HARTFORD (CBS Connecticut) – Artificial intelligence has done what a century’s worth of scientific observation has not: explain how a flatworm is able to regrow body parts.
Researchers at Tufts University designed the AI system based on principles of evolution.
It was programmed by Daniel Lobo, a post-doctoral researcher at Tufts and co-author of the study. The program works by taking models that attempt to explain how regeneration occurs and subjecting them to a process of “natural selection.”
Computer models are run through a virtual simulator that mimics various experiments on the planaria worm. The results are then compared with published experiments in which the worms were cut into pieces and manipulated before regenerating back into full organisms.
“We picked this problem because it really is incredibly interesting,” said Michael Levin, another study co-author. “These worms are basically immortal, you can cut them up and they continuously form new organisms. And why that happens could be key to developing everything from regenerative medicines to designing self-repairing robots.”
In each cycle, the potential models that best fit the results are “married” to each other to create new models and less accurate models are discarded. This process is repeated until the models “evolve” into one that fits the data perfectly.
“Here, the computer really did give back more than what was put in,” Levin told Live Science. “None of us could have come up with this model. We, as a field, have failed to do so after over a century of effort.”
Using this process, the AI system was able to produce a model that correctly predicted all 16 experiments included in the data within just 42 hours. The model also anticipated the results of a series of novel experiments carried out by the researchers to test its predictive power.
Previous explanations for the planarian worm’s regenerative ability have been incomplete. The Tufts AI was able to recreate a comprehensive model of the entire process for the first time.
The researchers are now working to improve the model, and they hope in the future to apply it to other areas of developmental biology, such as the growth of embryos and even the creation of self-repairing robots.
The study is published in the journal PLOS Computational Biology.
(TM and © Copyright 2015 CBS Radio Inc. and its relevant subsidiaries. CBS RADIO and EYE Logo TM and Copyright 2015 CBS Broadcasting Inc. Used under license. All Rights Reserved. This material may not be published, broadcast, rewritten, or redistributed.)