Computer A.I. Solves 120-Year-Old Biological Mystery
A computer has developed a new scientific theory using only its artificial intelligence, without any help from humans. Continue reading →
A computer has developed a new scientific theory using its own artificial intelligence, without any help from humans.
At Tufts University, computer scientists and biologists programmed a computer to analyze the data gathered from numerous studies that focused on a mystery about a flatworm called a planarian (above) that has been puzzling biologists for 120 years.
It turns out that planaria are able to regenerate body parts, but how they do it is a complete mystery.
The computer analyzed the data from the previous studies on planarian regeneration and then attacked the problem independently by reverse engineering a solution to explain the mechanism of the regeneration process.
The computer's findings were published in the journal PLOS Computational Biology, and the artificial intelligence method used to reach the theory was also documented.
"It simulated the network formed by a worm's genes many times over until its results matched those from real-life experiments. Every time it managed to match the results, the computer modified the random genetic network it had created in line with the results and kept honing it until it created a core genetic network that matched the results of all the studies," Wired explains.
After three days of trial and error guesses, the computer discovered that the process required three known molecules and two proteins that were previously unknown.
The discovery "represents the most comprehensive model of planarian regeneration found to date," Levin told Wired. It also marks important milestones for both regenerative medicine and computers' A.I. potential, opening the door to solving more problems in the future.