Skip to content

Topic

Computational protein design

Designing novel proteins by specifying a target structure and generating amino acid sequences expected to adopt it.

Current stories

scienceOne report1 publisher

Designed from scratch, 13 of 69 cysteine proteases cut the peptide backbone

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.

Publishers:nature.com

Reality

Evidence78
Adoption
Not scored
Hype gap+15
Incentives
Not scored
Confidence70
scienceConfirmed3 publishers

DeepMind's SynthIDBio embeds a detectable watermark in AI-designed proteins without loss of function

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
securityOne report1 publisher

DeepMind's SynthID Bio watermark passes wet-lab tests without harming protein binders

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
productConfirmed4 publishers

Anthropic puts its biology claims on the bench in a new Bay Area wet lab

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
productOne report1 publisher

AI BioDesign promises a database of molecules evolution never made

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.

Publishers:wired.com

Reality

Evidence34
Adoption
Not scored
Hype gap+45
Incentives66
Confidence52
productOne report1 publisher

Apple's SimpleDesign drops the tokenizer stage from protein co-design

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.

Publishers:9to5mac.com

Reality

Evidence45
Adoption10
Hype gap+15
Incentives62
Confidence55
scienceOne report1 publisher

PottsMPNN scores the many sequences that fit a fold rather than the one evolution kept

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.

Publishers:news.mit.edu phys.org

Reality

Evidence30
Adoption
Not scored
Hype gap+32
Incentives68
Confidence58