Researchers worldwide publish 2.5 million journal articles each year, adding to the tens of millions of scholarly articles in circulation. For a researcher or clinician, developing a holistic understanding of a field — for example, the systematic matching of genomic alterations in a tumor with proper drug treatments — is an immense task.
Now imagine that those researchers, faced with trying to understand the various mechanisms and cellular processes involved in a specific tumor type, had a new tool: an automated system that could review all that literature — analyzing each academic paper in seconds — and extract key information that could help them generate easily interpretable answers and conclusions.
Not only have researchers at the University of Arizona built such an automated information-extraction system, they are bringing it to the world through a startup, Lum.AI.
Mihai Surdeanu, associate professor in the department of computer science in the College of Science, was the lead inventor who worked in collaboration with then-Ph.D. candidates Gustave Hahn-Powell and Dane Bell from the College of Social and Behavioral Sciences, both of whom were focusing on computational linguistics. Also on the team was computer science post-doc Marco Antonio Valenzuela-Escárcega.
“We were faced with the problem of developing a holistic understanding of the field of signaling pathway fragments involved in cancer from biomedical research,” says Surdeanu. “We needed an automated system to extract that information from the millions of papers and journals published each year.”
Not only did the team develop this system, but they designed it with the end-user in mind, ensuring that the results generated are easy to interpret.
The inventors worked with Tech Launch Arizona, the office of the UA that commercializes inventions stemming from university research, to protect the intellectual property and develop their company launch strategy. They licensed the UA technology into their startup — Lum.AI — in 2016.
Throughout that process, they worked with TLA’s Kevin McLaughlin, mentor-in-residence and an experienced technology entrepreneur, who eventually accepted the position of CEO with the company.
The team’s original direction in the cancer space helped them find new clients and opportunities, including support from DARPA and the Melinda Gates Foundation. They have since made the decision to expand into agriculture.
“In early 2018, we started looking at where the startups were in the human-bio space,” says McLaughlin, noting that there are seven times more startups in the human space than the agriculture space. “The agriculture companies are really underserved and there is very little investment happening in companies that are making data useful to producers, agronomists and the like. That’s a hole in the market that we saw we could fill.”
To date, they have partnered with The Soil Health Institute, The American Society of Agronomy, Crop Science Society of America and Soil Science Society of America.
“There are any number of market spaces where this UA invention can make a difference,” says McLaughlin, “so we’re excited to see what’s next.”