License: FAMPNN is open source and free for academic and commercial use under an MIT license. Please refer to the license for full terms.
This generator is open source. Any third-party models, product names, or trademarks referenced are the property of their respective owners, and Proto is not affiliated with them.
evo-design/proto-language@inproceedingswidatalla2025fampnn
Generator contributors
brianhie
Protein sequence generator using FAMPNN.
brianhieAPI Reference
Configuration for FAMPNN inverse-folding generation.FAMPNN jointly designs amino-acid identities and sidechain conformations
conditioned on an input backbone. The generator writes the designed protein
sequence to the assigned segment and attaches FAMPNN’s full-atom output
structure to
proposal.structure.array
Structure(s) with optional chain, fixed-position, and fixed-sidechain selections.
string
When sampling a multi-chain structure, write only this chain’s sequence to the target segment.
string
default:"0.3"
FAMPNN checkpoint variant for sequence design.
number
default:"0.1"
Sampling temperature; lower is greedier and higher is more diverse.
integer
default:"1"
Number of sequences to process simultaneously on GPU.
integer
default:"100"
Number of iterative unmasking steps for sequence design.
boolean
default:"False"
If true, skip sidechain generation during sampling.
boolean
default:"True"
Repack sidechains after the final sequence is determined.
number
default:"0.3"
Only condition on sidechains below this predicted-error threshold during design.
integer
default:"50"
Number of sidechain diffusion denoising steps.
number
default:"1.5"
Step scale for sidechain diffusion.
string
default:"cuda"
Device for model inference.
boolean
default:"False"
Whether to print FAMPNN progress logs.
Usage
python