A Strategy to Identify Drug-Resistant Bacteria

By Katy Mena-Berkley
Tuesday, September 8, 2020

Game theory could be the key to identifying dangerous antimicrobial-resistant bacteria.

Every year antimicrobial-resistant (AMR) bacteria and fungi are responsible for more than 2.8 million infections and an estimated 35,000 deaths in the United States, according to the CDC. However, researchers with Washington State University (WSU) are working to shift the narrative with new technology.

The research team includes PhD computer science graduate Abu Sayed Chowdhury, Shira Broschat in the School of Electrical Engineering and Computer Science, and Douglas Call in the Paul G. Allen School for Global Animal Health. Together, they have created new software designed to recognize drug-resistant genes in bacteria.

A Concept for Clinical Solutions

Bacteria become resistant to medications such as antibiotics when they begin to evolve and develop genes encrypted with mechanisms to make the bacteria immune to drugs. Strains of drug-resistant staph- or strep-causing bacteria that lead to diseases such as pneumonia and tuberculosis are notoriously hard to treat and sometimes may not respond to treatment at all.

To target those types of bacteria, which are expected to become more ubiquitous in the decades to come, the WSU researchers crafted a machine-learning algorithm. This algorithm incorporates the concept of game theory to identify AMR genes in the environment.

Using this strategy, the research team was able to closely study genetic material, structure and composition of protein sequences and develop software to identify AMR genes that may have otherwise gone undetected.