AI robot conducts research on its own theories
Researchers at the University of Gothenburg and Chalmers have developed a robot scientist that uses artificial intelligence to independently formulate scientific theories, design experiments and make new biological discoveries. The ‘AI biologist’ represents an important step towards the development of autonomous laboratories.
Drawing on the major advances made in large language models such as ChatGPT and Claude, as well as automated reasoning, the researchers have developed an AI system that has been tasked with conducting research based on vast amounts of scientific knowledge about common baker’s yeast, Saccharomyces cerevisiae, including the organism’s genome, metabolism and information from previous research studies.
Can identify biological questions
“It is not possible for humans to work from such enormous amounts of information. Our robot scientist, however, was able to identify biological questions, recommend experiments to test them, evaluate the results and iteratively refine its own knowledge in a closed feedback loop. It does not merely function as a data analyst and decision-support tool, but can actively generate new scientific knowledge,” says Ievgeniia Tiukova, a researcher at Chalmers and one of the authors of the study.
Combining AI ‘thinking’ with practical experimentation is unusual and at the forefront of a rapidly growing field in which AI scientists, or robot scientists, can independently carry out extensive experiments at a rapid pace. Ievgeniia Tiukova compares the development to self-driving cars, where AI and machine learning are also used to process information, draw conclusions and take action.
Accerelerate discoveries
According to Ross King, Professor at the Department of Computer Science and Engineering at the University of Gothenburg and Chalmers and senior author of the study, autonomous laboratories will revolutionise the world of research by making it possible to explore biological systems more rapidly and systematically.
“Robot scientists will work alongside humans and help accelerate discoveries in biology, medicine and biotechnology. Such AI systems have the potential to reduce the time required to explore complex scientific questions and optimise the use of laboratory resources,” says Ross King.
Humans remain essential
Both Ievgeniia Tiukova and Ross King emphasise that the purpose of autonomous AI laboratories is not to replace researchers, but to handle the more routine aspects of formulating hypotheses and designing experiments.
“Humans will remain essential for setting priorities, interpreting broader contexts, developing research programmes and ensuring compliance with ethical rules. Future generations of autonomous laboratories will become increasingly capable of collaborating with humans and will be valuable partners in efforts to solve the most challenging questions in biology and medicine,” says Ross King.
The study in Journal of the Royal Society Interface: Self-driven biological discovery through automated hypothesis generation and experimental validation
Ross King was the first to develop the concept of a general-purpose robot scientist. His first robot scientist, Adam, was designed to independently conduct scientific experiments and generate new knowledge. He later developed a second robot scientist, Eve, which was specifically designed for drug development.
The underlying concept – using robotic systems to automate and accelerate scientific discoveries – has since been extended to other fields of research, including chemistry and other specialised scientific tasks.