Follow Us On

Closed-Loop Automation of Scientific Research

Closed-Loop Automation of Scientific Research



Recent advances in Artificial Intelligence (AI), especially machine learning (ML), are disrupting technological innovation, product development, and ultimately, society. AI is making a significant impact across the sciences, leaving few fields untouched, from material science to drug design, quantum physics to medicine. Indeed, the utilisation of AI is becoming characteristic of early 21st century science. Here we propose a future for AI and science based on scientists collaborating with teams of AI-driven closed-loop discovery laboratories, powered by self-driven hypothesis generation, and open-ended autonomous robotic experimentation. Automation of the very practice of science will increase the efficiency of scientific research, help mitigate the replication crisis, and potentially democratize scientific process. As was the case with AI and games, it is likely that advances in technology and AI will drive the development of ever-smarter AI systems for science. The Nobel Turing Grand Challenge aims to develop: AI systems capable of making Nobel-quality scientific discoveries highly autonomously at a level comparable, and possibly superior, to the best human scientists by 2050. Progress towards this challenge will unleash the deep potential of AI to search for and discover the fundamental structure of our world, and potentially transform the world through accelerated technological development. 


The application of Artificial Intelligence (AI) to science has a distinguished history.  Recent progress in AI and laboratory automation has made it possible to fully automate simple forms of scientific research. A Robot Scientist is a physically implemented robotic system that applies techniques from AI to execute cycles of automated scientific experimentation: hypothesis formation, selection of efficient experiments to discriminate between hypotheses, execution of experiments using laboratory automation equipment, and analysis of results. The motivation for Robot Scientists is to both better understand science, and to make science more efficient. Our Robot Scientist ‘Adam’ was the first machine to autonomously discover novel scientific knowledge.  Our Robot Scientist ‘Eve’ was originally designed to automate drug discovery, with a focus on neglected tropical diseases. We are now developing Genesis, a next-generation Robot Scientist designed to work on yeast systems biology. Genesis will soon be able to run 1,000 cycles of hypothesis-led experiment in parallel per day.