask important questions about how that information relates to COVID-19. The new COVID-19 version of ROBOKOP is available at http://covidkop.renci.org/.