ProteinMPNN likely memorized transmembrane folds; 0.3 noise breaks the recognition
sokrypton · x · 2026-11-05
Replying to a protein design discussion, sokrypton offers a hypothesis: ProteinMPNN needed retraining to exclude transmembrane proteins because it had memorized which protein folds are transmembrane. He guesses that at 0.3 noise the model no longer recognizes folds as transmembrane. A concrete, testable example of generative models memorizing their training distribution.
Related event: ProteinMPNN May Memorize Transmembrane Folds; Noise Disables Recognition(2 posts)→
More from Research
- RoboColosseum launches: 5,699 pairwise real-world robot evals across 124 sites — DJiafei · 2026-11-05
- New Book on Generative AI and Stochastic Thermodynamics by Welling Team Out This Month — mjdramstead · 2026-11-05
- New paper uses 288M job postings to measure where AI raises the value of work it can't do — robseamans · 2026-11-05
- Matthew Honnibal: LLMs can 'see' weight matrices — but only one layer at a time — honnibal · 2026-11-05
- RicursiveAI claims 16x compute efficiency gain on code pretraining vs Olmo 3 baseline — samiramanabi · 2026-11-05
- Claude drifts from 🌀 to 💖: refined AI symbols become less legible to humans (67%→44%) — mimi10v3 · 2026-11-05