AI model
Google DeepMind's AI model that predicts 3D structures of proteins and their interactions with DNA, RNA, ligands, and ions.
David Baker's University of Washington group tested 135 AI-designed zinc proteases, and 36% cut their target peptides. Cysteine designs fared worse, with 13 of 69 cutting theirs, and both rates come from a bacterial screen.
Reality
Google DeepMind and Google Cloud will give up to 200 European researchers access to frontier models and $3 million in compute credits. The pool is small, so any lock-in would come from the habits labs build around five Google models.
Perspective Coverage
5 publishersReality
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
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
A group at the Institute for Molecular Science added a bias energy that pushes each new AlphaFold3 prediction away from the last, and the sampled set reached open, closed and intermediate states of a subunit that AF3 alone gets wrong.
Reality
Computational biology proves a method by trying to break it on data it has not seen. Biomedical foundation models slip that test, and how the field responds decides what any benchmark number is worth.
Reality
The Constructor team reports two- to threefold better accuracy than AlphaFold 3 for ions such as calcium, potassium and magnesium, on the condition that you already hold a solved structure with its ordered waters intact.
Reality