Dan Johnson, associate professor of economics and business, and Matthew Whitehead, assistant professor of mathematics and computer science, received an honorable mention in the U.S. Commerce Department’s United States Patent and Trademark Office’s Cancer Moonshot Challenge, part of the White House Cancer Moonshot Task Force. The task force aims to speed up patient-focused cancer treatments, increase patient access to clinical trials and therapies, and align policies that improve the ability to prevent cancer and detect it at an early stage.
In their proposal, titled “Seeing the Forest AND the Trees; An Introduction to the Patent Projection Graphing Prototype,” Johnson and Whitehead used neural networks and linguistics to visualize and compare networks of patent documents centered on individual cancer-related concepts. Their prototype creates an online interactive visualization tool for analyzing the semantic proximities of U.S. patent documents that are related to cancer research and treatments.
This tool allows the user to perform keyword searches and then presents visualizations of sets of relevant patent documents clustered by semantic similarity. Semantic similarity is calculated using a combination of word embeddings obtained using the skip-gram algorithm and the t-SNE dimensionality reduction algorithm.
The user may then select individual points in the cluster to view more detailed patent information. This process allows the user to explore the connections between related patents and see more general trends in the semantic shape of the technological space. “It is our hope that this tool may serve as one of the starting points for data analysis leading to future innovative approaches to cancer treatment,” write Johnson and Whitehead in their submission. Their proposal was honored for the unique and innovative methodology applied.
Johnson has been on the faculty at Colorado College since 2004 and Whitehead joined the Colorado College faculty in 2010.