Technology at the service of health. Once again, technological advances have resulted in a clear benefit for human beings; in this case, in health matters. a group of scientists has developed a robotic system based on artificial intelligence to determine on its own what are the optimal conditions to grow replacement retinal layers necessary in various treatments aimed at restoring vision.
During the last experiment, the system managed a trial and error process covering a total of 200 million possible configurations and managed to dramatically improve cell culture viability necessary to carry out regenerative medicine therapy. An achievement that exemplifies how the automated design and execution of scientific experiments can increase the efficiency and speed of research in countless fields such as biology.
Autonomy, key in regenerative medicine
Traditionally, research in regenerative medicine requires numerous experiments that require a lot of time and work. In particular, creating specific tissues from stem cells – a process called induced cell differentiation – takes months of work, and the degree of success depends on a wide range of variables. Finding the optimal type, dose, and timing of reagents, as well as the optimal physical variables, such as cell transfer time or temperature, is difficult and requires an enormous amount of testing.
Thus, in order to make this process more efficient and practical, a research team led by Genki Kanda, from the RIKEN Institute in Japan, set out to develop an autonomous experimental system that can determine optimal conditions and grow functional retinal pigment layers from stem cells. For it retinal pigment epithelial cells were chosen because degeneration of these cells is a common aging-related disorder that leaves people unable to see. More importantly, transplanted retinal pigment epithelial layers have already shown some clinical success.
For autonomous experiments to be successful, the robot must repeatedly perform the same series of precise movements and manipulations; and artificial intelligence, for its part, must be able to evaluate the results and formulate the next experiment. The new system accomplishes these goals thanks to a general-purpose humanoid robot called Maholo, capable of performing high-precision biological experiments. Maholo is controlled by a software artificial intelligence that uses a newly designed optimization algorithm to determine which parameters should be changed, and how they should be changed, in order to improve differentiation efficiency in the next round of experiments.
What would have taken human researchers more than two and a half years, the robotic system with artificial intelligence only took 185 days. This translated into go from an initial efficiency in the differentiation rate of 50% to one of 90% thanks to the work of experimentation and improvement made by the robot.