The Dayhoff Atlas introduces GigaRef, an open set of 3.34B natural protein sequences in 1.70B clusters, and BackboneRef, 46M synthetic sequences.

The paper

The paper's details are OpenAlex's; the citation count is OpenAlex's, 15 Oct 2026. The line on the paper is machine-written, as noted under Why it matters.

Why it matters

Written by Claude (claude-sonnet-5-5) on 15 Oct 2026 from the paper's abstract (as the publisher's record at Crossref publishes it) and its OpenAlex record. Machine-written context to help a reader: it is not evidence, it moves no number, and it may be wrong. The quoted sentence is the claim; where it stands is computed from the record. If it misreads the paper, tell the stewards.

The story so far

1. 1

   What the authors did

   The authors assembled two sequence datasets, one from genomic and metagenomic sources and one derived from synthetic backbones. They then trained protein language models on them and tested the generated proteins for expression.

   Machine-written from the paper's abstract, as noted under Why it matters.

2. 2

   What they found

   • GigaRef is described as the largest open dataset of natural proteins, with 3.34B genomic and metagenomic sequences in 1.70B clusters.
   • BackboneRef distils structural information from 240,811 synthetic backbones into 46M synthetic sequences.
   • The Dayhoff language models can predict mutation effects, scaffold structural motifs and generate novel proteins within families, and training on metagenomic and structure-based synthetic sequences increased expression rates of generated proteins.

   Machine-written from the paper's abstract, as noted under Why it matters.

3. 3

   What has been checked on Ecdysis

   Exuvia registered the claim on 15 October 2026, with a test written from the paper. No check has been filed yet.

What would check it

How far it has been checked

1. 1
   The object itself, checked againverification · not yet

   Not yet: re-run the paper's analysis on its own data, where the authors have published it.

2. 2
   New instances of the constructionreproduction · not yet

   Not yet: the same construction run afresh.

3. 3
   The designrobustness tests and arguments · not yet

   Nothing yet: change the method or the data and see whether it holds (a robustness test), or argue that the method does not test what the claim says.

How sure is the record?

Share this finding

Ready-made posts, written from the record. You post them yourself, from your own account; nothing is ever posted for anyone.

Click a post's text to select all of it. Both posts give the claim's standing on the record, and the longer one says what the checks show and what they do not; the wording changes when the record does. The longer post quotes the paper first, then gives the machine-written headline, marked as such; edit it as you like. To cite the claim, see Cite this claim.

What would prove it wrong

Refuted if the publicly released GigaRef dataset contains fewer than 3.34 billion sequences or fewer than 1.70 billion clusters, or if BackboneRef contains fewer than 46 million synthetic sequences derived from 240,811 backbones; equivalently, if the metadata files or accompanying documentation report counts that differ by more than ±0.5% from those stated in the claim.

The test as Exuvia registered it on 15 Oct 2026, written from the paper's words.

The wider literature

Other claims from the same paper

• uncheckedDayhoff protein language models, trained on the new GigaRef and BackboneRef datasets, can predict mutation effects, scaffold motifs and generate proteins within families.“Leveraging these datasets, we trained the Dayhoff protein language models, which can predict mutation effects, scaffold structural motifs, and generate novel proteins within families.”
• uncheckedAdding metagenomic and structure-based synthetic sequences to training data raised the expression rates of proteins generated by the Dayhoff language models.“Training on metagenomic and structure-based synthetic sequences increased the expression rates of generated proteins, demonstrating the value of data diversity and scale.”

Headlines are machine-written from the paper's abstract, or from the quote and the paper's title where no abstract is open; each claim's own words are quoted beneath its headline.