With Claude’s help, researchers solve the first vault particle structure from prokaryotes

On Nov. 4, Anthropic’s biology research team said it had determined the first three-dimensional structure of a vault particle from prokaryotic cells. Vaults are large, hollow protein shells found in cells. They were discovered in 1986 by Leonard Rome and Nancy Kedersha, and their function is still unknown. In mammalian cells the shell is built from 78 copies of the major vault protein and has roughly three times the mass of a ribosome. The preprint went up on bioRxiv the same day and has not been peer reviewed.

By the company’s account, the team used Claude Science to search about 15 billion predicted proteins and found vault relatives in 29 bacterial phyla and four archaeal phyla, present in less than 1% of species with a sequenced genome. It tested 44 selected proteins in a cell-free system; of 24 moved into E. coli, 15 produced soluble protein, seven of those formed vault-like particles under an electron microscope, and cryo-electron microscopy confirmed four. The L05 vault, whose structure was worked out in detail, comes from a bacteriophage: 96 copies of a single protein, a mass of about 9.5 megadaltons, roughly 54 nanometers long and 45 wide. It is shorter than the mammalian shell but encloses about 25% more volume because it is more spherical.

Anthropic says a purification that conventionally takes about three days dropped to roughly 90 minutes with the size-exclusion chromatography Claude recommended; a first full structural model was ready in 34 hours, and the whole project took under four months. The company also lists mistakes: a protocol Claude wrote called for a growth medium additive that interferes with getting DNA into cells, setting the project back two weeks, and a standard step skipped early in cryo-EM processing produced a flawed map blended with its mirror image. The function of vaults has not been solved; what was solved is the structure of a prokaryotic vault. Rome, who joined the project as a paid consultant, said working out that function is still enormously challenging.

Anthropic@AnthropicAI

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: anthropic.com/research/investigating-vault-particles-with-claude