NetGoodIndexSubmit a correction

Benefit Ledger · verified · Biology

AlphaProteo designs experimentally validated high-affinity protein binders

DeepMind’s AlphaProteo, released 5 September 2024, produced binders to seven targets with higher experimental success and affinities than prior computational methods; Crick Institute labs confirmed SARS-CoV-2 and VEGF-A functions.

5 Sep 2024Tier 3 MajorMethodology 0.1

Current score

+1.22

10 base · Major (tier 3 of 5, 10 pts)
× 0.8000 attribution · Primary causal contribution
× 0.5000 evidence · External expert evaluation
× 0.5500 realization · Experimentally validated
× 0.6500 durability
Event-level product before credit split: 1.43

Strong experimental binder campaign (tier 3). High attribution with human screening. Technical report plus independent collaborator assays (0.50). Realization is research binders. Durable sequences.

What happened

A technical report described generative design plus filtering. Success rates reached 88 percent on BHRF1 in DeepMind’s wet lab. TNFα failed. Some SC2RBD binders blocked viral infection in collaborator assays. No therapeutic development is claimed.

Model attribution

+1.22

AlphaProteo

Designed binder sequences later expressed and assayed.

Model generated candidates; wet lab filtered successes.

Attribution 0.8000 · Credit share 85% · Google DeepMind

Claims

  • AlphaProteo binders to seven targets were experimentally confirmed, with collaborator validation on SC2RBD and VEGF-A.

    outcome · supported

Sources

primary sources

Secondary domains: Medicine & Health

Revision history

  • 13 Sep 2026 · 0.00 → 1.22

    Initial adjudicated seed score under methodology 0.1.

AlphaProteo designs experimentally validated high-affinity protein binders · NetGoodIndex