Skip to content

Topic

AI Protein Design

Machine-learning and agent-driven generation of protein binder sequences and their experimental validation.

Current stories

buildOne report1 publisher

Ginkgo offers NSF's X-Labs teams remote time on its Boston robotic lab

Ginkgo Bioworks is offering remote time on its Boston robotic lab to teams in NSF's X-Labs, a decade-long program that could invest up to $1.5 billion. The offer tests whether federally funded teams will rent a robotic wet lab before building their own.

Publishers:runtimewire.com

Reality

Evidence55
Adoption10
Hype gap+20
Incentives70
Confidence45
scienceOne report1 publisher

Columbia-led team is engineering glowing yeast into a handheld PFAS test for water utilities

Virginia Cornish's Columbia team is building a yeast-and-chip sensor for PFAS, the chemicals found in nearly half of US municipal water supplies. Utilities would get a handheld, real-time reading, though the yeast meant to detect PFOA and PFOS are still being engineered.

Publishers:phys.org

Reality

Evidence30
Adoption
Not scored
Hype gap+55
Incentives65
Confidence35
leadershipConfirmed3 publishers

Anthropic cuts Fable 5.1 prices by 25% and launches two-tier safeguard system with Mythos 5.1

The saving comes off cache reads, so it lands unevenly across teams, and the model's most sensitive capability now reaches users through a credential issued by an access program, not a purchase order a budget holder can sign off alone. Both changes move the decision away from the budget holder.

Perspective Coverage

3 publishers
Builder
Builder 37%
Operator
Operator 25%
Investor
Investor 38%

Reality

Evidence55
Adoption30
Hype gap+35
Incentives65
Confidence60
scienceOne report1 publisher

ORNL wins two more years to make bacterial spores pull rare earths from acid mine drainage

Oak Ridge is engineering spore surfaces to bind neodymium and dysprosium in Appalachian mine water, where those metals are dilute. The pilot's main output was the assay needed to tell one engineered design from another.

Publishers:phys.org

Reality

Evidence28
Adoption10
Hype gap+20
Incentives72
Confidence46
productOne report1 publisher

Anthropic's protein binders got tested by outside labs. The benchmark is still Anthropic's.

Two contract labs made and tested Claude's designs, which is genuinely new. The field baseline those results are scored against comes from the company that ran the experiment.

Publishers:thenextweb.com

Reality

Evidence42
Adoption20
Hype gap+25
Incentives82
Confidence45
buildOne report1 publisher

That 34.3% TREM2 Hit Rate Belongs To Six Agents, Not To Claude

A one-day hackathon put agent-designed binders through Adaptyv Bio's wet-lab screen. The durable result is that the designs cleared a shared assay at all, not that any single model won.

Publishers:dev.to

Reality

Evidence38
Adoption14
Hype gap+12
Incentives66
Confidence40