Protein Design · Nanjing University / ByteDance
Diffusion protein language model generating sequence and structure jointly.
No backend is configured for this model.
30s–5min
Not runnable yet
This model isn't available to run right now.Run this model
About this model
DPLM-2 unifies sequence and structure generation in a single diffusion process, so the two never disagree. A meaningful step past the generate-then-inverse-fold pipeline for cases where the backbone and sequence need to be co-designed.
Standardized I/O contract
Every model in the Hub speaks the same contract, which is what lets the Router and the agent call any of them without special-casing.
Inputs
Target length
Motif constraint
Outputs
All-atom coordinates in PDB format, viewable and downloadable.
Co-designed sequences.
