Researchers report in Nature that 13 of 69 de novo cysteine proteases, a 19% success rate, hydrolysed the polypeptide backbone. Measured as kcat/kuncat, the rate enhancement over the uncatalysed reaction reached up to 3 x 10^7.
Reality
- Evidence78
- Adoption
- Not scored
- Hype gap+15
- Incentives
- Not scored
- Confidence70
Google DeepMind's SynthID Bio embeds a traceable mark in an AI-designed protein that a detector can find in the physical molecule, without changing how it works. The mark is meant to help DNA synthesis firms screen orders and trace which model made a sequence.
Reality
- Evidence54
- Adoption36
- Hype gap+12
- Incentives66
- Confidence55
Google DeepMind's SynthIDBio hides a watermark in AI-designed proteins that a detector reads near-perfectly without weakening how they bind. The authors call it a proof of concept, and a determined user can still scrub the mark by rerunning a design through another tool.
Perspective Coverage
4 publishers
- Builder
- Builder 51%
- Operator
- Operator 36%
- Investor
- Investor 13%
Reality
- Evidence72
- Adoption25
- Hype gap+12
- Incentives62
- Confidence70
Google DeepMind's SynthID Bio watermark matched unwatermarked binders on hit rate, affinity and sequence diversity across three wet-lab targets. The company aims it at DNA synthesis screeners, who could use the signal to auto-clear orders from safeguarded AI models.
Reality
- Evidence42
- Adoption18
- Hype gap+18
- Incentives70
- Confidence45
The company's head of life sciences told Reuters that real lab work is still the final test in biology. Anthropic has not said which experiments the lab is running, and it has yet to run a clinical trial.
Perspective Coverage
5 publishers
- Builder
- Builder 28%
- Operator
- Operator 35%
- Investor
- Investor 37%
Reality
- Evidence55
- Adoption40
- Hype gap+30
- Incentives70
- Confidence57
The Allen Institute, the University of Washington and Fred Hutchinson are building models and databases of designed proteins. David Baker told WIRED the field usually sees that something works before it knows why.
Reality
- Evidence34
- Adoption
- Not scored
- Hype gap+45
- Incentives66
- Confidence52
Apple researchers report that one end-to-end training run on more than 2 million sequence-and-structure pairs competes with the usual tokenizer-then-generator pipelines.
Reality
- Evidence45
- Adoption10
- Hype gap+15
- Incentives62
- Confidence55
Protein design has graded its models on whether they can guess the sequence evolution happened to pick. An MIT group says that measures the wrong thing, and reports that leaning less on native sequences improves stability prediction.
Reality
- Evidence30
- Adoption
- Not scored
- Hype gap+32
- Incentives68
- Confidence58