Virtual lab powered by ‘AI scientists’ super-charges biomedical research

In an effort to automate scientific discovery using artificial intelligence (AI), researchers have created a virtual laboratory that combines several ‘AI scientists’ — large language models with defined scientific roles — that can collaborate to achieve goals set by human researchers.

The system, described in a preprint posted on bioRxiv last month¹, was able to design antibody fragments called nanobodies that can bind to the virus that causes COVID-19, proposing nearly 100 of these structures in a fraction of the time it would take an all-human research group.

“These virtual-lab AI agents have shown to be quite capable at doing a lot of tasks,” says study co-author James Zou, a computational biologist at Stanford University in California. “We’re quite excited about exploring the potential of the virtual lab across different scientific domains.”

The experiment “represents a new paradigm of taking AI as collaborators, not just tools”, says Yanjun Gao, who researches the health-care applications of AI at the University of Colorado Anschutz Medical Campus in Aurora. But she adds that human input and oversight are still crucial. “I don’t think at this stage we can fully trust the AI to make decisions.”

Interdisciplinary AI

Scientists worldwide have explored the potential of large language models (LLMs) to speed up research — including creating an ‘AI scientist’ that can carry out parts of the scientific process, from generating hypotheses and designing experiments to drafting papers. But Zou says that most studies have focused on the application of LLMs for experiments with a narrow scope, rather than exploring their potential in interdisciplinary research. He and his colleagues set up the virtual lab to combine expertise from different fields.