Several possible studies
Story checked
Researchers use AI to design proteins that cut up other proteins - Ars Technica (opens in a new tab)
arstechnica.com · 2026-10-14
Short answer
Several possible studiesNo clear answer.
More than one paper fits the article's details, and none fits well enough to single out. Checking claims against the wrong study would be worse than not checking them at all.
Checked against the study summary. The full text wasn't available, so some details couldn't be settled either way.
Share this check
The story
Researchers use AI to design proteins that cut up other proteins - Ars Technica
arstechnica.com · 2026-10-14
The story’s checkable claims.
Read the original story (opens in a new tab)NewsLink checks it
Several studies could be the source of this story.
More than one paper fits the article's details, and none fits well enough to single out. Checking claims against the wrong study would be worse than not checking them at all.
Open claim evidenceSearch result
Several studies could fit.
More than one paper fits the article's details, and none fits well enough to single out. Checking claims against the wrong study would be worse than not checking them at all.
Source layer
The 2 papers the story cites
Source study separated from background citations.
The research anchor for the report.
- Points somewhere elsementioned without context
10.1038/s41586-026-11143-w
- Points somewhere elsementioned without context
10.1038/s41586-026-11167-2
Evidence layer
Claim by claim
What the story asserts. With no source study, there is nothing to check these against.
Reading mode
Scan verdicts. Open evidence only when needed.
Claim 1 of 8Not checkedResearchers used AI-based protein design tools to take the catalytic core of two kinds of protease and replace the rest of the protein, creating new enzymes that could be tuned to cut specific proteins in half.View evidenceHide evidence
Not checked
NewsLink could not identify one source study, so this claim was not compared against a paper.
Claim 2 of 8Not checkedThe researchers demonstrated the designed enzymes by using them to cut proteins associated with neurological diseases.View evidenceHide evidence
Not checked
NewsLink could not identify one source study, so this claim was not compared against a paper.
Claim 3 of 8Not checkedThe work came from researchers primarily in David Baker’s lab at the University of Washington and used RFdiffusion2, ProteinMPNN, and AlphaFold3 in the design and screening process.View evidenceHide evidence
Not checked
NewsLink could not identify one source study, so this claim was not compared against a paper.
Claim 4 of 8Not checkedFor the cysteine protease design, 13 designs worked, a success rate of 19 percent, and they were less active than the yeast enzyme used as the model.View evidenceHide evidence
As stated13 designs; 19 percent
Not checked
NewsLink could not identify one source study, so this claim was not compared against a paper.
Claim 5 of 8Not checkedFor the zinc protease project, 35 out of 38 designs that included a placed water molecule showed some catalytic activity, and one optimized version accelerated peptide-bond cleavage by a factor of 10^9 while remaining highly specific for the intended target sequence.View evidenceHide evidence
As stated35 out of 38; 10^9
Not checked
NewsLink could not identify one source study, so this claim was not compared against a paper.
Claim 6 of 8Not checkedA second zinc-based version was reported as 30 times more active than the original design and to accelerate peptide-bond cleavage by a factor of 10^10.View evidenceHide evidence
As stated30 times; 10^10
Not checked
NewsLink could not identify one source study, so this claim was not compared against a paper.
Claim 7 of 8Not checkedThe article says the researchers also designed zinc proteases to target proteins associated with Alzheimer’s disease and frontotemporal dementia and were able to find one that could cut the intended target in cells.View evidenceHide evidence
Not checked
NewsLink could not identify one source study, so this claim was not compared against a paper.
Claim 8 of 8Not checkedThe article notes major limitations, including protein delivery, possible immune responses, and the difficulty of using the approach inside cells, and says the tools are better at producing the right structure than the desired catalytic activity.View evidenceHide evidence
Not checked
NewsLink could not identify one source study, so this claim was not compared against a paper.
Method layer
No single source study was found.
NewsLink still surfaces nearby research so you can inspect the field instead of a single paper.
Nearby research
No exact source, but these papers are close.
PubMed, Crossref, Europe PMC · 15 candidate papers
Substrate specificity in a designed RAS-targeting protease is coupled to active site and distal motions.
bioRxiv : the Preprint Server for Biology · 2026 · PubMed
c-di-GMP mediated regulation of the LapA biofilm adhesin through proteolysis by the calcium-dependent cysteine protease LapG
Crossref
De Novo Synthesis in Cancer Immunotherapy: Applications and Prospects.
2026 · Europe PMC
Prediction and design of protease enzyme specificity using a structure-aware graph convolutional network.
Proceedings of the National Academy of Sciences of the United States of America · 2023 · PubMed
The 85-kD Crystalline cysteine protease inhibitor from potato contains eight cystatin domains
Protein Engineering, Design and Selection · 1993 · Crossref
And 10 more candidates considered.