Research
Berkeley researchers repurpose protein folding models for generation via
PLAID, a new generative model from UC Berkeley, learns from protein folding model latent spaces to generate both protein sequences and 3D structures simultaneously, trained on sequence databases 100 to 10,000 times large
1 min read
SourceBerkeley AI Research
Researchers at UC Berkeley have developed PLAID, a generative model that learns to sample from the latent space of protein folding models to create new proteins with specified functions and organism origins. The work addresses a gap left open after AlphaFold2's 2024 Nobel Prize: if we can predict pr...
Sign in to read the full analysis
Free account. Full analysis on LLM unit economics, plus the weekly Cost-of-Inference column.
Method & sources
- Source type
- Primary publication (lab/vendor blog) — our analysis + implication
- Source link
- Berkeley AI Research
- Published
- UTC
- Byline
- By the gotcontext.ai team (editorial standards)
- Correction?
- corrections@gotcontext.ai