GoKawiilBiochemist Anna Pertl typed in her question, pressed Enter and left for the night.
The artificial-intelligence system that she had prompted is designed to produce innovative scientific hypotheses. But, unlike a typical chatbot, this AI tool — called Co-Scientist — doesn’t simply generate an answer in a single pass. It launches several autonomous AI systems, known as agents, to search for and synthesize information from papers, evaluate competing explanations, refine and critique hypotheses and iteratively test ideas against published evidence.
Why AI cannot do good science without humans
The process can involve vast quantities of computational power because agents pursue distinct lines of reasoning before converging on workable solutions. And that takes time. Long enough, Pertl jokes, for her to complete a long-distance triathlon, which she has done eight times since she started her PhD at the Whitehead Institute for Biomedical Research in Cambridge, Massachusetts.
On a rainy Tuesday in July, Pertl put the AI system to work on one of cancer’s most complicated problems. She asked Co-Scientist for non-obvious but practical ways of harnessing the biology of molecular droplets known as condensates to shut down MYC, a protein that runs amok in most cancers and has long defied attack attempts.
The request built on years of research by Pertl’s supervisor, Whitehead biologist Richard Young. In 2018, Young and his colleagues found that cells switch on crucial genes by gathering regulatory proteins into condensates that cluster at important genome-control regions called super-enhancers1. They also worked out how cancer cells hijack these super-enhancers to send the gene encoding MYC into overdrive, a strong hint that condensates help to fuel the high expression rate of the protein2.
To Young, the obvious next step is to target the tumour cells’ condensates directly. Dewpoint Therapeutics in Boston, Massachusetts, a company that he co-founded, is now exploring that option. However, because previous attempts to subdue MYC failed, Pertl wanted to see whether AI could come up with a fresh line of attack.
Getting to an idea worth pursuing took some work. Pertl and Whitehead bioengineer Kalon Overholt spent close to an hour going back and forth with Co-Scientist before it understood the question. At first, the AI model assumed that the protein clusters at the centre of the research were meant to be the drug rather than the target. The tool also assumed that the clusters always activated gene expression, when in fact some do the opposite.
Once Pertl and Overholt had corrected these misconceptions, they set the system loose. By the next day, Co-Scientist had combed through more than 700 scientific papers and generated 108 possible strategies. It rejected all but one of the approaches as unworkable. The last strategy turned the laboratory’s thinking on its head.
Rather than dissolving the clusters — the method that Dewpoint is pursuing — the AI tool proposed gluing them together. Using a molecular linking technology called click chemistry, the approach smushes proteins that either activate or repress the MYC gene into one gooey mass, setting off a chain reaction until MYC’s DNA can no longer be read.
... continue reading