Anthropic biology team uses Claude to map the first 3D structure of a bacterial vault particle
Anthropic's biology research team used Claude to map the first 3D structure of vault particles in bacteria and the viruses that infect them; this type of barrel-shaped protein structure had previously only been found in animal and plant cells. Claude participated in the actual wet lab workflow, cutting particle isolation time from 3 days to about 90 minutes, and produced the first 3D structure model within 34 hours, whereas manual analysis would originally have taken weeks to months. Anthropic also stated that Claude made some simple mistakes during the process, which the team handled in collaboration with machine learning researchers.
Why read this
SelectedAI score 80
The original text provides specific time comparisons for Claude's participation in the wet lab workflow, and also notes that it made simple mistakes along the way, which can be used to judge the boundaries of AI-accelerated scientific research.
Topics
View original postWe’re sharing how our biology research team worked with Claude to map the first 3D structure of a vault particle from bacterial life. Vault particles are a longstanding mystery. They are barrel-shaped objects, among the largest protein structures found in our cells. They were first discovered by Leonard Rome and Nancy Kedersha in 1986, but their function remains unknown. With Claude, we’ve found results that might bring us closer to solving that mystery. Until now, vaults were only known in the cells of complex things like animals and plants. We have shown that similar proteins from bacteria (and the viruses that infect them) can also assemble into vaults. Finding the structures in these simpler forms of life may make it easier to investigate their function in our own cells. For our life sciences team, the project was also a demonstration of the potential (and the limitations) of using AI to accelerate science. In our full piece, we discuss how Claude was able to dramatically speed up some stages—manually determining the vault particle’s structure would have taken weeks to months of painstaking work, but here it took days. We also discuss how Claude made some simple mistakes along the way, and how we collaborated with our machine learning researchers to address them. Read more: https://t.co/KowVVCSPp8
View original
We’re sharing how our biology research team worked with Claude to map the first 3D structure of a vault particle from bacterial life. Vault particles are a longstanding mystery. They are barrel-shaped objects, among the largest protein structures found in our cells. They were first discovered by Leonard Rome and Nancy Kedersha in 1986, but their function remains unknown. With Claude, we’ve found results that might bring us closer to solving that mystery. Until now, vaults were only known in the cells of complex things like animals and plants. We have shown that similar proteins from bacteria (and the viruses that infect them) can also assemble into vaults. Finding the structures in these simpler forms of life may make it easier to investigate their function in our own cells. For our life sciences team, the project was also a demonstration of the potential (and the limitations) of using AI to accelerate science. In our full piece, we discuss how Claude was able to dramatically speed up some stages—manually determining the vault particle’s structure would have taken weeks to months of painstaking work, but here it took days. We also discuss how Claude made some simple mistakes along the way, and how we collaborated with our machine learning researchers to address them. Read more: https://t.co/KowVVCSPp8
Body
Anthropic’s biology lab used Claude to find and map a vault particle, a hollow barrel of protein that has sat unexplained in human cells since 1986, inside bacteria and the viruses that infect them, which nobody had shown before.
> Claude ran the actual wet-lab pipeline, not just the reading, cutting particle isolation from 3 days to about 90 minutes and delivering a first 3D structural model in 34 hours instead of weeks.