An artificial intelligence system has for the first time reverse-engineered the regeneration mechanism of planaria—the small worms whose extraordinary power to regrow body parts has made them a research model in human regenerative medicine.
The discovery by Tufts University biologists presents the first model of regeneration discovered by a non-human intelligence and the first comprehensive model of planarian regeneration, which had eluded human scientists for over 100 years. The work, published in the June 4, 2015, issue of PLOS Computational Biology, demonstrates how “robot science” can help human scientists in the future.
In order to bioengineer complex organs, scientists need to understand the mechanisms by which those shapes are normally produced by the living organism. However, a significant knowledge gap persists between molecular genetic components identified as being necessary to produce a particular organism shape and understanding how and why that particular complex shape is generated in the correct size, shape and orientation, said the paper’s senior author, Michael Levin, Ph.D., Vannevar Bush professor of biology and director of the Tufts Center for Regenerative and Developmental Biology.
“Most regenerative models today derived from genetic experiments are arrow diagrams, showing which gene regulates which other gene. That’s fine, but it doesn’t tell you what the ultimate shape will be. You cannot tell if the outcome of many genetic pathway models will look like a tree, an octopus or a human,” said Levin. “Most models show some necessary components for the process to happen, but not what dynamics are sufficient to produce the shape, step by step. What we need are algorithmic or constructive models, which you could follow precisely and there would be no mystery or uncertainty. You follow the recipe and out comes the shape.”
Such models are required in order to know what triggers could be applied to such a system to cause regeneration of particular components, or other desired changes in shape. However, no such tools yet exist for mining the fast-growing mountain of published experimental data in regeneration and developmental biology, said the paper’s first author, Daniel Lobo, Ph.D., post-doctoral fellow in the Levin lab.
To address this challenge, Lobo and Levin developed an algorithm that would use evolutionary computation to produce regulatory networks able to “evolve” to accurately predict the results of published laboratory experiments that the researchers entered into a database.
“Our goal was to identify a regulatory network that could be executed in every cell in a virtual worm so that the head-tail patterning outcomes of simulated experiments would match the published data,” Lobo said.
Tufts biologists devloped an algorithm that used evolutionary computation to produce regulatory networks able to “evolve” to accurately predict the results of published research on planarian regeneration.
As expected, the initial random regulatory networks usually could not produce any of the experimental results. New candidate networks were generated by randomly combining previous networks and performing random changes, additions and deletions. Each candidate network was tested in a virtual worm, under simulated experiments. The algorithm compared the resulting shape from the simulation with real published data in the database. As evolution proceeded, gradually the new networks could explain more experiments in the database comprising most of the known planarian experimental literature regarding head vs. tail regeneration.
First Regenerative Model Discovered by Artificial Intelligence
The researchers ultimately applied the algorithm to a combined experimental dataset of 16 key planarian regeneration experiments to determine if the approach could identify a comprehensive regulatory network of planarian generation. After 42 hours, the algorithm returned the discovered regulatory network, which correctly predicted all 16 experiments in the dataset. The network comprised seven known regulatory molecules as well as two proteins that had not yet been identified in existing papers on planarian regeneration.
“This represents the most comprehensive model of planarian regeneration found to date. It is the only known model that mechanistically explains head-tail polarity determination in planaria under many different functional experiments and is the first regenerative model discovered by artificial intelligence,” said Levin.
Lobo and Levin are both trained in computer science and bring an unusual perspective to the field of developmental biology. Levin majored in computer science and biology at Tufts before earning his Ph.D. in genetics. Lobo earned a Ph.D. in the field before joining the Levin lab.
The paper represents a successful application of the growing field of “robot science” – which Levin says can help human researchers by doing much more than crunch enormous datasets quickly.
The Latest on: Robot science
via Google News
The Latest on: Robot science
- ROBOTS, IMAGINATION, AND SPIRITon November 17, 2019 at 2:41 pm
I allowed as that was an interesting notion. Interesting, but like most expert prognostications and recommendations, probably wrong. Isaac Asimov authored the Three Laws of Robotics, foremost of which ...
- Miko 2, one of the best kids robots, lauched in North America- 9to5Googleon November 16, 2019 at 4:36 pm
Miko 2 answers questions about science, maths, general knowledge, history and much more ... The built-in video and audio chat functionality makes it easy to call up your kids by dialing their personal ...
- DENSO Robots Featured at New Cranbrook Institute of Science Exhibiton November 15, 2019 at 4:18 pm
will feature up to ten robots and a robotics display at Cranbrook Institute of Science's Robot Revolution exhibit, presented by PNC Bank. DENSO, a contributing sponsor of the exhibit, has long been an ...
- Researchers teach robots to use inference to complete complex taskson November 15, 2019 at 8:02 am
There’s much robots can achieve by observing human demonstrations, like the actions necessary to move a box of crackers from a counter to storage. But imitation learning is by no means a perfect ...
- Miko launches educational robot Miko 2 in time for holidays (+ 25% off)on November 14, 2019 at 3:44 pm
Children can converse and have their questions answered about history, maths and science – making the Miko 2 a personal robot with a built in, child-safe search engine. Parents have the ability to ...
- How to do robotics righton November 14, 2019 at 3:00 am
Other types of tasks may require the participants to write on the spot a program that would direct the robot to successfully travel through an obstacle course. Due to the increasing interest in ...
- Meet OffWorld, the startup that wants to mine the moon with a swarm of robotson November 14, 2019 at 2:00 am
Will the future of space exploration involve swarms of smart robots aiding astronauts by mining for resources, or even autonomously preparing other planets for human habitation? It sounds like (and is ...
- Helping Delivery Robots Find Your Front Dooron November 13, 2019 at 9:15 am
While the algorithms that currently drive most delivery robots do generally get them to the destination, they're not always efficient. "This MIT navigation system is an important step in this overall ...
- Astronauts to test drive a lunar robot from the space stationon November 13, 2019 at 3:03 am
They will also observe how well Parmitano and the science team back on Earth were able to communicate to make decisions and plans for controlling the rover. "Robots have the ability to extend our ...
- Nuclear warheads? This robot can find themon November 12, 2019 at 10:30 am
The prototype of such robots, being developed by the U.S. Department of Energy's (DOE ... a Princeton professor of engineering and co-director of the Princeton Program in Science and Global Security, ...
via Bing News