Northwestern University researchers may have uncovered how parts inside human cells interact with each other thanks to a newly developed machine learning algorithm technology.
According to a recent Northwestern press release, the new machine learning algorithm, "Sliding Window Inference for Network Generation" (SWING), uses time-series data to uncover underlying biological interactions and networks within human cells. Specifically, SWING uses "time-resolved, high-throughput data" to calculate the time it takes for cause-and-effect interactions of genes within the cell to occur.
"We want to understand how cells make decisions, so we can control the decisions they make," said Neda Bagheri, PhD, assistant professor of chemical and biological engineering at Northwestern University, in a statement. "A cell might decide to divide uncontrollably, which is the case with cancer. If we understand how cells make that decision, then we can design strategies to intervene."
Bagheri and her colleagues research was published Feb. 13 in the Proceedings of the National Academy of Sciences and the algorithm is open for public use to be applied to multiple disciplines.
"The framework is not specific to cell signaling or even to biological contexts," Bagheri said in the press release. "It can be used in very broad contexts, such as in economics or finance. We expect that it could have a great impact."