MuseDrift: Navigating Protein Evolutionary Manifolds with Conditional Discrete Diffusion (opens in new tab)

Protein engineering often requires generating variants of a wild-type (WT) sequence while controlling how far they drift in sequence space. Existing generative models support de novo design but offer limited control over WT similarity. We introduce MuseDrift, a conditional discrete diffusion model for WT-anchored, distance-controlled protein generation. Trained on a 38.2M-pair Seed-and-Stratify corpus, MuseDrift combines WT-prefix conditioning with random-order iterative unmasking to enable s...